0.164 macro-f1
Geneformer + scCello Tabula Sapiens to HLCA macro-f1
- Tested configuration
- Ensemble Geneformer + scCello (Wu et al. 2025)
- Protocol
- Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
- Dataset
- HLCA core (CELLxGENE), 37 leaf cell types after processing
- Procedure
- cell-type-20261009-protocol-wu2025-ts-to-hlca
- Evaluation
- Geneformer + scCello: Tabula Sapiens to HLCA transfer (Wu et al. 2025)
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- Not reported by the source
- Evidence
- Independent external evaluation · source checkedWu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell C24, row 'Geneformer + scCello', column 'Macro-F1'
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
- Reference 20% stratified training split; query all shared-type cells
- Adaptation
- OnClass classifier trained on the reference; scFM frozen
- Scoring implementation
- Accuracy@1 and macro-F1 over shared types
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 0.164 Individual claims | Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) Table S2, cell C24, row 'Geneformer + scCello', column 'Macro-F1' Version: 13059_2025_3781_MOESM3_ESM.xlsx (38,926 bytes), as linked from the article XML <supplementary-material id="MOESM3"> | source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-09 independent paper Audit detailsExtracted by deterministic parse of the pinned XLSX cell XML (extract/extract_cell_type.py), with row and column labels asserted. printed_value is the shortest decimal that round-trips to the stored number. Pending independent review. Independent review 2026-10-09: value and identity match the source. metric_qualifier corrected: the source does not state which classes macro-F1 averages over. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record Extraction artifact SHA-256: |
Sources and history
Release 2026-10-10-6e93f504adfc · Record review: source checked
2 source records and release history
- Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Original source · 13059_2025_3781_MOESM3_ESM.xlsx (38,926 bytes), as linked from the article XML <supplementary-material id="MOESM3">
- Biology-driven insights into the power of single-cell foundation models · Original source · Genome Biology 26:334, published 2025-10-03; PMC12492631 full-text XML
Technical metadata and extraction receipts
Stable ID: cell-type-20261009-result-wu2025-ts-to-hlca-ensemble-geneformer-sccello-macro-f1
- metric
- macro-f1
- metric direction
- higher
- unit
- fraction
- printed value
- 0.164
- numeric value
- 0.164
- metric qualifier
- test cells of the 14 shared cell types; averaged over 'all classes' (Methods 'Macro-F1'), not stated as the 14 shared types or every source-atlas type
- source locator
- Table S2, cell C24, row 'Geneformer + scCello', column 'Macro-F1'
- missing metadata
- uncertainty: reason: unreported
- review
- method: source-hash-verification; deterministic-table-parse; independent-cell-check; reviewer: claude; reviewer note: Separate Claude review agent, independent of the extractor; no human review claimed; date: 2026-10-09; artifact sha256: 51ecea4318178dfb7dc6b51eae23303d68f25e83641809c95429b082353dc99d; retrieval url: https://static-content.springer.com/esm/art%3A10.1186%2Fs13059-025-03781-6/MediaObjects/13059_2025_3781_MOESM3_ESM.xlsx; method note: Re-downloaded the workbook and matched its SHA-256. Read Supplementary Tables S2 and S3 only, with a separate OOXML reader written for this review (the extractor's script was not run). Checked value, locator, metric, unit, direction, the evaluation's protocol and dataset, and that the configuration's model links match the row.; note: Extracted by deterministic parse of the pinned XLSX cell XML (extract/extract_cell_type.py), with row and column labels asserted. printed_value is the shortest decimal that round-trips to the stored number. Pending independent review. Independent review 2026-10-09: value and identity match the source. metric_qualifier corrected: the source does not state which classes macro-F1 averages over.