Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed
Error code: DatasetGenerationError
Exception: CastError
Message: Couldn't cast
uuid: string
agent_ref: struct<type: string, name: string>
child 0, type: string
child 1, name: string
pass_rate: double
pass_rate_total: int64
pass_rate_passed: int64
dataset: string
question: string
expected_answer: string
responses_create_params: struct<input: list<item: struct<role: string, content: string>>>
child 0, input: list<item: struct<role: string, content: string>>
child 0, item: struct<role: string, content: string>
child 0, role: string
child 1, content: string
verifier_metadata: struct<unit_tests: struct<inputs: list<item: string>, outputs: list<item: string>>>
child 0, unit_tests: struct<inputs: list<item: string>, outputs: list<item: string>>
child 0, inputs: list<item: string>
child 0, item: string
child 1, outputs: list<item: string>
child 0, item: string
hash_id: string
source: string
to
{'responses_create_params': {'input': List({'role': Value('string'), 'content': Value('string')})}, 'verifier_metadata': {'unit_tests': {'inputs': List(Value('string')), 'outputs': List(Value('string'))}}, 'hash_id': Value('string'), 'dataset': Value('string'), 'source': Value('string'), 'agent_ref': {'type': Value('string'), 'name': Value('string')}, 'pass_rate': Value('float64')}
because column names don't match
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1816, in _prepare_split_single
for key, table in generator:
^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 613, in wrapped
for item in generator(*args, **kwargs):
~~~~~~~~~^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 343, in _generate_tables
self._cast_table(pa_table, json_field_paths=json_field_paths),
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 132, in _cast_table
pa_table = table_cast(pa_table, self.info.features.arrow_schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2369, in table_cast
return cast_table_to_schema(table, schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2297, in cast_table_to_schema
raise CastError(
...<3 lines>...
)
datasets.table.CastError: Couldn't cast
uuid: string
agent_ref: struct<type: string, name: string>
child 0, type: string
child 1, name: string
pass_rate: double
pass_rate_total: int64
pass_rate_passed: int64
dataset: string
question: string
expected_answer: string
responses_create_params: struct<input: list<item: struct<role: string, content: string>>>
child 0, input: list<item: struct<role: string, content: string>>
child 0, item: struct<role: string, content: string>
child 0, role: string
child 1, content: string
verifier_metadata: struct<unit_tests: struct<inputs: list<item: string>, outputs: list<item: string>>>
child 0, unit_tests: struct<inputs: list<item: string>, outputs: list<item: string>>
