Evaluation

NT 500M human reference, 5-epoch fine-tuning time (Hegde et al. 2025 Table A1)

Published result; transcribed, not reproduced.

Evaluation results

1 evaluation · 6 results. Different protocols are not a single leaderboard.

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: NT 500M human reference, fine-tuned 5 epochs, unpruned (Hegde et al. 2025)	Protocol: Fine-tuning and evaluation wall time, 5 epochs on the Enformer eQTL dataset (Hegde et al. 2025 Table A1) Dataset: Enformer eQTL causal-variant dataset, Genomics Long-Range Benchmark version (Hegde et al. 2025)	8.49 Runtime (Evaluation on the eQTL test split after 5-epoch fine-tuning) minute · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 500M human reference, 5-epoch fine-tuning time (Hegde et al. 2025 Table A1) gfm-guide-20261014-protocol-hegde-eqtl-finetune-5-epochs-time Aggregation: Not reported Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction · Table A1, row seed 41, column 'Evaluation Time (Minutes)'
Configuration: NT 500M human reference, fine-tuned 5 epochs, unpruned (Hegde et al. 2025)	Protocol: Fine-tuning and evaluation wall time, 5 epochs on the Enformer eQTL dataset (Hegde et al. 2025 Table A1) Dataset: Enformer eQTL causal-variant dataset, Genomics Long-Range Benchmark version (Hegde et al. 2025)	8.51 Runtime (Evaluation on the eQTL test split after 5-epoch fine-tuning) minute · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 500M human reference, 5-epoch fine-tuning time (Hegde et al. 2025 Table A1) gfm-guide-20261014-protocol-hegde-eqtl-finetune-5-epochs-time Aggregation: Not reported Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction · Table A1, row seed 42, column 'Evaluation Time (Minutes)'
Configuration: NT 500M human reference, fine-tuned 5 epochs, unpruned (Hegde et al. 2025)	Protocol: Fine-tuning and evaluation wall time, 5 epochs on the Enformer eQTL dataset (Hegde et al. 2025 Table A1) Dataset: Enformer eQTL causal-variant dataset, Genomics Long-Range Benchmark version (Hegde et al. 2025)	8.49 Runtime (Evaluation on the eQTL test split after 5-epoch fine-tuning) minute · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 500M human reference, 5-epoch fine-tuning time (Hegde et al. 2025 Table A1) gfm-guide-20261014-protocol-hegde-eqtl-finetune-5-epochs-time Aggregation: Not reported Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction · Table A1, row seed 43, column 'Evaluation Time (Minutes)'
Configuration: NT 500M human reference, fine-tuned 5 epochs, unpruned (Hegde et al. 2025)	Protocol: Fine-tuning and evaluation wall time, 5 epochs on the Enformer eQTL dataset (Hegde et al. 2025 Table A1) Dataset: Enformer eQTL causal-variant dataset, Genomics Long-Range Benchmark version (Hegde et al. 2025)	7.53 Runtime (Fine-tuning, 5 epochs, unpruned model) hour · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 500M human reference, 5-epoch fine-tuning time (Hegde et al. 2025 Table A1) gfm-guide-20261014-protocol-hegde-eqtl-finetune-5-epochs-time Aggregation: Not reported Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction · Table A1, row seed 41, column 'Training Time (Hours)'
Configuration: NT 500M human reference, fine-tuned 5 epochs, unpruned (Hegde et al. 2025)	Protocol: Fine-tuning and evaluation wall time, 5 epochs on the Enformer eQTL dataset (Hegde et al. 2025 Table A1) Dataset: Enformer eQTL causal-variant dataset, Genomics Long-Range Benchmark version (Hegde et al. 2025)	7.5 Runtime (Fine-tuning, 5 epochs, unpruned model) hour · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 500M human reference, 5-epoch fine-tuning time (Hegde et al. 2025 Table A1) gfm-guide-20261014-protocol-hegde-eqtl-finetune-5-epochs-time Aggregation: Not reported Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction · Table A1, row seed 42, column 'Training Time (Hours)'
Configuration: NT 500M human reference, fine-tuned 5 epochs, unpruned (Hegde et al. 2025)	Protocol: Fine-tuning and evaluation wall time, 5 epochs on the Enformer eQTL dataset (Hegde et al. 2025 Table A1) Dataset: Enformer eQTL causal-variant dataset, Genomics Long-Range Benchmark version (Hegde et al. 2025)	7.48 Runtime (Fine-tuning, 5 epochs, unpruned model) hour · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 500M human reference, 5-epoch fine-tuning time (Hegde et al. 2025 Table A1) gfm-guide-20261014-protocol-hegde-eqtl-finetune-5-epochs-time Aggregation: Not reported Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction · Table A1, row seed 43, column 'Training Time (Hours)'

