Evidence claim

LIT-PCBA leakage audit source: evidence_concerns removed

Evidence concerns of Huang, Knight and Naprienko 2025, arXiv:2507.21404v2 (abstract page)

Removed. The source record now carries no evidence_concerns entry. The audit's finding is kept as the claim hitdisc-20261022-claim-litpcba-leakage-audit, as limitations on the LIT-PCBA benchmark record and the five-target protocol, and as a source warning on each of the 84 LIT-PCBA results.

The audit is the source that reports the LIT-PCBA problem, not a source with a problem. Keeping the entry withheld every judgement on the use case.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

7 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance
Claimed field attributes.evidence_concerns Context-only references	Huang, Knight and Naprienko 2025, arXiv:2507.21404v2 (abstract page) Original source ↗ arXiv:2507.21404v2 abstract page; shared/omics/use-cases.ts cleanSource Version: arXiv:2507.21404v2, submitted 2025-07-29, this version 2025-08-07 Retrieved: 2026-10-22T11:59:20Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.field` Source artifact SHA-256: `e766c8aa4f94287672b2b1bacab2480a41ec7c806ecbaf5e2d1bf8773781310f` Hash scope: This is a mutable web page: artifact_sha256 describes the single retrieval of 2026-10-22T11:59:20Z and a later change to the page would change it.
Previous value [{"source_id": "hitdisc-20261022-source-litpcba-audit", "message": "This preprint audits LIT-PCBA itself and concludes that extensive analogue and 2D-identical-compound leakage between its splits means a parameter-free memorisation baseline matches or exceeds published deep-learning and 3D-similarity results, so nearly all published LIT-PCBA results are undermined and zero-shot evaluations are also affected. It bears on every LIT-PCBA result in this store. It is a preprint and its tables were not retrieved: only the abstract was read.", "source_locator": "Abstract", "artifact_sha256": "e766c8aa4f94287672b2b1bacab2480a41ec7c806ecbaf5e2d1bf8773781310f", "review_date": "2026-10-22"}] Context-only references	Huang, Knight and Naprienko 2025, arXiv:2507.21404v2 (abstract page) Original source ↗ arXiv:2507.21404v2 abstract page; shared/omics/use-cases.ts cleanSource Version: arXiv:2507.21404v2, submitted 2025-07-29, this version 2025-08-07 Retrieved: 2026-10-22T11:59:20Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.previous_value` Source artifact SHA-256: `e766c8aa4f94287672b2b1bacab2480a41ec7c806ecbaf5e2d1bf8773781310f` Hash scope: This is a mutable web page: artifact_sha256 describes the single retrieval of 2026-10-22T11:59:20Z and a later change to the page would change it.
Source location arXiv:2507.21404v2 abstract page; shared/omics/use-cases.ts cleanSource Context-only references	Huang, Knight and Naprienko 2025, arXiv:2507.21404v2 (abstract page) Original source ↗ arXiv:2507.21404v2 abstract page; shared/omics/use-cases.ts cleanSource Version: arXiv:2507.21404v2, submitted 2025-07-29, this version 2025-08-07 Retrieved: 2026-10-22T11:59:20Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.source_locator` Source artifact SHA-256: `e766c8aa4f94287672b2b1bacab2480a41ec7c806ecbaf5e2d1bf8773781310f` Hash scope: This is a mutable web page: artifact_sha256 describes the single retrieval of 2026-10-22T11:59:20Z and a later change to the page would change it.
Claimed value Removed. The source record now carries no evidence_concerns entry. The audit's finding is kept as the claim hitdisc-20261022-claim-litpcba-leakage-audit, as limitations on the LIT-PCBA benchmark record and the five-target protocol, and as a source warning on each of the 84 LIT-PCBA results. Context-only references	Huang, Knight and Naprienko 2025, arXiv:2507.21404v2 (abstract page) Original source ↗ arXiv:2507.21404v2 abstract page; shared/omics/use-cases.ts cleanSource Version: arXiv:2507.21404v2, submitted 2025-07-29, this version 2025-08-07 Retrieved: 2026-10-22T11:59:20Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.value` Source artifact SHA-256: `e766c8aa4f94287672b2b1bacab2480a41ec7c806ecbaf5e2d1bf8773781310f` Hash scope: This is a mutable web page: artifact_sha256 describes the single retrieval of 2026-10-22T11:59:20Z and a later change to the page would change it.
Description The audit is the source that reports the LIT-PCBA problem, not a source with a problem. Keeping the entry withheld every judgement on the use case. Context-only references	Huang, Knight and Naprienko 2025, arXiv:2507.21404v2 (abstract page) Original source ↗ arXiv:2507.21404v2 abstract page; shared/omics/use-cases.ts cleanSource Version: arXiv:2507.21404v2, submitted 2025-07-29, this version 2025-08-07 Retrieved: 2026-10-22T11:59:20Z	not individually reviewed No individual claim review recorded Audit details Field: `description` Source artifact SHA-256: `e766c8aa4f94287672b2b1bacab2480a41ec7c806ecbaf5e2d1bf8773781310f` Hash scope: This is a mutable web page: artifact_sha256 describes the single retrieval of 2026-10-22T11:59:20Z and a later change to the page would change it.
Relationship: subject hitdisc-20261022-source-litpcba-audit Context-only references	Huang, Knight and Naprienko 2025, arXiv:2507.21404v2 (abstract page) Original source ↗ arXiv:2507.21404v2 abstract page; shared/omics/use-cases.ts cleanSource Version: arXiv:2507.21404v2, submitted 2025-07-29, this version 2025-08-07 Retrieved: 2026-10-22T11:59:20Z	not individually reviewed No individual claim review recorded Audit details Field: `links:subject:hitdisc-20261022-source-litpcba-audit` Source artifact SHA-256: `e766c8aa4f94287672b2b1bacab2480a41ec7c806ecbaf5e2d1bf8773781310f` Hash scope: This is a mutable web page: artifact_sha256 describes the single retrieval of 2026-10-22T11:59:20Z and a later change to the page would change it.
Name LIT-PCBA leakage audit source: evidence_concerns removed Context-only references	Huang, Knight and Naprienko 2025, arXiv:2507.21404v2 (abstract page) Original source ↗ arXiv:2507.21404v2 abstract page; shared/omics/use-cases.ts cleanSource Version: arXiv:2507.21404v2, submitted 2025-07-29, this version 2025-08-07 Retrieved: 2026-10-22T11:59:20Z	not individually reviewed No individual claim review recorded Audit details Field: `name` Source artifact SHA-256: `e766c8aa4f94287672b2b1bacab2480a41ec7c806ecbaf5e2d1bf8773781310f` Hash scope: This is a mutable web page: artifact_sha256 describes the single retrieval of 2026-10-22T11:59:20Z and a later change to the page would change it.