child 0, inputs: list<item: string>
child 0, item: string
child 1, outputs: list<item: string>
child 0, item: string
hash_id: string
source: string
to
{'responses_create_params': {'input': List({'role': Value('string'), 'content': Value('string')})}, 'verifier_metadata': {'unit_tests': {'inputs': List(Value('string')), 'outputs': List(Value('string'))}}, 'hash_id': Value('string'), 'dataset': Value('string'), 'source': Value('string'), 'agent_ref': {'type': Value('string'), 'name': Value('string')}, 'pass_rate': Value('float64')}
because column names don't match
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1369, in compute_config_parquet_and_info_response
parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
~~~~~~~~~~~~~~~~~~~~~~~~~^
builder, max_dataset_size_bytes=max_dataset_size_bytes
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 948, in stream_convert_to_parquet
builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1683, in _prepare_split
for job_id, done, content in self._prepare_split_single(
~~~~~~~~~~~~~~~~~~~~~~~~~~^
gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
):
^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1869, in _prepare_split_single
raise DatasetGenerationError("An error occurred while generating the dataset") from e
datasets.exceptions.DatasetGenerationError: An error occurred while generating the datasetNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
responses_create_params dict | verifier_metadata dict | hash_id string | dataset string | source string | agent_ref dict | pass_rate float64 |
|---|---|---|---|---|---|---|
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"10000\n5000 3150\n5000 5000\n0 0\n5000 1050\n5000 3980\n5000 210\n5000 5000\n5000 5000\n0 0\n5000 2100\n5000 2100\n5000 2100\n29170\n100000 100000\n100000 100000\n100000 100000\n100000 100000\n100000 100000\n100000 100000\n100000 100000\n100000 100000\n100000 100000\n100000 10... | d33eaf0eb9ec3c1de407af5b5afa6c14 | nano_v3_sft_profiled_comp_coding_50tests | aizu | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"5\r\n2 6 5 6 2\r\n9\r\n1 5 10\r\n2 5\r\n1 1 3\r\n3 3 6\r\n3 8 9\r\n1 2 9\r\n2 3\r\n2 2\r\n2 4\r\n"
],
"outputs": [
"10\r\n7\r\n9\r\n7\r\n"
]
}
} | c34bdd6b163d29b1f7c5157908054810 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.75 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"5\r\n0 1 2 1 2\r\n",
"4\r\n0 1 2 3\r\n",
"1\r\n0\r\n",
"8\r\n3 1 4 0 4 2 4 5\r\n",
"100\r\n81 96 65 28 4 40 5 49 5 89 48 70 94 70 17 58 58 1 61 19 45 33 46 19 22 83 56 67 62 82 57 16 29 36 84 71 42 66 78 54 73 45 82 80 67 88 79 69 61 66 5 36 24 60 96 21... | 3b6a7a1f26cad9204a95f043507a099e | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"10\noxooxoxoox",
"3\nxoo",
"6\nxooxoo",
"10\nxooxoxooxo",
"10\nxxooxoxooo",
