Call Neighbours Yourself: Graph Walks with Destination-Conditioned On-Policy Self-Distillation
Paper • 2608.29588 • Published
messages listlengths 1 1 | solution stringclasses 7
values | metadata unknown |
|---|---|---|
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>411</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>3</answer> to commit a category\n\nYou M... | {"ground_truth": 3, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2600</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>6</answer> to commit a category\n\nYou ... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2414</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou ... | {"ground_truth": 0, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1089</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>3</answer> to commit a category\n\nYou ... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>12</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou MA... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1681</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou ... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>24</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>3</answer> to commit a category\n\nYou MA... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1060</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>857</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>3</answer> to commit a category\n\nYou M... | {"ground_truth": 3, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2498</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>6</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2616</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou ... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>921</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou M... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>949</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>5</answer> to commit a category\n\nYou M... | {"ground_truth": 5, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>185</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou M... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2064</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>5</answer> to commit a category\n\nYou ... | {"ground_truth": 3, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>60</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou MA... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>83</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou MA... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1592</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou ... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1928</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>6</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1016</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>0</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1074</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou ... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1344</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>6</answer> to commit a category\n\nYou ... | {"ground_truth": 3, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2545</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou ... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2624</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1988</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>3</answer> to commit a category\n\nYou ... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2406</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>0</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2240</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou ... | {"ground_truth": 0, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>753</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>5</answer> to commit a category\n\nYou M... | {"ground_truth": 5, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1984</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1136</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2568</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2163</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>5</answer> to commit a category\n\nYou ... | {"ground_truth": 0, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1296</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1205</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>5</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2432</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou ... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1360</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou ... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2136</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou ... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1896</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>961</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou M... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2216</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou ... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1044</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1279</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>6</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1440</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou ... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1057</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2242</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou ... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1833</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1296</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou ... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1369</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>6</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1321</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>6</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1896</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou ... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1072</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>3</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1834</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>3</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1375</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>0</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1380</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou ... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1630</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>0</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1444</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou ... | {"ground_truth": 3, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1248</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>650</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>6</answer> to commit a category\n\nYou M... | {"ground_truth": 0, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1475</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou ... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1488</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>896</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou M... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1635</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>0</answer> to commit a category\n\nYou ... | {"ground_truth": 0, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1311</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>906</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>5</answer> to commit a category\n\nYou M... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1366</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>6</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1119</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>6</answer> to commit a category\n\nYou ... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2619</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>5</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1290</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>5</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1628</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou ... | {"ground_truth": 5, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>921</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>4</answer> to commit a category\n\nYou M... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2376</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2352</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>5</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1016</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>3</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1408</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>0</answer> to commit a category\n\nYou ... | {"ground_truth": 0, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1995</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou ... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>985</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou M... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>921</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou M... | {"ground_truth": 4, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2010</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>3</answer> to commit a category\n\nYou ... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1729</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou ... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>753</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>0</answer> to commit a category\n\nYou M... | {"ground_truth": 5, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2488</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>6</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1408</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>3</answer> to commit a category\n\nYou ... | {"ground_truth": 0, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>37</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou MA... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1784</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>0</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>312</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>6</answer> to commit a category\n\nYou M... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2216</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>6</answer> to commit a category\n\nYou ... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2377</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>904</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>5</answer> to commit a category\n\nYou M... | {"ground_truth": 5, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1171</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>5</answer> to commit a category\n\nYou ... | {"ground_truth": 5, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2177</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>3</answer> to commit a category\n\nYou ... | {"ground_truth": 5, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2189</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>5</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1272</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>0</answer> to commit a category\n\nYou ... | {"ground_truth": 5, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1371</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou ... | {"ground_truth": 3, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1954</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>3</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>947</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>0</answer> to commit a category\n\nYou M... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2641</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>5</answer> to commit a category\n\nYou ... | {"ground_truth": 5, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2011</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>1</answer> to commit a category\n\nYou ... | {"ground_truth": 1, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>2013</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>2</answer> to commit a category\n\nYou ... | {"ground_truth": 6, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>1408</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>0</answer> to commit a category\n\nYou ... | {"ground_truth": 0, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
[
{
"role": "user",
"content": "Classify the target paper into one of the 2 categories listed below.\n\nEach turn must look like one of:\n <thinking>...</thinking><walk>409</walk> to fetch a node's full text + its 1-hop neighbors\n <thinking>...</thinking><answer>3</answer> to commit a category\n\nYou M... | {"ground_truth": 2, "dataset_name": "cora", "task_type": "node_class", "label_names": ["Rule Learning", "Neural Networks", "Case-Based Reasoning", "Genetic Algorithms", "Learning Theory", "Reinforcement Learning", "Probabilistic Methods"]} | {} |
End of preview. Expand in Data Studio
CNY walk-ready graph reasoning data
Walk-ready data for CNY (Call Neighbours Yourself), the graph-walk reinforcement learning framework described in Call Neighbours Yourself: Graph Walks with Destination-Conditioned On-Policy Self-Distillation (EMNLP 2026), arXiv:2608.29588.
Models: Allen-UQ/CNY-7B,
Allen-UQ/CNY-14B.
