Source

Analyzing Genomic Foundation Models for Viral Sequence Identification

bioRxiv v1, posted 2026-09-28 · Preprint

DOI: 10.64898/2026.09.25.754388

What this source contributed

Records in this release that cite this source. A record can cite several sources.

1 model
42 configurations
3 protocols
3 datasets
47 evaluations
90 results
9 evidence claims

Results

Values as the source printed them. Compare results only under compatible protocols, datasets and metrics.

Model or configuration	Metric	Value	Dataset	Evaluation
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Accuracy (16-class long-sequence RVDB dataset)	0.9766 fraction	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	BLAST (blastn) on the RVDB long-sequence dataset, 16 classes
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Balanced accuracy (16-class long-sequence RVDB dataset)	0.9766 fraction	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	BLAST (blastn) on the RVDB long-sequence dataset, 16 classes
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Macro F1 (16-class long-sequence RVDB dataset)	0.9765 fraction	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	BLAST (blastn) on the RVDB long-sequence dataset, 16 classes
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	MCC (16-class long-sequence RVDB dataset)	0.9751 unitless	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	BLAST (blastn) on the RVDB long-sequence dataset, 16 classes
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Precision (16-class long-sequence RVDB dataset, macro-averaged over classes)	0.9776 fraction	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	BLAST (blastn) on the RVDB long-sequence dataset, 16 classes
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Recall (16-class long-sequence RVDB dataset, macro-averaged over classes)	0.9766 fraction	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	BLAST (blastn) on the RVDB long-sequence dataset, 16 classes
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset)	0.9677 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	blastn on the RVDB 33-class dataset (BLAST comparison)
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Macro F1 (33-class RVDB dataset)	0.9379 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	blastn on the RVDB 33-class dataset (BLAST comparison)
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Precision (33-class RVDB dataset, macro-averaged over classes)	0.9401 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	blastn on the RVDB 33-class dataset (BLAST comparison)
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Recall (33-class RVDB dataset, macro-averaged over classes)	0.9392 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	blastn on the RVDB 33-class dataset (BLAST comparison)
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Accuracy (40-class RVDB dataset)	0.9120 fraction	RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	blastn on the RVDB 40-class dataset (BLAST comparison)
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Macro F1 (40-class RVDB dataset)	0.8886 fraction	RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	blastn on the RVDB 40-class dataset (BLAST comparison)
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Precision (40-class RVDB dataset, macro-averaged over classes)	0.8925 fraction	RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	blastn on the RVDB 40-class dataset (BLAST comparison)
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Recall (40-class RVDB dataset, macro-averaged over classes)	0.8898 fraction	RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	blastn on the RVDB 40-class dataset (BLAST comparison)
DNABERT-2, frozen embeddings, cls token only pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.7053 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	DNABERT-2, cls token only pooling, on the RVDB 33-class dataset
DNABERT-2, frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.7198 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	DNABERT-2, max, all tokens pooling, on the RVDB 33-class dataset
DNABERT-2, frozen embeddings, max, special tokens excluded pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.7495 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	DNABERT-2, max, special tokens excluded pooling, on the RVDB 33-class dataset
DNABERT-2, frozen embeddings, mean, all tokens pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.8855 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	DNABERT-2, mean, all tokens pooling, on the RVDB 33-class dataset
DNABERT-2, frozen embeddings, mean, special tokens excluded pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.8848 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	DNABERT-2, mean, special tokens excluded pooling, on the RVDB 33-class dataset
DNABERT-2, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Accuracy (16-class long-sequence RVDB dataset, chunk-scored)	0.7864 fraction	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	DNABERT-2ᵃ on the RVDB long-sequence dataset, 16 classes
DNABERT-2, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Balanced accuracy (16-class long-sequence RVDB dataset, chunk-scored)	0.8170 fraction	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	DNABERT-2ᵃ on the RVDB long-sequence dataset, 16 classes
DNABERT-2, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Macro F1 (16-class long-sequence RVDB dataset, chunk-scored)	0.8127 fraction	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	DNABERT-2ᵃ on the RVDB long-sequence dataset, 16 classes
DNABERT-2, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	MCC (16-class long-sequence RVDB dataset, chunk-scored)	0.7711 unitless	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	DNABERT-2ᵃ on the RVDB long-sequence dataset, 16 classes
DNABERT-2, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Precision (16-class long-sequence RVDB dataset, chunk-scored, macro-averaged over classes)	0.8139 fraction	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	DNABERT-2ᵃ on the RVDB long-sequence dataset, 16 classes
