Age-class prediction probes frozen single-cell representations using donor-separated evaluation.
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Datasets | Five age-annotated human PBMC cohorts; AIDA cohorts are central and other cohorts provide stress tests.SourcesInflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 |
| Splits | All cells from a donor belong wholly to training or testing; targets are age-quartile classes.SourcesInflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 |
| Metrics | Balanced-accuracy comparisons against null expectations are described.SourcesInflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 |
| Baselines | Frozen scGPT and Geneformer probes, PCA-on-expression, within-stratum permutations and chance baselines.SourcesInflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 |
| Leakage controls | Donor grouping prevents direct memorization of donor identities across partitions.SourcesInflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 |
| Uncertainty | Permutation nulls calibrate the probe; exact test confidence intervals remain unextracted.SourcesInflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 |
| Entity type | Paper-specific computational evaluation protocol.SourcesInflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 |
| Organisms | Human PBMC donors.SourcesInflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 |
| Assays | Single-cell expression with donor age and cell-type metadata.SourcesInflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 |
| Allowed inputs | Frozen scGPT/Geneformer embeddings or expression-derived PCA representations.SourcesInflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 |
| Adaptation | Supervised probes; all cells of a donor stay within one arm.SourcesInflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 |
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Five age-annotated human PBMC cohorts; AIDA cohorts are central and other cohorts provide stress tests. All cells from a donor belong wholly to training or testing; targets are age-quartile classes. Balanced-accuracy comparisons against null expectations are described. Frozen scGPT and Geneformer probes, PCA-on-expression, within-stratum permutations and chance baselines. Donor grouping prevents direct memorization of donor identities across partitions. Permutation nulls calibrate the probe; exact test confidence intervals remain unextracted.
Each evaluation records what was tested and under which conditions.
Release 2026-09-17-d277315f7d76 · 2 evaluations · 2 metric rows. 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 Configuration: Best frozen single-cell foundation modelTask: Donor-aware age-class predictionDataset: 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. |
| Gene-expression PCA: Donor-aware age-class prediction Configuration: Gene-expression PCATask: Donor-aware age-class predictionDataset: AIDA v2 PBMC cohort Fifty-component gene-expression PCA with the same donor-aware probe splits. Independent external evaluation · Evaluation metadata: needs review | ||
| 0.384 Balanced accuracy Unit: unitless · Direction: unknown | Uncertainty: not reported in legacy extract 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, Gene-expr BA column Source checking is not independent reproduction. |
Last literature check: 2026-09-17. Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
| Paper or primary resource | Version | Reference |
|---|---|---|
| Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing | PMC archival version PMC13407579.1 | Read source DOI: 10.1007/s10522-026-10471-8 |
source found structured extraction pending
Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.
Stable record: reported-task-d6018ca598e525Trace 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.
18 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims | Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 Version: PMC archival version PMC13407579.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["Input: Frozen scGPT/Geneformer embeddings or expression-derived PCA representations.","Evaluation: Supervised probes; all cells of a donor stay within one arm.","Readout: Balanced-accuracy comparisons against null expectations are described."] Individual claims | Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 Version: PMC archival version PMC13407579.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Computational evaluation flow Individual claims | Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 Version: PMC archival version PMC13407579.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets Five age-annotated human PBMC cohorts; AIDA cohorts are central and other cohorts provide stress tests. Individual claims | Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 Version: PMC archival version PMC13407579.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits All cells from a donor belong wholly to training or testing; targets are age-quartile classes. Individual claims | Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 Version: PMC archival version PMC13407579.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation Supervised probes; all cells of a donor stay within one arm. Individual claims | Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 Version: PMC archival version PMC13407579.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Metrics Balanced-accuracy comparisons against null expectations are described. Individual claims | Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 Version: PMC archival version PMC13407579.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Baselines Frozen scGPT and Geneformer probes, PCA-on-expression, within-stratum permutations and chance baselines. Individual claims | Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 Version: PMC archival version PMC13407579.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Leakage controls Donor grouping prevents direct memorization of donor identities across partitions. Individual claims | Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 Version: PMC archival version PMC13407579.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Uncertainty Permutation nulls calibrate the probe; exact test confidence intervals remain unextracted. Individual claims | Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22 Version: PMC archival version PMC13407579.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Release 2026-09-17-d277315f7d76 · Record review: needs review
Stable ID: reported-task-d6018ca598e525