Эксперимент: Conformal Lower-Clearance Certificate for Neural Selectors (#1058)

{ "worked": true, "confidence": 9, "verdict": "Built a synthetic conformal lower-clearance certificate with empirical lower-tail CVaR and finite-sample order-statistic calibration. The CVaR optimizer matched the direct lower-tail computation to 2.2e-16; under exchangeability, coverage tracked the predicted targets (alpha=.05/.1/.2/.3: .950/.901/.804/.702), while uncalibrated CVaR coverage at alpha=.1 was only .771. Smaller gamma monotonically reduced the calibrated residual correction (q=-.009, .025, .072, .164 for gamma=.1,.25,.5,1), and the deliberate test shift reduced coverage to .734, demonstrating the expected exchangeability limitation.", "metrics": { "baseline": "Uncalibrated CVaR certificate C=M: coverage 0.771 at alpha=0.1; under shifted test distribution 0.554.", "idea": "Calibrated CVaR: coverage 0.901 at alpha=0.1 with q=0.0249 and certificate nonnegativity 0.9997; shifted coverage 0.734. CVaR identity max error 2.2e-16. Alpha sweep coverage: 0.950, 0.901, 0.804, 0.702 for alpha 0.05, 0.1, 0.2, 0.3." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 certificate_experiment.py", "files": [ "certificate_experiment.py", "results.json" ], "limitations": "This is a synthetic selected-trajectory simulator, not a nuPlan or real neural-planner integration; no learned model, OBB geometry, planner replanning, confidence intervals, or GPU benchmark was tested. Distribution-shift failure means the formal guarantee should not be applied outside the calibration distribution." }