Dataset subset

BMMC (Chen et al. 2026)

BMMC NeurIPS 2021 CITE-seq bone marrow (45 cell types), as preprocessed by Chen et al. 2026.

Evaluation results

14 evaluations · 57 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: CellPLM (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.86 Accuracy (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source CellPLM on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'CellPLM', dataset 'BMMC', column 'Accuracy'
Configuration: CellPLM (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.73 Macro F1 (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source CellPLM on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'CellPLM', dataset 'BMMC', column 'Macro-F1'
Configuration: CellPLM (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.8 AUPRC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source CellPLM on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'CellPLM', dataset 'BMMC', column 'PR-AUC'
Configuration: CellPLM (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.86 Precision (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source CellPLM on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'CellPLM', dataset 'BMMC', column 'Precision'
Configuration: CellPLM (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.86 Recall (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source CellPLM on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'CellPLM', dataset 'BMMC', column 'Recall'
Configuration: CellPLM (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.99 AUROC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source CellPLM on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'CellPLM', dataset 'BMMC', column 'ROC-AUC'
Configuration: GenePT-w (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.71 Accuracy (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source GenePT-w on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'GenePT-w', dataset 'BMMC', column 'Accuracy'
Configuration: GenePT-w (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.45 Macro F1 (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source GenePT-w on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'GenePT-w', dataset 'BMMC', column 'Macro-F1'
Configuration: GenePT-w (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.43 AUPRC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source GenePT-w on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'GenePT-w', dataset 'BMMC', column 'PR-AUC'
Configuration: GenePT-w (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.48 Precision (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source GenePT-w on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'GenePT-w', dataset 'BMMC', column 'Precision'
Configuration: GenePT-w (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.44 Recall (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source GenePT-w on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'GenePT-w', dataset 'BMMC', column 'Recall'
Configuration: GenePT-w (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.85 AUROC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source GenePT-w on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'GenePT-w', dataset 'BMMC', column 'ROC-AUC'
Configuration: Nicheformer (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.84 Accuracy (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source Nicheformer on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'Nicheformer', dataset 'BMMC', column 'Accuracy'
Configuration: Nicheformer (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.61 Macro F1 (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source Nicheformer on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'Nicheformer', dataset 'BMMC', column 'Macro-F1'
Configuration: Nicheformer (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.72 AUPRC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source Nicheformer on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'Nicheformer', dataset 'BMMC', column 'PR-AUC'
Configuration: Nicheformer (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.84 Precision (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source Nicheformer on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'Nicheformer', dataset 'BMMC', column 'Precision'
Configuration: Nicheformer (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.84 Recall (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source Nicheformer on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'Nicheformer', dataset 'BMMC', column 'Recall'
Configuration: Nicheformer (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.99 AUROC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source Nicheformer on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'Nicheformer', dataset 'BMMC', column 'ROC-AUC'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.8 Accuracy (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'BMMC', column 'Accuracy'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.51 Macro F1 (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'BMMC', column 'Macro-F1'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.61 AUPRC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'BMMC', column 'PR-AUC'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.58 Precision (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'BMMC', column 'Precision'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.51 Recall (held-out test set; described as global in the Methods, averaging not further defined) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'BMMC', column 'Recall'
Configuration: scELMo (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.86 AUROC (held-out test set; macro-averaged over classes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scELMo on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scELMo', dataset 'BMMC', column 'ROC-AUC'
Configuration: scGPT-spatial (fine-tuned, Chen et al. 2026)	Protocol: Chen et al. 2026 supervised cell type annotation, BMMC Dataset subset: BMMC (Chen et al. 2026)	0.84 Accuracy (held-out test set) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 4 precision and recall equal accuracy in all eight Nicheformer and CellPLM rows, as micro (global) averaging would give, but recall differs from accuracy in every scGPT-spatial, GenePT-w, scELMo and Novae row. The Methods call precision and recall 'global' without defining the averaging, so they may be averaged differently between models and should not be compared across models.Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, columns 'Accuracy', 'Precision' and 'Recall'; Methods 'Cell type annotation' (page 25) Methods, coverage and source scGPT-spatial on Chen et al. 2026 supervised cell type annotation, BMMC lit-cells-networks-20261011-chen2026-protocol-annotation-bmmc Aggregation: Not reported Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Table 4, model 'scGPT-spatial', dataset 'BMMC', column 'Accuracy'

Source checking is not independent reproduction. Release 2026-10-23-5347695500ed.

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-10-23-5347695500ed · 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.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Metrics are recomputed from the saved predictions: not yet verified

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.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Metrics are recomputed from the saved predictions: not yet verified
Sample annotations are recorded: not yet verified
Dependence between samples is assessed: not yet verified

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.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
A pinned run recipe exists: not yet verified
Compute requirements are estimated: not yet verified

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.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Independent validation data exist: not yet verified
Overlap with training data is checked: not yet verified

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.

Subset and evaluation context

This record describes a particular subset or cohort used in an evaluation. Its results do not describe the full dataset.

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.

4 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-23-5347695500ed
Property and statement	Original source and location	Review and provenance
Source dataset label BMMC Context-only references	Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation Original source ↗ Methods 'Datasets' Version: arXiv 2607.17227v2, updated 2026-09-17 (v1 posted 2026-07-19) Retrieved: 2026-10-11T21:29:34Z	not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.source_dataset_label` Source artifact SHA-256: `8137338c6146f570a6546f30707d4244baca9dab848b32c51539665a5ba539da` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Source location Methods 'Datasets' Context-only references	Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation Original source ↗ Methods 'Datasets' Version: arXiv 2607.17227v2, updated 2026-09-17 (v1 posted 2026-07-19) Retrieved: 2026-10-11T21:29:34Z	not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.source_locator` Source artifact SHA-256: `8137338c6146f570a6546f30707d4244baca9dab848b32c51539665a5ba539da` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Description BMMC NeurIPS 2021 CITE-seq bone marrow (45 cell types), as preprocessed by Chen et al. 2026. Context-only references	Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation Original source ↗ Methods 'Datasets' Version: arXiv 2607.17227v2, updated 2026-09-17 (v1 posted 2026-07-19) Retrieved: 2026-10-11T21:29:34Z	not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `description` Source artifact SHA-256: `8137338c6146f570a6546f30707d4244baca9dab848b32c51539665a5ba539da` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Name BMMC (Chen et al. 2026) Context-only references	Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation Original source ↗ Methods 'Datasets' Version: arXiv 2607.17227v2, updated 2026-09-17 (v1 posted 2026-07-19) Retrieved: 2026-10-11T21:29:34Z	not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `name` Source artifact SHA-256: `8137338c6146f570a6546f30707d4244baca9dab848b32c51539665a5ba539da` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

How to read the evidence

Sources and history

Release 2026-10-23-5347695500ed · Record review: source checked

1 source record and release history

Harmonised benchmarking of foundation models for single-cell and spatial transcriptomics reveals context-dependent generalisation · Original source · arXiv 2607.17227v2, updated 2026-09-17 (v1 posted 2026-07-19)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-cells-networks-20261011-chen2026-data-bmmc

areas: single-cell; spatial-omics
contexts: research
source dataset label: BMMC
source locator: Methods 'Datasets'
missing metadata: version: reason: unreported

Related records

Suggest a correction