Amylase
Source-defined subset: Amylase. Exact membership and scoring coverage remain as reported in the cited artifact.
Evaluation results
Release 2026-09-19-eb6149e5d766 · 36 evaluations · 71 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 |
|---|---|---|
| CARP-640M likelihood · FLIP2 Amylase far-to-close; held-out test set · Amylase Configuration: CARP-640M likelihoodProtocol: FLIP2 Amylase far-to-close; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase far-to-close; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.919 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 A3; row CARP-640M likelihood; column ndcg Source checking is not independent reproduction. |
| 0.566 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 A3; row CARP-640M likelihood; column spearman Source checking is not independent reproduction. |
| ESMC-300M naive supervised · FLIP2 Amylase far-to-close; held-out test set · Amylase Configuration: ESMC-300M naive supervisedProtocol: FLIP2 Amylase far-to-close; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase far-to-close; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.818 ± 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 A3; row ESMC-300M naive supervised; column ndcg Source checking is not independent reproduction. |
| CARP-640M naive supervised · FLIP2 Amylase far-to-close; held-out test set · Amylase Configuration: CARP-640M naive supervisedProtocol: FLIP2 Amylase far-to-close; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase far-to-close; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.825 ± 0.009 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.009; type: unreported; value: 0.009 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A3; row CARP-640M naive supervised; column ndcg Source checking is not independent reproduction. |
| Ridge (one-hot) · FLIP2 Amylase close-to-far; held-out test set · Amylase Configuration: Ridge (one-hot)Protocol: FLIP2 Amylase close-to-far; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase close-to-far; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.865 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 A2; row Ridge (one-hot); column ndcg Source checking is not independent reproduction. |
| CARP-640M supervised · FLIP2 Amylase by-mutation; held-out test set · Amylase Configuration: CARP-640M supervisedProtocol: FLIP2 Amylase by-mutation; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase by-mutation; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.926 ± 0.050 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.050; type: unreported; value: 0.05 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A4; row CARP-640M supervised; column ndcg Source checking is not independent reproduction. |
| 0.551 ± 0.239 spearman Unit: correlation · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.239; type: unreported; value: 0.239 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A4; row CARP-640M supervised; column spearman Source checking is not independent reproduction. |
| Ridge (one-hot + likelihoods) · FLIP2 Amylase by-mutation; held-out test set · Amylase Configuration: Ridge (one-hot + likelihoods)Protocol: FLIP2 Amylase by-mutation; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase by-mutation; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.940 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 A4; row Ridge (one-hot + likelihoods); column ndcg Source checking is not independent reproduction. |
| ESMC-300M naive supervised · FLIP2 Amylase one-to-many; held-out test set · Amylase Configuration: ESMC-300M naive supervisedProtocol: FLIP2 Amylase one-to-many; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase one-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.850 ± 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 A1; row ESMC-300M naive supervised; column ndcg Source checking is not independent reproduction. |
| Dayhoff likelihood · FLIP2 Amylase far-to-close; held-out test set · Amylase Configuration: Dayhoff likelihoodProtocol: FLIP2 Amylase far-to-close; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase far-to-close; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.580 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 A3; row Dayhoff likelihood; column spearman Source checking is not independent reproduction. |
| ESMC-300M naive supervised · FLIP2 Amylase close-to-far; held-out test set · Amylase Configuration: ESMC-300M naive supervisedProtocol: FLIP2 Amylase close-to-far; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase close-to-far; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.864 ± 0.012 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.012; type: unreported; value: 0.012 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A2; row ESMC-300M naive supervised; column ndcg Source checking is not independent reproduction. |
