TrpB
Source-defined subset: TrpB. Exact membership and scoring coverage remain as reported in the cited artifact.
Evaluation results
Release 2026-09-19-eb6149e5d766 · 27 evaluations · 53 metric rows. Different protocols are not a single leaderboard. Charts retain each source table’s protocol and dataset.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| ESMC-300M supervised · FLIP2 TrpB by-position; held-out test set · TrpB Configuration: ESMC-300M supervisedProtocol: FLIP2 TrpB by-position; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB by-position; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.980 ± 0.007 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.007; type: unreported; value: 0.007 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A9; row ESMC-300M supervised; column ndcg Source checking is not independent reproduction. |
| CARP-640M naive supervised · FLIP2 TrpB one-to-many; held-out test set · TrpB Configuration: CARP-640M naive supervisedProtocol: FLIP2 TrpB one-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB one-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.298 ± 0.217 spearman Unit: correlation · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.217; type: unreported; value: 0.217 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A7; row CARP-640M naive supervised; column spearman Source checking is not independent reproduction. |
| 0.984 ± 0.002 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.002; type: unreported; value: 0.002 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A7; row CARP-640M naive supervised; column ndcg Source checking is not independent reproduction. |
| Ridge (one-hot + likelihoods) · FLIP2 TrpB one-to-many; held-out test set · TrpB Configuration: Ridge (one-hot + likelihoods)Protocol: FLIP2 TrpB one-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB one-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.453 spearman Unit: correlation · Direction: higher Aggregation: reported point estimate | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A7; row Ridge (one-hot + likelihoods); column spearman Source checking is not independent reproduction. |
| CARP-640M naive supervised · FLIP2 TrpB two-to-many; held-out test set · TrpB Configuration: CARP-640M naive supervisedProtocol: FLIP2 TrpB two-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB two-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.985 ± 0.002 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.002; type: unreported; value: 0.002 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A8; row CARP-640M naive supervised; column ndcg Source checking is not independent reproduction. |
| Ridge (one-hot + likelihoods) · FLIP2 TrpB two-to-many; held-out test set · TrpB Configuration: Ridge (one-hot + likelihoods)Protocol: FLIP2 TrpB two-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB two-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.994 ndcg Unit: unitless · Direction: higher Aggregation: reported point estimate | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A8; row Ridge (one-hot + likelihoods); column ndcg Source checking is not independent reproduction. |
| Dayhoff likelihood · FLIP2 TrpB by-position; held-out test set · TrpB Configuration: Dayhoff likelihoodProtocol: FLIP2 TrpB by-position; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB by-position; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.183 spearman Unit: correlation · Direction: higher Aggregation: reported point estimate | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A9; row Dayhoff likelihood; column spearman Source checking is not independent reproduction. |
| ESMC-300M naive supervised · FLIP2 TrpB one-to-many; held-out test set · TrpB Configuration: ESMC-300M naive supervisedProtocol: FLIP2 TrpB one-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB one-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.986 ± 0.002 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.002; type: unreported; value: 0.002 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A7; row ESMC-300M naive supervised; column ndcg Source checking is not independent reproduction. |
| ESMC-300M naive supervised · FLIP2 TrpB by-position; held-out test set · TrpB Configuration: ESMC-300M naive supervisedProtocol: FLIP2 TrpB by-position; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB by-position; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.154 ± 0.059 spearman Unit: correlation · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.059; type: unreported; value: 0.059 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A9; row ESMC-300M naive supervised; column spearman Source checking is not independent reproduction. |
| 0.978 ± 0.004 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.004; type: unreported; value: 0.004 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A9; row ESMC-300M naive supervised; column ndcg Source checking is not independent reproduction. |
| Dayhoff likelihood · FLIP2 TrpB one-to-many; held-out test set · TrpB Configuration: Dayhoff likelihoodProtocol: FLIP2 TrpB one-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB one-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.991 ndcg Unit: unitless · Direction: higher Aggregation: reported point estimate | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A7; row Dayhoff likelihood; column ndcg Source checking is not independent reproduction. |
| CARP-640M supervised · FLIP2 TrpB two-to-many; held-out test set · TrpB Configuration: CARP-640M supervisedProtocol: FLIP2 TrpB two-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB two-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.996 ± 0.000 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.000; type: unreported; value: 0 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A8; row CARP-640M supervised; column ndcg Source checking is not independent reproduction. |
