compare-model-runs

Use when comparing metrics across multiple ML training executions in DerivaML — ranking model runs by accuracy/F1/loss, finding the best of N recent runs, identifying performance regressions, or aggregating results across a sweep. Covers three metric-storage patterns: features-as-scalars (`deriva_ml_list_feature_values(execution_rids=...)` for one-round-trip catalog query), metrics-as-JSONL-asset files (`Metrics_File` asset, download + parse locally), and prediction-CSV-as-`Execution_Asset` (per-execution tabular CSV plus optional per-analysis summary CSV — the deriva-ml-model-template's default pattern). ALSO use for **artifact provenance tracing** — when the question is 'where did this prediction come from', 'what code produced this asset', 'what dataset version trained this model', or 'why is this metric different from the last run' — `deriva_ml_get_lineage` walks the full data-flow chain in one call; the worked example shows the two-step pattern (lineage walk → workflow resource fetch) that yields the wor

By informatics-isi-edu schedule Updated 5/30/2026