mirror of
https://github.com/DeeJanuz/frametop.git
synced 2026-10-15 00:00:42 +02:00
gap_report: per side, for gaps where the full search lost the hand for a while (back in view) and the rest, the time from the oracle's first sample finding it again to the tracker having it. replay_gaps.sh: REPLAY=BINARY replays with another ft-handreplay build, for a baseline. On 2026-10-13 they showed student v13b losing hands v11c keeps (bright desk recording: 12.8% of findable hands missed against 3.3%, mostly palms the landmark model rejected). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>