Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 512 tokens) of NTv2 (250M) on one A100 80 GB (Aspidova et al. 2026) on Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)
30.6 Inference throughput (Encoder forward pass on one A100 80 GB; sequence length 512 tokens)
Methods
- Tested configuration
- NTv2 (250M) on one A100 80 GB (Aspidova et al. 2026)
- Protocol
- DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2)
- Dataset
- Fixed-length token sequences of 256 to 8,192 tokens (Aspidova et al. 2026)
- Procedure
- DNA language model inference throughput and maximum batch size on one A100 80 GB by sequence length (Aspidova et al. 2026 Table 2)
- Evaluation
- NTv2 (250M) inference throughput on one A100 (Aspidova et al. 2026)
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- Not reported by the source: Mean of 10 timing runs; spread not printed
- Evidence
- Independent external evaluation · source checkedBack to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Appendix B Table 2 (page 9), row 'NTv2 (250M)', sequence length L = 512, column 'tokens/s'
A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.
Reproduction
- Split
- Fixed-length inputs, L = 256 to 8192 tokens
- Adaptation
- None (pretrained encoder, forward pass only)
- Scoring implementation
- Maximum batch size by exponential growth and binary search; mean of 10 timing runs
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.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Reported result 30.62 Individual claims | Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models Appendix B Table 2 (page 9), row 'NTv2 (250M)', sequence length L = 512, column 'tokens/s' Version: bioRxiv preprint version 1, posted 2026-04-23 | source checked ["source-hash-verification","pdf-text-parse","rendered-source-visual-check","independent-cell-check"] · 2026-10-12T07:50:32Z independent paper Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsIndependent review 2026-10-12: printed value, numeric value, metric, qualifier, unit, direction, uncertainty, locator and configuration and protocol identity match the source. Transcribed, not reproduced. Field: Source artifact SHA-256: Hash scope: bioRxiv stamps each PDF download, so artifact_sha256 describes one retrieval; retrieved_at is the file's modification time. The pdftotext -layout text layer has SHA-256 ebaf0541c173359940737efde2c15d4ab4aa37d7cc323b3922a818feb5be6b4b. A second download at 21:43Z was refused with HTTP 429. Extraction artifact SHA-256: |
Sources and history
Release 2026-10-23-5347695500ed · Record review: source checked
1 source record and release history
- Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models · Original source · bioRxiv preprint version 1, posted 2026-04-23
Technical metadata and extraction receipts
Stable ID: model-execution-20261011-result-aspidova2026-ntv2-250m-l512-throughput
- metric
- inference-throughput
- metric direction
- higher
- unit
- sample-per-second
- metric qualifier
- Encoder forward pass on one A100 80 GB; sequence length 512 tokens
- unit detail
- printed tokens/s; see the protocol limitation on scale
- printed value
- 30.62
- numeric value
- 30.62
- source locator
- Appendix B Table 2 (page 9), row 'NTv2 (250M)', sequence length L = 512, column 'tokens/s'
- missing metadata
- uncertainty: reason: unreported; note: Mean of 10 timing runs; spread not printed
- review
- method: source-hash-verification; pdf-text-parse; rendered-source-visual-check; independent-cell-check; method note: Archived PDF matched the pinned SHA-256; a fresh bioRxiv download had the same text-layer SHA-256. Appendix B Table 2 parsed from pdftotext -layout with a separate review script (108 cells, 16 dashes) and every row read against a 200 dpi render of page 9.; reviewer: claude; reviewer note: Claude (Opus 5.5) review agent reviewer-exec, independent of the extractor uc-execution; no human review claimed; reviewed at: 2026-10-12T07:50:32Z; artifact sha256: 238ab9916d54b419bf31fd79ecf146d654eb6574d3b441aa2043d39632e709fa; retrieval url: https://www.biorxiv.org/content/10.64898/2026.04.21.719816v1.full.pdf; note: Independent review 2026-10-12: printed value, numeric value, metric, qualifier, unit, direction, uncertainty, locator and configuration and protocol identity match the source. Transcribed, not reproduced.