0.322 Balanced accuracy
Best frozen single-cell foundation model · Balanced accuracy · AIDA v2 PBMC cohort
- Tested model
- Best frozen single-cell foundation model
- Task or benchmark
- Donor-aware age-class prediction
- Dataset
- AIDA v2 PBMC cohort
- Procedure
- Same donor-aware splits and logistic-regression probe as expression PCA; text names Geneformer as best model on AIDA v2.
- Evaluation
- Best frozen single-cell foundation model: Donor-aware age-class prediction
- Evidence
- Independent external evaluation · source checkedInflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Table 2, AIDA v2 row, scFM BA ± SD column
A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: needs review. Source checked does not mean independently reproduced.
Evaluation results
Release 2026-09-16-d74d282221a9 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Best frozen single-cell foundation model: Donor-aware age-class prediction Model: Best frozen single-cell foundation model · Benchmark: Donor-aware age-class prediction · Dataset: AIDA v2 PBMC cohort Same donor-aware splits and logistic-regression probe as expression PCA; text names Geneformer as best model on AIDA v2. Independent external evaluation · Evaluation metadata: needs review | ||
| 0.322 Balanced accuracy Unit: unitless · Direction: unknown | Uncertainty: ± 0.008 standard deviation Scored: Not reported · Eligible: Not reported | source checkedInflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Table 2, AIDA v2 row, scFM BA ± SD column Source checking is not independent reproduction. |
Sources and history
Release 2026-09-16-d74d282221a9 · Record review: source checked
- Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Original source · PMC archival version PMC13407579.1
Technical metadata and extraction receipts
Stable ID: lit-b3-013
- areas
- cells-tissues
- tasks
- Donor-aware age-class prediction
- printed value
- 0.322
- numeric value
- 0.322
- metric
- Balanced accuracy
- metric direction
- unknown
- unit
- unitless
- uncertainty
- ± 0.008 standard deviation
- source locator
- Table 2, AIDA v2 row, scFM BA ± SD column
- review
- method: primary_xml_exact_label_cell_check; reviewer: rewire deterministic table checker v1; reviewed at: 2026-09-16T10:33:44.421Z; notes: Exact row/header labels and numeric cell matched. Check verifies transcription, not experimental correctness.; evidence: Table 2, AIDA v2 row, scFM BA ± SD column; cell: 0.322 ± 0.008; artifact sha256: d6cfb13933ceefed630954f804e7dc979b747bc4aec4c8c5518232f25772736a; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13407579/fullTextXML
- legacy id
- lit-b3-013
- legacy row
- id: lit-b3-013; paper id: single-cell-aging-probes-2026; domain id: cells-tissues; task: Donor-aware age-class prediction; model: Best frozen single-cell foundation model; model version: Not reported; dataset: AIDA v2 PBMC cohort; dataset version: 622 donors; split: Not reported; metric: Balanced accuracy; value: 0.322; unit: unitless; uncertainty: ± 0.008 standard deviation; protocol: Same donor-aware splits and logistic-regression probe as expression PCA; text names Geneformer as best model on AIDA v2.; source locator: Table 2, AIDA v2 row, scFM BA ± SD column; source url: https://pmc.ncbi.nlm.nih.gov/articles/PMC13407579/; evaluation origin: independent_paper; reviewed utc: 2026-09-15T23:29:32Z
- missing metadata
- model version: not_reported_in_legacy_extract; split: not_reported_in_legacy_extract