[
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-30T20:45:40.415045Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "4725273",
  "id": "a727c80597b648dea3c499e1fa5c3051",
  "label": "Depend on released gradecore, not its default branch",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-30T15:42:10.467925Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "b5e1949e7ce249c68fb2edc8a25143ba",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-30T15:41:18.453958Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "0e2529cfa05f4bf18aa679bb8256ec53",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-30T15:37:44.261501Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "ecf0ba0c3bb84cb4885c1f6a396823f7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-30T14:11:01.982197Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "dbf4773861c347b39d3e71736778b484",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-30T14:10:00.338208Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "eca3fb905ba743618d62fc9a1324b396",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-30T14:07:47.445157Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "453abc6828f940babb271f4f0b5f8bef",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-30T14:05:56.133747Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "8f6965c7da6048aaace05c636736c891",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-30T14:00:11.843069Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "88fbdbaf4959417aa2530041f7cc2eaf",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-30T13:57:54.992533Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "1b3c4c779e6f4df7bed9271a91b2ab5a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-30T13:57:00.871023Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "e17828feccc542f4b28265bb8c312d4f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-30T13:53:23.230758Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "57c65ed0342345938f93269f6d09a2b7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-30T13:50:15.025816Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "ce4371004fa54c92b8d37a1e3ebf0110",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-29T15:43:39.519511Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "ad8f881d4559490c88a13ad5129d1cbc",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-29T15:42:45.189523Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "d5ed32648a3f417ea00aa35f313982c8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-29T15:39:04.558030Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "8b5d0c7244f7464ab79030cb68fbf158",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-29T14:13:08.961579Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "5867808621b44a1787220b9a77091e18",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-29T14:12:03.764331Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "3c54e117979f4929b528d9520f4849ab",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-29T14:09:53.265221Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "996d585b554e4f5bb97666240347a03a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-29T14:08:06.563304Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "ec4bb9c0a4ef4447a80dabe1ca3eb634",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-29T14:02:22.037872Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "53596e71f37b48e68881151f10987dac",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-29T13:59:53.150890Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "f1c0ce94a9714adbbbd24267aded109e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-29T13:59:04.529868Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "59030dc848754ce2af1f321b342c719c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-29T13:55:56.845293Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "c20daeff23314c53bbb3f6ad7a0aa13a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-29T13:51:52.862952Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "59d03012b07e4fc0af6488752ea54336",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-28T22:11:38.428386Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "fafc06ca297741fdb916a2a9078a46ba",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-28T22:09:42.448269Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "90aea5342a8341479ecf850cdb1fa190",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-28T22:05:43.653375Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "34527e3f9c2143b6a60be4ea4df43dc3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-28T20:38:01.815513Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "b255e0867a1b4b20965d8f55e9df65d5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-28T20:36:57.666319Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "8ef87391da094af5a926b39c138c487f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-28T20:33:08.332174Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "72835fe66b4a4d1ca3892b8325bdece6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-28T20:30:49.862397Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "8398e7260f1049fd8818fa8c6dd71a0b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-28T20:25:08.931951Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "06cb4082175e4ce3baef9e6b87dbb56c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-28T20:22:13.513273Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "bb0d851aff2745b5aac65059ba1e316d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-28T20:21:09.369514Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "455ef8898bd6455eaad0c9ce2c3afef9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-28T20:17:38.488428Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "9fd6f9607a5846b9975f6c4700cbdeff",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-28T20:13:56.950867Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "c7664f0d75ac4d3aabda9f69a3798299",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-27T21:05:06.167417Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "2ea09c140e094478ab5edc5d5ea3fbc9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-27T21:03:52.443204Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "1df641ec63a94d77b050e14d8327bfef",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-27T20:59:26.941463Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "7fb0b75016d94d21aca09d4080451b21",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0571,
  "created_at": "2026-08-27T20:54:38.790902Z",
  "faithfulness": 0.0571,
  "flagged_cases": 33,
  "git_sha": "e76f17b6c56e",
  "id": "27dae82824294a0faa13dd38ec3f0b56",
  "label": "suite 2026-07-v3 \u00b7 median of 1 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.0571,
  "recall_at_k": 0.0571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-27T19:31:47.419492Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "bb1170ce95a54e0a88f9f625b31e8984",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-27T19:30:41.666311Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "48de83bda4ae48c5a8884494de3222ef",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-27T19:27:24.167793Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "2439d8affb7449439a5bb3d97b45fd95",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-27T19:25:13.216285Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "074ad73f725949fbbc64992557b05d71",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-27T19:19:36.981857Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "118dc3e2b6d648f09c74c3db444a97d9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-27T19:15:14.482831Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "b95ac4eea6f147d481121641bce65667",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-27T19:14:05.345663Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "f2b006c09be447e0b5baa94db87fba0f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-27T19:10:39.468501Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "87faca3d41b54aff9531151a73a045c4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-27T19:06:09.748716Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "5267df34b878415cbaf3d18f6f4f51e1",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-26T11:00:11.959578Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "14aa6407bada4620968afcdb45234983",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-26T10:59:20.694337Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "8bd8d30a7acd4e609409b673d6ac11dc",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-26T10:55:36.426369Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "6c2d46eacbe54b32a786acdf1d560d89",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0286,
  "created_at": "2026-08-26T10:24:17.872167Z",
  "faithfulness": 0.0286,
  "flagged_cases": 34,
  "git_sha": "e76f17b6c56e",
  "id": "a4217bb697cc42bc81c5c44859783cc7",
  "label": "suite 2026-07-v3 \u00b7 median of 1 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.0286,
  "recall_at_k": 0.0286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-26T09:29:15.665072Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "b26ddae736d148d4b560d7cd8122db43",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-26T09:28:09.981209Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "30416377e0fb4a97aa14e398f393881f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-26T09:24:35.623071Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "64cc80c813af4a6bb83750b1f8291ec8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-26T09:22:31.182346Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "20de8fb6a9274810907d6819d449383c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-26T09:15:57.847595Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "a915a924a370436bab4761b71ca25c5a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-26T09:12:42.758491Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "64addc9e925b4f94a2358d0e5c461a59",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-26T09:11:41.267250Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "1651781e7d7946d2b99b9ac36f12c50a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-26T09:08:37.842983Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "43b1c313b6294dcd8f9d9a85eefd4735",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-26T09:04:14.155222Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "eae9f5c9da164cdeab34dd039b90790e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-25T10:58:05.609059Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "e7393843a8104867bf66271e404ccd24",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-25T10:57:10.446918Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "86a0434ed8534d4887740440cc7eb3e1",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-25T10:53:18.230146Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "1637d446d5d44a2c9842d234e018019e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0286,
  "created_at": "2026-08-25T10:22:00.019284Z",
  "faithfulness": 0.0286,
  "flagged_cases": 34,
  "git_sha": "e76f17b6c56e",
  "id": "9c9325ad1a47484ba90f7cb1ed537d0d",
  "label": "suite 2026-07-v3 \u00b7 median of 1 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.0286,
  "recall_at_k": 0.0286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-25T09:27:21.885422Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "1c3d41018bee45598030f9a8de5c2318",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-25T09:26:12.493521Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "69bfdd7f80b449fca61cd3555d23beac",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-25T09:23:51.295590Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "840c432cb31743fa9d495d4e53eaddd5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-25T09:21:55.189582Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "f3997c0b92ff488883ced998ca40b40a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-25T09:12:36.567839Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "a3cf26b779d64f86a171faa42a006243",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-25T09:08:38.663414Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "b8c765be46c14f53a1684d27756882f3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-25T09:07:44.504000Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "1642b83aa4d945f481477b0955cc99df",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-25T09:04:54.746416Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "ff9bb8432f554a92b7e012c33d123b55",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-25T09:01:59.283584Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "2aff41ff2af74c96b50520c83bf9627f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-24T11:00:46.356849Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "fefe3c4d7356452e933aa171215b57f5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-24T10:59:43.081412Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "46222218c8a64e119c57321c5c481c8c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-24T10:55:58.687286Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "f533d9a449fb48a1b7af16739e972636",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0286,
  "created_at": "2026-08-24T10:52:37.137967Z",
  "faithfulness": 0.0286,
  "flagged_cases": 34,
  "git_sha": "e76f17b6c56e",
  "id": "e2cb2ce34b804c3582f7e85384f601c7",
  "label": "suite 2026-07-v3 \u00b7 median of 1 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.0286,
  "recall_at_k": 0.0286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-24T09:30:40.321997Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "d86ff6d1130f49e6b92a6031e97c52f6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-24T09:29:13.689794Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "1f029ad5ce9747369e6a9375bca02cbf",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-24T09:26:53.767752Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "efa5baaea65748819b103c71d8cc5161",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-24T09:24:52.483838Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "4ac0cabe6c3244e294780b187e0d9da7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-24T09:16:26.117494Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "90af04127cb54a8595052ed2c863a0de",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-24T09:13:35.188840Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "44d1ffa374424360a399b4e258f37d51",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-24T09:12:36.890444Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "d6e5c788961149fa978894fada6d5eac",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-24T09:10:09.690002Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "f3b1e820b64b4445abc2f22d184ae20d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-24T09:06:25.515612Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "d3654d7759a94d30a0c3c2bcf447aa60",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-23T10:42:20.093850Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "eef779aa100b4a50b2cfa26a079feda2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-23T10:41:24.408147Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "e1a06a63add24a83ab8c288fb679867d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-23T10:37:22.982861Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "07cb4ddfd8714213a9e902d35ad95531",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-23T09:12:31.280856Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "b6837d864eb54a40874a2492dd1d32ef",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-23T09:11:03.049215Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "99f7f86c4d0547d3be4fb9496c29ed80",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-23T09:08:43.258837Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "d3314192f8974542b0769386dca37c73",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-23T09:06:30.017368Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "e05406c9cfb3481e8c7f4101217d25f2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-23T08:59:55.125852Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "d43e7b7124044bbc8489ef0a0cc5cdb1",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-23T08:57:11.360824Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "affacc159b894fc1a0c5e34fd19ce09a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-23T08:56:04.128668Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "48cabc3a404f4db9ac60e4c8a8bfb50e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-23T08:53:51.346002Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "b03adc8db6134c6b8dce29e40654aa6f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-23T08:50:36.047275Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "d91ae69fc7164a52aa714211bcf0ceeb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-22T10:44:02.950868Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "aa085e486cce400785f240b18fea7dac",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-22T10:43:04.429118Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "85b87eb6dc494458bdb6d3a70a45c6b4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-22T10:39:00.834079Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "5ef026c5134449ec9cb8a95c65fc8503",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-22T09:12:56.204577Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "9d1a9615641a4f2690da26b6b68119f8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-22T09:11:39.809287Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "e7b3847329904de7893899c2622042a8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-22T09:08:49.141684Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "a2f538cb292b4e48969a3bc3211fa08f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-22T09:06:41.047887Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "9325130b67f241f982d6fadee929ab59",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-22T08:59:27.757793Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "7bb4a4e6c4184b669564dfde9ea50965",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-22T08:56:46.436111Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "b0be22663bc6446aa95255aa365066eb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-22T08:55:52.634032Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "1ea2a7ba204e4016a8863e8e67f7bffe",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-22T08:52:41.630625Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "fe6143b095e84bc39a84310f8518bc80",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-22T08:49:23.454225Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "3a918e2c1fd74b17be243ad9c1e0f915",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8857,
  "created_at": "2026-08-21T10:58:26.322320Z",
  "faithfulness": 0.8857,
  "flagged_cases": 4,
  "git_sha": "e76f17b6c56e",
  "id": "ccbc93428be5465f973305b8b23a83d1",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.8857,
  "recall_at_k": 0.8857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-21T10:56:29.599232Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "146328f83ac54c39a0d740adba283c8b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-21T10:52:30.869513Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "16889558419a4300abf8f658476f24e8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0286,
  "created_at": "2026-08-21T09:54:54.070959Z",
  "faithfulness": 0.0286,
  "flagged_cases": 34,
  "git_sha": "e76f17b6c56e",
  "id": "fe842ba85a2645a98faa0fe87e480d00",
  "label": "suite 2026-07-v3 \u00b7 median of 1 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.0286,
  "recall_at_k": 0.0286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-21T09:27:01.694788Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "51be14c3d0484216ad06d15b1eb53814",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-21T09:25:48.049228Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "d271dc57ed0c4f838c9018b10f2ba7b4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-21T09:23:20.013186Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "94579904dc364470ba6ff57ea4100363",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-21T09:21:20.181855Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "16af18f1a3024863ad462a8dc440b9c2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-21T09:13:57.261461Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "9265034f13284ae99f2d56ff37247c54",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-21T09:10:14.111089Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "b30827e8fbc9412d9c4113fab12b1b69",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-21T09:09:18.143029Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "3d879c22b3f24cf6a25c64b161ee8c11",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-21T09:05:41.981767Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "2b32bfc21d124a659094902d94b42c50",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-21T09:00:54.547151Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "a896ab0fbbbd4bd8953882d156e6dcb7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-20T10:56:47.337761Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "44564715d9114b3c9c2c6a0ab4e83849",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-20T10:55:49.381754Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "a831f9fe641641f4b5bf4b0e7a05f1a5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-20T10:51:28.799390Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "1d41bfe1cc7f4d4895f24ef1561dbfc6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0286,
