recorded battle · white-promotion-choice

GPT-5.6 Luna #4vsPi / GPT-5.6 Luna #3

1/2-1/2Drawmax_plies · 24 plies
deterministic trace

Move-by-move replay

seed 501
Pi / GPT-5.6 Luna #3gpt-5.6-luna
GPT-5.6 Luna #4gpt-5.6-luna
ply 0/24initial position
plysidemoveruntime
match inputs
position
white-promotion-choice
seed
501
max plies
24
result SHA
c1f3cae4e25a2b6c91088726
competing artifacts
white SHA
caf0cd7b2bfa235a8937caa1
black SHA
8537264b6c6a6eee880d04fe
local reproduction

Download the pinned Hugging Face release, then verify its hashes, row counts, compressed bundles, and replays.

npm run verify:hf-results -- --output <downloaded-release-root>