These checks assess whether the evidence supports a reproducible investigation. A source-checked score alone does not meet these requirements.
Release 2026-09-29-06401fd5b220 · Evidence verified: Not verified
Exact outcomes, predictions, identifiers and evaluator are connected.
Missing or unresolved evidence
Verified: Not verified
Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.
Missing or unresolved evidence
Verified: Not verified
A pinned recipe describes the inputs, environment and resource requirements.
Missing or unresolved evidence
Verified: Not verified
Separate data and exposure records support an independent test.
Missing or unresolved evidence
Verified: Not verified
Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.
No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.
8 evaluations · 32 results. Different protocols are not a single leaderboard.
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: ESM2 650M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 99.7% AUROC percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 650M: human-versus-viral protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry; Protein Language Models Expose Viral Immune Mimicry · Table 1, ESM2 650M row, AUC (%) column |
| Configuration: ESM2 8M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 92.2% Prec. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 8M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 8M, column Prec.; XML row4 column4 |
| Configuration: AA n-grams | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 91.5% AUROC percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceAA n-grams: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row AA n-grams, column AUC (%); XML row3 column2 |
| Configuration: AA n-grams | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 88.5% Prec. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceAA n-grams: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row AA n-grams, column Prec.; XML row3 column4 |
| Configuration: ESM2 650M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 96.8% Prec. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 650M: human-versus-viral protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 650M, column Prec.; XML row7 column4 |
| Configuration: ESM2 35M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 98.7% AUROC percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 35M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 35M, column AUC (%); XML row5 column2 |
| Configuration: ESM2 35M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 93.8% Prec. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 35M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 35M, column Prec.; XML row5 column4 |
| Configuration: ESM2 150M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 95.5% Prec. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 150M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 150M, column Prec.; XML row6 column4 |
| Configuration: Tree-T5 | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 97.7% Recall percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceTree-T5: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row Tree-T5, column Recall; XML row9 column5 |
| Configuration: ESM2 150M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 97% Accur. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 150M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 150M, column Accur.; XML row6 column3 |
| Configuration: ESM2 35M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 93.9% Recall percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 35M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 35M, column Recall; XML row5 column5 |
| Configuration: Tree-T5 | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 97.7% Accur. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceTree-T5: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row Tree-T5, column Accur.; XML row9 column3 |
| Configuration: ESM2 8M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 92.3% Recall percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 8M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 8M, column Recall; XML row4 column5 |
| Configuration: ESM2 35M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 95.8% Accur. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 35M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 35M, column Accur.; XML row5 column3 |
| Configuration: Tree-T5 | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 99.7% AUROC percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceTree-T5: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row Tree-T5, column AUC (%); XML row9 column2 |
| Configuration: Linear-T5 | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 97.6% Recall percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceLinear-T5: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row Linear-T5, column Recall; XML row8 column5 |
| Configuration: ESM2 650M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 97.9% Accur. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 650M: human-versus-viral protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 650M, column Accur.; XML row7 column3 |
| Configuration: Linear-T5 | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 97.6% Accur. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceLinear-T5: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row Linear-T5, column Accur.; XML row8 column3 |
| Configuration: BL Length | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 78.5% Accur. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBL Length: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row BL Length, column Accur.; XML row2 column3 |
| Configuration: ESM2 150M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 95.5% Recall percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 150M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 150M, column Recall; XML row6 column5 |
| Configuration: ESM2 8M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 98.1% AUROC percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 8M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 8M, column AUC (%); XML row4 column2 |
| Configuration: ESM2 650M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 96.7% Recall percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 650M: human-versus-viral protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 650M, column Recall; XML row7 column5 |
| Configuration: ESM2 150M | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 99.3% AUROC percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2 150M: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row ESM2 150M, column AUC (%); XML row6 column2 |
| Configuration: BL Length | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 78.5% Prec. percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBL Length: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row BL Length, column Prec.; XML row2 column4 |
| Configuration: BL Length | Protocol: Held-out human-versus-virus protein classification (human-versus-viral protein classification) Dataset: human and viral proteins | 78.5% Recall percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBL Length: Held-out human-versus-virus protein classification Compare protein origin classifiers; T 5 embeddings plus linear/tree models vs ESM 2 fine-tuning and simple controls. UniRef90 deduplication; proteins longer than1,600 residues excluded; UniRef50 clusters assigned80% training and20% test with no cluster shared. Separate four-fold error-analysis experiment not assigned toTable1. Aggregation: Not reported Protein Language Models Expose Viral Immune Mimicry · Table 1, row BL Length, column Recall; XML row2 column5 |
Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.
A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
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.
4 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| attributes.split Not reported Context-only references | Protein Language Models Expose Viral Immune Mimicry No field-specific location recorded Version: version of record | missing or unspecified No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.version Not reported Context-only references | Protein Language Models Expose Viral Immune Mimicry No field-specific location recorded Version: version of record | missing or unspecified No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| description No value recorded Context-only references | Protein Language Models Expose Viral Immune Mimicry No field-specific location recorded Version: version of record | missing or unspecified No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| name human and viral proteins Context-only references | Protein Language Models Expose Viral Immune Mimicry No field-specific location recorded Version: version of record | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: needs review
Stable ID: reported-dataset-43f24c4dfb7351