Eval report — step-001800

• entries evaluated: 4535
• full-parse exact match: 0.1074
• mean token confidence: 0.8566

Per-component F1

tag	precision	recall	f1	support
country	0.2955	0.2653	0.2796	245
region	0.4411	0.1098	0.1759	3205
locality	0.2330	0.3089	0.2657	3357
dependent_locality	0.0000	0.0000	0.0000	40
postcode	0.8426	0.6846	0.7554	2980
subregion	0.0000	0.0000	0.0000	0
cedex	0.0000	0.0000	0.0000	1
venue	0.3862	0.4024	0.3941	1101
street	0.3326	0.2217	0.2660	2928
house_number	0.7316	0.8433	0.7835	1742

Calibration (confidence bucket → accuracy)

bucket	n	accuracy
0.0–0.1	0	0.0000
0.1–0.2	19	0.5789
0.2–0.3	316	0.3323
0.3–0.4	1213	0.3776
0.4–0.5	2754	0.3413
0.5–0.6	3647	0.3548
0.6–0.7	3659	0.3884
0.7–0.8	4610	0.4063
0.8–0.9	7716	0.4396
0.9–1.0	37314	0.5988