RMSE (test RMSE of pair viability, training set with each gene seen about 4 times on average) of GEARS, trained once on a downsampled set on Norman et al. 2019 combinatorial CRISPRa in K562, gene-level viability (as processed by Qin et al. 2025)
16.6 (19.8) RMSE (test RMSE of pair viability, training set with each gene seen about 4 times on average)
Methods
- Tested configuration
- GEARS, trained once on a downsampled set
- Protocol
- Combination phenotype prediction from small training sets: test RMSE at fixed average gene frequency
- Dataset
- Norman et al. 2019 combinatorial CRISPRa in K562, gene-level viability (as processed by Qin et al. 2025)
- Procedure
- Combination phenotype prediction from small training sets: test RMSE at fixed average gene frequency
- Evaluation
- GEARS, trained once on a downsampled set on Norman (Tables 1 and 6, RMSE at fixed gene frequency)
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- SE 19.8. Caption: error is SE across three cross-fold replicates
- Evidence
- Independent external evaluation · source checkedQin et al. 2025, Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations (ICML 2025, PMLR 267) · Table 1, Gene Frequency 4 block, row "GEARS", column "Norman"
A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.
Reproduction
- Split
- Downsampled training set; 10% validation and 30% test
- Adaptation
- GEARS trained once on the downsampled set
- Scoring implementation
- RMSE of predicted pair viability on the test set
No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.
Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.
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
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Reported result 16.6 (19.8) Individual claims | Qin et al. 2025, Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations (ICML 2025, PMLR 267) Table 1, Gene Frequency 4 block, row "GEARS", column "Norman" Version: Proceedings of the 42nd ICML, PMLR 267:50363-50383, 2025; proceedings PDF qin25g.pdf. The arXiv preprint 2411.12010 was not read. | source checked ["source-hash-verification","pdf-text-parse","independent-cell-check","rendered-source-visual-check","scope-review"] · 2026-10-22 independent paper Audit detailsValue, standard error, metric, qualifier, unit, direction and the linked configuration, dataset and protocol checked. numeric_value stays at the printed x 10^-2 scale, as unit_detail says. Field: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/qin2025naiad.py Extraction artifact SHA-256: |
Sources and history
Release 2026-10-23-5347695500ed · Record review: source checked
1 source record and release history
- Qin et al. 2025, Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations (ICML 2025, PMLR 267) · Original source · Proceedings of the 42nd ICML, PMLR 267:50363-50383, 2025; proceedings PDF qin25g.pdf. The arXiv preprint 2411.12010 was not read.
Technical metadata and extraction receipts
Stable ID: pheno-20261022-qin2025-result-table1-6-gears-prediction-norman2019-rmse-gene-frequency-4
- metric
- root-mean-squared-error
- metric qualifier
- test RMSE of pair viability, training set with each gene seen about 4 times on average
- metric direction
- lower
- unit
- unitless
- unit detail
- printed x 10^-2
- printed value
- 16.6 (19.8)
- numeric value
- 16.6
- source locator
- Table 1, Gene Frequency 4 block, row "GEARS", column "Norman"
- review
- method: source-hash-verification; pdf-text-parse; independent-cell-check; rendered-source-visual-check; scope-review; reviewer: claude; reviewer note: Claude (Opus 5.5) review agent, independent of the extraction agent; no human review claimed; date: 2026-10-22; artifact sha256: 983b2da8aed78f0aced27053301c15f0f67ebd0fac706435bb6800e309dd64eb; retrieval url: https://raw.githubusercontent.com/mlresearch/v267/main/assets/qin25g/qin25g.pdf; method note: Re-hashed the PDF in the scratchpad (SHA-256 matches the source record). Ran scripts/omics/batch.py check-values on the pdftotext -layout layer (200 in_row, 12 row_not_found). Then parsed Tables 1 to 8 with a separate reviewer script (review/qin2025naiad-check.py) that asserts row labels and cells per row, and matched each result to its cell through the evaluation's system and data links and the metric qualifier, not through its locator: 212 of 212 printed values, numeric values and standard errors match, and every locator names the same cell. Tables 1 to 8 were also compared by eye with the rendered PDF pages 6 to 8, 18 and 20, including column order.; note: Value, standard error, metric, qualifier, unit, direction and the linked configuration, dataset and protocol checked. numeric_value stays at the printed x 10^-2 scale, as unit_detail says.
- uncertainty
- type: standard_error; value: 19.8; printed: (19.8); n: 3; scope: three cross-fold replicates; note: Caption: error is SE across three cross-fold replicates