rewire.it
Task

NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation

Fitness prediction on promoter assays, supervised, contiguous cross validation. Scored with Spearman ρ on NABench promoter assays. Scored supervised, contiguous cross validation across the NABench promoter assays.

23 evaluations · 23 metric rows

Overview

Fitness prediction on promoter assays, supervised, contiguous cross validation. Scored with Spearman ρ on NABench promoter assays. Scored supervised, contiguous cross validation across the NABench promoter assays.

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.

NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation

spearman (correlation) · Higher values are better for this metric.

Every method NABench reports on Fitness prediction on promoter assays, supervised, contiguous cross validation, scored with Spearman ρ on NABench promoter assays.

Evaluation protocol · NABench promoter assays (NABench split)

  1. RNA-FM · Configuration · Author-reported evaluation0.035
  2. LucaOne · Configuration · Author-reported evaluation0.164
  3. RESM · Configuration · Author-reported evaluation0.169
  4. Enformer · Configuration · Author-reported evaluation0.318
  5. GENERator-3B · Configuration · Author-reported evaluation0.172
  6. structRFM · Configuration · Author-reported evaluation0.033
  7. N.T.-v2-50m · Configuration · Author-reported evaluation0.220
  8. Evo_1.5_8k_base · Configuration · Author-reported evaluation0.037
  9. Evo2-7B · Configuration · Author-reported evaluation0.043
  10. Crafts · Configuration · Author-reported evaluation0.029
  11. Evo_1_8k_base · Configuration · Author-reported evaluation0.107
  12. Evo_1_8k · Configuration · Author-reported evaluation0.107
  13. BiRNA-BERT · Configuration · Author-reported evaluation0.031
  14. RNAernie · Configuration · Author-reported evaluation0.081
  15. Evo2-7B-base · Configuration · Author-reported evaluation0.128
  16. GENA-LM-large · Configuration · Author-reported evaluation0.592
  17. HyenaDNA · Configuration · Author-reported evaluation0.037
  18. GenerRNA · Configuration · Author-reported evaluation0.171
  19. Dnabert · Configuration · Author-reported evaluation0.049
  20. AIDO.RNA · Configuration · Author-reported evaluation0.095
  21. LucaVirus · Configuration · Author-reported evaluation0.164
  22. GenSLM · Configuration · Author-reported evaluation0.171
  23. Dnabert_6 · Configuration · Author-reported evaluation0.068

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.

NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, column(promoter)
Values, uncertainty and evidence
spearman: original source values
Tested entityPrinted valueUncertaintyEvidence
RNA-FM · Configuration0.035 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(RNA-FM), column(promoter)
LucaOne · Configuration0.164 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(LucaOne), column(promoter)
RESM · Configuration0.169 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(RESM), column(promoter)
Enformer · Configuration0.318 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Enformer), column(promoter)
GENERator-3B · Configuration0.172 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(GENERator-3B), column(promoter)
structRFM · Configuration0.033 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(structRFM), column(promoter)
N.T.-v2-50m · Configuration0.220 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(N.T.-v2-50m), column(promoter)
Evo_1.5_8k_base · Configuration0.037 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Evo_1.5_8k_base), column(promoter)
Evo2-7B · Configuration0.043 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Evo2-7B), column(promoter)
Crafts · Configuration0.029 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Crafts), column(promoter)
Evo_1_8k_base · Configuration0.107 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Evo_1_8k_base), column(promoter)
Evo_1_8k · Configuration0.107 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Evo_1_8k), column(promoter)
BiRNA-BERT · Configuration0.031 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(BiRNA-BERT), column(promoter)
RNAernie · Configuration0.081 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(RNAernie), column(promoter)
Evo2-7B-base · Configuration0.128 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Evo2-7B-base), column(promoter)
GENA-LM-large · Configuration0.592 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(GENA-LM-large), column(promoter)
HyenaDNA · Configuration0.037 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(HyenaDNA), column(promoter)
GenerRNA · Configuration0.171 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(GenerRNA), column(promoter)
Dnabert · Configuration0.049 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Dnabert), column(promoter)
AIDO.RNA · Configuration0.095 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(AIDO.RNA), column(promoter)
LucaVirus · Configuration0.164 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(LucaVirus), column(promoter)
GenSLM · Configuration0.171 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(GenSLM), column(promoter)
Dnabert_6 · Configuration0.068 correlationNot reportedAuthor-reported evaluation · source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Dnabert_6), column(promoter)
Scope and limitations
  • Author-reported numbers, source checked but not independently reproduced.
  • Zero-shot, few-shot and supervised cross validation figures come from different protocols and are not comparable to each other.
  • The per-nucleotide-type figures and the overall figures describe the same runs at different resolutions, so they must not be combined.

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 · 23 evaluations · 23 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
AIDO.RNA on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: AIDO.RNATask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.095 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(AIDO.RNA), column(promoter)

Source checking is not independent reproduction.

BiRNA-BERT on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: BiRNA-BERTTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.031 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(BiRNA-BERT), column(promoter)

Source checking is not independent reproduction.

Crafts on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: CraftsTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.029 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Crafts), column(promoter)

Source checking is not independent reproduction.

Dnabert_6 on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: Dnabert_6Task: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.068 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Dnabert_6), column(promoter)

Source checking is not independent reproduction.

Dnabert on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: DnabertTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.049 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Dnabert), column(promoter)

Source checking is not independent reproduction.

Enformer on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: EnformerTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.318 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Enformer), column(promoter)

Source checking is not independent reproduction.

Evo_1.5_8k_base on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: Evo_1.5_8k_baseTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.037 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Evo_1.5_8k_base), column(promoter)

Source checking is not independent reproduction.

