rewire.itbenchmarks
← Back to results
Task

PerturBench CT-RMSE-RANK: covariate transfer on Srivatsan20, RMSE mean rank

covariate transfer on Srivatsan20, RMSE mean rank. Scored with RMSE mean rank on Srivatsan20. Train on some cell types and predict drug effects in a held-out cell type, reported as the mean and one standard deviation over seeds.

10 evaluations · 10 results

Overview

covariate transfer on Srivatsan20, RMSE mean rank. Scored with RMSE mean rank on Srivatsan20. Train on some cell types and predict drug effects in a held-out cell type, reported as the mean and one standard deviation over seeds.

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

Results

Each comparison retains its reviewed evaluation scope, dataset and metric. Results are shown without a pooled ranking.

PerturBench CT-RMSE-RANK: covariate transfer on Srivatsan20, RMSE mean rank

rmse_mean_rank (fraction) · Lower values are better.

PerturBench CT-RMSE-RANK: covariate transfer on Srivatsan20, RMSE mean rank · Srivatsan20 (PerturBench split)

Evidence origin: Author-reported evaluation.

PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis · Table 2, column(RMSE, mean rank)
  • RMSE and both rank metrics are better when lower. The rank metrics measure how often another perturbation's prediction is closer than the right one's.
  • The two experiments use different datasets and splits, so their figures are not comparable to each other.
Comparison details and limitations

Every method PerturBench reports on covariate transfer on Srivatsan20, RMSE mean rank, scored with RMSE mean rank on Srivatsan20.

  • Author-reported numbers, source checked but not independently reproduced.

Automated source review: 2026-09-18. Numerical source review does not establish independent reproduction.

Dots show point estimates. Whiskers show only explicitly defined uncertainty (standard deviation, standard error or a labelled interval); their definitions remain in Table. Unresolved uncertainty is not plotted. Differences do not establish statistical significance.

Showing 10 of 10 matching rows.

Tested configuration
00.250.50.751
Reported score
  1. Decoder (Cov)0.50 ± 4 × 10 − 2
  2. SAMS-VAE*0.45 ± 2 × 10 − 2
  3. Biolord*0.35 ± 1 × 10 − 1
  4. CPA*0.32 ± 7 × 10 − 3
  5. CPA* (scGPT)0.32 ± 1 × 10 − 2
  6. CPA* (noAdv)0.29 ± 7 × 10 − 3
  7. Linear0.27 ± 2 × 10 − 3
  8. LA0.15 ± 3 × 10 − 3
  9. LA (scGPT)0.14 ± 5 × 10 − 3
  10. Decoder0.14 ± 7 × 10 − 3

Methods and evaluation design

Procedure, tasks and evaluated configurations

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Benchmarks

These source-backed links do not make different protocols or scores interchangeable.

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Run instructions

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

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

Strengths, limitations and unresolved questions

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statementOriginal source and locationReview and provenance
Relationship: part of
discovery-benchmark-perturbench
Individual claims		PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis

Original source ↗

Table 2, column(RMSE, mean rank)

Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Retrieved: 2026-09-17T08:06:28.400469+00:00

source checked

automated source review · 2026-09-18

Audit details

Primary-source transcription with no human sign-off and no independent reproduction.

Field: links:part_of:discovery-benchmark-perturbench

Claim: perturbench-association-ct-rmse-rank

Source artifact SHA-256: 5c4804565dd9faa17a11853a79e9847dcb6da73715b4c91f62e5b274cc79f186

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: source checked

1 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: perturbench-task-ct-rmse-rank

areas
cells-tissues
tasks
covariate transfer on Srivatsan20, RMSE mean rank
metric
RMSE mean rank
metric direction
lower
dataset
Srivatsan20
protocol
Train on some cell types and predict drug effects in a held-out cell type, reported as the mean and one standard deviation over seeds.
source locator
Table 2, column(RMSE, mean rank)
comparison panels
id: perturbench-panel-ct-rmse-rank; title: PerturBench CT-RMSE-RANK: covariate transfer on Srivatsan20, RMSE mean rank; protocol id: perturbench-task-ct-rmse-rank; dataset id: perturbench-dataset-srivatsan20; metric: rmse_mean_rank; unit: fraction; direction: lower; result ids: perturbench-result-cpa-ct-rmse-rank-rmse-mean-rank; perturbench-result-cpa-noadv-ct-rmse-rank-rmse-mean-rank; perturbench-result-cpa-scgpt-ct-rmse-rank-rmse-mean-rank; perturbench-result-sams-vae-ct-rmse-rank-rmse-mean-rank; perturbench-result-biolord-ct-rmse-rank-rmse-mean-rank; perturbench-result-la-ct-rmse-rank-rmse-mean-rank; perturbench-result-la-scgpt-ct-rmse-rank-rmse-mean-rank; perturbench-result-decoder-ct-rmse-rank-rmse-mean-rank; perturbench-result-decoder-cov-ct-rmse-rank-rmse-mean-rank; perturbench-result-linear-ct-rmse-rank-rmse-mean-rank; source ids: evidence-expansion-perturbench-5c480456; source locator: Table 2, column(RMSE, mean rank); context: Every method PerturBench reports on covariate transfer on Srivatsan20, RMSE mean rank, scored with RMSE mean rank on Srivatsan20.; caveats: Author-reported numbers, source checked but not independently reproduced.; RMSE and both rank metrics are better when lower. The rank metrics measure how often another perturbation's prediction is closer than the right one's.; The two experiments use different datasets and splits, so their figures are not comparable to each other.; review: method: automated_source_review; date: 2026-09-18
Related records

Suggest a correction