Configuration

Gene-expression PCA

The gene-expression PCA baseline predicts donor age from 50 principal components.

Sources

Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 2); Discussion/Robustness and control analyses (paragraph 7)

1 evaluation · 1 metric row

How it worksEvaluated procedure (conceptual)

Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings.

Sources

Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods/Models, baselines, and null calibrations (paragraph 2); Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 1)

At a glance

Model type

Linear predictive procedure; this record is the paper-specific evaluated configuration.

Sources

Biological inputs

Single-cell gene expression aggregated/handled under the study’s donor-aware protocol

Sources

Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Discussion/Robustness and control analyses (paragraph 7); Methods/Statistical safeguards (paragraph 1)

Outputs

Age predictions

Sources

Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Conclusion (paragraph 1); Discussion/Limitations (paragraph 7)

limited source coverage · Automated source review, 2026-09-16. All specifications and missing details

Evaluations and results

Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
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.

How it works

How the evaluated method works

PCA fits a linear low-dimensional representation of gene expression; a regression probe uses the same donor-aware partitions as the foundation-model comparisons.

Sources

What was evaluated

The linked evaluation record identifies Gene-expression PCA: Donor-aware age-class prediction. Its dataset, split, adaptation and evidence origin remain attached to the reported results.

Sources

Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-b3-014

Strengths and limitations

Strengths and considerations

Matches or exceeds the best frozen foundation-model probe across the five reported PBMC cohorts.
Sources
Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 2); Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 1)

Limitations and conditions

The baseline’s performance is a comparator under this experiment, not a biological ceiling on age prediction.
Sources
Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Results/The strongest aging signal: how it changes with sample size and under composition matching (paragraph 1); Discussion/Robustness and control analyses (paragraph 7)

Profile review details

Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction.

Stable record: reported-model-177f32ce8189a0

Specifications

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.

Inputs, outputs and configuration
Property	Description and evidence
Model type	Linear predictive procedure; this record is the paper-specific evaluated configuration. Sources Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods/Models, baselines, and null calibrations (paragraph 2); Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 1)
Architecture / procedure	PCA fits a linear low-dimensional representation of gene expression; a regression probe uses the same donor-aware partitions as the foundation-model comparisons. Sources Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods/Models, baselines, and null calibrations (paragraph 2); Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 1)
Biological inputs	Single-cell gene expression aggregated/handled under the study’s donor-aware protocol Sources Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Discussion/Robustness and control analyses (paragraph 7); Methods/Statistical safeguards (paragraph 1)
Outputs	Age predictions Sources Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Conclusion (paragraph 1); Discussion/Limitations (paragraph 7)
Parameters	50 principal components; this is not a pretrained neural parameter count. Sources Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Results/Randomized-weights ablations isolate the contribution of pretraining (asymmetric across models) (paragraph 2); Discussion/Robustness and control analyses (paragraph 7)
Known versions / configuration	Gene-expression PCA is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sources Sources Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label.
Training data / fitting	Fit within the same donor-aware training splits used for the competing probes. Sources Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Methods/Datasets (paragraph 1); Methods/Models, baselines, and null calibrations (paragraph 2)
Context limits	The baseline uses 50 gene-expression principal components; a sequence-token context is inapplicable. Sources Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 2); Table Tab2 (paragraph 1)
Access	Official study implementation and usage documentation: https://github.com/Biodyn-AI/longevity-mechinterp/blob/5a61464632a3c3e8bebd396eb1ab17bce1dc2493/README.md. This pinned documentation revision is not automatically the evaluated weight revision. Sources Biodyn-AI/longevity-mechinterp README.md · README.md; installation, model download and usage instructions
Code licence	No explicit code licence was established from the paper’s availability statement and inspected repository-root documentation. · Not reported in inspected sources Sources Biodyn-AI/longevity-mechinterp README.md · README.md and repository-root licence-file search
Weights licence	Not applicable to pretrained model weights; PCA and the regression probe are fitted experiment artifacts. · Not applicable Sources Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing · Results/Randomized-weights ablations isolate the contribution of pretraining (asymmetric across models) (paragraph 2); Results/Randomized-weights ablations isolate the contribution of pretraining (asymmetric across models) (paragraph 3)

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.

