Method

Random Labels

Control run included by Open Problems to bound the scale: perfect labels or random labels, not a competing method.

Overview

Control run included by Open Problems to bound the scale: perfect labels or random labels, not a competing method.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

24 evaluations · 24 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
Method: Random Labels	Task: Open Problems label projection CENGEN-BATCH-ACCURACY: Label projection on CeNGEN (split by batch), Accuracy Dataset subset: CeNGEN (split by batch) (Open Problems label projection split)	0.0144 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection CENGEN-BATCH-ACCURACY: Label projection on CeNGEN (split by batch), Accuracy 100k FACS-isolated C. elegans neurons from 17 experiments sequenced on 10x Genomics. Split into train/test by experimental batch. Dimensions: 100955 cells, 22469 genes. 169 cell types (avg. 597±800 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(cengen_batch), method(random_labels), paramset(none), metric(accuracy)
Method: Random Labels	Task: Open Problems label projection CENGEN-BATCH-F1: Label projection on CeNGEN (split by batch), F1 score Dataset subset: CeNGEN (split by batch) (Open Problems label projection split)	0.0236 f1 fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection CENGEN-BATCH-F1: Label projection on CeNGEN (split by batch), F1 score 100k FACS-isolated C. elegans neurons from 17 experiments sequenced on 10x Genomics. Split into train/test by experimental batch. Dimensions: 100955 cells, 22469 genes. 169 cell types (avg. 597±800 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(cengen_batch), method(random_labels), paramset(none), metric(f1)
Method: Random Labels	Task: Open Problems label projection CENGEN-BATCH-F1-MACRO: Label projection on CeNGEN (split by batch), Macro F1 score Dataset subset: CeNGEN (split by batch) (Open Problems label projection split)	0.00218 f1-macro fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection CENGEN-BATCH-F1-MACRO: Label projection on CeNGEN (split by batch), Macro F1 score 100k FACS-isolated C. elegans neurons from 17 experiments sequenced on 10x Genomics. Split into train/test by experimental batch. Dimensions: 100955 cells, 22469 genes. 169 cell types (avg. 597±800 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(cengen_batch), method(random_labels), paramset(none), metric(f1_macro)
Method: Random Labels	Task: Open Problems label projection CENGEN-RANDOM-ACCURACY: Label projection on CeNGEN (random split), Accuracy Dataset subset: CeNGEN (random split) (Open Problems label projection split)	0.0166 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection CENGEN-RANDOM-ACCURACY: Label projection on CeNGEN (random split), Accuracy 100k FACS-isolated C. elegans neurons from 17 experiments sequenced on 10x Genomics. Split into train/test randomly. Dimensions: 100955 cells, 22469 genes. 169 cell types avg. 597±800 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(cengen_random), method(random_labels), paramset(none), metric(accuracy)
Method: Random Labels	Task: Open Problems label projection CENGEN-RANDOM-F1: Label projection on CeNGEN (random split), F1 score Dataset subset: CeNGEN (random split) (Open Problems label projection split)	0.0166 f1 fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection CENGEN-RANDOM-F1: Label projection on CeNGEN (random split), F1 score 100k FACS-isolated C. elegans neurons from 17 experiments sequenced on 10x Genomics. Split into train/test randomly. Dimensions: 100955 cells, 22469 genes. 169 cell types avg. 597±800 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(cengen_random), method(random_labels), paramset(none), metric(f1)
Method: Random Labels	Task: Open Problems label projection CENGEN-RANDOM-F1-MACRO: Label projection on CeNGEN (random split), Macro F1 score Dataset subset: CeNGEN (random split) (Open Problems label projection split)	0.00526 f1-macro fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection CENGEN-RANDOM-F1-MACRO: Label projection on CeNGEN (random split), Macro F1 score 100k FACS-isolated C. elegans neurons from 17 experiments sequenced on 10x Genomics. Split into train/test randomly. Dimensions: 100955 cells, 22469 genes. 169 cell types avg. 597±800 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(cengen_random), method(random_labels), paramset(none), metric(f1_macro)
Method: Random Labels	Task: Open Problems label projection PANCREAS-BATCH-ACCURACY: Label projection on Pancreas (by batch), Accuracy Dataset subset: Pancreas (by batch) (Open Problems label projection split)	0.213 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection PANCREAS-BATCH-ACCURACY: Label projection on Pancreas (by batch), Accuracy Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq). Split into train/test by experimental batch. Dimensions: 16382 cells, 18771 genes. 14 cell types (avg. 1170±1703 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(pancreas_batch), method(random_labels), paramset(none), metric(accuracy)
Method: Random Labels	Task: Open Problems label projection PANCREAS-BATCH-F1: Label projection on Pancreas (by batch), F1 score Dataset subset: Pancreas (by batch) (Open Problems label projection split)	0.214 f1 fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection PANCREAS-BATCH-F1: Label projection on Pancreas (by batch), F1 score Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq). Split into train/test by experimental batch. Dimensions: 16382 cells, 18771 genes. 14 cell types (avg. 1170±1703 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(pancreas_batch), method(random_labels), paramset(none), metric(f1)