| 0.509 ± 0.010 spearman Unit: correlation · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.010; type: unreported; value: 0.01 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A8; row CARP-640M supervised; column spearman Source checking is not independent reproduction. |
| CARP-640M supervised · FLIP2 TrpB by-position; held-out test set · TrpB Configuration: CARP-640M supervisedProtocol: FLIP2 TrpB by-position; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB by-position; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.983 ± 0.003 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.003; type: unreported; value: 0.003 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A9; row CARP-640M supervised; column ndcg Source checking is not independent reproduction. |
| Ridge (one-hot + likelihoods) · FLIP2 TrpB by-position; held-out test set · TrpB Configuration: Ridge (one-hot + likelihoods)Protocol: FLIP2 TrpB by-position; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB by-position; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.988 ndcg Unit: unitless · Direction: higher Aggregation: reported point estimate | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A9; row Ridge (one-hot + likelihoods); column ndcg Source checking is not independent reproduction. |
| 0.294 spearman Unit: correlation · Direction: higher Aggregation: reported point estimate | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A9; row Ridge (one-hot + likelihoods); column spearman Source checking is not independent reproduction. |
| CARP-640M likelihood · FLIP2 TrpB one-to-many; held-out test set · TrpB Configuration: CARP-640M likelihoodProtocol: FLIP2 TrpB one-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB one-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.418 spearman Unit: correlation · Direction: higher Aggregation: reported point estimate | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A7; row CARP-640M likelihood; column spearman Source checking is not independent reproduction. |
| ESMC-300M naive supervised · FLIP2 TrpB two-to-many; held-out test set · TrpB Configuration: ESMC-300M naive supervisedProtocol: FLIP2 TrpB two-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB two-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.398 ± 0.020 spearman Unit: correlation · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.020; type: unreported; value: 0.02 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A8; row ESMC-300M naive supervised; column spearman Source checking is not independent reproduction. |
| 0.986 ± 0.001 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.001; type: unreported; value: 0.001 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A8; row ESMC-300M naive supervised; column ndcg Source checking is not independent reproduction. |
| CARP-640M likelihood · FLIP2 TrpB two-to-many; held-out test set · TrpB Configuration: CARP-640M likelihoodProtocol: FLIP2 TrpB two-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB two-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.992 ndcg Unit: unitless · Direction: higher Aggregation: reported point estimate | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A8; row CARP-640M likelihood; column ndcg Source checking is not independent reproduction. |
| ESM2-650M likelihood · FLIP2 TrpB two-to-many; held-out test set · TrpB Configuration: ESM2-650M likelihoodProtocol: FLIP2 TrpB two-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB two-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.992 ndcg Unit: unitless · Direction: higher Aggregation: reported point estimate | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A8; row ESM2-650M likelihood; column ndcg Source checking is not independent reproduction. |
| CARP-640M naive supervised · FLIP2 TrpB by-position; held-out test set · TrpB Configuration: CARP-640M naive supervisedProtocol: FLIP2 TrpB by-position; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB by-position; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| −0.009 ± nan spearman Unit: correlation · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: nan; type: unreported; value: Not reported Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A9; row CARP-640M naive supervised; column spearman Source checking is not independent reproduction. |
| ESMC-300M supervised · FLIP2 TrpB two-to-many; held-out test set · TrpB Configuration: ESMC-300M supervisedProtocol: FLIP2 TrpB two-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB two-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.991 ± 0.003 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.003; type: unreported; value: 0.003 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A8; row ESMC-300M supervised; column ndcg Source checking is not independent reproduction. |
| ESMC-300M supervised · FLIP2 TrpB one-to-many; held-out test set · TrpB Configuration: ESMC-300M supervisedProtocol: FLIP2 TrpB one-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB one-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.306 ± 0.063 spearman Unit: correlation · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.063; type: unreported; value: 0.063 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A7; row ESMC-300M supervised; column spearman Source checking is not independent reproduction. |
| Dayhoff likelihood · FLIP2 TrpB two-to-many; held-out test set · TrpB Configuration: Dayhoff likelihoodProtocol: FLIP2 TrpB two-to-many; held-out test set · TrpBDataset subset: TrpB FLIP2 TrpB two-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.991 ndcg Unit: unitless · Direction: higher Aggregation: reported point estimate | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A8; row Dayhoff likelihood; column ndcg Source checking is not independent reproduction. |
Subset and evaluation context
This record describes a particular subset or cohort used in an evaluation. Its results do not describe the full dataset.
