| Configuration: AlphaFold-Multimer with full-Fv ipSAE ranking | Protocol: POISK pairwise binder-versus-decoy accuracy at 50% coverage Dataset subset: POISK co-folding binder-decoy benchmark set (22,494 complexes) | 0.68 Paired accuracy (binder scored above its matched putative decoy by full-Fv ipSAE, top 50% of the 11,247 pairs ranked by within-pair maximum ipSAE, exact ties at half credit) fraction · higher Uncertainty: Not reported by the source: Table 1 prints no spread for this column. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceAlphaFold-Multimer on POISK pairwise binder-versus-decoy accuracy at 50% coverage poisk-20261115-protocol-pairwise-coverage-50 Aggregation: Not reported Tupikina et al. 2026, Can Folding Models Tell Binders from Bluffers? Evidence from POISK (bioRxiv v1 PDF) · Table 1, row "AlphaFold-Multimer", column "Accuracy at", sub-column "50% Pairs" |
|---|
| Configuration: AlphaFold-Multimer with full-Fv ipSAE ranking | Protocol: POISK pairwise binder-versus-decoy accuracy at 50% coverage Dataset subset: POISK co-folding binder-decoy benchmark set (22,494 complexes) | 0.679 Paired accuracy (binder scored above its matched putative decoy by full-Fv ipSAE, top 50% of the 11,247 pairs ranked by within-pair maximum ipSAE, exact ties at half credit) fraction · higher Uncertainty: Not reported by the source: Table 7 prints no spread; the paper says the pairwise benchmarks operate on the full set of 11,247 pairs without random sampling, so error bars do not apply. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceAlphaFold-Multimer on POISK pairwise binder-versus-decoy accuracy at 50% coverage poisk-20261115-protocol-pairwise-coverage-50 Aggregation: Not reported Tupikina et al. 2026, Can Folding Models Tell Binders from Bluffers? Evidence from POISK (bioRxiv v1 PDF) · Table 7, row "AlphaFold-Multimer", column "50%" |
|---|
| Configuration: Boltz-2 with full-Fv ipSAE ranking | Protocol: POISK pairwise binder-versus-decoy accuracy at 50% coverage Dataset subset: POISK co-folding binder-decoy benchmark set (22,494 complexes) | 0.6 Paired accuracy (binder scored above its matched putative decoy by full-Fv ipSAE, top 50% of the 11,247 pairs ranked by within-pair maximum ipSAE, exact ties at half credit) fraction · higher Uncertainty: Not reported by the source: Table 1 prints no spread for this column. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBoltz-2 on POISK pairwise binder-versus-decoy accuracy at 50% coverage poisk-20261115-protocol-pairwise-coverage-50 Aggregation: Not reported Tupikina et al. 2026, Can Folding Models Tell Binders from Bluffers? Evidence from POISK (bioRxiv v1 PDF) · Table 1, row "Boltz-2", column "Accuracy at", sub-column "50% Pairs" |
|---|
| Configuration: Boltz-2 with full-Fv ipSAE ranking | Protocol: POISK pairwise binder-versus-decoy accuracy at 50% coverage Dataset subset: POISK co-folding binder-decoy benchmark set (22,494 complexes) | 0.602 Paired accuracy (binder scored above its matched putative decoy by full-Fv ipSAE, top 50% of the 11,247 pairs ranked by within-pair maximum ipSAE, exact ties at half credit) fraction · higher Uncertainty: Not reported by the source: Table 7 prints no spread; the paper says the pairwise benchmarks operate on the full set of 11,247 pairs without random sampling, so error bars do not apply. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBoltz-2 on POISK pairwise binder-versus-decoy accuracy at 50% coverage poisk-20261115-protocol-pairwise-coverage-50 Aggregation: Not reported Tupikina et al. 2026, Can Folding Models Tell Binders from Bluffers? Evidence from POISK (bioRxiv v1 PDF) · Table 7, row "Boltz-2", column "50%" |
