Configuration

Decoder

Baseline implemented by the PerturBench authors.

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

13 evaluations · 38 results. Different protocols are not a single leaderboard.

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	Protocol and dataset	Perturbench cosine logfc	Perturbench cosine logfc rank	Perturbench RMSE of mean	Perturbench RMSE rank	Perturbench energy mmd (gene expression space)	Perturbench energy mmd (PCA space: top 256 principal components fitted on the ground-truth test split)
DecoderEvaluation	PerturBench v4 combination prediction of held-out dual perturbations on Norman19, Norman19 (PerturBench v4 combination split)	0.73 ± 2 × 10 − 2 (best in column)	0.017 ± 6 × 10 − 3 (best in column)	0.043 ± 3 × 10 − 4	0.014 ± 4 × 10 − 4 (best in column)	6.7 ± 6 × 10 − 3	3.2 ± 4 × 10 − 3
DecoderEvaluation	PerturBench CB-COSINE: combination prediction on Norman19, Cosine similarity of log fold change, Norman19 (PerturBench split)	0.73 ± 2 × 10 − 2 (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported
DecoderEvaluation	PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24, Jiang24 (PerturBench v4 covariate-transfer split)	0.64 ± 8 × 10 − 4	0.32 ± 8 × 10 − 3	0.015 ± 3 × 10 − 5 (best in column)	0.32 ± 5 × 10 − 3	8.0 ± 2 × 10 − 3	2.6 ± 2 × 10 − 3
DecoderEvaluation	PerturBench v4 covariate transfer to a held-out cell line on Srivatsan20, Srivatsan20 (PerturBench v4 covariate-transfer split)	0.35 ± 5 × 10 − 3	0.16 ± 1 × 10 − 2	0.018 ± 1 × 10 − 4	0.14 ± 7 × 10 − 3	4.2 ± 4 × 10 − 3 (best in column)	1.9 ± 5 × 10 − 3 (best in column)
DecoderEvaluation	PerturBench CT-COSINE: covariate transfer on Srivatsan20, Cosine similarity of log fold change, Srivatsan20 (PerturBench split)	0.35 ± 5 × 10 − 3	Not reported	Not reported	Not reported	Not reported	Not reported
DecoderEvaluation	PerturBench v4 covariate transfer of small-molecule effects across PBMC cell types on OP3, OP3 (PerturBench v4 split)	0.32 ± 6 × 10 − 3	0.070 ± 5 × 10 − 3	0.035 ± 2 × 10 − 4	0.068 ± 6 × 10 − 3	11.0 ± 5 × 10 − 3	4.4 ± 1 × 10 − 2
DecoderEvaluation	PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21, Frangieh21 (PerturBench v4 co-culture split)	0.10 ± 2 × 10 − 3	0.21 ± 5 × 10 − 3	0.025 ± 4 × 10 − 5	0.15 ± 4 × 10 − 4	6.6 ± 8 × 10 − 4	3.3 ± 4 × 10 − 4
DecoderEvaluation	PerturBench CB-COSINE-RANK: combination prediction on Norman19, Cosine LogFC rank, Norman19 (PerturBench split)	Not reported	0.017 ± 6 × 10 − 3 (best in column)	Not reported	Not reported	Not reported	Not reported
DecoderEvaluation	PerturBench CB-RMSE-RANK: combination prediction on Norman19, RMSE mean rank, Norman19 (PerturBench split)	Not reported	Not reported	Not reported	0.014 ± 4 × 10 − 4 (best in column)	Not reported	Not reported
DecoderEvaluation	PerturBench CB-RMSE: combination prediction on Norman19, RMSE of the mean, Norman19 (PerturBench split)	Not reported	Not reported	0.043 ± 3 × 10 − 4	Not reported	Not reported	Not reported
DecoderEvaluation	PerturBench CT-COSINE-RANK: covariate transfer on Srivatsan20, Cosine LogFC rank, Srivatsan20 (PerturBench split)	Not reported	0.16 ± 1 × 10 − 2	Not reported	Not reported	Not reported	Not reported
DecoderEvaluation	PerturBench CT-RMSE-RANK: covariate transfer on Srivatsan20, RMSE mean rank, Srivatsan20 (PerturBench split)	Not reported	Not reported	Not reported	0.14 ± 7 × 10 − 3	Not reported	Not reported
DecoderEvaluation	PerturBench CT-RMSE: covariate transfer on Srivatsan20, RMSE of the mean, Srivatsan20 (PerturBench split)	Not reported	Not reported	0.018 ± 1 × 10 − 4	Not reported	Not reported	Not reported

