# Cross-modal prediction on PerturbSeq Single Cell Image Data In Distribution (test)

Source: [Cross-modal prediction on PerturbSeq Single Cell Image Data In Distribution (test)](<https://www.sota2.com/research/sota/cross-modal-prediction-on-perturbseq-single-cell-image-data-in-distribution-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:52:31.929Z

Evaluation of Cross-modal prediction performance on the test split of the PerturbSeq Single Cell Image Data (In Distribution) dataset, measured using KL Divergence statistics (Median, Q1, Q3).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Cross-modal prediction |
| Dataset (including any stated split) | PerturbSeq Single Cell Image Data In Distribution (test) |
| Metric | Median KL Divergence |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Median KL Divergence](<https://www.sota2.com/research/sota/cross-modal-prediction-on-perturbseq-single-cell-image-data-in-distribution-test.md?metric=Median%20KL%20Divergence>): Lower is better; unit: SCALAR.

- [Q1 KL Divergence](<https://www.sota2.com/research/sota/cross-modal-prediction-on-perturbseq-single-cell-image-data-in-distribution-test.md?metric=Q1%20KL%20Divergence>): Lower is better; unit: SCALAR.

- [Q3 KL Divergence](<https://www.sota2.com/research/sota/cross-modal-prediction-on-perturbseq-single-cell-image-data-in-distribution-test.md?metric=Q3%20KL%20Divergence>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Median KL Divergence | Result date | Report paper |
| --- | --- | --- | --- |
| PS+OT | 50.967 | Not recorded | 68fa756a1e209131cea67b8d |
| VAE+OT | 55.483 | Not recorded | 68fa756a1e209131cea67b8d |
| Random | 58.806 | Not recorded | 68fa756a1e209131cea67b8d |

### PS+OT

Median KL Divergence: 50.967. Result ID: 6993a01d3a6c314849175b33.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756a1e209131cea67b8d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756a1e209131cea67b8d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### VAE+OT

Median KL Divergence: 55.483. Result ID: 6993a01d3a6c314849175b32.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756a1e209131cea67b8d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Random

Median KL Divergence: 58.806. Result ID: 6993a01d3a6c314849175b31.

[Reporting paper](<https://www.sota2.com/research/paper/68fa756a1e209131cea67b8d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