|---|
| Configuration: IntelliFold v2 with full-Fv ipSAE ranking | Protocol: POISK pairwise binder-versus-decoy accuracy at 50% coverage Dataset subset: POISK co-folding binder-decoy benchmark set (22,494 complexes) | 0.8 Paired accuracy (binder scored above its matched putative decoy by full-Fv ipSAE, top 50% of the 11,247 pairs ranked by within-pair maximum ipSAE, exact ties at half credit) fraction · higher Uncertainty: Not reported by the source: Table 1 prints no spread for this column. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceIntelliFold v2 on POISK pairwise binder-versus-decoy accuracy at 50% coverage poisk-20261115-protocol-pairwise-coverage-50 Aggregation: Not reported Tupikina et al. 2026, Can Folding Models Tell Binders from Bluffers? Evidence from POISK (bioRxiv v1 PDF) · Table 1, row "IntelliFold v2", column "Accuracy at", sub-column "50% Pairs" |
|---|
| Configuration: IntelliFold v2 with full-Fv ipSAE ranking | Protocol: POISK pairwise binder-versus-decoy accuracy at 50% coverage Dataset subset: POISK co-folding binder-decoy benchmark set (22,494 complexes) | 0.798 Paired accuracy (binder scored above its matched putative decoy by full-Fv ipSAE, top 50% of the 11,247 pairs ranked by within-pair maximum ipSAE, exact ties at half credit) fraction · higher Uncertainty: Not reported by the source: Table 7 prints no spread; the paper says the pairwise benchmarks operate on the full set of 11,247 pairs without random sampling, so error bars do not apply. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceIntelliFold v2 on POISK pairwise binder-versus-decoy accuracy at 50% coverage poisk-20261115-protocol-pairwise-coverage-50 Aggregation: Not reported Tupikina et al. 2026, Can Folding Models Tell Binders from Bluffers? Evidence from POISK (bioRxiv v1 PDF) · Table 7, row "IntelliFold v2", column "50%" |
|---|
| Configuration: OpenFold3 with full-Fv ipSAE ranking | Protocol: POISK pairwise binder-versus-decoy accuracy at 50% coverage Dataset subset: POISK co-folding binder-decoy benchmark set (22,494 complexes) | 0.67 Paired accuracy (binder scored above its matched putative decoy by full-Fv ipSAE, top 50% of the 11,247 pairs ranked by within-pair maximum ipSAE, exact ties at half credit) fraction · higher Uncertainty: Not reported by the source: Table 1 prints no spread for this column. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceOpenFold3 on POISK pairwise binder-versus-decoy accuracy at 50% coverage poisk-20261115-protocol-pairwise-coverage-50 Aggregation: Not reported Tupikina et al. 2026, Can Folding Models Tell Binders from Bluffers? Evidence from POISK (bioRxiv v1 PDF) · Table 1, row "OpenFold3", column "Accuracy at", sub-column "50% Pairs" |
|---|
| Configuration: OpenFold3 with full-Fv ipSAE ranking | Protocol: POISK pairwise binder-versus-decoy accuracy at 50% coverage Dataset subset: POISK co-folding binder-decoy benchmark set (22,494 complexes) | 0.672 Paired accuracy (binder scored above its matched putative decoy by full-Fv ipSAE, top 50% of the 11,247 pairs ranked by within-pair maximum ipSAE, exact ties at half credit) fraction · higher Uncertainty: Not reported by the source: Table 7 prints no spread; the paper says the pairwise benchmarks operate on the full set of 11,247 pairs without random sampling, so error bars do not apply. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceOpenFold3 on POISK pairwise binder-versus-decoy accuracy at 50% coverage poisk-20261115-protocol-pairwise-coverage-50 Aggregation: Not reported Tupikina et al. 2026, Can Folding Models Tell Binders from Bluffers? Evidence from POISK (bioRxiv v1 PDF) · Table 7, row "OpenFold3", column "50%" |
