Norman19 K562 CRISPRa single and dual gene perturbations, split by PerturBench v4 to predict held-out dual perturbations.
11 evaluations · 67 results. Different protocols are not a single leaderboard.
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: Biolord* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.027 ± 1 × 10 − 3 Perturbench cosine logfc rank fraction · lower Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceBiolord ∗ 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 'Biolord ∗', column 'Cosine LogFC rank' |
| Configuration: Biolord* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.41 ± 2 × 10 − 2 Perturbench cosine logfc fraction · higher Uncertainty: SD 0.02 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceBiolord ∗ 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 'Biolord ∗', column 'Cosine logFC' |
| Configuration: Biolord* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination 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 | Independent external evaluation · Source checkedMethods, coverage and sourceBiolord ∗ 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 'Biolord ∗', column 'DEG recall' |
| Configuration: Biolord* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 1.6 ± 5 × 10 − 3 Perturbench energy mmd (PCA space: top 256 principal components fitted on the ground-truth test split) unit-unreported · lower Uncertainty: SD 0.005 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceBiolord ∗ 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 'Biolord ∗', column 'MMD PCA' |
| Configuration: Biolord* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 2.8 ± 5 × 10 − 3 Perturbench energy mmd (gene expression space) unit-unreported · lower Uncertainty: SD 0.005 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceBiolord ∗ 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 'Biolord ∗', column 'MMD' |
| Configuration: Biolord* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.028 ± 1 × 10 − 3 Perturbench RMSE rank fraction · lower Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceBiolord ∗ 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 'Biolord ∗', column 'RMSE mean rank' |
| Configuration: Biolord* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.086 ± 6 × 10 − 4 Perturbench RMSE of mean unit-unreported · lower Uncertainty: SD 0.0006 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceBiolord ∗ 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 'Biolord ∗', column 'RMSE mean' |
| Configuration: CPA* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.0072 ± 2 × 10 − 3 Perturbench cosine logfc rank fraction · lower Uncertainty: SD 0.002 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCPA ∗ 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 'CPA ∗', column 'Cosine LogFC rank' |
| Configuration: CPA* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.76 ± 4 × 10 − 3 Perturbench cosine logfc fraction · higher Uncertainty: SD 0.004 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCPA ∗ 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 'CPA ∗', column 'Cosine logFC' |
| Configuration: CPA* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.032 ± 4 × 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 0.004 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCPA ∗ 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 'CPA ∗', column 'DEG recall' |
| Configuration: CPA* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 2.2 ± 2 × 10 − 2 Perturbench energy mmd (PCA space: top 256 principal components fitted on the ground-truth test split) unit-unreported · lower Uncertainty: SD 0.02 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCPA ∗ 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 'CPA ∗', column 'MMD PCA' |
| Configuration: CPA* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 5.6 ± 3 × 10 − 2 Perturbench energy mmd (gene expression space) unit-unreported · lower Uncertainty: SD 0.03 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCPA ∗ 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 'CPA ∗', column 'MMD' |
| Configuration: CPA* (noAdv) | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.0057 ± 3 × 10 − 3 Perturbench cosine logfc rank fraction · lower Uncertainty: SD 0.003 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCPA ∗ (noAdv) 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 'CPA ∗ (noAdv)', column 'Cosine LogFC rank' |
| Configuration: CPA* (noAdv) | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.77 ± 1 × 10 − 2 Perturbench cosine logfc fraction · higher Uncertainty: SD 0.01 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCPA ∗ (noAdv) 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 'CPA ∗ (noAdv)', column 'Cosine logFC' |
| Configuration: CPA* (noAdv) | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.016 ± 9 × 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 0.009 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCPA ∗ (noAdv) 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 'CPA ∗ (noAdv)', column 'DEG recall' |
| Configuration: CPA* (noAdv) | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 2.2 ± 1 × 10 − 1 Perturbench energy mmd (PCA space: top 256 principal components fitted on the ground-truth test split) unit-unreported · lower Uncertainty: SD 0.1 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCPA ∗ (noAdv) 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 'CPA ∗ (noAdv)', column 'MMD PCA' |
| Configuration: CPA* (noAdv) | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 5.5 ± 1 × 10 − 1 Perturbench energy mmd (gene expression space) unit-unreported · lower Uncertainty: SD 0.1 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCPA ∗ (noAdv) 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 'CPA ∗ (noAdv)', column 'MMD' |
