ibl_bwb_eval.scoring.ts1#

TS1 scoring utility.

Loads prediction .safetensors files, matches them to pre-generated ground truth files by trial_id, and computes all metrics defined in the TS1ReadoutSpec.

Usage:

python -m ibl_bwb_eval.scoring.ts1 –pred_dir predictions/ts1 –gt_dir ground_truth/ts1 python -m ibl_bwb_eval.scoring.ts1 –pred_dir predictions/ts1/mlp-baseline/ts1-licking_rate –gt_dir ground_truth/ts1

score_file

Score one prediction file against its ground truth file.

score_dir

Score all TS1 prediction files found under pred_dir.

summarize

Aggregate per-seed scores into mean ± SEM per (label, task, recording_id).