Source

ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks

Evidence concern: excluded from comparisons

Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'

Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks · Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'

arXiv 2605.25388v1 (submitted 2026-05-25); 42-page PDF; KDD '26 header on every page · Preprint

DOI: 10.48550/arXiv.2605.25388 Original source

What this source contributed

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

10 models
2 methods
76 configurations
1 benchmark
12 protocols
6 datasets
912 evaluations
912 results

Results

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

Value	Metric	Model or configuration	Dataset	Evaluation
80.65 (1.23) percent	Macro F1 (ViroBench ALL viruses, host, G-Split)	AIDO.DNA-7B (ViroBench classification)	ViroBench ALL viruses, G-Split test set	AIDO.DNA-7B on ViroBench ALL viruses host classification (G-Split)
47.47 (1.38) percent	Macro F1 (ViroBench ALL viruses, host, T-Split)	AIDO.DNA-7B (ViroBench classification)	ViroBench ALL viruses, T-Split test set	AIDO.DNA-7B on ViroBench ALL viruses host classification (T-Split)
69.87 (3.05) percent	Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)	AIDO.DNA-7B (ViroBench classification)	ViroBench ALL viruses, G-Split test set	AIDO.DNA-7B on ViroBench ALL viruses taxonomy classification (G-Split)
55.27 (6.59) percent	Macro F1 (ViroBench ALL viruses, taxonomy, T-Split)	AIDO.DNA-7B (ViroBench classification)	ViroBench ALL viruses, T-Split test set	AIDO.DNA-7B on ViroBench ALL viruses taxonomy classification (T-Split)
56.61 (2.01) percent	Macro F1 (ViroBench DNA viruses, host, G-Split)	AIDO.DNA-7B (ViroBench classification)	ViroBench DNA viruses, G-Split test set	AIDO.DNA-7B on ViroBench DNA viruses host classification (G-Split)
45.13 (1.25) percent	Macro F1 (ViroBench DNA viruses, host, T-Split)	AIDO.DNA-7B (ViroBench classification)	ViroBench DNA viruses, T-Split test set	AIDO.DNA-7B on ViroBench DNA viruses host classification (T-Split)
79.37 (2.04) percent	Macro F1 (ViroBench DNA viruses, taxonomy, G-Split)	AIDO.DNA-7B (ViroBench classification)	ViroBench DNA viruses, G-Split test set	AIDO.DNA-7B on ViroBench DNA viruses taxonomy classification (G-Split)
63.52 (4.08) percent	Macro F1 (ViroBench DNA viruses, taxonomy, T-Split)	AIDO.DNA-7B (ViroBench classification)	ViroBench DNA viruses, T-Split test set	AIDO.DNA-7B on ViroBench DNA viruses taxonomy classification (T-Split)
62.90 (0.69) percent	Macro F1 (ViroBench RNA viruses, host, G-Split)	AIDO.DNA-7B (ViroBench classification)	ViroBench RNA viruses, G-Split test set	AIDO.DNA-7B on ViroBench RNA viruses host classification (G-Split)
40.72 (6.88) percent	Macro F1 (ViroBench RNA viruses, host, T-Split)	AIDO.DNA-7B (ViroBench classification)	ViroBench RNA viruses, T-Split test set	AIDO.DNA-7B on ViroBench RNA viruses host classification (T-Split)
81.28 (2.17) percent	Macro F1 (ViroBench RNA viruses, taxonomy, G-Split)	AIDO.DNA-7B (ViroBench classification)	ViroBench RNA viruses, G-Split test set	AIDO.DNA-7B on ViroBench RNA viruses taxonomy classification (G-Split)
64.64 (4.66) percent	Macro F1 (ViroBench RNA viruses, taxonomy, T-Split)	AIDO.DNA-7B (ViroBench classification)	ViroBench RNA viruses, T-Split test set	AIDO.DNA-7B on ViroBench RNA viruses taxonomy classification (T-Split)
82.82 (1.15) percent	Macro F1 (ViroBench ALL viruses, host, G-Split)	AIDO.DNA-300M (ViroBench classification)	ViroBench ALL viruses, G-Split test set	AIDO.DNA-300M on ViroBench ALL viruses host classification (G-Split)
46.96 (2.85) percent	Macro F1 (ViroBench ALL viruses, host, T-Split)	AIDO.DNA-300M (ViroBench classification)	ViroBench ALL viruses, T-Split test set	AIDO.DNA-300M on ViroBench ALL viruses host classification (T-Split)
71.27 (2.63) percent	Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)	AIDO.DNA-300M (ViroBench classification)	ViroBench ALL viruses, G-Split test set	AIDO.DNA-300M on ViroBench ALL viruses taxonomy classification (G-Split)