DNABERT-2, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Recall (16-class long-sequence RVDB dataset, chunk-scored, macro-averaged over classes)	0.8170 fraction	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	DNABERT-2ᵃ on the RVDB long-sequence dataset, 16 classes
DNABERT-S, frozen embeddings, cls token only pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.7713 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	DNABERT-S, cls token only pooling, on the RVDB 33-class dataset
DNABERT-S, frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.7907 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	DNABERT-S, max, all tokens pooling, on the RVDB 33-class dataset
DNABERT-S, frozen embeddings, max, special tokens excluded pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.8000 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	DNABERT-S, max, special tokens excluded pooling, on the RVDB 33-class dataset
DNABERT-S, frozen embeddings, mean, all tokens pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.8735 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	DNABERT-S, mean, all tokens pooling, on the RVDB 33-class dataset
DNABERT-S, frozen embeddings, mean, special tokens excluded pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.8733 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	DNABERT-S, mean, special tokens excluded pooling, on the RVDB 33-class dataset
BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset)	0.8994 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	megablast on the RVDB 33-class dataset (BLAST comparison)
BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Macro F1 (33-class RVDB dataset)	0.8989 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	megablast on the RVDB 33-class dataset (BLAST comparison)
BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Precision (33-class RVDB dataset, macro-averaged over classes)	0.9600 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	megablast on the RVDB 33-class dataset (BLAST comparison)
BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Recall (33-class RVDB dataset, macro-averaged over classes)	0.8729 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	megablast on the RVDB 33-class dataset (BLAST comparison)
BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Accuracy (40-class RVDB dataset)	0.8490 fraction	RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	megablast on the RVDB 40-class dataset (BLAST comparison)
BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Macro F1 (40-class RVDB dataset)	0.8512 fraction	RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	megablast on the RVDB 40-class dataset (BLAST comparison)
BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Precision (40-class RVDB dataset, macro-averaged over classes)	0.9064 fraction	RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	megablast on the RVDB 40-class dataset (BLAST comparison)
BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Recall (40-class RVDB dataset, macro-averaged over classes)	0.8283 fraction	RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	megablast on the RVDB 40-class dataset (BLAST comparison)
NTv1 (Multispecies 2.5B), frozen embeddings, cls token only pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.8655 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	NTv1 (Multispecies 2.5B), cls token only pooling, on the RVDB 33-class dataset
NTv1 (Multispecies 2.5B), frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.9030 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	NTv1 (Multispecies 2.5B), max, all tokens pooling, on the RVDB 33-class dataset
NTv1 (Multispecies 2.5B), frozen embeddings, max, special tokens excluded pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.9028 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	NTv1 (Multispecies 2.5B), max, special tokens excluded pooling, on the RVDB 33-class dataset
NTv1 (Multispecies 2.5B), frozen embeddings, mean, all tokens pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.9109 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	NTv1 (Multispecies 2.5B), mean, all tokens pooling, on the RVDB 33-class dataset
NTv1 (Multispecies 2.5B), frozen embeddings, mean, special tokens excluded pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.9097 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	NTv1 (Multispecies 2.5B), mean, special tokens excluded pooling, on the RVDB 33-class dataset
NTv2-50M, frozen embeddings, cls token only pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.7584 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	NTv2-50M, cls token only pooling, on the RVDB 33-class dataset
NTv2-50M, frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.8673 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	NTv2-50M, max, all tokens pooling, on the RVDB 33-class dataset
NTv2-50M, frozen embeddings, max, special tokens excluded pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.8667 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	NTv2-50M, max, special tokens excluded pooling, on the RVDB 33-class dataset
NTv2-50M, frozen embeddings, mean, all tokens pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.9133 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	NTv2-50M, mean, all tokens pooling, on the RVDB 33-class dataset
NTv2-50M, frozen embeddings, mean, special tokens excluded pooling, 1-NN (Bůžková et al. 2026)	Accuracy (33-class RVDB dataset, 1-NN over frozen embeddings)	0.9127 fraction	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	NTv2-50M, mean, special tokens excluded pooling, on the RVDB 33-class dataset
NTv2-50M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Accuracy (16-class long-sequence RVDB dataset, chunk-scored)	0.8532 fraction	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	NTv2-50Mᵃ on the RVDB long-sequence dataset, 16 classes
NTv2-50M, frozen embeddings, pooling not stated, 1-NN, long-sequence run (Bůžková et al. 2026)	Balanced accuracy (16-class long-sequence RVDB dataset, chunk-scored)	0.8699 fraction	RVDB C-RVDB v31.0 long-sequence dataset, 16 classes	NTv2-50Mᵃ on the RVDB long-sequence dataset, 16 classes

