PRIME examines how protein representations generalise across a published viral-variant dataset. This record covers its binding-prediction endpoint.
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Entity type | Paper-specific evaluation task; this profile is a descriptive evidence summary.SourcesPRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings |
| Datasets | The paper’s PRIME receptor-binding-domain variant collection; this is a paper-specific task, not a universal protein benchmark.SourcesPRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings |
| Organisms | SARS-CoV-2 in the reported variant dataset.SourcesPRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings |
| Assays | Previously published binding and expression measurements provide phenotype labels; this record concerns binding prediction.SourcesPRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings |
| Splits | Random and position-stratified settings are distinct. The linked results retain the reported setting; this profile does not supply an executable split manifest.SourcesPRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings |
| Allowed inputs | Protein-sequence representations associated with measured phenotype labels.SourcesPRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings |
| Adaptation | The paper distinguishes frozen representations from adapted models. Individual evaluation records retain that distinction.SourcesPRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings |
| Metrics | R² for the linked binding-regression results; preserve the endpoint and split beside each value.SourcesPRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings |
| Baselines | The paper compares pretrained encoder configurations. The exact method named in each retained result remains its identity; no model recommendation follows from this summary.SourcesPRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings |
Conceptual overview of the published statistical assessment.
The paper contrasts ordinary random assessment with assessment across withheld mutation positions. These settings ask different generalisation questions and their scores should not be pooled. Binding and expression are separate measured labels; neither is a direct measure of infection, transmission or clinical risk.
Each evaluation records what was tested and under which conditions.
Release 2026-09-17-d277315f7d76 · 2 evaluations · 2 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| ESM-2: Mutated RBD binding prediction Frozen mean-pooled representation with downstream regression; position-stratified split. Independent external evaluation · Evaluation metadata: needs review | ||
| 0.0248 R² Unit: unitless · Direction: unknown | Uncertainty: ± 0.01 Scored: Not reported · Eligible: Not reported | source checkedPRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, ESM-2 8M / Mean / not fine-tuned row, Position-Stratified Split Binding R² column Source checking is not independent reproduction. |
| ESM-C: Mutated RBD binding prediction Frozen mean-pooled representation with downstream regression; position-stratified split. Independent external evaluation · Evaluation metadata: needs review | ||
| -0.0162 R² Unit: unitless · Direction: unknown | Uncertainty: ± 0.01 Scored: Not reported · Eligible: Not reported | source checkedPRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, ESM-C 300M / Mean / not fine-tuned row, Position-Stratified Split Binding R² column Source checking is not independent reproduction. |
Last literature check: 2026-09-17. Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.
| Paper or primary resource | Version | Reference |
|---|---|---|
| PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space | version of record | Read source |
primary comparison tables located
Inspected the cited primary abstract and descriptive computational-evaluation sections. Review covers the descriptive claims shown; no executable protocol was reconstructed. Original numerical records retain their prior transcription review.
Stable record: reported-task-00e594df6a182dTrace 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.
16 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual overview of the published statistical assessment. Individual claims | PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings Version: version of record | source checked automated source review · 2026-09-16 Audit detailsInspected the cited primary abstract and descriptive computational-evaluation sections. Review covers the descriptive claims shown; no executable protocol was reconstructed. Original numerical records retain their prior transcription review. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["Published phenotype dataset","Distinguish assessment settings","Evaluate the specified endpoint","Read the metric with its evidence"] Individual claims | PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings Version: version of record | source checked automated source review · 2026-09-16 Audit detailsInspected the cited primary abstract and descriptive computational-evaluation sections. Review covers the descriptive claims shown; no executable protocol was reconstructed. Original numerical records retain their prior transcription review. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Conceptual assessment outline Individual claims | PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings Version: version of record | source checked automated source review · 2026-09-16 Audit detailsInspected the cited primary abstract and descriptive computational-evaluation sections. Review covers the descriptive claims shown; no executable protocol was reconstructed. Original numerical records retain their prior transcription review. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Entity type Paper-specific evaluation task; this profile is a descriptive evidence summary. Individual claims | PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings Version: version of record | source checked automated source review · 2026-09-16 Audit detailsInspected the cited primary abstract and descriptive computational-evaluation sections. Review covers the descriptive claims shown; no executable protocol was reconstructed. Original numerical records retain their prior transcription review. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets The paper’s PRIME receptor-binding-domain variant collection; this is a paper-specific task, not a universal protein benchmark. Individual claims | PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings Version: version of record | source checked automated source review · 2026-09-16 Audit detailsInspected the cited primary abstract and descriptive computational-evaluation sections. Review covers the descriptive claims shown; no executable protocol was reconstructed. Original numerical records retain their prior transcription review. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Organisms SARS-CoV-2 in the reported variant dataset. Individual claims | PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings Version: version of record | source checked automated source review · 2026-09-16 Audit detailsInspected the cited primary abstract and descriptive computational-evaluation sections. Review covers the descriptive claims shown; no executable protocol was reconstructed. Original numerical records retain their prior transcription review. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Assays Previously published binding and expression measurements provide phenotype labels; this record concerns binding prediction. Individual claims | PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings Version: version of record | source checked automated source review · 2026-09-16 Audit detailsInspected the cited primary abstract and descriptive computational-evaluation sections. Review covers the descriptive claims shown; no executable protocol was reconstructed. Original numerical records retain their prior transcription review. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits Random and position-stratified settings are distinct. The linked results retain the reported setting; this profile does not supply an executable split manifest. Individual claims | PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings Version: version of record | source checked automated source review · 2026-09-16 Audit detailsInspected the cited primary abstract and descriptive computational-evaluation sections. Review covers the descriptive claims shown; no executable protocol was reconstructed. Original numerical records retain their prior transcription review. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Allowed inputs Protein-sequence representations associated with measured phenotype labels. Individual claims | PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings Version: version of record | source checked automated source review · 2026-09-16 Audit detailsInspected the cited primary abstract and descriptive computational-evaluation sections. Review covers the descriptive claims shown; no executable protocol was reconstructed. Original numerical records retain their prior transcription review. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation The paper distinguishes frozen representations from adapted models. Individual evaluation records retain that distinction. Individual claims | PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Abstract; Results: Benchmark data collection for viral phenotype prediction; Table 1 task and column headings Version: version of record | source checked automated source review · 2026-09-16 Audit detailsInspected the cited primary abstract and descriptive computational-evaluation sections. Review covers the descriptive claims shown; no executable protocol was reconstructed. Original numerical records retain their prior transcription review. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Release 2026-09-17-d277315f7d76 · Record review: needs review
Stable ID: reported-task-00e594df6a182d