Strengths and considerations
No source-reviewed explanatory claims are recorded here yet.
Configuration
Transformer (no pretraining)
Transformer as evaluated in the cited study. No pretraining; original TAPE paper task-specific supervised head
tape primary benchmark evidence · Table2,p.7,row1(No pretraining/Transformer),columnSecondary structureAt a glance
Explanatory profile: limited source coverage · Automated source review, 2026-09-17. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
How it works
Evaluation in this paper
No pretraining; original TAPE paper task-specific supervised head
tape primary benchmark evidence · Table2,p.7,row1(No pretraining/Transformer),columnSecondary structureEvaluations and results
Release 2026-09-17-d277315f7d76 · 5 evaluations · 5 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Transformer (no pretraining): CB513 CB513 test set; train/test proteins filtered at 25% sequence identity Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.70 accuracy Unit: fraction · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedtape primary benchmark evidence · Table2,p.7,row1(No pretraining/Transformer),columnSecondary structure Source checking is not independent reproduction. |
| Transformer (no pretraining): Sarkisyan GFP fluorescence Configuration: Transformer (no pretraining)Task: TAPE FluorescenceDataset: TAPE Fluorescence source dataset Train/validation at most 3 mutations; test 4–15 mutations from the GFP parent Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.22 Spearman's rho Unit: correlation · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedtape primary benchmark evidence · Table2,p.7,row1(No pretraining/Transformer),columnFluorescence Source checking is not independent reproduction. |
| Transformer (no pretraining): Rocklin designed-protein stability Configuration: Transformer (no pretraining)Task: TAPE StabilityDataset: TAPE Stability source dataset Test 17 one-mutation neighbourhoods around candidate proteins; train on broad experimental design rounds Author-reported evaluation · Evaluation metadata: needs review | ||
| -0.06 Spearman's rho Unit: correlation · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedtape primary benchmark evidence · Table2,p.7,row1(No pretraining/Transformer),columnStability Source checking is not independent reproduction. |
| Transformer (no pretraining): SCOP1.75 fold-level test Configuration: Transformer (no pretraining)Task: TAPE Remote Homology DetectionDataset: SCOP1.75 fold-level test Held-out evolutionary groups; fold-level classification into 1,195 folds Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.09 accuracy Unit: fraction · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedtape primary benchmark evidence · Table2,p.7,row1(No pretraining/Transformer),columnRemote homology Source checking is not independent reproduction. |
| Transformer (no pretraining): ProteinNet CASP12 CASP12 test, 30% sequence-identity partition; medium/long-range contacts Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.32 precision at L/5 Unit: fraction · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedtape primary benchmark evidence · Table2,p.7,row1(No pretraining/Transformer),columnContact prediction Source checking is not independent reproduction. |
Strengths and limitations
Limitations and conditions
No source-reviewed explanatory claims are recorded here yet.
Profile review details
Primary-source transcription and separate automated review. No human sign-off or experimental reproduction.
Stable record: paper-model-536a4bbdbe5a079837Evidence table
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.
2 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Evaluation in this paper No pretraining; original TAPE paper task-specific supervised head Individual claims | tape primary benchmark evidence Table2,p.7,row1(No pretraining/Transformer),columnSecondary structure Version: 1906.08230v1 | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated review. No human sign-off or experimental reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Introduction Transformer as evaluated in the cited study. No pretraining; original TAPE paper task-specific supervised head Individual claims | tape primary benchmark evidence Table2,p.7,row1(No pretraining/Transformer),columnSecondary structure Version: 1906.08230v1 | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated review. No human sign-off or experimental reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-09-17-d277315f7d76 · Record review: needs review
- tape primary benchmark evidence · Original source · 1906.08230v1
Technical metadata and extraction receipts
Stable ID: paper-model-536a4bbdbe5a079837
- areas
- protein-function
- entity level
- method
- configuration type
- reported_configuration
- version
- No pretraining; original TAPE paper task-specific supervised head
- legacy kinds
- model
- entity classification
- review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: evidence-discovery-final-tape; source locator: Table2,p.7,row1(No pretraining/Transformer),columnSecondary structure; ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.