Datasets
Five age-annotated human PBMC cohorts; AIDA cohorts are central and other cohorts provide stress tests.
Task
Donor-aware age-class prediction
Age-class prediction probes frozen single-cell representations using donor-separated evaluation.
Sources
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 13–22Overview
Metrics
Balanced-accuracy comparisons against null expectations are described.
Allowed inputs
Frozen scGPT/Geneformer embeddings or expression-derived PCA representations.
Sources
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 13–22Evaluation procedure diagram
How it worksComputational evaluation flow
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Sources
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 13–22limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
2 evaluations · 2 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: Best frozen single-cell foundation model | Task: Donor-aware age-class prediction Dataset: AIDA v2 PBMC cohort | 0.322 Balanced accuracy unitless · unknown Uncertainty: ± 0.008 standard deviation Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceBest frozen single-cell foundation model: Donor-aware age-class prediction Same donor-aware splits and logistic-regression probe as expression PCA; text names Geneformer as best model on AIDA v2. Aggregation: Not reported Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Table 2, AIDA v2 row, scFM BA ± SD column |
| Configuration: Gene-expression PCA | Task: Donor-aware age-class prediction Dataset: AIDA v2 PBMC cohort | 0.384 Balanced accuracy unitless · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceGene-expression PCA: Donor-aware age-class prediction Fifty-component gene-expression PCA with the same donor-aware probe splits. Aggregation: Not reported Inflammation-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. Release 2026-09-29-06401fd5b220.
Methods and evaluation design
Procedure, tasks and evaluated configurations
How it works
Evaluation methodology
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.
Sources
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 13–22Recorded evaluations
Each evaluation records what was tested and under which conditions.
Run instructions
No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.
Strengths, limitations and unresolved questions
Strengths and limitations
Strengths and considerations
- Whole-donor partitioning prevents cells from one donor appearing in both fitting and testing.
Sources
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
Limitations and conditions
- A fitted probe is distinct from fine-tuning the foundation model. External cohorts are not treated as interchangeable training pools.
Sources
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
Profile review details
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-d6018ca598e525Specifications
Inputs, training, access and other details
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 |
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Papers and result coverage
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 |
Historical gaps recorded on 2026-09-17
The catalogue now holds 2 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.
- Complete raw comparison acquired. Best-scFM is a selected pipeline, not a named family by inference. PCA, permutation mean/p 95 and chance 1/K remain separate reference types. Structured extraction pending.
Search and extraction details
source found structured extraction pending
Searches
- Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing primary paper benchmark results
Evidence locations
- Table2, five donor cohorts; donor-aware split and null controls
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.
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
| 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 |
Sources and history
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: needs review
2 source records and release history
- Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Original source · PMC archival version PMC13407579.1
- 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: reported-task-d6018ca598e525
- areas
- cells-tissues
- tasks
- Donor-aware age-class prediction
- entity level
- task
- version
- Not reported
- task
- Donor-aware age-class prediction
- scope note
- Paper-specific evaluation task; protocol completeness requires further extraction.
- benchmark research
- review date: 2026-09-17; status: source_found_structured_extraction_pending; primary sources: evidence-expansion-p2-single-cell-aging-probes-2026-d6cfb13933ce; inspected locators: Table2, five donor cohorts; donor-aware split and null controls; searched queries: Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing primary paper benchmark results; gaps: Complete raw comparison acquired. Best-scFM is a selected pipeline, not a named family by inference. PCA, permutation mean/p 95 and chance 1/K remain separate reference types. Structured extraction pending.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
- historical missing metadata
- protocol version: not_reported_in_legacy_extract; split: not_reported_in_legacy_extract
- metadata review scope
- historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
- legacy kinds
- benchmark
- entity classification
- review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: single-cell-aging-probes-2026; source locator: Methods: Datasets; Models, baselines and null calibrations; Age probe; cached text lines 13–22; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.