Home
/
Sample-level evals
Sample-level evals · eval bucket
Whole-sample phenotype.
Whole-sample classification and phenotype — grading a model on the sample as a whole.
11
evals implemented · 1 families
01
Overview
The sample bucket grades whole-sample classification and phenotype — one prediction per
biological sample. 11 evals span 1 task
family, each a (task × dataset-arm) pair drawn
straight from the runtime registry.
02
Families
Task families present in this bucket, by eval count.
03
Catalog
Filter and sort every sample eval; expand any card for its IO contract.
Task all sample_classification
Publication all caggiano_2025_genome_medicine chang_2024_nature_communications tao_2023_cell_reports_medicine
sort Task Dataset Family Publication # metrics ↑
11 of 11 evals · 1 family
sample_classification 11 sample_classification caggiano_2025_genome_medicine / cfdna_methylation_als@0.0.1 9m # ▸
sample_classification caggiano_2025_genome_medicine / cfdna_methylation_als_tim@0.0.1 9m # ▸
sample_classification chang_2024_nature_communications / cfrna_tb@0.0.1 9m # ▸
sample_classification chang_2024_nature_communications / cfrna_tb_counts@0.0.1 9m # ▸
sample_classification chang_2024_nature_communications / cfrna_tb_counts_validation@0.0.1 9m # ▸
sample_classification chang_2024_nature_communications / cfrna_tb_validation@0.0.1 9m # ▸
sample_classification tao_2023_cell_reports_medicine / cfdna@0.0.1 9m # ▸
sample_classification tao_2023_cell_reports_medicine / cfmedip@0.0.1 9m # ▸
sample_classification tao_2023_cell_reports_medicine / cfrna@0.0.1 9m # ▸
sample_classification tao_2023_cell_reports_medicine / cfrna_1pct@0.0.1 9m # ▸
sample_classification tao_2023_cell_reports_medicine / cfrna_counts@0.0.1 9m # ▸