rewirebio.iobenchmarks
Protocol

Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2)

Hold out each drug's highest dose in each of 12 cell line and drug pairs, predict the held-out cell distribution, score mean distance, Pearson r and Sinkhorn W2, min-max normalise each across the compared methods within a protocol and average over protocols.

7 evaluations · 41 results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

7 recorded evaluations, 41 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

7 evaluations · 41 results. Different protocols are not a single leaderboard.

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)

Sorted by 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) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configurationMin 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)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)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)Rank (Rank of the overall normalised score among the seven Table 2 rows on 12 Sci-Plex highest-dose protocols)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)Runtime (Mean wall-clock seconds per Sci-Plex highest-dose protocol on one NVIDIA RTX 4090 worker, without any one-time pretraining cost)Runtime (Mean wall-clock seconds per Sci-Plex highest-dose protocol on one NVIDIA RTX 4090 worker, plus PerturbPFN's one-time pretraining cost divided across the 12 protocols)
PerturbPFN step-3100 checkpoint, in-context forward passEvaluation0.918 (best in column)0.7190.881(#2)0.8391.11433
RF X-Learner (100-tree random forest, PerturbPFN Table 2)Evaluation0.8120.879 (best in column)0.97 (best in column)(#1) (best in column)0.887 (best in column)1.83Not reported
MLP shift regression (GIM codebase, PerturbPFN Table 2)Evaluation0.7580.7820.922(#4)0.8210.82 (best in column)Not reported
CondOT (PICNN, PerturbPFN Table 2)Evaluation0.740.8010.932(#3)0.8257270Not reported
Naive nearest-lower-dose baselineEvaluation0.630.5430.629(#6)0.601Not reportedNot reported
GIM (Sci-Plex configuration, PerturbPFN Table 2)Evaluation0.2930.6910.861(#5)0.6154500Not reported
No change baselineEvaluation0.069800(#7)0.0233Not reportedNot reported
All 41 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
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 checked
Methods, coverage and source

CondOT 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 checked
Methods, coverage and source

CondOT 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 checked
Methods, coverage and source

CondOT 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 checked
Methods, coverage and source

CondOT 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 checked
Methods, coverage and source

CondOT 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 checked
Methods, coverage and source

CondOT 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 checked
Methods, coverage and source

GIM 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 checked
Methods, coverage and source

GIM 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 checked
Methods, coverage and source

GIM 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 checked
Methods, coverage and source

GIM 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 checked
Methods, coverage and source

GIM 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 checked
Methods, coverage and source

GIM 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 checked
Methods, coverage and source

MLP 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 checked
Methods, coverage and source

MLP 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 checked
Methods, coverage and source

MLP 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 checked
Methods, coverage and source

MLP 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 checked
Methods, coverage and source

MLP 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 checked
Methods, coverage and source

MLP 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 baselineProtocol: 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 checked
Methods, coverage and source

Naive 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 baselineProtocol: 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 checked
Methods, coverage and source

Naive 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 baselineProtocol: 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 checked
Methods, coverage and source

Naive 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 baselineProtocol: 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 checked
Methods, coverage and source

Naive 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 baselineProtocol: 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 checked
Methods, coverage and source

Naive 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 baselineProtocol: 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 checked
Methods, coverage and source

Observational 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 baselineProtocol: 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 checked
Methods, coverage and source

Observational 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

Source checking is not independent reproduction. Release 2026-11-21-adc15377fab2.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations
7

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

No-change prediction under matched control conditions

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Training-only mean-effect or linear prediction

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-11-21-adc15377fab2. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-adc15377fab2
Property and statementOriginal source and locationReview and provenance

No evidence rows match these filters. Choose another scope or clear the search.

Sources and history

Release 2026-11-21-adc15377fab2 · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and record identifiers

Technical metadata for this record is tracked under stable ID perturbpfn-20261115-protocol-sciplex-highest-dose-normalised.

Source locator: Section 4.2; Appendix D; Table 2

Related records

Suggest a correction