EXP-15 / completed
Research checkpoint; not the selected default. CM-5 is selected again. Historical results and checkpoint identity are preserved.
CM-8 / research checkpoint
Random-initialized mixed-data experiment
Fresh random initialization; selected update 46,875 by fixed validation NLL. Research-only, not promoted.
86,235,648 parameters. 120-slot prefix encoding current board/state plus optional 16-ply history; up to 122 inference positions, with 512 allocated vocabulary IDs. Complete past game history is not required, and repetition history may be unknown. Different training objective; loss is not comparable to full-history runs. No reasoning traces.
Checkpoint SHA-256 57c714120d47a06d30386f63c135a3afd141c61d012b46774cd2485b8c78fa2e
No verified parent checkpoint is asserted; see the experiment initialization evidence.
Experiments
EXP-14 / completed
CM-8 checkpoint trajectory and final Sunfish evaluation
Read experiment →EXP-13 / completed
Eight-hour random-initialization training
Read experiment →Inspect and reproduce
Recorded evidence and source · All versioned source, including Rust · Published downloads and limitations · Games and checkpoint filters