| Configuration: ESM2-650M likelihood | Protocol: FLIP2 hydro low-to-high; held-out test set · hydro Dataset subset: hydro | 0.865 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 hydro low-to-high; held-out test set · hydro FLIP2 hydro low-to-high; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row ESM2-650M likelihood; column ndcg |
|---|
| Configuration: ESMC-300M supervised | Protocol: FLIP2 hydro to-P0A9X9; held-out test set · hydro Dataset subset: hydro | 0.078 ± 0.133 Spearman unitless · higher Uncertainty: ± 0.133 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESMC-300M supervised · FLIP2 hydro to-P0A9X9; held-out test set · hydro FLIP2 hydro to-P0A9X9; 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 A13; row ESMC-300M supervised; column spearman |
|---|
| Configuration: Ridge (one-hot) | Protocol: FLIP2 hydro to-P01053; held-out test set · hydro Dataset subset: hydro | 0.889 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 hydro to-P01053; held-out test set · hydro FLIP2 hydro to-P01053; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A14; row Ridge (one-hot); column ndcg |
|---|
| Configuration: ESMC-300M naive supervised | Protocol: FLIP2 hydro to-P06241; held-out test set · hydro Dataset subset: hydro | 0.098 ± 0.024 Spearman unitless · higher Uncertainty: ± 0.024 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESMC-300M naive supervised · FLIP2 hydro to-P06241; held-out test set · hydro FLIP2 hydro to-P06241; 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 A12; row ESMC-300M naive supervised; column spearman |
|---|
| Configuration: CARP-640M likelihood | Protocol: FLIP2 hydro low-to-high; held-out test set · hydro Dataset subset: hydro | 0.284 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 hydro low-to-high; held-out test set · hydro FLIP2 hydro low-to-high; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row CARP-640M likelihood; column spearman |
|---|
| Configuration: CARP-640M supervised | Protocol: FLIP2 hydro to-P0A9X9; held-out test set · hydro Dataset subset: hydro | 0.961 ± 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 hydro to-P0A9X9; held-out test set · hydro FLIP2 hydro to-P0A9X9; 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 A13; row CARP-640M supervised; column ndcg |
|---|
| Configuration: Ridge (one-hot) | Protocol: FLIP2 hydro to-P06241; held-out test set · hydro Dataset subset: hydro | −0.138 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 hydro to-P06241; held-out test set · hydro FLIP2 hydro to-P06241; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A12; row Ridge (one-hot); column spearman |
|---|
| Configuration: ESM2-650M likelihood | Protocol: FLIP2 hydro to-P0A9X9; held-out test set · hydro Dataset subset: hydro | 0.049 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 hydro to-P0A9X9; held-out test set · hydro FLIP2 hydro to-P0A9X9; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A13; row ESM2-650M likelihood; column spearman |
|---|
| Configuration: CARP-640M naive supervised | Protocol: FLIP2 hydro to-P06241; held-out test set · hydro Dataset subset: hydro | 0.927 ± 0.006 NDCG (cutoff not stated) unitless · higher Uncertainty: ± 0.006 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCARP-640M naive supervised · FLIP2 hydro to-P06241; held-out test set · hydro FLIP2 hydro to-P06241; 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 A12; row CARP-640M naive supervised; column ndcg |
|---|
| Configuration: Ridge (one-hot) | Protocol: FLIP2 hydro three-to-many; held-out test set · hydro Dataset subset: hydro | 0.148 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 hydro three-to-many; held-out test set · hydro FLIP2 hydro three-to-many; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A10; row Ridge (one-hot); column spearman |
|---|
| Configuration: Ridge (one-hot) | Protocol: FLIP2 hydro to-P0A9X9; held-out test set · hydro Dataset subset: hydro | 0.957 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 hydro to-P0A9X9; held-out test set · hydro FLIP2 hydro to-P0A9X9; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A13; row Ridge (one-hot); column ndcg |
|---|
| Configuration: ESM2-650M likelihood | Protocol: FLIP2 hydro three-to-many; held-out test set · hydro Dataset subset: hydro | −0.036 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 hydro three-to-many; held-out test set · hydro FLIP2 hydro three-to-many; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A10; row ESM2-650M likelihood; column spearman |
|---|
| Configuration: CARP-640M supervised | Protocol: FLIP2 hydro three-to-many; held-out test set · hydro Dataset subset: hydro | 0.516 ± 0.035 Spearman unitless · higher Uncertainty: ± 0.035 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCARP-640M supervised · FLIP2 hydro three-to-many; held-out test set · hydro FLIP2 hydro three-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 A10; row CARP-640M supervised; column spearman |
