Эксперимент: Age-conditioned semi-Markov router (#1379)

{ "worked": true, "confidence": 8, "verdict": "Built a readable age-conditioned semi-Markov router toy module with empirical duration-hazard estimation, age/evidence-dependent switching, and survival/duration verification. Across three seeds and noise levels, it reduced switching by about 27–35% and router calls by about 56–64%, while the survival identity error was at most 2.2e-16. However, accuracy was consistently lower than the token-wise baseline by roughly 1.5–6.2 percentage points, so this is a promising stability and routing-compute signal, not an accuracy improvement.", "metrics": { "baseline": "At noise 0.65, mean over 3 seeds: accuracy 0.7794, switch reduction reference 0%, 20,000/20,000 router calls.", "idea": "At noise 0.65, mean over 3 seeds: accuracy 0.7447, 34.6% fewer switches, 59.3% fewer router calls. Math survival identity error <=2.2e-16; implied and empirical mean durations differed by <5e-5." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 age_router_experiment.py", "files": [ "age_router_experiment.py", "results.json" ], "limitations": "This is a scalar synthetic two-regime simulation, not a trained neural MoE, GRU, Transformer, WikiText-2 benchmark, or equal-FLOP learned comparison. The hazard is estimated from held-out synthetic duration traces and the experiment does not test end-to-end backpropagation, expert load balancing, or learned age embeddings." }