  "created_at": "2026-08-20T10:20:38.675523Z",
  "faithfulness": 0.0286,
  "flagged_cases": 34,
  "git_sha": "e76f17b6c56e",
  "id": "805b96ed7f67439d84887b93be0c3c6d",
  "label": "suite 2026-07-v3 \u00b7 median of 1 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.0286,
  "recall_at_k": 0.0286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-20T09:25:49.022523Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "a5f316d5a298413c9e118627f2ab8e89",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-20T09:24:35.289606Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "70162c2dd4064f4fba5abbf5f310fe81",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-20T09:20:36.900894Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "9f0ce27d0ebf45ec9e4186668a93a96d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-20T09:18:10.390721Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "161f30cff7c04ad38dfd6d9153679f85",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-20T09:10:40.901267Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "baeb9d1e181546c4908ca08ee1a9204f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-20T09:07:22.094535Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "0029f6102c0445328a84453b16dc3f1b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-20T09:06:21.013823Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "f050361161fb4b428f18ac6aeca61c0d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-20T09:02:53.543621Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "e4263728088b407595300e6fa70550fc",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-20T08:58:34.482050Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "68602409c736442e811352df856abe35",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-19T10:56:38.425906Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "87581c6d77f74588bed9a06bbc8821cc",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8857,
  "created_at": "2026-08-19T10:55:45.306577Z",
  "faithfulness": 0.8857,
  "flagged_cases": 4,
  "git_sha": "e76f17b6c56e",
  "id": "ca836d2a489a408d987524dbd5e7f1d2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.8857,
  "recall_at_k": 0.8857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-19T10:52:09.398630Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "be41e1cc05ad435f8c42a6eb840bef4b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-19T09:26:34.163922Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "97001da2ac284f2280bf6b94e390d741",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-19T09:25:26.983962Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "7361277cb72040ff992e4939a589cb86",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-19T09:21:38.237119Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "9ac67ac00e814108aa254a0315c601de",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-19T09:18:55.616960Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "bb2e943439934aa7abf0afc6fd7eec33",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-19T09:10:34.036001Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "ca242adbc84c494c81494913dcdc91d7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-19T09:07:14.197678Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "10b8550c7a4b43028734e99a78efaf78",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-19T09:06:12.638464Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "334376b46e6941559f76331c0179c30e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-19T09:02:22.181682Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "c86433d56c564a84882516f2cd1ef710",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-19T08:56:28.077674Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "7c1c727ea67548e8af4cdf2128e44500",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-18T19:26:07.341631Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "298f60a",
  "id": "65d5c56e7558413da0fa639de2e2c42c",
  "label": "feat(api): redirect the root at the interactive docs",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-18T10:54:43.531957Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "9dbc286e753c47298d3b686eb11ec67b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-18T10:53:41.179491Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "b6d99e8931734e4882e61e8e150766a8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-18T10:49:18.715244Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "80a42f3602f84c41b1bc61b8f2d7c9e3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-18T09:22:56.122941Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "ddc77fdb209241b8bb45523dcacb8751",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-18T09:21:29.736146Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "481cb29f0602442f97a470dac388b604",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-18T09:17:44.765193Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "9f3b5afebb39412b8cc3a9d6465014c9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-18T09:15:38.596412Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "b03fb70a291140709d54da101d3068bc",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-18T09:07:50.600967Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "5b875e72c4f349e78f128576b211ee15",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-18T09:04:57.118510Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "7a8695c1dd80414988314fe081b429c2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-18T09:04:04.156045Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "fc60209ddd7343df8a5dd167d5d75610",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-18T09:01:02.086942Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "6ddefc66a4e341f2aa5031a1baea2d35",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-18T08:55:38.004615Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "a5e69ed5178c4781ba6dabf982cde0e1",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-17T10:59:51.105767Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "3898f4619cc544d58597ba2424432e9d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-17T10:58:46.652341Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "5c9d110f116e4706b2df3a4f74832f7e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-17T10:54:27.776842Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "34ba51b140324c209fa4cd4df19a06af",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-17T09:35:07.861147Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "daacbc5",
  "id": "52c73e0083b540cab7af30d1d9181953",
  "label": "Guard the SciFact BM25 claim: benchmark runs in CI, not just in the README",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-17T09:29:27.942389Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "7d7e88ed62ca4bd7ae5f529bf0c50dac",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-17T09:27:56.700424Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "a70e3b4a65734103a0d0a4712fc04379",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-17T09:24:08.838221Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "f9d0a988188040e2971b39f673dec09a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-17T09:22:02.694667Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "70d5df007c234863a698f0884cc8f7a9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-17T09:14:28.317486Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "a7c43ae10c7c4c3c8174cf0c3b00b03b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-17T09:11:21.689004Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "75a19b1211234ac3a73511095b7f3af3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-17T09:10:25.502332Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "6b63abb1ee3b4be491e7435544bd6e24",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-17T09:07:48.025166Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "1bbc19ba017447de8bc865a4fedefef5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-17T09:02:25.330317Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "7a78ff62a3a24624a46fabe99e82f0e9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-16T10:51:11.167076Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "d02d91c0db9848c6b8f06241c82e9ac3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-08-16T10:47:11.398663Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "4c4e2aff5916481ab4a21e46890c2fb1",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-16T10:43:14.357480Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "70b1b4a6e8694d99882bdf9399142963",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-16T10:42:11.431036Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "eecedf128f934c269defe90aaa97bd03",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-16T10:38:05.272151Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "1254055edba64147a95c4cb8d96658da",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0286,
  "created_at": "2026-08-16T10:34:24.619929Z",
  "faithfulness": 0.0286,
  "flagged_cases": 34,
  "git_sha": "e76f17b6c56e",
  "id": "2ce9bdc38e354b6bbec31d2d8a67a064",
  "label": "suite 2026-07-v3 \u00b7 median of 1 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.0286,
  "recall_at_k": 0.0286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-16T09:11:17.599853Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "5875ed20a94943f78304a155fdceb4c2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8235,
  "created_at": "2026-08-16T09:10:03.844333Z",
  "faithfulness": 0.8235,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "ac4d19dbc88142ef9b465ccda0790e5e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8235,
  "recall_at_k": 0.8235,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-16T09:07:36.396471Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "526e0820794b44d2b29c5410d88c7732",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-16T09:05:39.032495Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "7cca2ccf7f7e4d96b54738e657086b94",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-16T08:59:30.626522Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "666dee051c4643bdb38a8223e29f2a9c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-16T08:56:43.783765Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "f981be9defb240f4b5227e1019aa4f8c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-16T08:55:50.025909Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "300071df9cf04b359f433a1cdefc9030",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-16T08:53:16.130860Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "623828427a9c48c0844c47da8b4318c7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-16T08:48:54.731417Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "8ebd65b861074f2a91c9bb7ca721686a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-15T10:46:46.941577Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "b78260733cfb4c21888d4e9e7f60cb6f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-15T10:42:49.927756Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "c82af458add34daf851f893dbaa1a9b6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-15T10:38:39.891406Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "0ff43b7a029f429985933ce71a600819",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-15T10:37:40.943643Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "dcfd1fd8ce504ded8b9225da9e264f29",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-15T10:33:26.344833Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "cf0774fac1a440cabf95a7b03af4b655",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-15T09:07:37.836140Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "b84a2666725b4d97b8bc7a4f4c79f5aa",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-15T09:06:33.218959Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "cd1598f4f0204e81b7f5b15bf3a57137",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-15T09:04:14.673243Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "c0f9efd708fd4e39a9057062b2bc23e5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-15T09:02:31.267543Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "11d2e51425a24f5296c5e30171e0672a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-15T08:56:58.647212Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "05107303ad0645258419e5bd87b92672",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-15T08:54:20.825380Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "3bfca58116ba439d9d91dcaf7f542f19",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-15T08:53:29.406702Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "e99fb2aebcea4405a98f52343c780ed2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-15T08:50:52.760653Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "94e7e51e63a24d93a19053365b2c1cb3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-15T08:47:23.179781Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "eb38b0729a35485e9ff0130c60bfb3fe",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-14T11:28:46.299413Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "d0472b158d564ee29e5c50715ec1f65e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-08-14T11:24:49.844815Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "9d8e8fa0698a46e48c94115d3914e3c4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-14T11:20:57.752594Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "f15aced2002b4c8c9045006056a33b76",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8857,
  "created_at": "2026-08-14T11:19:47.591206Z",
  "faithfulness": 0.8857,
  "flagged_cases": 4,
  "git_sha": "e76f17b6c56e",
  "id": "43842eeb086c42daaf1c9619a29b3751",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.8857,
  "recall_at_k": 0.8857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-14T11:15:26.203762Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "cf0ddec812e74be386ba3df2d1feef30",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0286,
  "created_at": "2026-08-14T11:12:13.558408Z",
  "faithfulness": 0.0286,
  "flagged_cases": 34,
  "git_sha": "e76f17b6c56e",
  "id": "43ef6ddf99af479f94d194f820747bbd",
  "label": "suite 2026-07-v3 \u00b7 median of 1 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.0286,
  "recall_at_k": 0.0286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0286,
  "created_at": "2026-08-14T10:44:18.080925Z",
  "faithfulness": 0.0286,
  "flagged_cases": 34,
  "git_sha": "e76f17b6c56e",
  "id": "13ab0a3ebae9495ca1154b0132c6f02b",
  "label": "suite 2026-07-v3 \u00b7 median of 1 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.0286,
  "recall_at_k": 0.0286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-14T09:48:54.590499Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "088e2aed4a1442aea68d788aa6310b6d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-14T09:47:35.292645Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "fecf7c224a484a628cb404e1eeaf65c2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-14T09:43:53.283974Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "66b0e749d1c241098fc120e4ff5804bd",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-14T09:41:48.583915Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "29bb09a52e314084bd6856e5806eeee2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-14T09:35:42.202272Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "3b91236c45c94a8bbda5baa75ac75b0f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-14T09:32:05.150825Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "e5f2a3101c64485f8c4b9e73836a64e4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-14T09:31:18.363096Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "256e6d6610b94535a7f874f6124bf71b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-14T09:28:04.990032Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "d0f84b0908f545f2be1634dbde867f3b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-14T09:22:52.406002Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "6aca8d2155364f22acbc89c50684f224",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-13T11:40:40.043677Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "039a18c00c9542cebb7c2c118a404dfb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-08-13T11:36:45.057941Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "5bb4e165c9784cc6958ee79c53710732",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-13T11:32:55.727544Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "20b23f190cbf40bda1286f09fafbc6e8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-13T11:31:48.045391Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "c29d54802cdf452d87b486e816a3c997",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-13T11:27:50.511942Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "e7054195751e49b39f6dd4c938cf2bd5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-13T10:01:03.516051Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "02fb5cc6f2064f33a64c6282df6c52a4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-13T09:59:52.594550Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "c01e7aea56784ca8817f6708abf17eae",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-13T09:55:30.336234Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "6c3a12615b3c40b4a02fc88204b4afb9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-13T09:53:30.685041Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "e49faed931b84c3dbe3eba97c00f5636",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-13T09:46:18.935673Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "7e2bde9495364fb5acf656ff82f84bbb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-13T09:43:02.098910Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "45b09cf61b1c4c41b2b1dcf23c565189",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-13T09:42:08.544616Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "5daf6fb57f4a4ca187eb9ad2172de9d6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-13T09:38:41.244436Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "1da2d4105cfd4733b7c9ebe79a89298f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-13T09:35:26.006541Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "10b67a1c2cd047a79542f79ae1f1e80c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-12T11:40:54.680883Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "32c54d84e4fd469e83814e0c3da7d72b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-08-12T11:36:54.710745Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "3cab3eda9e654d33863fd42f3dd1e50d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-12T11:32:56.207168Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "765be81107484a3d9d68475779f76db0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-12T11:31:55.242672Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "fe0d3f9c1aaa463d94843b8667ffb011",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-12T11:27:30.403673Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "944ebb1165c14a96ad10af86e615ffe7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-12T10:01:21.089895Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "718502dfe97e433c8064eb4de2946620",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-12T10:00:01.123704Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "9110ccb83199421d808880935c21eeef",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-12T09:55:54.464196Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "91e8ca712da1447ca17c1e2cbd92de33",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-12T09:53:35.328697Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "8611d046c9b54acca4f65544dc8d0261",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-12T09:45:15.298513Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "91a314fb2b794fcdb8e658512586fa23",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-12T09:42:19.836734Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "44a0e18585444e588d6c456b3b083d2c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-12T09:41:21.180136Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "549a55e9f7f94d298d97bdaac08c8990",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-12T09:37:23.918064Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "de079460afeb4dc2ad5c6ee7545b4b48",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-12T09:33:50.050503Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "5b1be80b395946128cbef8d7ea39bc14",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-11T11:32:42.395255Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "28612f9d1eba47f888ec323718633554",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-08-11T11:28:39.039862Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "74396303d40c449f83049ae7eca4bdcb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-11T11:24:36.310558Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "b707a2fa0c144c9d874cec9c553b0215",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-11T11:22:30.238677Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "6d83a33412e446649938e42c932203b9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-11T11:17:49.293816Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "b68d4cae2e5c4b55879bfd739a18e646",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-11T09:51:02.537355Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "4215da6d346c42138a1649be98ee145c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-11T09:49:21.162971Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "d576dcb3d8684b82b4495130e8fd31f2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-11T09:44:52.042277Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "78c80bc20f7c4f2d948969849263c7d5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-11T09:42:30.443005Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "ed2d6fc773d14a41a7ce516d6486a72c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-11T09:35:22.246133Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "9a985a8d2f7344fc98875e4d1534799e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-11T09:31:54.367760Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "0ff20385184b4b97a700defcf39a1713",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-11T09:30:43.583613Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "953f83ea0996471b8265695a4a6b477d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-11T09:26:23.110997Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "6ae7dd19cf934a0bb647d2cf35b4f308",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-11T09:16:22.886156Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "99ee117c0ad941edb7f5c4ebeacbb6be",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-10T11:57:16.986536Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "591adf0f0abd4e3e9581b8614a738971",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-10T11:53:21.606355Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "7fe9d8eb1e8841708418227da44a0975",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-10T11:49:23.614424Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "b91cf193e6be4da8b7af1fcf40accd5f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-10T11:48:25.305443Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "0750ac48804f4e72904fb58c2f3da329",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-10T11:44:21.757185Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "0ed399f9d3854b0d8dec0821a0e04601",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-10T10:18:28.372719Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "6dfd943fff3148d9885bab7057ccfe2f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-10T10:16:58.141002Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "1e4a0387e14e4c248017effeffee5bc6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-10T10:12:22.638398Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "0e053236454344d3833b051707b272a9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-10T10:09:45.901421Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "92e06cc32fa64f09abf0364ec0449224",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-10T10:03:09.286949Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "61247c660d4b496b8820b6a3e1e0ba5a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-10T09:59:27.394953Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "89e3d25408dc441eaa37ee48e3ef80b4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-10T09:58:13.219456Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "44c0cd2895e043d08822863c31485a98",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-10T09:54:49.937272Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "f9976a514afb46e99127521560c98594",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-10T09:49:58.944565Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "e48ab774b354455bbef89c7818572d9b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-09T11:43:59.853017Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "044d1a479bec4b8ba6e10d2abd1f544d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-08-09T11:40:01.544642Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "45289df1bc9c43dba0b07db277ac8588",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-09T11:36:03.523529Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "10f82a2a14524203a0fbaf7eb3a5417e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-09T11:34:33.813094Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "ced380d6b1a84a7a9f05e6cce3b4f1be",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-09T11:30:13.159262Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "7e6b2c67d82b417e9a1085dcd1368375",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-09T11:26:56.551696Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "c78c8be5204a408a98a0b2454b81b593",
  "label": "suite 2026-07-v3 \u00b7 median of 1 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-09T11:06:58.277909Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "ab38a9598bbf480eb78bf6f754b4953c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.4,
  "created_at": "2026-08-09T10:49:14.586420Z",
  "faithfulness": 0.4,
  "flagged_cases": 21,
  "git_sha": "e76f17b6c56e",
  "id": "6e1fc7d69a4847e7892a46628d387b2f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.4,
  "recall_at_k": 0.4,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-09T09:30:23.276740Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "e69370d20fdc4e358cf42344e8d3117b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-09T09:28:59.438123Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "79dedd9cbd0c49e49bf681c479921f9c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-09T09:25:02.620582Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "4a661fb8bde04f1abd5789399837ea62",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-09T09:22:28.470495Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "704050769a394ffbbc44df14eb851bf6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-09T09:16:38.954251Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "14519e82122845e88605fb8f6552c63a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-09T09:13:36.648020Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "4446e20c81cd4236aa7adb209dc8195d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-09T09:12:36.914525Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "b3eea6ed63bb4323a7161d95f2e178c9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-09T09:09:21.995132Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "a17dee22f2704d28a91dbaf5b061bdc6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-09T09:04:52.478062Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "6c4b3099a2c84fe6b1a1341e54d0ba8e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-08T10:40:17.238914Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "7a379d3f49804ccf9cf1d5021c9e63ca",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-08-08T10:36:24.511083Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "bb015b33f7a44b389d0987117d56624f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-08T10:32:31.114821Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "9804d23513bd43249df721baa8bae257",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-08T10:31:35.918462Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "754295cf6ff4451f87f41623b3fa2e2d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-08T10:27:24.410431Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "77aa16a82891490a94efc7390bef2ee4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-08T10:24:13.439209Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "1309237fc5d14aadad7f93cbac2f11c4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-08T10:23:22.957679Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "8ce426df56904765b5a73d08a99a4194",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-08-08T10:21:09.844882Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "7e10fda59a1744efa6b4d94e9bbb238e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-08T09:26:38.655318Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "d4cb941829394d47883c61997b141b02",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-08T09:25:16.055092Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "03fa393300b54f6e9f6be5611dcb6490",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-08T09:21:34.616182Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "b33dbb0d7783446b8b4e787dcb1e3f40",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-08T09:19:05.573725Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "ebd8ee05235c44dca883a927ddf3be28",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-08T09:13:34.840771Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "d18d3565a8a5490183425c9e91852b93",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-08T09:10:27.686476Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "a2d39921e9f8487c87631f822fc7bae3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-08T09:09:32.845062Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "fff5d669a4d14f8e9cdb7c82ea5849ab",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-08T09:06:50.784274Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "1264bc5f83eb4df695b8ac5145139975",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-08T09:02:05.328586Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "32761b1b573049d6a0771b599c289815",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-07T10:51:17.329217Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "7fa50a3a41424b949c4a490f81aa4416",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-07T10:47:16.911632Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "ab407c298610463789e30312bcd27f7d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-07T10:43:14.926142Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "77a566447da843119ac97d33ca3b0874",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8857,
  "created_at": "2026-08-07T10:42:08.946319Z",
  "faithfulness": 0.8857,
  "flagged_cases": 4,
  "git_sha": "e76f17b6c56e",
  "id": "4f7dd379d3ce4ea2b511ec597d74db90",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.8857,
  "recall_at_k": 0.8857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-07T10:37:36.518750Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "cfe2244f021f417d9080ca8bfc4f274a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-07T10:34:18.054505Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "d958095654ac47ea96ebbc45b67055ca",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-07T10:33:25.317330Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "4301f84d44e04df8955fd469e8ca3a35",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-07T10:29:30.283095Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "528c7343eb354477b647a50c56b6357e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-07T09:46:48.927688Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "f5e33e9acc044972bfa682c7d55a3a61",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-07T09:45:04.234994Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "14feee5239484172a8350b1966b42109",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-07T09:40:41.700791Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "0da45d5707544d26a29f4a0ed7e4c735",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-07T09:37:25.853935Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "0644b75f6c9c44a3a9a3c57b3e495c92",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-07T09:30:24.896382Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "75429947dbda43bf92895a9844cdc4bb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-07T09:26:16.341660Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "a92fa0c0bc86447b8169860b8dff45e6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-07T09:25:07.847760Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "54d321a91888487a96bf98e5abe111b6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-07T09:22:07.444604Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "ae34febb033d4124bccd2268233434e0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-07T09:17:12.365974Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "a9814ca730eb401a979f389b9f6b55df",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-06T12:56:45.063616Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "c00d142d911d40bab1790f6433620e59",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-06T12:52:50.407041Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "1f5024a63d9249f295348f76b490c665",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-06T12:48:58.938795Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "d6a9afc90d7a4bd589d3ccb620e1d8b3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-06T12:47:54.115769Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "4f1d22760e7e490498b5861d7ee0e7e4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-06T12:43:33.638647Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "db34ed3b7f3840f59a7d465bb60e31be",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-06T12:40:21.785799Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "83e2759a038f4aff88d30b4549d12f0f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-06T12:38:44.539907Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "301981dc961d4717bc6413286dd32549",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-08-06T12:20:17.803412Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "825042f9aa7b455081c2a5d47e39ac38",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-06T11:19:59.784030Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "9a8b04108a03401fac5ace64175cdcb4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-06T11:18:13.144249Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "7b84f68c46f94f3eae3399c804e11ca5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-06T11:13:24.622236Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "c241ad17129341ceb76ee088dd6d88ab",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-06T11:10:38.703121Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "fbd8cc82a654443a879b887911c51407",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-06T11:03:57.942939Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "fbe6c5fe42a04cd182b7afd71541dc88",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-06T10:59:58.354737Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "4089291cfdb74cb8907eb72904d72afd",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-06T10:58:50.904484Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "cb468f8259724b8a9ae43e0c9c399886",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-06T10:54:45.793784Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "85b4eae5ade64dd0a74ed112510b381a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-06T10:50:19.758431Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "db38f056385343c59f410f70b15ccb29",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-05T12:12:43.068675Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "c0179c50f7bd49daad4f286d6bb1e7c0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-08-05T12:08:45.864832Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "5758391e1e024ef29572d091f8ffb1ee",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-05T12:04:44.696423Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "104caef052a84d95b5c3ff6d1ab3a6a2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-05T12:03:43.149664Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "8af34b75ff20439bb81c5be456f31727",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-05T11:59:09.730402Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "fc6c45caaf4e4657bf4f51e4aa3cf578",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-05T11:55:54.541571Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "77c1e5e6757c48f4aa10af33a4cf300a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-05T11:54:47.529359Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "15a85d07be824e1f88cdcff103163625",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-05T11:42:56.055091Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "f5265523331a41cbb3c153a735170a60",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-05T11:20:30.870858Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "835a129878ba44c3b80d733b90eefed9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-05T11:18:49.576095Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "459a34e9596f4b5c8cd4113fcce7093d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-05T11:15:19.842875Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "c79584cac12940d1bcd6c913287ff6ff",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7429,
  "created_at": "2026-08-05T11:12:24.633915Z",
  "faithfulness": 0.7429,
  "flagged_cases": 9,
  "git_sha": "e76f17b6c56e",
  "id": "a2a8fe1d33644249a22e2757002c2557",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.7429,
  "recall_at_k": 0.7429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-05T11:03:19.114030Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "51de6096e2b94a8fa8964298383d35f5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-05T10:59:39.178600Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "73ae4ec895b349a89b486c6ca59de175",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-05T10:58:36.971701Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "b17d91d4926a46fe890b671fb76fce03",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-05T10:55:01.870366Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "ba9c80b3c2fc49018f96cee87e7a61eb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-05T10:48:17.356134Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "aa343f6b83ef40129d104b0ba1567fd3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-04T12:11:30.480043Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "f6493466d53041c989fcc3ccddce3fbb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-08-04T12:07:31.462173Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "741734e9f6614fe9ad1730699c5c86ed",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-04T12:03:40.160254Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "4d42f48474db4db9a0f29d8372006189",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-04T12:02:46.066976Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "55f599881c1147619db02b8cc33ca083",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-04T11:58:39.884250Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "7d28f2ec455c4e54b28fdb0480d3887c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-04T11:55:34.648118Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "e4dfbff6626a48eba7d3c88752672c53",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-04T11:53:48.080633Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "8fab6f85616a4ef4a85153b7e59e8ddf",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-04T11:43:39.175919Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "28aa4a34a10f44549318d7af3a91a242",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-04T11:19:31.858687Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "bd6199be8b9e4361b134e7b544d1391b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-04T11:18:02.837880Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "c871f08b97744899ae686f0e0a242be5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-04T11:14:27.381912Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "61014fac945e4f26ae7a3cf1fc1b0aeb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-04T11:11:59.221160Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "e44ad134c8ba48de873d2857b78844d8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-04T11:04:53.640979Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "7b6182afa2dd4327ac431075d6967a14",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-04T11:00:32.760796Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "cc712cb467734ece8bea1d6a3542282d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-04T10:59:30.992857Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "06f601b845ff43ca934c3f2c48a91c99",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-04T10:56:08.344686Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "817d32781e7447588d2482661677b515",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-04T10:51:01.263022Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "584da78e841046a89b9e10362913383d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-03T13:05:44.283862Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "e29ff912f26e42b68ae064d4bfb106ef",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-03T13:01:41.114210Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "a71a464c264a4b15882ed2385e849882",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8857,
