Configuration

SAMS-VAE* (S)

SAMS-VAE (S): SAMS-VAE as reimplemented by the PerturBench authors with the sparse mask and global latent variables removed; Selected per dataset and task by Optuna HPO (at least 60 trials), then retrained with 5 seeds.

7 evaluations · 43 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.

Evaluations and results

7 evaluations · 43 results. Different protocols are not a single leaderboard.

Sorted by Perturbench RMSE of mean (lower 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 RMSE of mean	Perturbench RMSE rank	Perturbench cosine logfc	Perturbench cosine logfc rank	Perturbench energy mmd (gene expression space)	Perturbench energy mmd (PCA space: top 256 principal components fitted on the ground-truth test split)	Recall (DEG recall: fraction of the top 20 ground-truth DEGs (scanpy t-scores against controls) recalled from predicted cells)	Perturbench matrix distance	Perturbench RMSE transposed rank
SAMS-VAE* (S)Evaluation	PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24, Jiang24 (PerturBench v4 covariate-transfer split)	0.016 ± 2 × 10 − 3 (best in column)	0.42 ± 3 × 10 − 2	0.57 ± 5 × 10 − 2	0.42 ± 2 × 10 − 2	6.5 ± 2 × 10 0	1.6 ± 1 × 10 0	0.002 ± 1 × 10 − 4	Not reported	Not reported
SAMS-VAE* (S)Evaluation	PerturBench v4 covariate transfer to a held-out cell line on Srivatsan20, Srivatsan20 (PerturBench v4 covariate-transfer split)	0.018 ± 3 × 10 − 4	0.13 ± 1 × 10 − 2	0.53 ± 1 × 10 − 2	0.12 ± 2 × 10 − 2	2.9 ± 1 × 10 − 2	0.79 ± 1 × 10 − 2	0.000 ± 0	Not reported	Not reported
SAMS-VAE* (S)Evaluation	PerturBench v4 mode-collapse diagnostics on Srivatsan20, Srivatsan20 (PerturBench v4 covariate-transfer split)	0.02	0.111	Not reported	Not reported	Not reported	Not reported	Not reported	19.3 (best in column)	0.179 (best in column)
SAMS-VAE* (S)Evaluation	PerturBench v4 mode-collapse diagnostics on Frangieh21, Frangieh21 (PerturBench v4 co-culture split)	0.023	0.16	Not reported	Not reported	Not reported	Not reported	Not reported	54.5	0.416
SAMS-VAE* (S)Evaluation	PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21, Frangieh21 (PerturBench v4 co-culture split)	0.025 ± 5 × 10 − 5	0.22 ± 1 × 10 − 2	0.22 ± 3 × 10 − 3	0.22 ± 8 × 10 − 3	2.4 ± 1 × 10 − 2 (best in column)	0.32 ± 4 × 10 − 3 (best in column)	0.000 ± 0	Not reported	Not reported
SAMS-VAE* (S)Evaluation	PerturBench v4 covariate transfer of small-molecule effects across PBMC cell types on OP3, OP3 (PerturBench v4 split)	0.031 ± 1 × 10 − 4	0.051 ± 4 × 10 − 3	0.43 ± 2 × 10 − 3	0.079 ± 7 × 10 − 3	5.6 ± 9 × 10 − 3	0.74 ± 3 × 10 − 3	0.000 ± 0	Not reported	Not reported
SAMS-VAE* (S)Evaluation	PerturBench v4 combination prediction of held-out dual perturbations on Norman19, Norman19 (PerturBench v4 combination split)	0.047 ± 2 × 10 − 3	0.030 ± 7 × 10 − 3 (best in column)	0.78 ± 6 × 10 − 3 (best in column)	0.019 ± 5 × 10 − 3 (best in column)	3.3 ± 5 × 10 − 2	0.74 ± 5 × 10 − 2	0.028 ± 6 × 10 − 3 (best in column)	Not reported	Not reported

