{
  "id": "page:epoch-crosswalk",
  "type": "WebPage",
  "canonical_url": "https://www.honesty.tools/epoch-crosswalk",
  "source_url": "https://www.honesty.tools/epoch-crosswalk",
  "title": "Epoch AI reviews meet our cue test: batches 1 and 2 · Honesty.tools",
  "summary": "Our pre-registered crosswalk with Epoch AI's Benchmark Reviews. GraphWalks: no surface cue detected, a weak result because its node ids are hashes. Humanity's Last Exam: batch 1 void, because our own shuffled-label control fired; batch 2, a new within-question test on the same items, passed, with the grouped test borderline and answer length the weakest spot. SimpleQA Verified: not applicable.",
  "status": "Published public page; research and product status remains as stated in the source text.",
  "published_at": null,
  "updated_at": null,
  "last_verified_at": null,
  "date_basis": "No normalized editorial or research-verification date asserted. Dated statements remain in the source text.",
  "verification_basis": "Static authored content from the public HTML. Interactive outputs are not simulated. Source-specific research, product and evidence limits remain in the text; this export is not new verification.",
  "source_revision": "sha256:59104738c9d665d18b6af58354281ee6d690702970f7ec834460dc8670eb3e79",
  "source_revision_basis": "Public source HTML excluding generated representation links and head metadata; a content revision, not a research verification.",
  "sources": [
    {
      "label": "Details and receipts ↓",
      "url": "https://www.honesty.tools/epoch-crosswalk#status-detail"
    },
    {
      "label": "Files and hashes ↓",
      "url": "https://www.honesty.tools/epoch-crosswalk#receipts"
    },
    {
      "label": "Details ↓",
      "url": "https://www.honesty.tools/epoch-crosswalk#batch2-v2"
    },
    {
      "label": "Epoch’s list ↗",
      "url": "https://epoch.ai/data/benchmark-reviews-documentation/included-benchmarks"
    },
    {
      "label": "/audit",
      "url": "https://www.honesty.tools/audit"
    },
    {
      "label": "nulltest.py",
      "url": "https://www.honesty.tools/verifier/nulltest.py"
    },
    {
      "label": "below",
      "url": "https://www.honesty.tools/epoch-crosswalk#batch2-v2"
    },
    {
      "label": "results.json",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-batch1/results.json"
    },
    {
      "label": "REPORT.md",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-batch1/REPORT.md"
    },
    {
      "label": "DEVIATION_1.md",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-batch1/DEVIATION_1.md"
    },
    {
      "label": "DEVIATION_1_DECISION.md",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-batch1/DEVIATION_1_DECISION.md"
    },
    {
      "label": "EXPLORATORY_HLE_SHUFFLE.md",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-batch1/EXPLORATORY_HLE_SHUFFLE.md"
    },
    {
      "label": "batch 2 below",
      "url": "https://www.honesty.tools/epoch-crosswalk#batch2"
    },
    {
      "label": "Jump to the result ↓",
      "url": "https://www.honesty.tools/epoch-crosswalk#batch2-v2"
    },
    {
      "label": "score pack",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/publish_pack/README.md"
    },
    {
      "label": "D6",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/publish_pack/DEVIATION_D6_ARM_P_STRATUM.md"
    },
    {
      "label": "D7",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/publish_pack/DEVIATION_D7_ARM_P_SECONDARY.md"
    },
    {
      "label": "PREREG_HLE_B2_v2.md",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/PREREG_HLE_B2_v2.md"
    },
    {
      "label": "b2v2_pilot.py",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/b2v2_pilot.py"
    },
    {
      "label": "B2_SIM_GATE.json",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/B2_SIM_GATE.json"
    },
    {
      "label": "NOTE.md",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/NOTE.md"
    },
    {
      "label": "B2V2_SIM_GATE.json",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/B2V2_SIM_GATE.json"
    },
    {
      "label": "PILOT_SUMMARY.json",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/PILOT_SUMMARY.json"
    },
    {
      "label": "publish_pack.tar.gz",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/publish_pack.tar.gz"
    },
    {
      "label": "README.md",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/publish_pack/README.md"
    },
    {
      "label": "DEVIATION_D6_ARM_P_STRATUM.md",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/publish_pack/DEVIATION_D6_ARM_P_STRATUM.md"
    },
    {
      "label": "DEVIATION_D7_ARM_P_SECONDARY.md",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/publish_pack/DEVIATION_D7_ARM_P_SECONDARY.md"
    },
    {
      "label": "primary_G.json",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/publish_pack/scores/primary_G.json"
    },
    {
      "label": "primary_P.json",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/publish_pack/scores/primary_P.json"
    },
    {
      "label": "SCORE_RUN.log",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/publish_pack/logs/SCORE_RUN.log"
    },
    {
      "label": "SHA256SUMS",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/publish_pack/SHA256SUMS"
    },
    {
      "label": "SHA256SUMS",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-hle-b2/SHA256SUMS"
    },
    {
      "label": "Flawed",
      "url": "https://epoch.ai/benchmarks/hle/review"
    },
    {
      "label": "Verified",
      "url": "https://epoch.ai/benchmarks/graphwalks/review"
    },
    {
      "label": "Verified",
      "url": "https://epoch.ai/benchmarks/simple-qa-verified/review"
    },
    {
      "label": "PREREG.md",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-batch1/PREREG.md"
    },
    {
      "label": "PREREG_DRAFT.md",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-batch1/PREREG_DRAFT.md"
    },
    {
      "label": "SCOPE.md",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-batch1/SCOPE.md"
    },
    {
      "label": "SHA256SUMS",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-batch1/SHA256SUMS"
    },
    {
      "label": "raw/SHA256SUMS",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-batch1/raw/SHA256SUMS"
    },
    {
      "label": "DATA_MANIFEST.json",
      "url": "https://www.honesty.tools/receipts/epoch-crosswalk-batch1/DATA_MANIFEST.json"
    },
    {
      "label": "The /audit table",
      "url": "https://www.honesty.tools/audit"
    },
    {
      "label": "Our Goodfire re-check",
      "url": "https://www.honesty.tools/goodfire"
    },
    {
      "label": "Epoch AI: included benchmarks ↗",
      "url": "https://epoch.ai/data/benchmark-reviews-documentation/included-benchmarks"
    }
  ],
  "claims": null,
  "limitations": [
    "Static authored content from the public HTML. Interactive outputs are not simulated. Source-specific research, product and evidence limits remain in the text; this export is not new verification."
  ],
  "corrections": [],
  "supersedes": [],
  "representations": {
    "html": "https://www.honesty.tools/epoch-crosswalk",
    "markdown": "/page-text/epoch-crosswalk.md",
    "metadata": "/page-data/epoch-crosswalk.json"
  }
}