Dataset

Synthetic uniform random DNA sequences, seed 42 (Saadat and Fellay 2026)

DNA sequences sampled uniformly from A, C, G and T with random seed 42, used to measure implementation and hardware effects.

Evaluation results

10 evaluations · 10 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: GENA-LM 110M, efficient inference implementation (Saadat and Fellay 2026)	Protocol: Pseudo-perplexity agreement between reference and efficient implementations (Saadat and Fellay 2026 Figure 1) Dataset: Synthetic uniform random DNA sequences, seed 42 (Saadat and Fellay 2026)	r = 1.00 Pearson (Agreement of per-sequence pseudo-perplexity between the reference and the efficient implementation, 50 synthetic sequences of length 1000) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM 110M efficient implementation, pseudo-perplexity agreement with the reference saadat-fellay-20261015-protocol-pseudo-perplexity-agreement Aggregation: Not reported Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) · Figure 1 (page 4, raster), panel 'GENA-LM 110M', legend text 'r = 1.00'
Configuration: GENA-LM 110M, training with FlashAttention and checkpointing (Saadat and Fellay 2026)	Protocol: Training peak GPU memory under progressive optimizations, sequence length 1000, batch size 16 (Saadat and Fellay 2026 Figure 3) Dataset: Synthetic uniform random DNA sequences, seed 42 (Saadat and Fellay 2026)	1.18 Peak memory (Training, sequence length 1000, batch size 16, stage + Checkpointing (FlashAttention and activation checkpointing)) gigabyte · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM 110M training peak memory, stage + Checkpointing saadat-fellay-20261015-protocol-training-peak-memory Aggregation: Not reported Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) · Section 3.3 'ZeRO offload' paragraph (page 6): '(e.g., GENA-LM 110M increases from 1.18 to 2.49 GB)'; stage + Checkpointing (FlashAttention and activation checkpointing) of Figure 3
Configuration: GENA-LM 110M, training with FlashAttention, checkpointing and ZeRO-2 offload (Saadat and Fellay 2026)	Protocol: Training peak GPU memory under progressive optimizations, sequence length 1000, batch size 16 (Saadat and Fellay 2026 Figure 3) Dataset: Synthetic uniform random DNA sequences, seed 42 (Saadat and Fellay 2026)	2.49 Peak memory (Training, sequence length 1000, batch size 16, stage + DeepSpeed (FlashAttention, checkpointing and ZeRO Stage-2 CPU offload)) gigabyte · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM 110M training peak memory, stage + DeepSpeed saadat-fellay-20261015-protocol-training-peak-memory Aggregation: Not reported Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) · Section 3.3 'ZeRO offload' paragraph (page 6): '(e.g., GENA-LM 110M increases from 1.18 to 2.49 GB)'; stage + DeepSpeed (FlashAttention, checkpointing and ZeRO Stage-2 CPU offload) of Figure 3
Configuration: GENA-LM 336M, efficient inference implementation (Saadat and Fellay 2026)	Protocol: Pseudo-perplexity agreement between reference and efficient implementations (Saadat and Fellay 2026 Figure 1) Dataset: Synthetic uniform random DNA sequences, seed 42 (Saadat and Fellay 2026)	r = 1.00 Pearson (Agreement of per-sequence pseudo-perplexity between the reference and the efficient implementation, 50 synthetic sequences of length 1000) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GENA-LM 336M efficient implementation, pseudo-perplexity agreement with the reference saadat-fellay-20261015-protocol-pseudo-perplexity-agreement Aggregation: Not reported Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) · Figure 1 (page 4, raster), panel 'GENA-LM 336M', legend text 'r = 1.00'
Configuration: NT 2.5B, efficient inference implementation (Saadat and Fellay 2026)	Protocol: Pseudo-perplexity agreement between reference and efficient implementations (Saadat and Fellay 2026 Figure 1) Dataset: Synthetic uniform random DNA sequences, seed 42 (Saadat and Fellay 2026)	r = 0.98 Pearson (Agreement of per-sequence pseudo-perplexity between the reference and the efficient implementation, 50 synthetic sequences of length 1000) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 2.5B efficient implementation, pseudo-perplexity agreement with the reference saadat-fellay-20261015-protocol-pseudo-perplexity-agreement Aggregation: Not reported Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) · Figure 1 (page 4, raster), panel 'NT 2.5B', legend text 'r = 0.98'