57.11 (6.19) percent	Macro F1 (ViroBench ALL viruses, taxonomy, T-Split)	AIDO.DNA-300M (ViroBench classification)	ViroBench ALL viruses, T-Split test set	AIDO.DNA-300M on ViroBench ALL viruses taxonomy classification (T-Split)
57.58 (0.84) percent	Macro F1 (ViroBench DNA viruses, host, G-Split)	AIDO.DNA-300M (ViroBench classification)	ViroBench DNA viruses, G-Split test set	AIDO.DNA-300M on ViroBench DNA viruses host classification (G-Split)
44.34 (1.25) percent	Macro F1 (ViroBench DNA viruses, host, T-Split)	AIDO.DNA-300M (ViroBench classification)	ViroBench DNA viruses, T-Split test set	AIDO.DNA-300M on ViroBench DNA viruses host classification (T-Split)
79.38 (3.84) percent	Macro F1 (ViroBench DNA viruses, taxonomy, G-Split)	AIDO.DNA-300M (ViroBench classification)	ViroBench DNA viruses, G-Split test set	AIDO.DNA-300M on ViroBench DNA viruses taxonomy classification (G-Split)
63.40 (2.00) percent	Macro F1 (ViroBench DNA viruses, taxonomy, T-Split)	AIDO.DNA-300M (ViroBench classification)	ViroBench DNA viruses, T-Split test set	AIDO.DNA-300M on ViroBench DNA viruses taxonomy classification (T-Split)
76.33 (5.33) percent	Macro F1 (ViroBench RNA viruses, host, G-Split)	AIDO.DNA-300M (ViroBench classification)	ViroBench RNA viruses, G-Split test set	AIDO.DNA-300M on ViroBench RNA viruses host classification (G-Split)
47.45 (1.67) percent	Macro F1 (ViroBench RNA viruses, host, T-Split)	AIDO.DNA-300M (ViroBench classification)	ViroBench RNA viruses, T-Split test set	AIDO.DNA-300M on ViroBench RNA viruses host classification (T-Split)
84.97 (2.64) percent	Macro F1 (ViroBench RNA viruses, taxonomy, G-Split)	AIDO.DNA-300M (ViroBench classification)	ViroBench RNA viruses, G-Split test set	AIDO.DNA-300M on ViroBench RNA viruses taxonomy classification (G-Split)
66.86 (3.64) percent	Macro F1 (ViroBench RNA viruses, taxonomy, T-Split)	AIDO.DNA-300M (ViroBench classification)	ViroBench RNA viruses, T-Split test set	AIDO.DNA-300M on ViroBench RNA viruses taxonomy classification (T-Split)
69.24 (1.81) percent	Macro F1 (ViroBench ALL viruses, host, G-Split)	AIDO.RNA-1.6B (ViroBench classification)	ViroBench ALL viruses, G-Split test set	AIDO.RNA-1.6B on ViroBench ALL viruses host classification (G-Split)
30.32 (3.20) percent	Macro F1 (ViroBench ALL viruses, host, T-Split)	AIDO.RNA-1.6B (ViroBench classification)	ViroBench ALL viruses, T-Split test set	AIDO.RNA-1.6B on ViroBench ALL viruses host classification (T-Split)
53.28 (7.02) percent	Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)	AIDO.RNA-1.6B (ViroBench classification)	ViroBench ALL viruses, G-Split test set	AIDO.RNA-1.6B on ViroBench ALL viruses taxonomy classification (G-Split)
33.56 (5.69) percent	Macro F1 (ViroBench ALL viruses, taxonomy, T-Split)	AIDO.RNA-1.6B (ViroBench classification)	ViroBench ALL viruses, T-Split test set	AIDO.RNA-1.6B on ViroBench ALL viruses taxonomy classification (T-Split)
47.28 (1.13) percent	Macro F1 (ViroBench DNA viruses, host, G-Split)	AIDO.RNA-1.6B (ViroBench classification)	ViroBench DNA viruses, G-Split test set	AIDO.RNA-1.6B on ViroBench DNA viruses host classification (G-Split)
43.39 (2.57) percent	Macro F1 (ViroBench DNA viruses, host, T-Split)	AIDO.RNA-1.6B (ViroBench classification)	ViroBench DNA viruses, T-Split test set	AIDO.RNA-1.6B on ViroBench DNA viruses host classification (T-Split)
59.58 (2.71) percent	Macro F1 (ViroBench DNA viruses, taxonomy, G-Split)	AIDO.RNA-1.6B (ViroBench classification)	ViroBench DNA viruses, G-Split test set	AIDO.RNA-1.6B on ViroBench DNA viruses taxonomy classification (G-Split)
37.07 (4.16) percent	Macro F1 (ViroBench DNA viruses, taxonomy, T-Split)	AIDO.RNA-1.6B (ViroBench classification)	ViroBench DNA viruses, T-Split test set	AIDO.RNA-1.6B on ViroBench DNA viruses taxonomy classification (T-Split)
44.71 (1.80) percent	Macro F1 (ViroBench RNA viruses, host, G-Split)	AIDO.RNA-1.6B (ViroBench classification)	ViroBench RNA viruses, G-Split test set	AIDO.RNA-1.6B on ViroBench RNA viruses host classification (G-Split)
