Configuration

UNI

Published histology patch encoder whose frozen features the HEST authors scored with a Random Forest regression head.

Overview

Published histology patch encoder whose frozen features the HEST authors scored with a Random Forest regression head.

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

Evaluations and results

Release 2026-09-17-134cd1815de8 · 10 evaluations · 10 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.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
UNI on HEST-Benchmark CCRCC: Gene expression prediction from histology, Clear cell renal cell carcinoma Configuration: UNITask: HEST-Benchmark CCRCC: Gene expression prediction from histology, Clear cell renal cell carcinomaDataset subset: HEST-Benchmark CCRCC (HEST-Benchmark split) Random Forest regression with 70 trees over frozen patch features, averaged over folds or patients. Author-reported evaluation · Evaluation metadata: source checked
0.186 ±0.05 pearson_r Unit: correlation · Direction: higher	Uncertainty: type: standard deviation; value: 0.05 Scored: Not reported · Eligible: Not reported	source checkedHEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis · Table 1, row(CCRCC), column(UNI) Source checking is not independent reproduction.
UNI on HEST-Benchmark COAD: Gene expression prediction from histology, Colon adenocarcinoma Configuration: UNITask: HEST-Benchmark COAD: Gene expression prediction from histology, Colon adenocarcinomaDataset subset: HEST-Benchmark COAD (HEST-Benchmark split) Random Forest regression with 70 trees over frozen patch features, averaged over folds or patients. Author-reported evaluation · Evaluation metadata: source checked
0.147 ±0.05 pearson_r Unit: correlation · Direction: higher	Uncertainty: type: standard deviation; value: 0.05 Scored: Not reported · Eligible: Not reported	source checkedHEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis · Table 1, row(COAD), column(UNI) Source checking is not independent reproduction.
UNI on HEST-Benchmark HCC: Gene expression prediction from histology, Hepatocellular carcinoma Configuration: UNITask: HEST-Benchmark HCC: Gene expression prediction from histology, Hepatocellular carcinomaDataset subset: HEST-Benchmark HCC (HEST-Benchmark split) Random Forest regression with 70 trees over frozen patch features, averaged over folds or patients. Author-reported evaluation · Evaluation metadata: source checked
0.051 ±0.00 pearson_r Unit: correlation · Direction: higher	Uncertainty: type: standard deviation; value: 0.00 Scored: Not reported · Eligible: Not reported	source checkedHEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis · Table 1, row(HCC), column(UNI) Source checking is not independent reproduction.
UNI on HEST-Benchmark IDC: Gene expression prediction from histology, Invasive ductal carcinoma Configuration: UNITask: HEST-Benchmark IDC: Gene expression prediction from histology, Invasive ductal carcinomaDataset subset: HEST-Benchmark IDC (HEST-Benchmark split) Random Forest regression with 70 trees over frozen patch features, averaged over folds or patients. Author-reported evaluation · Evaluation metadata: source checked
0.502 ±0.06 pearson_r Unit: correlation · Direction: higher	Uncertainty: type: standard deviation; value: 0.06 Scored: Not reported · Eligible: Not reported	source checkedHEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis · Table 1, row(IDC), column(UNI) Source checking is not independent reproduction.
UNI on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung Configuration: UNITask: HEST-Benchmark LUNG: Gene expression prediction from histology, LungDataset subset: HEST-Benchmark LUNG (HEST-Benchmark split) Random Forest regression with 70 trees over frozen patch features, averaged over folds or patients. Author-reported evaluation · Evaluation metadata: source checked
0.511 ±0.03 pearson_r Unit: correlation · Direction: higher	Uncertainty: type: standard deviation; value: 0.03 Scored: Not reported · Eligible: Not reported	source checkedHEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis · Table 1, row(LUNG), column(UNI) Source checking is not independent reproduction.
UNI on HEST-Benchmark LYMPH_IDC: Gene expression prediction from histology, Lymph node metastasis of invasive ductal carcinoma Configuration: UNITask: HEST-Benchmark LYMPH_IDC: Gene expression prediction from histology, Lymph node metastasis of invasive ductal carcinomaDataset subset: HEST-Benchmark LYMPH_IDC (HEST-Benchmark split) Random Forest regression with 70 trees over frozen patch features, averaged over folds or patients. Author-reported evaluation · Evaluation metadata: source checked
0.234 ±0.05 pearson_r Unit: correlation · Direction: higher	Uncertainty: type: standard deviation; value: 0.05 Scored: Not reported · Eligible: Not reported	source checkedHEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis · Table 1, row(LYMPH_IDC), column(UNI) Source checking is not independent reproduction.
UNI on HEST-Benchmark PAAD: Gene expression prediction from histology, Pancreatic adenocarcinoma Configuration: UNITask: HEST-Benchmark PAAD: Gene expression prediction from histology, Pancreatic adenocarcinomaDataset subset: HEST-Benchmark PAAD (HEST-Benchmark split) Random Forest regression with 70 trees over frozen patch features, averaged over folds or patients. Author-reported evaluation · Evaluation metadata: source checked
0.424 ±0.06 pearson_r Unit: correlation · Direction: higher	Uncertainty: type: standard deviation; value: 0.06 Scored: Not reported · Eligible: Not reported	source checkedHEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis · Table 1, row(PAAD), column(UNI) Source checking is not independent reproduction.
UNI on HEST-Benchmark PRAD: Gene expression prediction from histology, Prostate adenocarcinoma Configuration: UNITask: HEST-Benchmark PRAD: Gene expression prediction from histology, Prostate adenocarcinomaDataset subset: HEST-Benchmark PRAD (HEST-Benchmark split) Random Forest regression with 70 trees over frozen patch features, averaged over folds or patients. Author-reported evaluation · Evaluation metadata: source checked
0.357 ±0.00 pearson_r Unit: correlation · Direction: higher	Uncertainty: type: standard deviation; value: 0.00 Scored: Not reported · Eligible: Not reported	source checkedHEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis · Table 1, row(PRAD), column(UNI) Source checking is not independent reproduction.
UNI on HEST-Benchmark READ: Gene expression prediction from histology, Rectum adenocarcinoma Configuration: UNITask: HEST-Benchmark READ: Gene expression prediction from histology, Rectum adenocarcinomaDataset subset: HEST-Benchmark READ (HEST-Benchmark split) Random Forest regression with 70 trees over frozen patch features, averaged over folds or patients. Author-reported evaluation · Evaluation metadata: source checked
0.162 ±0.08 pearson_r Unit: correlation · Direction: higher	Uncertainty: type: standard deviation; value: 0.08 Scored: Not reported · Eligible: Not reported	source checkedHEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis · Table 1, row(READ), column(UNI) Source checking is not independent reproduction.
UNI on HEST-Benchmark SKCM: Gene expression prediction from histology, Skin cutaneous melanoma Configuration: UNITask: HEST-Benchmark SKCM: Gene expression prediction from histology, Skin cutaneous melanomaDataset subset: HEST-Benchmark SKCM (HEST-Benchmark split) Random Forest regression with 70 trees over frozen patch features, averaged over folds or patients. Author-reported evaluation · Evaluation metadata: source checked
0.613 ±0.02 pearson_r Unit: correlation · Direction: higher	Uncertainty: type: standard deviation; value: 0.02 Scored: Not reported · Eligible: Not reported	source checkedHEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis · Table 1, row(SKCM), column(UNI) 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.

0 evidence rows matching the loaded filters