Configuration

GEARS (PerturBench Norman19 run)

Configuration of GEARS: Selected per dataset and task by Optuna HPO (at least 60 trials), then retrained with 5 seeds.

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.

Evaluations and results

1 evaluation · 4 results. Different protocols are not a single leaderboard.

Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 · Dataset subset: Norman19 (PerturBench v4 combination split)

Sorted by Perturbench cosine logfc (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 configuration	Perturbench cosine logfc	Perturbench cosine logfc rank	Perturbench RMSE of mean	Perturbench RMSE rank
GEARS (PerturBench Norman19 run)Evaluation	0.44 ± 5 × 10 − 3	0.051 ± 1 × 10 − 2	0.069 ± 1 × 10 − 3	0.055 ± 6 × 10 − 3

All 4 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: GEARS (PerturBench Norman19 run)	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.051 ± 1 × 10 − 2 Perturbench cosine logfc rank fraction · lower Uncertainty: SD 0.01 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GEARS on PerturBench v4 norman19 lit-cells-networks-20261011-perturbench-v4-protocol-norman19 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 3, row 'GEARS', column 'Cosine LogFC rank'
Configuration: GEARS (PerturBench Norman19 run)	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.44 ± 5 × 10 − 3 Perturbench cosine logfc fraction · higher Uncertainty: SD 0.005 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GEARS on PerturBench v4 norman19 lit-cells-networks-20261011-perturbench-v4-protocol-norman19 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 3, row 'GEARS', column 'Cosine logFC'
Configuration: GEARS (PerturBench Norman19 run)	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.055 ± 6 × 10 − 3 Perturbench RMSE rank fraction · lower Uncertainty: SD 0.006 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GEARS on PerturBench v4 norman19 lit-cells-networks-20261011-perturbench-v4-protocol-norman19 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 6, row 'GEARS', column 'RMSE mean rank'
Configuration: GEARS (PerturBench Norman19 run)	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.069 ± 1 × 10 − 3 Perturbench RMSE of mean unit-unreported · lower Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GEARS on PerturBench v4 norman19 lit-cells-networks-20261011-perturbench-v4-protocol-norman19 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 6, row 'GEARS', column 'RMSE mean'

Source checking is not independent reproduction. Release 2026-10-23-5347695500ed.

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

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 2026-10-23-5347695500ed
Property and statement	Original source and location	Review and provenance

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

How to read the evidence

Sources and history

Release 2026-10-23-5347695500ed · Record review: source checked

1 source record and release history

PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Original source · arXiv 2408.10609v4, posted 2025-10-24 (NeurIPS 2025 Datasets and Benchmarks Track version)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-cells-networks-20261011-perturbench-v4-config-gears-perturbench-norman19-run

areas: single-cell
contexts: research
method types: supervised_machine_learning
reported name: GEARS
source locator: Appendix D.5 'GEARS'
foundation model eligible: false
hyperparameters: Selected per dataset and task by Optuna HPO (at least 60 trials), then retrained with 5 seeds (Section 4.3)
access reuse: Code in the PerturBench repository (github.com/altoslabs/perturbench)
missing metadata: version: reason: unreported; note: No code commit is printed for the v4 runs
provenance note: GEARS trained and evaluated by the PerturBench authors with its public code and their HPO script on the PerturBench Norman19 split (Appendix D.5).

Related records

configuration of: GEARS
system: GEARS on PerturBench v4 norman19

Suggest a correction