recorded battle · white-promotion-choice
Pi / GPT-5.6 Luna #4vsGPT-5.6 Terra #5
1/2-1/2Drawmax_plies · 24 plies
deterministic trace
seed 501Move-by-move replay
GPT-5.6 Terra #5gpt-5.6-terra
8
♚
♙7
6
5
4
3
2
♟
1a
b
c
d
♔e
f
g
h
Pi / 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
- 1b47ff745d8d4a118f07184c
competing artifacts
- white SHA
- 8ed212384df2ffd09a15c642
- black SHA
- 984468d6bc9e7172d85729c5
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>