Eval Matrix Report
Generated: 2026-05-25T23:23:42.184Z Golden rows: 4535
Summaryโ
| Mode | Exact Match | Macro F1 | Empty Parse | Overconf Wrong |
|---|---|---|---|---|
| rule-only | 30.8% | 22.0% | 6.3% | 2.4% |
| neural | 0.1% | 7.3% | 0.2% | 56.7% |
| hybrid | 0.1% | 7.3% | 0.2% | 56.8% |
| hybrid-joint | 6.0% | 16.9% | 0.0% | 0.2% |
rule-onlyโ
Per-component F1โ
| Tag | P | R | F1 | TP | FP | FN |
|---|---|---|---|---|---|---|
| region | 96.9% | 84.1% | 90.1% | 2697 | 86 | 508 |
| house_number | 75.5% | 92.0% | 82.9% | 1602 | 520 | 140 |
| postcode | 98.8% | 65.4% | 78.7% | 1948 | 24 | 1032 |
| street | 72.6% | 71.2% | 71.9% | 2085 | 786 | 843 |
| locality | 83.4% | 57.0% | 67.8% | 1915 | 381 | 1442 |
| venue | 38.6% | 17.7% | 24.3% | 195 | 310 | 906 |
| country | 21.0% | 25.7% | 23.1% | 63 | 237 | 182 |
| unit | 0.9% | 20.0% | 1.7% | 1 | 115 | 4 |
| street_prefix | 0.0% | 0.0% | 0.0% | 0 | 0 | 10 |
| street_suffix | 0.0% | 0.0% | 0.0% | 0 | 0 | 2 |
| po_box | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| unit_designator | 0.0% | 0.0% | 0.0% | 0 | 115 | 0 |
| intersection_a | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| intersection_b | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| dependent_locality | 0.0% | 0.0% | 0.0% | 0 | 0 | 40 |
| level_designator | 0.0% | 0.0% | 0.0% | 0 | 1 | 0 |
| level | 0.0% | 0.0% | 0.0% | 0 | 1 | 0 |
| street_prefix_particle | 0.0% | 0.0% | 0.0% | 0 | 0 | 6 |
| cedex | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| attention | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
Calibrationโ
| Bucket | Total | Correct | Accuracy |
|---|---|---|---|
| conf > 0.9 | 946 | 835 | 88.3% |
| conf:0.7-0.9 | 1330 | 564 | 42.4% |
| conf:0.5-0.7 | 1199 | 0 | 0.0% |
| conf < 0.5 | 1060 | 0 | 0.0% |
Per-failure-classโ
| Class | Total | Exact Match | Rate |
|---|---|---|---|
| failure/tokenization-trap | 3 | 0 | 0.0% |
| kryptonite/place-shaped-venue | 6 | 0 | 0.0% |
| kryptonite/particle-honorific | 9 | 0 | 0.0% |
| normal | 4503 | 1389 | 30.8% |
| failure/street-locality-collision | 5 | 2 | 40.0% |
| kryptonite/place-name-venue | 10 | 5 | 50.0% |
| failure/ambiguous-locality | 4 | 3 | 75.0% |
| failure/numeric-chaos | 1 | 1 | 100.0% |
| kryptonite/disambiguation | 4 | 4 | 100.0% |
neuralโ
Per-component F1โ
| Tag | P | R | F1 | TP | FP | FN |
|---|---|---|---|---|---|---|
| region | 84.4% | 62.5% | 71.8% | 2004 | 371 | 1201 |
| locality | 58.5% | 20.0% | 29.9% | 673 | 477 | 2684 |
| country | 25.2% | 25.3% | 25.3% | 62 | 184 | 183 |
| dependent_locality | 1.1% | 27.5% | 2.2% | 11 | 962 | 29 |
| postcode | 25.0% | 0.8% | 1.6% | 25 | 75 | 2955 |
| house_number | 8.8% | 0.5% | 0.9% | 8 | 83 | 1734 |
| street | 10.0% | 0.1% | 0.3% | 4 | 36 | 2924 |
| street_prefix | 0.0% | 0.0% | 0.0% | 0 | 0 | 10 |
| street_suffix | 0.0% | 0.0% | 0.0% | 0 | 0 | 2 |
| po_box | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| unit | 0.0% | 0.0% | 0.0% | 0 | 0 | 5 |
| intersection_a | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| intersection_b | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| venue | 0.0% | 0.0% | 0.0% | 0 | 33 | 1101 |
| subregion | 0.0% | 0.0% | 0.0% | 0 | 287 | 0 |
| street_prefix_particle | 0.0% | 0.0% | 0.0% | 0 | 0 | 6 |
| cedex | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| attention | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
Calibrationโ
| Bucket | Total | Correct | Accuracy |
|---|---|---|---|
| conf > 0.9 | 2575 | 4 | 0.2% |
| conf:0.7-0.9 | 989 | 0 | 0.0% |
| conf:0.5-0.7 | 704 | 0 | 0.0% |
| conf < 0.5 | 267 | 0 | 0.0% |
Per-failure-classโ
| Class | Total | Exact Match | Rate |
|---|---|---|---|
| kryptonite/place-name-venue | 10 | 0 | 0.0% |
| failure/ambiguous-locality | 4 | 0 | 0.0% |
| failure/street-locality-collision | 5 | 0 | 0.0% |
