Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
Label projection on Pancreas (random split with label noise), F1 score. Scored with F1 score on Pancreas (random split with label noise). 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).
Overview
Label projection on Pancreas (random split with label noise), F1 score. Scored with F1 score on Pancreas (random split with label noise). 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).
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Evaluation design
Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.
Benchmarks
These source-backed links do not make different protocols or scores interchangeable.
Recorded evaluations
Each evaluation records what was tested and under which conditions.
- K-neighbors classifier (log CP10k) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- K-neighbors classifier (log scran) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- Logistic regression (log CP10k) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- Logistic regression (log scran) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- Majority Vote on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- Multilayer perceptron (log CP10k) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- Multilayer perceptron (log scran) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- Random Labels on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- scANVI (All genes) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- scANVI (Seurat v3 2000 HVG) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- scArches+scANVI (All genes) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- scArches+scANVI (Seurat v3 2000 HVG) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
Run instructions
No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.
Published comparisons
Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies. The pooled view gathers every source table that reports the same metric and names what it does not hold constant.
Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
f1 (fraction) · Higher values are better for this metric.
Every method Open Problems label projection reports on Label projection on Pancreas (random split with label noise), F1 score, scored with F1 score on Pancreas (random split with label noise).
Evaluation protocol · Pancreas (random split with label noise) (Open Problems label projection split)
- Majority Vote · Configuration · Author-reported evaluation0.16837763151390925
- Random Labels · Method · Author-reported evaluation0.18787809947778522
- K-neighbors classifier (log CP10k) · Configuration · Author-reported evaluation0.9460810866713062
- True Labels · Method · Author-reported evaluation1
- Multilayer perceptron (log CP10k) · Configuration · Author-reported evaluation0.8366856872231097
- Logistic regression (log CP10k) · Configuration · Author-reported evaluation0.9791824244686764
- XGBoost (log CP10k) · Configuration · Author-reported evaluation0.9638063508972504
- K-neighbors classifier (log scran) · Configuration · Author-reported evaluation0.9404360005933883
- Multilayer perceptron (log scran) · Configuration · Author-reported evaluation0.925397640256357
- Logistic regression (log scran) · Configuration · Author-reported evaluation0.7759818120203118
- XGBoost (log scran) · Configuration · Author-reported evaluation0.9528870337485718
- Seurat reference mapping (SCTransform) · Configuration · Author-reported evaluation0.975085587274387
- scArches+scANVI (Seurat v3 2000 HVG) · Configuration · Author-reported evaluation0.9372298848234738
- scArches+scANVI (All genes) · Configuration · Author-reported evaluation0.9363141652450575
- scANVI (All genes) · Configuration · Author-reported evaluation0.9672436357663169
- scANVI (Seurat v3 2000 HVG) · Configuration · Author-reported evaluation0.963942105070359
Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.
openproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), metric(f1)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| Majority Vote · Configuration | 0.16837763151390925 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(majority_vote), paramset(none), metric(f1) |
| Random Labels · Method | 0.18787809947778522 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(random_labels), paramset(none), metric(f1) |
| K-neighbors classifier (log CP10k) · Configuration | 0.9460810866713062 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(k_neighbors_classifier), paramset(log CP10k), metric(f1) |
| True Labels · Method | 1 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(true_labels), paramset(none), metric(f1) |
| Multilayer perceptron (log CP10k) · Configuration | 0.8366856872231097 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(multilayer_perceptron), paramset(log CP10k), metric(f1) |
| Logistic regression (log CP10k) · Configuration | 0.9791824244686764 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(logistic_regression), paramset(log CP10k), metric(f1) |
| XGBoost (log CP10k) · Configuration | 0.9638063508972504 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(xgboost), paramset(log CP10k), metric(f1) |
| K-neighbors classifier (log scran) · Configuration | 0.9404360005933883 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(k_neighbors_classifier), paramset(log scran), metric(f1) |
| Multilayer perceptron (log scran) · Configuration | 0.925397640256357 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(multilayer_perceptron), paramset(log scran), metric(f1) |
| Logistic regression (log scran) · Configuration | 0.7759818120203118 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(logistic_regression), paramset(log scran), metric(f1) |
| XGBoost (log scran) · Configuration | 0.9528870337485718 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(xgboost), paramset(log scran), metric(f1) |
| Seurat reference mapping (SCTransform) · Configuration | 0.975085587274387 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(seurat_reference_mapping), paramset(SCTransform), metric(f1) |
| scArches+scANVI (Seurat v3 2000 HVG) · Configuration | 0.9372298848234738 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(scarches_scanvi), paramset(Seurat v3 2000 HVG), metric(f1) |
| scArches+scANVI (All genes) · Configuration | 0.9363141652450575 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(scarches_scanvi), paramset(All genes), metric(f1) |
| scANVI (All genes) · Configuration | 0.9672436357663169 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(scanvi), paramset(All genes), metric(f1) |
| scANVI (Seurat v3 2000 HVG) · Configuration | 0.963942105070359 fraction | Not reported | Author-reported evaluation · source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(scanvi), paramset(Seurat v3 2000 HVG), metric(f1) |
Scope and limitations
- Results published by the Open Problems project, source checked but not independently reproduced.
