reasoning-gym
Collection
Datasets generated using https://github.com/open-thought/reasoning-gym (with Qwen3-instruct templates) • 15 items • Updated
data_source stringclasses 1
value | prompt listlengths 1 1 | ability stringclasses 1
value | reward_model dict | extra_info dict |
|---|---|---|---|---|
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n8 8 1 1 1 8 8 8 8 8 8 8 8 8\n8 8 1 9 1 8 8 8 8 8 8 8 8 8\n8 8 1 1 1 8 8 ... | reasoning | {
"ground_truth": {
"entry": {
"answer": "8 1 9 1 8 8 8 8 8 8 8 8 8\n8 1 1 1 8 8 8 8 8 8 8 8 8\n8 1 1 1 8 8 8 8 8 8 8 8 8\n8 8 8 8 8 8 8 8 8 8 8 8 8\n8 8 8 8 8 8 8 8 8 8 8 8 8\n8 8 8 8 8 8 8 8 8 8 8 8 8\n8 8 8 8 8 8 8 8 8 8 8 8 8\n8 8 8 8 8 8 8 8 8 8 8 8 8\n8 8 8 8 8 8 1 1 1 1 8 1 1\n8 8 8 8 8 8 1 1 1 1 8 1... | {
"index": 0,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n9 8 8 8 8 8 8 8 8 2\n9 8 8 8 8 8 8 8 8 2\n9 8 8 8 8 8 8 8 8 2\n9 8 0 8 8... | reasoning | {
"ground_truth": {
"entry": {
"answer": "4 8 8 8 8 8 8 8 8 6\n4 8 4 8 8 8 6 8 8 6\n4 8 8 8 4 8 8 8 8 6\n4 8 8 8 8 8 8 8 8 6\n4 8 8 4 8 8 8 8 8 6\n4 8 8 8 8 8 6 8 8 6\n4 8 8 4 8 8 8 8 8 6\n4 8 8 8 8 8 8 8 8 6\n4 8 8 8 8 6 8 8 6 6\n4 4 8 8 8 8 8 8 8 6",
"metadata": {
"difficulty": {
"... | {
"index": 1,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n3 3 4 4 4 3 3 3 3 3\n3 3 4 4 4 3 3 3 3 3\n3 3 4 4 4 3 4 4 3 3\n3 3 4 4 4... | reasoning | {
"ground_truth": {
"entry": {
"answer": "3 3 3 3 3 3 3 3 3 3 3 5 3 3 3 3 3 3 5 3 3 3 3\n3 3 3 3 4 4 4 3 3 3 3 5 3 3 4 4 4 3 5 3 3 3 3\n3 3 3 3 4 4 4 3 3 3 3 5 3 3 4 4 4 3 5 5 5 5 3\n3 3 3 3 4 4 4 3 3 3 3 5 3 3 3 3 3 3 5 5 5 5 3\n3 3 3 3 3 3 3 3 3 3 3 5 3 3 3 3 3 3 5 5 5 5 3\n3 3 3 3 3 3 3 3 3 3 3 5 3 3 3 3... | {
"index": 2,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n8 8 8 4 4 4 4 4 8 8 4 4\n8 4 8 4 4 4 4 4 8 4 4 4\n8 8 8 4 4 4 4 4 8 8 8 ... | reasoning | {
"ground_truth": {
"entry": {
"answer": "4 4 4 4 4 4 8 8 8 8 8 4 4 4 4 4\n8 8 8 8 4 4 8 4 4 8 4 4 4 4 4 4\n4 4 4 8 4 4 4 4 4 8 4 4 4 4 4 4\n4 4 4 4 4 4 4 4 8 8 8 8 8 8 8 4\n4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4\n5 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4\n5 5 5 5 4 4 4 4 4 4 4 4 4 4 4 4\n5 4 4 5 4 4 4 4 5 5 5 5 5 5 4 4\n5 ... | {
"index": 3,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n7 7 7 7 7 7 7 7 7 7 7 7 7 7\n7 7 7 7 7 7 1 1 7 7 7 7 7 7\n7 0 7 0 7 7 7 ... | reasoning | {
"ground_truth": {
"entry": {
"answer": "7 9 9\n9 9 9\n7 9 7",
"metadata": {
"difficulty": {
"mirrors_weights": [
0.2,
0.2,
0.2,
0.2,
0.2
],
"rotations_weights": [
