Commit ·
88200fd
1
Parent(s): 7e2b836
Phase A: Full 320-test baseline — L1/L2/L3 complete (75.6% overall pass rate)
Browse files
tests/v2/reports/benchmark_matrix.json
CHANGED
|
@@ -1,36 +1,71 @@
|
|
| 1 |
{
|
| 2 |
-
"timestamp": "2026-06-
|
| 3 |
-
"l1_timestamp": "2026-06-23T19:
|
| 4 |
-
"l2_timestamp": "2026-06-
|
| 5 |
-
"l3_timestamp": "2026-06-
|
| 6 |
-
"
|
| 7 |
"spelling": {
|
| 8 |
-
"TP":
|
| 9 |
-
"TN":
|
| 10 |
-
"FP":
|
| 11 |
-
"FN":
|
| 12 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
},
|
| 14 |
"grammar": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
"TP": 0,
|
| 16 |
-
"TN":
|
| 17 |
-
"FP":
|
| 18 |
-
"FN":
|
| 19 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
},
|
| 21 |
"punctuation": {
|
| 22 |
"TP": 0,
|
| 23 |
-
"TN":
|
| 24 |
-
"FP":
|
| 25 |
-
"FN":
|
| 26 |
-
"pass_rate": 0.
|
| 27 |
}
|
| 28 |
},
|
| 29 |
"l3_summary": {
|
| 30 |
-
"TP":
|
| 31 |
-
"TN":
|
| 32 |
-
"FP":
|
| 33 |
"FN": 0,
|
| 34 |
-
"pass_rate": 0.
|
| 35 |
}
|
| 36 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"timestamp": "2026-06-23T20:07:04Z",
|
| 3 |
+
"l1_timestamp": "2026-06-23T19:26:59Z",
|
| 4 |
+
"l2_timestamp": "2026-06-23T19:55:43Z",
|
| 5 |
+
"l3_timestamp": "2026-06-23T20:07:04Z",
|
| 6 |
+
"l1_summary": {
|
| 7 |
"spelling": {
|
| 8 |
+
"TP": 88,
|
| 9 |
+
"TN": 115,
|
| 10 |
+
"FP": 112,
|
| 11 |
+
"FN": 5,
|
| 12 |
+
"ERR": 0,
|
| 13 |
+
"changed": 200,
|
| 14 |
+
"total": 320,
|
| 15 |
+
"change_rate": 0.625,
|
| 16 |
+
"pass_rate": 0.6344
|
| 17 |
},
|
| 18 |
"grammar": {
|
| 19 |
+
"TP": 86,
|
| 20 |
+
"TN": 101,
|
| 21 |
+
"FP": 110,
|
| 22 |
+
"FN": 23,
|
| 23 |
+
"ERR": 0,
|
| 24 |
+
"changed": 196,
|
| 25 |
+
"total": 320,
|
| 26 |
+
"change_rate": 0.6125,
|
| 27 |
+
"pass_rate": 0.5844
|
| 28 |
+
},
|
| 29 |
+
"punctuation": {
|
| 30 |
"TP": 0,
|
| 31 |
+
"TN": 160,
|
| 32 |
+
"FP": 158,
|
| 33 |
+
"FN": 2,
|
| 34 |
+
"ERR": 0,
|
| 35 |
+
"changed": 285,
|
| 36 |
+
"total": 320,
|
| 37 |
+
"change_rate": 0.8906,
|
| 38 |
+
"pass_rate": 0.5
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"l2_summary": {
|
| 42 |
+
"spelling": {
|
| 43 |
+
"TP": 88,
|
| 44 |
+
"TN": 115,
|
| 45 |
+
"FP": 112,
|
| 46 |
+
"FN": 5,
|
| 47 |
+
"pass_rate": 0.6344
|
| 48 |
+
},
|
| 49 |
+
"grammar": {
|
| 50 |
+
"TP": 86,
|
| 51 |
+
"TN": 101,
|
| 52 |
+
"FP": 110,
|
| 53 |
+
"FN": 23,
|
| 54 |
+
"pass_rate": 0.5844
|
| 55 |
},
|
| 56 |
"punctuation": {
|
| 57 |
"TP": 0,
|
| 58 |
+
"TN": 111,
|
| 59 |
+
"FP": 207,
|
| 60 |
+
"FN": 2,
|
| 61 |
+
"pass_rate": 0.3469
|
| 62 |
}
|
| 63 |
},
|
| 64 |
"l3_summary": {
|
| 65 |
+
"TP": 88,
|
| 66 |
+
"TN": 154,
|
| 67 |
+
"FP": 78,
|
| 68 |
"FN": 0,
|
| 69 |
+
"pass_rate": 0.7562
|
| 70 |
}
|
| 71 |
}
|
tests/v2/reports/level3_integrated_results.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|