This repository does not redistribute any graph dataset in its original form. It
provides the derived, prompt-rendered form in which each graph instance is presented
to the walk policy: an ego-node text, the label descriptions and one short preview
line per neighbour, with a neighbour's full text withheld until the model emits a
<walk> action.
Format
One JSON object per line, in the schema the training stack consumes directly
(input_key = messages, label_key = solution):
| field | type | content |
|---|---|---|
messages |
list | chat turns; the user turn carries the rendered walk prompt |
solution |
str | JSON string with ground_truth, dataset_name, task_type |
metadata |
dict | reserved, empty in this release |
from datasets import load_dataset
ds = load_dataset("Allen-UQ/CNY-data", "cora-7way", split="test")
Evaluation configs
Every directory carries the config_snapshot.yaml that generated it, so the exact
preview length, neighbour cap, topology radius and random state are recoverable.
| config | rows | n-way | source cache version |
|---|---|---|---|
cora-7way |
540 | all 7 | cora/06fc44e652981591 |
cora-2way |
540 | 2 | cora/9025a930a351fc1d |
wikics-10way |
2,340 | all 10 | wikics/d11d65bf1f380875 |
wikics-5way |
2,340 | 5 | wikics/d0e6c4699e60da6e |
products-10way |
3,000 | 10 | products_sub/8f7441753fd26449 |
products-5way |
3,000 | 5 | products_sub/9cde029277a0b020 |
products-full |
37,745 | n-way sampled at evaluation | products/2c35a69d89f14c18 |
fb15k237-10way |
20,466 | 10 | fb15k237_edge_tag/3a282e77d408bd39 |
expla-graph |
554 | 2 stances | expla_graph_walk/640b55c2e57ccda6 |
webqsp |
1,628 | open-ended | webqsp_walk/216e2599b263ef3a |
fb15k237-10way and expla-graph are the exact versions behind the corresponding
Table 1 entries of the paper. The Cora, WikiCS and Products configs are the versions
used by the paired multi-seed evaluation runs; products-full matches the 37,745-row
test split reported in the paper's dataset statistics.
Graphs
raw_datasets/<dataset>.pt holds the graphs a <walk> traverses. A prompt only
carries the ego-node text and neighbour previews, so the graph is required to reveal
a destination's full text during rollout.
| file | role |
|---|---|
citeseer pubmed photo computer history sportsfit instagram wn18rr_edge_tag |
training graphs |
cora wikics products products_sub fb15k237_edge_tag expla_graph_walk webqsp_walk |
evaluation graphs |
wikics_shuffle |
rewired control used by the topology-versus-semantics analysis |
products_sub_test_indices.json |
index defining the fixed Products subsets |
Training configs
train is the mixture the reported models were trained on. The other two expose its
two halves for analysis.
| config | rows | content |
|---|---|---|
train |
317,495 | the full 8-dataset mixture actually used for training |
train-node-mixture |
230,660 | its node-classification half, seven graphs |
train-wn18rr-edge |
86,835 | its relation-classification half, WN18RR |
Composition of train: node_class 230,660 (Sportsfit 103,834, Computer 52,336,
Photo 29,016, History 24,930, PubMed 11,830, Instagram 6,803, CiteSeer 1,911) and
relation_class 86,835 (WN18RR). The totals match the training splits in the paper's
dataset statistics table.
Provenance and licensing
Each config is a derivative of a published graph dataset. Copyright in the underlying node text remains with the original owners, and use of a config is governed by the licence of its source.
| config group | source dataset | original release | licence of source |
|---|---|---|---|
cora-* |
Cora | Sen et al., 2008 | academic use |
wikics-* |
WikiCS | Mernyei and Cangea, 2020 | derived from Wikipedia, CC BY-SA 3.0 |
products-* |
ogbn-products | Hu et al., 2020 (OGB) | OGB code MIT; underlying Amazon product data subject to its own terms |
fb15k237-10way |
FB15k-237 | Toutanova and Chen, 2015 | derived from Freebase, CC BY 2.5 |
expla-graph |
ExplaGraphs | Saha et al., 2021 | see original release |
webqsp |
WebQSP | Yih et al., 2016 | see original release |
train-node-mixture |
CiteSeer, PubMed, and the Amazon-derived Photo, Computer, History, Sportsfit, plus Instagram | respective authors | mixed; the Amazon-derived subsets carry the same terms as products-* |
train-wn18rr-edge |
WN18RR | Dettmers et al., 2018 | derived from WordNet, WordNet licence |
Users must satisfy the terms of the original sources. Anyone requiring a distribution
free of third-party text can instead rebuild every config from source: the random
state is fixed at 42 and construction is deterministic, so the config_snapshot.yaml
in each directory reproduces the same splits, neighbourhoods and previews.
Citation
@inproceedings{liu2026cny,
title = {Call Neighbours Yourself: Graph Walks with Destination-Conditioned On-Policy Self-Distillation},
author = {Yilun Liu and Boyu Luo and Yanran Tang and Ruihong Qiu and Zi Huang},
booktitle = {EMNLP},
year = {2026}
}
Please also cite the source dataset of any config used.
- Downloads last month
- 14