0.25,
0.25,
... | {
"index": 4,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n2 2 2 2 2 2 2 2 2 2\n2 2 2 2 2 2 2 2 2 2\n2 2 2 2 2 2 2 2 2 2\n2 2 2 2 2... | reasoning | {
"ground_truth": {
"entry": {
"answer": "2 2 2 2 2 2 2 2 2 2\n2 2 2 2 0 2 0 2 2 2\n2 2 2 2 0 1 0 2 2 2\n2 2 0 0 0 1 0 0 0 2\n2 2 2 1 1 0 1 1 2 2\n2 2 0 0 0 1 0 0 0 2\n2 2 2 2 0 1 0 2 2 2\n2 2 2 2 0 2 0 2 2 2\n2 2 2 2 2 2 2 2 2 2\n2 2 2 2 2 2 2 2 2 2",
"metadata": {
"difficulty": {
"... | {
"index": 5,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n0 6 6 6 5 6\n6 6 6 6 6 6\n6 6 2 6 6 6\n6 6 6 6 6 6\n6 6 6 6 5 6\n6 6 6 6... | reasoning | {
"ground_truth": {
"entry": {
"answer": "9 3 3\n9 6 6\n1 0 0",
"metadata": {
"difficulty": {
"mirrors_weights": [
0.2,
0.2,
0.2,
0.2,
0.2
],
"rotations_weights": [
0.25,
0.25,
... | {
"index": 6,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n4 4 4 4 4 4 4 4 4 4\n4 4 4 4 4 4 4 8 8 4\n4 4 8 8 4 4 8 8 8 4\n4 8 8 8 4... | reasoning | {
"ground_truth": {
"entry": {
"answer": "4 4 4 4 4 4 4 4 4 4\n4 4 2 2 4 4 4 2 2 4\n4 1 1 2 1 4 1 1 2 1\n4 4 1 4 4 4 4 1 4 4\n4 4 4 4 4 4 4 4 4 4\n4 4 4 4 4 4 4 4 4 4\n4 4 2 2 4 4 4 4 4 4\n4 1 1 2 1 4 4 4 4 4\n4 4 1 4 4 4 4 4 4 4\n4 4 4 4 4 4 4 4 4 4",
"metadata": {
"difficulty": {
"... | {
"index": 7,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n9 9 7 7 9 9 9 9 9\n9 9 7 7 9 9 9 9 9\n9 7 9 9 9 9 9 9 9\n9 9 9 9 9 9 2 9... | reasoning | {
"ground_truth": {
"entry": {
"answer": "7 7 7\n7 9 7\n9 7 9\n7 7 7\n7 9 7\n9 7 9",
"metadata": {
"difficulty": {
"mirrors_weights": [
0.2,
0.2,
0.2,
0.2,
0.2
],
"rotations_weights": [
0.25,
... | {
"index": 8,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n0 0 0 0 0 0 0 0 0 0\n0 0 0 0 0 0 8 0 0 0\n0 0 8 0 0 0 0 0 0 0\n0 0 0 0 0... | reasoning | {
"ground_truth": {
"entry": {
"answer": "0 0 0 0 0 0 0 0 0 0\n0 0 0 0 0 0 0 0 0 0\n0 0 0 0 0 0 0 0 0 0\n0 0 0 0 0 0 0 0 0 0\n0 0 0 0 0 0 0 0 0 0\n0 0 0 8 8 0 0 0 0 0\n0 0 2 2 0 0 0 0 0 0\n0 8 2 2 8 0 0 0 0 0\n0 0 0 0 0 0 0 0 0 0\n0 0 0 0 0 0 0 0 0 0",
"metadata": {
"difficulty": {
"... | {
"index": 9,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n9 2 2 8\n2 9 8 2\n2 8 9 2\n8 2 2 9\n2 5 2 2\n2 5 2 2\n5 5 5 5\n2 5 2 2\n... | reasoning | {
"ground_truth": {
"entry": {
"answer": "2 3 3 3 2 2 2 2 2 2 2 2 2 3 3 3\n3 3 2 3 2 2 2 2 2 2 2 2 3 3 2 3\n3 3 2 3 2 2 2 2 2 2 2 2 3 3 2 3\n2 3 3 3 2 2 2 2 2 2 2 2 2 3 3 3\n2 2 2 2 2 9 9 9 2 9 9 9 2 2 2 2\n2 2 2 2 9 9 2 9 9 9 2 9 2 2 2 2\n2 2 2 2 9 9 2 9 9 9 2 9 2 2 2 2\n2 2 2 2 2 9 9 9 2 9 9 9 2 2 2 2\n2 ... | {