19 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings. Individual claims	Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Original source ↗ Methods/Models, baselines, and null calibrations (paragraph 2); Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 1) Version: PMC archival version PMC13407579.1 Retrieved: 2026-09-16T10:33:44.421Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `d6cfb13933ceefed630954f804e7dc979b747bc4aec4c8c5518232f25772736a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps ["Single-cell gene expression aggregated/handled under the study’s donor-aware protocol","Gene-expression PCA","Age predictions"] Individual claims	Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Original source ↗ Methods/Models, baselines, and null calibrations (paragraph 2); Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 1) Version: PMC archival version PMC13407579.1 Retrieved: 2026-09-16T10:33:44.421Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `d6cfb13933ceefed630954f804e7dc979b747bc4aec4c8c5518232f25772736a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Evaluated procedure (conceptual) Individual claims	Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Original source ↗ Methods/Models, baselines, and null calibrations (paragraph 2); Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 1) Version: PMC archival version PMC13407579.1 Retrieved: 2026-09-16T10:33:44.421Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `d6cfb13933ceefed630954f804e7dc979b747bc4aec4c8c5518232f25772736a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Model type Linear predictive procedure; this record is the paper-specific evaluated configuration. Individual claims	Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Original source ↗ Methods/Models, baselines, and null calibrations (paragraph 2); Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 1) Version: PMC archival version PMC13407579.1 Retrieved: 2026-09-16T10:33:44.421Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `d6cfb13933ceefed630954f804e7dc979b747bc4aec4c8c5518232f25772736a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Architecture / procedure PCA fits a linear low-dimensional representation of gene expression; a regression probe uses the same donor-aware partitions as the foundation-model comparisons. Individual claims	Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Original source ↗ Methods/Models, baselines, and null calibrations (paragraph 2); Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 1) Version: PMC archival version PMC13407579.1 Retrieved: 2026-09-16T10:33:44.421Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `d6cfb13933ceefed630954f804e7dc979b747bc4aec4c8c5518232f25772736a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Weights licence Not applicable to pretrained model weights; PCA and the regression probe are fitted experiment artifacts. Individual claims	Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Original source ↗ Results/Randomized-weights ablations isolate the contribution of pretraining (asymmetric across models) (paragraph 2); Results/Randomized-weights ablations isolate the contribution of pretraining (asymmetric across models) (paragraph 3) Version: PMC archival version PMC13407579.1 Retrieved: 2026-09-16T10:33:44.421Z	inapplicable automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `d6cfb13933ceefed630954f804e7dc979b747bc4aec4c8c5518232f25772736a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Biological inputs Single-cell gene expression aggregated/handled under the study’s donor-aware protocol Individual claims	Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Original source ↗ Discussion/Robustness and control analyses (paragraph 7); Methods/Statistical safeguards (paragraph 1) Version: PMC archival version PMC13407579.1 Retrieved: 2026-09-16T10:33:44.421Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `d6cfb13933ceefed630954f804e7dc979b747bc4aec4c8c5518232f25772736a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Outputs Age predictions Individual claims	Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Original source ↗ Conclusion (paragraph 1); Discussion/Limitations (paragraph 7) Version: PMC archival version PMC13407579.1 Retrieved: 2026-09-16T10:33:44.421Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `d6cfb13933ceefed630954f804e7dc979b747bc4aec4c8c5518232f25772736a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Parameters 50 principal components; this is not a pretrained neural parameter count. Individual claims	Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Original source ↗ Results/Randomized-weights ablations isolate the contribution of pretraining (asymmetric across models) (paragraph 2); Discussion/Robustness and control analyses (paragraph 7) Version: PMC archival version PMC13407579.1 Retrieved: 2026-09-16T10:33:44.421Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `d6cfb13933ceefed630954f804e7dc979b747bc4aec4c8c5518232f25772736a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Known versions / configuration Gene-expression PCA is the comparison-table label; that label does not specify an immutable weight revision. Individual claims	Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing Original source ↗ Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. Version: PMC archival version PMC13407579.1 Retrieved: 2026-09-16T10:33:44.421Z	unreported automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.5.value` Source artifact SHA-256: `d6cfb13933ceefed630954f804e7dc979b747bc4aec4c8c5518232f25772736a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

Release 2026-09-17-d277315f7d76 · 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
Biodyn-AI/longevity-mechinterp README.md · Original source · 5a61464632a3c3e8bebd396eb1ab17bce1dc2493

Download this release

Technical metadata and extraction receipts

Stable ID: reported-model-177f32ce8189a0

areas: cells-tissues
entity level: method
version: Not reported
reported name: Gene-expression PCA
historical missing metadata: version: not_reported_in_legacy_extract; checkpoint revision: not_reported_in_legacy_extract; training data: not_reported_in_legacy_extract; licence: 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: model
entity classification: review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: single-cell-aging-probes-2026; source locator: Methods/Models, baselines, and null calibrations (paragraph 2); Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 1) | Results/Foundation models detect age, but not better than a gene-expression PCA baseline (paragraph 2); Discussion/Robustness and control analyses (paragraph 7); ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.

Related records

model: Gene-expression PCA: Donor-aware age-class prediction

Suggest a correction