"10\noxoooxxoox",
"10\noxooooxoxx",
"10\noxoooxooxx",
"10\noxxoooxoox",
"10\nxxooooxxoo",
"10\noxoxoxoxoo",
"10\nooxoxoxoxo",
"10... | 0a29a431588876ba4f9dd2bbfcb528b5 | nano_v3_sft_profiled_comp_coding_50tests | atcoder | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.75 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"8 4\n4 2 3 1 5 1 6 4\n",
"100 3\n86 53 82 40 2 20 59 2 46 63 75 49 24 81 70 22 9 9 93 72 47 23 29 77 78 51 17 59 19 71 35 3 20 60 70 9 11 96 71 94 91 19 88 93 50 49 72 19 53 30 38 67 62 71 81 86 5 26 5 32 63 98 1 97 22 32 87 65 96 55 43 85 56 37 56 67 12 100 98 58 77 54 ... | 7a96a1cf6612a8ea00662c9dbfc93ba3 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"3 2\r\n0 2 1\r\n",
"5 1\r\n0 1 2 3 4\r\n",
"6 200000\r\n0 1 2 3 4 5\r\n",
"7 6\r\n3 2 4 1 0 5 6\r\n",
"1 1\r\n0\r\n",
"1 200000\r\n0\r\n",
"73 95\r\n4 53 37 9 45 54 16 34 12 10 13 24 2 36 33 48 50 43 15 11 47 42 46 30 27 52 67 72 66 19 56 61... | 47829176877708131d4d75d986508358 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.625 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"3\r\n-1 0\r\n0 2\r\n1 0\r\n",
"5\r\n1 0\r\n1 -1\r\n0 -1\r\n-1 0\r\n-1 -1\r\n",
"1\r\n-751115 -925948\r\n"
],
"outputs": [
"2\r\n",
"1\r\n",
"0\r\n"
]
}
} | eb3d65208f9a6f8f7ed8a3ad39b0e113 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.5 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"5\r\n5 2\r\n1 2 2 4 2\r\n4\r\n1 4 4 2\r\n6 2\r\n1 2 2 8 2 2\r\n2\r\n1 16\r\n8 3\r\n3 3 3 3 3 3 3 3\r\n4\r\n6 6 6 6\r\n8 3\r\n3 9 6 3 12 12 36 12\r\n16\r\n9 3 2 2 2 3 4 12 4 12 4 12 4 12 4 4\r\n8 3\r\n3 9 6 3 12 12 36 12\r\n7\r\n12 2 4 3 4 12 56\r\n"
],
"outputs": [
... | 57e671ec2e5a07c8b1af13ec58a8a147 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.625 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"6\r\n1 3\r\n2 3\r\n3 4\r\n4 5\r\n5 6\r\n",
"6\r\n1 3\r\n2 3\r\n3 4\r\n4 5\r\n4 6\r\n",
"7\r\n1 2\r\n2 7\r\n3 4\r\n4 7\r\n5 6\r\n6 7\r\n",
"3\r\n1 2\r\n2 3\r\n",
"5\r\n1 2\r\n2 3\r\n1 4\r\n3 5\r\n",
"4\r\n1 2\r\n2 3\r\n3 4\r\n",
"5\r\n1 2\r\n... | e2215e4c62c7ef79672c5abd2b3a894c | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.75 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"3\r\n0 2 7\r\n2 0 9\r\n7 9 0\r\n",
"3\r\n1 2 7\r\n2 0 9\r\n7 9 0\r\n",
"3\r\n0 2 2\r\n7 0 9\r\n7 9 0\r\n",
"3\r\n0 1 1\r\n1 0 1\r\n1 1 0\r\n",
"2\r\n0 0\r\n0 0\r\n",
"1\r\n0\r\n",
"1\r\n1\r\n",
"2\r\n0 1000000000\r\n1000000000 0\r\n",
... | 8a4f45ae16947b48702987dfafda82d9 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"4\n1 5 5 9\n1 6 6 5\n1 6 5 10\n2 6 5\n",
"1\n2 2 2\n",
"9\n1 0 0 1073741823\n1 1 1 987654321\n1 2 2 123456789\n2 0 0\n2 1073741822 1073741822\n2 987654323 987654323\n2 123456788 123456789\n2 86087500 86087503\n2 1032168868 1032168870\n",
"1\n2 0 2\n",
