ARC-AGI-2 contest implementation: CHIMERA symbolic candidates, reproducible ablations and clearly separated public evaluation and official scores.
Quick read
Latest capture 2026-10-31 04:00
Compare the starting count and capture dates, not just the percentage. How to read GitHub star growth. Missing history is not zero growth.
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
0 paths
Agent instructions and tool configuration found in this repository.
No config files detected.
2 observed captures since 2026-10-30. Observed captures are shown by default.
Stars from first capture 0
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Offline ARC-AGI-3 graph exploration agent with public-game evidence and reproducible evaluation.
Research proof-of-concept. ~2-5% accuracy on ARC-AGI. NOT an ARC Prize submission. GPU compute-shader playground.
Proof-carrying adaptive Luna-first cognitive routing for Promptothon 2026
Airline satisfaction: nested GBDT ensembles, Darwin-Cage residual diagnostics, complete experiment records and attributed public prediction sources.
MiniCPM5-2B competition benchmark harness, numerical gates and three fixed experiment directions; official hardware evaluation pending.
Autonomous, evidence-first engineering system for the BuildArena S02 (Besiege) Human-AI Engineering Challenge: rules-validated scorer, orbit/landing gates, isolated Autopilot agent run, submission packager.
