Hugging Face's logo

Datasets:
AweAI-Team
/
DeNovoSWE-Trajectory-Raw

Tasks:
Text Generation
ArXiv:
License:
Dataset card Data Studio Files
xet
 Community
1
Dataset Preview
Duplicate
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:    TypeError
Message:      Couldn't cast array of type
struct<total_expected: int64, passed_ptp_count: int64, failed_ptp_count_skipped: int64, passed: int64, failed: int64, errors: int64, pass_rate: double, num_test_files: int64, per_file: string, output: string, validate_run: bool, error: string, rejected_files: string, stderr: string>
to
{'total_expected': Value('int64'), 'passed_ptp_count': Value('int64'), 'failed_ptp_count_skipped': Value('int64'), 'passed': Value('int64'), 'failed': Value('int64'), 'errors': Value('int64'), 'pass_rate': Value('float64'), 'num_test_files': Value('int64'), 'per_file': Json(decode=True), 'output': Value('string'), 'validate_run': Value('bool')}
Traceback:    Traceback (most recent call last):
                File "/usr/local/lib/python3.12/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 611, in wrapped
                  for item in generator(*args, **kwargs):
                              ^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 310, in _generate_tables
                  self._cast_table(pa_table, json_field_paths=json_field_paths),
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 130, in _cast_table
                  pa_table = table_cast(pa_table, self.info.features.arrow_schema)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2369, in table_cast
                  return cast_table_to_schema(table, schema)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2303, in cast_table_to_schema
                  cast_array_to_feature(
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1852, in wrapper
                  return pa.chunked_array([func(chunk, *args, **kwargs) for chunk in array.chunks])
                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2059, in cast_array_to_feature
                  _c(array.field(name) if name in array_fields else null_array, subfeature)
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1854, in wrapper
                  return func(array, *args, **kwargs)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2149, in cast_array_to_feature
                  raise TypeError(f"Couldn't cast array of type\n{_short_str(array.type)}\nto\n{_short_str(feature)}")
              TypeError: Couldn't cast array of type
              struct<total_expected: int64, passed_ptp_count: int64, failed_ptp_count_skipped: int64, passed: int64, failed: int64, errors: int64, pass_rate: double, num_test_files: int64, per_file: string, output: string, validate_run: bool, error: string, rejected_files: string, stderr: string>
              to
              {'total_expected': Value('int64'), 'passed_ptp_count': Value('int64'), 'failed_ptp_count_skipped': Value('int64'), 'passed': Value('int64'), 'failed': Value('int64'), 'errors': Value('int64'), 'pass_rate': Value('float64'), 'num_test_files': Value('int64'), 'per_file': Json(decode=True), 'output': Value('string'), 'validate_run': Value('bool')}
              
              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 1361, in compute_config_parquet_and_info_response
                  parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
                                                                        ^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 940, in stream_convert_to_parquet
                  builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1683, in _prepare_split
                  for job_id, done, content in self._prepare_split_single(
                                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/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 dataset