"index": 10,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2\n2 2 2 2 2 2 2 2 2 2 2 2 2 2... | reasoning | {
"ground_truth": {
"entry": {
"answer": "2 2 2 2 2 0 2 2 2 2 2 2 2 2 2 2 2 2 2 2\n2 2 2 2 0 0 0 2 2 2 2 2 2 2 2 2 2 2 2 2\n2 2 2 0 0 0 0 0 2 2 2 2 2 2 2 2 2 2 2 2\n2 2 7 7 7 7 7 7 7 2 2 2 2 2 2 2 2 2 2 2\n2 7 7 7 7 7 7 7 7 7 2 2 2 2 2 2 2 2 2 2\n7 7 7 7 7 7 7 7 7 7 7 2 2 2 2 2 2 2 2 2\n7 7 7 7 7 7 7 7 7 7 ... | {
"index": 11,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n1 1 1 1 1 1 1\n1 1 1 1 1 1 1\n1 1 1 1 1 1 1\n1 1 1 1 1 1 1\n1 1 1 6 1 1 ... | reasoning | {
"ground_truth": {
"entry": {
"answer": "1 1 1 1 1 9 1 1 1 1 1 1 1 9 1 1 1\n1 1 1 1 1 1 9 1 1 1 1 1 9 1 1 1 1\n1 1 1 1 1 1 1 9 1 1 1 9 1 1 1 1 1\n1 1 1 1 1 1 1 1 9 1 9 1 1 1 1 1 1\n1 1 1 1 1 1 1 1 1 9 1 1 1 1 1 1 1\n1 1 1 1 1 1 1 1 9 1 9 1 1 1 1 1 1\n1 1 1 1 1 1 1 9 1 1 1 9 1 1 1 1 1\n1 1 1 1 1 1 9 1 1 1 1... | {
"index": 12,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n5 5 5 5 5 0 0 0 0 5 5 5 5 5\n5 5 5 5 5 0 0 0 0 5 5 5 5 5\n5 5 5 5 5 0 0 ... | reasoning | {
"ground_truth": {
"entry": {
"answer": "5 5 5 5 5 5 5 5 5 5 5 5 5 5\n5 5 5 5 5 5 5 5 5 5 5 5 5 5\n5 5 5 5 5 5 5 5 5 5 5 5 5 5\n5 5 5 5 5 5 5 5 5 5 5 5 5 5\n5 5 5 5 5 5 5 5 5 5 5 5 5 5\n5 5 5 5 5 5 0 5 5 5 5 5 5 5\n5 0 5 5 5 5 0 5 5 5 5 0 5 0\n0 0 0 0 0 0 0 0 0 0 0 0 0 0\n0 0 0 0 0 0 0 0 0 0 0 0 0 0\n5 0 5... | {
"index": 13,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n7 7 1 7 7 7 1 7 7 7 7 7\n1 1 7 7 7 7 7 7 7 1 7 7\n7 7 7 7 7 7 7 1 1 7 7 ... | reasoning | {
"ground_truth": {
"entry": {
"answer": "7 7 7 1 7 7 7 1 7 7 7 1 7\n7 7 7 7 7 7 7 7 1 1 1 7 7\n7 7 7 1 1 7 1 7 7 7 7 1 7\n1 7 7 7 1 7 1 7 7 1 3 3 3\n3 3 3 3 3 3 3 3 3 3 3 1 7\n1 1 7 7 1 7 1 1 7 7 7 7 7\n7 7 1 1 7 7 7 1 7 7 7 1 7\n7 1 7 1 7 7 1 7 7 1 3 3 3\n7 7 7 7 7 1 7 1 3 3 3 7 7\n7 1 7 7 7 7 7 7 1 1 1 3... | {
"index": 14,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n1 8 8 1 1 2 2 2 2 2\n1 8 8 1 1 2 2 1 1 2\n1 1 1 1 5 2 2 2 2 2\n1 1 1 1 1... | reasoning | {
"ground_truth": {
"entry": {
"answer": "0 1 1 2 2 2 2 2 2 2\n1 0 1 2 6 6 6 2 2 2\n1 1 1 2 2 2 2 2 2 2\n1 1 1 1 1 1 1 1 1 1\n1 1 1 1 1 0 1 0 1 1\n1 1 2 2 2 2 2 1 1 0\n1 1 2 2 2 2 2 1 1 1\n1 1 2 2 5 2 2 1 1 1\n0 1 2 5 5 5 2 1 1 1\n1 1 2 2 2 2 2 1 1 0",
"metadata": {
"difficulty": {
"... | {
"index": 15,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n8 8 8 8 8 1 1\n8 8 8 8 8 1 1\n8 8 1 1 8 8 8\n8 8 1 1 8 8 8\n8 8 8 8 8 8 ... | reasoning | {
"ground_truth": {
"entry": {
