summaryrefslogtreecommitdiff
path: root/initial_perturb_robustness/smoke_baseline.summary.csv
diff options
context:
space:
mode:
authorYurenHao0426 <blackhao0426@gmail.com>2026-06-29 12:15:51 -0500
committerYurenHao0426 <blackhao0426@gmail.com>2026-06-29 12:15:51 -0500
commita6ec4288a2232988b130b2f00bb2565f81706966 (patch)
tree1bb86e7f0b899b823b9e7fdf383e832d30a181e0 /initial_perturb_robustness/smoke_baseline.summary.csv
Recursive reasoning dynamics: analysis pipeline, paper drafts, toy models
Failure=more-chaotic (task-general under validity labeling) reduces to convergence/completeness detection; mechanism (transient chaos vs multistability vs input-induced) under investigation. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Diffstat (limited to 'initial_perturb_robustness/smoke_baseline.summary.csv')
-rw-r--r--initial_perturb_robustness/smoke_baseline.summary.csv3
1 files changed, 3 insertions, 0 deletions
diff --git a/initial_perturb_robustness/smoke_baseline.summary.csv b/initial_perturb_robustness/smoke_baseline.summary.csv
new file mode 100644
index 0000000..c5fd40c
--- /dev/null
+++ b/initial_perturb_robustness/smoke_baseline.summary.csv
@@ -0,0 +1,3 @@
+label,sigma,n_samples,rollouts,ckpt_root,ckpt_name,perturb,noise_distribution,mean_rollout_exact,mean_rollout_token_acc,pass_at_k,all_k,correct_count_mean,correct_count_std,correct_count_q10,correct_count_q50,correct_count_q90,zero_frac,full_frac
+trm_baseline_smoke,0.0,16,2,/home/yurenh2/rrm/trm/checkpoints/Sudoku-extreme-1k-aug-1000-ACT-torch/pretrain_mlp_t_sudoku_official_gbs768_repro,step_58590,both,gaussian,0.875,0.9537037014961243,0.875,0.875,1.75,0.6614378094673157,1.0,2.0,2.0,0.125,0.875
+trm_baseline_smoke,0.001,16,2,/home/yurenh2/rrm/trm/checkpoints/Sudoku-extreme-1k-aug-1000-ACT-torch/pretrain_mlp_t_sudoku_official_gbs768_repro,step_58590,both,gaussian,0.8125,0.9309413433074951,0.875,0.75,1.625,0.6959705352783203,0.5,2.0,2.0,0.125,0.75