| failure/tokenization-trap | 3 | 0 | 0.0% |
| kryptonite/place-shaped-venue | 6 | 0 | 0.0% |
| kryptonite/particle-honorific | 9 | 0 | 0.0% |
| failure/numeric-chaos | 1 | 0 | 0.0% |
| kryptonite/disambiguation | 4 | 0 | 0.0% |
| normal | 4503 | 4 | 0.1% |
hybridโ
Per-component F1โ
| Tag | P | R | F1 | TP | FP | FN |
|---|---|---|---|---|---|---|
| region | 84.4% | 62.6% | 71.9% | 2005 | 370 | 1200 |
| locality | 58.6% | 20.1% | 29.9% | 674 | 476 | 2683 |
| country | 25.2% | 25.3% | 25.3% | 62 | 184 | 183 |
| dependent_locality | 1.1% | 27.5% | 2.2% | 11 | 956 | 29 |
| postcode | 24.0% | 0.8% | 1.6% | 24 | 76 | 2956 |
| house_number | 9.2% | 0.5% | 0.9% | 8 | 79 | 1734 |
| street | 10.0% | 0.1% | 0.3% | 4 | 36 | 2924 |
| street_prefix | 0.0% | 0.0% | 0.0% | 0 | 0 | 10 |
| street_suffix | 0.0% | 0.0% | 0.0% | 0 | 0 | 2 |
| po_box | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| unit | 0.0% | 0.0% | 0.0% | 0 | 0 | 5 |
| intersection_a | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| intersection_b | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| venue | 0.0% | 0.0% | 0.0% | 0 | 33 | 1101 |
| subregion | 0.0% | 0.0% | 0.0% | 0 | 287 | 0 |
| street_prefix_particle | 0.0% | 0.0% | 0.0% | 0 | 0 | 6 |
| cedex | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| attention | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
Calibrationโ
| Bucket | Total | Correct | Accuracy |
|---|---|---|---|
| conf > 0.9 | 2581 | 4 | 0.2% |
| conf:0.7-0.9 | 987 | 0 | 0.0% |
| conf:0.5-0.7 | 701 | 0 | 0.0% |
| conf < 0.5 | 266 | 0 | 0.0% |
Per-failure-classโ
| Class | Total | Exact Match | Rate |
|---|---|---|---|
| kryptonite/place-name-venue | 10 | 0 | 0.0% |
| failure/ambiguous-locality | 4 | 0 | 0.0% |
| failure/street-locality-collision | 5 | 0 | 0.0% |
| failure/tokenization-trap | 3 | 0 | 0.0% |
| kryptonite/place-shaped-venue | 6 | 0 | 0.0% |
| kryptonite/particle-honorific | 9 | 0 | 0.0% |
| failure/numeric-chaos | 1 | 0 | 0.0% |
| kryptonite/disambiguation | 4 | 0 | 0.0% |
| normal | 4503 | 4 | 0.1% |
hybrid-jointโ
Per-component F1โ
| Tag | P | R | F1 | TP | FP | FN |
|---|---|---|---|---|---|---|
| house_number | 77.7% | 87.1% | 82.1% | 1518 | 436 | 224 |
| postcode | 86.2% | 68.9% | 76.6% | 2053 | 330 | 927 |
| region | 81.7% | 60.3% | 69.4% | 1933 | 433 | 1272 |
| locality | 71.3% | 45.0% | 55.2% | 1509 | 606 | 1848 |
| country | 12.6% | 12.2% | 12.4% | 30 | 208 | 215 |
| street | 3.5% | 3.2% | 3.4% | 95 | 2621 | 2833 |
| venue | 3.1% | 3.2% | 3.1% | 35 | 1094 | 1066 |
| dependent_locality | 0.6% | 15.0% | 1.2% | 6 | 922 | 34 |
| street_prefix | 0.0% | 0.0% | 0.0% | 0 | 0 | 10 |
| street_suffix | 0.0% | 0.0% | 0.0% | 0 | 0 | 2 |
| po_box | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| unit | 0.0% | 0.0% | 0.0% | 0 | 0 | 5 |
| intersection_a | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| intersection_b | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| subregion | 0.0% | 0.0% | 0.0% | 0 | 210 | 0 |
| street_prefix_particle | 0.0% | 0.0% | 0.0% | 0 | 0 | 6 |
| cedex | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
| attention | 0.0% | 0.0% | 0.0% | 0 | 0 | 1 |
Calibrationโ
| Bucket | Total | Correct | Accuracy |
|---|---|---|---|
| conf > 0.9 | 9 | 0 | 0.0% |
| conf:0.7-0.9 | 741 | 74 | 10.0% |
| conf:0.5-0.7 | 3413 | 188 | 5.5% |
| conf < 0.5 | 372 | 12 | 3.2% |
Per-failure-classโ
| Class | Total | Exact Match | Rate |
|---|---|---|---|
| kryptonite/place-name-venue | 10 | 0 | 0.0% |
| failure/ambiguous-locality | 4 | 0 | 0.0% |
| failure/street-locality-collision | 5 | 0 | 0.0% |
| failure/tokenization-trap | 3 | 0 | 0.0% |
| kryptonite/place-shaped-venue | 6 | 0 | 0.0% |
| kryptonite/particle-honorific | 9 | 0 | 0.0% |
| failure/numeric-chaos | 1 | 0 | 0.0% |
| kryptonite/disambiguation | 4 | 0 | 0.0% |
| normal | 4503 | 274 | 6.1% |