Claims

Statements this source supports, each with where in the source it was checked.

model_characteristics: gfm2-20261011-buzkova2026-config-dnabert-2-mean-all: Model characteristics DNABERT-2: 117M parameters; context 512; flex.; tokenizer BPE (4,096); training data 135-species genomes (Table 2, row 'DNABERT-2')
model_characteristics: gfm2-20261011-buzkova2026-config-dnabert-s-mean-all: Model characteristics DNABERT-S: 117M parameters; context 512; flex.; tokenizer BPE (4,096); training data 135-species genomes (Table 2, row 'DNABERT-S')
model_characteristics: gfm2-20261011-buzkova2026-config-ntv1-mean-all: Model characteristics NTv1 (Multispecies 2.5B): 2.5B parameters; context 1,000; tokenizer 6-mer; training data 850-species genomes (Table 2, row 'NTv1 (Multispecies 2.5B)')
model_characteristics: gfm2-20261011-buzkova2026-config-ntv2-50m-mean-all: Model characteristics NTv2-50M: 50M parameters; context 2,048; tokenizer 6-mer; training data 850-species genomes (Table 2, row 'NTv2-50M')
model_characteristics: gfm2-20261011-buzkova2026-config-ntv2-250m-mean-all: Model characteristics NTv2-250M: 250M parameters; context 2,048; tokenizer 6-mer; training data 850-species genomes (Table 2, row 'NTv2-250M')
model_characteristics: gfm2-20261011-buzkova2026-config-ntv2-500m-mean-all: Model characteristics NTv2-500M: 500M parameters; context 2,048; tokenizer 6-mer; training data 850-species genomes (Table 2, row 'NTv2-500M')
model_characteristics: gfm2-20261011-buzkova2026-config-ntv3-8m-mean-all: Model characteristics NTv3-8M: 8M parameters; context 1 Mb; tokenizer Single-base; training data OpenGenome2 (Table 2, row 'NTv3-8M')
model_characteristics: gfm2-20261011-buzkova2026-config-ntv3-100m-mean-all: Model characteristics NTv3-100M: 100M parameters; context 1 Mb; tokenizer Single-base; training data OpenGenome2 (Table 2, row 'NTv3-100M')
model_characteristics: gfm2-20261011-buzkova2026-config-ntv3-650m-mean-all: Model characteristics NTv3-650M: 650M parameters; context 1 Mb; tokenizer Single-base; training data OpenGenome2 (Table 2, row 'NTv3-650M')

Models, benchmarks and other records

Models (1)

DNABERT-S

Configurations (42)

Protocols (3)

Datasets (3)

Evaluations (47)

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.

