{
  "schema_version": 1,
  "run_id": "20261024-v4",
  "protocol_hash": "3e5f296a6fbc3efffcb6ede48283b2834b500dbc8be1fae8785e3431a0384dd7",
  "generated_at": "2026-10-24T03:33:49.349621+00:00",
  "dataset": {
    "name": "SimpleQA Verified",
    "revision": "0dc97e0d28d8233463e005cdc4475cc2a13ba2dc",
    "source": "https://huggingface.co/datasets/google/simpleqa-verified/resolve/0dc97e0d28d8233463e005cdc4475cc2a13ba2dc/simpleqa_verified.csv",
    "source_sha256": "b5db21155444763543fe31b67e7cf28ce2bb225742a5b889421c5f182e2f92f5",
    "license": "MIT",
    "full_size": 1000,
    "sampling": "proportional topic-stratified; largest remainder; fixed seed"
  },
  "n": 300,
  "reader_model": "deepseek-flash",
  "judge_model": "deepseek-flash",
  "profiles": [
    {
      "id": "searchpipe-basic",
      "label": "SearchPipe Basic",
      "provider": "searchpipe",
      "status": "complete",
      "n": 300,
      "collected": 300,
      "graded": 300,
      "correct": 97,
      "accuracy": 0.3233333333333333,
      "accuracy_ci95": [
        0.2729253960837475,
        0.37820845374892526
      ],
      "labels": {
        "CORRECT": 97,
        "NOT_ATTEMPTED": 197,
        "INCORRECT": 6
      },
      "errors": 0,
      "success_rate": 1.0,
      "empty_results": 58,
      "mean_results": 6.183333333333334,
      "p50_ms": 2370.535,
      "p95_ms": 5871.262500000001,
      "price_per_1000_usd": 5.0,
      "cached": 0,
      "attempted_answers": 103,
      "literal_quote_matches": 101
    },
    {
      "id": "searchpipe-advanced",
      "label": "SearchPipe Advanced",
      "provider": "searchpipe",
      "status": "complete",
      "n": 300,
      "collected": 300,
      "graded": 300,
      "correct": 98,
      "accuracy": 0.32666666666666666,
      "accuracy_ci95": [
        0.2760784389482685,
        0.3816377910762407
      ],
      "labels": {
        "CORRECT": 98,
        "NOT_ATTEMPTED": 198,
        "INCORRECT": 4
      },
      "errors": 0,
      "success_rate": 1.0,
      "empty_results": 57,
      "mean_results": 6.1866666666666665,
      "p50_ms": 2388.885,
      "p95_ms": 5564.912000000001,
      "price_per_1000_usd": 10.0,
      "cached": 0,
      "attempted_answers": 102,
      "literal_quote_matches": 100
    },
    {
      "id": "tavily-basic",
      "label": "Tavily Basic",
      "provider": "tavily",
      "status": "complete",
      "n": 300,
      "collected": 300,
      "graded": 300,
      "correct": 252,
      "accuracy": 0.84,
      "accuracy_ci95": [
        0.7942563251514081,
        0.8771464544159004
      ],
      "labels": {
        "CORRECT": 252,
        "NOT_ATTEMPTED": 45,
        "INCORRECT": 3
      },
      "errors": 18,
      "success_rate": 0.94,
      "empty_results": 0,
      "mean_results": 9.26,
      "p50_ms": 2185.5150000000003,
      "p95_ms": 3997.6614999999993,
      "price_per_1000_usd": 8.0,
      "cached": 0,
      "attempted_answers": 255,
      "literal_quote_matches": 246
    },
    {
      "id": "tavily-advanced",
      "label": "Tavily Advanced",
      "provider": "tavily",
      "status": "complete",
      "n": 300,
      "collected": 300,
      "graded": 300,
      "correct": 262,
      "accuracy": 0.8733333333333333,
      "accuracy_ci95": [
        0.8309188299507383,
        0.9063077515349339
      ],
      "labels": {
        "CORRECT": 262,
        "NOT_ATTEMPTED": 36,
        "INCORRECT": 2
      },
      "errors": 18,
      "success_rate": 0.94,
      "empty_results": 0,
      "mean_results": 9.4,
      "p50_ms": 4754.44,
      "p95_ms": 6601.873500000001,
      "price_per_1000_usd": 16.0,
      "cached": 0,
      "attempted_answers": 264,
      "literal_quote_matches": 245
    },
    {
      "id": "exa-auto",
      "label": "Exa Auto",
      "provider": "exa",
      "status": "complete",
      "n": 300,
      "collected": 300,
      "graded": 300,
      "correct": 291,
      "accuracy": 0.97,
      "accuracy_ci95": [
        0.9439774608583589,
        0.9841381461905676
      ],
      "labels": {
        "CORRECT": 291,
        "NOT_ATTEMPTED": 8,
        "INCORRECT": 1
      },
      "errors": 0,
      "success_rate": 1.0,
      "empty_results": 0,
      "mean_results": 9.98,
      "p50_ms": 2231.5,
      "p95_ms": 3476.321500000001,
      "price_per_1000_usd": 7.0,
      "cached": 0,
      "attempted_answers": 292,
      "literal_quote_matches": 277
    },
    {
      "id": "parallel-fast",