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

instance_id
string
success
bool
score
float64
finish_reason
string
error
null
initial_messages
list
patch
string
trajectory
list
eval_result
dict
difficulty
float64
mewwts_addict_pr130
true
1
finish
null
[{"role":"system","content":"You are a Senior Software Engineer and Technical Lead. You are tasked w(...TRUNCATED)
"diff --git a/.gitignore b/.gitignore\nindex 919ffc5..f50365c 100644\n--- a/.gitignore\n+++ b/.gitig(...TRUNCATED)
[{"step":0,"action":{"type":"tool_call","content":null,"tool_calls":[{"id":"call_00_UvAPtF44MKrlUNi3(...TRUNCATED)
{"accepted":true,"score":1.0,"details":{"total_expected":120,"passed_ptp_count":120,"failed_ptp_coun(...TRUNCATED)
0.047231
pycompression_xopen_pr7
false
0.647059
finish
null
[{"role":"system","content":"You are a Senior Software Engineer and Technical Lead. You are tasked w(...TRUNCATED)
"diff --git a/.gitignore b/.gitignore\nindex f10536c..777fe03 100644\n--- a/.gitignore\n+++ b/.gitig(...TRUNCATED)
[{"step":0,"action":{"type":"tool_call","content":null,"tool_calls":[{"id":"call_00_ONpZCLax26uQ1Bp2(...TRUNCATED)
{"accepted":false,"score":0.6470588235,"details":{"total_expected":17,"passed_ptp_count":17,"failed_(...TRUNCATED)
0.170236
python-social-auth_social-app-django_pr812
false
0.971429
finish
null
[{"role":"system","content":"You are a Senior Software Engineer and Technical Lead. You are tasked w(...TRUNCATED)
"diff --git a/.gitignore b/.gitignore\nindex d1f0a81..432e27e 100644\n--- a/.gitignore\n+++ b/.gitig(...TRUNCATED)
[{"step":0,"action":{"type":"tool_call","content":null,"tool_calls":[{"id":"call_00_QLCQwwSKJLjwAwPe(...TRUNCATED)
{"accepted":false,"score":0.9714285714,"details":{"total_expected":70,"passed_ptp_count":70,"failed_(...TRUNCATED)
0.583124
python-trio_unasync_pr59
true
1
finish
null
[{"role":"system","content":"You are a Senior Software Engineer and Technical Lead. You are tasked w(...TRUNCATED)
"diff --git a/.gitignore b/.gitignore\nindex 2516c64..a72345d 100644\n--- a/.gitignore\n+++ b/.gitig(...TRUNCATED)
[{"step":0,"action":{"type":"tool_call","content":null,"tool_calls":[{"id":"call_00_OI7hunx65YfrIyTH(...TRUNCATED)
{"accepted":true,"score":1.0,"details":{"total_expected":12,"passed_ptp_count":12,"failed_ptp_count_(...TRUNCATED)
0.146443
zhanyong-wan_dongbei_pr64
false
0.703125
finish
null
[{"role":"system","content":"You are a Senior Software Engineer and Technical Lead. You are tasked w(...TRUNCATED)
"diff --git a/.gitignore b/.gitignore\nindex 61acd52..af9bf62 100644\n--- a/.gitignore\n+++ b/.gitig(...TRUNCATED)
[{"step":0,"action":{"type":"tool_call","content":null,"tool_calls":[{"id":"call_00_So2WvejVdpq7hVPj(...TRUNCATED)
{"accepted":false,"score":0.703125,"details":{"total_expected":64,"passed_ptp_count":64,"failed_ptp_(...TRUNCATED)
0.599187
mivek_python-metar-taf-parser_pr73
false
0.128834
finish
null
[{"role":"system","content":"You are a Senior Software Engineer and Technical Lead. You are tasked w(...TRUNCATED)
"diff --git a/.gitignore b/.gitignore\nindex d990c28..3461374 100644\n--- a/.gitignore\n+++ b/.gitig(...TRUNCATED)
[{"step":0,"action":{"type":"tool_call","content":null,"tool_calls":[{"id":"call_00_KiYm30rlhAY27g8i(...TRUNCATED)
{"accepted":false,"score":0.1288343558,"details":{"total_expected":163,"passed_ptp_count":163,"faile(...TRUNCATED)
0.691266
jaraco_path_pr237
true
1
finish
null
[{"role":"system","content":"You are a Senior Software Engineer and Technical Lead. You are tasked w(...TRUNCATED)
"diff --git a/.gitignore b/.gitignore\nindex eab7315..269c1e3 100644\n--- a/.gitignore\n+++ b/.gitig(...TRUNCATED)
[{"step":0,"action":{"type":"tool_call","content":null,"tool_calls":[{"id":"call_00_B33t8Ka8yqge3XPY(...TRUNCATED)
{"accepted":true,"score":1.0,"details":{"total_expected":106,"passed_ptp_count":106,"failed_ptp_coun(...TRUNCATED)
0.520729
sprymix_csscompressor_pr12
false
0.5
finish
null
[{"role":"system","content":"You are a Senior Software Engineer and Technical Lead. You are tasked w(...TRUNCATED)
"diff --git a/.gitignore b/.gitignore\nindex 461be8a..df4c8dc 100644\n--- a/.gitignore\n+++ b/.gitig(...TRUNCATED)
[{"step":0,"action":{"type":"tool_call","content":null,"tool_calls":[{"id":"call_00_c6u4Lwn0CWRYfTTH(...TRUNCATED)
{"accepted":false,"score":0.5,"details":{"total_expected":72,"passed_ptp_count":72,"failed_ptp_count(...TRUNCATED)
0.337079
warpnet_salt-lint_pr236
false
0.119048
finish
null
[{"role":"system","content":"You are a Senior Software Engineer and Technical Lead. You are tasked w(...TRUNCATED)
"diff --git a/.gitignore b/.gitignore\nindex 770072d..c05f54d 100644\n--- a/.gitignore\n+++ b/.gitig(...TRUNCATED)
[{"step":0,"action":{"type":"tool_call","content":null,"tool_calls":[{"id":"call_00_UiLprJ9iiLoxBNNi(...TRUNCATED)
{"accepted":false,"score":0.119047619,"details":{"total_expected":42,"passed_ptp_count":42,"failed_p(...TRUNCATED)
0.468788
keis_base58_pr63
true
1
finish
null
[{"role":"system","content":"You are a Senior Software Engineer and Technical Lead. You are tasked w(...TRUNCATED)
"diff --git a/.gitignore b/.gitignore\nindex 8d08b33..bed5568 100644\n--- a/.gitignore\n+++ b/.gitig(...TRUNCATED)
[{"step":0,"action":{"type":"tool_call","content":null,"tool_calls":[{"id":"call_00_12XCkegJqSbbzc46(...TRUNCATED)
{"accepted":true,"score":1.0,"details":{"total_expected":28,"passed_ptp_count":28,"failed_ptp_count_(...TRUNCATED)
0.0875
End of preview.

DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch

arXiv Hugging Face Datasets GitHub License

🔥 Highlights

  • 4,818 high-quality instances.
  • 11k filtered trajectories from 34k DeepSeek-v4-High trajectories.
  • Strong performance: 50% in BeyondSWE-Doc2Repo trained from Qwen3.5-35B-A3B.

📣 News

FAQ

  • For evaluation of DeNovoSWE-Data, you can use AweAgent and refer to this recipe.

📊 Data Format

Field Description
instance_id Unique identifier for each benchmark instance.
document Ground-truth documentation provided to the agent for repository reconstruction.
pypi_name PyPI package name used to enforce anti-cheating constraints during evaluation.
image_url URL of the Docker image configured for the environment.
user GitHub username or organization owning the repository.
repo Name of the target GitHub repository.
workdir Working directory path of the repository inside the Docker container.
unit_test List of all unit test identifiers.
test_patch Code patch for unit tests, applied during the evaluation phase.
test_binary_files Binary files used by unit tests that are unsuitable for standard text patching.

🤖 Results

DeNovoSWE-Agent

Key parameters can be seen below:

Parameter Value
Max turns 500
Max sequence length 256k
Temperature 1

📖 Citation

If you find this project useful for your research, please consider citing our paper:

@misc{zhao2026denovoswescalinglonghorizonenvironments,
      title={DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch}, 
      author={Jiale Zhao and Guoxin Chen and Fanzhe Meng and Wayne Xin Zhao and Ruihua Song and Ji-Rong Wen and Kai Jia},
      year={2026},
      eprint={2606.10728},
      archivePrefix={arXiv},
      primaryClass={cs.SE},
      url={https://arxiv.org/abs/2606.10728}, 
}

📄 License

This project is licensed under the CC BY 4.0 License - see the LICENSE file for details.

If you find this project useful, please consider giving it a ⭐ !
Downloads last month
104
Total file size:
24.7 GB

Collection including AweAI-Team/DeNovoSWE-Trajectory-Raw

Paper for AweAI-Team/DeNovoSWE-Trajectory-Raw