  "created_at": "2026-08-03T12:57:43.334375Z",
  "faithfulness": 0.8857,
  "flagged_cases": 4,
  "git_sha": "e76f17b6c56e",
  "id": "234eaacf6b0641a7b4e2a3df8af46f8a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.8857,
  "recall_at_k": 0.8857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-03T12:56:43.998956Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "981cbbe31e6347b4bce348c6790d5dbe",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-03T12:53:17.178498Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "cba2630a443a4c2d8fc7ecb0a76e95df",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-03T12:49:33.815695Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "09caa716c49e40cb810c44c535f76f32",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-03T12:48:42.490172Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "80576777697947b09083248684e34dee",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-03T12:42:59.720668Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "715d9fa6fd364ba9a10ece9aae3bb965",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-03T12:13:23.661236Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "da2bb75f3baa42edb142d478332ceed2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-03T12:11:47.564795Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "e247aa75b3a848a59193effa238f33ff",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-03T12:08:02.664482Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "9b5b43aaf1db4e1d83f41c0f96556a57",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-03T12:05:21.343758Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "dc3a234de27b4fbf9a0c95a727e219b5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-03T11:58:28.112674Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "9429f8201b2c42fb8ac9f739635c48c7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-03T11:54:43.192657Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "f013a31720214ce78c2ca7393c7c8278",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-03T11:53:39.239123Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "40b6a43b3c644786a55a0566272f7154",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-03T11:50:04.568887Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "4f0fd6bf19f441699cbee038dccac695",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-03T11:45:50.678264Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "b298587753ab4873a991128a4f66f92b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-02T10:58:12.656647Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "2934628aba2d4a678bfc483184f0af19",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-08-02T10:54:22.719270Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "3a9fe55e729a43d78ee723ac66c209cd",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-02T10:50:14.817808Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "dac9d809fb5740a2a5a620f6a101f5e7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-02T10:49:22.322309Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "85a6fd04cc004dd4ad30a1e6a27e11d3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-02T10:46:26.787799Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "4b2d5b978c2644959155f975b576bf27",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-02T10:43:28.939277Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "30572fa6a21e4b87abb8f721ae8cc405",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-02T10:42:48.121312Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "f0550271236242f1a78d71f1aad0d2d0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-02T10:40:47.548921Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "65dee7ba0fdf4bf0bb87d25de48de21f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-02T10:31:32.796277Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "ab2f73d92d1644eba11081ff15faad18",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-08-02T10:30:03.102697Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "51f0a6da9894494ba05aa2a9a95cc7d8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-02T10:27:15.833113Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "4f5cfdca37a64898b46b1a3bff01b071",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-02T10:25:08.089206Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "c76fbb2b5e794e098edfd7e3f1b1e1f8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-02T10:19:36.257507Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "9fe8346cb4254dfb97fdef7ef213e569",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-02T10:16:34.507836Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "eb5c7ee927ad4428bf68f209873c5dd8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-02T10:15:38.585096Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "33b22f00f24e47629e4837907b5ad4a3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-02T10:12:32.746219Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "91d5def55437446692c175e8bd926fd7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-02T10:09:03.740970Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "2be61c33ad854b98ae62af96aa92563c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-08-01T10:58:46.899673Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "7e86691f5ef14bf2a431edfb063c2ec9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-08-01T10:54:58.350887Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "32241187d8ff4b8caae0bc2ad54f2e05",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-01T10:51:04.829512Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "46c0ed5944cd41faaa7ec7eb7673b658",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-01T10:50:15.672164Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "015776fe4a5746e897b55b72f9749c93",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-01T10:47:20.768619Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "a7f7e6657b0e4058a1d43602a70a2ba1",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-08-01T10:44:39.605153Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "056aebd577e94788965495a2b57178cd",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-01T10:43:53.992292Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "b3b58dded3b946c59f3944bdb058e957",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-08-01T10:41:52.174560Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "cbbb3704a303446f9ce996c354bde674",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-01T10:35:33.120371Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "777fffb85eea4b2c8f135ed9d0bb3d9b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-08-01T10:34:15.708718Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "70d6a27c042d4608a17350557dda1242",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-01T10:32:10.941538Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "2952692",
  "id": "b6223ed6a654411aa69a2f2bf5cbdf8a",
  "label": "Put the substance above the badges",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-01T10:31:49.055612Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "fba2843ae874405fbedfd708ae4729de",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-08-01T10:29:47.694839Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "18bfe0e6e1214efb8d3012a25c7716f2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-01T10:29:37.166739Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "e0ec78f",
  "id": "3414539f89824404a3aaddf3fb1fa4e9",
  "label": "Say 'no third-party dependencies', because dependency-free is not true",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-01T10:23:40.553869Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "ad664f2fbec2408f82478354d245bc7f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-08-01T10:19:34.538095Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "44bf2256ce504ae3b774127b332337ed",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-01T10:18:35.247610Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "c71515b8704a44d8a0cae01932c6a5fe",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-01T10:15:17.418508Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "a85495abfd3c4d7b83fe828a63b8a8e9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-01T10:11:11.760015Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "fcd94dda493c466baa55b1d0b97a8243",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-01T01:59:00.969056Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "3753e6a",
  "id": "f97cd893b8fe4cecb0e67b93738ef493",
  "label": "docs: show the tool running, at the top of the README",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-08-01T01:49:24.370933Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "ee15354",
  "id": "4f90b52103c6485abcc51b0e90ee537d",
  "label": "fix: the browser demo has been broken since grounding moved to gradecore",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-07-31T23:57:09.348494Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "f116464c6f89449a9a94d86432a339db",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-31T23:53:18.426491Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "5e2449bbc98442f0ad7c2566c1973cf0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-31T23:49:27.044694Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "c94dc1eaf3114cb7acc033e4eb02e938",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-31T23:48:24.764553Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "00ffa397da0440309302baf19c37e0e4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-31T23:45:17.708308Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "903f5bd729d743df991c17326de87742",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-31T23:42:21.328135Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "1ec7e98347a34615ad859886deb9d8b6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.1714,
  "created_at": "2026-07-31T23:41:35.487660Z",
  "faithfulness": 0.1714,
  "flagged_cases": 29,
  "git_sha": "e76f17b6c56e",
  "id": "2f3c6614a38245c98f0bb296cc9b150d",
  "label": "suite 2026-07-v3 \u00b7 median of 1 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.1714,
  "recall_at_k": 0.1714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-31T23:04:18.449559Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "a17abadf191a498683b9227fc19ea041",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-31T22:53:13.011563Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "628b7bd2dee14685834d6ab62f3db814",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-07-31T22:51:59.194925Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "6affdb704d294c178e58b28d7d4963dc",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-31T22:49:15.849752Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "30c3f893df334a65aa3183eb52a437d9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-31T22:47:18.540377Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "04e3e02194804c70964299cab0a4e1a7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-31T22:41:15.945172Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "eea99b5d14654bf3a128da883814b603",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-31T22:38:21.614023Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "2c2cdd1961d1433ca968ec275e5728aa",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-31T22:37:28.107801Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "1651ab03522f4f13baebc1e92c7de824",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-31T22:33:53.029972Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "434cceb780e44606b3f9bcf49c8d7507",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-31T22:29:51.578047Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "e27e15bb23a340bbb4183b153e748bc9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-07-31T13:09:37.777350Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "47df0c33f601483e96c54a480f52faf0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-31T13:05:36.925168Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "eea61c0d65e8446c97854144c17faa03",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-31T13:01:33.923894Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "716b913d35cf417594a75c2c8f601776",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-31T13:00:18.252326Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "d102e8c0f72645b9b195d2e633dab4a0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-31T12:56:31.000120Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "66ba69920841494cae065f89fedf00a4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-31T12:53:15.366067Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "52e50d5743444e50914dd0f613791205",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-31T12:18:29.988492Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "41074d4117534964abb76c9a2b08a208",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-31T11:28:00.943692Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "8e8b3a0eeca74316b30696145f53d1c8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-31T11:26:17.654346Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "6959b74cc8124e3aa71120ea9283a7c4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-31T11:23:04.168494Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "e563a80dd3a342b8a77510ec60ed29c2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-31T11:20:43.610358Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "e5482c8b436943aca451a9877f4ad71a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-31T11:14:15.163488Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "823bcd32f21845978ef1ca95df6954ec",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-31T11:10:32.501719Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "08c299f4111e4ae7832c2db08d5f45d7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-31T11:09:18.147564Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "8a19f4fb06cd48089a4235f04fdfa75e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-31T11:05:17.344260Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "849555b615ca4a47932e7b8cb39c6072",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-31T11:00:28.083063Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "51615a8427404e33934e1707905bac33",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-07-30T12:00:04.023887Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "3e800f28ea7649bfba9a41899c9432f7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-30T11:56:06.948692Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "e1a7c799d2ff43ada358ccd1eb47d858",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-30T11:52:13.514549Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "42f167828d0d4e4bac3361a400c4e62f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-30T11:51:21.203432Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "62828f7bc797427fb29b17214b4a2dba",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-30T11:48:08.981224Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "419bcf238acd44ac957c275455685fd2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-30T11:44:54.937516Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "220bfcd7d4754ccaa942dad96909c250",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-30T11:12:21.370853Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "20a8700b5ae54f939acc7945ccaea31a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-30T10:59:17.988837Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "2106604c52a1486ba77b5c59f51fe902",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-07-30T10:57:51.726519Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "b79a83063eba47e38b24a9e4ade0c0e9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-30T10:54:07.889053Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "ed24b485b5b44e04918d3e1aacfa87e4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-30T10:52:02.197048Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "b66b3ef135d745a0bc038a13c1ab457f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-30T10:46:39.110432Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "ba98cba191bc4c1299153a143508f583",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-30T10:44:00.367375Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "1f432281eccb4972a619e2ab29013bb8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-30T10:42:57.111467Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "e0130974ba5f4b7c849bf535c5e46387",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-30T10:40:00.836039Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "9c465efe45c04e509bf0f8567ab7d67e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-30T10:36:05.794579Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "d53f3cf9e9f544adaa59eb49426deefe",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-07-28T11:50:17.272176Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "cd85ac83a3eb45b8a5d9101eaf5c4ba3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-28T11:46:28.470255Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "5b820b1e59624e639a17046fd1a77147",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8857,
  "created_at": "2026-07-28T11:42:36.689561Z",
  "faithfulness": 0.8857,
  "flagged_cases": 4,
  "git_sha": "e76f17b6c56e",
  "id": "b1489446928447a0bf20f7fab5105776",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.8857,