"answer": "8 8 8 8 8 0 0\n8 8 8 8 8 0 0\n8 8 1 1 8 8 8\n8 8 1 1 8 8 8\n8 8 8 8 0 0 8\n8 8 8 8 0 0 8\n8 8 8 8 8 8 8\n8 1 1 8 8 8 8\n8 1 1 8 8 0 0\n8 8 8 8 8 0 0\n8 8 8 8 8 8 8\n8 8 8 8 1 1 8\n8 8 8 8 1 1 8\n8 0 0 8 8 8 8\n8 0 0 8 8 8 8",
"metadata": {
"difficulty"... | {
"index": 16,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n3 3 3 3 3 3 3 3 3 3\n3 3 3 3 3 3 3 3 3 3\n3 3 3 3 3 3 3 3 3 3\n3 3 3 3 3... | reasoning | {
"ground_truth": {
"entry": {
"answer": "5 3 3 4 3 3 3 3 3 3 3 3 3 3 3\n3 9 9 3 3 3 3 3 3 5 3 3 4 3 3\n3 9 9 3 3 3 3 3 3 3 9 9 3 3 3\n1 3 3 8 3 3 3 3 3 3 9 9 3 3 3\n3 3 3 5 3 3 4 3 3 1 3 3 8 3 3\n3 3 3 3 9 9 3 3 3 3 3 3 3 3 3\n3 3 3 3 9 9 3 3 3 3 3 3 3 3 3\n3 3 3 1 3 3 8 3 3 3 3 3 3 3 3\n3 3 3 3 3 3 3 3 3 ... | {
"index": 17,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n6 6 6 6 3 6 6 6 6 6\n6 6 1 6 6 6 6 6 6 6\n6 6 6 6 6 6 6 6 5 6\n6 6 6 6 6... | reasoning | {
"ground_truth": {
"entry": {
"answer": "3 5 0\n2 0 4\n9 1 3",
"metadata": {
"difficulty": {
"mirrors_weights": [
0.2,
0.2,
0.2,
0.2,
0.2
],
"rotations_weights": [
0.25,
0.25,
... | {
"index": 18,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n9 8 8 8 8 2 8 8 8 8 8 8 8\n8 8 8 8 2 2 8 8 8 8 8 8 8\n8 8 2 1 2 8 8 8 8 ... | reasoning | {
"ground_truth": {
"entry": {
"answer": "0 0 0 0 0 0 0 6 9 9 9 9 9\n0 0 0 0 0 0 0 6 6 9 9 9 9\n0 0 0 0 0 0 0 0 6 9 9 9 9\n6 6 6 6 6 6 6 6 6 6 6 6 9\n9 9 9 9 9 6 4 4 4 4 4 6 9\n9 9 9 9 9 6 6 6 4 4 4 6 9\n9 9 9 9 9 9 9 6 4 4 4 6 9\n9 9 9 9 9 9 9 6 4 4 4 6 9\n9 9 9 9 9 9 9 6 4 4 4 6 9\n3 3 3 9 9 9 6 6 4 4 6 6... | {
"index": 19,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9\n9 9 9 9 9 9 9 9 9 5 9 9 9 9 9 9 9 9... | reasoning | {
"ground_truth": {
"entry": {
"answer": "5 9 5 9 8 9 8\n5 5 5 9 8 8 8\n9 5 9 9 8 9 8\n9 9 9 9 9 9 9\n7 7 7 9 0 9 9\n9 7 7 9 9 0 0\n9 7 9 9 9 0 9",
"metadata": {
"difficulty": {
"mirrors_weights": [
0.2,
0.2,
0.2,
0.2,
0.2
... | {
"index": 20,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n8 8 8 8 8 8 8 8 8 8 8 8 8 8 8\n8 8 7 7 8 8 8 8 8 0 0 0 0 0 8\n8 8 8 8 8 ... | reasoning | {
"ground_truth": {
"entry": {
"answer": "2 2 2 2 2 2 9 7 3 3\n2 2 2 2 2 2 9 7 7 7\n2 2 2 2 2 2 9 9 9 9\n2 2 2 2 2 2 9 9 9 9\n2 2 2 2 2 2 2 2 2 2\n2 2 2 2 2 2 2 2 2 2",
"metadata": {
"difficulty": {
"mirrors_weights": [
0.2,
0.2,
0.2,
0... | {
"index": 21,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n6 6 6 5 6 6 6 5 6 6 6 5 6 6 6\n6 9 6 5 6 6 6 5 6 6 6 5 6 6 6\n6 9 6 5 6 ... | reasoning | {
"ground_truth": {
"entry": {