| 0.007 ± 0.032 spearman Unit: correlation · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.032; type: unreported; value: 0.032 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A2; row ESMC-300M naive supervised; column spearman Source checking is not independent reproduction. |
| Ridge (one-hot + likelihoods) · FLIP2 Amylase close-to-far; held-out test set · Amylase Configuration: Ridge (one-hot + likelihoods)Protocol: FLIP2 Amylase close-to-far; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase close-to-far; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.955 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 A2; row Ridge (one-hot + likelihoods); column ndcg Source checking is not independent reproduction. |
| ESMC-300M supervised · FLIP2 Amylase by-mutation; held-out test set · Amylase Configuration: ESMC-300M supervisedProtocol: FLIP2 Amylase by-mutation; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase by-mutation; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.061 ± 0.130 spearman Unit: correlation · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.130; type: unreported; value: 0.13 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A4; row ESMC-300M supervised; column spearman Source checking is not independent reproduction. |
| ESM2-650M likelihood · FLIP2 Amylase close-to-far; held-out test set · Amylase Configuration: ESM2-650M likelihoodProtocol: FLIP2 Amylase close-to-far; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase close-to-far; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.955 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 A2; row ESM2-650M likelihood; column ndcg Source checking is not independent reproduction. |
| CARP-640M likelihood · FLIP2 Amylase by-mutation; held-out test set · Amylase Configuration: CARP-640M likelihoodProtocol: FLIP2 Amylase by-mutation; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase by-mutation; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.468 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 A4; row CARP-640M likelihood; column spearman Source checking is not independent reproduction. |
| ESM2-650M likelihood · FLIP2 Amylase one-to-many; held-out test set · Amylase Configuration: ESM2-650M likelihoodProtocol: FLIP2 Amylase one-to-many; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase one-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.942 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 A1; row ESM2-650M likelihood; column ndcg Source checking is not independent reproduction. |
| 0.560 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 A1; row ESM2-650M likelihood; column spearman Source checking is not independent reproduction. |
| Dayhoff likelihood · FLIP2 Amylase by-mutation; held-out test set · Amylase Configuration: Dayhoff likelihoodProtocol: FLIP2 Amylase by-mutation; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase by-mutation; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.499 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 A4; row Dayhoff likelihood; column spearman Source checking is not independent reproduction. |
| ESMC-300M supervised · FLIP2 Amylase one-to-many; held-out test set · Amylase Configuration: ESMC-300M supervisedProtocol: FLIP2 Amylase one-to-many; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase one-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.869 ± 0.028 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.028; type: unreported; value: 0.028 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A1; row ESMC-300M supervised; column ndcg Source checking is not independent reproduction. |
| CARP-640M likelihood · FLIP2 Amylase one-to-many; held-out test set · Amylase Configuration: CARP-640M likelihoodProtocol: FLIP2 Amylase one-to-many; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase one-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.931 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 A1; row CARP-640M likelihood; column ndcg Source checking is not independent reproduction. |
| CARP-640M supervised · FLIP2 Amylase one-to-many; held-out test set · Amylase Configuration: CARP-640M supervisedProtocol: FLIP2 Amylase one-to-many; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase one-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.873 ± 0.029 ndcg Unit: unitless · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.029; type: unreported; value: 0.029 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A1; row CARP-640M supervised; column ndcg Source checking is not independent reproduction. |
| Dayhoff likelihood · FLIP2 Amylase one-to-many; held-out test set · Amylase Configuration: Dayhoff likelihoodProtocol: FLIP2 Amylase one-to-many; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase one-to-many; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.522 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 A1; row Dayhoff likelihood; column spearman Source checking is not independent reproduction. |
