maxime and Claude Opus 5.5
4836929bc7
Steps 5 and 6: pre-trained M2 passes the criterion for Obstruction, not for Visibility; episodes and sensors (decode.py)
...
m2.py: one thread per process, --test to share the stations left out between processes, --out on the time split.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-17 11:59:49 +01:00
maxime and Claude Opus 5.5
7312a1c3ca
M2 results: no better than M1 on stations seen, worse on a station left out
...
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-16 20:54:46 +01:00
maxime and Claude Opus 5.5
975ebc7c1a
The criterion: stations seen, cut in time; M1's regressions station by station; no regression when nothing is flagged
...
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-16 17:59:06 +01:00
maxime and Claude Opus 5.5
f93cdf3cd1
Step 3: M1, gradient boosting on station aggregates (leave one station out, and a time split)
...
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-16 17:48:11 +01:00
maxime and Claude Opus 5.5
c04cbc90bb
Step 2: the evaluator (the measure of bench/score.py on predictions per instant; the rules reproduce it exactly)
...
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-16 16:25:03 +01:00
maxime and Claude Opus 5.5
b2d3734152
README: how to build the dataset
...
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-16 15:49:05 +01:00
maxime and Claude Opus 5.5
9cf20766a5
aimsight-models: the pilot of learned detectors (README)
...
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com >
2026-11-16 15:40:17 +01:00