Huang Qi 50dbf40709 refactor(generator): remove deterministic speed_profile and hard log_dt clip ...

These post-processing hacks were added to compensate for small-data
training. With Balabit pretraining they suppress the multimodal
timing distribution and cause the template-y Δt curves seen in the
verify UI.

2026-05-10 13:22:57 +08:00

..

__init__.py

chore: initialize git repo, add matplotlib dep, extend config

2026-05-10 12:24:07 +08:00

conftest.py

chore: initialize git repo, add matplotlib dep, extend config

2026-05-10 12:24:07 +08:00

test_balabit_adapter.py

feat(adapter): implement process_session and CLI

2026-05-10 12:42:43 +08:00

test_coord.py

chore: initialize git repo, add matplotlib dep, extend config

2026-05-10 12:24:07 +08:00

test_generator.py

refactor(generator): remove deterministic speed_profile and hard log_dt clip

2026-05-10 13:22:57 +08:00

test_models.py

chore: initialize git repo, add matplotlib dep, extend config

2026-05-10 12:24:07 +08:00

test_scroll_collector.py

chore: initialize git repo, add matplotlib dep, extend config

2026-05-10 12:24:07 +08:00

test_scroll_generator.py

chore: initialize git repo, add matplotlib dep, extend config

2026-05-10 12:24:07 +08:00

test_scroll_models.py

chore: initialize git repo, add matplotlib dep, extend config

2026-05-10 12:24:07 +08:00

test_scroll_trainer.py

chore: initialize git repo, add matplotlib dep, extend config

2026-05-10 12:24:07 +08:00

test_server.py

chore: initialize git repo, add matplotlib dep, extend config

2026-05-10 12:24:07 +08:00

test_trainer.py

fix(trainer): rename _LOG_1_1 → _LOG_INV_0_9, add tests for aug_ids 2-5

2026-05-10 13:11:27 +08:00