The split of GENCODE that BEND evaluated on. The upstream dataset release is not catalogued here, so no claim is made that this matches its original splits.
These checks assess whether the evidence supports a reproducible investigation. A source-checked score alone does not meet these requirements.
Release 2026-09-29-06401fd5b220 · 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.
16 evaluations · 16 results. Different protocols are not a single leaderboard.
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: AUGUSTUS | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.8 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceAUGUSTUS on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(Expert method), column(Gene finding) |
| Method: AWD-LSTM | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.05 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceAWD-LSTM on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(AWD-LSTM), column(Gene finding) |
| Method: CNN | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCNN on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(CNN), column(Gene finding) |
| Configuration: DNABERT-2 | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.43 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceDNABERT-2 on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(DNABERT-2), column(Gene finding) |
| Configuration: DNABERT | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.2 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceDNABERT on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(DNABERT), column(Gene finding) |
| Configuration: GENA-LM BERT | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.52 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGENA-LM BERT on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(GENA-LM BERT), column(Gene finding) |
| Configuration: GENA-LM BigBird | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.39 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGENA-LM BigBird on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(GENA-LM BigBird), column(Gene finding) |
| Configuration: GROVER | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.28 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGROVER on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(GROVER), column(Gene finding) |
| Configuration: HyenaDNA large | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.35 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceHyenaDNA large on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(HyenaDNA large), column(Gene finding) |
| Configuration: HyenaDNA tiny | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.1 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceHyenaDNA tiny on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(HyenaDNA tiny), column(Gene finding) |
| Configuration: NT-1000G | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.49 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT-1000G on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-1000G), column(Gene finding) |
| Method: NT-H | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.41 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT-H on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-H), column(Gene finding) |
| Method: NT-MS | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.68 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT-MS on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-MS), column(Gene finding) |
| Configuration: NT-V2 | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.64 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT-V2 on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-V2), column(Gene finding) |
| Configuration: ResNet | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.46 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceResNet on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(ResNet), column(Gene finding) |
| Method: ResNet-LM | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.36 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceResNet-LM on BEND GENE-FINDING: Gene finding A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(ResNet-LM), column(Gene finding) |
Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.
This record describes a particular subset or cohort used in an evaluation. Its results do not describe the full dataset.
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.
2 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| description The split of GENCODE that BEND evaluated on. The upstream dataset release is not catalogued here, so no claim is made that this matches its original splits. Context-only references | BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks No field-specific location recorded Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| name GENCODE (BEND split) Context-only references | BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks No field-specific location recorded Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: source checked
Stable ID: bend-dataset-gencode