      "label": "Parallel Fast",
      "provider": "parallel",
      "status": "complete",
      "n": 300,
      "collected": 300,
      "graded": 300,
      "correct": 281,
      "accuracy": 0.9366666666666666,
      "accuracy_ci95": [
        0.9032086875144784,
        0.9590831176160847
      ],
      "labels": {
        "CORRECT": 281,
        "NOT_ATTEMPTED": 16,
        "INCORRECT": 3
      },
      "errors": 0,
      "success_rate": 1.0,
      "empty_results": 0,
      "mean_results": 10.0,
      "p50_ms": 1384.115,
      "p95_ms": 2081.4695,
      "price_per_1000_usd": 1.0,
      "cached": 0,
      "attempted_answers": 284,
      "literal_quote_matches": 162
    }
  ],
  "paired_comparisons": [
    {
      "left": "searchpipe-basic",
      "right": "searchpipe-advanced",
      "difference": -0.0033333333333333335,
      "ci95": [
        -0.01,
        0.0
      ]
    },
    {
      "left": "searchpipe-basic",
      "right": "tavily-basic",
      "difference": -0.5166666666666667,
      "ci95": [
        -0.58,
        -0.45
      ]
    },
    {
      "left": "searchpipe-basic",
      "right": "tavily-advanced",
      "difference": -0.55,
      "ci95": [
        -0.61,
        -0.48333333333333334
      ]
    },
    {
      "left": "searchpipe-basic",
      "right": "exa-auto",
      "difference": -0.6466666666666666,
      "ci95": [
        -0.7,
        -0.5933333333333334
      ]
    },
    {
      "left": "searchpipe-basic",
      "right": "parallel-fast",
      "difference": -0.6133333333333333,
      "ci95": [
        -0.6666666666666666,
        -0.56
      ]
    },
    {
      "left": "searchpipe-advanced",
      "right": "tavily-basic",
      "difference": -0.5133333333333333,
      "ci95": [
        -0.5766666666666667,
        -0.44666666666666666
      ]
    },
    {
      "left": "searchpipe-advanced",
      "right": "tavily-advanced",
      "difference": -0.5466666666666666,
      "ci95": [
        -0.6066666666666667,
        -0.48
      ]
    },
    {
      "left": "searchpipe-advanced",
      "right": "exa-auto",
      "difference": -0.6433333333333333,
      "ci95": [
        -0.6966666666666667,
        -0.59
      ]
    },
    {
      "left": "searchpipe-advanced",
      "right": "parallel-fast",
      "difference": -0.61,
      "ci95": [
        -0.6633333333333333,
        -0.5566666666666666
      ]
    },
    {
      "left": "tavily-basic",
      "right": "tavily-advanced",
      "difference": -0.03333333333333333,
      "ci95": [
        -0.06333333333333334,
        -0.0033333333333333335
      ]
    },
    {
      "left": "tavily-basic",
      "right": "exa-auto",
      "difference": -0.13,
      "ci95": [
        -0.17333333333333334,
        -0.09
      ]
    },
    {
      "left": "tavily-basic",
      "right": "parallel-fast",
      "difference": -0.09666666666666666,
      "ci95": [
        -0.14333333333333334,
        -0.05
      ]
    },
    {
      "left": "tavily-advanced",
      "right": "exa-auto",
      "difference": -0.09666666666666666,
      "ci95": [
        -0.13666666666666666,
        -0.056666666666666664
      ]
    },
    {
      "left": "tavily-advanced",
      "right": "parallel-fast",
      "difference": -0.06333333333333334,
      "ci95": [
        -0.10666666666666667,
        -0.02
      ]
    },
    {
      "left": "exa-auto",
      "right": "parallel-fast",
      "difference": 0.03333333333333333,
      "ci95": [
        0.006666666666666667,
        0.06
      ]
    }
  ],
  "complete": true,
  "method": {
    "search_calls_per_question": 1,
    "top_k": 10,
    "per_document_utf8_bytes": 2400,
    "total_content_utf8_bytes": 18000,
    "timeout_seconds": 90,
    "attempts": 2,
    "retry_statuses": [
      429,
      500,
      502,
      503,
      504
    ],
    "pace_seconds": 1.2,
    "max_collection_window_hours": 24,
    "failure_denominator": "all frozen questions",
    "metric": "semantic final-answer accuracy with a shared search-only reader",
    "latency": "end-to-end search including retries/backoff, successful queries only; public endpoints; observed cache state",
    "pricing_date": "2026-10-24",
    "budget_usd": 40,
    "limitations": [
      "Not the official closed-book SimpleQA Verified evaluation.",
      "Not comparable with other publishers historical scores.",
      "Byte-bounded returned text; no extra fetches or multi-turn agent.",
      "SearchPipe organizes and participates in this evaluation."
