From 66e0d8b9fd4d0f7a2231d689c055e26fdf1cf04a Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Sat, 13 Jun 2026 12:35:36 -0500 Subject: rrm workspace: TRM/HRM/SRM code, Maze dataset, dynamical-analysis pipeline Curated export for clone-and-run Maze training (2x A6000) + diagnostics. trm/hrm pretrain.py carry trajectory-augmentation code (backward-compatible). Heavy artifacts (checkpoints/wandb/npz) gitignored; see PROVENANCE.md. Co-Authored-By: Claude Fable 5 --- .../analysis_2x2/early_pairing_trm_official58590.md | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 research/flossing/analysis_2x2/early_pairing_trm_official58590.md (limited to 'research/flossing/analysis_2x2/early_pairing_trm_official58590.md') diff --git a/research/flossing/analysis_2x2/early_pairing_trm_official58590.md b/research/flossing/analysis_2x2/early_pairing_trm_official58590.md new file mode 100644 index 0000000..2b29ab5 --- /dev/null +++ b/research/flossing/analysis_2x2/early_pairing_trm_official58590.md @@ -0,0 +1,17 @@ +# Early-window pairing — trm_official58590 +- paired n=2048; final acc=0.8760; already-correct@step4=0.6943 +- of final-correct, fraction already correct@4: 0.7926 +- early-window lam1: final-correct med +0.0178, final-wrong med +0.1075 + +## Forecasting FINAL outcome from the first 4 ACT steps +- AUC(-lam1_early -> final correct) = 0.891 +- AUC(-drift@4 -> final correct) = 0.800 +- AUC(q_halt@4 -> final correct) = 0.901 +- reference: AUC(-lam1_full -> final correct) = 0.993 + +## Restricted to examples NOT yet correct at step 4 (the decision-relevant set) +- n=626, of which eventually correct: 372 (0.594) +- AUC(-lam1_early -> eventually correct) = 0.543 +- AUC(-drift@4 -> eventually correct) = 0.492 +- AUC(q_halt@4 -> eventually correct) = 0.521 +- early lam1 med: eventually-correct +0.1060 vs never-correct +0.1075 \ No newline at end of file -- cgit v1.2.3