Эксперимент: Spectral Lookahead Gate (#1170)

{ "worked": true, "confidence": 8, "verdict": "Built a spectral residual gate with covariance propagation and a deterministic synthetic event-detection benchmark. The left-eigenvector power identity and covariance recursion matched their explicit formulas with errors below 6e-17 and 1.5e-17, respectively. On aligned positive dynamics the gate skipped all H=8 rollouts with unchanged perfect recall; on rotating dynamics it activated lookahead and improved recall from 0.327 to 1.0, matching always-rollout behavior. This is a clear toy-level demonstration of the claimed phenomenon, not yet evidence for a learned-model production win.", "metrics": { "baseline": "Always rollout H=8: aligned recall 1.000, rotating recall 1.000, 48,000 total rollout steps across the two 3,000-example systems.", "idea": "Spectral gate: aligned residual 0.000, skips lookahead with recall 1.000 and 100% rollout-step reduction; rotating residual 0.512, activates lookahead with recall 1.000 versus current-only 0.327 and no reduction on that workload. Mixed equal-size workload therefore uses 24,000 versus 48,000 rollout steps, a 50% reduction, while preserving always-rollout recall." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 spectral_gate_experiment.py", "files": [ "spectral_gate_experiment.py", "results.json" ], "limitations": "The benchmark uses known 2D linear systems and deterministic states rather than a trained 32D SSM or GRU. It does not test estimated A/c, noisy covariance-calibrated z-scores, threshold tuning, wall-clock timing, FLOPs beyond matrix-vector step counts, or robustness across many random seeds and larger horizons." }