    ],
    "quote_policy": "literal quote provenance is diagnostic only; it never overrides the semantic answer grade"
  },
  "source": "SearchPipe-run evaluation; no imported vendor scores",
  "budget": {
    "limit_usd": 40,
    "accounted_usd": 20.143257000000002,
    "basis": "conservative billable ceilings on uncertain calls; SearchPipe at retail price; free credits not deducted"
  },
  "availability": {
    "searchpipe-basic": true,
    "searchpipe-advanced": true,
    "tavily-basic": true,
    "tavily-advanced": true,
    "exa-auto": true,
    "parallel-fast": true
  },
  "audit": {
    "protocol_hash": "3e5f296a6fbc3efffcb6ede48283b2834b500dbc8be1fae8785e3431a0384dd7",
    "status": "reviewed",
    "reviewer": "Codex (provider-blind AI reference-consistency spot-check; not human verification)",
    "reviewed_count": 180,
    "sample_per_profile": 30,
    "agreement_count": 180,
    "agreement_rate": 1.0,
    "items": [
      {
        "audit_id": "0219054a786240bc",
        "grade": "CORRECT"
      },
      {
        "audit_id": "02fe8f25a1347d5a",
        "grade": "CORRECT"
      },
      {
        "audit_id": "0320e8e65bfb532e",
        "grade": "CORRECT"
      },
      {
        "audit_id": "044ac5f0d5cd1e0c",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "054058f7bf318084",
        "grade": "CORRECT"
      },
      {
        "audit_id": "06369f70328d768c",
        "grade": "CORRECT"
      },
      {
        "audit_id": "07564bad7bbc0d6a",
        "grade": "CORRECT"
      },
      {
        "audit_id": "078c18ed71b911bb",
        "grade": "CORRECT"
      },
      {
        "audit_id": "091b015735f75a1f",
        "grade": "CORRECT"
      },
      {
        "audit_id": "0a6cf17f5ea3252c",
        "grade": "CORRECT"
      },
      {
        "audit_id": "0b99e2d50e9706f4",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "0d888e72b75e98d0",
        "grade": "CORRECT"
      },
      {
        "audit_id": "0da3a2bc0984b091",
        "grade": "CORRECT"
      },
      {
        "audit_id": "1083100ff7c0a15f",
        "grade": "CORRECT"
      },
      {
        "audit_id": "1103299dae5630ce",
        "grade": "CORRECT"
      },
      {
        "audit_id": "12ef969baf71321d",
        "grade": "CORRECT"
      },
      {
        "audit_id": "134dca3e58fe9845",
        "grade": "CORRECT"
      },
      {
        "audit_id": "158a76f1d9b20f94",
        "grade": "CORRECT"
      },
      {
        "audit_id": "16757ca8cb077d19",
        "grade": "CORRECT"
      },
      {
        "audit_id": "178c1c34c792f09e",
        "grade": "CORRECT"
      },
      {
        "audit_id": "19bd39e96bf8c540",
        "grade": "CORRECT"
      },
      {
        "audit_id": "1a1edbca5fdadaca",
        "grade": "CORRECT"
      },
      {
        "audit_id": "1a20c3ac74aea2da",
        "grade": "CORRECT"
      },
      {
        "audit_id": "1b222cd75495d86c",
        "grade": "CORRECT"
      },
      {
        "audit_id": "1b4ddd822feaa949",
        "grade": "CORRECT"
      },
      {
        "audit_id": "1d483bd89af8d394",
        "grade": "CORRECT"
      },
      {
        "audit_id": "20478329692c25ac",
        "grade": "CORRECT"
      },
      {
        "audit_id": "224efb2d404aeb93",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "23c37f0556865e35",
        "grade": "CORRECT"
      },
      {
        "audit_id": "276b642c83c83518",
        "grade": "CORRECT"
      },
      {
        "audit_id": "277b960281b3a55a",
        "grade": "CORRECT"
      },
      {
        "audit_id": "2bedd8f75bb589bd",
        "grade": "CORRECT"
      },
      {
        "audit_id": "2c0276f388e627fb",
        "grade": "CORRECT"
      },
      {
        "audit_id": "2d4d536012a55efb",
        "grade": "CORRECT"
      },
      {
        "audit_id": "2d879a9ecb59d01b",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "31c47e8bf8af7546",
        "grade": "CORRECT"
      },
      {
        "audit_id": "354e82b4e20c2312",
        "grade": "CORRECT"
      },
      {
        "audit_id": "35b81f0190cd6061",
        "grade": "CORRECT"
      },