Method: Random Labels	Task: Open Problems label projection PANCREAS-BATCH-F1-MACRO: Label projection on Pancreas (by batch), Macro F1 score Dataset subset: Pancreas (by batch) (Open Problems label projection split)	0.0707 f1-macro fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection PANCREAS-BATCH-F1-MACRO: Label projection on Pancreas (by batch), Macro F1 score Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq). Split into train/test by experimental batch. Dimensions: 16382 cells, 18771 genes. 14 cell types (avg. 1170±1703 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(pancreas_batch), method(random_labels), paramset(none), metric(f1_macro)
Method: Random Labels	Task: Open Problems label projection PANCREAS-RANDOM-ACCURACY: Label projection on Pancreas (random split), Accuracy Dataset subset: Pancreas (random split) (Open Problems label projection split)	0.221 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection PANCREAS-RANDOM-ACCURACY: Label projection on Pancreas (random split), Accuracy Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq). Split into train/test randomly. Dimensions: 16382 cells, 18771 genes. 14 cell types (avg. 1170±1703 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(pancreas_random), method(random_labels), paramset(none), metric(accuracy)
Method: Random Labels	Task: Open Problems label projection PANCREAS-RANDOM-F1: Label projection on Pancreas (random split), F1 score Dataset subset: Pancreas (random split) (Open Problems label projection split)	0.221 f1 fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection PANCREAS-RANDOM-F1: Label projection on Pancreas (random split), F1 score Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq). Split into train/test randomly. Dimensions: 16382 cells, 18771 genes. 14 cell types (avg. 1170±1703 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(pancreas_random), method(random_labels), paramset(none), metric(f1)
Method: Random Labels	Task: Open Problems label projection PANCREAS-RANDOM-F1-MACRO: Label projection on Pancreas (random split), Macro F1 score Dataset subset: Pancreas (random split) (Open Problems label projection split)	0.0762 f1-macro fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection PANCREAS-RANDOM-F1-MACRO: Label projection on Pancreas (random split), Macro F1 score Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq). Split into train/test randomly. Dimensions: 16382 cells, 18771 genes. 14 cell types (avg. 1170±1703 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(pancreas_random), method(random_labels), paramset(none), metric(f1_macro)
Method: Random Labels	Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-ACCURACY: Label projection on Pancreas (random split with label noise), Accuracy Dataset subset: Pancreas (random split with label noise) (Open Problems label projection split)	0.173 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-ACCURACY: Label projection on Pancreas (random split with label noise), Accuracy Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq). Split into train/test randomly with 20% label noise. Dimensions: 16382 cells, 18771 genes. 14 cell types (avg. 1170±1703 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(random_labels), paramset(none), metric(accuracy)
Method: Random Labels	Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Dataset subset: Pancreas (random split with label noise) (Open Problems label projection split)	0.188 f1 fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq). Split into train/test randomly with 20% label noise. Dimensions: 16382 cells, 18771 genes. 14 cell types (avg. 1170±1703 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(random_labels), paramset(none), metric(f1)
Method: Random Labels	Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1-MACRO: Label projection on Pancreas (random split with label noise), Macro F1 score Dataset subset: Pancreas (random split with label noise) (Open Problems label projection split)	0.0626 f1-macro fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1-MACRO: Label projection on Pancreas (random split with label noise), Macro F1 score Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq). Split into train/test randomly with 20% label noise. Dimensions: 16382 cells, 18771 genes. 14 cell types (avg. 1170±1703 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(random_labels), paramset(none), metric(f1_macro)
Method: Random Labels	Task: Open Problems label projection TABULA-MURIS-SENIS-LUNG-RANDOM-ACCURACY: Label projection on Tabula Muris Senis Lung (random split), Accuracy Dataset subset: Tabula Muris Senis Lung (random split) (Open Problems label projection split)	0.0893 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection TABULA-MURIS-SENIS-LUNG-RANDOM-ACCURACY: Label projection on Tabula Muris Senis Lung (random split), Accuracy All lung cells from Tabula Muris Senis, a 500k cell-atlas from 18 organs and tissues across the mouse lifespan. Split into train/test randomly. Dimensions: 24540 cells, 17985 genes. 39 cell types (avg. 629±999 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(tabula_muris_senis_lung_random), method(random_labels), paramset(none), metric(accuracy)
Method: Random Labels	Task: Open Problems label projection TABULA-MURIS-SENIS-LUNG-RANDOM-F1: Label projection on Tabula Muris Senis Lung (random split), F1 score Dataset subset: Tabula Muris Senis Lung (random split) (Open Problems label projection split)	0.0892 f1 fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection TABULA-MURIS-SENIS-LUNG-RANDOM-F1: Label projection on Tabula Muris Senis Lung (random split), F1 score All lung cells from Tabula Muris Senis, a 500k cell-atlas from 18 organs and tissues across the mouse lifespan. Split into train/test randomly. Dimensions: 24540 cells, 17985 genes. 39 cell types (avg. 629±999 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(tabula_muris_senis_lung_random), method(random_labels), paramset(none), metric(f1)
