| { |
| "total_grammar_fn": 17, |
| "category_counts": { |
| "PATCH_FAILURE": 13, |
| "FILTER_FAILURE": 2, |
| "MODEL_FAILURE": 2 |
| }, |
| "classifications": [ |
| { |
| "sample_id": "G001", |
| "input": "البنات ذهب إلى المدرسة", |
| "expected": "ذهبن/ذهبت", |
| "pipeline_output": "البنات ذهبن إلى المدرسة", |
| "classification": "PATCH_FAILURE", |
| "evidence": "Grammar patch accepted but final output doesn't match expected", |
| "filter_rejections": [], |
| "accepted_patches": 1 |
| }, |
| { |
| "sample_id": "G002", |
| "input": "الطلاب يذهب إلى الجامعة", |
| "expected": "يذهبون", |
| "pipeline_output": "الطلاب يذهبون إلى الجامعة", |
| "classification": "PATCH_FAILURE", |
| "evidence": "Grammar patch accepted but final output doesn't match expected", |
| "filter_rejections": [], |
| "accepted_patches": 1 |
| }, |
| { |
| "sample_id": "G003", |
| "input": "المهندسون حضر الاجتماع", |
| "expected": "حضروا", |
| "pipeline_output": "المهندسون حضرون الاجتماع", |
| "classification": "PATCH_FAILURE", |
| "evidence": "Grammar patch accepted but final output doesn't match expected", |
| "filter_rejections": [], |
| "accepted_patches": 1 |
| }, |
| { |
| "sample_id": "G004", |
| "input": "الرجال يعمل في المصنع", |
| "expected": "يعملون", |
| "pipeline_output": "الرجال يعملون في المصنع", |
| "classification": "PATCH_FAILURE", |
| "evidence": "Grammar patch accepted but final output doesn't match expected", |
| "filter_rejections": [], |
| "accepted_patches": 1 |
| }, |
| { |
| "sample_id": "G005", |
| "input": "النساء ذهب إلى السوق", |
| "expected": "ذهبن", |
| "pipeline_output": "النساء ذهبن إلى السوق", |
| "classification": "PATCH_FAILURE", |
| "evidence": "Grammar patch accepted but final output doesn't match expected", |
| "filter_rejections": [], |
| "accepted_patches": 1 |
| }, |
| { |
| "sample_id": "G006", |
| "input": "الأولاد لعب في الحديقة", |
| "expected": "لعبوا", |
| "pipeline_output": "الأولاد لعب في الحديقة", |
| "classification": "FILTER_FAILURE", |
| "evidence": "Rejected by: IVtoOOV", |
| "filter_rejections": [ |
| "IVtoOOV" |
| ], |
| "accepted_patches": 0 |
| }, |
| { |
| "sample_id": "G007", |
| "input": "المعلمات حضر الاجتماع", |
| "expected": "حضرن", |
| "pipeline_output": "المعلمات حضرن الاجتماع", |
| "classification": "PATCH_FAILURE", |
| "evidence": "Grammar patch accepted but final output doesn't match expected", |
| "filter_rejections": [], |
| "accepted_patches": 1 |
| }, |
| { |
| "sample_id": "G008", |
| "input": "الأطباء يعالج المرضى", |
| "expected": "يعالجون", |
| "pipeline_output": "الأطباء يعالجون المرضى", |
| "classification": "PATCH_FAILURE", |
| "evidence": "Grammar patch accepted but final output doesn't match expected", |
| "filter_rejections": [], |
| "accepted_patches": 1 |
| }, |
| { |
| "sample_id": "G009", |
| "input": "العمال بنى المبنى", |
| "expected": "بنوا", |
| "pipeline_output": "العمال بنى المبنى", |
| "classification": "MODEL_FAILURE", |
| "evidence": "Grammar model returned input unchanged", |
| "filter_rejections": [], |
| "accepted_patches": 0 |
| }, |
| { |
| "sample_id": "G010", |
| "input": "الطالبات كتب الواجب", |
| "expected": "كتبن", |
| "pipeline_output": "الطالبات كتبن الواجب", |
| "classification": "PATCH_FAILURE", |
| "evidence": "Grammar patch accepted but final output doesn't match expected", |
| "filter_rejections": [], |
| "accepted_patches": 1 |
| }, |
| { |
| "sample_id": "G011", |
| "input": "السيارة جميل جداً", |
| "expected": "جميلة", |
| "pipeline_output": "السيارة جميلة جداً", |
| "classification": "PATCH_FAILURE", |
| "evidence": "Grammar patch accepted but final output doesn't match expected", |
| "filter_rejections": [], |
| "accepted_patches": 1 |
| }, |
| { |
| "sample_id": "G012", |
| "input": "البنت ذكي في المدرسة", |
| "expected": "ذكية", |
| "pipeline_output": "البنت ذكية في المدرسة", |
| "classification": "PATCH_FAILURE", |
| "evidence": "Grammar patch accepted but final output doesn't match expected", |
| "filter_rejections": [], |
| "accepted_patches": 1 |
| }, |
| { |
| "sample_id": "G013", |
| "input": "الطالبة متفوق في دراسته", |
| "expected": "متفوقة/دراستها", |
| "pipeline_output": "الطالب متفوق في دراسته", |
| "classification": "PATCH_FAILURE", |
| "evidence": "Grammar patch accepted but final output doesn't match expected", |
| "filter_rejections": [], |
| "accepted_patches": 1 |
| }, |
| { |
| "sample_id": "G014", |
| "input": "المدينة كبير وواسع", |
| "expected": "كبيرة وواسعة", |
| "pipeline_output": "المدينة كبيرة وواسعة", |
| "classification": "PATCH_FAILURE", |
| "evidence": "Grammar patch accepted but final output doesn't match expected", |
| "filter_rejections": [], |
| "accepted_patches": 1 |
| }, |
| { |
| "sample_id": "G015", |
| "input": "الشمس مشرق اليوم", |
| "expected": "مشرقة", |
| "pipeline_output": "الشمس مشرقة اليوم", |
| "classification": "PATCH_FAILURE", |
| "evidence": "Grammar patch accepted but final output doesn't match expected", |
| "filter_rejections": [], |
| "accepted_patches": 1 |
| }, |
| { |
| "sample_id": "G022", |
| "input": "رأيت أخوك في المسجد", |
| "expected": "أخاك", |
| "pipeline_output": "رأيت أخوك في المسجد", |
| "classification": "MODEL_FAILURE", |
| "evidence": "Grammar model returned input unchanged", |
| "filter_rejections": [], |
| "accepted_patches": 0 |
| }, |
| { |
| "sample_id": "G028", |
| "input": "لم يفعلون الواجب بعد", |
| "expected": "يفعلوا", |
| "pipeline_output": "لم يفعلون الواجب بعد", |
| "classification": "FILTER_FAILURE", |
| "evidence": "Rejected by: IVtoOOV", |
| "filter_rejections": [ |
| "IVtoOOV" |
| ], |
| "accepted_patches": 0 |
| } |
| ] |
| } |
