rewirebio.iobenchmarks
Evidence claim

POISK patent-derived antibody dataset, version 1.1: scope_note

Scope note of POISK patent-derived antibody dataset, version 1.1

93,193 rows and 47 columns, each row carrying a distinct unique_record_id. The record states that version 1.1 corrects errors found in version 1.0.1 and adds the folding data for the paper's benchmark, and that those folding predictions were run against version 1.0.1 rather than against this release. The 93,193 rows are therefore not the manuscript's 89,074 extracted records and not the benchmark's 22,494 complexes. Relationship to version 1.0.1, after review: no link is recorded between the two dataset records. The releases do not hold the same data, so same_data_as, which states informational data reuse, does not apply: the Zenodo file lists give poisk_dataset.csv as 124,175,590 bytes with md5 1d663c6797f03466349c995b4e8a913a in version 1.0.1 and 234,128,089 bytes with md5 f0c1f098abf1756e4b9891aa4dc028ee here, and this record's own description says version 1.1 corrects errors found in version 1.0.1. supersedes is not recorded either, because version 1.0.1 is still the release the published folding predictions were run against and is what every evaluation in this batch pins. The two releases share poisk_all_models_folding_metrics.zip, md5 9b56b7095d32c3c2357aa6d4fa3369f8, which claim-v1-1-folding-metrics-files records, and claim-v1-1-folding-version carries the release's own statement about which version the predictions were run against.

Correction made by the independent review of the POISK batch. The previous value is kept here.

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 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Claimed field
scope_note
Context-only references
POISK dataset version 1.1 on Zenodo (record 21775623)

Original source ↗

Zenodo records 19883049 and 21775623, file lists and description sections 'Dataset Structure and Documentation' and 'Relationship to the folding predictions'

Version: 1.1, published 23 October 2026
Retrieved: 2026-11-15T23:36:08Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.field

Source artifact SHA-256: 1b95773c269ca57f971f3b60c5df4558c48edc88b11580ca46e97a06e3d99981

Hash scope: Hash scope not separately documented; inspect source record

Format: application/json (Zenodo REST record)

Inspected artifact

Previous value
93,193 rows and 47 columns, each row carrying a distinct unique_record_id. The record states that version 1.1 corrects errors found in version 1.0.1 and adds the folding data for the paper's benchmark, and that those folding predictions were run against version 1.0.1 rather than against this release. The 93,193 rows are therefore not the manuscript's 89,074 extracted records and not the benchmark's 22,494 complexes.
Context-only references
POISK dataset version 1.1 on Zenodo (record 21775623)

Original source ↗

Zenodo records 19883049 and 21775623, file lists and description sections 'Dataset Structure and Documentation' and 'Relationship to the folding predictions'

Version: 1.1, published 23 October 2026
Retrieved: 2026-11-15T23:36:08Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.previous_value

Source artifact SHA-256: 1b95773c269ca57f971f3b60c5df4558c48edc88b11580ca46e97a06e3d99981

Hash scope: Hash scope not separately documented; inspect source record

Format: application/json (Zenodo REST record)

Inspected artifact

Source location
Zenodo records 19883049 and 21775623, file lists and description sections 'Dataset Structure and Documentation' and 'Relationship to the folding predictions'
Context-only references
POISK dataset version 1.1 on Zenodo (record 21775623)

Original source ↗

Zenodo records 19883049 and 21775623, file lists and description sections 'Dataset Structure and Documentation' and 'Relationship to the folding predictions'

Version: 1.1, published 23 October 2026
Retrieved: 2026-11-15T23:36:08Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.source_locator

Source artifact SHA-256: 1b95773c269ca57f971f3b60c5df4558c48edc88b11580ca46e97a06e3d99981

Hash scope: Hash scope not separately documented; inspect source record

Format: application/json (Zenodo REST record)