All 38 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: Decoder	Protocol: PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	0.21 ± 5 × 10 − 3 Perturbench cosine logfc rank fraction · lower Uncertainty: SD 0.005 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 frangieh21 lit-cells-networks-20261011-perturbench-v4-protocol-frangieh21 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 7, row 'Decoder', column 'Cosine LogFC rank'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	0.10 ± 2 × 10 − 3 Perturbench cosine logfc fraction · higher Uncertainty: SD 0.002 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 frangieh21 lit-cells-networks-20261011-perturbench-v4-protocol-frangieh21 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 7, row 'Decoder', column 'Cosine logFC'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	3.3 ± 4 × 10 − 4 Perturbench energy mmd (PCA space: top 256 principal components fitted on the ground-truth test split) unit-unreported · lower Uncertainty: SD 0.0004 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 frangieh21 lit-cells-networks-20261011-perturbench-v4-protocol-frangieh21 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 7, row 'Decoder', column 'MMD PCA'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	6.6 ± 8 × 10 − 4 Perturbench energy mmd (gene expression space) unit-unreported · lower Uncertainty: SD 0.0008 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 frangieh21 lit-cells-networks-20261011-perturbench-v4-protocol-frangieh21 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 8, row 'Decoder', column 'MMD'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	0.15 ± 4 × 10 − 4 Perturbench RMSE rank fraction · lower Uncertainty: SD 0.0004 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 frangieh21 lit-cells-networks-20261011-perturbench-v4-protocol-frangieh21 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 8, row 'Decoder', column 'RMSE mean rank'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	0.025 ± 4 × 10 − 5 Perturbench RMSE of mean unit-unreported · lower Uncertainty: SD 0.00004 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 frangieh21 lit-cells-networks-20261011-perturbench-v4-protocol-frangieh21 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 8, row 'Decoder', column 'RMSE mean'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24 Dataset subset: Jiang24 (PerturBench v4 covariate-transfer split)	0.32 ± 8 × 10 − 3 Perturbench cosine logfc rank fraction · lower Uncertainty: SD 0.008 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 jiang24 lit-cells-networks-20261011-perturbench-v4-protocol-jiang24 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 4, row 'Decoder', column 'Cosine LogFC rank'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24 Dataset subset: Jiang24 (PerturBench v4 covariate-transfer split)	0.64 ± 8 × 10 − 4 Perturbench cosine logfc fraction · higher Uncertainty: SD 0.0008 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 jiang24 lit-cells-networks-20261011-perturbench-v4-protocol-jiang24 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 4, row 'Decoder', column 'Cosine logFC'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24 Dataset subset: Jiang24 (PerturBench v4 covariate-transfer split)	2.6 ± 2 × 10 − 3 Perturbench energy mmd (PCA space: top 256 principal components fitted on the ground-truth test split) unit-unreported · lower Uncertainty: SD 0.002 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 jiang24 lit-cells-networks-20261011-perturbench-v4-protocol-jiang24 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 4, row 'Decoder', column 'MMD PCA'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24 Dataset subset: Jiang24 (PerturBench v4 covariate-transfer split)	8.0 ± 2 × 10 − 3 Perturbench energy mmd (gene expression space) unit-unreported · lower Uncertainty: SD 0.002 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 jiang24 lit-cells-networks-20261011-perturbench-v4-protocol-jiang24 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 11, row 'Decoder', column 'MMD'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24 Dataset subset: Jiang24 (PerturBench v4 covariate-transfer split)	0.32 ± 5 × 10 − 3 Perturbench RMSE rank fraction · lower Uncertainty: SD 0.005 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 jiang24 lit-cells-networks-20261011-perturbench-v4-protocol-jiang24 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 11, row 'Decoder', column 'RMSE mean rank'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24 Dataset subset: Jiang24 (PerturBench v4 covariate-transfer split)	0.015 ± 3 × 10 − 5 Perturbench RMSE of mean unit-unreported · lower Uncertainty: SD 0.00003 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 jiang24 lit-cells-networks-20261011-perturbench-v4-protocol-jiang24 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 11, row 'Decoder', column 'RMSE mean'
Configuration: Decoder	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.017 ± 6 × 10 − 3 Perturbench cosine logfc rank fraction · lower Uncertainty: SD 0.006 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder 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 'Decoder', column 'Cosine LogFC rank'