"... | f968a447d27b44e007cace53b47ef2e4 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"4\n1 1\n1 2\n2 1\n2 2\n",
"3\n1 1\n1 2\n2 1\n",
"2\n1 2\n2 3\n",
"1\n1000 3434\n",
"10\n4126 18194\n143965 18194\n32687 18194\n118527 18194\n186573 18194\n97223 18194\n179697 18194\n175536 18194\n107767 18194\n127019 18194\n",
"1\n200000 200000\n"... | 13ddaddc79a662b742794d0b2a58fcdf | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"abba\r\n",
"abacaba\r\n",
"qqqpvmgd\r\n",
"wyemcafatp\r\n"
],
"outputs": [
"6 1 0 0 \r\n",
"12 4 1 0 0 0 0 \r\n",
"11 3 0 0 0 0 0 0 \r\n",
"11 1 0 0 0 0 0 0 0 0 \r\n"
]
}
} | 9fd2971f53263e4ac3d661676097e564 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.625 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"6\r\n5\r\n1 5 6 3 4\r\n1\r\n5\r\n4\r\n1 6 3 9\r\n6\r\n1 13 9 3 7 2\r\n4\r\n2 2 2 2\r\n5\r\n4 5 2 2 3\r\n",
"2\r\n5\r\n1 5 6 3 4\r\n1\r\n5\r\n",
"3\r\n1\r\n1\r\n1\r\n1\r\n1\r\n1\r\n"
],
"outputs": [
"7\r\n0\r\n11\r\n23\r\n0\r\n5\r\n",
"7\r\n0\r\n... | ec873d7700032d79a8c2deb8eb8d24b5 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"00100010\r\n",
"1001011100\r\n",
"0\r\n",
"0110100101110110100110000\r\n",
"1011110000111101111111101011001111111101111000011110110101110011011000101100000010101011010101110001\r\n"
],
"outputs": [
"2 1 1 1 1 1 1 1\r\n",
"3 2 2 2 1 1... | df3ccd0f0819bd566da4dbf214f3e344 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.625 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"3\r\n5\r\n*..**\r\n.**..\r\n1\r\n*\r\n.\r\n3\r\n...\r\n***\r\n"
],
"outputs": [
"2\r\n0\r\n2\r\n"
]
}
} | 2a779c2982c4c23adf8818957be05cb1 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"4 3\n1\n2\n3",
"4 3\n2\n2\n4",
"6 4\n1\n2\n1\n2",
"4 3\n2\n2\n3",
"4 3\n2\n3\n4",
"5 3\n4\n2\n3",
"9 3\n4\n2\n3",
"4 3\n1\n2\n2",
"10 4\n4\n3\n1\n2",
"7 3\n2\n2\n4",
"6 3\n2\n3\n4",
"4 3\n3\n4\n4",
"9 3\n7... | 9771955b683bc20ab679f9169cba5642 | nano_v3_sft_profiled_comp_coding_50tests | aizu | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.5 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"2 3 13\n4 6\n2 1\n3 4\n",
"1 1234 5\n1\n1\n1\n",
"4 4 4\n0 1 3 2\n1 2 0 3\n2 3 1 0\n",
"1 443 5\n1\n1\n1\n",
"2 4 5\n1 1\n1 1\n1 2\n",
"2 3 13\n2 6\n0 1\n6 4\n",
"2 3 8\n2 6\n0 1\n6 4\n",
"3 2 2\n0 1 0\n0 0 0\n1 1 0\n",
"4 4 7\n0... | fe6f42e0482eda50d68b59838c0a44aa | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.75 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"5 1 2 0 1 2\r\n",
"1 1 1 -1 -1 2\r\n",
"1 1 1 1 1 0\r\n",
"2 2 1 -2 -2 5\r\n",
"1000000000 1 1 1 1 1000000000000000000\r\n",
"1000000000 1 2 -100 -100 1\r\n",
"3 2 2 -100 -100 2\r\n",
"1000000000 1000000000 1000000000 100 -100 10000000... | c0562ed226926927f4e0ba8480930ec2 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.625 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"4\r\n9840 9920\r\n9860 9980\r\n9930 10020\r\n10040 10090\r\n",