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

Fine-tuning and evaluation wall time, 5 epochs on the Enformer eQTL dataset (Hegde et al. 2025 Table A1)

Configuration: NT 500M human reference, fine-tuned 5 epochs, unpruned (Hegde et al. 2025)
Protocol: Fine-tuning and evaluation wall time, 5 epochs on the Enformer eQTL dataset (Hegde et al. 2025 Table A1)
Dataset: Enformer eQTL causal-variant dataset, Genomics Long-Range Benchmark version (Hegde et al. 2025)

origin: Independent external evaluation
configuration: Primary source as retrieved 2026-10-14
dataset version: Not reported
split: Benchmark train split for fine-tuning; evaluation split for evaluation
population: Enformer eQTL causal-variant sequences
inputs: Variant-centred DNA sequences
adaptation: LoRA parameter-efficient fine-tuning (peft; r=1, lora_alpha=32, lora_dropout=0.1)
metric implementation: Not reported
aggregation: One value per seed
budget: 5 epochs
protocol id: gfm-guide-20261014-protocol-hegde-eqtl-finetune-5-epochs-time

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

Reproduction

Split: Benchmark train split for fine-tuning; evaluation split for evaluation
Adaptation: LoRA parameter-efficient fine-tuning (peft; r=1, lora_alpha=32, lora_dropout=0.1)
Scoring implementation: Not reported

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.

19 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: aggregation One value per seed Context-only references	Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction Original source ↗ Table A1 Version: Genes 16(11):1358, 2025; PMC12652071 full-text XML Retrieved: 2026-10-14T12:48:26Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.aggregation` Source artifact SHA-256: `9ea68b688637b40f0aeced7c905822f6b14c352a3a935c61c407945f3d66ef47` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: budget 5 epochs Context-only references	Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction Original source ↗ Table A1 Version: Genes 16(11):1358, 2025; PMC12652071 full-text XML Retrieved: 2026-10-14T12:48:26Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.budget` Source artifact SHA-256: `9ea68b688637b40f0aeced7c905822f6b14c352a3a935c61c407945f3d66ef47` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: dataset version Not reported Context-only references	Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction Original source ↗ Table A1 Version: Genes 16(11):1358, 2025; PMC12652071 full-text XML Retrieved: 2026-10-14T12:48:26Z	missing or unspecified No individual claim review recorded independent paper Audit details Field: `attributes.comparison.dataset_version` Source artifact SHA-256: `9ea68b688637b40f0aeced7c905822f6b14c352a3a935c61c407945f3d66ef47` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: inputs Variant-centred DNA sequences Context-only references	Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction Original source ↗ Table A1 Version: Genes 16(11):1358, 2025; PMC12652071 full-text XML Retrieved: 2026-10-14T12:48:26Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.inputs` Source artifact SHA-256: `9ea68b688637b40f0aeced7c905822f6b14c352a3a935c61c407945f3d66ef47` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: metric implementation Not reported Context-only references	Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction Original source ↗ Table A1 Version: Genes 16(11):1358, 2025; PMC12652071 full-text XML Retrieved: 2026-10-14T12:48:26Z	missing or unspecified No individual claim review recorded independent paper Audit details Field: `attributes.comparison.metric_implementation` Source artifact SHA-256: `9ea68b688637b40f0aeced7c905822f6b14c352a3a935c61c407945f3d66ef47` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: population Enformer eQTL causal-variant sequences Context-only references	Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction Original source ↗ Table A1 Version: Genes 16(11):1358, 2025; PMC12652071 full-text XML Retrieved: 2026-10-14T12:48:26Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.population` Source artifact SHA-256: `9ea68b688637b40f0aeced7c905822f6b14c352a3a935c61c407945f3d66ef47` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: protocol id gfm-guide-20261014-protocol-hegde-eqtl-finetune-5-epochs-time Context-only references	Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction Original source ↗ Table A1 Version: Genes 16(11):1358, 2025; PMC12652071 full-text XML Retrieved: 2026-10-14T12:48:26Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.protocol_id` Source artifact SHA-256: `9ea68b688637b40f0aeced7c905822f6b14c352a3a935c61c407945f3d66ef47` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: split Benchmark train split for fine-tuning; evaluation split for evaluation Context-only references	Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction Original source ↗ Table A1 Version: Genes 16(11):1358, 2025; PMC12652071 full-text XML Retrieved: 2026-10-14T12:48:26Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.split` Source artifact SHA-256: `9ea68b688637b40f0aeced7c905822f6b14c352a3a935c61c407945f3d66ef47` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
N runs 3 Context-only references	Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction Original source ↗ Table A1 Version: Genes 16(11):1358, 2025; PMC12652071 full-text XML Retrieved: 2026-10-14T12:48:26Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.n_runs` Source artifact SHA-256: `9ea68b688637b40f0aeced7c905822f6b14c352a3a935c61c407945f3d66ef47` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Origin independent_paper Context-only references	Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction Original source ↗ Table A1 Version: Genes 16(11):1358, 2025; PMC12652071 full-text XML Retrieved: 2026-10-14T12:48:26Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.origin` Source artifact SHA-256: `9ea68b688637b40f0aeced7c905822f6b14c352a3a935c61c407945f3d66ef47` 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

