rewire.it
Task

DART-Eval REI-PAIR: Regulatory element identification, paired accuracy

Regulatory element identification, paired accuracy. Scored with Paired accuracy on ENCODE cCREs against dinucleotide-shuffled backgrounds. Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name.

13 evaluations · 13 metric rows

Overview

Regulatory element identification, paired accuracy. Scored with Paired accuracy on ENCODE cCREs against dinucleotide-shuffled backgrounds. Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Benchmarks

These source-backed links do not make different protocols or scores interchangeable.

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Run instructions

No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

Published comparisons

Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies. The pooled view gathers every source table that reports the same metric and names what it does not hold constant.

DART-Eval REI-PAIR: Regulatory element identification, paired accuracy

paired_accuracy (fraction) · Higher values are better for this metric.

Every method DART-Eval reports on Regulatory element identification, paired accuracy, scored with Paired accuracy on ENCODE cCREs against dinucleotide-shuffled backgrounds.

Evaluation protocol · ENCODE cCREs against dinucleotide-shuffled backgrounds (DART-Eval split)

  1. Caduceus (probed) · Configuration · Author-reported evaluation0.896
  2. Caduceus (fine-tuned) · Configuration · Author-reported evaluation0.971
  3. DNABERT-2 (probed) · Configuration · Author-reported evaluation0.943
  4. DNABERT-2 (fine-tuned) · Configuration · Author-reported evaluation0.973
  5. GENA-LM (probed) · Configuration · Author-reported evaluation0.959
  6. GENA-LM (fine-tuned) · Configuration · Author-reported evaluation0.972
  7. HyenaDNA (probed) · Configuration · Author-reported evaluation0.935
  8. HyenaDNA (fine-tuned) · Configuration · Author-reported evaluation0.952
  9. Mistral-DNA (probed) · Configuration · Author-reported evaluation0.859
  10. Probing-head-like (ab initio) · Method · Author-reported evaluation0.932

Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.

DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, column(Paired accuracy)
Values, uncertainty and evidence
paired_accuracy: original source values
Tested entityPrinted valueUncertaintyEvidence
Caduceus (probed) · Configuration0.896 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Caduceus), column(probed paired_accuracy)
Caduceus (fine-tuned) · Configuration0.971 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Caduceus), column(fine-tuned paired_accuracy)
DNABERT-2 (probed) · Configuration0.943 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(DNABERT-2), column(probed paired_accuracy)
DNABERT-2 (fine-tuned) · Configuration0.973 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(DNABERT-2), column(fine-tuned paired_accuracy)
GENA-LM (probed) · Configuration0.959 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(GENA-LM), column(probed paired_accuracy)
GENA-LM (fine-tuned) · Configuration0.972 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(GENA-LM), column(fine-tuned paired_accuracy)
HyenaDNA (probed) · Configuration0.935 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(HyenaDNA), column(probed paired_accuracy)
HyenaDNA (fine-tuned) · Configuration0.952 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(HyenaDNA), column(fine-tuned paired_accuracy)
Mistral-DNA (probed) · Configuration0.859 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Mistral-DNA), column(probed paired_accuracy)
Mistral-DNA (fine-tuned) · Configuration0.905 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Mistral-DNA), column(fine-tuned paired_accuracy)
Nucleotide Transformer (probed) · Configuration0.917 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Nucleotide Transformer), column(probed paired_accuracy)
Nucleotide Transformer (fine-tuned) · Configuration0.976 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Nucleotide Transformer), column(fine-tuned paired_accuracy)
Probing-head-like (ab initio) · Method0.932 fractionNot reportedAuthor-reported evaluation · source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Ab initio Probing-head-like), column(ab initio paired_accuracy)
Scope and limitations
  • Author-reported numbers, source checked but not independently reproduced.
  • The evaluation setting is part of the method name: a zero-shot, probed and fine-tuned run of the same model are different entries.
  • Metrics and datasets differ between tasks, so these figures cannot be averaged into one score.

Source transcription and grouping reviewed by automated source review on 2026-09-18. These experiments were not independently reproduced by rewire.

Tested entities and results

Release 2026-09-17-134cd1815de8 · 13 evaluations · 13 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
Caduceus (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.

Author-reported evaluation · Evaluation metadata: source checked

0.971 paired_accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Caduceus), column(fine-tuned paired_accuracy)

Source checking is not independent reproduction.

Caduceus (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.

Author-reported evaluation · Evaluation metadata: source checked

0.896 paired_accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Caduceus), column(probed paired_accuracy)

Source checking is not independent reproduction.

DNABERT-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.

Author-reported evaluation · Evaluation metadata: source checked

0.973 paired_accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(DNABERT-2), column(fine-tuned paired_accuracy)

Source checking is not independent reproduction.

DNABERT-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.

Author-reported evaluation · Evaluation metadata: source checked

0.943 paired_accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(DNABERT-2), column(probed paired_accuracy)

Source checking is not independent reproduction.

GENA-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.

Author-reported evaluation · Evaluation metadata: source checked

0.972 paired_accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(GENA-LM), column(fine-tuned paired_accuracy)

Source checking is not independent reproduction.