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.
3 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| attributes.source_locator Table A7; row Ridge (one-hot); column spearman Context-only references | FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications Table A7; row Ridge (one-hot); column spearman Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| description Source-defined subset: TrpB. Exact membership and scoring coverage remain as reported in the cited artifact. Context-only references | FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications Table A7; row Ridge (one-hot); column spearman Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| name TrpB Context-only references | FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications Table A7; row Ridge (one-hot); column spearman Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
View linked audit checks and correction history
Release 2026-09-19-eb6149e5d766 · Record review: discovered
1 source records and release history
- FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Original source · Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Technical metadata and extraction receipts
Stable ID: acquired-dataset-80c2f9413c0c60d9b53d
- source locator
- Table A7; row Ridge (one-hot); column spearman
- missing metadata
- split manifest: unextracted
Related records
- dataset: ESMC-300M naive supervised · FLIP2 TrpB by-position; held-out test set · TrpB
- dataset: CARP-640M supervised · FLIP2 TrpB one-to-many; held-out test set · TrpB
- dataset: ESMC-300M naive supervised · FLIP2 TrpB two-to-many; held-out test set · TrpB
- dataset: Ridge (one-hot) · FLIP2 TrpB by-position; held-out test set · TrpB
- dataset: ESMC-300M supervised · FLIP2 TrpB by-position; held-out test set · TrpB
- dataset: Ridge (one-hot + likelihoods) · FLIP2 TrpB one-to-many; held-out test set · TrpB
- dataset: ESMC-300M naive supervised · FLIP2 TrpB one-to-many; held-out test set · TrpB
- dataset: ESM2-650M likelihood · FLIP2 TrpB by-position; held-out test set · TrpB
- dataset: Ridge (one-hot) · FLIP2 TrpB two-to-many; held-out test set · TrpB
- dataset: CARP-640M likelihood · FLIP2 TrpB one-to-many; held-out test set · TrpB
- dataset: Dayhoff likelihood · FLIP2 TrpB one-to-many; held-out test set · TrpB
- dataset: ESM2-650M likelihood · FLIP2 TrpB two-to-many; held-out test set · TrpB
- dataset: Ridge (one-hot + likelihoods) · FLIP2 TrpB two-to-many; held-out test set · TrpB
- dataset: CARP-640M supervised · FLIP2 TrpB two-to-many; held-out test set · TrpB
- dataset: ESMC-300M supervised · FLIP2 TrpB two-to-many; held-out test set · TrpB
- dataset: Dayhoff likelihood · FLIP2 TrpB two-to-many; held-out test set · TrpB
- dataset: ESMC-300M supervised · FLIP2 TrpB one-to-many; held-out test set · TrpB
- dataset: CARP-640M naive supervised · FLIP2 TrpB by-position; held-out test set · TrpB
- dataset: CARP-640M likelihood · FLIP2 TrpB two-to-many; held-out test set · TrpB
- dataset: CARP-640M likelihood · FLIP2 TrpB by-position; held-out test set · TrpB
- dataset: CARP-640M supervised · FLIP2 TrpB by-position; held-out test set · TrpB
- dataset: ESM2-650M likelihood · FLIP2 TrpB one-to-many; held-out test set · TrpB
- dataset: Ridge (one-hot + likelihoods) · FLIP2 TrpB by-position; held-out test set · TrpB
- dataset: CARP-640M naive supervised · FLIP2 TrpB two-to-many; held-out test set · TrpB
- dataset: Ridge (one-hot) · FLIP2 TrpB one-to-many; held-out test set · TrpB
- dataset: CARP-640M naive supervised · FLIP2 TrpB one-to-many; held-out test set · TrpB
- dataset: Dayhoff likelihood · FLIP2 TrpB by-position; held-out test set · TrpB