| CARP-640M supervised · FLIP2 Amylase far-to-close; held-out test set · Amylase Configuration: CARP-640M supervisedProtocol: FLIP2 Amylase far-to-close; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase far-to-close; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.140 ± 0.102 spearman Unit: correlation · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.102; type: unreported; value: 0.102 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A3; row CARP-640M supervised; column spearman Source checking is not independent reproduction. |
| CARP-640M supervised · FLIP2 Amylase close-to-far; held-out test set · Amylase Configuration: CARP-640M supervisedProtocol: FLIP2 Amylase close-to-far; held-out test set · AmylaseDataset subset: Amylase FLIP2 Amylase close-to-far; held-out test set Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.081 ± 0.055 spearman Unit: correlation · Direction: higher Aggregation: mean of five random-seed fits (Section 4.3) | Uncertainty: printed spread: 0.055; type: unreported; value: 0.055 Scored: Not reported · Eligible: Not reported | source checkedFLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A2; row CARP-640M supervised; column spearman 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 A1; row Ridge (one-hot); column spearman Context-only references | FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications Table A1; 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: Amylase. 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 A1; 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 Amylase Context-only references | FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications Table A1; 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-b0b4eca267c04e159e7c
- source locator
- Table A1; row Ridge (one-hot); column spearman
- missing metadata
- split manifest: unextracted
Related records
- dataset: Dayhoff likelihood · FLIP2 Amylase far-to-close; held-out test set · Amylase
- dataset: CARP-640M supervised · FLIP2 Amylase one-to-many; held-out test set · Amylase
- dataset: Ridge (one-hot) · FLIP2 Amylase by-mutation; held-out test set · Amylase
- dataset: Dayhoff likelihood · FLIP2 Amylase one-to-many; held-out test set · Amylase
- dataset: Ridge (one-hot + likelihoods) · FLIP2 Amylase one-to-many; held-out test set · Amylase
- dataset: Ridge (one-hot) · FLIP2 Amylase one-to-many; held-out test set · Amylase
- dataset: CARP-640M supervised · FLIP2 Amylase far-to-close; held-out test set · Amylase
- dataset: CARP-640M naive supervised · FLIP2 Amylase close-to-far; held-out test set · Amylase
- dataset: CARP-640M likelihood · FLIP2 Amylase close-to-far; held-out test set · Amylase
- dataset: Dayhoff likelihood · FLIP2 Amylase by-mutation; held-out test set · Amylase
- dataset: CARP-640M naive supervised · FLIP2 Amylase far-to-close; held-out test set · Amylase
- dataset: CARP-640M naive supervised · FLIP2 Amylase by-mutation; held-out test set · Amylase
- dataset: CARP-640M likelihood · FLIP2 Amylase by-mutation; held-out test set · Amylase
- dataset: ESMC-300M naive supervised · FLIP2 Amylase one-to-many; held-out test set · Amylase
- dataset: ESM2-650M likelihood · FLIP2 Amylase far-to-close; held-out test set · Amylase
- dataset: ESMC-300M naive supervised · FLIP2 Amylase by-mutation; held-out test set · Amylase
- dataset: CARP-640M naive supervised · FLIP2 Amylase one-to-many; held-out test set · Amylase
- dataset: ESMC-300M naive supervised · FLIP2 Amylase close-to-far; held-out test set · Amylase
- dataset: Ridge (one-hot) · FLIP2 Amylase far-to-close; held-out test set · Amylase
- dataset: CARP-640M likelihood · FLIP2 Amylase far-to-close; held-out test set · Amylase
- dataset: Ridge (one-hot + likelihoods) · FLIP2 Amylase far-to-close; held-out test set · Amylase
- dataset: ESM2-650M likelihood · FLIP2 Amylase one-to-many; held-out test set · Amylase
- dataset: ESM2-650M likelihood · FLIP2 Amylase by-mutation; held-out test set · Amylase
- dataset: ESMC-300M supervised · FLIP2 Amylase far-to-close; held-out test set · Amylase
- dataset: CARP-640M supervised · FLIP2 Amylase by-mutation; held-out test set · Amylase
- dataset: CARP-640M likelihood · FLIP2 Amylase one-to-many; held-out test set · Amylase
- dataset: Ridge (one-hot + likelihoods) · FLIP2 Amylase by-mutation; held-out test set · Amylase
- dataset: ESMC-300M supervised · FLIP2 Amylase close-to-far; held-out test set · Amylase
- dataset: Ridge (one-hot + likelihoods) · FLIP2 Amylase close-to-far; held-out test set · Amylase
- dataset: ESMC-300M supervised · FLIP2 Amylase one-to-many; held-out test set · Amylase
- dataset: CARP-640M supervised · FLIP2 Amylase close-to-far; held-out test set · Amylase
- dataset: ESM2-650M likelihood · FLIP2 Amylase close-to-far; held-out test set · Amylase
- dataset: Dayhoff likelihood · FLIP2 Amylase close-to-far; held-out test set · Amylase
- dataset: ESMC-300M supervised · FLIP2 Amylase by-mutation; held-out test set · Amylase
- dataset: Ridge (one-hot) · FLIP2 Amylase close-to-far; held-out test set · Amylase
- dataset: ESMC-300M naive supervised · FLIP2 Amylase far-to-close; held-out test set · Amylase