Method: Random Labels	Task: Open Problems label projection TABULA-MURIS-SENIS-LUNG-RANDOM-F1-MACRO: Label projection on Tabula Muris Senis Lung (random split), Macro F1 score Dataset subset: Tabula Muris Senis Lung (random split) (Open Problems label projection split)	0.0253 f1-macro fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection TABULA-MURIS-SENIS-LUNG-RANDOM-F1-MACRO: Label projection on Tabula Muris Senis Lung (random split), Macro F1 score All lung cells from Tabula Muris Senis, a 500k cell-atlas from 18 organs and tissues across the mouse lifespan. Split into train/test randomly. Dimensions: 24540 cells, 17985 genes. 39 cell types (avg. 629±999 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(tabula_muris_senis_lung_random), method(random_labels), paramset(none), metric(f1_macro)
Method: Random Labels	Task: Open Problems label projection ZEBRAFISH-LABS-ACCURACY: Label projection on Zebrafish (by laboratory), Accuracy Dataset subset: Zebrafish (by laboratory) (Open Problems label projection split)	0.0278 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection ZEBRAFISH-LABS-ACCURACY: Label projection on Zebrafish (by laboratory), Accuracy 90k cells from zebrafish embryos throughout the first day of development, with and without a knockout of chordin, an important developmental gene. Split into train/test by laboratory. Dimensions: 26022 cells, 25258 genes. 24 cell types (avg. 1084±1156 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(zebrafish_labs), method(random_labels), paramset(none), metric(accuracy)
Method: Random Labels	Task: Open Problems label projection ZEBRAFISH-LABS-F1: Label projection on Zebrafish (by laboratory), F1 score Dataset subset: Zebrafish (by laboratory) (Open Problems label projection split)	0.0387 f1 fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection ZEBRAFISH-LABS-F1: Label projection on Zebrafish (by laboratory), F1 score 90k cells from zebrafish embryos throughout the first day of development, with and without a knockout of chordin, an important developmental gene. Split into train/test by laboratory. Dimensions: 26022 cells, 25258 genes. 24 cell types (avg. 1084±1156 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(zebrafish_labs), method(random_labels), paramset(none), metric(f1)
Method: Random Labels	Task: Open Problems label projection ZEBRAFISH-LABS-F1-MACRO: Label projection on Zebrafish (by laboratory), Macro F1 score Dataset subset: Zebrafish (by laboratory) (Open Problems label projection split)	0.0151 f1-macro fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection ZEBRAFISH-LABS-F1-MACRO: Label projection on Zebrafish (by laboratory), Macro F1 score 90k cells from zebrafish embryos throughout the first day of development, with and without a knockout of chordin, an important developmental gene. Split into train/test by laboratory. Dimensions: 26022 cells, 25258 genes. 24 cell types (avg. 1084±1156 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(zebrafish_labs), method(random_labels), paramset(none), metric(f1_macro)
Method: Random Labels	Task: Open Problems label projection ZEBRAFISH-RANDOM-ACCURACY: Label projection on Zebrafish (random split), Accuracy Dataset subset: Zebrafish (random split) (Open Problems label projection split)	0.0874 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection ZEBRAFISH-RANDOM-ACCURACY: Label projection on Zebrafish (random split), Accuracy 90k cells from zebrafish embryos throughout the first day of development, with and without a knockout of chordin, an important developmental gene. Split into train/test randomly. Dimensions: 26022 cells, 25258 genes. 24 cell types (avg. 1084±1156 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(zebrafish_random), method(random_labels), paramset(none), metric(accuracy)
Method: Random Labels	Task: Open Problems label projection ZEBRAFISH-RANDOM-F1: Label projection on Zebrafish (random split), F1 score Dataset subset: Zebrafish (random split) (Open Problems label projection split)	0.0877 f1 fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection ZEBRAFISH-RANDOM-F1: Label projection on Zebrafish (random split), F1 score 90k cells from zebrafish embryos throughout the first day of development, with and without a knockout of chordin, an important developmental gene. Split into train/test randomly. Dimensions: 26022 cells, 25258 genes. 24 cell types (avg. 1084±1156 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(zebrafish_random), method(random_labels), paramset(none), metric(f1)
Method: Random Labels	Task: Open Problems label projection ZEBRAFISH-RANDOM-F1-MACRO: Label projection on Zebrafish (random split), Macro F1 score Dataset subset: Zebrafish (random split) (Open Problems label projection split)	0.0412 f1-macro fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Random Labels on Open Problems label projection ZEBRAFISH-RANDOM-F1-MACRO: Label projection on Zebrafish (random split), Macro F1 score 90k cells from zebrafish embryos throughout the first day of development, with and without a knockout of chordin, an important developmental gene. Split into train/test randomly. Dimensions: 26022 cells, 25258 genes. 24 cell types (avg. 1084±1156 cells per cell type). Aggregation: Not reported openproblems-label primary benchmark evidence · results, dataset(zebrafish_random), method(random_labels), paramset(none), metric(f1_macro)

Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.

Use this model

How it works, versions and access

Strengths, limitations and unresolved questions

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.

0 evidence rows matching the loaded filters