Эксперимент: Equivariant Shared-Mechanism World Model (#1321)

{ "worked": true, "confidence": 7, "verdict": "Built a reproducible toy world-model experiment with a shared MLP transition and sampled C4 equivariance penalty. The numerical checks passed exactly: C4 composition and the synthetic mechanism equivariance had zero error, while a deliberately non-equivariant linear map had penalty 1.928. On anisotropic held-out-rotation data, the equivariant model reduced MSE from 0.001083 to 0.000722 and reduced equivariance violation from 0.000510 to 0.000092, while also improving in-distribution MSE; however, an initial isotropic run showed no gain, so the result is promising but not universal.", "metrics": { "baseline": "2690 parameters; train MSE 0.000664; in-distribution MSE 0.000934; held-out rotation MSE 0.001083; held-out equivariance penalty 0.000510", "idea": "2690 parameters; train MSE 0.000710; in-distribution MSE 0.000617; held-out rotation MSE 0.000722; held-out equivariance penalty 0.000092" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "This is a small synthetic C4 toy rather than a real graph/recurrent world model. The comparison uses one fixed seed and one held-out rotation; no multi-agent dataset, separate context-specific predictor baseline, trajectory adaptation, FLOP analysis, or multi-seed confidence interval was tested." }