-
v0.4.10: watchdog env-driven checkpoint
-
v0.4.10: heads-WIP upload hole (FUKJA61G lesson) + recover fixes (archive root, shutil.move nest, stamps prep/data only, max_steps 110)
-
v0.4.10: heads-WIP upload hole (FUKJA61G lesson) + recover fixes (archive root, shutil.move nest, stamps prep/data only, max_steps 110)
-
QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified)
-
v0.4.9: RCA evidence archived + HANDOVER §0.4
-
v0.4.9: RCA evidence archived + HANDOVER §0.4
-
v0.4.8: safetensors-loss fix + HEAD verification + v0.4.7 OOM-gate sync
-
v0.4.8: safetensors-loss fix + HEAD verification + v0.4.7 OOM-gate sync
-
v0.4.8: safetensors-loss fix + HEAD verification + v0.4.7 OOM-gate sync
-
QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified)
-
QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified)
-
v0.4.5: restore tooling lost with sandbox reset
-
v0.4.5: restore tooling lost with sandbox reset
-
v0.4.5: restore tooling lost with sandbox reset
-
v3: real-games training round tooling
-
QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified)
-
QwenJev v0.2.0: vision tower on the System-1 inference path (tiny/hf backends, mock env, e2e local run)
-
QwenJev: multimodal-retrofitted NanoJev for ARC-AGI-3 (initial skeleton)