Evaluation

UTRLM on NT-splice-sites-donors

Published comparison; transcribed, not reproduced.

Evaluation results

1 evaluation · 4 results. Different protocols are not a single leaderboard.

Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) · Dataset: Nucleotide Transformer benchmark splice-site dataset, donors

Sorted by Accuracy (NT-splice-sites-donors, fine-tuned) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Accuracy (NT-splice-sites-donors, fine-tuned)	F1 (NT-splice-sites-donors, fine-tuned)	Precision (NT-splice-sites-donors, fine-tuned)	Recall (NT-splice-sites-donors, fine-tuned)
UTRLM fine-tuned with an appended convolutional layer (You et al. 2026)Evaluation	0.9741(0.0000)	0.9741(0.0000)	0.9741(0.0000)	0.9741(0.0000)

All 4 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: UTRLM fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9741(0.0000) Accuracy (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source UTRLM on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM', column 'Accuracy'
Configuration: UTRLM fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9741(0.0000) F1 (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source UTRLM on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM', column 'F1 Score'
Configuration: UTRLM fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9741(0.0000) Precision (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source UTRLM on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM', column 'Precision'
Configuration: UTRLM fine-tuned with an appended convolutional layer (You et al. 2026)	Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4) Dataset: Nucleotide Transformer benchmark splice-site dataset, donors	0.9741(0.0000) Recall (NT-splice-sites-donors, fine-tuned) fraction · higher Uncertainty: SD 0.0000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source UTRLM on NT-splice-sites-donors gfm2-20261011-you2026-protocol-nt-splice-donors Aggregation: Not reported Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications; You et al. 2026, Supplementary Information · Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM', column 'Recall'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Research readiness

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.

Readiness checks, gaps and artifacts

Release 2026-10-22-1b7cf027e4f6 · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Metrics are recomputed from the saved predictions: not yet verified
Sample annotations are recorded: not yet verified
Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
A pinned run recipe exists: not yet verified
Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Independent validation data exist: not yet verified
Overlap with training data is checked: not yet verified

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.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Evaluation procedure

NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)

Configuration: UTRLM fine-tuned with an appended convolutional layer (You et al. 2026)
Protocol: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)
Dataset: Nucleotide Transformer benchmark splice-site dataset, donors

origin: Independent external evaluation
configuration: Primary source as retrieved 2026-10-11
protocol id: gfm2-20261011-you2026-protocol-nt-splice-donors
dataset version: NT-splice-sites-donors as used by You et al. 2026
split: 19,775 train / 2,198 test
population: 147 species, 2 categories; 21,973 sequences
inputs: DNA sequence from the NT benchmark splice-site dataset; length not stated in this source
adaptation: Fine-tuned with an appended convolution head
metric implementation: F1 score, precision, recall and accuracy
aggregation: Mean over three fine-tuning runs
budget: Not reported

Metadata review: source checked. Unreported conditions prevent automatic comparisons.

Reproduction

Split: 19,775 train / 2,198 test
Adaptation: Fine-tuned with an appended convolution head
Scoring implementation: F1 score, precision, recall and accuracy

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

Evidence

Source checking verifies the cited claim or transcription. It does not establish 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.

