rewirebio.iobenchmarks
Protocol

GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)

Infer a weighted directed TF-gene network from 300BCG baseline profiles, submit at most 50,000 ranked links and score them with the official GeneRNIB pipeline on held-out profiles and external references.

6 evaluations · 30 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.

6 recorded evaluations, 30 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

6 evaluations · 30 results. Different protocols are not a single leaderboard.

Protocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3) · Dataset: GeneRNIB 300BCG

Sorted by F1 (GeneRNIB gene-set F1: pathways enriched among predicted TF targets against pathways active in held-out expression, averaged across gene-set collections; 300BCG, at most 50,000 links) (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 configurationF1 (GeneRNIB gene-set F1: pathways enriched among predicted TF targets against pathways active in held-out expression, averaged across gene-set collections; 300BCG, at most 50,000 links)F1 (GeneRNIB TF-binding F1: normalised agreement and coverage against UniBind, ChIP-Atlas and ReMap TF-binding references; 300BCG, at most 50,000 links)Genernib regression precision (GeneRNIB regression precision with ridge regression, conservative regulator budget; 300BCG, at most 50,000 links)Genernib regression recall (GeneRNIB regression recall with ridge regression, broader regulator budget; 300BCG, at most 50,000 links)Genernib virtual cell score (GeneRNIB virtual-cell score: prediction of held-out perturbed expression by a model constrained by the inferred network; 300BCG, at most 50,000 links)
PerturbPFN step-3100 checkpoint, GeneRNIB panel aggregationEvaluation0.641 (best in column)0.1150.2250.1980.0731
PORTIAEvaluation0.6190.1010.3970.2670.117
GRNBoost2Evaluation0.5570.1130.6080.375 (best in column)0.158
SCENICEvaluation0.4810.118 (best in column)0.380.2750.0672
Pearson correlation networkEvaluation0.4690.110.615 (best in column)0.2740.188 (best in column)
PPCOR (partial Pearson correlation)Evaluation0.098200.1740.1920.066
All 30 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
Method: GRNBoost2Protocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.557 F1 (GeneRNIB gene-set F1: pathways enriched among predicted TF targets against pathways active in held-out expression, averaged across gene-set collections; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

GRNBoost2 on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'GRNBoost2', column 'GS-F1'
Method: GRNBoost2Protocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.608 Genernib regression precision (GeneRNIB regression precision with ridge regression, conservative regulator budget; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

GRNBoost2 on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'GRNBoost2', column 'R-Prec.'
Method: GRNBoost2Protocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.375 Genernib regression recall (GeneRNIB regression recall with ridge regression, broader regulator budget; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

GRNBoost2 on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'GRNBoost2', column 'R-Recall'
Method: GRNBoost2Protocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.113 F1 (GeneRNIB TF-binding F1: normalised agreement and coverage against UniBind, ChIP-Atlas and ReMap TF-binding references; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

GRNBoost2 on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'GRNBoost2', column 'TFB-F1'
Method: GRNBoost2Protocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.158 Genernib virtual cell score (GeneRNIB virtual-cell score: prediction of held-out perturbed expression by a model constrained by the inferred network; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

GRNBoost2 on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'GRNBoost2', column 'VC'
Method: Pearson correlation networkProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.469 F1 (GeneRNIB gene-set F1: pathways enriched among predicted TF targets against pathways active in held-out expression, averaged across gene-set collections; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

Pearson corr. on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'Pearson corr.', column 'GS-F1'
Method: Pearson correlation networkProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.615 Genernib regression precision (GeneRNIB regression precision with ridge regression, conservative regulator budget; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

Pearson corr. on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'Pearson corr.', column 'R-Prec.'
Method: Pearson correlation networkProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.274 Genernib regression recall (GeneRNIB regression recall with ridge regression, broader regulator budget; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

Pearson corr. on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'Pearson corr.', column 'R-Recall'
Method: Pearson correlation networkProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.11 F1 (GeneRNIB TF-binding F1: normalised agreement and coverage against UniBind, ChIP-Atlas and ReMap TF-binding references; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

Pearson corr. on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'Pearson corr.', column 'TFB-F1'
Method: Pearson correlation networkProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.188 Genernib virtual cell score (GeneRNIB virtual-cell score: prediction of held-out perturbed expression by a model constrained by the inferred network; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

Pearson corr. on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'Pearson corr.', column 'VC'
Configuration: PerturbPFN step-3100 checkpoint, GeneRNIB panel aggregationProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.641 F1 (GeneRNIB gene-set F1: pathways enriched among predicted TF targets against pathways active in held-out expression, averaged across gene-set collections; 300BCG, at most 50,000 links)
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