      {
        "audit_id": "37fe978ec48cfd8a",
        "grade": "CORRECT"
      },
      {
        "audit_id": "384ec938eadb8269",
        "grade": "CORRECT"
      },
      {
        "audit_id": "3912318a68998a1d",
        "grade": "CORRECT"
      },
      {
        "audit_id": "3a8c6fcc88c82cf8",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "3ac05f4bbcdb322f",
        "grade": "CORRECT"
      },
      {
        "audit_id": "3e07e7e3a0e91429",
        "grade": "CORRECT"
      },
      {
        "audit_id": "3e3d8168e7c257f7",
        "grade": "CORRECT"
      },
      {
        "audit_id": "40838943cb9ebe02",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "40b89ec691bacb8a",
        "grade": "CORRECT"
      },
      {
        "audit_id": "41bb8167f96ad9ed",
        "grade": "CORRECT"
      },
      {
        "audit_id": "445f34bc7a9174e6",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "44a5a387e1984862",
        "grade": "CORRECT"
      },
      {
        "audit_id": "4a44b272e76f1f29",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "4ac0c4b2559affec",
        "grade": "CORRECT"
      },
      {
        "audit_id": "4b7bf28aade5597f",
        "grade": "CORRECT"
      },
      {
        "audit_id": "4cdd7016960143f3",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "4ce1dc054f218602",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "50f3e144ff5ab771",
        "grade": "CORRECT"
      },
      {
        "audit_id": "51bee105e4d594d6",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "53a6fb62e722c72b",
        "grade": "CORRECT"
      },
      {
        "audit_id": "548d2f2f4b1cadfc",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "57273b4460454c0e",
        "grade": "CORRECT"
      },
      {
        "audit_id": "5908408d8d5880f4",
        "grade": "CORRECT"
      },
      {
        "audit_id": "5b10160dd25a617b",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "5c4a9e8cffd608f0",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "5dcb7a245c4c6b96",
        "grade": "CORRECT"
      },
      {
        "audit_id": "5f41e382c664b3e4",
        "grade": "CORRECT"
      },
      {
        "audit_id": "5fb5be3d143f800a",
        "grade": "CORRECT"
      },
      {
        "audit_id": "61f3f6c845566dc9",
        "grade": "CORRECT"
      },
      {
        "audit_id": "6316d461b9d6d565",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "633de377a2bb62d4",
        "grade": "CORRECT"
      },
      {
        "audit_id": "66771d9f2c4dd27d",
        "grade": "CORRECT"
      },
      {
        "audit_id": "698f8277d41d37ef",
        "grade": "INCORRECT"
      },
      {
        "audit_id": "69a6a7e129cbf631",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "6a7eea2a13814cac",
        "grade": "CORRECT"
      },
      {
        "audit_id": "6c93fd183110cfd9",
        "grade": "CORRECT"
      },
      {
        "audit_id": "6ccdae1e00960e79",
        "grade": "CORRECT"
      },
      {
        "audit_id": "6dfd713fb18a0c25",
        "grade": "CORRECT"
      },
      {
        "audit_id": "6e08f106f9351361",
        "grade": "CORRECT"
      },
      {
        "audit_id": "70b06af27b55e342",
        "grade": "CORRECT"
      },
      {
        "audit_id": "718b3b99ca61131a",
        "grade": "CORRECT"
      },
      {
        "audit_id": "71d6a12ac7d87727",
        "grade": "CORRECT"
      },
      {
        "audit_id": "724d8dad9df43bbd",
        "grade": "CORRECT"
      },
      {
        "audit_id": "73a1dbaa18fb22d2",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "74c8af9d59bfc417",
        "grade": "CORRECT"
      },
      {
        "audit_id": "751e14a55effd43c",
        "grade": "CORRECT"
      },
      {
        "audit_id": "7551833a1ca1cc23",
        "grade": "CORRECT"
      },
      {
        "audit_id": "7555d2dd4a440923",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "759b743ef6c7a690",
        "grade": "CORRECT"
      },
      {
        "audit_id": "75f2ae2d14f044d0",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "76a2432bd57cea9f",
        "grade": "CORRECT"