12.12 (14.22) percent	Macro F1 (ViroBench RNA viruses, host, T-Split)	AIDO.RNA-1.6B (ViroBench classification)	ViroBench RNA viruses, T-Split test set	AIDO.RNA-1.6B on ViroBench RNA viruses host classification (T-Split)
64.62 (5.77) percent	Macro F1 (ViroBench RNA viruses, taxonomy, G-Split)	AIDO.RNA-1.6B (ViroBench classification)	ViroBench RNA viruses, G-Split test set	AIDO.RNA-1.6B on ViroBench RNA viruses taxonomy classification (G-Split)
42.97 (5.18) percent	Macro F1 (ViroBench RNA viruses, taxonomy, T-Split)	AIDO.RNA-1.6B (ViroBench classification)	ViroBench RNA viruses, T-Split test set	AIDO.RNA-1.6B on ViroBench RNA viruses taxonomy classification (T-Split)
77.74 (1.30) percent	Macro F1 (ViroBench ALL viruses, host, G-Split)	AIDO.RNA-1.6B-CDS (ViroBench classification)	ViroBench ALL viruses, G-Split test set	AIDO.RNA-1.6B-CDS on ViroBench ALL viruses host classification (G-Split)
38.19 (1.97) percent	Macro F1 (ViroBench ALL viruses, host, T-Split)	AIDO.RNA-1.6B-CDS (ViroBench classification)	ViroBench ALL viruses, T-Split test set	AIDO.RNA-1.6B-CDS on ViroBench ALL viruses host classification (T-Split)
60.84 (6.35) percent	Macro F1 (ViroBench ALL viruses, taxonomy, G-Split)	AIDO.RNA-1.6B-CDS (ViroBench classification)	ViroBench ALL viruses, G-Split test set	AIDO.RNA-1.6B-CDS on ViroBench ALL viruses taxonomy classification (G-Split)
43.18 (5.64) percent	Macro F1 (ViroBench ALL viruses, taxonomy, T-Split)	AIDO.RNA-1.6B-CDS (ViroBench classification)	ViroBench ALL viruses, T-Split test set	AIDO.RNA-1.6B-CDS on ViroBench ALL viruses taxonomy classification (T-Split)
53.31 (2.64) percent	Macro F1 (ViroBench DNA viruses, host, G-Split)	AIDO.RNA-1.6B-CDS (ViroBench classification)	ViroBench DNA viruses, G-Split test set	AIDO.RNA-1.6B-CDS on ViroBench DNA viruses host classification (G-Split)
44.74 (0.83) percent	Macro F1 (ViroBench DNA viruses, host, T-Split)	AIDO.RNA-1.6B-CDS (ViroBench classification)	ViroBench DNA viruses, T-Split test set	AIDO.RNA-1.6B-CDS on ViroBench DNA viruses host classification (T-Split)
69.71 (3.74) percent	Macro F1 (ViroBench DNA viruses, taxonomy, G-Split)	AIDO.RNA-1.6B-CDS (ViroBench classification)	ViroBench DNA viruses, G-Split test set	AIDO.RNA-1.6B-CDS on ViroBench DNA viruses taxonomy classification (G-Split)
51.35 (4.84) percent	Macro F1 (ViroBench DNA viruses, taxonomy, T-Split)	AIDO.RNA-1.6B-CDS (ViroBench classification)	ViroBench DNA viruses, T-Split test set	AIDO.RNA-1.6B-CDS on ViroBench DNA viruses taxonomy classification (T-Split)
68.17 (3.83) percent	Macro F1 (ViroBench RNA viruses, host, G-Split)	AIDO.RNA-1.6B-CDS (ViroBench classification)	ViroBench RNA viruses, G-Split test set	AIDO.RNA-1.6B-CDS on ViroBench RNA viruses host classification (G-Split)
29.98 (2.18) percent	Macro F1 (ViroBench RNA viruses, host, T-Split)	AIDO.RNA-1.6B-CDS (ViroBench classification)	ViroBench RNA viruses, T-Split test set	AIDO.RNA-1.6B-CDS on ViroBench RNA viruses host classification (T-Split)
74.10 (2.83) percent	Macro F1 (ViroBench RNA viruses, taxonomy, G-Split)	AIDO.RNA-1.6B-CDS (ViroBench classification)	ViroBench RNA viruses, G-Split test set	AIDO.RNA-1.6B-CDS on ViroBench RNA viruses taxonomy classification (G-Split)
51.40 (3.10) percent	Macro F1 (ViroBench RNA viruses, taxonomy, T-Split)	AIDO.RNA-1.6B-CDS (ViroBench classification)	ViroBench RNA viruses, T-Split test set	AIDO.RNA-1.6B-CDS on ViroBench RNA viruses taxonomy classification (T-Split)
74.60 (1.86) percent	Macro F1 (ViroBench ALL viruses, host, G-Split)	AIDO.RNA-650M (ViroBench classification)	ViroBench ALL viruses, G-Split test set	AIDO.RNA-650M on ViroBench ALL viruses host classification (G-Split)
33.99 (0.73) percent	Macro F1 (ViroBench ALL viruses, host, T-Split)	AIDO.RNA-650M (ViroBench classification)	ViroBench ALL viruses, T-Split test set	AIDO.RNA-650M on ViroBench ALL viruses host classification (T-Split)