- This covers the label projection task at v1.0.0 only, not the whole Open Problems suite.
- true_labels and random_labels are controls that bound the scale, not competing methods.
- Preprocessing is part of the run, so the same method appears once per parameter set.
Source transcription and grouping reviewed by automated source review on 2026-09-18. These experiments were not independently reproduced by rewire.
Tested entities and results
Release 2026-09-17-134cd1815de8 · 16 evaluations · 16 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| K-neighbors classifier (log CP10k) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: K-neighbors classifier (log CP10k)Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.9460810866713062 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(k_neighbors_classifier), paramset(log CP10k), metric(f1) Source checking is not independent reproduction. |
| K-neighbors classifier (log scran) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: K-neighbors classifier (log scran)Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.9404360005933883 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(k_neighbors_classifier), paramset(log scran), metric(f1) Source checking is not independent reproduction. |
| Logistic regression (log CP10k) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: Logistic regression (log CP10k)Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.9791824244686764 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(logistic_regression), paramset(log CP10k), metric(f1) Source checking is not independent reproduction. |
| Logistic regression (log scran) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: Logistic regression (log scran)Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.7759818120203118 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(logistic_regression), paramset(log scran), metric(f1) Source checking is not independent reproduction. |
| Majority Vote on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: Majority VoteTask: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.16837763151390925 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(majority_vote), paramset(none), metric(f1) Source checking is not independent reproduction. |
| Multilayer perceptron (log CP10k) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: Multilayer perceptron (log CP10k)Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.8366856872231097 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(multilayer_perceptron), paramset(log CP10k), metric(f1) Source checking is not independent reproduction. |
| Multilayer perceptron (log scran) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: Multilayer perceptron (log scran)Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.925397640256357 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(multilayer_perceptron), paramset(log scran), metric(f1) Source checking is not independent reproduction. |
| Random Labels on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Method: Random LabelsTask: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.18787809947778522 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(random_labels), paramset(none), metric(f1) Source checking is not independent reproduction. |
| scANVI (All genes) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: scANVI (All genes)Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.9672436357663169 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(scanvi), paramset(All genes), metric(f1) Source checking is not independent reproduction. |
| scANVI (Seurat v3 2000 HVG) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: scANVI (Seurat v3 2000 HVG)Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.963942105070359 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(scanvi), paramset(Seurat v3 2000 HVG), metric(f1) Source checking is not independent reproduction. |
| scArches+scANVI (All genes) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: scArches+scANVI (All genes)Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.9363141652450575 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(scarches_scanvi), paramset(All genes), metric(f1) Source checking is not independent reproduction. |
| scArches+scANVI (Seurat v3 2000 HVG) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: scArches+scANVI (Seurat v3 2000 HVG)Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.9372298848234738 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(scarches_scanvi), paramset(Seurat v3 2000 HVG), metric(f1) Source checking is not independent reproduction. |
| Seurat reference mapping (SCTransform) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: Seurat reference mapping (SCTransform)Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.975085587274387 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(seurat_reference_mapping), paramset(SCTransform), metric(f1) Source checking is not independent reproduction. |
| True Labels on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Method: True LabelsTask: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 1 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(true_labels), paramset(none), metric(f1) Source checking is not independent reproduction. |
| XGBoost (log CP10k) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: XGBoost (log CP10k)Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.9638063508972504 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(xgboost), paramset(log CP10k), metric(f1) Source checking is not independent reproduction. |
| XGBoost (log scran) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score Configuration: XGBoost (log scran)Task: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 scoreDataset subset: Pancreas (random split with label noise) (Open Problems label projection split) 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). Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.9528870337485718 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedopenproblems-label primary benchmark evidence · results, dataset(pancreas_random_label_noise), method(xgboost), paramset(log scran), metric(f1) Source checking is not 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.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: part of discovery-benchmark-open-problems Individual claims | openproblems-label primary benchmark evidence results, dataset(pancreas_random_label_noise), metric(f1) Version: v1.0.0 | source checked automated source review · 2026-09-18 Audit detailsPrimary-source transcription with no human sign-off and no independent reproduction. Field: Claim: open-problems-association-pancreas-random-label-noise-f1 Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
Release 2026-09-17-134cd1815de8 · Record review: source checked
1 source records and release history
Download this releaseTechnical metadata and extraction receipts
Stable ID: open-problems-task-pancreas-random-label-noise-f1
- areas
- cells-tissues
- tasks
- Label projection on Pancreas (random split with label noise), F1 score
- metric
- F1 score
- metric direction
- higher
- dataset
- Pancreas (random split with label noise)
- protocol
- 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).