1 source record and release history

Reaping the Fruits of LLM Pruning: Towards Small Language Models for Efficient Non-Coding Variant Effect Prediction · Original source · Genes 16(11):1358, 2025; PMC12652071 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm-guide-20261014-eval-hegde-nt-500m-human-ref-5-epochs

areas: dna-genomes
contexts: research
origin: independent_paper
protocol: gfm-guide-20261014-protocol-hegde-eqtl-finetune-5-epochs-time
version: Primary source as retrieved 2026-10-14
comparison: dataset version: Not reported; split: Benchmark train split for fine-tuning; evaluation split for evaluation; population: Enformer eQTL causal-variant sequences; inputs: Variant-centred DNA sequences; adaptation: LoRA parameter-efficient fine-tuning (peft; r=1, lora_alpha=32, lora_dropout=0.1); metric implementation: Not reported; aggregation: One value per seed; budget: 5 epochs; protocol id: gfm-guide-20261014-protocol-hegde-eqtl-finetune-5-epochs-time
source locator: Table A1
missing metadata: comparison.dataset version: reason: unreported; comparison.metric implementation: reason: unreported
training hardware: 2 × NVIDIA TITAN Xp (Methods)
n runs: 3

Related records

system: NT 500M human reference, fine-tuned 5 epochs, unpruned (Hegde et al. 2025)
assessment: Fine-tuning and evaluation wall time, 5 epochs on the Enformer eQTL dataset (Hegde et al. 2025 Table A1)
data: Enformer eQTL causal-variant dataset, Genomics Long-Range Benchmark version (Hegde et al. 2025)
evaluation: NT 500M human ref evaluation time, seed 41
evaluation: NT 500M human ref evaluation time, seed 42
evaluation: NT 500M human ref evaluation time, seed 43
evaluation: NT 500M human ref 5-epoch training time, seed 41
evaluation: NT 500M human ref 5-epoch training time, seed 42
evaluation: NT 500M human ref 5-epoch training time, seed 43
subject: gfm-guide-20261014-eval-hegde-nt-500m-human-ref-5-epochs: attributes.comparison.adaptation

Suggest a correction