All 43 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: SAMS-VAE* (S)	Protocol: PerturBench v4 mode-collapse diagnostics on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	54.5 Perturbench matrix distance unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) on PerturBench v4 frangieh21-collapse lit-cells-networks-20261011-perturbench-v4-protocol-frangieh21-mode-collapse Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 13, row 'SAMS-VAE ∗ (S)', column 'Matrix distance'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 mode-collapse diagnostics on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	0.16 Perturbench RMSE rank fraction · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) on PerturBench v4 frangieh21-collapse lit-cells-networks-20261011-perturbench-v4-protocol-frangieh21-mode-collapse Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 13, row 'SAMS-VAE ∗ (S)', column 'RMSE mean rank'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 mode-collapse diagnostics on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	0.023 Perturbench RMSE of mean unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) on PerturBench v4 frangieh21-collapse lit-cells-networks-20261011-perturbench-v4-protocol-frangieh21-mode-collapse Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 13, row 'SAMS-VAE ∗ (S)', column 'RMSE mean'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 mode-collapse diagnostics on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	0.416 Perturbench RMSE transposed rank fraction · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) on PerturBench v4 frangieh21-collapse lit-cells-networks-20261011-perturbench-v4-protocol-frangieh21-mode-collapse Aggregation: Not reported PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) · Table 13, row 'SAMS-VAE ∗ (S)', column 'RMSE mean transposed-rank'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	0.22 ± 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 SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'Cosine LogFC rank'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	0.22 ± 3 × 10 − 3 Perturbench cosine logfc fraction · higher Uncertainty: SD 0.003 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'Cosine logFC'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	0.000 ± 0 Recall (DEG recall: fraction of the top 20 ground-truth DEGs (scanpy t-scores against controls) recalled from predicted cells) fraction · higher Uncertainty: SD 0 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'DEG recall'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	0.32 ± 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 SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'MMD PCA'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	2.4 ± 1 × 10 − 2 Perturbench energy mmd (gene expression space) unit-unreported · lower Uncertainty: SD 0.01 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'MMD'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	0.22 ± 1 × 10 − 2 Perturbench RMSE rank fraction · lower Uncertainty: SD 0.01 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'RMSE mean rank'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer from mono-culture to co-culture on Frangieh21 Dataset subset: Frangieh21 (PerturBench v4 co-culture split)	0.025 ± 5 × 10 − 5 Perturbench RMSE of mean unit-unreported · lower Uncertainty: SD 0.00005 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'RMSE mean'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24 Dataset subset: Jiang24 (PerturBench v4 covariate-transfer split)	0.42 ± 2 × 10 − 2 Perturbench cosine logfc rank fraction · lower Uncertainty: SD 0.02 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'Cosine LogFC rank'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24 Dataset subset: Jiang24 (PerturBench v4 covariate-transfer split)	0.57 ± 5 × 10 − 2 Perturbench cosine logfc fraction · higher Uncertainty: SD 0.05 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'Cosine logFC'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24 Dataset subset: Jiang24 (PerturBench v4 covariate-transfer split)	0.002 ± 1 × 10 − 4 Recall (DEG recall: fraction of the top 20 ground-truth DEGs (scanpy t-scores against controls) recalled from predicted cells) fraction · higher Uncertainty: SD 0.0001 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'DEG recall'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24 Dataset subset: Jiang24 (PerturBench v4 covariate-transfer split)	1.6 ± 1 × 10 0 Perturbench energy mmd (PCA space: top 256 principal components fitted on the ground-truth test split) unit-unreported · lower Uncertainty: SD 1 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'MMD PCA'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24 Dataset subset: Jiang24 (PerturBench v4 covariate-transfer split)	6.5 ± 2 × 10 0 Perturbench energy mmd (gene expression space) unit-unreported · lower Uncertainty: SD 2 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'MMD'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24 Dataset subset: Jiang24 (PerturBench v4 covariate-transfer split)	0.42 ± 3 × 10 − 2 Perturbench RMSE rank fraction · lower Uncertainty: SD 0.03 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'RMSE mean rank'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 covariate transfer to held-out perturbations in held-out biological states on Jiang24 Dataset subset: Jiang24 (PerturBench v4 covariate-transfer split)	0.016 ± 2 × 10 − 3 Perturbench RMSE of mean unit-unreported · lower Uncertainty: SD 0.002 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'RMSE mean'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.019 ± 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 SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'Cosine LogFC rank'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.78 ± 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 SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'Cosine logFC'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.028 ± 6 × 10 − 3 Recall (DEG recall: fraction of the top 20 ground-truth DEGs (scanpy t-scores against controls) recalled from predicted cells) fraction · higher Uncertainty: SD 0.006 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'DEG recall'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.74 ± 5 × 10 − 2 Perturbench energy mmd (PCA space: top 256 principal components fitted on the ground-truth test split) unit-unreported · lower Uncertainty: SD 0.05 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'MMD PCA'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	3.3 ± 5 × 10 − 2 Perturbench energy mmd (gene expression space) unit-unreported · lower Uncertainty: SD 0.05 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'MMD'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.030 ± 7 × 10 − 3 Perturbench RMSE rank fraction · lower Uncertainty: SD 0.007 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', column 'RMSE mean rank'
Configuration: SAMS-VAE* (S)	Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split)	0.047 ± 2 × 10 − 3 Perturbench RMSE of mean unit-unreported · lower Uncertainty: SD 0.002 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SAMS-VAE ∗ (S) 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 'SAMS-VAE ∗ (S)', 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-sams-vae-s

areas: single-cell
contexts: research
method types: supervised_machine_learning
reported name: SAMS-VAE ∗ (S)
source locator: Section 3.2; Section 5
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: SAMS-VAE as reimplemented by the PerturBench authors with the sparse mask and global latent variables removed (Section 3.2 and Section 5).

Related records

system: SAMS-VAE ∗ (S) on PerturBench v4 frangieh21-collapse
system: SAMS-VAE ∗ (S) on PerturBench v4 frangieh21
system: SAMS-VAE ∗ (S) on PerturBench v4 jiang24
system: SAMS-VAE ∗ (S) on PerturBench v4 norman19
system: SAMS-VAE ∗ (S) on PerturBench v4 op3
system: SAMS-VAE ∗ (S) on PerturBench v4 srivatsan20-collapse
system: SAMS-VAE ∗ (S) on PerturBench v4 srivatsan20

Suggest a correction