      },
      {
        "audit_id": "79aed029181b83f4",
        "grade": "CORRECT"
      },
      {
        "audit_id": "79b4c4b77b109a6e",
        "grade": "CORRECT"
      },
      {
        "audit_id": "7a4c898dfa02d842",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "7a9a7880ffff7dd4",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "7bcf9c0de4eed31f",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "7d4aacc96f7fedf8",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "7d5acca576aafdea",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "7e21f754417cde38",
        "grade": "CORRECT"
      },
      {
        "audit_id": "7ee4d639af601e41",
        "grade": "CORRECT"
      },
      {
        "audit_id": "7f276e1128a57e07",
        "grade": "CORRECT"
      },
      {
        "audit_id": "802dd0aab88f6946",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "8098cf73086ba687",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "844ab52ea25a6300",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "8497d01bee56a555",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "84e84e36c1b22e9b",
        "grade": "CORRECT"
      },
      {
        "audit_id": "86fd2964b7e7458c",
        "grade": "CORRECT"
      },
      {
        "audit_id": "87a9dece84330867",
        "grade": "CORRECT"
      },
      {
        "audit_id": "8963ca327aff0d63",
        "grade": "CORRECT"
      },
      {
        "audit_id": "8abbf955a536a0db",
        "grade": "CORRECT"
      },
      {
        "audit_id": "8c2c759cddcba79f",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "8e3ad3b5b28d7edf",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "90289df36a8632d3",
        "grade": "CORRECT"
      },
      {
        "audit_id": "902ab7c9d6317718",
        "grade": "CORRECT"
      },
      {
        "audit_id": "9233144fcd3299f5",
        "grade": "INCORRECT"
      },
      {
        "audit_id": "94822ccbaa4279c2",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "95517fb9ca1a7d15",
        "grade": "CORRECT"
      },
      {
        "audit_id": "96decdc6e674090d",
        "grade": "CORRECT"
      },
      {
        "audit_id": "96fd90316c3782a0",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "99dda2d12af6b2df",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "9c0f3a14ee0602e9",
        "grade": "CORRECT"
      },
      {
        "audit_id": "9fd6a88c8cf939d7",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "a059d769a1147591",
        "grade": "CORRECT"
      },
      {
        "audit_id": "a1bd460bc83fdefd",
        "grade": "CORRECT"
      },
      {
        "audit_id": "a20ad5bcefab0de0",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "a45fe87b16686dcd",
        "grade": "CORRECT"
      },
      {
        "audit_id": "a4c34e842081e394",
        "grade": "CORRECT"
      },
      {
        "audit_id": "a6757e33c3b8a8e7",
        "grade": "CORRECT"
      },
      {
        "audit_id": "a6d2ed32846fe953",
        "grade": "CORRECT"
      },
      {
        "audit_id": "a73f0680457e0f08",
        "grade": "CORRECT"
      },
      {
        "audit_id": "a8dfc108fdd63c15",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "ad463d9730fba81e",
        "grade": "CORRECT"
      },
      {
        "audit_id": "af5f0a834bb628d2",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "b15b90598317fa3a",
        "grade": "CORRECT"
      },
      {
        "audit_id": "b3027fd1adc9fa12",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "b6fa338c8ebc0bba",
        "grade": "CORRECT"
      },
      {
        "audit_id": "b9dbde7becce43a6",
        "grade": "CORRECT"
      },
      {
        "audit_id": "be470ddb729d04c5",
        "grade": "CORRECT"
      },
      {
        "audit_id": "bff4b0d471bc531f",
        "grade": "CORRECT"
      },
      {
        "audit_id": "c130a72102fc132a",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "c17ccbcdc3e2aebd",
        "grade": "CORRECT"
      },
      {
        "audit_id": "c19e9da8ad886e9b",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "c212f3bacbbafa57",
