GEARS (trained from scratch, no pretrained weights)
GEARS trained from scratch without pretrained weights, on train-test splits aligned with SPECTRA and with other parameters at their default values.
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.
Model Capabilities & Hardware Requirements
Deployment facts recorded for GEARS (trained from scratch, no pretrained weights). Fields the record does not carry are marked not recorded.
Evaluations and results
1 evaluation · 1 result. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: GEARS (trained from scratch, no pretrained weights) | Protocol: PertEval-scFM Norman single-gene (2,000 HVGs) AUSPC across SPECTRA sparsification splits Dataset subset: Norman et al. 2019 single-gene perturbations, K562, top 2,000 HVGs (PertEval-scFM Table 1) | 0.815 ± 0.039 AUSPC unitless · lower Uncertainty: SE 0.039. The source describes this quantity as a standard error (main-text Figure 2 caption: 'Average AUSPC (down-arrow) across sparsification probabilities for each model with standard error bars') and separately gives its own propagation formula (Appendix F.2, Eqs. F3-F5): AUSPC's uncertainty is derived from each split's own MSE uncertainty via the trapezoidal integral's partial derivatives (sigma^2 = sum_i (d/2)^2 * sigma_phi_i^2, where d=0.1 is the fixed sparsification step size). These two author statements describe the same quantity and are not in conflict: a propagated quantity can correctly be reported as a standard error. This is recorded as the author's own reported, propagated uncertainty; the F3-F5 derivation is the authors' own formula and its mathematical correctness has not been independently validated here. It must not be read as an independently resampled model-seed standard deviation or a confidence interval. The underlying per-split uncertainty is attributed by the source to triplicate experiments per model (Appendix I, Figure I1 caption: 'Experiments were carried out in triplicate for each model'), not to the main-text Figure 2 region. Figure I1's own caption separately states '8 train-test splits of increasing difficulty' for this same Norman single-gene evaluation, while Table 1 prints seven S-columns (S0.1-S0.7) and Appendix F.2 describes the sparsification probabilities as spanning 0.1 to 0.7. This 7-vs-8 discrepancy between the Figure I1 caption and the Table 1 / F.2 grid is preserved exactly as printed, not resolved; it must not be read as establishing an eighth Table 1 column or a confirmed n_runs=7, and no significance claim is made from any overlapping error bars. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGEARS on PertEval-scFM Norman single-gene (2,000 HVGs) AUSPC Trapezoidal-rule AUSPC of MSE, scored on the perturbation-effect delta=P-Xc (Eq. 5), across seven SPECTRA sparsification splits (s=0.1..0.7), Norman single-gene, 2,000 HVGs. Aggregation: Not reported PertEval-scFM (Wenteler et al., ICML 2025), full text · Table 1, Norman single-gene section, row GEARS, column AUSPC (10^-2). |
Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.
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
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
1 source record and release history
- PertEval-scFM (Wenteler et al., ICML 2025), full text · Original source · PMLR v267 wenteler25a (as served by the PMLR-affiliated mlresearch/v267 GitHub mirror; ETag "ed9f0fe44cf6edc939ee6950d024f65dcd8dd6f16414bd9f5297cda9395d6e58" at retrieval)
Technical metadata and record identifiers
Technical metadata for this record is tracked under stable ID perteval-scfm-2025-method-gears.
Source locator: Table 1, row GEARS, Norman single-gene section; Section 2.2 ('GEARS baseline', and the sentence 'we train GEARS from scratch without using pretrained weights').
Related records
How to cite
GEARS (trained from scratch, no pretrained weights). Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/perteval-scfm-2025-method-gears/
Release 2026-11-21-c8bea25e5abb. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.
The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence