PCNN Fold 1

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	21.80%
Test F1 score	0.1626
Hierarchical loss	0.92891120
P-adic loss (total)	395.56464000
P-adic loss (mean)	0.57494860
Prime base	71
Hidden layer size	27
Max tags	32
Training samples	2,735
Test samples	688

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	150	21.80%	0.000000	0.000000
p^4	4	0.58%	0.000000	0.000000
p^3	23	3.34%	0.000003	0.000064
p^2	77	11.19%	0.000198	0.015275
p^1	39	5.67%	0.014085	0.549296
p^0	395	57.41%	1.000000	395.000000

Tag Rank vs First-Layer Weight Magnitude

Tag rank vs max first-layer weight magnitude — Scatter plot showing the relationship between tag battle ranking and maximum absolute first-layer weight value across all hidden units. Shows which input features contribute most to the parameter constrained neural network's hidden representations.

About p-adic loss

P-adic loss measures the distance between predicted and true taxonomy using p-adic metric (base 71). Lower values indicate closer predictions in the taxonomy hierarchy. This metric is shared with the umllr model for comparison.