  "recall_at_k": 0.8857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-28T11:41:28.671936Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "936d8bfba926470cb21bae40c651b334",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-28T11:37:24.907280Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "33be8a0109484ba6a2bac00c3e6261df",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-28T11:34:20.904048Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "6683a3f0e592464ab6e1a2e4739d94aa",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-28T11:33:28.883123Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "d64ba18fd09142b5ba93e28d4c889923",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-28T11:30:12.123080Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "d5a332f317b443c4913a968283ff9ad0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-28T11:12:23.616519Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "74be205f8d7745bfbd01c9ee2707d0c9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-28T11:10:50.810020Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "9393092e2915436c9e1a8316bcd84e58",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-28T11:07:38.557302Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "2a7f37f911da4ab0a9c24fd5ca984bba",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-28T11:05:14.498593Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "7541f31a76fd4b52976b148463d204c5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-28T10:58:54.626354Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "a141d0984d0b4231b31efb688585c95d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-28T10:55:50.648307Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "75b25c5898ba45949bae5b4a47c5f8da",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-28T10:54:44.435559Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "ff9f487a5c654ebdb4add5caa65ff371",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-28T10:51:19.354711Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "0ca6d9ebad904400a06f95ccc64ba6c0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-28T10:46:39.989714Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "c40b69086bd644b7b457481e740bdce4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-07-27T13:15:07.932542Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "89ae5c3a73f34cd0be8beed9225f5c0a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-27T13:11:11.963096Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "c0351c07682c41afb3c342c498bab94b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-27T13:07:10.007249Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "2425120988444761a12bc7acb304bbc7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-27T13:06:08.543875Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "81c82ced99434d18b0e286ccedecc093",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-27T13:02:01.545687Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "fb9d149b69f9431d9c923a9045016553",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-27T12:58:24.832785Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "189c63727fcd4ec1abcb4400931cfbd4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-27T12:18:00.399507Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "382e2461540d493da2639307be829f40",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-27T12:07:09.472328Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "b31c45f2ce9a465db67b5fe30e5a91a5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-27T12:05:18.781115Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "2ef296dd616b4485869c9d90b7f7813e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-27T12:02:08.941044Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "3d3ed365881045bf86053637fd0cdb6a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-27T11:59:09.740974Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "fd555f3e0d3a47678855bd9bd554ca83",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-27T11:52:34.741690Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "e92387b2ee584f7882be3ca30d24878c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-27T11:49:24.023863Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "14ce65574a4544d3a038373b34d9782f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-27T11:48:22.837545Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "bdecc46da7fb48c9ae04a26ef88e9896",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-27T11:44:38.447720Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "1c1f351ad5ed4cceaa69c1ac698cc058",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-27T11:40:54.414369Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "f2c248c47c584ee3807bc409eb2edb99",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-07-26T11:12:34.608938Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "4fc3f3993c5141febc746107f06fda06",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-26T11:08:35.987657Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "7692509648174a7e8a64d6fe105a1fe4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-26T11:04:44.004886Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "e3daeba978d1466e86001ac7f044cf0d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-26T11:03:29.611215Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "ad13595812d2414d82331eecc3b84ab5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-26T10:59:04.976843Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "642aba5432aa4f73a5c92128e965e280",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-26T10:56:05.579520Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "5c522c54733c4c079d9e57bd5c59600a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-26T10:55:25.873458Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "ccfe01b4e11540628f9f05e3178fb82b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-26T10:44:07.460881Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "fc335975f4ba4fb6a8812a7274b67ecc",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-26T10:36:13.837515Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "318342f07b694776bdf21d9fb6c98726",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-07-26T10:34:51.636547Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "7a70b45a74ea41658a0ba3a6ca865ea8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-26T10:32:12.572086Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "09f789f192744df2acdb178817481375",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-26T10:29:48.213121Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "8359cea41edb46d480ab3cd3d6ea268f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-26T10:24:04.480497Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "ed63d711bf8245e8807496b6b2c3a1f6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-26T10:21:23.439943Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "a84a47b1afec4941971715b71c16d2ab",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-26T10:20:39.003886Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "108618a6178a4430ab5403f2ac6d68a4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-26T10:17:25.368059Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "ad776ef2da14418b99ad470591f06fe6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-26T10:14:24.661550Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "1571c30143d14eddb848f63e2ef4ffde",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-07-25T11:07:01.965973Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "5a5e7f0571d8443589be265cf58ff0c7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-25T11:03:09.774701Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "661654be17134c1ead2558d88c4e0570",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-25T10:59:13.454444Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "7dec631dc5ba4d5cbb18f7f2437937e0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-25T10:58:09.621893Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "2ef753d9961d42ada58b8ef748cd2d39",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-25T10:53:45.368990Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "1d9cd73c2fa74807aad6b5a27db95b89",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-25T10:50:36.967793Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "74c575abbc01461aab5c888638c36c6d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-25T10:49:52.547924Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "7b9339e1ce6f4377ba6a8b47675b163d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-25T10:41:54.497665Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "744387a5825e440e92d3fc2b56449598",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-25T10:22:56.733475Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "8748eeb95b89441e9665af9c6800cb3e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-07-25T10:21:37.408682Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "ad8355deb9344f35828dc798cdf12120",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-25T10:19:04.916380Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "c10749ad7fdb4a108d271054841894d0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-25T10:16:51.772429Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "ed21841bafd542ad8af0622f73e1bcba",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-25T10:11:16.916502Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "1afdc4bbce4a49de993852eda2ad61a1",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-25T10:08:35.193142Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "bf09819128e34794b01199df226bcbaa",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-25T10:07:46.208104Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "3971f98202aa4b278c1e09fe9bcea6fd",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-25T10:05:34.149086Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "c36e1362ad424c1b8971199cd4c2309b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-25T10:01:35.975472Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "6e423e98f95d41b28bae6048c57c66fd",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-24T21:30:10.239291Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "f228a4f",
  "id": "480c72033bab40c4abb91cc79de75932",
  "label": "Install git in the image so the gradecore dep can be fetched",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-24T21:21:54.655992Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "f040587",
  "id": "3e0b4c72d86f40ddb2c8630880b33dc8",
  "label": "Delegate grounding to the shared gradecore engine",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-07-24T11:42:14.027340Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "4aaa233b21834ca3b1379edbec59ae28",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-24T11:38:19.840969Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "b4bc23bdfed64e8a8f47f42f1715507b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8857,
  "created_at": "2026-07-24T11:34:19.854966Z",
  "faithfulness": 0.8857,
  "flagged_cases": 4,
  "git_sha": "e76f17b6c56e",
  "id": "205b6746e9294868b1429814d95e4658",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.8857,
  "recall_at_k": 0.8857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-24T11:32:45.016429Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "315cf64c10e6453aafd2f0171ff6238c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-24T11:27:25.228311Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "c130a3ba2d844473b56591bac33e6912",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-24T11:24:08.552347Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "ac0a102d703f4ea79ca13cd0c6537ea4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-24T11:23:17.003841Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "8d3ad2ee04734a2f91da17278a8c4cac",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-24T10:53:47.002253Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "0017d9f4f6eb4e58bb45e4ff19e2f596",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8182,
  "created_at": "2026-07-24T10:52:21.776991Z",
  "faithfulness": 0.8182,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "ab963e779ce74a129d58242f38af80dd",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8182,
  "recall_at_k": 0.8182,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-24T10:49:39.419522Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "924abc8f75f348169528bb9d2c27ff8e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-24T10:46:56.468397Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "4941e81489d74b9ea83689541628d66c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-24T10:41:10.991159Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "2341dd25179240a28c4d33ebddd42b14",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-24T10:38:09.932510Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "30b2418e50b44493a22dc06e07fa275b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-24T10:37:19.996180Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "5a2185afab5f4731922fd55c3aa54d7a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-24T10:33:54.654188Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "2a0211e6afef4899a0d95ae5298f22e6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-24T10:29:58.280095Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "a170903a342e476db40c7b28e2f484b9",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-07-23T13:03:38.306106Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "81b0c711c2a54e83b5b21921884f2bff",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-23T12:59:44.216294Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "c28d8d911c1f427ca93e430e20b1e5a5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-23T12:55:49.929839Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "f03a2236ef2b46b5ac8abc4fc8f67369",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8857,
  "created_at": "2026-07-23T12:53:38.956670Z",
  "faithfulness": 0.8857,
  "flagged_cases": 4,
  "git_sha": "e76f17b6c56e",
  "id": "dc4d56e9ee17442abcf93ed50fb77ea2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.8857,
  "recall_at_k": 0.8857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-23T12:47:37.819596Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "dc1007524c2e4cbdb2494ae7c0f5bfca",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-23T12:43:03.043985Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "c75dee33d71b4a37956ad05a85a28dc1",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8857,
  "created_at": "2026-07-23T12:41:54.503104Z",
  "faithfulness": 0.8857,
  "flagged_cases": 4,
  "git_sha": "e76f17b6c56e",
  "id": "8a1a09615f63468c9971e664fa404b68",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.8857,
  "recall_at_k": 0.8857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8857,
  "created_at": "2026-07-23T11:52:33.178510Z",
  "faithfulness": 0.8857,
  "flagged_cases": 4,
  "git_sha": "e76f17b6c56e",
  "id": "2f5d2cc91741439c909e2532d2b0d2eb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.8857,
  "recall_at_k": 0.8857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-23T11:02:09.097270Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "afb0c34749c6420cae9f5120e937f400",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-07-23T11:00:49.949203Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "efcc10f2f39247619e3e39a24d4aa6cd",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-23T10:57:51.757741Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "c67b8d01974448efa897de1c0f035879",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-23T10:55:08.674746Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "1bb7425c022d4b2cb57bcc7b602438c3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-23T10:48:51.090239Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "276ec3cf1812439f85ff4cb8ce977e4b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-23T10:45:15.896226Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "5dd95a8a50974aecbad71b4cca035a4c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-23T10:44:12.699368Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "da59150fb8fa48d19612a6a1576b42fb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-23T10:40:20.243098Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "ff153fc3cf854a63bf3203ad02b304f7",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-23T10:36:50.370570Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "56740ab69afb4a23ac0a767a53a49678",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-07-22T12:13:21.213963Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "3a94f4aecb534b2b943bf9f8a87bf5ea",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-22T12:09:26.866443Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "0b8c1b488d734a95a34c0d123f8b9679",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-22T12:05:26.798249Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "9494654e4aba41ae8d1e1ce6b0b56f06",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7429,
  "created_at": "2026-07-22T12:04:07.402701Z",
  "faithfulness": 0.7429,
  "flagged_cases": 9,
  "git_sha": "e76f17b6c56e",
  "id": "aad9267230a640cbb99f7d15bc3ef997",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.7429,
  "recall_at_k": 0.7429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-22T11:59:26.248501Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "85ba133777cd4f24971ba337edc43f0a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-22T11:56:25.126199Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "1f5f19f217c54a3ab07d8000638281eb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-22T11:55:19.196351Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "09222d2c601640408fdf33318b894073",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-22T11:49:05.418041Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "647ca045a4eb4bb38a22d263bc9ffe3c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-22T11:02:45.163897Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "4dd4e89186534c97982ad94f97b918c2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8235,
  "created_at": "2026-07-22T11:01:29.272032Z",
  "faithfulness": 0.8235,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "f3f3e73517194755aff4fa0110a8d10a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8235,
  "recall_at_k": 0.8235,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-22T10:58:37.299042Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "29fe3841ae684fa8885c48df559728c3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-22T10:55:50.523014Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "744267efcd734c69af8d47bf06b12d7d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-22T10:48:55.367373Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "78b03fcc4dca44da8764460e3b8e680d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-22T10:44:34.277411Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "6061c085ba494e748948bf4f5d0e80f0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-22T10:43:31.435658Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "5abfdd79f864464b97f2c13aed610ea4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-22T10:40:17.004668Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "a22d47edcdb94468a70919ee4bc66182",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-22T10:35:47.980113Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "b7e33b275e8e48eab51f03941d785c8d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-22T06:54:44.159997Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "ba4f8f9",
  "id": "33ac91243ac84058a3b721b03c8a1fce",
  "label": "Make /eval body optional; add the live URL to the README",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-22T06:50:09.742427Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "51c9248",
  "id": "ad67fb65d6464dc1a52c9994025bffe6",
  "label": "render: drop the unused DATABASE_URL prompt",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-22T06:40:32.291843Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "272c919",
  "id": "4066e59e013a49a39d39990a539b9e16",
  "label": "Fix pgvector search: send a vector literal, not a float array",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-22T06:36:00.404248Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "c4b7819",
  "id": "46fd9a3a55454117a89582fafad2c78d",
  "label": "Wrap the pipeline in a FastAPI service and test the pgvector path",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5714,
  "created_at": "2026-07-21T11:38:55.291199Z",
  "faithfulness": 0.5714,
  "flagged_cases": 15,
  "git_sha": "e76f17b6c56e",
  "id": "336a86df7fd94e7188ad647e164f38d2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5714,
  "recall_at_k": 0.5714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-21T11:35:09.407784Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "904fac2121934d6487d274b7fad45efd",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-21T11:31:17.481209Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "96b293e5579b4596b41b74a84e2180d2",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7429,
  "created_at": "2026-07-21T11:27:51.203907Z",
  "faithfulness": 0.7429,
  "flagged_cases": 9,
  "git_sha": "e76f17b6c56e",
  "id": "b6bf8f179b90401e9f652310f0ca097b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.7429,
  "recall_at_k": 0.7429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-21T11:20:59.598390Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "b06bfd9952ac4cf19049d5a2b6e6f612",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-21T11:17:57.816615Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "e518b1082cdb4413872986930707cc58",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-21T11:17:11.124000Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "611e0627a5fb46049e08cb3363888d28",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8857,
  "created_at": "2026-07-21T11:14:58.742496Z",
  "faithfulness": 0.8857,
  "flagged_cases": 4,
  "git_sha": "e76f17b6c56e",
  "id": "6e1931ab1fd74668ab5499171ebe762c",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.8857,
