The split of ENCODE cCREs against dinucleotide-shuffled backgrounds that DART-Eval 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.
32 evaluations · 32 results. Different protocols are not a single leaderboard.
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: Caduceus (fine-tuned) | Task: DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.903 absolute_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCaduceus (fine-tuned) on DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Caduceus), column(fine-tuned absolute_accuracy) |
| Configuration: Caduceus (fine-tuned) | Task: DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.971 paired_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCaduceus (fine-tuned) on DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Caduceus), column(fine-tuned paired_accuracy) |
| Configuration: Caduceus (probed) | Task: DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.726 absolute_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCaduceus (probed) on DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Caduceus), column(probed absolute_accuracy) |
| Configuration: Caduceus (probed) | Task: DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.896 paired_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCaduceus (probed) on DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Caduceus), column(probed paired_accuracy) |
| Configuration: Caduceus (zero-shot) | Task: DART-Eval REI-ACC: Regulatory element identification, zero-shot accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.971 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCaduceus (zero-shot) on DART-Eval REI-ACC: Regulatory element identification, zero-shot accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences, scored zero-shot from model likelihood. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Caduceus), column(zero-shot accuracy) |
| Configuration: DNABERT-2 (fine-tuned) | Task: DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.913 absolute_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceDNABERT-2 (fine-tuned) on DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(DNABERT-2), column(fine-tuned absolute_accuracy) |
| Configuration: DNABERT-2 (fine-tuned) | Task: DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.973 paired_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceDNABERT-2 (fine-tuned) on DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(DNABERT-2), column(fine-tuned paired_accuracy) |
| Configuration: DNABERT-2 (probed) | Task: DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.847 absolute_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceDNABERT-2 (probed) on DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(DNABERT-2), column(probed absolute_accuracy) |
| Configuration: DNABERT-2 (probed) | Task: DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.943 paired_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceDNABERT-2 (probed) on DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(DNABERT-2), column(probed paired_accuracy) |
| Configuration: DNABERT-2 (zero-shot) | Task: DART-Eval REI-ACC: Regulatory element identification, zero-shot accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.876 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceDNABERT-2 (zero-shot) on DART-Eval REI-ACC: Regulatory element identification, zero-shot accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences, scored zero-shot from model likelihood. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(DNABERT-2), column(zero-shot accuracy) |
| Configuration: GENA-LM (fine-tuned) | Task: DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.909 absolute_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGENA-LM (fine-tuned) on DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(GENA-LM), column(fine-tuned absolute_accuracy) |
| Configuration: GENA-LM (fine-tuned) | Task: DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.972 paired_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGENA-LM (fine-tuned) on DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(GENA-LM), column(fine-tuned paired_accuracy) |
| Configuration: GENA-LM (probed) | Task: DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.887 absolute_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGENA-LM (probed) on DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(GENA-LM), column(probed absolute_accuracy) |
| Configuration: GENA-LM (probed) | Task: DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.959 paired_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGENA-LM (probed) on DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(GENA-LM), column(probed paired_accuracy) |
| Configuration: GENA-LM (zero-shot) | Task: DART-Eval REI-ACC: Regulatory element identification, zero-shot accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.947 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGENA-LM (zero-shot) on DART-Eval REI-ACC: Regulatory element identification, zero-shot accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences, scored zero-shot from model likelihood. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(GENA-LM), column(zero-shot accuracy) |
| Configuration: HyenaDNA (fine-tuned) | Task: DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.877 absolute_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceHyenaDNA (fine-tuned) on DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(HyenaDNA), column(fine-tuned absolute_accuracy) |
| Configuration: HyenaDNA (fine-tuned) | Task: DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.952 paired_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceHyenaDNA (fine-tuned) on DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(HyenaDNA), column(fine-tuned paired_accuracy) |
| Configuration: HyenaDNA (probed) | Task: DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.847 absolute_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceHyenaDNA (probed) on DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(HyenaDNA), column(probed absolute_accuracy) |
| Configuration: HyenaDNA (probed) | Task: DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.935 paired_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceHyenaDNA (probed) on DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(HyenaDNA), column(probed paired_accuracy) |
| Configuration: HyenaDNA (zero-shot) | Task: DART-Eval REI-ACC: Regulatory element identification, zero-shot accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.891 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceHyenaDNA (zero-shot) on DART-Eval REI-ACC: Regulatory element identification, zero-shot accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences, scored zero-shot from model likelihood. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(HyenaDNA), column(zero-shot accuracy) |
| Configuration: Mistral-DNA (fine-tuned) | Task: DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.817 absolute_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMistral-DNA (fine-tuned) on DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Mistral-DNA), column(fine-tuned absolute_accuracy) |
| Configuration: Mistral-DNA (fine-tuned) | Task: DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.905 paired_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMistral-DNA (fine-tuned) on DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Mistral-DNA), column(fine-tuned paired_accuracy) |
| Configuration: Mistral-DNA (probed) | Task: DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.759 absolute_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMistral-DNA (probed) on DART-Eval REI-ABS: Regulatory element identification, absolute accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Mistral-DNA), column(probed absolute_accuracy) |
| Configuration: Mistral-DNA (probed) | Task: DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.859 paired_accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMistral-DNA (probed) on DART-Eval REI-PAIR: Regulatory element identification, paired accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Mistral-DNA), column(probed paired_accuracy) |
| Configuration: Mistral-DNA (zero-shot) | Task: DART-Eval REI-ACC: Regulatory element identification, zero-shot accuracy Dataset subset: ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) | 0.863 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMistral-DNA (zero-shot) on DART-Eval REI-ACC: Regulatory element identification, zero-shot accuracy Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences, scored zero-shot from model likelihood. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Mistral-DNA), column(zero-shot accuracy) |
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 ENCODE cCREs against dinucleotide-shuffled backgrounds that DART-Eval evaluated on. The upstream dataset release is not catalogued here, so no claim is made that this matches its original splits. Context-only references | DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA No field-specific location recorded Version: 2412.05430v1 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| name ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split) Context-only references | DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA No field-specific location recorded Version: 2412.05430v1 | 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: dart-eval-dataset-encode-ccres-against-dinucleotide-shuffled-backgrounds