Эксперимент: Unexplained Topology Distillation (#1184)

{ "worked": true, "confidence": 6, "verdict": "Built a compact directional PCE prototype for unequal-size persistence diagrams, including teacher persistence weighting, Gaussian explanation scores, induced unexplained-event mass, and optimization against a Chamfer control. The probability validity check passed and the excess identity error was 1.8e-7. In the main run unexplained mass fell from 0.488 to 0.147 with PCE versus 0.271 with Chamfer; across three additional starts PCE was better in two of three, giving a modest but promising signal rather than definitive evidence.", "metrics": { "baseline": "Chamfer control: main final unexplained mass 0.2712, excess 0.3548; repeated-start mean unexplained mass 0.2085", "idea": "Directional PCE: main final unexplained mass 0.1471, excess 0.1772; repeated-start mean unexplained mass 0.1609; probability validity true; excess identity absolute error 1.79e-7" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 pce_experiment.py", "files": [ "pce_experiment.py", "results.json", "run_output.txt" ], "limitations": "This is a toy diagram-point optimization, not a CNN distillation experiment: no cubical-complex persistence computation, real activation tensors, classification task, differentiable persistence backend, bandwidth sweep, FLOP/accuracy measurement, calibration analysis, or reverse-direction ablation was tested. The control is a symmetric Chamfer diagram matching objective, and the repeated-start advantage was not universal." }