Configuration: NT 2.5B, 4-bit weights for embedding inference (Saadat and Fellay 2026)	Protocol: Peak memory under 8-bit and 4-bit quantization relative to BF16 (Saadat and Fellay 2026 Figure 5) Dataset: Synthetic uniform random DNA sequences, seed 42 (Saadat and Fellay 2026)	5.6 Peak memory (Embedding inference with 4-bit weights; the paper calls it parameter memory in Section 2.4 and peak memory in Figure 5) gigabyte · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 2.5B 4-bit inference memory saadat-fellay-20261015-protocol-quantization-peak-memory Aggregation: Not reported Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) · Section 3.5 'Memory' paragraph (page 7): 'For NT 2.5B, memory decreases from 6.7 GB (BF16) to 5.6 GB (4-bit).'
Configuration: NT 2.5B, BF16 weights for embedding inference (Saadat and Fellay 2026)	Protocol: Peak memory under 8-bit and 4-bit quantization relative to BF16 (Saadat and Fellay 2026 Figure 5) Dataset: Synthetic uniform random DNA sequences, seed 42 (Saadat and Fellay 2026)	6.7 Peak memory (Embedding inference with BF16 weights; the paper calls it parameter memory in Section 2.4 and peak memory in Figure 5) gigabyte · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 2.5B BF16 inference memory saadat-fellay-20261015-protocol-quantization-peak-memory Aggregation: Not reported Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) · Section 3.5 'Memory' paragraph (page 7): 'For NT 2.5B, memory decreases from 6.7 GB (BF16) to 5.6 GB (4-bit).'
Configuration: NT 2.5B, training with FlashAttention and checkpointing (Saadat and Fellay 2026)	Protocol: Training peak GPU memory under progressive optimizations, sequence length 1000, batch size 16 (Saadat and Fellay 2026 Figure 3) Dataset: Synthetic uniform random DNA sequences, seed 42 (Saadat and Fellay 2026)	33.9 Peak memory (Training, sequence length 1000, batch size 16, stage + Checkpointing (FlashAttention and activation checkpointing)) gigabyte · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 2.5B training peak memory, stage + Checkpointing saadat-fellay-20261015-protocol-training-peak-memory Aggregation: Not reported Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) · Section 3.3 'ZeRO offload' paragraph (page 6): 'the NT 2.5B checkpoint (33.88 → 11.49 GB)'; stage + Checkpointing (FlashAttention and activation checkpointing) of Figure 3
Configuration: NT 2.5B, training with FlashAttention, checkpointing and ZeRO-2 offload (Saadat and Fellay 2026)	Protocol: Training peak GPU memory under progressive optimizations, sequence length 1000, batch size 16 (Saadat and Fellay 2026 Figure 3) Dataset: Synthetic uniform random DNA sequences, seed 42 (Saadat and Fellay 2026)	11.5 Peak memory (Training, sequence length 1000, batch size 16, stage + DeepSpeed (FlashAttention, checkpointing and ZeRO Stage-2 CPU offload)) gigabyte · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 2.5B training peak memory, stage + DeepSpeed saadat-fellay-20261015-protocol-training-peak-memory Aggregation: Not reported Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) · Section 3.3 'ZeRO offload' paragraph (page 6): 'the NT 2.5B checkpoint (33.88 → 11.49 GB)'; stage + DeepSpeed (FlashAttention, checkpointing and ZeRO Stage-2 CPU offload) of Figure 3
Configuration: NT 500M, efficient inference implementation (Saadat and Fellay 2026)	Protocol: Pseudo-perplexity agreement between reference and efficient implementations (Saadat and Fellay 2026 Figure 1) Dataset: Synthetic uniform random DNA sequences, seed 42 (Saadat and Fellay 2026)	r = 1.00 Pearson (Agreement of per-sequence pseudo-perplexity between the reference and the efficient implementation, 50 synthetic sequences of length 1000) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT 500M efficient implementation, pseudo-perplexity agreement with the reference saadat-fellay-20261015-protocol-pseudo-perplexity-agreement Aggregation: Not reported Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) · Figure 1 (page 4, raster), panel 'NT 500M', legend text 'r = 1.00'

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.

Dataset and evaluation context

A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.

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.

