| Configuration: CARP-640M likelihood | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.144 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCARP-640M likelihood · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row CARP-640M likelihood; column spearman |
|---|
| Configuration: ESMC-300M naive supervised | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.106 ± 0.005 Spearman unitless · higher Uncertainty: ± 0.005 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESMC-300M naive supervised · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: mean of five random-seed fits (Section 4.3) FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row ESMC-300M naive supervised; column spearman |
|---|
| Configuration: Dayhoff likelihood | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.955 NDCG (cutoff not stated) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceDayhoff likelihood · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row Dayhoff likelihood; column ndcg |
|---|
| Configuration: Ridge (one-hot + likelihoods) | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.211 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRidge (one-hot + likelihoods) · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row Ridge (one-hot + likelihoods); column spearman |
|---|
| Configuration: ESM2-650M likelihood | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.141 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2-650M likelihood · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row ESM2-650M likelihood; column spearman |
|---|
| Configuration: CARP-640M naive supervised | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.012 ± 0.017 Spearman unitless · higher Uncertainty: ± 0.017 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCARP-640M naive supervised · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: mean of five random-seed fits (Section 4.3) FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row CARP-640M naive supervised; column spearman |
|---|
| Configuration: CARP-640M supervised | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.948 ± 0.004 NDCG (cutoff not stated) unitless · higher Uncertainty: ± 0.004 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCARP-640M supervised · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: mean of five random-seed fits (Section 4.3) FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row CARP-640M supervised; column ndcg |
|---|
| Configuration: Ridge (one-hot + likelihoods) | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.964 NDCG (cutoff not stated) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRidge (one-hot + likelihoods) · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row Ridge (one-hot + likelihoods); column ndcg |
|---|
| Configuration: Ridge (one-hot) | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.193 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRidge (one-hot) · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row Ridge (one-hot); column spearman |
|---|
| Configuration: Ridge (one-hot) | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.96 NDCG (cutoff not stated) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRidge (one-hot) · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row Ridge (one-hot); column ndcg |
|---|
| Configuration: ESMC-300M naive supervised | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.949 ± 0.001 NDCG (cutoff not stated) unitless · higher Uncertainty: ± 0.001 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESMC-300M naive supervised · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: mean of five random-seed fits (Section 4.3) FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row ESMC-300M naive supervised; column ndcg |
|---|
| Configuration: ESMC-300M supervised | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.954 ± 0.002 NDCG (cutoff not stated) unitless · higher Uncertainty: ± 0.002 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESMC-300M supervised · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: mean of five random-seed fits (Section 4.3) FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row ESMC-300M supervised; column ndcg |
|---|
| Configuration: Dayhoff likelihood | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.142 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceDayhoff likelihood · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row Dayhoff likelihood; column spearman |
|---|
| Configuration: ESM2-650M likelihood | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.953 NDCG (cutoff not stated) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESM2-650M likelihood · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row ESM2-650M likelihood; column ndcg |
|---|
| Configuration: CARP-640M naive supervised | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.944 ± 0.001 NDCG (cutoff not stated) unitless · higher Uncertainty: ± 0.001 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCARP-640M naive supervised · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: mean of five random-seed fits (Section 4.3) FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row CARP-640M naive supervised; column ndcg |
|---|
| Configuration: CARP-640M likelihood | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.956 NDCG (cutoff not stated) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCARP-640M likelihood · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row CARP-640M likelihood; column ndcg |
|---|
| Configuration: ESMC-300M supervised | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.160 ± 0.022 Spearman unitless · higher Uncertainty: ± 0.022 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESMC-300M supervised · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: mean of five random-seed fits (Section 4.3) FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row ESMC-300M supervised; column spearman |
|---|
| Configuration: CARP-640M supervised | Protocol: FLIP2 IRED two-to-many; held-out test set · IRED Dataset subset: IRED | 0.072 ± 0.046 Spearman unitless · higher Uncertainty: ± 0.046 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCARP-640M supervised · FLIP2 IRED two-to-many; held-out test set · IRED FLIP2 IRED two-to-many; held-out test set Aggregation: mean of five random-seed fits (Section 4.3) FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A5; row CARP-640M supervised; column spearman |
|---|