Эксперимент: Risk-Calibrated World-Model Gates (#958)

{ "worked": true, "confidence": 8, "verdict": "Built a reproducible risk-calibrated gate MVP with required-rollout sizing, conservative lower event bounds, ordinary sampling, and planner-directed probes. The exact miss law matched Monte Carlo within 0.00272 absolute error; all required-count sweeps achieved target delta=0.05, with the small-r approximation within 3.2%. Matched-budget probes reduced observed miss probability from 0.77877 to 0.03343 at r=0.005 and from 0.60664 to 0.00065 at r=0.01, closely matching the multiplicative prediction. This confirms the mechanism, but not a real deployment win because probe effectiveness was prescribed rather than learned.", "metrics": { "baseline": "Uniform 50-rollout miss probabilities: 0.77877, 0.60664, 0.36528, 0.07742 for r={0.005,0.01,0.02,0.05}.", "idea": "30 random plus 20 directed-probe miss probabilities: 0.03343, 0.00065, 0.0, 0.0 for the same r values; analytical predictions were 0.03335, 0.00059, 6.0e-9, and 2.36e-9." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 risk_gate_experiment.py", "files": [ "risk_gate_experiment.py", "results.json" ], "limitations": "No learned simulator, reference environment, planner regret, collision detector, deployment threshold, or false-rejection analysis was tested. The stress probe rate q=min(0.60,30r) is synthetic and assumes independent stationary events." }