25 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
Artifact SHA-256 9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19 Source metadata	Analyzing Genomic Foundation Models for Viral Sequence Identification Original source ↗ No field-specific location recorded Version: bioRxiv v1, posted 2026-09-28 Retrieved: 2026-10-11T00:48:35Z	catalogued No individual claim review recorded Audit details Field: `attributes.artifact_sha256` Source artifact SHA-256: `9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Artifact url https://www.biorxiv.org/content/10.64898/2026.09.25.754388v1.full.pdf Source metadata	Analyzing Genomic Foundation Models for Viral Sequence Identification Original source ↗ No field-specific location recorded Version: bioRxiv v1, posted 2026-09-28 Retrieved: 2026-10-11T00:48:35Z	catalogued No individual claim review recorded Audit details Field: `attributes.artifact_url` Source artifact SHA-256: `9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Doi 10.64898/2026.09.25.754388 Source metadata	Analyzing Genomic Foundation Models for Viral Sequence Identification Original source ↗ No field-specific location recorded Version: bioRxiv v1, posted 2026-09-28 Retrieved: 2026-10-11T00:48:35Z	catalogued No individual claim review recorded Audit details Field: `attributes.doi` Source artifact SHA-256: `9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Licence CC-BY-4.0 Source metadata	Analyzing Genomic Foundation Models for Viral Sequence Identification Original source ↗ No field-specific location recorded Version: bioRxiv v1, posted 2026-09-28 Retrieved: 2026-10-11T00:48:35Z	catalogued No individual claim review recorded Audit details Field: `attributes.licence` Source artifact SHA-256: `9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Media type application/pdf Source metadata	Analyzing Genomic Foundation Models for Viral Sequence Identification Original source ↗ No field-specific location recorded Version: bioRxiv v1, posted 2026-09-28 Retrieved: 2026-10-11T00:48:35Z	catalogued No individual claim review recorded Audit details Field: `attributes.media_type` Source artifact SHA-256: `9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Publication status preprint Source metadata	Analyzing Genomic Foundation Models for Viral Sequence Identification Original source ↗ No field-specific location recorded Version: bioRxiv v1, posted 2026-09-28 Retrieved: 2026-10-11T00:48:35Z	catalogued No individual claim review recorded Audit details Field: `attributes.publication_status` Source artifact SHA-256: `9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Retrieved at 2026-10-11T00:48:35Z Source metadata	Analyzing Genomic Foundation Models for Viral Sequence Identification Original source ↗ No field-specific location recorded Version: bioRxiv v1, posted 2026-09-28 Retrieved: 2026-10-11T00:48:35Z	catalogued No individual claim review recorded Audit details Field: `attributes.retrieved_at` Source artifact SHA-256: `9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Review: artifact sha256 9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19 Source metadata	Analyzing Genomic Foundation Models for Viral Sequence Identification Original source ↗ No field-specific location recorded Version: bioRxiv v1, posted 2026-09-28 Retrieved: 2026-10-11T00:48:35Z	catalogued No individual claim review recorded Audit details Field: `attributes.review.artifact_sha256` Source artifact SHA-256: `9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Review: date 2026-10-11 Source metadata	Analyzing Genomic Foundation Models for Viral Sequence Identification Original source ↗ No field-specific location recorded Version: bioRxiv v1, posted 2026-09-28 Retrieved: 2026-10-11T00:48:35Z	catalogued No individual claim review recorded Audit details Field: `attributes.review.date` Source artifact SHA-256: `9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Review method 2 values source-hash-verification ai-assisted-source-review Source metadata	Analyzing Genomic Foundation Models for Viral Sequence Identification Original source ↗ No field-specific location recorded Version: bioRxiv v1, posted 2026-09-28 Retrieved: 2026-10-11T00:48:35Z	catalogued No individual claim review recorded Audit details Field: `attributes.review.method` Source artifact SHA-256: `9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

How to read the evidence

Sources and history

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

bioRxiv preprint v1 comparing frozen Nucleotide Transformer and DNABERT embeddings with nearest-neighbour search against BLAST on RVDB-derived viral classification.

Release history

No supporting source is linked yet.

Read original source

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm2-20261011-buzkova2026-source

areas: dna-genomes
contexts: research
url: https://doi.org/10.64898/2026.09.25.754388
doi: 10.64898/2026.09.25.754388
artifact url: https://www.biorxiv.org/content/10.64898/2026.09.25.754388v1.full.pdf
artifact sha256: 9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19
retrieved at: 2026-10-11T00:48:35Z
publication status: preprint
version: bioRxiv v1, posted 2026-09-28
licence: CC-BY-4.0
media type: application/pdf
source locator: Full text PDF, 27 pages; Tables 1-10
review: method: source-hash-verification; ai-assisted-source-review; 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: 9a589a2088f8466502b1035228db3e594065e984e5755c25d907471225f75c19; retrieval url: https://www.biorxiv.org/content/10.64898/2026.09.25.754388v1.full.pdf; note: Archived copy matches the pinned SHA-256; licence CC BY 4.0 confirmed on the PDF banner.

Related records

Suggest a correction