Files
cs249r_book/taxonomy/method-study/evaluation-reconstruction.json

201 lines
6.7 KiB
JSON

{
"schema_version": 1,
"record_kind": "retrospective-evaluation-inventory",
"evidence_scope": "Observed unit identities in stored evaluator outputs; no metric recomputation or independent verification.",
"limitations": [
"Does not establish when material was unsealed or what reviewers could access.",
"Does not establish source independence, human participation, or correctness of judgments.",
"Does not establish a recorded pre-exposure registration.",
"Source artifacts are maintainer-local; hashes alone do not make the study publicly reproducible."
],
"source_slice_sha256": "221fb94438db2d5e0f78f4dbb73c99c081e73d8788c89cbd12468f6a054607c7",
"sources": [
{
"artifact": "phase6-raw-claude-cov-Vocab-X.md",
"sha256": "ba5c9140dc162e50cc2524640d649c037027d71a4dc907fb5acfbc0bd607fc9c",
"kind": "coverage_judgments",
"arm": "Vocab-X",
"unit_count": 79
},
{
"artifact": "phase6-raw-claude-cov-Vocab-Y.md",
"sha256": "c496fe49cd63eaf48bba84495d1e65351021a308eef2e9e8586abe19d843fdf8",
"kind": "coverage_judgments",
"arm": "Vocab-Y",
"unit_count": 79
},
{
"artifact": "phase6-raw-codex-cov-Vocab-X.md",
"sha256": "e954c2a7072508be80463b7629993b6f622e5fbc3df45cfa691850f43aef84c6",
"kind": "coverage_judgments",
"arm": "Vocab-X",
"unit_count": 79
},
{
"artifact": "phase6-raw-codex-cov-Vocab-Y.md",
"sha256": "34a9a7c3294b5e75ef69ab0358bb84ad0dc3a0e84d96df0e6c0c4a06fadf3174",
"kind": "coverage_judgments",
"arm": "Vocab-Y",
"unit_count": 79
},
{
"artifact": "phase6-raw-claude-tag-Vocab-X.md",
"sha256": "f1753cf83f3d4b893a680f8128df39e482e70386f47ecea09dedd1bc6d557bcc",
"kind": "indexing_tags",
"arm": "Vocab-X",
"unit_count": 43
},
{
"artifact": "phase6-raw-claude-tag-Vocab-Y.md",
"sha256": "cfedf04e63f83c99c5ec498b8a60c828a589f56db5a758f4a328e4f9a460dd5c",
"kind": "indexing_tags",
"arm": "Vocab-Y",
"unit_count": 43
},
{
"artifact": "phase6-raw-codex-tag-Vocab-X.md",
"sha256": "550be6ad6f6840b8c95bc0b6065518f904802d92624d224ca6c3ef47e395b200",
"kind": "indexing_tags",
"arm": "Vocab-X",
"unit_count": 43
},
{
"artifact": "phase6-raw-codex-tag-Vocab-Y.md",
"sha256": "e330b686cf2ddfc3376355b5b882c1394b3c5a46b889d4e9689b6118ecbe7e29",
"kind": "indexing_tags",
"arm": "Vocab-Y",
"unit_count": 43
}
],
"evaluated_coverage_unit_ids": [
"P4-COV-courses-and-standards-2026-212",
"P4-COV-systems-venues-2026-001",
"P4-COV-systems-venues-2026-002",
"P4-COV-systems-venues-2026-003",
"P4-COV-systems-venues-2026-004",
"P4-COV-systems-venues-2026-005",
"P4-COV-systems-venues-2026-011",
"P4-COV-systems-venues-2026-012",
"P4-COV-systems-venues-2026-017",
"P4-COV-systems-venues-2026-018",
"P4-COV-systems-venues-2026-019",
"P4-COV-systems-venues-2026-021",
"P4-COV-systems-venues-2026-029",
"P4-COV-systems-venues-2026-030",
"P4-COV-systems-venues-2026-031",
"P4-COV-systems-venues-2026-032",
"P4-COV-systems-venues-2026-042",
"P4-COV-systems-venues-2026-045",
"P4-COV-systems-venues-2026-048",
"P4-COV-systems-venues-2026-051",
"P4-COV-systems-venues-2026-054",