"4\r\n9900 9850\r\n9940 9930\r\n10000 10020\r\n10060 10110\r\n",
"1\r\n1 2\r\n",
"1\r\n2 1\r\n",
"2\r\n1 2\r\n3 4\r\n",
"2\r\n3 1\r\n4 2\r\n",
"3\r\n1 3\r\n2 5\r\n4 6\r\n",
... | ad8e0d0a01c474a28313af117d4a6b5e | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.75 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"10\n65\n010\n30\n95",
"10\n65\n111\n30\n47",
"10\n65\n010\n30\n100",
"10\n9\n110\n30\n95",
"10\n101\n110\n4\n48",
"10\n25\n010\n24\n9",
"10\n101\n001\n21\n3",
"10\n23\n010\n30\n164",
"10\n130\n100\n65\n101",
"10\n3\n111\n19... | 3f0878480054763ad523663d85c372c7 | nano_v3_sft_profiled_comp_coding_50tests | aizu | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"4 4\n5 2\n5 -3\n2 1\n4 -2\n",
"50 1000\n48 74\n684 197\n134 237\n37 -20\n79 37\n197 -212\n370 54\n577 -195\n329 -50\n963 -81\n85 135\n365 93\n293 -178\n503 -31\n126 -136\n709 -52\n118 153\n19 -260\n305 -260\n619 -35\n72 29\n352 163\n366 -175\n1186 101\n147 268\n235 -225\... | 3b8c7ba4ee4f3c615aeede669d5f4042 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"0 0\r\n0 1\r\n0 2\r\n1 0\r\n1 2\r\n2 0\r\n2 1\r\n2 2\r\n",
"0 0\r\n1 0\r\n2 0\r\n3 0\r\n4 0\r\n5 0\r\n6 0\r\n7 0\r\n",
"1 1\r\n1 2\r\n1 3\r\n2 1\r\n2 2\r\n2 3\r\n3 1\r\n3 2\r\n",
"0 0\r\n0 0\r\n0 0\r\n0 0\r\n0 0\r\n0 0\r\n0 0\r\n0 0\r\n",
"1000000 10000... | d2ee791ce83c903a4acd03f8f025c6dc | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"1\n1 114514\n",
"1\n1 500\n",
"1\n1 2887\n",
"1\n1 228\n",
"1\n1 182\n",
"1\n1 176923\n",
"1\n1 6\n",
"1\n1 391\n",
"1\n1 1904\n",
"1\n1 455\n",
"8\n2 2 4\n1 1\n1 4\n1 2\n2 2 6\n2 4 3\n1 2\n2 2 7\n",
"4\n1 2\n1 ... | e3ae28211140ea2a7ff7942eba7a6cbc | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"6\r\n1 10\r\n2 100\r\n3 1000\r\n1 10000\r\n2 100000\r\n3 1000000\r\n3\r\n1 3\r\n2 2 3\r\n2 1 2\r\n",
"3\r\n1 10\r\n2 100\r\n1 1000\r\n2\r\n2 1 2\r\n2 2 3\r\n",
"1\r\n1 1\r\n1\r\n1 1\r\n",
"2\r\n1 1\r\n2 2\r\n3\r\n1 1\r\n1 2\r\n2 1 2\r\n",
"4\r\n1 3\r\n2... | 547a5fd00f3f56556aa2930d1adaf8cf | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.625 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"5\r\n3\r\n2 3 1\r\n3 3 2\r\n8\r\n6 6 5 4 9 4 3 6\r\n7 6 10 6 9 6 6 8\r\n2\r\n4 2\r\n4 2\r\n3\r\n2 2 2\r\n3 3 3\r\n1\r\n5\r\n10\r\n",
"3\r\n7\r\n1 1 1 1 3 2 1\r\n3 2 2 3 4 4 2\r\n4\r\n1 1 1 1\r\n1 1 1 1\r\n1\r\n1000000000\r\n1000000000\r\n",
"1\r\n4\r\n1 1 3 3\r\n4 ... | 46d2e7151071b0d319f018dd0be17fcd | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.625 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"15 2\n4\nUURL\n8\nLRLLLLLLLL\n",
"1 1\n1\nU\n",
"7 10\n3\nLLULULLLR\n4\nLUUURLLLUURRU\n1\nULURR\n6\nLURLLLLRLR\n2\nULULURU\n7\nRRUUUURLRLR\n7\nUUURRULRRLUL\n7\nULLLRUULULR\n6\nUURRLL\n6\nRULUUULLRLLLUULL\n",
