wassname e5b68acf69 diag(#40): z-norm scores within family, winsorized 2-threshold Otsu zones, --feats offline mode ...

Synthetic and live scores share an axis with meaningful zero (raw scores carry a
common <mu,v> offset since v = mean diff is not orthogonal to the family mean).
Zones come from label-free online stats (EMA mean/std + Otsu valley), replacing
mean+k*sd which placed both cuts beyond every distribution. Winsorize at 1/99%
before Otsu: variance-maximizing cuts otherwise buy a class for one outlier.
Fresh-eyes review verified z-norm is affine (AUROCs unchanged), zones label-free,
P/R recompute from parquet matches titles.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

2026-06-11 11:23:42 +00:00

..

attic

cleanup: delete antipasto.py; attic 7 erase-era scripts (T1/T6)

2026-06-10 11:21:53 +00:00

build_combined_pool.py

reorg: out/ sorted by datatype (vhack/ pools/ runs/ vhack_grads/ figs/)

2026-05-30 03:52:24 +00:00

build_runtests_pool.py

fix: dense run_tests teacher pool (6 -> 215 prompts) so the hack seeds in 60 steps

2026-06-07 11:01:31 +00:00

build_solve_pool_openrouter.py

misc

2026-06-11 11:07:28 +00:00

build_substrate.py

misc

2026-06-11 11:07:28 +00:00

diag_pinning_followup.py

diag(#40): offline follow-up -- pooling variants, synthetic common-mode, env_mode join

2026-06-11 10:58:16 +00:00

diag_pinning_refresh.py

diag(#40): z-norm scores within family, winsorized 2-threshold Otsu zones, --feats offline mode

2026-06-11 11:23:42 +00:00

diag_pinning.py

diag(#40): z-norm scores within family, winsorized 2-threshold Otsu zones, --feats offline mode

2026-06-11 11:23:42 +00:00

make_random_vhack.py

cleanup: trim 2 stale provenance/train-of-thought comments

2026-06-03 00:25:22 +00:00

migrate_deploy_v1_to_v2.py

tool: migrate v1 deploy_test/eval_curve -> v2 field names (for mid-flight runs)

2026-06-10 05:27:38 +00:00

pairs_from_rollouts.py

misc

2026-06-11 11:07:28 +00:00

plot_deploy_overlay.py

misc

2026-06-11 11:07:28 +00:00

plot_dynamics.py

misc

2026-06-11 11:07:28 +00:00

plot_emergence.py

rename python package projected_grpo -> vgrout

2026-06-05 14:51:48 +08:00

plot_floor_ceiling.py

misc

2026-06-11 11:07:28 +00:00

plot_substrate.py

misc

2026-06-11 11:07:28 +00:00

probe_plot_stack.py

misc

2026-06-11 11:07:28 +00:00

results_deploy.py

Consolidate tagged hack pairsets in data

2026-06-10 11:58:53 +00:00

results.py

Consolidate tagged hack pairsets in data

2026-06-10 11:58:53 +00:00

validate_spoonfeed.py

cleanup: consolidate stale loaders and pair scripts

2026-06-09 12:47:32 +00:00

verify_base_solve.py

fix: eval on paper test set, not contaminated holdout (base solve 0.94->0.094)

2026-06-07 11:01:31 +00:00

verify_eval_gap.py

refactor: extract train_config.py + run_artifacts.py from train.py; slim results scripts

2026-06-09 13:34:50 +00:00

verify_lora2r_routing.py

misc

2026-06-11 11:07:28 +00:00

verify_partition.py

misc

2026-06-11 11:07:28 +00:00

verify_rewards.py

misc

2026-06-11 11:07:28 +00:00

verify_rotation.py

misc

2026-06-11 11:07:28 +00:00

verify_science_invariants.py

Consolidate tagged hack pairsets in data

2026-06-10 11:58:53 +00:00