Models, benchmarks and other records

Models (10)

Methods (2)

Configurations (76)

Benchmarks (1)

ViroBench

Protocols (12)

Datasets (6)

Evaluations (912)

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 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance
attributes.artifact_sha256 22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42 Source metadata	ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks Original source ↗ No field-specific location recorded Version: arXiv 2605.25388v1 (submitted 2026-05-25); 42-page PDF; KDD '26 header on every page Retrieved: 2026-10-11T21:24:29Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.artifact_sha256` Source artifact SHA-256: `22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Artifact url https://arxiv.org/pdf/2605.25388v1 Source metadata	ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks Original source ↗ No field-specific location recorded Version: arXiv 2605.25388v1 (submitted 2026-05-25); 42-page PDF; KDD '26 header on every page Retrieved: 2026-10-11T21:24:29Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.artifact_url` Source artifact SHA-256: `22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Code url https://github.com/QIANJINYDX/ViroBench Source metadata	ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks Original source ↗ No field-specific location recorded Version: arXiv 2605.25388v1 (submitted 2026-05-25); 42-page PDF; KDD '26 header on every page Retrieved: 2026-10-11T21:24:29Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.code_url` Source artifact SHA-256: `22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Doi 10.48550/arXiv.2605.25388 Source metadata	ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks Original source ↗ No field-specific location recorded Version: arXiv 2605.25388v1 (submitted 2026-05-25); 42-page PDF; KDD '26 header on every page Retrieved: 2026-10-11T21:24:29Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.doi` Source artifact SHA-256: `22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Evidence concerns 2 values source id lit-microbial-20261011-virobench-source-ye2026 message Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code. source locator Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM' artifact sha256 22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42 reviewed at 2026-10-11T00:00:00Z review method ai-assisted-source-review source id lit-microbial-20261011-virobench-source-ye2026 message Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim. source locator Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)' artifact sha256 22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42 reviewed at 2026-10-11T00:00:00Z review method ai-assisted-source-review Source metadata	ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks Original source ↗ No field-specific location recorded Version: arXiv 2605.25388v1 (submitted 2026-05-25); 42-page PDF; KDD '26 header on every page Retrieved: 2026-10-11T21:24:29Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.evidence_concerns` Source artifact SHA-256: `22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Licence CC-BY-4.0 Source metadata	ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks Original source ↗ No field-specific location recorded Version: arXiv 2605.25388v1 (submitted 2026-05-25); 42-page PDF; KDD '26 header on every page Retrieved: 2026-10-11T21:24:29Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.licence` Source artifact SHA-256: `22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Limitations 3 values The pages carry a KDD '26 conference header and the arXiv page lists a related ACM DOI (10.1145/3770855.3819057); the conference version was not retrieved, so the record stays at the arXiv preprint. Values were read from the pdftotext (poppler 26.08.0) layout text layer of the PDF; the archived copy is that text layer, SHA-256 48071e2e329430de04b90c16d92261af52fe953cfc424e8caa5acf2babc574c7. Table 3 lists NT v3 under phage-specific coverage (P) and Table 9 lists it as non-viral (N); Table 25 groups NTv3 rows under phage-specific coverage. Source metadata	ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks Original source ↗ No field-specific location recorded Version: arXiv 2605.25388v1 (submitted 2026-05-25); 42-page PDF; KDD '26 header on every page Retrieved: 2026-10-11T21:24:29Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.limitations` Source artifact SHA-256: `22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Media type application/pdf Source metadata	ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks Original source ↗ No field-specific location recorded Version: arXiv 2605.25388v1 (submitted 2026-05-25); 42-page PDF; KDD '26 header on every page Retrieved: 2026-10-11T21:24:29Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.media_type` Source artifact SHA-256: `22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Publication status preprint Source metadata	ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks Original source ↗ No field-specific location recorded Version: arXiv 2605.25388v1 (submitted 2026-05-25); 42-page PDF; KDD '26 header on every page Retrieved: 2026-10-11T21:24:29Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.publication_status` Source artifact SHA-256: `22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Retrieved at 2026-10-11T21:24:29Z Source metadata	ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks Original source ↗ No field-specific location recorded Version: arXiv 2605.25388v1 (submitted 2026-05-25); 42-page PDF; KDD '26 header on every page Retrieved: 2026-10-11T21:24:29Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.retrieved_at` Source artifact SHA-256: `22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42` 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

