Protocol

RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10)

Classification of 84.6 to 409 kb viral genomes from about four indexed sequences per class, for four foundation models and blastn.

5 evaluations · 30 results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

5 recorded evaluations, 30 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

5 evaluations · 30 results. Different protocols are not a single leaderboard.

Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) · Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes

Sorted by Accuracy (16-class long-sequence RVDB dataset, chunk-scored) (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 (16-class long-sequence RVDB dataset, chunk-scored)	Balanced accuracy (16-class long-sequence RVDB dataset, chunk-scored)	Macro F1 (16-class long-sequence RVDB dataset, chunk-scored)	MCC (16-class long-sequence RVDB dataset, chunk-scored)	Precision (16-class long-sequence RVDB dataset, chunk-scored, macro-averaged over classes)	Recall (16-class long-sequence RVDB dataset, chunk-scored, macro-averaged over classes)	Accuracy (16-class long-sequence RVDB dataset)	Balanced accuracy (16-class long-sequence RVDB dataset)	Macro F1 (16-class long-sequence RVDB dataset)	MCC (16-class long-sequence RVDB dataset)	Precision (16-class long-sequence RVDB dataset, macro-averaged over classes)	Recall (16-class long-sequence RVDB dataset, macro-averaged over classes)
NTv2-50M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)Evaluation	0.853 (best in column)	0.87 (best in column)	0.869 (best in column)	0.842 (best in column)	0.871 (best in column)	0.87 (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
NTv2-250M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)Evaluation	0.831	0.844	0.842	0.818	0.844	0.844	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
DNABERT-2, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)Evaluation	0.786	0.817	0.813	0.771	0.814	0.817	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)Evaluation	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	0.977 (best in column)	0.977 (best in column)	0.977 (best in column)	0.975 (best in column)	0.978 (best in column)	0.977 (best in column)
NTv3-650M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)Evaluation	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	0.953	0.953	0.953	0.95	0.958	0.953

All 30 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: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.977 Accuracy (16-class long-sequence RVDB dataset) fraction · higher Uncertainty: 95% CI 0.950 to 0.989. Wilson binomial interval quoted in Section 3.8; method stated in Section 2.9 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BLAST (blastn) on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'BLAST (blastn)', column 'Accuracy'
Configuration: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.977 Balanced accuracy (16-class long-sequence RVDB dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BLAST (blastn) on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'BLAST (blastn)', column 'Bal. Acc.'
Configuration: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.977 Macro F1 (16-class long-sequence RVDB dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BLAST (blastn) on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'BLAST (blastn)', column 'F1'
Configuration: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.975 MCC (16-class long-sequence RVDB dataset) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BLAST (blastn) on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'BLAST (blastn)', column 'MCC'
Configuration: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.978 Precision (16-class long-sequence RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BLAST (blastn) on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'BLAST (blastn)', column 'Precision'
Configuration: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.977 Recall (16-class long-sequence RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BLAST (blastn) on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'BLAST (blastn)', column 'Recall'
Configuration: DNABERT-2, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.786 Accuracy (16-class long-sequence RVDB dataset, chunk-scored) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-2ᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'DNABERT-2ᵃ', column 'Accuracy'
Configuration: DNABERT-2, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.817 Balanced accuracy (16-class long-sequence RVDB dataset, chunk-scored) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-2ᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'DNABERT-2ᵃ', column 'Bal. Acc.'
Configuration: DNABERT-2, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.813 Macro F1 (16-class long-sequence RVDB dataset, chunk-scored) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-2ᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'DNABERT-2ᵃ', column 'F1'
Configuration: DNABERT-2, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.771 MCC (16-class long-sequence RVDB dataset, chunk-scored) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-2ᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'DNABERT-2ᵃ', column 'MCC'
Configuration: DNABERT-2, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.814 Precision (16-class long-sequence RVDB dataset, chunk-scored, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-2ᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'DNABERT-2ᵃ', column 'Precision'
Configuration: DNABERT-2, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.817 Recall (16-class long-sequence RVDB dataset, chunk-scored, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-2ᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'DNABERT-2ᵃ', column 'Recall'
Configuration: NTv2-250M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.831 Accuracy (16-class long-sequence RVDB dataset, chunk-scored) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv2-250Mᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'NTv2-250Mᵃ', column 'Accuracy'
Configuration: NTv2-250M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.844 Balanced accuracy (16-class long-sequence RVDB dataset, chunk-scored) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv2-250Mᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'NTv2-250Mᵃ', column 'Bal. Acc.'
Configuration: NTv2-250M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.842 Macro F1 (16-class long-sequence RVDB dataset, chunk-scored) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv2-250Mᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'NTv2-250Mᵃ', column 'F1'
Configuration: NTv2-250M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.818 MCC (16-class long-sequence RVDB dataset, chunk-scored) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv2-250Mᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'NTv2-250Mᵃ', column 'MCC'
Configuration: NTv2-250M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.844 Precision (16-class long-sequence RVDB dataset, chunk-scored, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv2-250Mᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'NTv2-250Mᵃ', column 'Precision'
Configuration: NTv2-250M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.844 Recall (16-class long-sequence RVDB dataset, chunk-scored, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv2-250Mᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'NTv2-250Mᵃ', column 'Recall'
Configuration: NTv2-50M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.853 Accuracy (16-class long-sequence RVDB dataset, chunk-scored) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv2-50Mᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'NTv2-50Mᵃ', column 'Accuracy'
Configuration: NTv2-50M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.87 Balanced accuracy (16-class long-sequence RVDB dataset, chunk-scored) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv2-50Mᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'NTv2-50Mᵃ', column 'Bal. Acc.'
Configuration: NTv2-50M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.869 Macro F1 (16-class long-sequence RVDB dataset, chunk-scored) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv2-50Mᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'NTv2-50Mᵃ', column 'F1'
Configuration: NTv2-50M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.842 MCC (16-class long-sequence RVDB dataset, chunk-scored) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv2-50Mᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'NTv2-50Mᵃ', column 'MCC'
Configuration: NTv2-50M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.871 Precision (16-class long-sequence RVDB dataset, chunk-scored, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv2-50Mᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'NTv2-50Mᵃ', column 'Precision'
Configuration: NTv2-50M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.87 Recall (16-class long-sequence RVDB dataset, chunk-scored, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv2-50Mᵃ on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'NTv2-50Mᵃ', column 'Recall'
Configuration: NTv3-650M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Protocol: RVDB long-sequence viral classification, 16 classes (Bůžková et al. 2026 Table 10) Dataset: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	0.953 Accuracy (16-class long-sequence RVDB dataset) fraction · higher Uncertainty: 95% CI 0.920 to 0.973. Wilson binomial interval quoted in Section 3.8; method stated in Section 2.9 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv3-650M on the RVDB long-sequence dataset, 16 classes gfm2-20261011-buzkova2026-protocol-long Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 10, row 'NTv3-650M', column 'Accuracy'

Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

External evaluations: 5

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Training-set class prior where supervised fitting is permitted

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Regularised classifier on simple permitted features, or protocol's conventional reference

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-11-02-a7f03c9e55a5. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-02-a7f03c9e55a5
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-11-02-a7f03c9e55a5 · Record review: source checked

1 source record and release history

Analyzing Genomic Foundation Models for Viral Sequence Identification · Original source · bioRxiv v1, posted 2026-09-28

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm2-20261011-buzkova2026-protocol-long

areas: dna-genomes
contexts: research
protocol: As for the primary dataset, but with about 4 indexed and about 16 queried sequences per class. NTv3-650M and blastn process each sequence whole; DNABERT-2, NTv2-50M and NTv2-250M are scored over overlapping chunks because their context window is shorter than these genomes.
version: Table 10 (16 classes, 256 test sequences)
metric direction: higher
unit: fraction
aggregation: Pooled over test sequences; balanced accuracy, MCC and macro F1, precision and recall also reported
limitations: Nearest-neighbour probe over labelled reference embeddings, not zero-shot classification: the index holds the training labels (Section 2.7).; Point estimates from one fixed split with a fixed random seed; 95% Wilson intervals are quoted in the text, not in the tables.; RVDB organism labels are not a controlled taxonomy; the 33-class refinement removed seven ambiguous labels found through the models' own confusions (Sections 3.2 and 4).; Chunk-scored rows (DNABERT-2, NTv2-50M, NTv2-250M) are not computed on the same unit as the whole-sequence rows (Table 10 footnote a).; 256 test sequences: the interval half-width near an accuracy of 0.95 is about 0.026, and the authors state the narrowing against BLAST is indicative only (Sections 2.9 and 3.8).; The long-sequence classes are more divergent viruses than the primary dataset's closely related subtypes, so dataset difficulty differs in more than sequence length (Section 4).; Pooling for the long-sequence run is not stated; the foundation-model rows use configurations with pooling unreported.
source locator: Table 10; Section 3.8

Related records

uses data: RVDB C-RVDB v31.0 long-sequence dataset, 16 classes
assessment: BLAST (blastn) on the RVDB long-sequence dataset, 16 classes
assessment: DNABERT-2ᵃ on the RVDB long-sequence dataset, 16 classes
assessment: NTv2-250Mᵃ on the RVDB long-sequence dataset, 16 classes
assessment: NTv2-50Mᵃ on the RVDB long-sequence dataset, 16 classes
assessment: NTv3-650M on the RVDB long-sequence dataset, 16 classes

Suggest a correction