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

Huang, Knight and Naprienko 2025, arXiv:2507.21404v2 (abstract page) · Original source · arXiv:2507.21404v2, submitted 2025-07-29, this version 2025-08-07

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: metadata-correction-566a4c4c58e0d8661fa7

areas: molecular-interactions
contexts: research
field: attributes.evidence_concerns
previous value: [{"source_id": "hitdisc-20261022-source-litpcba-audit", "message": "This preprint audits LIT-PCBA itself and concludes that extensive analogue and 2D-identical-compound leakage between its splits means a parameter-free memorisation baseline matches or exceeds published deep-learning and 3D-similarity results, so nearly all published LIT-PCBA results are undermined and zero-shot evaluations are also affected. It bears on every LIT-PCBA result in this store. It is a preprint and its tables were not retrieved: only the abstract was read.", "source_locator": "Abstract", "artifact_sha256": "e766c8aa4f94287672b2b1bacab2480a41ec7c806ecbaf5e2d1bf8773781310f", "review_date": "2026-10-22"}]
value: Removed. The source record now carries no evidence_concerns entry. The audit's finding is kept as the claim hitdisc-20261022-claim-litpcba-leakage-audit, as limitations on the LIT-PCBA benchmark record and the five-target protocol, and as a source warning on each of the 84 LIT-PCBA results.
source locator: arXiv:2507.21404v2 abstract page; shared/omics/use-cases.ts cleanSource
review: method: scope-review; independent-cell-check; reviewer: claude; reviewer note: Claude review agent, independent of the extraction agent; no human review claimed; date: 2026-10-22; method note: Read the abstract of the pinned page against the entry, and traced the effect of a concerned source through shared/omics/use-cases.ts.; note: Correction found by the independent review pass of batch use-case-coverage-hitdisc-20261022. The previous value is kept here.; receipt: data/omics/use-case-coverage-hitdisc-20261022/review.json

Related records

subject: Huang, Knight and Naprienko 2025, arXiv:2507.21404v2 (abstract page)

Suggest a correction