rrm workspace: TRM/HRM/SRM code, Maze dataset, dynamical-analysis pipelineHEADmain

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 <noreply@anthropic.com>

1 files changed, 2 insertions, 0 deletions

diff --git a/research/flossing/ptrm_selection_trm_multi4_104164_k8_n512.summary.csv b/research/flossing/ptrm_selection_trm_multi4_104164_k8_n512.summary.csv
new file mode 100644
index 0000000..4be4cf7
--- /dev/null
+++ b/research/flossing/ptrm_selection_trm_multi4_104164_k8_n512.summary.csv
@@ -0,0 +1,2 @@
+deterministic/exact,deterministic/token_acc,fd_lyap,include_clean,lambda_fail_mean,lambda_mean,lambda_success_mean,lyap_min/exact,lyap_min/token_acc,mean_rollout/exact,mean_rollout/token_acc,n_samples,noise_std,oracle_pass/exact,oracle_pass/token_acc,q_fail_mean,q_max/exact,q_max/token_acc,q_mean,q_minus_0.25lambda/exact,q_minus_0.25lambda/token_acc,q_minus_0.5lambda/exact,q_minus_0.5lambda/token_acc,q_minus_1lambda/exact,q_minus_1lambda/token_acc,q_minus_2lambda/exact,q_minus_2lambda/token_acc,q_success_mean,rollout0/exact,rollout0/token_acc,rollouts

+0.841796875,0.9395254254341125,1.0,1.0,7.1426215171813965,6.046740531921387,5.835097789764404,0.9140625,0.9662663340568542,0.838134765625,0.9396581649780273,512.0,0.001,0.91796875,0.9709925055503845,-10.85094928741455,0.91796875,0.9674961566925049,4.857690811157227,0.91796875,0.9673996567726135,0.91796875,0.9672791957855225,0.916015625,0.967013955116272,0.916015625,0.9671344757080078,7.891430377960205,0.826171875,0.9349681735038757,8.0