        "grade": "CORRECT"
      },
      {
        "audit_id": "c29737402fab13d4",
        "grade": "CORRECT"
      },
      {
        "audit_id": "c414ebd5feed5866",
        "grade": "CORRECT"
      },
      {
        "audit_id": "c4658f7ce05f8f69",
        "grade": "CORRECT"
      },
      {
        "audit_id": "c55c2c91cd6c17e9",
        "grade": "CORRECT"
      },
      {
        "audit_id": "c9b73c8b825988ba",
        "grade": "CORRECT"
      },
      {
        "audit_id": "cb8973987bd315e7",
        "grade": "CORRECT"
      },
      {
        "audit_id": "cc54fbb77339f6cc",
        "grade": "CORRECT"
      },
      {
        "audit_id": "cf99f09f7b16a09d",
        "grade": "CORRECT"
      },
      {
        "audit_id": "d19c63511ea023da",
        "grade": "CORRECT"
      },
      {
        "audit_id": "d1d7266e862504a1",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "d1f30de7d0c75649",
        "grade": "CORRECT"
      },
      {
        "audit_id": "d34fe1f0cc1a17ca",
        "grade": "CORRECT"
      },
      {
        "audit_id": "d3ead11bd0ce8813",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "d4ba8307f78fe3c9",
        "grade": "CORRECT"
      },
      {
        "audit_id": "d5e67d28183e4e4c",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "d8eeae94eb71d44f",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "d95361834bedf21c",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "db17a65f5b13e810",
        "grade": "CORRECT"
      },
      {
        "audit_id": "db895667c6c7aa15",
        "grade": "CORRECT"
      },
      {
        "audit_id": "dd977f034662dff4",
        "grade": "CORRECT"
      },
      {
        "audit_id": "de1ab7bff8250409",
        "grade": "CORRECT"
      },
      {
        "audit_id": "dead3a7ee881843a",
        "grade": "CORRECT"
      },
      {
        "audit_id": "dfa0e8a741b8f539",
        "grade": "CORRECT"
      },
      {
        "audit_id": "e0bebd9b324cd62b",
        "grade": "CORRECT"
      },
      {
        "audit_id": "e16f1e8446e8ab80",
        "grade": "CORRECT"
      },
      {
        "audit_id": "e21a709c13e507fa",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "e44cc4ea32ae30f5",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "e868fb0bde9e5907",
        "grade": "CORRECT"
      },
      {
        "audit_id": "ed858dbed3afffc5",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "f20ca64827222542",
        "grade": "CORRECT"
      },
      {
        "audit_id": "f3be57912d0140de",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "f3e6509d93412627",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "f5bbf405f63998a7",
        "grade": "CORRECT"
      },
      {
        "audit_id": "f612d2bc74fe5035",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "f774fb0c212de01f",
        "grade": "CORRECT"
      },
      {
        "audit_id": "f855e3fac4a26e37",
        "grade": "CORRECT"
      },
      {
        "audit_id": "f983a0b1d8e745dc",
        "grade": "CORRECT"
      },
      {
        "audit_id": "f9dcb41bc7f5ae6d",
        "grade": "NOT_ATTEMPTED"
      },
      {
        "audit_id": "ff8c43b73979961e",
        "grade": "CORRECT"
      }
    ],
    "disagreements": [],
    "notes": [
      "Provider names and primary grades hidden during review. Primary grades unchanged after spot-check.",
      "A sampled result reproduced benchmark reference wording; public benchmark mirrors can affect retrieval. This run applies no post-hoc exclusions."
    ],
    "retrieval_diagnostic": {
      "description": "Queries with a returned URL containing simpleqa (case-insensitive; hyphens/underscores removed), or content containing acceptable range: anything between. Heuristic marker only; not exhaustive contamination detection. No exclusions applied.",
      "queries_by_profile": {
        "searchpipe-basic": 0,
        "searchpipe-advanced": 0,
        "tavily-basic": 11,
        "tavily-advanced": 11,
        "exa-auto": 17,
        "parallel-fast": 7
      }
    }
  },
  "published_at": "2026-10-24T03:33:49.412154+00:00"
}
