Continual-ARCby unify

ReplayARC-AGI-1 · Workstreams · GPT-6 Luna, low

OpenClaw, memory wiped

Everything the harness wrote deleted before every instance.

Share learned
0 its own reset
Stream, budget used
45.4 solved 70%
Epilogue, budget used
74.3 solved 30%
Model spend
$10.61 4,449 calls
Instances
227 15.8 hours

Budget used is the share of the cap of 16 that an instance was charged, averaged over the instances: a solved instance costs 1 for each wrong answer and each demonstration, an unsolved one all 16, so lower is better. The share learned reads the stream's budget against the learner itself reset before every instance, and this learner keeps nothing between instances, so it is its own reset and reads 0.

Loading the run