AlphaGenome Atlas: variant offset from the input centre
Scoring setup of AlphaGenome merged splicing score, distilled model, Atlas precomputed (AlphaGenome Atlas v1)
Atlas scores use a 1 Mb input centred on each 128 bp window, so variants sit up to 64 bp from the centre. The authors re-ran the AlphaGenome paper evaluations with variants at their windowed positions and report no statistically significant difference in any evaluation metric.
Descriptive fact transcribed from the pinned source.
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
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Claimed field scoring_setup Context-only references | AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) Methods 'Sliding Window Approach' and 'Reference Prediction Caching' (pages 18 to 19) Version: medRxiv preprint version 1, posted 2026-09-20; full-text PDF with supplementary figures and tables (83 pages) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the medRxiv PDF. A second retrieval at 2026-10-19T12:30:54Z had the same length (15,415,633 bytes) and the same SHA-256. |
Limitations1 values
| AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) Methods 'Sliding Window Approach' and 'Reference Prediction Caching' (pages 18 to 19) Version: medRxiv preprint version 1, posted 2026-09-20; full-text PDF with supplementary figures and tables (83 pages) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the medRxiv PDF. A second retrieval at 2026-10-19T12:30:54Z had the same length (15,415,633 bytes) and the same SHA-256. |
| Source location Methods 'Sliding Window Approach' and 'Reference Prediction Caching' (pages 18 to 19) Context-only references | AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) Methods 'Sliding Window Approach' and 'Reference Prediction Caching' (pages 18 to 19) Version: medRxiv preprint version 1, posted 2026-09-20; full-text PDF with supplementary figures and tables (83 pages) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the medRxiv PDF. A second retrieval at 2026-10-19T12:30:54Z had the same length (15,415,633 bytes) and the same SHA-256. |
| Claimed value Atlas scores use a 1 Mb input centred on each 128 bp window, so variants sit up to 64 bp from the centre. The authors re-ran the AlphaGenome paper evaluations with variants at their windowed positions and report no statistically significant difference in any evaluation metric. Context-only references | AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) Methods 'Sliding Window Approach' and 'Reference Prediction Caching' (pages 18 to 19) Version: medRxiv preprint version 1, posted 2026-09-20; full-text PDF with supplementary figures and tables (83 pages) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the medRxiv PDF. A second retrieval at 2026-10-19T12:30:54Z had the same length (15,415,633 bytes) and the same SHA-256. |
| Description Descriptive fact transcribed from the pinned source. Context-only references | AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) Methods 'Sliding Window Approach' and 'Reference Prediction Caching' (pages 18 to 19) Version: medRxiv preprint version 1, posted 2026-09-20; full-text PDF with supplementary figures and tables (83 pages) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the medRxiv PDF. A second retrieval at 2026-10-19T12:30:54Z had the same length (15,415,633 bytes) and the same SHA-256. |
| Relationship: subject ag-atlas-20261019-config-alphagenome-merged-splicing Context-only references | AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) Methods 'Sliding Window Approach' and 'Reference Prediction Caching' (pages 18 to 19) Version: medRxiv preprint version 1, posted 2026-09-20; full-text PDF with supplementary figures and tables (83 pages) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the medRxiv PDF. A second retrieval at 2026-10-19T12:30:54Z had the same length (15,415,633 bytes) and the same SHA-256. |
| Name AlphaGenome Atlas: variant offset from the input centre Context-only references | AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) Methods 'Sliding Window Approach' and 'Reference Prediction Caching' (pages 18 to 19) Version: medRxiv preprint version 1, posted 2026-09-20; full-text PDF with supplementary figures and tables (83 pages) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the medRxiv PDF. A second retrieval at 2026-10-19T12:30:54Z had the same length (15,415,633 bytes) and the same SHA-256. |
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
1 source record and release history
- AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) · Original source · medRxiv preprint version 1, posted 2026-09-20; full-text PDF with supplementary figures and tables (83 pages)
Technical metadata and extraction receipts
Stable ID: ag-atlas-20261019-claim-alphagenome-window-position
- field
- scoring_setup
- value
- Atlas scores use a 1 Mb input centred on each 128 bp window, so variants sit up to 64 bp from the centre. The authors re-ran the AlphaGenome paper evaluations with variants at their windowed positions and report no statistically significant difference in any evaluation metric.
- source locator
- Methods 'Sliding Window Approach' and 'Reference Prediction Caching' (pages 18 to 19)
- review
- method: source-hash-verification; automated-source-review; scope-review; method note: Sentences asserted in the pdftotext -layout text.; reviewer: claude; reviewer note: Independent Claude review agent for PR #214, 2026-11-01; did not extract this batch; no human review claimed.; date: 2026-11-01; artifact sha256: b32d1539005ca4ea31c3dcef49b834424b1d8b5da4ce6b9fc3e1f942d39fc453; retrieval url: https://www.medrxiv.org/content/10.64898/2026.09.16.26363192v1.full.pdf; note: Checked the claim's statements against the cited pages of a 2026-11-01 retrieval. The 2026-11-01 retrieval is stamped differently from the pinned bytes (different SHA-256); re-running the extractor on it, with only the hash assertion relaxed, reproduced batch.jsonl byte for byte. Verdict in docs/reviews/2026-11-01-alphagenome-atlas-lu-brandes.md.
- limitations
- The re-run metrics are not printed.