"P4-COV-systems-venues-2026-061",
"P4-COV-systems-venues-2026-063",
"P4-COV-systems-venues-2026-065",
"P4-COV-systems-venues-2026-070",
"P4-COV-systems-venues-2026-072",
"P4-COV-systems-venues-2026-074",
"P4-COV-systems-venues-2026-076",
"P4-COV-systems-venues-2026-077",
"P4-COV-systems-venues-2026-080",
"P4-COV-systems-venues-2026-082",
"P4-COV-systems-venues-2026-085",
"P4-COV-systems-venues-2026-093",
"P4-COV-systems-venues-2026-094",
"P4-COV-systems-venues-2026-095",
"P4-COV-systems-venues-2026-096",
"P4-COV-systems-venues-2026-097",
"P4-COV-systems-venues-2026-098",
"P4-COV-systems-venues-2026-105",
"P4-COV-systems-venues-2026-107",
"P4-COV-systems-venues-2026-108",
"P4-COV-systems-venues-2026-109",
"P4-COV-systems-venues-2026-110",
"P4-COV-systems-venues-2026-112",
"P4-COV-systems-venues-2026-114",
"P4-COV-systems-venues-2026-118",
"P4-COV-systems-venues-2026-126",
"P4-COV-systems-venues-2026-129",
"P4-COV-systems-venues-2026-131",
"P4-COV-systems-venues-2026-133",
"P4-COV-systems-venues-2026-134",
"P4-COV-systems-venues-2026-135",
"P4-COV-systems-venues-2026-138",
"P4-COV-systems-venues-2026-140",
"P4-COV-systems-venues-2026-141",
"P4-COV-systems-venues-2026-142",
"P4-COV-systems-venues-2026-148",
"P4-COV-systems-venues-2026-149",
"P4-COV-systems-venues-2026-150",
"P4-COV-systems-venues-2026-151",
"P4-COV-systems-venues-2026-152",
"P4-COV-systems-venues-2026-157",
"P4-COV-systems-venues-2026-158",
"P4-COV-systems-venues-2026-160",
"P4-COV-systems-venues-2026-163",
"P4-COV-systems-venues-2026-164",
"P4-COV-systems-venues-2026-165",
"P4-COV-systems-venues-2026-169",
"P4-COV-systems-venues-2026-182",
"P4-COV-systems-venues-2026-183",
"P4-COV-systems-venues-2026-188",
"P4-COV-systems-venues-2026-189",
"P4-COV-systems-venues-2026-192",
"P4-S2-STANFORD-CS336-01",
"P4-S3-SLORA-2024",
"Q4-COV-courses-and-standards-2026-191",
"Q4-COV-systems-venues-2026-186",
"Q4-S2-BERKELEY-CS294-267-01",
"Q4-S5-NIST-RMF-600-1"
],
"evaluated_indexing_unit_ids": [
"P4-S4-HELDOUT-Q-003",
"P4-S4-HELDOUT-Q-008",
"P4-S4-HELDOUT-Q-044",
"P4-S4-HELDOUT-Q-045",
"P4-S4-HELDOUT-Q-049",
"P4-S4-HELDOUT-Q-051",
"P4-S4-HELDOUT-Q-054",
"P4-S4-HELDOUT-Q-062",
"P4-S4-HELDOUT-Q-077",
"P4-S4-HELDOUT-Q-082",
"P4-S4-HELDOUT-Q-100",
"P4-S4-HELDOUT-Q-101",
"P4-S4-HELDOUT-Q-115",
"P4-S4-HELDOUT-Q-123",
"P4-S4-HELDOUT-Q-130",
"P4-S4-HELDOUT-Q-141",
"P4-S4-HELDOUT-Q-164",
"P4-S4-HELDOUT-Q-166",
"P4-S4-HELDOUT-Q-169",
"P4-S4-HELDOUT-Q-174",
"P4-S4-HELDOUT-Q-178",
"P4-S4-HELDOUT-Q-182",
"P4-S4-HELDOUT-Q-198",
"P4-S4-HELDOUT-Q-213",
"P4-S4-HELDOUT-Q-217",
"P4-S4-HELDOUT-Q-220",
"P4-S4-HELDOUT-Q-229",
"P4-S4-HELDOUT-Q-236",
"P4-S4-HELDOUT-Q-250",
"P4-S4-HELDOUT-Q-251",
"P4-S4-HELDOUT-Q-256",
"P4-S4-HELDOUT-Q-261",
"P4-S4-HELDOUT-Q-269",
"P4-S4-HELDOUT-Q-273",
"P4-S4-HELDOUT-Q-277",
"P4-S4-HELDOUT-Q-285",
"Q4-COV-courses-and-standards-2026-191",
"Q4-S2-BERKELEY-CS294-267-01",
"Q4-S4-HELDOUT-Q-161",
"Q4-S4-HELDOUT-Q-246",
"Q4-S4-SAMPLE1-Q-160",
"Q4-S4-SAMPLE1-Q-249",
"Q4-S5-NIST-RMF-600-1"
],
"counts": {
"coverage_judgments": 79,
"indexing_tags": 43
}
}