Configuration: Decoder	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.73 ± 2 × 10 − 2 Perturbench cosine logfc fraction · higher Uncertainty: SD 0.02 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder 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 'Decoder', column 'Cosine logFC'
Configuration: Decoder	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	3.2 ± 4 × 10 − 3 Perturbench energy mmd (PCA space: top 256 principal components fitted on the ground-truth test split) unit-unreported · lower Uncertainty: SD 0.004 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder 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 'Decoder', column 'MMD PCA'
Configuration: Decoder	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	6.7 ± 6 × 10 − 3 Perturbench energy mmd (gene expression space) unit-unreported · lower Uncertainty: SD 0.006 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder 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 'Decoder', column 'MMD'
Configuration: Decoder	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.014 ± 4 × 10 − 4 Perturbench RMSE rank fraction · lower Uncertainty: SD 0.0004 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder 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 'Decoder', column 'RMSE mean rank'
Configuration: Decoder	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.043 ± 3 × 10 − 4 Perturbench RMSE of mean unit-unreported · lower Uncertainty: SD 0.0003 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder 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 'Decoder', column 'RMSE mean'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer of small-molecule effects across PBMC cell types on OP3 Dataset subset: OP3 (PerturBench v4 split)	0.070 ± 5 × 10 − 3 Perturbench cosine logfc rank fraction · lower Uncertainty: SD 0.005 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 op3 lit-cells-networks-20261011-perturbench-v4-protocol-op3 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 9, row 'Decoder', column 'Cosine LogFC rank'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer of small-molecule effects across PBMC cell types on OP3 Dataset subset: OP3 (PerturBench v4 split)	0.32 ± 6 × 10 − 3 Perturbench cosine logfc fraction · higher Uncertainty: SD 0.006 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 op3 lit-cells-networks-20261011-perturbench-v4-protocol-op3 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 9, row 'Decoder', column 'Cosine LogFC'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer of small-molecule effects across PBMC cell types on OP3 Dataset subset: OP3 (PerturBench v4 split)	4.4 ± 1 × 10 − 2 Perturbench energy mmd (PCA space: top 256 principal components fitted on the ground-truth test split) unit-unreported · lower Uncertainty: SD 0.01 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 op3 lit-cells-networks-20261011-perturbench-v4-protocol-op3 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 9, row 'Decoder', column 'MMD PCA'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer of small-molecule effects across PBMC cell types on OP3 Dataset subset: OP3 (PerturBench v4 split)	11.0 ± 5 × 10 − 3 Perturbench energy mmd (gene expression space) unit-unreported · lower Uncertainty: SD 0.005 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 op3 lit-cells-networks-20261011-perturbench-v4-protocol-op3 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 10, row 'Decoder', column 'MMD'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer of small-molecule effects across PBMC cell types on OP3 Dataset subset: OP3 (PerturBench v4 split)	0.068 ± 6 × 10 − 3 Perturbench RMSE rank fraction · lower Uncertainty: SD 0.006 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 op3 lit-cells-networks-20261011-perturbench-v4-protocol-op3 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 10, row 'Decoder', column 'RMSE mean rank'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer of small-molecule effects across PBMC cell types on OP3 Dataset subset: OP3 (PerturBench v4 split)	0.035 ± 2 × 10 − 4 Perturbench RMSE of mean unit-unreported · lower Uncertainty: SD 0.0002 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 op3 lit-cells-networks-20261011-perturbench-v4-protocol-op3 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 10, row 'Decoder', column 'RMSE mean'
Configuration: Decoder	Protocol: PerturBench v4 covariate transfer to a held-out cell line on Srivatsan20 Dataset subset: Srivatsan20 (PerturBench v4 covariate-transfer split)	0.16 ± 1 × 10 − 2 Perturbench cosine logfc rank fraction · lower Uncertainty: SD 0.01 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Decoder on PerturBench v4 srivatsan20 lit-cells-networks-20261011-perturbench-v4-protocol-srivatsan20 Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 2, row 'Decoder', column 'Cosine LogFC rank'

Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.

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 2026-11-02-a7f03c9e55a5
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 2026-11-02-a7f03c9e55a5 · Record review: source checked

1 source record and release history

PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis · Original source · Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: perturbench-method-decoder

areas: cells-tissues
source locator: Table 2, row(Decoder)
missing metadata: checkpoint revision: reason: unreported; parameters: reason: unextracted

Related records

Suggest a correction