Upload data/validation_report.txt with huggingface_hub
Browse files- data/validation_report.txt +67 -0
data/validation_report.txt
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
======================================================================
|
| 2 |
+
PatchJudge Validation Report
|
| 3 |
+
======================================================================
|
| 4 |
+
|
| 5 |
+
📊 Dataset: 160 examples
|
| 6 |
+
|
| 7 |
+
📈 Score Distribution:
|
| 8 |
+
Mean: 22.8
|
| 9 |
+
Median: 0.0
|
| 10 |
+
Std: 26.9
|
| 11 |
+
|
| 12 |
+
Score Distribution:
|
| 13 |
+
0-10: ████████████████████████████████████████████████████████████████████████████████████████ (88)
|
| 14 |
+
10-20: (0)
|
| 15 |
+
20-30: ████████ (8)
|
| 16 |
+
30-40: ██████ (6)
|
| 17 |
+
40-50: ███████████████████████ (23)
|
| 18 |
+
50-60: ███████████████ (15)
|
| 19 |
+
60-70: ██████████████ (14)
|
| 20 |
+
70-80: █████ (5)
|
| 21 |
+
80-90: █ (1)
|
| 22 |
+
90-100: (0)
|
| 23 |
+
|
| 24 |
+
🎯 METR Alignment:
|
| 25 |
+
Test-passing patches below 50.0: 65.0%
|
| 26 |
+
⚠️ Too harsh — scoring too many patches as not merge-worthy
|
| 27 |
+
|
| 28 |
+
🔀 Resolved vs Unresolved Separation:
|
| 29 |
+
Mean score (resolved): 35.6
|
| 30 |
+
Mean score (unresolved): 1.4
|
| 31 |
+
Separation: +34.2
|
| 32 |
+
Correlation: 1.000
|
| 33 |
+
|
| 34 |
+
🚨 Known-Bad Pattern Detection:
|
| 35 |
+
Detected: 50/50 (100.0%)
|
| 36 |
+
✅ Good detection rate
|
| 37 |
+
|
| 38 |
+
📐 Per-Dimension Scores:
|
| 39 |
+
correctness: mean=2.7 std=3.1 [0-9]
|
| 40 |
+
completeness: mean=2.0 std=2.3 [0-6]
|
| 41 |
+
code_quality: mean=2.4 std=2.9 [0-9]
|
| 42 |
+
non_regression_risk: mean=2.4 std=2.9 [0-9]
|
| 43 |
+
merge_readiness: mean=1.7 std=2.2 [0-8]
|
| 44 |
+
|
| 45 |
+
🏴 Most Common Flags:
|
| 46 |
+
9x partial_fix
|
| 47 |
+
8x missing_edge_cases
|
| 48 |
+
7x Limited edge case coverage
|
| 49 |
+
6x not_production_ready
|
| 50 |
+
6x missing_edge_case_handling
|
| 51 |
+
5x Style violations
|
| 52 |
+
5x minimal_test_coverage
|
| 53 |
+
4x style_violations
|
| 54 |
+
4x Fundamentally flawed approach
|
| 55 |
+
4x Poor code quality
|
| 56 |
+
|
| 57 |
+
⭐ Top 3 Patches:
|
| 58 |
+
80.5 django__django-11066 (CoderForge-Qwen3-32B, PASS)
|
| 59 |
+
75.0 django__django-11999 (CoderForge-Qwen3-32B, PASS)
|
| 60 |
+
74.0 django__django-12143 (CoderForge-Qwen3-32B, PASS)
|
| 61 |
+
|
| 62 |
+
💀 Bottom 3 Patches:
|
| 63 |
+
0.0 pydata__xarray-3151 (OpenHands-O1-reasoning-high, FAIL)
|
| 64 |
+
0.0 django__django-14792 (OpenHands-O1-reasoning-high, FAIL)
|
| 65 |
+
0.0 django__django-11848 (OpenHands-O1-reasoning-high, FAIL)
|
| 66 |
+
|
| 67 |
+
======================================================================
|