Result

F1 (NT benchmark Promoter All, frozen-embedding probe) of HyenaDNA-436K, frozen embeddings with a lightweight probe (Datta et al. 2026) on Nucleotide Transformer benchmark task data (Datta et al. 2026)

0.933 F1 (NT benchmark Promoter All, frozen-embedding probe)

Evidence concern: excluded from comparisons

Table 1 prints the same frozen value and spread (.5252+-.0262) for NT on both 'Enhancer' and 'Enhancer Types', while the fine-tuned references differ (.548 and .424). One of the two frozen cells is likely a transcription error in the source; both are kept as printed and should not support comparison until the authors clarify.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'NT', rows 'Enhancer' and 'Enhancer Types'

Table 1 and Table 4 disagree for HyenaDNA Splice Acceptor: Table 1 prints .4752±.0108 (recovery 50), while Table 4 prints 0.7308 ± 0.0033 (validation-selected) and 0.7360 ± 0.0052 (diagnostic grid-best). Five other HyenaDNA cells of Table 1 equal Table 4's grid-best values, but Splice Donor (.7247±.0087) equals the validation-selected value instead. Table 3 and Table 4 also name different grid-best readouts for HyenaDNA Splice All (MLP+Mean against MLP+Attn). Table 1 values are kept as printed.Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, column 'HyenaDNA', rows 'Splice Acceptor' and 'Splice Donor'; Table 4; Table 3, row 'Splice All'

Methods

Tested configuration: HyenaDNA-436K, frozen embeddings with a lightweight probe (Datta et al. 2026)
Protocol: Nucleotide Transformer benchmark under frozen-embedding probing (Datta et al. 2026 Table 1)
Dataset: Nucleotide Transformer benchmark task data (Datta et al. 2026)
Procedure: Nucleotide Transformer benchmark under frozen-embedding probing (Datta et al. 2026 Table 1)
Evaluation: HyenaDNA-436K on NT benchmark Promoter All (frozen probe)
Coverage: Not reported scored / Not reported eligible
Uncertainty: SD 0.0004
Evidence: Independent external evaluation · source checkedFrozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Table 1, row 'Promoter All', column 'HyenaDNA', frozen value

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: Benchmark train/test split
Adaptation: None: frozen backbone with a trained probe
Scoring implementation: F1 score

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

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance
Reported result .9329 Individual claims	Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models Original source ↗ Table 1, row 'Promoter All', column 'HyenaDNA', frozen value Version: arXiv:2608.05329v1, submitted 2026-08-05 Retrieved: 2026-10-11T00:51:27Z	source checked ["source-hash-verification","pdf-text-parse","independent-cell-check"] · 2026-10-11 independent paper Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Independent review 2026-10-11: value and identity match the source; printed recovery agrees with the two scores. Corrected in review: metric_qualifier changed from 'frozen-embedding probe' to 'NT benchmark Promoter All, frozen-embedding probe'. Field: `attributes.printed_value` Source artifact SHA-256: `df36e4772562329550c924004a546812c8d76149a1b5238e4d0b0cfa8a82bb5c` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact Extraction artifact SHA-256: `df36e4772562329550c924004a546812c8d76149a1b5238e4d0b0cfa8a82bb5c` Extraction artifact

How to read the evidence

Sources and history

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

1 source record and release history

Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models · Original source · arXiv:2608.05329v1, submitted 2026-08-05

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm2-20261011-datta2026-result-hyenadna-promoter-all-frozen

metric: f1-score
metric direction: higher
unit: fraction
printed value: .9329
numeric value: 0.9329
source locator: Table 1, row 'Promoter All', column 'HyenaDNA', frozen value
metric qualifier: NT benchmark Promoter All, frozen-embedding probe
uncertainty: type: standard_deviation; value: 0.0004; printed: ±.0004; n: 5; scope: Five probe seeds
review: method: source-hash-verification; pdf-text-parse; independent-cell-check; method note: Re-downloaded the arXiv PDF and matched the pinned SHA-256. Parsed Table 1 from the `pdftotext -layout` (poppler 26.08.0) text with a separate parser (review/review.py) and checked printed value, numeric value, spread, metric (Section 3.2), qualifier, unit, direction, locator and the linked configuration, protocol and dataset; recomputed each cell's printed recovery from the two scores as a transcription check.; reviewer: claude; reviewer note: Claude (Opus 5.5) review agent reviewer-gfm-a, independent of the extractor lit-gfm-2; no human review claimed; date: 2026-10-11; artifact sha256: df36e4772562329550c924004a546812c8d76149a1b5238e4d0b0cfa8a82bb5c; retrieval url: https://arxiv.org/pdf/2608.05329v1; note: Independent review 2026-10-11: value and identity match the source; printed recovery agrees with the two scores. Corrected in review: metric_qualifier changed from 'frozen-embedding probe' to 'NT benchmark Promoter All, frozen-embedding probe'.

Related records

evaluation: HyenaDNA-436K on NT benchmark Promoter All (frozen probe)

Suggest a correction