- source locator
- results, dataset(pancreas_random_label_noise), metric(f1)
- comparison panels
- id: open-problems-panel-pancreas-random-label-noise-f1; title: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score; protocol id: open-problems-task-pancreas-random-label-noise-f1; dataset id: open-problems-dataset-pancreas-random-split-with-label-noise; metric: f1; unit: fraction; direction: higher; result ids: open-problems-result-majority-vote-pancreas-random-label-noise-f1-f1; open-problems-result-random-labels-pancreas-random-label-noise-f1-f1; open-problems-result-k-neighbors-classifier-log-cp10k-pancreas-random-label-noise-f1-f1; open-problems-result-true-labels-pancreas-random-label-noise-f1-f1; open-problems-result-multilayer-perceptron-log-cp10k-pancreas-random-label-noise-f1-f1; open-problems-result-logistic-regression-log-cp10k-pancreas-random-label-noise-f1-f1; open-problems-result-xgboost-log-cp10k-pancreas-random-label-noise-f1-f1; open-problems-result-k-neighbors-classifier-log-scran-pancreas-random-label-noise-f1-f1; open-problems-result-multilayer-perceptron-log-scran-pancreas-random-label-noise-f1-f1; open-problems-result-logistic-regression-log-scran-pancreas-random-label-noise-f1-f1; open-problems-result-xgboost-log-scran-pancreas-random-label-noise-f1-f1; open-problems-result-seurat-reference-mapping-sctransform-pancreas-random-label-noise-f1-f1; open-problems-result-scarches-plus-scanvi-seurat-v3-2000-hvg-pancreas-random-label-noise-f1-f1; open-problems-result-scarches-plus-scanvi-all-genes-pancreas-random-label-noise-f1-f1; open-problems-result-scanvi-all-genes-pancreas-random-label-noise-f1-f1; open-problems-result-scanvi-seurat-v3-2000-hvg-pancreas-random-label-noise-f1-f1; source ids: expansion-p3-open-problems; source locator: results, dataset(pancreas_random_label_noise), metric(f1); context: Every method Open Problems label projection reports on Label projection on Pancreas (random split with label noise), F1 score, scored with F1 score on Pancreas (random split with label noise).; caveats: Results published by the Open Problems project, source checked but not independently reproduced.; This covers the label projection task at v1.0.0 only, not the whole Open Problems suite.; true_labels and random_labels are controls that bound the scale, not competing methods.; Preprocessing is part of the run, so the same method appears once per parameter set.; review: method: automated_source_review; date: 2026-09-18
Related records
- part of: Open Problems
- subject: Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: part of discovery-benchmark-open-problems
- benchmark: K-neighbors classifier (log CP10k) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: K-neighbors classifier (log scran) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: Logistic regression (log CP10k) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: Logistic regression (log scran) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: Majority Vote on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: Multilayer perceptron (log CP10k) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: Multilayer perceptron (log scran) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: Random Labels on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: scANVI (All genes) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: scANVI (Seurat v3 2000 HVG) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: scArches+scANVI (All genes) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: scArches+scANVI (Seurat v3 2000 HVG) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: Seurat reference mapping (SCTransform) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: True Labels on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: XGBoost (log CP10k) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score
- benchmark: XGBoost (log scran) on Open Problems label projection PANCREAS-RANDOM-LABEL-NOISE-F1: Label projection on Pancreas (random split with label noise), F1 score