reported_finding: feng-dna-fm-20261013-protocol-tad-attention-nt-v2
Reported finding of Feng TAD recognition from NT-v2 attention
The difference between average NT-v2 attention for TAD-centred and background sequences showed no distinct pattern: values were near zero apart from the diagonal. The authors conclude that NT-v2 self-attention does not recognise TAD boundaries without fine-tuning. The heatmap is Supplementary Fig. 2 (Supplementary Information page 11).
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.
12 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Claimed field reported_finding Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Results, 'TAD region recognition', paragraph 2; Supplementary Fig. 2 (Supplementary Information page 11) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Claimed field reported_finding Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Information Results, 'TAD region recognition', paragraph 2; Supplementary Fig. 2 (Supplementary Information page 11) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Communications 16, 10780 (2025); Supplementary Information PDF (MOESM1, 11 pages) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Source location Results, 'TAD region recognition', paragraph 2; Supplementary Fig. 2 (Supplementary Information page 11) Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Results, 'TAD region recognition', paragraph 2; Supplementary Fig. 2 (Supplementary Information page 11) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Source location Results, 'TAD region recognition', paragraph 2; Supplementary Fig. 2 (Supplementary Information page 11) Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Information Results, 'TAD region recognition', paragraph 2; Supplementary Fig. 2 (Supplementary Information page 11) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Communications 16, 10780 (2025); Supplementary Information PDF (MOESM1, 11 pages) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Claimed value The difference between average NT-v2 attention for TAD-centred and background sequences showed no distinct pattern: values were near zero apart from the diagonal. The authors conclude that NT-v2 self-attention does not recognise TAD boundaries without fine-tuning. The heatmap is Supplementary Fig. 2 (Supplementary Information page 11). Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Results, 'TAD region recognition', paragraph 2; Supplementary Fig. 2 (Supplementary Information page 11) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Claimed value The difference between average NT-v2 attention for TAD-centred and background sequences showed no distinct pattern: values were near zero apart from the diagonal. The authors conclude that NT-v2 self-attention does not recognise TAD boundaries without fine-tuning. The heatmap is Supplementary Fig. 2 (Supplementary Information page 11). Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Information Results, 'TAD region recognition', paragraph 2; Supplementary Fig. 2 (Supplementary Information page 11) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Communications 16, 10780 (2025); Supplementary Information PDF (MOESM1, 11 pages) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Description Descriptive fact transcribed from the pinned source. Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Results, 'TAD region recognition', paragraph 2; Supplementary Fig. 2 (Supplementary Information page 11) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Description Descriptive fact transcribed from the pinned source. Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Information Results, 'TAD region recognition', paragraph 2; Supplementary Fig. 2 (Supplementary Information page 11) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Communications 16, 10780 (2025); Supplementary Information PDF (MOESM1, 11 pages) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Relationship: subject feng-dna-fm-20261013-protocol-tad-attention-nt-v2 Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Results, 'TAD region recognition', paragraph 2; Supplementary Fig. 2 (Supplementary Information page 11) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC12663285.1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Relationship: subject feng-dna-fm-20261013-protocol-tad-attention-nt-v2 Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Information Results, 'TAD region recognition', paragraph 2; Supplementary Fig. 2 (Supplementary Information page 11) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Communications 16, 10780 (2025); Supplementary Information PDF (MOESM1, 11 pages) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
2 source records and release history
- Benchmarking DNA foundation models for genomic and genetic tasks · Original source · PMC12663285.1
- Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Information · Original source · Nature Communications 16, 10780 (2025); Supplementary Information PDF (MOESM1, 11 pages)
Technical metadata and extraction receipts
Stable ID: feng-dna-fm-20261013-claim-tad-finding
- field
- reported_finding
- value
- The difference between average NT-v2 attention for TAD-centred and background sequences showed no distinct pattern: values were near zero apart from the diagonal. The authors conclude that NT-v2 self-attention does not recognise TAD boundaries without fine-tuning. The heatmap is Supplementary Fig. 2 (Supplementary Information page 11).
- source locator
- Results, 'TAD region recognition', paragraph 2; Supplementary Fig. 2 (Supplementary Information page 11)
- review
- method: source-hash-verification; ai-assisted-source-review; rendered-source-visual-check; method note: Checked against Results, 'TAD region recognition', paragraph 2, and the rendered Supplementary Fig. 2 (PDF page 11, SHA-256 373f59b8...4a15). The figure caption puts the TAD tokens at about positions 200-600; the main text says about 300-700. Recorded on the Supplementary Information source.; reviewer: claude; reviewer note: Independent Claude (Opus 5.5) review agent, separate from the extraction agent feng-19 that built this batch. Automated review only; no human review claimed. Transcription, not reproduction.; reviewed at: 2026-10-13T14:40:00Z; artifact sha256: 5d8ca9bcf88cc1b38ad667906a2e4699b1aefa6d31c6f49259784930353f3202; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12663285/fullTextXML; note: Hand transcription by the extraction agent, written out by extract/extract_feng.py. Independent review: wording matches the cited text; nothing added that the source does not say.