| Configuration: CPA* (noAdv) | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.017 ± 3 × 10 − 3 Perturbench RMSE rank fraction · lower Uncertainty: SD 0.003 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCPA ∗ (noAdv) 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 'CPA ∗ (noAdv)', column 'RMSE mean rank' |
| Configuration: CPA* (noAdv) | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.046 ± 1 × 10 − 3 Perturbench RMSE of mean unit-unreported · lower Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCPA ∗ (noAdv) 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 'CPA ∗ (noAdv)', column 'RMSE mean' |
| Configuration: CPA* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.019 ± 3 × 10 − 3 Perturbench RMSE rank fraction · lower Uncertainty: SD 0.003 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCPA ∗ 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 'CPA ∗', column 'RMSE mean rank' |
| Configuration: CPA* | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.046 ± 5 × 10 − 4 Perturbench RMSE of mean unit-unreported · lower Uncertainty: SD 0.0005 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCPA ∗ 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 'CPA ∗', column 'RMSE mean' |
| Configuration: CPA* (scGPT) | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.025 ± 6 × 10 − 3 Perturbench cosine logfc rank fraction · lower Uncertainty: SD 0.006 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCPA ∗ (scGPT) 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 'CPA ∗ (scGPT)', column 'Cosine LogFC rank' |
| Configuration: CPA* (scGPT) | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.70 ± 2 × 10 − 2 Perturbench cosine logfc fraction · higher Uncertainty: SD 0.02 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCPA ∗ (scGPT) 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 'CPA ∗ (scGPT)', column 'Cosine logFC' |
| Configuration: CPA* (scGPT) | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.036 ± 3 × 10 − 3 Perturbench RMSE rank fraction · lower Uncertainty: SD 0.003 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCPA ∗ (scGPT) 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 'CPA ∗ (scGPT)', column 'RMSE mean rank' |
| Configuration: CPA* (scGPT) | Protocol: PerturBench v4 combination prediction of held-out dual perturbations on Norman19 Dataset subset: Norman19 (PerturBench v4 combination split) | 0.053 ± 1 × 10 − 3 Perturbench RMSE of mean unit-unreported · lower Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCPA ∗ (scGPT) 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 'CPA ∗ (scGPT)', column 'RMSE mean' |
Source checking is not independent reproduction. Release 2026-10-23-5347695500ed.
0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.
Release 2026-10-23-5347695500ed · Evidence verified: Not verified
Exact outcomes, predictions, identifiers and evaluator are connected.
Missing or unresolved evidence
Verified: Not verified
Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.
Missing or unresolved evidence
Verified: Not verified
A pinned recipe describes the inputs, environment and resource requirements.
Missing or unresolved evidence
Verified: Not verified
Separate data and exposure records support an independent test.
Missing or unresolved evidence
Verified: Not verified
Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.
No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.
This record describes a particular subset or cohort used in an evaluation. Its results do not describe the full dataset.
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
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.
4 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Source location Table 1; Appendix D.4 Context-only references | PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) Table 1; Appendix D.4 Version: arXiv 2408.10609v4, posted 2025-10-24 (NeurIPS 2025 Datasets and Benchmarks Track version) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact bytes of the arXiv HTML rendering of v4 as retrieved; arXiv may regenerate HTML, so the hash describes this retrieval. |
| Split Norman19 K562 CRISPRa single and dual gene perturbations, split by PerturBench v4 to predict held-out dual perturbations. Context-only references | PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) Table 1; Appendix D.4 Version: arXiv 2408.10609v4, posted 2025-10-24 (NeurIPS 2025 Datasets and Benchmarks Track version) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact bytes of the arXiv HTML rendering of v4 as retrieved; arXiv may regenerate HTML, so the hash describes this retrieval. |
| Description Norman19 K562 CRISPRa single and dual gene perturbations, split by PerturBench v4 to predict held-out dual perturbations. Context-only references | PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) Table 1; Appendix D.4 Version: arXiv 2408.10609v4, posted 2025-10-24 (NeurIPS 2025 Datasets and Benchmarks Track version) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact bytes of the arXiv HTML rendering of v4 as retrieved; arXiv may regenerate HTML, so the hash describes this retrieval. |
| Name Norman19 (PerturBench v4 combination split) Context-only references | PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (arXiv v4) Table 1; Appendix D.4 Version: arXiv 2408.10609v4, posted 2025-10-24 (NeurIPS 2025 Datasets and Benchmarks Track version) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact bytes of the arXiv HTML rendering of v4 as retrieved; arXiv may regenerate HTML, so the hash describes this retrieval. |
Release 2026-10-23-5347695500ed · Record review: source checked
Stable ID: lit-cells-networks-20261011-perturbench-v4-data-norman19