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

ai_mouse

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

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

docs/superpowers

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

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

static

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

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

tests

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

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

.gitignore

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

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

main.py

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

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

pyproject.toml

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

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

uv.lock

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

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

Description

No description provided

3.2 MiB

Languages

Python 79.1%

JavaScript 17.3%

CSS 3%

HTML 0.6%