PerturbPFN on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PerturbPFN', column 'GS-F1'
Configuration: PerturbPFN step-3100 checkpoint, GeneRNIB panel aggregationProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.225 Genernib regression precision (GeneRNIB regression precision with ridge regression, conservative regulator budget; 300BCG, at most 50,000 links)
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

PerturbPFN on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PerturbPFN', column 'R-Prec.'
Configuration: PerturbPFN step-3100 checkpoint, GeneRNIB panel aggregationProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.198 Genernib regression recall (GeneRNIB regression recall with ridge regression, broader regulator budget; 300BCG, at most 50,000 links)
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

PerturbPFN on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PerturbPFN', column 'R-Recall'
Configuration: PerturbPFN step-3100 checkpoint, GeneRNIB panel aggregationProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.115 F1 (GeneRNIB TF-binding F1: normalised agreement and coverage against UniBind, ChIP-Atlas and ReMap TF-binding references; 300BCG, at most 50,000 links)
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

PerturbPFN on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PerturbPFN', column 'TFB-F1'
Configuration: PerturbPFN step-3100 checkpoint, GeneRNIB panel aggregationProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.0731 Genernib virtual cell score (GeneRNIB virtual-cell score: prediction of held-out perturbed expression by a model constrained by the inferred network; 300BCG, at most 50,000 links)
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

PerturbPFN on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PerturbPFN', column 'VC'
Method: PORTIAProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.619 F1 (GeneRNIB gene-set F1: pathways enriched among predicted TF targets against pathways active in held-out expression, averaged across gene-set collections; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

PORTIA on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PORTIA', column 'GS-F1'
Method: PORTIAProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.397 Genernib regression precision (GeneRNIB regression precision with ridge regression, conservative regulator budget; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

PORTIA on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PORTIA', column 'R-Prec.'
Method: PORTIAProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.267 Genernib regression recall (GeneRNIB regression recall with ridge regression, broader regulator budget; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

PORTIA on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PORTIA', column 'R-Recall'
Method: PORTIAProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.101 F1 (GeneRNIB TF-binding F1: normalised agreement and coverage against UniBind, ChIP-Atlas and ReMap TF-binding references; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

PORTIA on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PORTIA', column 'TFB-F1'
Method: PORTIAProtocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.117 Genernib virtual cell score (GeneRNIB virtual-cell score: prediction of held-out perturbed expression by a model constrained by the inferred network; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

PORTIA on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PORTIA', column 'VC'
Method: PPCOR (partial Pearson correlation)Protocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.0982 F1 (GeneRNIB gene-set F1: pathways enriched among predicted TF targets against pathways active in held-out expression, averaged across gene-set collections; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

PPCOR on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PPCOR', column 'GS-F1'
Method: PPCOR (partial Pearson correlation)Protocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.174 Genernib regression precision (GeneRNIB regression precision with ridge regression, conservative regulator budget; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

PPCOR on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PPCOR', column 'R-Prec.'
Method: PPCOR (partial Pearson correlation)Protocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.192 Genernib regression recall (GeneRNIB regression recall with ridge regression, broader regulator budget; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

PPCOR on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PPCOR', column 'R-Recall'
Method: PPCOR (partial Pearson correlation)Protocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0 F1 (GeneRNIB TF-binding F1: normalised agreement and coverage against UniBind, ChIP-Atlas and ReMap TF-binding references; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

PPCOR on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PPCOR', column 'TFB-F1'
Method: PPCOR (partial Pearson correlation)Protocol: GeneRNIB 300BCG GRN inference, 50,000-link budget, official all_metrics scoring (PerturbPFN Table 3)
Dataset: GeneRNIB 300BCG
0.066 Genernib virtual cell score (GeneRNIB virtual-cell score: prediction of held-out perturbed expression by a model constrained by the inferred network; 300BCG, at most 50,000 links)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Result quoted from another source · Source checked
Methods, coverage and source

PPCOR on GeneRNIB 300BCG (PerturbPFN Table 3)

perturbpfn-20261115-protocol-genernib-300bcg-50k

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 3, row 'PPCOR', column 'VC'

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

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
1
Evaluations quoted from another source
5

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-c8bea25e5abb. 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-c8bea25e5abb
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-c8bea25e5abb · 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-genernib-300bcg-50k.

Source locator: Section 4.3; Appendix E; Table 3

Related records

Suggest a correction