6 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
Population 50 sequences of length 1000 for the pseudo-perplexity comparison; counts for the other synthetic-input measurements are not stated Context-only references	Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) Original source ↗ Section 2.4 'Data' (page 3) Version: OpenReview PDF headed 'Published as a workshop paper at ICLR 2026' (11 pages; PDF CreationDate 2026-03-09) Retrieved: 2026-10-15T10:56:26Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.population` Source artifact SHA-256: `4bc2452110f280a7ba8baa4c7c28beac89769511019666bc77fc33af9b3bcd60` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Source location Section 2.4 'Data' (page 3) Context-only references	Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) Original source ↗ Section 2.4 'Data' (page 3) Version: OpenReview PDF headed 'Published as a workshop paper at ICLR 2026' (11 pages; PDF CreationDate 2026-03-09) Retrieved: 2026-10-15T10:56:26Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.source_locator` Source artifact SHA-256: `4bc2452110f280a7ba8baa4c7c28beac89769511019666bc77fc33af9b3bcd60` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Species None (synthetic) Context-only references	Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) Original source ↗ Section 2.4 'Data' (page 3) Version: OpenReview PDF headed 'Published as a workshop paper at ICLR 2026' (11 pages; PDF CreationDate 2026-03-09) Retrieved: 2026-10-15T10:56:26Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.species` Source artifact SHA-256: `4bc2452110f280a7ba8baa4c7c28beac89769511019666bc77fc33af9b3bcd60` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Split Not applicable: synthetic inputs for implementation measurements Context-only references	Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) Original source ↗ Section 2.4 'Data' (page 3) Version: OpenReview PDF headed 'Published as a workshop paper at ICLR 2026' (11 pages; PDF CreationDate 2026-03-09) Retrieved: 2026-10-15T10:56:26Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.split` Source artifact SHA-256: `4bc2452110f280a7ba8baa4c7c28beac89769511019666bc77fc33af9b3bcd60` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Description DNA sequences sampled uniformly from A, C, G and T with random seed 42, used to measure implementation and hardware effects. Context-only references	Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) Original source ↗ Section 2.4 'Data' (page 3) Version: OpenReview PDF headed 'Published as a workshop paper at ICLR 2026' (11 pages; PDF CreationDate 2026-03-09) Retrieved: 2026-10-15T10:56:26Z	not individually reviewed No individual claim review recorded Audit details Field: `description` Source artifact SHA-256: `4bc2452110f280a7ba8baa4c7c28beac89769511019666bc77fc33af9b3bcd60` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Name Synthetic uniform random DNA sequences, seed 42 (Saadat and Fellay 2026) Context-only references	Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) Original source ↗ Section 2.4 'Data' (page 3) Version: OpenReview PDF headed 'Published as a workshop paper at ICLR 2026' (11 pages; PDF CreationDate 2026-03-09) Retrieved: 2026-10-15T10:56:26Z	not individually reviewed No individual claim review recorded Audit details Field: `name` Source artifact SHA-256: `4bc2452110f280a7ba8baa4c7c28beac89769511019666bc77fc33af9b3bcd60` 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

Optimizing genomic language models for efficient training, fine-tuning, and inference (Saadat and Fellay, ICLR 2026 workshop) · Original source · OpenReview PDF headed 'Published as a workshop paper at ICLR 2026' (11 pages; PDF CreationDate 2026-03-09)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: saadat-fellay-20261015-data-synthetic-dna

areas: dna-genomes
contexts: research
population: 50 sequences of length 1000 for the pseudo-perplexity comparison; counts for the other synthetic-input measurements are not stated
split: Not applicable: synthetic inputs for implementation measurements
species: None (synthetic)
source locator: Section 2.4 'Data' (page 3)
missing metadata: version: reason: unreported; note: Generated by the authors' code; no code or data release is cited in the PDF
review: reviewer: claude; reviewer note: Claude review agent; no human review claimed. Independent Claude (Opus 5.5) review agent, separate from the extraction agent that built this batch. Automated review only. Transcription, not reproduction.; reviewed at: 2026-10-15T22:00:00Z; artifact sha256: 4bc2452110f280a7ba8baa4c7c28beac89769511019666bc77fc33af9b3bcd60; retrieval url: https://openreview.net/pdf?id=NUleWh1GFx; method: source-hash-verification; pdf-text-parse; ai-assisted-source-review; scope-review; method note: Descriptive fields, identity links and missing-metadata reasons checked against the PDF.; note: Checked; see the dated review.

Related records

Suggest a correction