Latest Benchmark

Rolling nightly benchmark compiled from the live operational runs. Snapshot label: latest-2026-04-20T0007Z.

Trained params is the average non-zero parameter count in the fitted model across folds. Avg active params / classification is the mean number of active parameters or scoring decisions touched while classifying one product.

9,935Filtered products

3,316Filtered tags

455Filtered taxonomies

79Prime base

View UMLLR tag-order ablation View operational UMLLR page

Benchmark dashboard chart for latest benchmark view — Small-multiples dashboard generated directly from the comparison table rows below.

Model comparison chart for latest benchmark view — Log-log scatter of trained parameters versus mean p-adic loss, overlaid with the current parsimoniousness baseline.

Active parameter comparison chart for latest benchmark view — Scatter plot of avg active params versus mean p-adic loss, excluding PCLR and PCNN. Fitted equation: mean p-adic loss = -0.0935 log10(active params) + 0.3907. Regression fitted on log10(active params): R²=0.677, p=0.023.

Active parameter versus log-loss chart for latest benchmark view — Scatter plot of avg active params versus log10(mean p-adic loss), excluding PCLR and PCNN. Fitted equation: log10(mean p-adic loss) = -0.1697 log10(active params) - 0.4350. Regression fitted on log10(active params): R²=0.817, p=0.005.

Model	Trained params	Mean p-adic loss	Exact acc.	Prefix-2 acc.	Avg active params / classification
Dummy Baseline	1.0	0.577208	4.49%	21.04%	1.00
Importance-Optimised p-adic Linear Regression	887.4	0.275238	50.70%	64.11%	1.09
Parameter-constrained Logistic Regression	14949.0	0.814109	4.80%	12.85%	658.81
Unconstrained Logistic Regression with L1	5376.0	0.099622	66.50%	81.95%	468.12
Parameter-constrained Neural Network	13575.0	0.505807	11.88%	30.57%	12723.27
Decision Tree	44510.4	0.127238	59.23%	77.59%	333.46
Level-wise Logistic Regression	178532.2	0.126724	54.53%	77.92%	210.05
Unconstrained Neural Network with L1	45693.0	0.117328	63.73%	79.90%	5960.77
Zubarev (greedy init.)	1032.0	0.337716	43.94%	58.24%	1.45