|---|
| Configuration: Protenix-v1 with full-Fv ipSAE ranking | Protocol: POISK pairwise binder-versus-decoy accuracy at 50% coverage Dataset subset: POISK co-folding binder-decoy benchmark set (22,494 complexes) | 0.8 Paired accuracy (binder scored above its matched putative decoy by full-Fv ipSAE, top 50% of the 11,247 pairs ranked by within-pair maximum ipSAE, exact ties at half credit) fraction · higher Uncertainty: Not reported by the source: Table 1 prints no spread for this column. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceProtenix-v1 on POISK pairwise binder-versus-decoy accuracy at 50% coverage poisk-20261115-protocol-pairwise-coverage-50 Aggregation: Not reported Tupikina et al. 2026, Can Folding Models Tell Binders from Bluffers? Evidence from POISK (bioRxiv v1 PDF) · Table 1, row "Protenix-v1", column "Accuracy at", sub-column "50% Pairs" |
|---|
| Configuration: Protenix-v1 with full-Fv ipSAE ranking | Protocol: POISK pairwise binder-versus-decoy accuracy at 50% coverage Dataset subset: POISK co-folding binder-decoy benchmark set (22,494 complexes) | 0.797 Paired accuracy (binder scored above its matched putative decoy by full-Fv ipSAE, top 50% of the 11,247 pairs ranked by within-pair maximum ipSAE, exact ties at half credit) fraction · higher Uncertainty: Not reported by the source: Table 7 prints no spread; the paper says the pairwise benchmarks operate on the full set of 11,247 pairs without random sampling, so error bars do not apply. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceProtenix-v1 on POISK pairwise binder-versus-decoy accuracy at 50% coverage poisk-20261115-protocol-pairwise-coverage-50 Aggregation: Not reported Tupikina et al. 2026, Can Folding Models Tell Binders from Bluffers? Evidence from POISK (bioRxiv v1 PDF) · Table 7, row "Protenix-v1", column "50%" |
|---|
| Configuration: Protenix-v2 with full-Fv ipSAE ranking | Protocol: POISK pairwise binder-versus-decoy accuracy at 50% coverage Dataset subset: POISK co-folding binder-decoy benchmark set (22,494 complexes) | 0.87 Paired accuracy (binder scored above its matched putative decoy by full-Fv ipSAE, top 50% of the 11,247 pairs ranked by within-pair maximum ipSAE, exact ties at half credit) fraction · higher Uncertainty: Not reported by the source: Table 1 prints no spread for this column. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceProtenix-v2 on POISK pairwise binder-versus-decoy accuracy at 50% coverage poisk-20261115-protocol-pairwise-coverage-50 Aggregation: Not reported Tupikina et al. 2026, Can Folding Models Tell Binders from Bluffers? Evidence from POISK (bioRxiv v1 PDF) · Table 1, row "Protenix-v2", column "Accuracy at", sub-column "50% Pairs" |
|---|
| Configuration: Protenix-v2 with full-Fv ipSAE ranking | Protocol: POISK pairwise binder-versus-decoy accuracy at 50% coverage Dataset subset: POISK co-folding binder-decoy benchmark set (22,494 complexes) | 0.868 Paired accuracy (binder scored above its matched putative decoy by full-Fv ipSAE, top 50% of the 11,247 pairs ranked by within-pair maximum ipSAE, exact ties at half credit) fraction · higher Uncertainty: Not reported by the source: Table 7 prints no spread; the paper says the pairwise benchmarks operate on the full set of 11,247 pairs without random sampling, so error bars do not apply. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceProtenix-v2 on POISK pairwise binder-versus-decoy accuracy at 50% coverage poisk-20261115-protocol-pairwise-coverage-50 Aggregation: Not reported Tupikina et al. 2026, Can Folding Models Tell Binders from Bluffers? Evidence from POISK (bioRxiv v1 PDF) · Table 7, row "Protenix-v2", column "50%" |
|---|