result · source checked
0.677 AUROC
scGPT + residual geometry · AUROC · immune tissue
- Tested model
- scGPT + residual geometry
- Task or benchmark
- gene-regulatory signal prediction
- Dataset
- immune tissue
- Procedure
- Asymmetric extraction, PCA-64 centered cosine geometry added to scGPT baseline
- Evaluation
- scGPT + residual geometry: gene-regulatory signal prediction
- Evidence
- Author-reported evaluation · source checkedResidual-stream geometry of single-cell foundation models carries incremental gene-regulatory signal across tissues · Table 4, Immune row, scGPT > +geom AUROC 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 |
|---|---|---|
| scGPT + residual geometry: gene-regulatory signal prediction Model: scGPT + residual geometry · Benchmark: gene-regulatory signal prediction · Dataset: immune tissue Asymmetric extraction, PCA-64 centered cosine geometry added to scGPT baseline Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.677 AUROC Unit: fraction · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedResidual-stream geometry of single-cell foundation models carries incremental gene-regulatory signal across tissues · Table 4, Immune row, scGPT > +geom AUROC column Source checking is not independent reproduction. |
Sources and history
Release 2026-09-16-d74d282221a9 · Record review: source checked
- Residual-stream geometry of single-cell foundation models carries incremental gene-regulatory signal across tissues · Original source · version of record
Technical metadata and extraction receipts
Stable ID: lit-b4-013
- areas
- cells-tissues
- tasks
- gene-regulatory signal prediction
- printed value
- 0.677
- numeric value
- 0.677
- metric
- AUROC
- metric direction
- unknown
- unit
- fraction
- uncertainty
- Not reported
- source locator
- Table 4, Immune row, scGPT > +geom AUROC column
- review
- method: independent_ai_table_review; reviewer: Codex primary curator table review; reviewed at: 2026-09-16T10:41:06Z; notes: Immune row, scGPT +geom (second numeric column), not Geneformer or delta. Transcription verified; experimental claims not independently reproduced.; evidence: 0.677; artifact sha256: 77546faec51cfb5c78b73c5943f940c4e0097d130b1ddde4ab8287b507b36df6; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13418759/fullTextXML
- legacy id
- lit-b4-013
- legacy row
- id: lit-b4-013; paper id: single-cell-residual-geometry-2026; domain id: cells-tissues; task: gene-regulatory signal prediction; model: scGPT + residual geometry; model version: Not reported; dataset: immune tissue; dataset version: Not reported; split: Not reported; metric: AUROC; value: 0.677; unit: fraction; uncertainty: Not reported; protocol: Asymmetric extraction, PCA-64 centered cosine geometry added to scGPT baseline; source locator: Table 4, Immune row, scGPT > +geom AUROC column; source url: https://pmc.ncbi.nlm.nih.gov/articles/PMC13418759/; evaluation origin: author_reported; reviewed utc: 2026-09-15T23:37:05Z
- missing metadata
- model version: not_reported_in_legacy_extract; dataset version: not_reported_in_legacy_extract; split: not_reported_in_legacy_extract; uncertainty: not_reported_in_legacy_extract