GENA-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.

Author-reported evaluation · Evaluation metadata: source checked

0.959 paired_accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(GENA-LM), column(probed paired_accuracy)

Source checking is not independent reproduction.

HyenaDNA (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.

Author-reported evaluation · Evaluation metadata: source checked

0.952 paired_accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(HyenaDNA), column(fine-tuned paired_accuracy)

Source checking is not independent reproduction.

HyenaDNA (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.

Author-reported evaluation · Evaluation metadata: source checked

0.935 paired_accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(HyenaDNA), column(probed paired_accuracy)

Source checking is not independent reproduction.

Mistral-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.

Author-reported evaluation · Evaluation metadata: source checked

0.905 paired_accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Mistral-DNA), column(fine-tuned paired_accuracy)

Source checking is not independent reproduction.

Mistral-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.

Author-reported evaluation · Evaluation metadata: source checked

0.859 paired_accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Mistral-DNA), column(probed paired_accuracy)

Source checking is not independent reproduction.

Nucleotide Transformer (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.

Author-reported evaluation · Evaluation metadata: source checked

0.976 paired_accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Nucleotide Transformer), column(fine-tuned paired_accuracy)

Source checking is not independent reproduction.

Nucleotide Transformer (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.

Author-reported evaluation · Evaluation metadata: source checked

0.917 paired_accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Nucleotide Transformer), column(probed paired_accuracy)

Source checking is not independent reproduction.

Probing-head-like (ab initio) 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.

Author-reported evaluation · Evaluation metadata: source checked

0.932 paired_accuracy

Unit: fraction · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedDART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 3, row(Ab initio Probing-head-like), column(ab initio paired_accuracy)

Source checking is not 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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-134cd1815de8
Property and statementOriginal source and locationReview and provenance
Relationship: part of

discovery-benchmark-dart-eval

Individual claims
DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA

Original source ↗

Table 3, column(Paired accuracy)

Version: 2412.05430v1
Retrieved: 2026-09-17T07:56:09.182117+00:00

source checked

automated source review · 2026-09-18

Audit details

Primary-source transcription with no human sign-off and no independent reproduction.

Field: links:part_of:discovery-benchmark-dart-eval

Claim: dart-eval-association-rei-pair

Source artifact SHA-256: 4194b137ba55c9a2c269d119a9afec6ae1bb0feaf17d91433ae483c41221a56b

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Sources and history

Release 2026-09-17-134cd1815de8 · Record review: source checked

1 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: dart-eval-task-rei-pair

areas
dna-genomes
tasks
Regulatory element identification, paired accuracy
metric
Paired accuracy
metric direction
higher
dataset
ENCODE cCREs against dinucleotide-shuffled backgrounds
protocol
Distinguish ENCODE cCREs from dinucleotide-shuffled background sequences. The setting the model was run in is part of the method name.
source locator
Table 3, column(Paired accuracy)
comparison panels
id: dart-eval-panel-rei-pair; title: DART-Eval REI-PAIR: Regulatory element identification, paired accuracy; protocol id: dart-eval-task-rei-pair; dataset id: dart-eval-dataset-encode-ccres-against-dinucleotide-shuffled-backgrounds; metric: paired_accuracy; unit: fraction; direction: higher; result ids: dart-eval-result-caduceus-probed-rei-pair-paired-accuracy; dart-eval-result-caduceus-fine-tuned-rei-pair-paired-accuracy; dart-eval-result-dnabert-2-probed-rei-pair-paired-accuracy; dart-eval-result-dnabert-2-fine-tuned-rei-pair-paired-accuracy; dart-eval-result-gena-lm-probed-rei-pair-paired-accuracy; dart-eval-result-gena-lm-fine-tuned-rei-pair-paired-accuracy; dart-eval-result-hyenadna-probed-rei-pair-paired-accuracy; dart-eval-result-hyenadna-fine-tuned-rei-pair-paired-accuracy; dart-eval-result-mistral-dna-probed-rei-pair-paired-accuracy; dart-eval-result-mistral-dna-fine-tuned-rei-pair-paired-accuracy; dart-eval-result-nucleotide-transformer-probed-rei-pair-paired-accuracy; dart-eval-result-nucleotide-transformer-fine-tuned-rei-pair-paired-accuracy; dart-eval-result-probing-head-like-ab-initio-rei-pair-paired-accuracy; source ids: evidence-expansion-p2-evidence-discovery-final-dart-4194b137ba55; source locator: Table 3, column(Paired accuracy); context: Every method DART-Eval reports on Regulatory element identification, paired accuracy, scored with Paired accuracy on ENCODE cCREs against dinucleotide-shuffled backgrounds.; caveats: Author-reported numbers, source checked but not independently reproduced.; The evaluation setting is part of the method name: a zero-shot, probed and fine-tuned run of the same model are different entries.; Metrics and datasets differ between tasks, so these figures cannot be averaged into one score.; review: method: automated_source_review; date: 2026-09-18
Related records

Suggest a correction