  "recall_at_k": 0.8857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-21T10:58:40.054761Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "a1087d38eecc4ceb9dfef77c82bd8355",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-07-21T10:57:09.982501Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "19e2120f830345d0b38223061795c200",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-21T10:54:16.444927Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "6a3e8ff627414856ba23eeef32e024fb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-21T10:51:54.588604Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "b15f38bb6b7a412e89ac81c0436e3b53",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-21T10:45:17.582234Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "337207cf97de49d081bb29b4a434e235",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-21T10:42:02.160344Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "4104362a1f84477394957c5626c2c82a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-21T10:41:01.148501Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "39fa2f1975a541ffa191f2caa3657bc6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-21T10:38:16.373069Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "3bcf891346c64cc595aaab95a871abeb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-21T10:34:28.948310Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "66427cb52e4e4cd7a287e1530e9da68a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-21T06:32:37.581782Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "8ddaf36",
  "id": "68422ed5eb9d48f6b0c2477262c7e221",
  "label": "Add a back-to-portfolio link to the demo",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-20T12:33:14.088638Z",
  "faithfulness": 0.0,
  "flagged_cases": 35,
  "git_sha": "e76f17b6c56e",
  "id": "fc22ab4b5634420eab2553e7a26bd0ad",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0286,
  "created_at": "2026-07-20T12:33:04.612416Z",
  "faithfulness": 0.0286,
  "flagged_cases": 34,
  "git_sha": "e76f17b6c56e",
  "id": "f659c2f3b006414b8f7aa3cdfb37c16b",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.0286,
  "recall_at_k": 0.0286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-20T12:32:54.192404Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "388a144780f14c03ab66bcf1c29d9823",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-20T12:28:37.423468Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "e1e9397115584a1f9a02b64102d540b4",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-20T12:19:57.601886Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "8baa3179c1ba43958366a1fee429dcce",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-20T12:16:14.717388Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "f90eb7f66b064137ae9e913629c1aeba",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-20T12:15:29.089775Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "f6d6aa4c42a14a86ae20a3bff0310a13",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-20T12:03:37.686042Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "06c85a5e5068419bb7f10e26f684e7c5",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-20T11:41:50.051367Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "4fdf8b4297fe4cbd842bd4523a64b788",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-20T11:39:59.710503Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "daf164e2ec824ccbb686d3d4587d4b84",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-20T11:36:34.810429Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "bad01a8fcf95405cb16e4f4f72d32752",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-20T11:33:33.259914Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "19ca39b1616f4fb19fa8f89254018708",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-20T11:26:38.242957Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "156c484b0f9143aaa8639a6674b1faaa",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-20T11:23:07.101996Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "a011ff377f934e38aaed5a6ed30dab07",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-20T11:21:56.187631Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "7c438d3c80a640038252c84c388890fd",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-20T11:18:59.548982Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "f41f44b24d5e49109c599c225a21b00f",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-20T11:14:20.244779Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "8e58d18c9c5848a482de3ba37a34c151",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0286,
  "created_at": "2026-07-19T10:51:04.105880Z",
  "faithfulness": 0.0286,
  "flagged_cases": 34,
  "git_sha": "e76f17b6c56e",
  "id": "1f623662b2194491946d952a271303f1",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.0286,
  "recall_at_k": 0.0286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0286,
  "created_at": "2026-07-19T10:50:56.212657Z",
  "faithfulness": 0.0286,
  "flagged_cases": 34,
  "git_sha": "e76f17b6c56e",
  "id": "d2568b1e9124431482062a7a3967043e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.0286,
  "recall_at_k": 0.0286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-19T10:50:46.293555Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "b235a2de59164c189b3c145be18bd242",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-19T10:49:27.044082Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "5fac39d58b8340f6b98e9f7c5f2cb039",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T10:43:37.972207Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "9691affc0b32490899972486f1d51eeb",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T10:40:23.178508Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "2f604db4dfec46efa2d31e5b759af279",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-19T10:39:37.406390Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "dc9d33f8ab834482afc5a13c4da1d4c8",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-19T10:37:29.561762Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "5c0ac9989fca43908a5d03e8bde6bce0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-19T10:27:10.095054Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "0b49ff686abe480dabb4e16cf0a54b23",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-07-19T10:25:46.135856Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "e742405b8855468082c14776ae97a159",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-19T10:23:17.307627Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "5f7eb74f43464349a703ed8fe6e72161",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T10:21:01.592104Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "950990730a2c4c14bfe1b773e80a2dfc",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T10:14:40.455080Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "3ff973e67ad7499f954577ebf12015e3",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-19T10:11:22.668054Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "12a30de293e3419880b6ddadbd75b20a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T10:10:25.440110Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "6449c090ce36405ea9ae7ab3fbd9722d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T10:07:14.449064Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "4d5b35ef42da47d895e2a986f5f58eaf",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T10:02:06.404311Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "43892f748f574062836bf6c4b2729c0a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.2571,
  "created_at": "2026-07-19T06:55:27.480863Z",
  "faithfulness": 0.2571,
  "flagged_cases": 34,
  "git_sha": "e76f17b6c56e",
  "id": "bc5db20206a449ef87ee38803e2e3705",
  "label": "suite 2026-07-v3 \u00b7 median of 2 runs",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.2571,
  "recall_at_k": 0.2571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.3571,
  "created_at": "2026-07-19T06:55:20.351451Z",
  "faithfulness": 0.3571,
  "flagged_cases": 34,
  "git_sha": "e76f17b6c56e",
  "id": "3194ad5166054c7cb219147e6bf12e53",
  "label": "suite 2026-07-v3 \u00b7 median of 2 runs",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.3571,
  "recall_at_k": 0.3571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T06:55:12.686269Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "2a3d21797e594e388c80df2315e8b750",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-19T06:53:51.952440Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "346e2cecf2d14164ab7d6fec62c13067",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T06:48:53.011042Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "5dd1f363790b4ca1b176665d22b83969",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T06:46:13.247896Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "6c3d4a391f9a4b30813e71c682e7dbce",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T06:45:27.667295Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "659a70fa2f8946d6a8b27d0c0e5d5ac6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.3429,
  "created_at": "2026-07-19T06:43:26.039926Z",
  "faithfulness": 0.3429,
  "flagged_cases": 23,
  "git_sha": "e76f17b6c56e",
  "id": "c33de6c05f4b4d87ae198abec9f2e39e",
  "label": "suite 2026-07-v3 \u00b7 median of 1 runs",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.3429,
  "recall_at_k": 0.3429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-19T06:42:48.810499Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "892f81871dd442659f2d39839f2f630a",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-07-19T06:41:32.398049Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "c950deed242e4e8e92463f7fe4e84ab0",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-19T06:39:08.417346Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "5bff2a285c9642fb95de741b9fdcce83",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T06:37:08.734026Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "6419bd3a08c840339c50b0726226c8b6",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T06:30:15.816772Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "18a3f67af04c4fa78a91addc20ce3616",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-19T06:27:35.471842Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "ea4d2b2e0439473093dcda0f133794f1",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T06:26:42.724528Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "fb168d8b9ffe49a4a20e24a3e215a162",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T06:24:04.248971Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "835a2f2e089342fca643c6708174a35d",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T06:21:01.068062Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "b837954ed1f942409044105c31e60c6e",
  "label": "suite 2026-07-v3 \u00b7 median of 3 runs",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T05:27:45.902647Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "43f61e2dd0dd483faed48188ad832420",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-19T05:27:29.259972Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "9f6d513f0e864d0f973f8de16f600c44",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-19T05:26:45.185834Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "2b7dcd04f2f74e6d93c327d89c6c2958",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-19T05:25:13.687297Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "903600f197d34fd99a7af225cde21479",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-19T05:24:48.181999Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "c5424bd59e574c0280f00f4f22813bf0",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-19T05:24:00.128250Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "37a72a2c26c74b28afe80b381cee44a6",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-19T05:23:14.471062Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "29a36bd8743940348785fec7ca3d38db",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T05:21:02.330748Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "3086ca1aa46c4dd3b4f0a6a8a7b17d54",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-19T05:20:10.661085Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "918524866ec9455d8e126597e67e6cb3",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T05:19:53.431222Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "de65486f79034aeca16163e9bcf4664c",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T05:18:32.905332Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "a12aa890dfd84a32a331e1a763a1e85b",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T05:17:35.344994Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "36cb863be3ce4b0b93433b1509a068a5",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.4857,
  "created_at": "2026-07-19T05:16:56.965044Z",
  "faithfulness": 0.4857,
  "flagged_cases": 18,
  "git_sha": "e76f17b6c56e",
  "id": "c9f7f61d5e374c488716ec5ac926d7a8",
  "label": "suite 2026-07-v3 \u00b7 5 provider error(s)",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.4857,
  "recall_at_k": 0.4857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.6857,
  "created_at": "2026-07-19T05:16:53.283797Z",
  "faithfulness": 0.6857,
  "flagged_cases": 11,
  "git_sha": "e76f17b6c56e",
  "id": "1de40f02a8ee46028569e6747c7c1b31",
  "label": "suite 2026-07-v3 \u00b7 5 provider error(s)",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.6857,
  "recall_at_k": 0.6857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-19T05:16:48.621702Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "6851270782b44abd947da4795414dc44",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7429,
  "created_at": "2026-07-19T05:16:22.287182Z",
  "faithfulness": 0.7429,
  "flagged_cases": 9,
  "git_sha": "e76f17b6c56e",
  "id": "023b2b6a67324ea7ba62cdc8e4f5e950",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.7429,
  "recall_at_k": 0.7429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T05:14:46.227147Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "e41c015eb48d47da98fda9d4b49c944b",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T05:13:55.520251Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "08f79baa117c43e4ac360d04cf775a36",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T05:13:35.564045Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "c3f159ae1fb1481fbd3e55c5fb4a9bda",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-19T05:12:45.953996Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "f23a4c033d074f9a83e399272640c517",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-19T05:11:13.422829Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "5c271da824154588a2723d84c1708777",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-19T05:10:47.792204Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "187b10a0e1cb4d2db9d0dcda2c8a8519",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-19T05:09:55.787706Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "85920abb5b164115bb817a6faa911f0c",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-19T05:09:13.446793Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "9df296d7bb3a462c86e75fed982230eb",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T05:07:07.363819Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "2054c75df3004ad1b365ccaf2e4b06af",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-19T05:06:05.563076Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "c053f3e378ac453bb0dbeb2b28d9edb9",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T05:05:48.135978Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "fece6f90a75a4b848c654565f194bd85",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T05:04:38.081996Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "883941aa953744c3a2669b11ac820697",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T05:03:31.804261Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "dde6d2be753f41ca83e4ec97d4b3c1de",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.4857,
  "created_at": "2026-07-19T05:02:36.552989Z",
  "faithfulness": 0.4857,
  "flagged_cases": 18,
  "git_sha": "e76f17b6c56e",
  "id": "9e893f22c65a4814a1843358cddf9b8e",
  "label": "suite 2026-07-v3 \u00b7 5 provider error(s)",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.4857,
  "recall_at_k": 0.4857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.6857,
  "created_at": "2026-07-19T05:02:32.164876Z",
  "faithfulness": 0.6857,
  "flagged_cases": 11,
  "git_sha": "e76f17b6c56e",
  "id": "794473779d1946c4828edee6e38d98f7",
  "label": "suite 2026-07-v3 \u00b7 5 provider error(s)",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.6857,
  "recall_at_k": 0.6857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T05:02:25.691319Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "d53ae9ab6120417892b23cc9eec8667f",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-19T05:02:01.486960Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "cd94a986d53a4dd29cf3499cde3d9450",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T05:00:20.530636Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "06e7c7b8418c4023af539ea5e4b53ac4",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T04:59:23.057729Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "1e3df71275754b669ffdc838a9fd8562",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:59:06.846041Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "1cd8443a6aa946b4aee1e8fdc9c91140",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-19T04:58:26.480638Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "08b618c67b48459fb0f0f55e8a04b93c",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-19T04:56:55.401170Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "55e26d4758c843d399dcb69fe4ea233e",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8286,
  "created_at": "2026-07-19T04:56:27.305368Z",
  "faithfulness": 0.8286,
  "flagged_cases": 6,
  "git_sha": "e76f17b6c56e",
  "id": "e7b5ec1920eb4d638a6909be49b15e23",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8286,
  "recall_at_k": 0.8286,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T04:55:43.328726Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "4ddd49dcdbb4437e9d708ae065c35de8",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T04:54:58.900272Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "f862409b056542ed9c47b9bbe0315636",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:52:55.434377Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "abeba6ffdf564900ae69912e14f45993",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-19T04:52:03.703018Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "490d156f2cf94d809825a4d9fb3b2bb4",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:51:46.183491Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "818ab362d49d4c59b27d29400d006349",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:50:54.305553Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "d3f952887eea47e1a4bc4eed4c50d35a",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:49:56.451550Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "d51aa5d57a694e4da77e8c4c6c41c605",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.4857,
  "created_at": "2026-07-19T04:33:04.749030Z",
  "faithfulness": 0.4857,
  "flagged_cases": 18,
  "git_sha": "e76f17b6c56e",
  "id": "cd535fbf7ec74e36ad658b624d85d177",
  "label": "suite 2026-07-v3 \u00b7 5 provider error(s)",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.4857,
  "recall_at_k": 0.4857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.6857,
  "created_at": "2026-07-19T04:33:00.056672Z",
  "faithfulness": 0.6857,
  "flagged_cases": 11,
  "git_sha": "e76f17b6c56e",
  "id": "aa93886855d745469533447bd5c1801d",
  "label": "suite 2026-07-v3 \u00b7 5 provider error(s)",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.6857,
  "recall_at_k": 0.6857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T04:32:54.152211Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "7495ac1cdc7a43dea901e0c9eb20079b",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7429,
  "created_at": "2026-07-19T04:32:29.238735Z",
  "faithfulness": 0.7429,
  "flagged_cases": 9,
  "git_sha": "e76f17b6c56e",
  "id": "084973e2466244b79b0b683dc9618c9b",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.7429,
  "recall_at_k": 0.7429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:30:49.192851Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "5d91600568fb4091aedaf8e26af1a7f7",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T04:29:54.945074Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "882ca67c138f4098a960ae3954407d6b",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:29:37.861570Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "fd1142c75b0b40d89635928fb32fa11a",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-19T04:28:56.079893Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "68da69210db64ddf998329fd2e9435a5",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-19T04:27:19.356029Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "835ee04cab4e40c996da8c97f9a51fdb",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7714,
