rewirebio.iobenchmarks
Dataset

HLCA core (CELLxGENE), 37 leaf cell types after processing

Public atlas used as reference or query for annotation transfer; labels are the atlas annotations.

Research readiness

These checks assess whether the evidence supports a reproducible investigation. A source-checked score alone does not meet these requirements.

Release 2026-10-10-6e93f504adfc · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • artifact hashes: verification is missing
  • join integrity: verification is missing
  • score semantics: verification is missing
  • metric replay: verification is missing

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • artifact hashes: verification is missing
  • join integrity: verification is missing
  • score semantics: verification is missing
  • metric replay: verification is missing
  • annotations: verification is missing
  • dependence: verification is missing

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • artifact hashes: verification is missing
  • join integrity: verification is missing
  • score semantics: verification is missing
  • recipe pinned: verification is missing
  • resource estimate: verification is missing

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • artifact hashes: verification is missing
  • join integrity: verification is missing
  • score semantics: verification is missing
  • independent validation: verification is missing
  • overlap checked: verification is missing

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Read reviewed discrepancy investigations

Evaluation results

23 evaluations · 46 results. Different protocols are not a single leaderboard.

Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: Ensemble Geneformer + LangCell (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.75 top-1-accuracy
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Geneformer + LangCell: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell B22, row 'Geneformer + LangCell', column 'Accuracy@1'
Configuration: Ensemble Geneformer + LangCell (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.162 macro-f1
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Geneformer + LangCell: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell C22, row 'Geneformer + LangCell', column 'Macro-F1'
Configuration: Ensemble Geneformer + scCello (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.76 top-1-accuracy
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Geneformer + scCello: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell B24, row 'Geneformer + scCello', column 'Accuracy@1'
Configuration: Ensemble Geneformer + scCello (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.164 macro-f1
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Geneformer + scCello: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell C24, row 'Geneformer + scCello', column 'Macro-F1'
Configuration: Ensemble Geneformer + scFoundation (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.744 top-1-accuracy
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Geneformer + scFoundation: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell B19, row 'Geneformer + scFoundation', column 'Accuracy@1'
Configuration: Ensemble Geneformer + scFoundation (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.156 macro-f1
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Geneformer + scFoundation: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell C19, row 'Geneformer + scFoundation', column 'Macro-F1'
Configuration: Ensemble Geneformer + scGPT (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.756 top-1-accuracy
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Geneformer + scGPT: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell B23, row 'Geneformer + scGPT', column 'Accuracy@1'
Configuration: Ensemble Geneformer + scGPT (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.161 macro-f1
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Geneformer + scGPT: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell C23, row 'Geneformer + scGPT', column 'Macro-F1'
Configuration: Ensemble Geneformer + UCE (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.747 top-1-accuracy
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Geneformer + UCE: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell B21, row 'Geneformer + UCE', column 'Accuracy@1'
Configuration: Ensemble Geneformer + UCE (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.161 macro-f1
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Geneformer + UCE: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell C21, row 'Geneformer + UCE', column 'Macro-F1'
Configuration: Ensemble LangCell + scCello (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.747 top-1-accuracy
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

LangCell + scCello: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell B20, row 'LangCell + scCello', column 'Accuracy@1'
Configuration: Ensemble LangCell + scCello (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.125 macro-f1
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

LangCell + scCello: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell C20, row 'LangCell + scCello', column 'Macro-F1'
Configuration: Ensemble LangCell + scFoundation (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.708 top-1-accuracy
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

LangCell + scFoundation: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell B12, row 'LangCell + scFoundation', column 'Accuracy@1'
Configuration: Ensemble LangCell + scFoundation (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.111 macro-f1
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

LangCell + scFoundation: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell C12, row 'LangCell + scFoundation', column 'Macro-F1'
Configuration: Ensemble LangCell + scGPT (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.719 top-1-accuracy
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

scGPT + LangCell: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell B15, row 'scGPT + LangCell', column 'Accuracy@1'
Configuration: Ensemble LangCell + scGPT (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.112 macro-f1
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

scGPT + LangCell: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell C15, row 'scGPT + LangCell', column 'Macro-F1'
Configuration: Ensemble LangCell + UCE (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.713 top-1-accuracy
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

UCE + LangCell: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell B13, row 'UCE + LangCell', column 'Accuracy@1'
Configuration: Ensemble LangCell + UCE (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.111 macro-f1
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

UCE + LangCell: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell C13, row 'UCE + LangCell', column 'Macro-F1'
Configuration: Ensemble Logit aggregation (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.753 top-1-accuracy
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Logit aggregation: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell B27, row 'Logit aggregation', column 'Accuracy@1'
Configuration: Ensemble Logit aggregation (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.163 macro-f1
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Logit aggregation: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell C27, row 'Logit aggregation', column 'Macro-F1'
Configuration: Ensemble Majority voting (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.758 top-1-accuracy
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Majority voting: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell B28, row 'Majority voting', column 'Accuracy@1'
Configuration: Ensemble Majority voting (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.119 macro-f1
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Majority voting: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell C28, row 'Majority voting', column 'Macro-F1'
Configuration: Ensemble scCello + scFoundation (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.731 top-1-accuracy
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