"4503599627370495 1\n2251799813685248\nLLLLLLLL\n",... | e31bc178d1e11544eb7d6dd5deb6f144 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.75 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"3\r\n1 2 4\r\n",
"4\r\n6 9 15 30\r\n",
"3\r\n1 1 1\r\n",
"2\r\n1 7\r\n",
"5\r\n8 6 7 3 7\r\n",
"10\r\n10 8 9 5 4 8 8 10 8 1\r\n",
"100\r\n95 94 31 65 35 95 70 78 81 36 69 97 39 28 89 62 36 23 35 21 36 11 65 39 13 34 79 87 91 70 43 82 24 97 6... | 88a2a2a4cd7c5fe3638ed2c08bf54cdb | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"3 1 3\r\n1 2\r\n2 3\r\n",
"3 1 3\r\n1 2\r\n1 3\r\n",
"61 26 12\r\n33 38\r\n32 8\r\n27 59\r\n1 21\r\n61 57\r\n61 22\r\n35 18\r\n61 14\r\n39 56\r\n50 10\r\n1 42\r\n21 43\r\n61 41\r\n31 30\r\n35 9\r\n23 28\r\n39 34\r\n39 4\r\n39 25\r\n27 60\r\n45 51\r\n1 11\r\n35 26\r... | 9690f044eb23978f6a4051cf92f15b21 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"2\r\n4\r\n4 8 9 6\r\n6\r\n2 1 7 4 0 0\r\n"
],
"outputs": [
"17\r\n12\r\n"
]
}
} | 7dbb88b6885afd72487eda7f6390d05e | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.75 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"7\r\n1\r\n2 2\r\n3\r\n2 8\r\n4 3\r\n5 2\r\n1\r\n200 200\r\n4\r\n1 20\r\n5 9\r\n3 179\r\n100 1\r\n2\r\n10 1\r\n1 18\r\n2\r\n1 1\r\n1 2\r\n3\r\n1 3\r\n1 1\r\n1 3\r\n"
],
"outputs": [
"2\r\n5\r\n299\r\n9\r\n9\r\n1\r\n1\r\n"
]
}
} | 2663e2395cf9bcafd9f7d905b470f614 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.75 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"1 1 1\r\n",
"6 5 7\r\n",
"12 12 24\r\n",
"21 32 10\r\n",
"30 12 20\r\n",
"589 505 50\r\n",
"499 599 100\r\n",
"4346 1611 880\r\n",
"532 1670 830\r\n",
"4066 1109 4375\r\n",
"1910 3945 1026\r\n",
"298 282 2458\r\... | a0ee8d5e33e931c27f4c86a3e3fffbd9 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"5\r\n3\r\n...\r\n7\r\n##....#\r\n7\r\n..#.#..\r\n4\r\n####\r\n10\r\n#...#..#.#\r\n",
"7\r\n3\r\n...\r\n3\r\n...\r\n3\r\n...\r\n3\r\n...\r\n3\r\n...\r\n3\r\n...\r\n3\r\n...\r\n"
],
"outputs": [
"2\r\n2\r\n5\r\n0\r\n2\r\n",
"2\r\n2\r\n2\r\n2\r\n2\r\n2\r... | a223c63651ab2108631c45c445444741 | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.75 |
{
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | {
"unit_tests": {
"inputs": [
"5 4\r\nabaca\r\n1 2\r\n1 3\r\n3 4\r\n4 5\r\n",
"6 6\r\nxzyabc\r\n1 2\r\n3 1\r\n2 3\r\n5 4\r\n4 3\r\n6 4\r\n",
"10 14\r\nxzyzyzyzqx\r\n1 2\r\n2 4\r\n3 5\r\n4 5\r\n2 6\r\n6 8\r\n6 5\r\n2 10\r\n3 9\r\n10 9\r\n4 6\r\n1 10\r\n2 8\r\n3 7\r\n",
"1 1\r\nf\r\n1 1\r\n"... | db5822e621148c380f103ee4340e65de | nano_v3_sft_profiled_comp_coding_50tests | codeforces | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.75 |
End of preview.
Nemotron-3-Nano-RL-Training-Blend
This dataset is a translated, parallel version of the nvidia/Nemotron-3-Nano-RL-Training-Blend dataset, excluding the instruction following subset.