  "created_at": "2026-07-19T04:26:52.497669Z",
  "faithfulness": 0.7714,
  "flagged_cases": 8,
  "git_sha": "e76f17b6c56e",
  "id": "eec7f9ccb2a241a1b170e2b38d349eaf",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.7714,
  "recall_at_k": 0.7714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-19T04:26:06.301845Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "c10b41fceb70446f9d66f6cc7c681280",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-19T04:25:21.571031Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "e4faba56eaf4476090b9464c71364cbf",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:23:20.351693Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "01f8e6ad5add4933b8706cae96dbf269",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-19T04:22:21.926007Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "58ae3ac848304893a8d775dbfb5fcb0e",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:22:03.860849Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "73d379e59d9b4c7c9cf39da532d58456",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:20:56.582790Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "1e7b448b2ec845a68f1ebdfc084e498f",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:19:44.729183Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "d09499bc4e644caea79f39445e54f7af",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.4857,
  "created_at": "2026-07-19T04:17:50.350418Z",
  "faithfulness": 0.4857,
  "flagged_cases": 18,
  "git_sha": "e76f17b6c56e",
  "id": "95e0778b501c478f84a57ee155412f4d",
  "label": "suite 2026-07-v3 \u00b7 5 provider error(s)",
  "n_cases": 35,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.4857,
  "recall_at_k": 0.4857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.6857,
  "created_at": "2026-07-19T04:17:44.773612Z",
  "faithfulness": 0.6857,
  "flagged_cases": 11,
  "git_sha": "e76f17b6c56e",
  "id": "faf45ada8fdc4d838c6efc8377a545fd",
  "label": "suite 2026-07-v3 \u00b7 5 provider error(s)",
  "n_cases": 35,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.6857,
  "recall_at_k": 0.6857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8857,
  "created_at": "2026-07-19T04:17:38.192390Z",
  "faithfulness": 0.8857,
  "flagged_cases": 4,
  "git_sha": "e76f17b6c56e",
  "id": "541413596e9b485ca39a6cf62113dfef",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.8857,
  "recall_at_k": 0.8857,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7429,
  "created_at": "2026-07-19T04:17:17.754831Z",
  "faithfulness": 0.7429,
  "flagged_cases": 9,
  "git_sha": "e76f17b6c56e",
  "id": "2187ea6a0c83486c9bd1e31bde7236d5",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.7429,
  "recall_at_k": 0.7429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:15:44.958161Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "eb2e5748a4444c068033edbd7831c63d",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T04:14:56.798688Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "fd882e22a6c24890b72e0ac65ac0e266",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-19T04:14:39.290432Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "1053688080da45029d54d499996055b1",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9714,
  "created_at": "2026-07-19T04:13:55.335321Z",
  "faithfulness": 0.9714,
  "flagged_cases": 1,
  "git_sha": "e76f17b6c56e",
  "id": "608e944e51e246da829e80959e534d88",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9714,
  "recall_at_k": 0.9714,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8571,
  "created_at": "2026-07-19T04:11:34.925576Z",
  "faithfulness": 0.8571,
  "flagged_cases": 5,
  "git_sha": "e76f17b6c56e",
  "id": "6e95824f89f440daa9513448dcf138ab",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8571,
  "recall_at_k": 0.8571,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-19T04:11:08.832147Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "c2a95d50e77b4e3dacfb7a7018b134e3",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9143,
  "created_at": "2026-07-19T04:10:22.518348Z",
  "faithfulness": 0.9143,
  "flagged_cases": 3,
  "git_sha": "e76f17b6c56e",
  "id": "59077a583820438bb13039d80cfee53d",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 0.9143,
  "recall_at_k": 0.9143,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9429,
  "created_at": "2026-07-19T04:09:40.718408Z",
  "faithfulness": 0.9429,
  "flagged_cases": 2,
  "git_sha": "e76f17b6c56e",
  "id": "b1a76770960e4054bcc3deef99cbb096",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 0.9429,
  "recall_at_k": 0.9429,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:07:29.310106Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "4e2eda8b0d694f88b46fd4282ebc687f",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8,
  "created_at": "2026-07-19T04:06:31.056720Z",
  "faithfulness": 0.8,
  "flagged_cases": 7,
  "git_sha": "e76f17b6c56e",
  "id": "6622d2281e7d4f3d80e20d826f5de8e5",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.8,
  "recall_at_k": 0.8,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:06:13.036165Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "e43185df287a400fbe2a798a5b79a08c",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:05:04.863173Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "8c877d7b286b417b9d1b0aafe72db628",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-19T04:03:46.662767Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "e76f17b6c56e",
  "id": "40d5dc89e75847f6b2c23c802b6c3512",
  "label": "suite 2026-07-v3",
  "n_cases": 35,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.5909,
  "created_at": "2026-07-18T19:23:14.822670Z",
  "faithfulness": 0.5909,
  "flagged_cases": 9,
  "git_sha": "cc2161d8bac2",
  "id": "09d6bf44b369466fb5604b606121b604",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "meta:llama-3.1-8b",
  "precision_at_k": 0.5909,
  "recall_at_k": 0.5909,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T19:23:10.855466Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "6e0e3542a07b46218bf9fe91ecd60994",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "meta:llama-3.3-70b",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T19:23:05.696827Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "da0c2c31260647829943404b8f3b8794",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T19:22:45.933160Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "1b120501349447a78c35731a853af980",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:21:54.717216Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "537804cab5564fd397815f0235fc5202",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9545,
  "created_at": "2026-07-18T19:21:20.925745Z",
  "faithfulness": 0.9545,
  "flagged_cases": 1,
  "git_sha": "cc2161d8bac2",
  "id": "4c4350b2aedf49e3ba7aac14ec06334e",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9545,
  "recall_at_k": 0.9545,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:21:09.555783Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "06a4daadf1f0417ab22a0295a1272190",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9545,
  "created_at": "2026-07-18T19:20:45.230545Z",
  "faithfulness": 0.9545,
  "flagged_cases": 1,
  "git_sha": "cc2161d8bac2",
  "id": "b31941a3da314df387537d33e2fe6581",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9545,
  "recall_at_k": 0.9545,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T19:19:51.560442Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "63e7509ddd104b269e9a878f8354b7d0",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T19:19:33.428097Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "4703dfc789a1416eb47d1dcb34a9d0b4",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:19:02.995086Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "4a03d5bbe95c49bdbf70df13866da3a8",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:18:36.885667Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "7d5bf9fd28a84ed997e133463db6c64f",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:17:12.879191Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "93269e37bb7b4fb3b14e8b79c56118b2",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T19:16:33.538880Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "4413210098b540d489119c2f488e3bdc",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:16:20.782966Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "75e68395390b4f0f9bf98b51e0767f77",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:15:44.308098Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "da2b127588f14b5d818cb067790634a4",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:14:58.652946Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "8103a968caaf4550a15ba11cbd06959c",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T19:11:57.298838Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "1316292511624f20997c54d98b7238a6",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T19:11:37.400882Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "d191f4f586124b63be96e091bfe7cc68",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:10:41.000555Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "22beb804d943467a8f1597d91ea71b9a",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9545,
  "created_at": "2026-07-18T19:10:02.117207Z",
  "faithfulness": 0.9545,
  "flagged_cases": 1,
  "git_sha": "cc2161d8bac2",
  "id": "a819354437da4d81a1438aca13cfcb67",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9545,
  "recall_at_k": 0.9545,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:09:50.558935Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "accf4c146d2e4a15a76bcdf1d36035ee",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9545,
  "created_at": "2026-07-18T19:09:25.075024Z",
  "faithfulness": 0.9545,
  "flagged_cases": 1,
  "git_sha": "cc2161d8bac2",
  "id": "14e004b8c6e845dfbb1bbcfd5da0ef0d",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9545,
  "recall_at_k": 0.9545,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T19:08:27.041166Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "9acbce9c53004c3e9d71741589bf35e5",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8182,
  "created_at": "2026-07-18T19:08:07.061611Z",
  "faithfulness": 0.8182,
  "flagged_cases": 4,
  "git_sha": "cc2161d8bac2",
  "id": "6462ecbad5934babab836e3c7a616694",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8182,
  "recall_at_k": 0.8182,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:07:35.118760Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "73939e6450244023a35657b6b1688cfb",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:07:01.751685Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "e86200b5cbc8459dbe96dfbafdd3bf7e",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:05:47.828533Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "23287a6809804ef0a03b39f930ceebef",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T19:05:17.078666Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "4c2f9c63131f4920a0a767945efd7414",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:05:06.146583Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "9503122b555c44498c6ff06d28c9e39e",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:04:29.767729Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "8cd4b94a4a284cf5b595ab4867afffc8",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T19:03:30.825200Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "c4a3d365c8cf44eeab4f7a57d655aaa4",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9545,
  "created_at": "2026-07-18T18:47:25.808290Z",
  "faithfulness": 0.9545,
  "flagged_cases": 1,
  "git_sha": "cc2161d8bac2",
  "id": "44f6090620fa43e2b99d8dfa64b81cf9",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9545,
  "recall_at_k": 0.9545,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8182,
  "created_at": "2026-07-18T18:47:05.503356Z",
  "faithfulness": 0.8182,
  "flagged_cases": 4,
  "git_sha": "cc2161d8bac2",
  "id": "201fb300404e4b38bd1b3bdd343effad",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.8182,
  "recall_at_k": 0.8182,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:46:12.963391Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "701c7ab1fa99435a96e9ece29c3c15c5",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9545,
  "created_at": "2026-07-18T18:45:37.994339Z",
  "faithfulness": 0.9545,
  "flagged_cases": 1,
  "git_sha": "cc2161d8bac2",
  "id": "31c96d87736443889413cc940de0b256",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "google:gemini-3.1-flash-lite",
  "precision_at_k": 0.9545,
  "recall_at_k": 0.9545,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:45:27.263047Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "fe74fd8508314dc1946d91c08084432e",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "google:gemini-3.5-flash",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9545,
  "created_at": "2026-07-18T18:45:02.610890Z",
  "faithfulness": 0.9545,
  "flagged_cases": 1,
  "git_sha": "cc2161d8bac2",
  "id": "156b1d31d29f4beea1cb0193a999a764",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "google:gemini-3.1-pro",
  "precision_at_k": 0.9545,
  "recall_at_k": 0.9545,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T18:44:09.583004Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "142ea18144924ef68ac18be899a90fe0",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8182,
  "created_at": "2026-07-18T18:43:53.750337Z",
  "faithfulness": 0.8182,
  "flagged_cases": 4,
  "git_sha": "cc2161d8bac2",
  "id": "f81b89c854d74383ab81fd1d0a501327",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8182,
  "recall_at_k": 0.8182,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:43:21.723932Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "d394311e04064fd199b99e8f19f567ab",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:42:56.080969Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "d950bed240a54c4a9bae3a2589bf9890",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:41:47.117085Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "02fcebe4f93e4b0ab7009f1127ec58db",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T18:41:08.026973Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "55b43994762d44088cc4a982432e8b08",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:40:55.141801Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "3f53dcb566214fcea0da6e7404c59465",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:40:18.540001Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "3146bb17443a4464928710e5f8e7bf23",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:39:28.574957Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "e9a00dce5a86446cacb1bcb211823138",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T18:30:22.905219Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "00626ffc2e0e4af0b148eb2504522f70",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8182,
  "created_at": "2026-07-18T18:29:57.566749Z",
  "faithfulness": 0.8182,
  "flagged_cases": 4,
  "git_sha": "cc2161d8bac2",
  "id": "cc40ed22ad8e445ca044581907ba5c96",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.8182,
  "recall_at_k": 0.8182,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:28:59.886544Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "b6615d4b215f4772ba6fd9c3132790b1",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T18:28:15.199045Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "d676536b16304f31b4768682b55a9e34",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8182,
  "created_at": "2026-07-18T18:28:00.345216Z",
  "faithfulness": 0.8182,
  "flagged_cases": 4,
  "git_sha": "cc2161d8bac2",
  "id": "5b17c335c8714e5db9a472ba5bdab2f9",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8182,
  "recall_at_k": 0.8182,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:27:28.820988Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "5fbc11f510e449889c354061b3ed37a0",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:27:01.804350Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "db6b425274fc4bae8e1473c2068b2912",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:25:45.356761Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "fccc8651e9de4c79917e4ca2fd4eb194",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T18:25:10.186910Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "2d7039ba222d4643bed5f21c1f1cb207",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:24:57.946908Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "64a166f401af42fa9b337419f8118b59",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:24:27.772967Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "ac9542efbe4f45d2af9ed71395d975e6",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:23:49.576456Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "7ef798be15b44583b19a101848908685",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.9091,
  "created_at": "2026-07-18T18:18:25.149646Z",
  "faithfulness": 0.9091,
  "flagged_cases": 2,
  "git_sha": "cc2161d8bac2",
  "id": "0c49a90029e94946bcc7f186890161ea",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4-fast",
  "precision_at_k": 0.9091,
  "recall_at_k": 0.9091,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T18:18:04.823216Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "06f2d8b628574405abcb7e71dce68a9d",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:17:05.278396Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "c44b644b755947ebb3b31635feb8438b",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "xai:grok-4.5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T18:16:24.118378Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "3b3455be2ccf476ca7c6d9e8f3fdb58f",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8182,
  "created_at": "2026-07-18T18:16:04.731557Z",
  "faithfulness": 0.8182,
  "flagged_cases": 4,
  "git_sha": "cc2161d8bac2",
  "id": "da2735924fdd4558a772fb2ad64f7760",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8182,
  "recall_at_k": 0.8182,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:15:32.377145Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "d8347daf22a74be08274140b5bfa7055",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:15:07.929193Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "5b8cb694ed7c460e9859fbadfdf1896a",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:13:47.340029Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "1748c26fe63c485bac60c7a8dcc3ca92",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T18:13:10.917734Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "8eec7df1d30b4a41a794740eacf233aa",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:12:59.537927Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "04ed9222bd894d6c90092e35c49c73e8",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:12:29.585524Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "3706ca135b7047be91907534b2b9743e",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:11:32.957008Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "555812141a864d14a827aba628237969",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T18:10:07.144482Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "ea518489d03f480f8a30517e03ec5bc8",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T18:09:51.818361Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "bae842e7e51d41d2abefcb650ab8fa49",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:09:19.395717Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "585146762d714466a4f72eb0209929ef",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:08:54.461183Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "f96b714e3ccb43929b3449ebde21c8f9",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:07:44.557411Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "92058d45c48646f094ef5a60dcf01869",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T18:07:05.434831Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "f0e0a15c98984a4c8432e8c4e954947e",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:06:54.975261Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "2eb1b5531d0a4292987426c1473267dc",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:06:25.801103Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "7405e5f2003a4fef9899dbb8d9424d6b",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T18:05:34.797748Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "add136342008406ab5e5000351e260fc",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T17:29:18.207603Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "b2b383b6872f450e98a3afe97556ebe3",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T17:28:58.276559Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "512e103ae68c42669d1483051963af92",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T17:28:23.537957Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "b76af64806954b64922259de8b838091",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T17:27:58.722058Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "f95fb55ff74849f6aed4057a566ad543",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T17:26:42.868531Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "69e9981c72cf45849e3a4090528b7865",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T17:26:00.364409Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "44f938579ec14a7e8f1a10b60e054b78",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T17:25:44.955004Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "2f63ee0e90a74359ac36272a4f9bbe33",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T17:25:05.554146Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "0c9e80c15712494c82616e81d57e17b4",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T17:24:18.031632Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "f6599ca8076140f28d65db40b1f6ed6b",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T10:17:09.425174Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "11d243472d1c44bf9bed152254bc931f",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8182,
