scTab Table 2 hardware-specific resources
Training hours and inference throughput on explicitly different hardware. Not normalized model speed.
Overview
Training hours and inference throughput on explicitly different hardware. Not normalized model speed.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
5 recorded evaluations, 10 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
5 evaluations · 10 results. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: CellTypist — scTab Table 1 | Protocol: scTab Table 2 hardware-specific resources Dataset: scTab processed CELLxGENE 2023-05-15 donor holdouts | ~2000 inference-throughput samples/second · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNot reported Aggregation: Not reported scTab supplementary comparison tables · Supplementary Table 2, celltypist, inference time |
| Configuration: CellTypist — scTab Table 1 | Protocol: scTab Table 2 hardware-specific resources Dataset: scTab processed CELLxGENE 2023-05-15 donor holdouts | ~16h training-hours hours · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNot reported Aggregation: Not reported scTab supplementary comparison tables · Supplementary Table 2, celltypist, training time |
| Configuration: Optimized linear logistic regression — scTab Table 1 | Protocol: scTab Table 2 hardware-specific resources Dataset: scTab processed CELLxGENE 2023-05-15 donor holdouts | ~29500 inference-throughput samples/second · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNot reported Aggregation: Not reported scTab supplementary comparison tables · Supplementary Table 2, linear, inference time |
| Configuration: Optimized linear logistic regression — scTab Table 1 | Protocol: scTab Table 2 hardware-specific resources Dataset: scTab processed CELLxGENE 2023-05-15 donor holdouts | ~20h training-hours hours · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNot reported Aggregation: Not reported scTab supplementary comparison tables · Supplementary Table 2, linear, training time |
| Configuration: MLP — scTab Table 1 | Protocol: scTab Table 2 hardware-specific resources Dataset: scTab processed CELLxGENE 2023-05-15 donor holdouts | ~21400 inference-throughput samples/second · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNot reported Aggregation: Not reported scTab supplementary comparison tables · Supplementary Table 2, mlp, inference time |
| Configuration: MLP — scTab Table 1 | Protocol: scTab Table 2 hardware-specific resources Dataset: scTab processed CELLxGENE 2023-05-15 donor holdouts | ~29h training-hours hours · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNot reported Aggregation: Not reported scTab supplementary comparison tables · Supplementary Table 2, mlp, training time |
| Configuration: scTab — scTab Table 1 | Protocol: scTab Table 2 hardware-specific resources Dataset: scTab processed CELLxGENE 2023-05-15 donor holdouts | ~10800 inference-throughput samples/second · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNot reported Aggregation: Not reported scTab supplementary comparison tables · Supplementary Table 2, sctab, inference time |
| Configuration: scTab — scTab Table 1 | Protocol: scTab Table 2 hardware-specific resources Dataset: scTab processed CELLxGENE 2023-05-15 donor holdouts | ~33h training-hours hours · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNot reported Aggregation: Not reported scTab supplementary comparison tables · Supplementary Table 2, sctab, training time |
| Configuration: XGBoost — scTab Table 1 | Protocol: scTab Table 2 hardware-specific resources Dataset: scTab processed CELLxGENE 2023-05-15 donor holdouts | ~4200 inference-throughput samples/second · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNot reported Aggregation: Not reported scTab supplementary comparison tables · Supplementary Table 2, xgboost, inference time |
| Configuration: XGBoost — scTab Table 1 | Protocol: scTab Table 2 hardware-specific resources Dataset: scTab processed CELLxGENE 2023-05-15 donor holdouts | ~10h training-hours hours · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNot reported Aggregation: Not reported scTab supplementary comparison tables · Supplementary Table 2, xgboost, training time |
Source checking is not independent reproduction. Release 2026-09-30-e37e3ab1284d.
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.
Baseline coverage
Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.
0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.
No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.
- Author-reported evaluations
- 5
Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.
Null control
Proposed control: requires review
Select a task-valid null control after reviewing inputs and metric
Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.
This is a suggested selection rule, not a validated method or a measured score.
Conventional reference
Proposed control: requires review
Select an upstream conventional reference after reviewing the full protocol
Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.
This is a suggested selection rule, not a validated method or a measured score.
Protocol coverage CSV · Model evaluation matrix · Source table · Release and checksums
Coverage is derived from release 2026-09-30-e37e3ab1284d. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.
Run instructions
No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
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.
3 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: part of ucc-research-benchmark-sctab Individual claims | scTab official reproducibility repository Supplementary Tables 1,2,6 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 5ede7f2ba1f9618b86924f2ff587931de18f4ada | source checked automated source review · 2026-09-30T21:43:56Z Audit detailsPrimary-source table transcription and scope review; no independent reproduction or human scientific review. Field: Claim: ucc-research-membership-sctab-resources Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Relationship: part of ucc-research-benchmark-sctab Individual claims | scTab: Scaling cross-tissue single-cell annotation models Supplementary Tables 1,2,6 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 10.1038/s41467-024-51059-5; published article XML retrieved 2026-09-30 | source checked automated source review · 2026-09-30T21:43:56Z Audit detailsPrimary-source table transcription and scope review; no independent reproduction or human scientific review. Field: Claim: ucc-research-membership-sctab-resources Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Relationship: part of ucc-research-benchmark-sctab Individual claims | scTab supplementary comparison tables Supplementary Tables 1,2,6 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Supplementary Information to 10.1038/s41467-024-51059-5 | source checked automated source review · 2026-09-30T21:43:56Z Audit detailsPrimary-source table transcription and scope review; no independent reproduction or human scientific review. Field: Claim: ucc-research-membership-sctab-resources Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
View linked audit checks and correction history
Release 2026-09-30-e37e3ab1284d · Record review: source checked
1 source records and release history
- scTab supplementary comparison tables · Original source · Supplementary Information to 10.1038/s41467-024-51059-5
Technical metadata and extraction receipts
Stable ID: ucc-research-protocol-sctab-resources
- review
- method: automated_source_review; actor: Codex research coverage worker; reviewed at: 2026-09-30T21:43:56Z; note: Primary-source table transcription and scope review; no independent reproduction or human scientific review.
Related records
- dataset: scTab processed CELLxGENE 2023-05-15 donor holdouts
- part of: scTab published annotation evaluation
- protocol: sctab resources celltypist
- protocol: sctab resources linear
- protocol: sctab resources mlp
- protocol: sctab resources sctab
- protocol: sctab resources xgboost
- subject: Source membership: ucc-research-protocol-sctab-resources