Inspected artifact

Claimed value
93,193 rows and 47 columns, each row carrying a distinct unique_record_id. The record states that version 1.1 corrects errors found in version 1.0.1 and adds the folding data for the paper's benchmark, and that those folding predictions were run against version 1.0.1 rather than against this release. The 93,193 rows are therefore not the manuscript's 89,074 extracted records and not the benchmark's 22,494 complexes. Relationship to version 1.0.1, after review: no link is recorded between the two dataset records. The releases do not hold the same data, so same_data_as, which states informational data reuse, does not apply: the Zenodo file lists give poisk_dataset.csv as 124,175,590 bytes with md5 1d663c6797f03466349c995b4e8a913a in version 1.0.1 and 234,128,089 bytes with md5 f0c1f098abf1756e4b9891aa4dc028ee here, and this record's own description says version 1.1 corrects errors found in version 1.0.1. supersedes is not recorded either, because version 1.0.1 is still the release the published folding predictions were run against and is what every evaluation in this batch pins. The two releases share poisk_all_models_folding_metrics.zip, md5 9b56b7095d32c3c2357aa6d4fa3369f8, which claim-v1-1-folding-metrics-files records, and claim-v1-1-folding-version carries the release's own statement about which version the predictions were run against.
Context-only references
POISK dataset version 1.1 on Zenodo (record 21775623)

Original source ↗

Zenodo records 19883049 and 21775623, file lists and description sections 'Dataset Structure and Documentation' and 'Relationship to the folding predictions'

Version: 1.1, published 23 October 2026
Retrieved: 2026-11-15T23:36:08Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.value

Source artifact SHA-256: 1b95773c269ca57f971f3b60c5df4558c48edc88b11580ca46e97a06e3d99981

Hash scope: Hash scope not separately documented; inspect source record

Format: application/json (Zenodo REST record)

Inspected artifact

Description
Correction made by the independent review of the POISK batch. The previous value is kept here.
Context-only references
POISK dataset version 1.1 on Zenodo (record 21775623)

Original source ↗

Zenodo records 19883049 and 21775623, file lists and description sections 'Dataset Structure and Documentation' and 'Relationship to the folding predictions'

Version: 1.1, published 23 October 2026
Retrieved: 2026-11-15T23:36:08Z

not individually reviewed

No individual claim review recorded

Audit details

Field: description

Source artifact SHA-256: 1b95773c269ca57f971f3b60c5df4558c48edc88b11580ca46e97a06e3d99981

Hash scope: Hash scope not separately documented; inspect source record

Format: application/json (Zenodo REST record)

Inspected artifact

Relationship: subject
poisk-20261115-dataset-poisk-v1-1
Context-only references
POISK dataset version 1.1 on Zenodo (record 21775623)

Original source ↗

Zenodo records 19883049 and 21775623, file lists and description sections 'Dataset Structure and Documentation' and 'Relationship to the folding predictions'

Version: 1.1, published 23 October 2026
Retrieved: 2026-11-15T23:36:08Z

not individually reviewed

No individual claim review recorded

Audit details

Field: links:subject:poisk-20261115-dataset-poisk-v1-1

Source artifact SHA-256: 1b95773c269ca57f971f3b60c5df4558c48edc88b11580ca46e97a06e3d99981

Hash scope: Hash scope not separately documented; inspect source record

Format: application/json (Zenodo REST record)

Inspected artifact

Name
POISK patent-derived antibody dataset, version 1.1: scope_note
Context-only references
POISK dataset version 1.1 on Zenodo (record 21775623)

Original source ↗

Zenodo records 19883049 and 21775623, file lists and description sections 'Dataset Structure and Documentation' and 'Relationship to the folding predictions'

Version: 1.1, published 23 October 2026
Retrieved: 2026-11-15T23:36:08Z

not individually reviewed

No individual claim review recorded

Audit details

Field: name

Source artifact SHA-256: 1b95773c269ca57f971f3b60c5df4558c48edc88b11580ca46e97a06e3d99981

Hash scope: Hash scope not separately documented; inspect source record

Format: application/json (Zenodo REST record)

Inspected artifact

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: metadata-correction-0b86aff1c266a6acf5a5

areas
molecular-interactions; proteins-complexes
field
scope_note
previous value
93,193 rows and 47 columns, each row carrying a distinct unique_record_id. The record states that version 1.1 corrects errors found in version 1.0.1 and adds the folding data for the paper's benchmark, and that those folding predictions were run against version 1.0.1 rather than against this release. The 93,193 rows are therefore not the manuscript's 89,074 extracted records and not the benchmark's 22,494 complexes.
review
artifact sha256: e75c18130ca43770d2f0ed05ae96528759666c0e4fa08f7725f5a32b21187696; method: independent-cell-check; deterministic-table-parse; pdf-text-parse; source-hash-verification; method note: Independent review pass. All five pinned artifacts were re-retrieved. The two Zenodo API responses, the explorer page and the bioRxiv v1 JATS XML all hashed to the values on their source records. The v1 PDF did not: three downloads on 2026-11-16 gave 3389c1bf6d3654c5b2151a07fcfcefc67cf6f36e5f0facfc03c33521d8b84491 twice and d699fd680e3b0097ca80130c288e8d872773dc1e523044f4605e06fc4f89d9bc once, none equal to the recorded artifact_sha256, because bioRxiv regenerates the container on request. A pdftotext -layout run (poppler 26.08.0) on all three downloads gave the same text layer, byte for byte the contents of the archived artifacts/biorxiv-v1-layout.txt.gz, SHA-256 e75c18130ca43770d2f0ed05ae96528759666c0e4fa08f7725f5a32b21187696, so the archive is provably derived from the pinned article and is the artifact this review verified values against. npm run batch -- check-values reproduced the extractor's figures exactly (36 in_cell, 36 in_row, 6 locator_not_parsed, no wrong_column and no overclaimed_in_row) and wrote an identical value-check.tsv. All 78 results were then re-read by review/check_values_independent.py, written for this pass and importing nothing from extract/build_batch.py: it takes each table's column spans from the character offsets of the label text in that table's own printed header lines, assigns every numeric token on a body row to the column whose centre is nearest and rejects the row unless the token count matches the column count, the nearest column is the one in the token's own left-to-right position, and the runner-up column loses by at least three characters; it also checks that Table 1's sub-columns sit under their group labels and that Table 7's Coverage group does not reach the Ties column. Records are matched to cells through each result's source_locator text, not its ID. 72 results were checked in cell, including all 36 the repository parser could only place at row level, and the 6 prose values were checked against the sentence each locator names. Two negative controls confirmed the checker fails on a swapped pair of values and on a value shifted into a neighbouring column of the same row, which a row-level check passes. Independently of the script, all 42 printed cells of Tables 2 and 7 were transcribed by hand into review/manual-transcription.tsv and compared with the records, covering column assignment for every one of the 36 cells left unverified at extraction. Version 2 of the preprint, posted 2026-11-14, was retrieved (PDF SHA-256 aeaec593d7aa2d42382a49bd6fadbbccabaa6c084843ea1c7f0c91097dedb0c2, text layer 82a99bc2e061b7247cf65f7bc9450924b7af5be7ab3ef283d2284ba787ea629c): every numeric token in it is identical to v1's apart from an added author affiliation and the two Zenodo record identifiers, so no stored value changes and the batch stays pinned to v1. The 40 descriptive claims were read against the pinned PDF text layer, both Zenodo API responses and the explorer page.; note: States in the record what the removed same_data_as link used to assert, and why neither that relation nor supersedes is recorded. reuse_note is declared for dataset_subset only, so the note goes in scope_note.; retrieval url: https://www.biorxiv.org/content/10.64898/2026.10.24.761513v1.full.pdf; reviewed at: 2026-11-16T00:00:00Z; reviewer: claude; reviewer note: Claude review agent (independent of the extractor); no human review claimed. Transcription was checked against the pinned source; nothing was reproduced and no value was recomputed.
source locator
Zenodo records 19883049 and 21775623, file lists and description sections 'Dataset Structure and Documentation' and 'Relationship to the folding predictions'
value
93,193 rows and 47 columns, each row carrying a distinct unique_record_id. The record states that version 1.1 corrects errors found in version 1.0.1 and adds the folding data for the paper's benchmark, and that those folding predictions were run against version 1.0.1 rather than against this release. The 93,193 rows are therefore not the manuscript's 89,074 extracted records and not the benchmark's 22,494 complexes. Relationship to version 1.0.1, after review: no link is recorded between the two dataset records. The releases do not hold the same data, so same_data_as, which states informational data reuse, does not apply: the Zenodo file lists give poisk_dataset.csv as 124,175,590 bytes with md5 1d663c6797f03466349c995b4e8a913a in version 1.0.1 and 234,128,089 bytes with md5 f0c1f098abf1756e4b9891aa4dc028ee here, and this record's own description says version 1.1 corrects errors found in version 1.0.1. supersedes is not recorded either, because version 1.0.1 is still the release the published folding predictions were run against and is what every evaluation in this batch pins. The two releases share poisk_all_models_folding_metrics.zip, md5 9b56b7095d32c3c2357aa6d4fa3369f8, which claim-v1-1-folding-metrics-files records, and claim-v1-1-folding-version carries the release's own statement about which version the predictions were run against.
Related records

Suggest a correction