Эксперимент: Equation-addressable equilibrium layer (#993)

{ "worked": true, "confidence": 9, "verdict": "Built a readable equation-addressable equilibrium layer for the three-variable bipartite system, including maximum matching, damped Newton solving, and exact mechanism-specific residual replacement. Numerical checks reproduced the predicted Newton behavior, and two interventions that both fix S=0.8 produced identical S but different downstream P values. Across 80 fixed-seed cases, the mechanism solver had mean state error 3.42e-16 versus 1.616 for an observational variable-clamping baseline, so the claimed mechanism distinction was clearly observed in this toy system.", "metrics": { "baseline": "Variable-only observational clamp: mean intervention state error 1.6163475739511235 over 80 cases", "idea": "Equation replacement: mean intervention state error 3.4238284121931226e-16, mean target error 5.570630762230521e-17, mean 2 solver iterations, max residual 5.389157964038493e-16; same-value f2/f3 interventions differed in downstream P by 1.7747252747252749" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "This is an exact linear, zero-parameter toy equilibrium rather than a learned neural residual layer; it does not test MLP parameterization, training, implicit differentiation, nonlinear solver robustness, wall-clock speed, or generalization to held-out interventions." }