| Configuration: CondOT (PICNN, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.825 Weighted composite score (Equal-weight mean of the three protocol-averaged min-max normalised scores (mean distance, Pearson r, Sinkhorn W2) across the seven Table 2 rows on 12 Sci-Plex highest-dose protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCondOT on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'CondOT', column 'Avg. ŝ / rank', score before the bracket |
|---|
| Configuration: CondOT (PICNN, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | (#3) Rank (Rank of the overall normalised score among the seven Table 2 rows on 12 Sci-Plex highest-dose protocols) unitless · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCondOT on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'CondOT', column 'Avg. ŝ / rank', bracketed rank |
|---|
| Configuration: CondOT (PICNN, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 7270 Runtime (Mean wall-clock seconds per Sci-Plex highest-dose protocol on one NVIDIA RTX 4090 worker, without any one-time pretraining cost) second · lower Uncertainty: SD 585.9 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCondOT on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'CondOT', column 'Time (s) / protocol' |
|---|
| Configuration: CondOT (PICNN, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.801 Min max normalised score (Mean distance (L2 distance between predicted and observed mean expression over the 50 marker genes), negated, then min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCondOT on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'CondOT', column 'ŝMD ↑' |
|---|
| Configuration: CondOT (PICNN, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.932 Min max normalised score (Pearson correlation between predicted and observed mean expression over the 50 marker genes, min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCondOT on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'CondOT', column 'ŝr ↑' |
|---|
| Configuration: CondOT (PICNN, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.74 Min max normalised score (Debiased Sinkhorn 2-Wasserstein distance between predicted and observed cell sets (epsilon 0.1), negated, then min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCondOT on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'CondOT', column 'ŝW2 ↑' |
|---|
| Configuration: GIM (Sci-Plex configuration, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.615 Weighted composite score (Equal-weight mean of the three protocol-averaged min-max normalised scores (mean distance, Pearson r, Sinkhorn W2) across the seven Table 2 rows on 12 Sci-Plex highest-dose protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGIM on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'GIM', column 'Avg. ŝ / rank', score before the bracket |
|---|
| Configuration: GIM (Sci-Plex configuration, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | (#5) Rank (Rank of the overall normalised score among the seven Table 2 rows on 12 Sci-Plex highest-dose protocols) unitless · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGIM on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'GIM', column 'Avg. ŝ / rank', bracketed rank |
|---|
| Configuration: GIM (Sci-Plex configuration, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 4500 Runtime (Mean wall-clock seconds per Sci-Plex highest-dose protocol on one NVIDIA RTX 4090 worker, without any one-time pretraining cost) second · lower Uncertainty: SD 116.9 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGIM on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'GIM', column 'Time (s) / protocol' |
|---|
| Configuration: GIM (Sci-Plex configuration, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.691 Min max normalised score (Mean distance (L2 distance between predicted and observed mean expression over the 50 marker genes), negated, then min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGIM on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'GIM', column 'ŝMD ↑' |
|---|
| Configuration: GIM (Sci-Plex configuration, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.861 Min max normalised score (Pearson correlation between predicted and observed mean expression over the 50 marker genes, min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGIM on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'GIM', column 'ŝr ↑' |
|---|
| Configuration: GIM (Sci-Plex configuration, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.293 Min max normalised score (Debiased Sinkhorn 2-Wasserstein distance between predicted and observed cell sets (epsilon 0.1), negated, then min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGIM on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'GIM', column 'ŝW2 ↑' |
|---|
| Configuration: MLP shift regression (GIM codebase, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.821 Weighted composite score (Equal-weight mean of the three protocol-averaged min-max normalised scores (mean distance, Pearson r, Sinkhorn W2) across the seven Table 2 rows on 12 Sci-Plex highest-dose protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMLP on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'MLP', column 'Avg. ŝ / rank', score before the bracket |
|---|
| Configuration: MLP shift regression (GIM codebase, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | (#4) Rank (Rank of the overall normalised score among the seven Table 2 rows on 12 Sci-Plex highest-dose protocols) unitless · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMLP on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'MLP', column 'Avg. ŝ / rank', bracketed rank |
|---|
| Configuration: MLP shift regression (GIM codebase, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.82 Runtime (Mean wall-clock seconds per Sci-Plex highest-dose protocol on one NVIDIA RTX 4090 worker, without any one-time pretraining cost) second · lower Uncertainty: SD 0.25 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMLP on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'MLP', column 'Time (s) / protocol' |
|---|
| Configuration: MLP shift regression (GIM codebase, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.782 Min max normalised score (Mean distance (L2 distance between predicted and observed mean expression over the 50 marker genes), negated, then min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMLP on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'MLP', column 'ŝMD ↑' |
|---|
| Configuration: MLP shift regression (GIM codebase, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.922 Min max normalised score (Pearson correlation between predicted and observed mean expression over the 50 marker genes, min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMLP on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'MLP', column 'ŝr ↑' |
|---|
| Configuration: MLP shift regression (GIM codebase, PerturbPFN Table 2) | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.758 Min max normalised score (Debiased Sinkhorn 2-Wasserstein distance between predicted and observed cell sets (epsilon 0.1), negated, then min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMLP on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'MLP', column 'ŝW2 ↑' |
|---|
| Method: Naive nearest-lower-dose baseline | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.601 Weighted composite score (Equal-weight mean of the three protocol-averaged min-max normalised scores (mean distance, Pearson r, Sinkhorn W2) across the seven Table 2 rows on 12 Sci-Plex highest-dose protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNaive on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'Naive', column 'Avg. ŝ / rank', score before the bracket |
|---|
| Method: Naive nearest-lower-dose baseline | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | (#6) Rank (Rank of the overall normalised score among the seven Table 2 rows on 12 Sci-Plex highest-dose protocols) unitless · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNaive on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'Naive', column 'Avg. ŝ / rank', bracketed rank |
|---|
| Method: Naive nearest-lower-dose baseline | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.543 Min max normalised score (Mean distance (L2 distance between predicted and observed mean expression over the 50 marker genes), negated, then min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNaive on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'Naive', column 'ŝMD ↑' |
|---|
| Method: Naive nearest-lower-dose baseline | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.629 Min max normalised score (Pearson correlation between predicted and observed mean expression over the 50 marker genes, min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNaive on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'Naive', column 'ŝr ↑' |
|---|
| Method: Naive nearest-lower-dose baseline | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.63 Min max normalised score (Debiased Sinkhorn 2-Wasserstein distance between predicted and observed cell sets (epsilon 0.1), negated, then min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNaive on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'Naive', column 'ŝW2 ↑' |
|---|
| Method: No change baseline | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | 0.0233 Weighted composite score (Equal-weight mean of the three protocol-averaged min-max normalised scores (mean distance, Pearson r, Sinkhorn W2) across the seven Table 2 rows on 12 Sci-Plex highest-dose protocols) unitless · higher Uncertainty: Not reported by the source: No spread is printed for this value. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceObservational on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'Observational', column 'Avg. ŝ / rank', score before the bracket |
|---|
| Method: No change baseline | Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing) | (#7) Rank (Rank of the overall normalised score among the seven Table 2 rows on 12 Sci-Plex highest-dose protocols) unitless · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceObservational on the Sci-Plex highest-dose holdout (PerturbPFN Table 2) perturbpfn-20261115-protocol-sciplex-highest-dose-normalised Aggregation: Not reported PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'Observational', column 'Avg. ŝ / rank', bracketed rank |
|---|