"answer": "6 6 4\n6 4 4\n4 4 4\n6 4 4\n6 6 4\n6 4 4\n9 9 9\n6 9 9\n6 6 9\n6 9 9\n9 9 9\n6 9 9\n6 6 9",
"metadata": {
"difficulty": {
"mirrors_weights": [
0.2,
0.2,
0.2,
0.2,
0.2
],
... | {
"index": 22,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n0 0 0 0 0 0 0 0 0 0 0\n0 1 0 0 0 0 2 0 0 0 0\n1 1 1 0 0 0 0 0 0 0 0\n1 0... | reasoning | {
"ground_truth": {
"entry": {
"answer": "0 5 5\n5 5 5\n5 0 0\n0 7 7\n7 7 7\n7 0 0\n0 2 2\n2 2 2\n2 0 0\n0 4 4\n4 4 4\n4 0 0",
"metadata": {
"difficulty": {
"mirrors_weights": [
0.2,
0.2,
0.2,
0.2,
0.2
],
... | {
"index": 23,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n2 2 2 2 2\n2 2 2 2 2\n2 1 2 1 2\n2 9 2 9 2\n9 9 9 9 9\nOutput:\n2 2 2 2 ... | reasoning | {
"ground_truth": {
"entry": {
"answer": "2 2 2 2 2\n2 2 2 2 2\n2 2 2 2 2\n9 2 9 2 2\n1 9 1 9 9",
"metadata": {
"difficulty": {
"mirrors_weights": [
0.2,
0.2,
0.2,
0.2,
0.2
],
"rotations_weights": [
... | {
"index": 24,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n1 1 1 6 6 6 6 6 1 1 6 1 1 1 1 6\n1 1 6 1 6 1 6 1 1 1 1 1 1 1 6 1\n6 1 6 ... | reasoning | {
"ground_truth": {
"entry": {
"answer": "1 7 1 1 1 1 1 1 7 7 1 1 7 7 7 1 1 1\n1 1 1 1 1 7 1 1 7 1 1 1 5 0 0 5 0 7\n1 7 1 1 7 1 1 7 7 7 1 1 0 5 5 0 0 1\n1 7 1 7 7 7 7 7 7 1 1 1 1 1 1 1 1 1\n7 7 7 7 1 1 7 1 7 7 1 7 1 1 1 7 7 1\n1 1 1 1 7 1 1 7 0 0 5 0 7 1 7 7 7 7\n1 1 1 1 7 7 1 7 0 0 0 0 7 1 1 1 1 1\n7 1 7 7... | {
"index": 25,
"source_dataset": "arc_agi",
"split": "train"
} |
reasoning_gym | [
{
"content": "<|im_start|>system\nYou are a helpful assistant. Think step by step, then answer.<|im_end|>\n<|im_start|>user\nFind the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n9 0 9 0 0 4 0 0 0 5 0 0 0 0 6\n0 9 0 0 4 ... | reasoning | {
"ground_truth": {
"entry": {
"answer": "9 0 9 0 0 4 0 0 5 5 5 0 6 6 0\n9 0 9 0 4 4 4 0 0 5 0 0 0 0 6\n9 0 9 0 0 4 0 0 5 5 0 0 6 6 0",
"metadata": {
"difficulty": {
"mirrors_weights": [
0.2,
0.2,
0.2,
0.2,
0.2
],
... | {
"index": 26,
"source_dataset": "arc_agi",
"split": "train"
} |
End of preview. Expand in Data Studio
RLVR generated dataset
Procedural rows from reasoning-gym, formatted for verl GRPO.
Build metadata
{
"config": "/home/owais/Projects/rlvr/rlvr/configs/datasets/arc_agi-instruct.yaml",
"template_type": "qwen-instruct",
"developer_prompt": null,
"data_source": "reasoning_gym",
"default_extract": "answer_tag",
"train_rows": 100000,
"test_rows": 4096,
"train_seed": 42,
"test_seed": 43,
"tasks": {
"arc_agi": {
"weight": 1,
"config": {}
}
},
"reasoning_gym_version": "0.1.19"
}
- Downloads last month
- 76