38 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance
Comparison: adaptation Fine-tuned with an appended convolution head Context-only references	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.adaptation` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: adaptation Fine-tuned with an appended convolution head Context-only references	You et al. 2026, Supplementary Information Original source ↗ Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 41467_2025_66899_MOESM1_ESM.pdf inside the Europe PMC supplementaryFiles zip (outer zip 9a0d0a8d8643872ab265e3e6ed7eea944563da4861bf764f97c68fc6aa502525, assembled per request; the member hash is the bound artifact) Retrieved: 2026-10-11T00:55:34Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.adaptation` Source artifact SHA-256: `cbb69e05045a4526e35479d2c1361ebb9cfadfd968e00675390dad597035d882` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: aggregation Mean over three fine-tuning runs Context-only references	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.aggregation` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: aggregation Mean over three fine-tuning runs Context-only references	You et al. 2026, Supplementary Information Original source ↗ Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 41467_2025_66899_MOESM1_ESM.pdf inside the Europe PMC supplementaryFiles zip (outer zip 9a0d0a8d8643872ab265e3e6ed7eea944563da4861bf764f97c68fc6aa502525, assembled per request; the member hash is the bound artifact) Retrieved: 2026-10-11T00:55:34Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.aggregation` Source artifact SHA-256: `cbb69e05045a4526e35479d2c1361ebb9cfadfd968e00675390dad597035d882` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: budget Not reported Context-only references	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	missing or unspecified No individual claim review recorded independent paper Audit details Field: `attributes.comparison.budget` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: budget Not reported Context-only references	You et al. 2026, Supplementary Information Original source ↗ Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 41467_2025_66899_MOESM1_ESM.pdf inside the Europe PMC supplementaryFiles zip (outer zip 9a0d0a8d8643872ab265e3e6ed7eea944563da4861bf764f97c68fc6aa502525, assembled per request; the member hash is the bound artifact) Retrieved: 2026-10-11T00:55:34Z	missing or unspecified No individual claim review recorded independent paper Audit details Field: `attributes.comparison.budget` Source artifact SHA-256: `cbb69e05045a4526e35479d2c1361ebb9cfadfd968e00675390dad597035d882` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: dataset version NT-splice-sites-donors as used by You et al. 2026 Context-only references	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.dataset_version` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: dataset version NT-splice-sites-donors as used by You et al. 2026 Context-only references	You et al. 2026, Supplementary Information Original source ↗ Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 41467_2025_66899_MOESM1_ESM.pdf inside the Europe PMC supplementaryFiles zip (outer zip 9a0d0a8d8643872ab265e3e6ed7eea944563da4861bf764f97c68fc6aa502525, assembled per request; the member hash is the bound artifact) Retrieved: 2026-10-11T00:55:34Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.dataset_version` Source artifact SHA-256: `cbb69e05045a4526e35479d2c1361ebb9cfadfd968e00675390dad597035d882` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: inputs DNA sequence from the NT benchmark splice-site dataset; length not stated in this source Context-only references	Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications Original source ↗ Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML Retrieved: 2026-10-11T00:55:34Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.inputs` Source artifact SHA-256: `2c6b2816846a21296c56b4dd58f3d1e8810e9d96e224d3ab21b5eb8faa9928e4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: inputs DNA sequence from the NT benchmark splice-site dataset; length not stated in this source Context-only references	You et al. 2026, Supplementary Information Original source ↗ Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 41467_2025_66899_MOESM1_ESM.pdf inside the Europe PMC supplementaryFiles zip (outer zip 9a0d0a8d8643872ab265e3e6ed7eea944563da4861bf764f97c68fc6aa502525, assembled per request; the member hash is the bound artifact) Retrieved: 2026-10-11T00:55:34Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.inputs` Source artifact SHA-256: `cbb69e05045a4526e35479d2c1361ebb9cfadfd968e00675390dad597035d882` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

2 source records and release history

Benchmarking pre-trained genomic language models for RNA sequence-related predictive applications · Original source · Nat Commun 17:223, published online 2025-12-07; PMC12780105 full-text XML
You et al. 2026, Supplementary Information · Original source · 41467_2025_66899_MOESM1_ESM.pdf inside the Europe PMC supplementaryFiles zip (outer zip 9a0d0a8d8643872ab265e3e6ed7eea944563da4861bf764f97c68fc6aa502525, assembled per request; the member hash is the bound artifact)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm2-20261011-you2026-eval-t4-nt-splice-donors-utrlm

areas: dna-genomes
contexts: research
origin: independent_paper
protocol: gfm2-20261011-you2026-protocol-nt-splice-donors
version: Primary source as retrieved 2026-10-11
comparison: protocol id: gfm2-20261011-you2026-protocol-nt-splice-donors; dataset version: NT-splice-sites-donors as used by You et al. 2026; split: 19,775 train / 2,198 test; population: 147 species, 2 categories; 21,973 sequences; inputs: DNA sequence from the NT benchmark splice-site dataset; length not stated in this source; adaptation: Fine-tuned with an appended convolution head; metric implementation: F1 score, precision, recall and accuracy; aggregation: Mean over three fine-tuning runs; budget: Not reported
source locator: Supplementary Table 4, block 'NT-splice-sites-donors', row 'UTRLM'
limitations: Fine-tuned and tested three times with different random initialisations; the printed spread is the standard deviation over those three runs (Methods, 'To ensure the reliability of our findings').; Input length for the NT splice-site datasets is not stated in this source; the 500 bp division applies to the GTEx task.; Each language model is fine-tuned with an appended convolution head, so the comparison measures the adapted model, not zero-shot likelihood.; Values are read from the Supplementary Information tables behind the figures; the main-text figures are not read.; Every printed standard deviation for this method in this table is 0.0000, which three runs with different random initialisations would not normally give; the source does not explain it.

Related records

system: UTRLM fine-tuned with an appended convolutional layer (You et al. 2026)
assessment: NT-splice-sites-donors splice-site classification, fine-tuned models (You et al. 2026 Supplementary Table 4)
data: Nucleotide Transformer benchmark splice-site dataset, donors
evaluation: t4-nt-splice-donors-UTRLM-Accuracy accuracy
evaluation: t4-nt-splice-donors-UTRLM-F1 Score f1-score
evaluation: t4-nt-splice-donors-UTRLM-Precision precision
evaluation: t4-nt-splice-donors-UTRLM-Recall recall

Suggest a correction