Evo_1_8k_base on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: Evo_1_8k_baseTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.107 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Evo_1_8k_base), column(promoter)

Source checking is not independent reproduction.

Evo_1_8k on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: Evo_1_8kTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.107 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Evo_1_8k), column(promoter)

Source checking is not independent reproduction.

Evo2-7B-base on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: Evo2-7B-baseTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.128 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Evo2-7B-base), column(promoter)

Source checking is not independent reproduction.

Evo2-7B on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: Evo2-7BTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.043 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(Evo2-7B), column(promoter)

Source checking is not independent reproduction.

GENA-LM-large on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: GENA-LM-largeTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.592 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(GENA-LM-large), column(promoter)

Source checking is not independent reproduction.

GENERator-3B on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: GENERator-3BTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.172 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(GENERator-3B), column(promoter)

Source checking is not independent reproduction.

GenerRNA on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: GenerRNATask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.171 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(GenerRNA), column(promoter)

Source checking is not independent reproduction.

GenSLM on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: GenSLMTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.171 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(GenSLM), column(promoter)

Source checking is not independent reproduction.

HyenaDNA on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: HyenaDNATask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.037 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(HyenaDNA), column(promoter)

Source checking is not independent reproduction.

LucaOne on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: LucaOneTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.164 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(LucaOne), column(promoter)

Source checking is not independent reproduction.

LucaVirus on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: LucaVirusTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.164 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(LucaVirus), column(promoter)

Source checking is not independent reproduction.

N.T.-v2-50m on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: N.T.-v2-50mTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.220 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(N.T.-v2-50m), column(promoter)

Source checking is not independent reproduction.

RESM on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: RESMTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.169 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(RESM), column(promoter)

Source checking is not independent reproduction.

RNA-FM on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: RNA-FMTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.035 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(RNA-FM), column(promoter)

Source checking is not independent reproduction.

RNAernie on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: RNAernieTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.081 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(RNAernie), column(promoter)

Source checking is not independent reproduction.

structRFM on NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation
Configuration: structRFMTask: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validationDataset subset: NABench promoter assays (NABench split)

Scored supervised, contiguous cross validation across the NABench promoter assays.

Author-reported evaluation · Evaluation metadata: source checked

0.033 spearman

Unit: correlation · Direction: higher

Uncertainty: Not reported

Scored: Not reported · Eligible: Not reported

source checkedNABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(structRFM), column(promoter)

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-nabench

Individual claims		NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction

Original source ↗

Table 11, column(promoter)

Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Retrieved: 2026-09-17T08:06:28.183421+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-nabench

Claim: nabench-association-ccv-corr-promoter

Source artifact SHA-256: fefd48d53b1a7eadf9e14db96adacc8e646304c1b592562d9f136f4508941350

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

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: nabench-task-ccv-corr-promoter

areas
rna-transcriptomes
tasks
Fitness prediction on promoter assays, supervised, contiguous cross validation
metric
Spearman ρ
metric direction
higher
dataset
NABench promoter assays
protocol
Scored supervised, contiguous cross validation across the NABench promoter assays.
source locator
Table 11, column(promoter)
comparison panels
id: nabench-panel-ccv-corr-promoter; title: NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation; protocol id: nabench-task-ccv-corr-promoter; dataset id: nabench-dataset-nabench-promoter-assays; metric: spearman; unit: correlation; direction: higher; result ids: nabench-result-rna-fm-ccv-corr-promoter-spearman; nabench-result-lucaone-ccv-corr-promoter-spearman; nabench-result-resm-ccv-corr-promoter-spearman; nabench-result-enformer-ccv-corr-promoter-spearman; nabench-result-generator-3b-ccv-corr-promoter-spearman; nabench-result-structrfm-ccv-corr-promoter-spearman; nabench-result-n-t-v2-50m-ccv-corr-promoter-spearman; nabench-result-evo-1-5-8k-base-ccv-corr-promoter-spearman; nabench-result-evo2-7b-ccv-corr-promoter-spearman; nabench-result-crafts-ccv-corr-promoter-spearman; nabench-result-evo-1-8k-base-ccv-corr-promoter-spearman; nabench-result-evo-1-8k-ccv-corr-promoter-spearman; nabench-result-birna-bert-ccv-corr-promoter-spearman; nabench-result-rnaernie-ccv-corr-promoter-spearman; nabench-result-evo2-7b-base-ccv-corr-promoter-spearman; nabench-result-gena-lm-large-ccv-corr-promoter-spearman; nabench-result-hyenadna-ccv-corr-promoter-spearman; nabench-result-generrna-ccv-corr-promoter-spearman; nabench-result-dnabert-ccv-corr-promoter-spearman; nabench-result-aido-rna-ccv-corr-promoter-spearman; nabench-result-lucavirus-ccv-corr-promoter-spearman; nabench-result-genslm-ccv-corr-promoter-spearman; nabench-result-dnabert-6-ccv-corr-promoter-spearman; source ids: evidence-expansion-nabench-fefd48d5; source locator: Table 11, column(promoter); context: Every method NABench reports on Fitness prediction on promoter assays, supervised, contiguous cross validation, scored with Spearman ρ on NABench promoter assays.; caveats: Author-reported numbers, source checked but not independently reproduced.; Zero-shot, few-shot and supervised cross validation figures come from different protocols and are not comparable to each other.; The per-nucleotide-type figures and the overall figures describe the same runs at different resolutions, so they must not be combined.; review: method: automated_source_review; date: 2026-09-18
Related records

Suggest a correction