Primary source retrieved and hashed for the 2026-10-11 microbial and interactions literature pass.

Release history

No supporting source is linked yet.

Read original source

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-microbial-20261011-virobench-source-ye2026

areas: microbes-communities; dna-genomes
contexts: research
url: https://arxiv.org/abs/2605.25388v1
artifact url: https://arxiv.org/pdf/2605.25388v1
version: arXiv 2605.25388v1 (submitted 2026-05-25); 42-page PDF; KDD '26 header on every page
retrieved at: 2026-10-11T21:24:29Z
artifact sha256: 22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42
doi: 10.48550/arXiv.2605.25388
publication status: preprint
licence: CC-BY-4.0
media type: application/pdf
code url: https://github.com/QIANJINYDX/ViroBench
limitations: The pages carry a KDD '26 conference header and the arXiv page lists a related ACM DOI (10.1145/3770855.3819057); the conference version was not retrieved, so the record stays at the arXiv preprint.; Values were read from the pdftotext (poppler 26.08.0) layout text layer of the PDF; the archived copy is that text layer, SHA-256 48071e2e329430de04b90c16d92261af52fe953cfc424e8caa5acf2babc574c7.; Table 3 lists NT v3 under phage-specific coverage (P) and Table 9 lists it as non-viral (N); Table 25 groups NTv3 rows under phage-specific coverage.
evidence concerns: source id: lit-microbial-20261011-virobench-source-ye2026; message: Table 25 prints one Macro-F1 per model for the taxonomy columns. For 143 of the 144 model-by-split taxonomy cells on the ALL-virus set, the printed value equals the mean of the five per-rank values in Table 26 rounded to two decimals. The exception is RNA-FM under the genus-disjoint split: Table 25 prints 48.67 and the mean of the Table 26 ranks (59.96, 65.35, 37.58, 58.78, 43.82) is 53.10. One of the two tables is wrong for that row, so RNA-FM ALL taxonomy G-Split should not be used in a comparison without checking the published code.; source locator: Table 25, row 'RNA-FM', column 'ALL viruses / Taxonomy / G-Split'; Table 26, row 'RNA-FM'; artifact sha256: 22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42; reviewed at: 2026-10-11T00:00:00Z; review method: ai-assisted-source-review; source id: lit-microbial-20261011-virobench-source-ye2026; message: Table 3 lists NT v3 under phage-specific pretraining coverage (P) and Table 9 lists it as non-viral (N). Table 25 groups the NTv3 rows under phage-specific coverage, which is what the configurations record. Pretraining coverage is the paper's main explanatory variable, so NT v3 rows should not be used to support a coverage-versus-performance claim.; source locator: Table 3 row 'NT v3'; Table 9 row 'NT v3'; Table 25 section 'DNA Foundation Models (Phage-specific Coverage)'; artifact sha256: 22ad7d742eeba37dd7f7f407a483776ba15fc38dedfb8c27ec05f5db231f9e42; reviewed at: 2026-10-11T00:00:00Z; review method: ai-assisted-source-review
review: method: source-hash-verification; method note: PDF re-downloaded and its SHA-256 matched; pdftotext -layout rerun and the text-layer hash matched the record and the archived gzip.; reviewer: claude; reviewer note: Claude review agent reviewer-mi-1, independent of the extractor lit-microbial-interactions; no human review claimed; date: 2026-10-11

Related records

Suggest a correction