  "created_at": "2026-07-18T10:16:44.133179Z",
  "faithfulness": 0.8182,
  "flagged_cases": 4,
  "git_sha": "cc2161d8bac2",
  "id": "3d7f7386c3414c00805b74c1ec8b2cc7",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8182,
  "recall_at_k": 0.8182,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T10:16:12.278305Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "56049937a32044a0905826e283958d70",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T10:15:39.982401Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "22da04b6695f4537b207d57b24696b83",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T10:14:25.164743Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "78f6047a67f249e7b03b40c54d644d95",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T10:13:38.657184Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "0d5fc7599f44459b926f15c2f0606e2e",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T10:13:20.661688Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "04612410567d46d990e755f9dea3e9c4",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T10:12:50.028940Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "c6d52b82bcbc4cdf9dec1d34b69dd19e",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T10:11:58.798944Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "ec6b903b320b4b2fb6bcf0d1bea50186",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T09:55:44.850186Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "e3b8ec80dba647edabd605272f6eca90",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8182,
  "created_at": "2026-07-18T09:55:26.467074Z",
  "faithfulness": 0.8182,
  "flagged_cases": 4,
  "git_sha": "cc2161d8bac2",
  "id": "20d527849f5041508a99ea2a212a2913",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8182,
  "recall_at_k": 0.8182,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:54:53.405212Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "44d1ef8279924a769b8c568a6aeeeae3",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:54:27.312224Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "e86dfe0c70d5496085acbf632974a30c",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:53:04.489481Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "3f691699fff442f8a7540d9661026528",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T09:52:28.483323Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "403478b12ca84a07979e12ae9530e158",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:52:16.652885Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "c7c00606c9c140f99c91e34fc24deee7",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:51:39.140307Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "d450945b1778446d924676b952f10d7a",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:50:50.767046Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "65f7b6fcc64747dfb68d075c89b49196",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T09:22:48.372877Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "88552acc294647418c412e38790bc81a",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T09:22:29.613934Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "702d094247db4029be76dab56050e3f0",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:21:53.128560Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "df7a347013fb4f5a99e05f437e7df257",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:21:29.043364Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "247d1d578fd345f78e22581def4fb668",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:20:16.261077Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "0979014a8fda4c3bb91f3778fae527cd",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T09:19:38.014792Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "322bc10c336e46d0825518f9f5547233",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:19:27.629508Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "bf50edf76c294099b897728d57b859cc",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:18:57.861636Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "b872f64177514aaabb75cd0c0f8f2cde",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:18:07.002178Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "f92e176fd90d46e6bc8479b2940a045c",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T09:13:44.088840Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "34a3b1caba5541b684a0336a4b568ea1",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T09:13:25.875765Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "2d7973be3a7b48f1a01dca9c44f1478b",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:12:55.011813Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "dcb526ecd8f54180befa79d7aa58985b",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:12:26.435590Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "628a93e01e394fe695667b46eae14ea1",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:11:14.651029Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "10f8e9f1616f4adcb86e2fe19d2d3971",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T09:10:44.744418Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "c33816eac25b40cd93dd277153964aa8",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:10:32.540623Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "fc66a8ef0858433c84bd12d8e0d37c2a",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:10:03.345894Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "61e94b53eff84a44bc1697f6da7291cf",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:09:11.403397Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "f364ee05730c44ee8dcb622eb0ac517a",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T09:07:12.016933Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "cb47872b70794a168e80c92a947bc9e6",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8182,
  "created_at": "2026-07-18T09:06:53.349713Z",
  "faithfulness": 0.8182,
  "flagged_cases": 4,
  "git_sha": "cc2161d8bac2",
  "id": "9936b9c0fe7b4ac9ae6bf27effc6fcd2",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8182,
  "recall_at_k": 0.8182,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:06:22.250716Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "b03296a2db1c44f8ad7845190f66bb97",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:05:43.815242Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "1d5e663a0ca0433b9fe102b0715b2344",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:04:25.258926Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "4c690a3e8bcb47729ad79a15790c7e28",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T09:03:53.163936Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "db40673db6574d2ba6f41842448149a0",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:03:39.807199Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "870ce3026dfa4acc84b2eb0f1b701106",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:03:05.390505Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "a0ac3b5f1008458083aba87428c0f98a",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T09:02:15.256957Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "8550de60e09b4a33927d07a3c4ce0463",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:56:58.849685Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "8a794ec461e145c1b381070f8db313c8",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "xai:grok-4.1-fast",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:56:56.071944Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "3e76f921a565413b936be0180716899b",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:56:53.345662Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "27186ed21b93422381dd5ab2e9c043be",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:56:50.634040Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "e2e8cc9617de41e6a47fbbb7187cd511",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "xai:grok-4-heavy",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:56:48.132861Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "ca4c7c9867a04ab2925e9791368d0f3d",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "google:gemini-2.5-flash-lite",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:56:44.779402Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "21439f1f68bc40bf9f9a86bf3064e0cf",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "google:gemini-2.5-flash",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:56:41.518151Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "6d87ad746b914bd7ae5e0cf32f0ce24e",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "google:gemini-2.5-pro",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T08:56:37.626450Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "e0da68e8c9b2466e941bee5950ef0338",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T08:56:16.831991Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "e4822100013949c09f7bac1ddab98a21",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:55:44.131954Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "42ad99d83741404eaa5bdc03cdc7d395",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:55:18.540931Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "b44fed5b6dc0428fbdc33b3706a2a2b8",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:53:56.190965Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "3996560159d5412fa43ffa3d25b91251",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T08:53:27.477142Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "d003ad09eba346f5b2427d62974e0726",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:53:15.732140Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "0267a565af274f2b95a243207f84732a",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:52:42.718987Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "71be60b5cb1a418195a88bc9b4a6cd90",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:51:50.435253Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "2939c4a5a9004aa99034da18df155f51",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:50:49.585432Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "1487b4177a514dc1bf31da8ebb525c7e",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "xai:grok-4.1-fast",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:50:47.932417Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "e2f974708432455c8242af0001879281",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:50:46.049710Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "0cb64438894546d9872b780eed391c09",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:50:43.911886Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "8c3d4b4aa1c84e18aedca63adbf5a9a1",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "xai:grok-4-heavy",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:50:42.045539Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "7671d6ef9e6d4ad5af2051b284d2c0d1",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "google:gemini-2.5-flash-lite",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:50:39.794167Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "bc21aa58a7ea4aecb8fe607003a21df1",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "google:gemini-2.5-flash",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:50:37.404666Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "436509bc29bb41bfa4ce3a887670e5ff",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "google:gemini-2.5-pro",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T08:50:34.625945Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "5214a9b066f94072957680b012fd176f",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T08:50:17.447558Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "d023aa2ef91b4575ae027c1e9f056e6f",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:49:45.977009Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "efcbe4d93bfa4ec69acab66034ff6c42",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:49:18.019478Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "c7299bf0e1ec4c65b73b05cf5e24adb3",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:48:03.300865Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "f9de1ae9871e47c38968c1ae90712ef7",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T08:47:31.520472Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "e8d5feeede314bccaf436800c7929bda",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:47:14.687305Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "2b5f84b842824cc8ad813895f1a2091a",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:46:39.901781Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "feb952d2a2984ea496ffef0da1e4336c",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:45:43.619030Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "51eaf62b37c04608b24958392471c2ec",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:40:16.550410Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "92704ecf974d4fedbc5b35391f8faf0c",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "xai:grok-4.1-fast",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:40:14.181866Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "e2f59a8b12244f44a4fd7b20d0863280",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "xai:grok-4.3",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:40:12.097798Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "f08c56c98ea941669f1fd7916dfec36a",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "xai:grok-4.5",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:40:09.894330Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "d312b7b1788f44d1afa361d44c1ab487",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "xai:grok-4-heavy",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:40:07.618855Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "fb707e22cfbc4c00a45b45d28443f534",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "google:gemini-2.5-flash-lite",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:40:04.509653Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "2313f1304345485d91f32e64e987214d",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "google:gemini-2.5-flash",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.0,
  "created_at": "2026-07-18T08:40:01.369481Z",
  "faithfulness": 0.0,
  "flagged_cases": 22,
  "git_sha": "cc2161d8bac2",
  "id": "82229eaff2bc44e5a06915b2f273ff43",
  "label": "suite 2026-07-v2 \u00b7 22 provider error(s)",
  "n_cases": 22,
  "name": "google:gemini-2.5-pro",
  "precision_at_k": 0.0,
  "recall_at_k": 0.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T08:39:57.930487Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "5a254324b1d64d1d8c4d6b5b1d02e4cf",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-haiku-4-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.8636,
  "created_at": "2026-07-18T08:39:39.752063Z",
  "faithfulness": 0.8636,
  "flagged_cases": 3,
  "git_sha": "cc2161d8bac2",
  "id": "89ebf11a5e8f4c4c99e6e4bd3164a1db",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-sonnet-5",
  "precision_at_k": 0.8636,
  "recall_at_k": 0.8636,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:39:03.141761Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "1b29642459b64eec8f25c7d7df3a79e8",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-opus-4-8",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:38:28.206668Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "f988e73558be4d32bc446359afa0b119",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "anthropic:claude-fable-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:37:06.356763Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "a4044a934caa4ca48e8f064b2c398c73",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-nano",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 0.7727,
  "created_at": "2026-07-18T08:36:24.846787Z",
  "faithfulness": 0.7727,
  "flagged_cases": 5,
  "git_sha": "cc2161d8bac2",
  "id": "0443f563da554958ab811b2cd1f2f1fa",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-4o-mini",
  "precision_at_k": 0.7727,
  "recall_at_k": 0.7727,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:36:10.224999Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "366956e7f65f4542bb55c7275988685b",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5-mini",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:35:22.764321Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "80debe07893e4c7a9699ea726c3c9f68",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "openai:gpt-5",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T08:34:30.664166Z",
  "faithfulness": 1.0,
  "flagged_cases": 0,
  "git_sha": "cc2161d8bac2",
  "id": "3fedf194f3304cb2a0d2db04b01917ff",
  "label": "suite 2026-07-v2",
  "n_cases": 22,
  "name": "mock:stable",
  "precision_at_k": 1.0,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T05:23:00.369155Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "b9367c0",
  "id": "cbf300b74294487d8f89bf91e1167c4e",
  "label": "Dogfood prompt-regress: gate this repo's own PRs",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-18T04:57:13.553871Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "85ed4c3",
  "id": "f0df75781d5e4424ab8bc2ca24026fd2",
  "label": "Add BM25, hybrid, and a reranker \u2014 and report what actually helped",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-17T06:34:03.750033Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "a5d48b3",
  "id": "dc5cf00fcb0d44149e0a594d1ea9fd44",
  "label": "Measure the retriever on SciFact: nDCG@10 = 0.581",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-17T06:01:32.599884Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "0b0b3d3",
  "id": "95c927a46d324998a25046d597a900f3",
  "label": "Build the image, don't just ship a Dockerfile",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-17T05:16:02.168224Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "f5bf5b1",
  "id": "5b28f9c336904f6ab625b620cb1f2008",
  "label": "Let a run be re-recorded without inventing a commit",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-17T04:12:10.440311Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "f5bf5b1",
  "id": "12d80ba9a4594c5087db6945fb5b0091",
  "label": "Let a run be re-recorded without inventing a commit",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.25,
  "recall_at_k": 1.0,
  "source": "ci",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-17T02:57:39.578127Z",
  "faithfulness": 0.889,
  "flagged_cases": 1,
  "git_sha": "352896d",
  "id": "2a95eaada39c453d9920f2ab4fd50391",
  "label": "retrieval k=2 (candidate)",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.5,
  "recall_at_k": 1.0,
  "source": "ablation",
  "vulnerability_score": null
 },
 {
  "citation_rate": 1.0,
  "created_at": "2026-07-17T02:57:37.629275Z",
  "faithfulness": 0.917,
  "flagged_cases": 1,
  "git_sha": "352896d",
  "id": "d800b9a8d3284240bd536bb63fa5f2da",
  "label": "retrieval k=3 (baseline)",
  "n_cases": 6,
  "name": "rag-eval-lab",
  "precision_at_k": 0.333,
  "recall_at_k": 1.0,
  "source": "ablation",
  "vulnerability_score": null
 }
]
