Varshith dharmaj commited on
Upload datasets/demo_cases.json with huggingface_hub
Browse files- datasets/demo_cases.json +77 -77
datasets/demo_cases.json
CHANGED
|
@@ -1,78 +1,78 @@
|
|
| 1 |
-
{
|
| 2 |
-
"metadata": {
|
| 3 |
-
"version": "2.0",
|
| 4 |
-
"created": "2025-11-22",
|
| 5 |
-
"description": "Test cases for MVM² multimodal math verifier"
|
| 6 |
-
},
|
| 7 |
-
"cases": [
|
| 8 |
-
{
|
| 9 |
-
"id": 1,
|
| 10 |
-
"name": "Arithmetic Error",
|
| 11 |
-
"category": "arithmetic",
|
| 12 |
-
"problem": "Janet has 3 apples. She buys 2 more. She gives 1 away. How many does she have?",
|
| 13 |
-
"steps": [
|
| 14 |
-
"Janet starts with 3 apples",
|
| 15 |
-
"She buys 2 more: 3 + 2 = 5 apples",
|
| 16 |
-
"She gives 1 away: 5 - 1 = 4 apples"
|
| 17 |
-
],
|
| 18 |
-
"expected_verdict": "VALID",
|
| 19 |
-
"difficulty": "easy"
|
| 20 |
-
},
|
| 21 |
-
{
|
| 22 |
-
"id": 2,
|
| 23 |
-
"name": "Subtraction Error",
|
| 24 |
-
"category": "arithmetic",
|
| 25 |
-
"problem": "Calculate 10 - 3 + 2",
|
| 26 |
-
"steps": [
|
| 27 |
-
"10 - 3 = 7",
|
| 28 |
-
"7 + 2 = 9"
|
| 29 |
-
],
|
| 30 |
-
"expected_verdict": "VALID",
|
| 31 |
-
"difficulty": "easy"
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"id": 3,
|
| 35 |
-
"name": "Multiplication Error",
|
| 36 |
-
"category": "arithmetic",
|
| 37 |
-
"problem": "There are 5 boxes with 8 apples each. How many apples total?",
|
| 38 |
-
"steps": [
|
| 39 |
-
"Number of boxes = 5",
|
| 40 |
-
"Apples per box = 8",
|
| 41 |
-
"Total = 5 × 8 = 45"
|
| 42 |
-
],
|
| 43 |
-
"expected_verdict": "ERROR",
|
| 44 |
-
"error_type": "arithmetic_error",
|
| 45 |
-
"difficulty": "easy"
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"id": 4,
|
| 49 |
-
"name": "Complex Multi-Step",
|
| 50 |
-
"category": "word_problem",
|
| 51 |
-
"problem": "John has $50. He spends $12 on lunch and $8 on coffee. How much is left?",
|
| 52 |
-
"steps": [
|
| 53 |
-
"Starting amount = $50",
|
| 54 |
-
"Lunch cost = $12",
|
| 55 |
-
"Coffee cost = $8",
|
| 56 |
-
"Total spent = 12 + 8 = 20",
|
| 57 |
-
"Remaining = 50 - 20 = 30"
|
| 58 |
-
],
|
| 59 |
-
"expected_verdict": "VALID",
|
| 60 |
-
"difficulty": "medium"
|
| 61 |
-
},
|
| 62 |
-
{
|
| 63 |
-
"id": 5,
|
| 64 |
-
"name": "Division with Remainder",
|
| 65 |
-
"category": "arithmetic",
|
| 66 |
-
"problem": "Divide 17 candies equally among 5 children. How many does each get?",
|
| 67 |
-
"steps": [
|
| 68 |
-
"Total candies = 17",
|
| 69 |
-
"Number of children = 5",
|
| 70 |
-
"17 ÷ 5 = 3.4",
|
| 71 |
-
"Each child gets 3 candies",
|
| 72 |
-
"Remainder = 2 candies"
|
| 73 |
-
],
|
| 74 |
-
"expected_verdict": "VALID",
|
| 75 |
-
"difficulty": "medium"
|
| 76 |
-
}
|
| 77 |
-
]
|
| 78 |
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"version": "2.0",
|
| 4 |
+
"created": "2025-11-22",
|
| 5 |
+
"description": "Test cases for MVM² multimodal math verifier"
|
| 6 |
+
},
|
| 7 |
+
"cases": [
|
| 8 |
+
{
|
| 9 |
+
"id": 1,
|
| 10 |
+
"name": "Arithmetic Error",
|
| 11 |
+
"category": "arithmetic",
|
| 12 |
+
"problem": "Janet has 3 apples. She buys 2 more. She gives 1 away. How many does she have?",
|
| 13 |
+
"steps": [
|
| 14 |
+
"Janet starts with 3 apples",
|
| 15 |
+
"She buys 2 more: 3 + 2 = 5 apples",
|
| 16 |
+
"She gives 1 away: 5 - 1 = 4 apples"
|
| 17 |
+
],
|
| 18 |
+
"expected_verdict": "VALID",
|
| 19 |
+
"difficulty": "easy"
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"id": 2,
|
| 23 |
+
"name": "Subtraction Error",
|
| 24 |
+
"category": "arithmetic",
|
| 25 |
+
"problem": "Calculate 10 - 3 + 2",
|
| 26 |
+
"steps": [
|
| 27 |
+
"10 - 3 = 7",
|
| 28 |
+
"7 + 2 = 9"
|
| 29 |
+
],
|
| 30 |
+
"expected_verdict": "VALID",
|
| 31 |
+
"difficulty": "easy"
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"name": "Multiplication Error",
|
| 36 |
+
"category": "arithmetic",
|
| 37 |
+
"problem": "There are 5 boxes with 8 apples each. How many apples total?",
|
| 38 |
+
"steps": [
|
| 39 |
+
"Number of boxes = 5",
|
| 40 |
+
"Apples per box = 8",
|
| 41 |
+
"Total = 5 × 8 = 45"
|
| 42 |
+
],
|
| 43 |
+
"expected_verdict": "ERROR",
|
| 44 |
+
"error_type": "arithmetic_error",
|
| 45 |
+
"difficulty": "easy"
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"id": 4,
|
| 49 |
+
"name": "Complex Multi-Step",
|
| 50 |
+
"category": "word_problem",
|
| 51 |
+
"problem": "John has $50. He spends $12 on lunch and $8 on coffee. How much is left?",
|
| 52 |
+
"steps": [
|
| 53 |
+
"Starting amount = $50",
|
| 54 |
+
"Lunch cost = $12",
|
| 55 |
+
"Coffee cost = $8",
|
| 56 |
+
"Total spent = 12 + 8 = 20",
|
| 57 |
+
"Remaining = 50 - 20 = 30"
|
| 58 |
+
],
|
| 59 |
+
"expected_verdict": "VALID",
|
| 60 |
+
"difficulty": "medium"
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"id": 5,
|
| 64 |
+
"name": "Division with Remainder",
|
| 65 |
+
"category": "arithmetic",
|
| 66 |
+
"problem": "Divide 17 candies equally among 5 children. How many does each get?",
|
| 67 |
+
"steps": [
|
| 68 |
+
"Total candies = 17",
|
| 69 |
+
"Number of children = 5",
|
| 70 |
+
"17 ÷ 5 = 3.4",
|
| 71 |
+
"Each child gets 3 candies",
|
| 72 |
+
"Remainder = 2 candies"
|
| 73 |
+
],
|
| 74 |
+
"expected_verdict": "VALID",
|
| 75 |
+
"difficulty": "medium"
|
| 76 |
+
}
|
| 77 |
+
]
|
| 78 |
}
|