scFoundation + scCello: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell B17, row 'scFoundation + scCello', column 'Accuracy@1'
Configuration: Ensemble scCello + scFoundation (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.128 macro-f1
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

scFoundation + scCello: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell C17, row 'scFoundation + scCello', column 'Macro-F1'
Configuration: Ensemble scCello + scGPT (Wu et al. 2025)Protocol: Cross-atlas annotation transfer, Tabula Sapiens to HLCA, 14 shared cell types (Wu et al. 2025 Table S2)
Dataset: HLCA core (CELLxGENE), 37 leaf cell types after processing
0.775 top-1-accuracy
fraction · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

scGPT + scCello: Tabula Sapiens to HLCA transfer (Wu et al. 2025)

cell-type-20261009-protocol-wu2025-ts-to-hlca

Aggregation: Not reported

Wu et al. 2025, Additional file 3 (Supplementary Tables S1-S13) · Table S2, cell B25, row 'scGPT + scCello', column 'Accuracy@1'

Source checking is not independent reproduction. Release 2026-10-10-6e93f504adfc.

Dataset and evaluation context

A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

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.

6 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-10-6e93f504adfc
Property and statementOriginal source and locationReview and provenance
attributes.population
585 K cells from healthy lung across 107 individuals; label column 'cell_type'; 37 leaf cell types kept after removing non-leaf terms and types with fewer than 10 cells
Context-only references
Biology-driven insights into the power of single-cell foundation models

Original source ↗

Table 2; Methods 'Batch integration and cell type annotation' paragraphs 1-3

Version: Genome Biology 26:334, published 2025-10-03; PMC12492631 full-text XML
Retrieved: 2026-10-09T21:22:13Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.population

Source artifact SHA-256: 368051b7cda5acd4864331875a1faac6f1d68e0a209ed999e4c2ee3b25b57c2c

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

attributes.source_locator
Table 2; Methods 'Batch integration and cell type annotation' paragraphs 1-3
Context-only references
Biology-driven insights into the power of single-cell foundation models

Original source ↗

Table 2; Methods 'Batch integration and cell type annotation' paragraphs 1-3

Version: Genome Biology 26:334, published 2025-10-03; PMC12492631 full-text XML
Retrieved: 2026-10-09T21:22:13Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.source_locator

Source artifact SHA-256: 368051b7cda5acd4864331875a1faac6f1d68e0a209ed999e4c2ee3b25b57c2c

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

attributes.split
Reference model trained on a 20% stratified split; query test set is every cell of the 14 cell types shared by the two atlases
Context-only references
Biology-driven insights into the power of single-cell foundation models

Original source ↗

Table 2; Methods 'Batch integration and cell type annotation' paragraphs 1-3

Version: Genome Biology 26:334, published 2025-10-03; PMC12492631 full-text XML
Retrieved: 2026-10-09T21:22:13Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.split

Source artifact SHA-256: 368051b7cda5acd4864331875a1faac6f1d68e0a209ed999e4c2ee3b25b57c2c

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

attributes.version
CELLxGENE collection as downloaded by the authors (Table 2)
Context-only references
Biology-driven insights into the power of single-cell foundation models

Original source ↗

Table 2; Methods 'Batch integration and cell type annotation' paragraphs 1-3

Version: Genome Biology 26:334, published 2025-10-03; PMC12492631 full-text XML
Retrieved: 2026-10-09T21:22:13Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.version

Source artifact SHA-256: 368051b7cda5acd4864331875a1faac6f1d68e0a209ed999e4c2ee3b25b57c2c

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

description
Public atlas used as reference or query for annotation transfer; labels are the atlas annotations.
Context-only references
Biology-driven insights into the power of single-cell foundation models

Original source ↗

Table 2; Methods 'Batch integration and cell type annotation' paragraphs 1-3

Version: Genome Biology 26:334, published 2025-10-03; PMC12492631 full-text XML
Retrieved: 2026-10-09T21:22:13Z

not individually reviewed

No individual claim review recorded

Audit details

Field: description

Source artifact SHA-256: 368051b7cda5acd4864331875a1faac6f1d68e0a209ed999e4c2ee3b25b57c2c

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

name
HLCA core (CELLxGENE), 37 leaf cell types after processing
Context-only references
Biology-driven insights into the power of single-cell foundation models

Original source ↗

Table 2; Methods 'Batch integration and cell type annotation' paragraphs 1-3

Version: Genome Biology 26:334, published 2025-10-03; PMC12492631 full-text XML
Retrieved: 2026-10-09T21:22:13Z

not individually reviewed

No individual claim review recorded

Audit details

Field: name

Source artifact SHA-256: 368051b7cda5acd4864331875a1faac6f1d68e0a209ed999e4c2ee3b25b57c2c

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Sources and history

Release 2026-10-10-6e93f504adfc · Record review: source checked

1 source records and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: cell-type-20261009-data-wu2025-hlca-core

areas
cells-tissues
contexts
research
version
CELLxGENE collection as downloaded by the authors (Table 2)
population
585 K cells from healthy lung across 107 individuals; label column 'cell_type'; 37 leaf cell types kept after removing non-leaf terms and types with fewer than 10 cells
split
Reference model trained on a 20% stratified split; query test set is every cell of the 14 cell types shared by the two atlases
source locator
Table 2; Methods 'Batch integration and cell type annotation' paragraphs 1-3
Related records

Suggest a correction