|---|
| Configuration: CARP-640M likelihood | Protocol: FLIP2 hydro low-to-high; held-out test set · hydro Dataset subset: hydro | 0.921 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 hydro low-to-high; held-out test set · hydro FLIP2 hydro low-to-high; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A11; row CARP-640M likelihood; column ndcg |
|---|
| Configuration: ESMC-300M supervised | Protocol: FLIP2 hydro to-P01053; held-out test set · hydro Dataset subset: hydro | 0.949 ± 0.024 NDCG (cutoff not stated) unitless · higher Uncertainty: ± 0.024 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESMC-300M supervised · FLIP2 hydro to-P01053; held-out test set · hydro FLIP2 hydro to-P01053; 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 A14; row ESMC-300M supervised; column ndcg |
|---|
| Configuration: CARP-640M naive supervised | Protocol: FLIP2 hydro to-P01053; held-out test set · hydro Dataset subset: hydro | 0.061 ± 0.094 Spearman unitless · higher Uncertainty: ± 0.094 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCARP-640M naive supervised · FLIP2 hydro to-P01053; held-out test set · hydro FLIP2 hydro to-P01053; 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 A14; row CARP-640M naive supervised; column spearman |
|---|
| Configuration: CARP-640M likelihood | Protocol: FLIP2 hydro to-P06241; held-out test set · hydro Dataset subset: hydro | 0.957 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 hydro to-P06241; held-out test set · hydro FLIP2 hydro to-P06241; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A12; row CARP-640M likelihood; column ndcg |
|---|
| Configuration: ESMC-300M naive supervised | Protocol: FLIP2 hydro three-to-many; held-out test set · hydro Dataset subset: hydro | 0.367 ± 0.042 Spearman unitless · higher Uncertainty: ± 0.042 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESMC-300M naive supervised · FLIP2 hydro three-to-many; held-out test set · hydro FLIP2 hydro three-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 A10; row ESMC-300M naive supervised; column spearman |
|---|
| Configuration: CARP-640M supervised | Protocol: FLIP2 hydro to-P0A9X9; held-out test set · hydro Dataset subset: hydro | 0.004 ± 0.103 Spearman unitless · higher Uncertainty: ± 0.103 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCARP-640M supervised · FLIP2 hydro to-P0A9X9; held-out test set · hydro FLIP2 hydro to-P0A9X9; 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 A13; row CARP-640M supervised; column spearman |
|---|
| Configuration: ESM2-650M likelihood | Protocol: FLIP2 hydro to-P01053; held-out test set · hydro Dataset subset: hydro | 0.053 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 hydro to-P01053; held-out test set · hydro FLIP2 hydro to-P01053; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A14; row ESM2-650M likelihood; column spearman |
|---|
| Configuration: Ridge (one-hot) | Protocol: FLIP2 hydro three-to-many; held-out test set · hydro Dataset subset: hydro | 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 hydro three-to-many; held-out test set · hydro FLIP2 hydro three-to-many; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A10; row Ridge (one-hot); column ndcg |
|---|
| Configuration: ESMC-300M supervised | Protocol: FLIP2 hydro to-P06241; held-out test set · hydro Dataset subset: hydro | 0.934 ± 0.011 NDCG (cutoff not stated) unitless · higher Uncertainty: ± 0.011 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceESMC-300M supervised · FLIP2 hydro to-P06241; held-out test set · hydro FLIP2 hydro to-P06241; 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 A12; row ESMC-300M supervised; column ndcg |
|---|
| Configuration: Ridge (one-hot + likelihoods) | Protocol: FLIP2 hydro to-P01053; held-out test set · hydro Dataset subset: hydro | 0.942 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 hydro to-P01053; held-out test set · hydro FLIP2 hydro to-P01053; held-out test set Aggregation: reported point estimate FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications · Table A14; row Ridge (one-hot + likelihoods); column ndcg |
|---|
| Configuration: CARP-640M supervised | Protocol: FLIP2 hydro to-P01053; held-out test set · hydro Dataset subset: hydro | 0.909 ± 0.008 NDCG (cutoff not stated) unitless · higher Uncertainty: ± 0.008 (type not stated) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCARP-640M supervised · FLIP2 hydro to-P01053; held-out test set · hydro FLIP2 hydro to-P01053; 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 A14; row CARP-640M supervised; column ndcg |
|---|
| Configuration: ESMC-300M naive supervised | Protocol: FLIP2 hydro to-P06241; held-out test set · hydro Dataset subset: hydro | 0.927 ± 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 hydro to-P06241; held-out test set · hydro FLIP2 hydro to-P06241; 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 A12; row ESMC-300M naive supervised; column ndcg |
|---|