Dataset Origin & Sampling
The original NVIDIA dataset blends multiple sources. For this parallel corpus, we sampled 1/3 of the datasets except for the instruction following subset where we extracted all unique prompts from the unsampled dataset to avoid duplicates:
| Subset / Source Dataset | Target Filename | English (en) |
Cantonese (yue) |
Traditional Chinese (zh-hk) |
|---|---|---|---|---|
| BytedTsinghua-SIA/DAPO-Math-17k (0.10 ratio) | nano_v3_sft_profiled_dapo17k.jsonl |
2,572 | 2,534 | 2,542 |
| Skywork/Skywork-OR1-RL-Data (0.12 ratio) | nano_v3_sft_profiled_skywork_no_omni.jsonl |
2,998 | 2,975 | 2,979 |
| nvidia/Nemotron-RL-knowledge-mcqa (0.20 ratio) | nano_v3_sft_profiled_stem_mcqa.jsonl |
2,639 | 2,850 | 2,690 |
| nvidia/Nemotron-RL-agent-workplace_assistant (0.20 ratio) | nano_v3_sft_profiled_workbench.jsonl |
990 | 990 | 990 |
| nvidia/Nemotron-RL-coding-competitive_coding (0.25 ratio) | nano_v3_sft_profiled_comp_coding_50tests.jsonl |
4,812 | 4,183 | 4,098 |
Languages
For each subset, files are provided in three parallel directories:
en/: English (Source / Cleaned)yue/: Cantonese (Translated)zh-hk/: Traditional Chinese (Hong Kong) (Translated)
The Law Filter (STEM MCQA Cleaning)
The original nvidia/Nemotron-RL-knowledge-mcqa dataset included multiple-choice questions from various general benchmarks. A significant number of these questions turned out to be related to US Law (e.g., Constitutional Law, Contracts, Civil Procedure, and Torts) rather than pure STEM knowledge.
To clean the dataset:
- We applied a keyword-based law filter (checking for terms like
刑事,法律,法例,憲法,州,合約,法院,聯邦,被告, etc.) on the translations. - Any entry that triggered this filter was dropped from the Cantonese and Traditional Chinese translations.
- To keep the three languages aligned, the corresponding English records for these law questions were also excluded.
- This process successfully filtered out 2,333 law questions, leaving exactly 2,639 clean STEM multiple-choice questions in the final parallel release of
stem_mcqa.
nvidia/Nemotron-RL-agent-workplace_assistant Processing
The original nvidia/Nemotron-RL-agent-workplace_assistant dataset features office-style agent tasks, such as retrieving emails, scheduling meetings, and managing calendars with tool-calling capabilities.
To optimize this subset:
- Deduplication: The raw dataset contained many duplicate user queries. We deduplicated the subset based on the user prompt, retaining only the 990 unique prompts (and 1 system prompt) in the final parallel release.
nvidia/Nemotron-RL-coding-competitive_coding Processing
The nvidia/Nemotron-RL-coding-competitive_coding subset consists of competitive programming questions.
To process and translate this subset:
- Deduplication: We extracted the core coding questions and deduplicated them down to 4,291 unique questions (out of 4,812 total records) to optimize translation.
- Cantonese Translation: The Cantonese translations were generated using the in-development model jed351/cantonese_llm_v2_chat_gsm8k_GRPO_Qwen3-30B-A3B-Think-2507.
- Traditional Chinese Translation: The Cantonese translations of the core questions were further translated into Traditional Chinese (
zh-hk) using the google/gemma-4-26B-A4B-it model on vLLM. - Rule-Based Quality Filtering: Competitive-programming statements contain structured data (large numbers, LaTeX math, variable names) that must survive translation unchanged. We ran an automated, rule-based quality check on every translation and dropped any record that failed a hard check — e.g. token-limit truncation, dropped large numbers, unbalanced LaTeX, non-Chinese output, or the model solving the problem in code instead of translating it. Filtering is per stage; because
zh-hkis translated fromyue, questions dropped at theyuestage are also dropped fromzh-hk. English (en) is the clean source and is retained in full. This removed 563 uniqueyuequestions and 636 uniquezh-hkquestions, leaving final parallel counts of 4,812en/ 4,183yue/ 4,098zh-hk.
- Downloads last month
- 61