N4-methylcytosine (4mC) site detection benchmark, A. thaliana set of six species datasets; 41 bp sequences centred on potential 4mC sites (Methods, 'Sequence classification datasets', 4mC site detection in multiple species; Supplementary Note 1 (Supplementary Information pages 1-2)); as used in Feng et al. 2025 Table 3.
5 evaluations · 5 results. Different protocols are not a single leaderboard.
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: Caduceus-Ph (A.Thaliana 4mC classification) | Protocol: Feng A.Thaliana 4mC sequence classification Dataset: Feng A.Thaliana 4mC dataset | 0.615 AUROC (task: a.thaliana 4mc) unitless · higher Uncertainty: Not reported by the source: Table 3 prints point AUCs only. Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCaduceus-Ph A.Thaliana 4mC evaluation Table 3, frozen embeddings + task-specific random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 3, row 'A.Thaliana 4mC', column 'Caduceus-Ph'. Printed in bold (table footnote: 'Bolded: higher than at least two other AUCs, p < 0.01.'). |
| Configuration: DNABERT-2 (A.Thaliana 4mC classification) | Protocol: Feng A.Thaliana 4mC sequence classification Dataset: Feng A.Thaliana 4mC dataset | 0.599 AUROC (task: a.thaliana 4mc) unitless · higher Uncertainty: Not reported by the source: Table 3 prints point AUCs only. Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceDNABERT-2 A.Thaliana 4mC evaluation Table 3, frozen embeddings + task-specific random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 3, row 'A.Thaliana 4mC', column 'DNABERT-2'. |
| Configuration: GROVER (A.Thaliana 4mC classification) | Protocol: Feng A.Thaliana 4mC sequence classification Dataset: Feng A.Thaliana 4mC dataset | 0.603 AUROC (task: a.thaliana 4mc) unitless · higher Uncertainty: Not reported by the source: Table 3 prints point AUCs only. Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceGROVER A.Thaliana 4mC evaluation Table 3, frozen embeddings + task-specific random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 3, row 'A.Thaliana 4mC', column 'GROVER'. |
| Configuration: HyenaDNA (A.Thaliana 4mC classification) | Protocol: Feng A.Thaliana 4mC sequence classification Dataset: Feng A.Thaliana 4mC dataset | 0.594 AUROC (task: a.thaliana 4mc) unitless · higher Uncertainty: Not reported by the source: Table 3 prints point AUCs only. Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceHyenaDNA A.Thaliana 4mC evaluation Table 3, frozen embeddings + task-specific random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 3, row 'A.Thaliana 4mC', column 'HyenaDNA'. |
| Configuration: NT-v2 (A.Thaliana 4mC classification) | Protocol: Feng A.Thaliana 4mC sequence classification Dataset: Feng A.Thaliana 4mC dataset | 0.633 AUROC (task: a.thaliana 4mc) unitless · higher Uncertainty: Not reported by the source: Table 3 prints point AUCs only. Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceNT-v2 A.Thaliana 4mC evaluation Table 3, frozen embeddings + task-specific random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 3, row 'A.Thaliana 4mC', column 'NT-v2'. Printed in bold (table footnote: 'Bolded: higher than at least two other AUCs, p < 0.01.'). |
Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.
0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.
Release 2026-11-02-a7f03c9e55a5 · Evidence verified: Not verified
Exact outcomes, predictions, identifiers and evaluator are connected.
Missing or unresolved evidence
Verified: Not verified
Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.
Missing or unresolved evidence
Verified: Not verified
A pinned recipe describes the inputs, environment and resource requirements.
Missing or unresolved evidence
Verified: Not verified
Separate data and exposure records support an independent test.
Missing or unresolved evidence
Verified: Not verified
Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.
No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.
A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
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.
33 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Negatives 111927 Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Supplementary Data 6, row 'A.thaliana 4mC'; Supplementary Note 1 (Supplementary Information pages 1-2) 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. |
| Negatives 111927 Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Data 1-6 Supplementary Data 6, row 'A.thaliana 4mC'; Supplementary Note 1 (Supplementary Information pages 1-2) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Communications 16, 10780 (2025); Supplementary Data 1-6 workbook (MOESM3, .xlsm) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Negatives 111927 Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Information Supplementary Data 6, row 'A.thaliana 4mC'; Supplementary Note 1 (Supplementary Information pages 1-2) 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 |
| Population N4-methylcytosine (4mC) site detection benchmark, A. thaliana set of six species datasets; 41 bp sequences centred on potential 4mC sites (Methods, 'Sequence classification datasets', 4mC site detection in multiple species; Supplementary Note 1 (Supplementary Information pages 1-2)); sequence length median 41 bp (range 41-41 bp) per Supplementary Data 6. Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Supplementary Data 6, row 'A.thaliana 4mC'; Supplementary Note 1 (Supplementary Information pages 1-2) 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. |
| Population N4-methylcytosine (4mC) site detection benchmark, A. thaliana set of six species datasets; 41 bp sequences centred on potential 4mC sites (Methods, 'Sequence classification datasets', 4mC site detection in multiple species; Supplementary Note 1 (Supplementary Information pages 1-2)); sequence length median 41 bp (range 41-41 bp) per Supplementary Data 6. Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Data 1-6 Supplementary Data 6, row 'A.thaliana 4mC'; Supplementary Note 1 (Supplementary Information pages 1-2) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Communications 16, 10780 (2025); Supplementary Data 1-6 workbook (MOESM3, .xlsm) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Population N4-methylcytosine (4mC) site detection benchmark, A. thaliana set of six species datasets; 41 bp sequences centred on potential 4mC sites (Methods, 'Sequence classification datasets', 4mC site detection in multiple species; Supplementary Note 1 (Supplementary Information pages 1-2)); sequence length median 41 bp (range 41-41 bp) per Supplementary Data 6. Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Information Supplementary Data 6, row 'A.thaliana 4mC'; Supplementary Note 1 (Supplementary Information pages 1-2) 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 |
| Positives 111927 Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Supplementary Data 6, row 'A.thaliana 4mC'; Supplementary Note 1 (Supplementary Information pages 1-2) 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. |
| Positives 111927 Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Data 1-6 Supplementary Data 6, row 'A.thaliana 4mC'; Supplementary Note 1 (Supplementary Information pages 1-2) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Communications 16, 10780 (2025); Supplementary Data 1-6 workbook (MOESM3, .xlsm) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Positives 111927 Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Information Supplementary Data 6, row 'A.thaliana 4mC'; Supplementary Note 1 (Supplementary Information pages 1-2) 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 |
| Scope note Methods ('Sequence classification datasets') state that for eukaryotic species 4mC site annotations often rely on computational predictions rather than direct genome-wide chemical mapping; Results treat these tasks as exploratory. Supplementary Note 2 (Supplementary Information pages 3-4) nonetheless marks this dataset 'Yes' for reliance on experimental evidence or gold-standard sources. Methods ('Sequence classification datasets', the paragraph defining four task categories) give 4mC site detection as an example of a human epigenetic task, but all six 4mC datasets are non-human (Table 3; Methods, 4mC paragraph). This dataset is recorded under its printed species. Context-only references | Benchmarking DNA foundation models for genomic and genetic tasks Supplementary Data 6, row 'A.thaliana 4mC'; Supplementary Note 1 (Supplementary Information pages 1-2) 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. |
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
Stable ID: feng-dna-fm-20261014-dataset-t3-a-thaliana-4mc