an-sub-acc-2026/weave-ccwm-qwen2.5-coder-7b-kl-lora
Updated • 30
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
messages: list<item: struct<role: string, content: string>>
child 0, item: struct<role: string, content: string>
child 0, role: string
child 1, content: string
program_id: string
trajectory_type: string
concurrency_pattern: string
nondeterminism: string
n_steps: int64
split_percent: int64
to
{'messages': List({'role': Value('string'), 'content': Value('string')}), 'concurrency_pattern': Value('string'), 'nondeterminism': Value('string'), 'program_id': Value('string'), 'split_percent': Value('int64')}
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
messages: list<item: struct<role: string, content: string>>
child 0, item: struct<role: string, content: string>
child 0, role: string
child 1, content: string
program_id: string
trajectory_type: string
concurrency_pattern: string
nondeterminism: string
n_steps: int64
split_percent: int64
to
{'messages': List({'role': Value('string'), 'content': Value('string')}), 'concurrency_pattern': Value('string'), 'nondeterminism': Value('string'), 'program_id': Value('string'), 'split_percent': Value('int64')}
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.
messages list | concurrency_pattern string | nondeterminism string | program_id string | split_percent int64 |
|---|---|---|---|---|
[
{
"role": "system",
"content": "You are a code execution simulator."
},
{
"role": "user",
"content": "You are reasoning about concurrent Go program execution.\n\nHere is a Go program:\n<program>\n// WEAVE_META\n// outcome: success\n// concurrency_pattern: channel\n// goroutine_count: 2\n// expec... | channel | low | 01_simple_channel | 25 |
[
{
"role": "system",
"content": "You are a code execution simulator."
},
{
"role": "user",
"content": "You are reasoning about concurrent Go program execution.\n\nHere is a Go program:\n<program>\n// WEAVE_META\n// outcome: success\n// concurrency_pattern: channel\n// goroutine_count: 2\n// expec... | channel | low | 01_simple_channel | 25 |
[
{
"role": "system",
"content": "You are a code execution simulator."
},
{
"role": "user",
"content": "You are reasoning about concurrent Go program execution.\n\nHere is a Go program:\n<program>\n// WEAVE_META\n// outcome: success\n// concurrency_pattern: channel\n// goroutine_count: 2\n// expec... | channel | low | 01_simple_channel | 25 |
[
{
"role": "system",
"content": "You are a code execution simulator."
},
{
"role": "user",
"content": "You are reasoning about concurrent Go program execution.\n\nHere is a Go program:\n<program>\n// WEAVE_META\n// outcome: success\n// concurrency_pattern: channel\n// goroutine_count: 2\n// expec... | channel | low | 01_simple_channel | 25 |
[
{
"role": "system",
"content": "You are a code execution simulator."
},
{
"role": "user",
"content": "You are reasoning about concurrent Go program execution.\n\nHere is a Go program:\n<program>\n// WEAVE_META\n// outcome: success\n// concurrency_pattern: channel\n// goroutine_count: 2\n// expec... | channel | low | 01_simple_channel | 25 |
[
{
"role": "system",
"content": "You are a code execution simulator."
},
{
"role": "user",
"content": "You are reasoning about concurrent Go program execution.\n\nHere is a Go program:\n<program>\n// WEAVE_META\n// outcome: success\n// concurrency_pattern: channel\n// goroutine_count: 2\n// expec... | channel | low | 01_simple_channel | 50 |
[
{
"role": "system",
"content": "You are a code execution simulator."
},
{
"role": "user",
"content": "You are reasoning about concurrent Go program execution.\n\nHere is a Go program:\n<program>\n// WEAVE_META\n// outcome: success\n// concurrency_pattern: channel\n// goroutine_count: 2\n// expec... | channel | low | 01_simple_channel | 50 |
[
{
"role": "system",
"content": "You are a code execution simulator."
},
{
"role": "user",
"content": "You are reasoning about concurrent Go program execution.\n\nHere is a Go program:\n<program>\n// WEAVE_META\n// outcome: success\n// concurrency_pattern: channel\n// goroutine_count: 2\n// expec... | channel | low | 01_simple_channel | 50 |
[
{
"role": "system",
"content": "You are a code execution simulator."
},
{
"role": "user",
"content": "You are reasoning about concurrent Go program execution.\n\nHere is a Go program:\n<program>\n// WEAVE_META\n// outcome: success\n// concurrency_pattern: channel\n// goroutine_count: 2\n// expec... | channel | low | 01_simple_channel | 50 |
[
{
"role": "system",
"content": "You are a code execution simulator."
},
{
"role": "user",
"content": "You are reasoning about concurrent Go program execution.\n\nHere is a Go program:\n<program>\n// WEAVE_META\n// outcome: success\n// concurrency_pattern: channel\n// goroutine_count: 2\n// expec... | channel | low | 01_simple_channel | 50 |
[
{
"role": "system",
"content": "You are a code execution simulator."
},
{
"role": "user",
"content": "You are reasoning about concurrent Go program execution.\n\nHere is a Go program:\n<program>\n// WEAVE_META\n// outcome: success\n// concurrency_pattern: channel\n// goroutine_count: 2\n// expec... | channel | low | 01_simple_channel | 75 |
End of preview.
Weave-Bench: Concurrent Go Execution Trace Benchmark Dataset
Weave-Bench is a benchmark corpus of 130 concurrent Go programs (26 hand-crafted, 38 synthetically generated, and 66 real-world concurrency bug kernels extracted from CockroachDB, Kubernetes, gRPC, etcd, etc.) and execution traces collected from multiple runs per program.
This dataset is used to train and evaluate execution-trace world models for concurrent Go programs, specifically next-scheduler-event distribution estimation and multi-step rollout coherence.
Structure
The dataset contains the following splits:
data/train.jsonl(Point-prediction fine-tuning - hand-crafted + generated programs)data/validation.jsonl(Held-out evaluation set - real-world concurrency bugs from production systems)data/train_trajectory.jsonl(Trajectory fine-tuning dataset)data/val_trajectory.jsonl(Trajectory validation dataset)data/train_dist.jsonl(Distribution estimation training split)data/val_dist.jsonl(Distribution estimation validation split)
Each trace includes Go scheduler events (GoStart, GoBlock, GoUnblock, GoCreate, GoEnd, GoSched) and reasoning states.
Citation
If you use this model, dataset, or codebase, please cite:
@misc{anon-artifacts,
author = {Anonymous},
title = {Weave: Dataset, Trained Adapters, and Tooling},
howpublished = {\url{https://github.com/an-sub-acc-2026/weave-submission} and \url{https://huggingface.co/datasets/an-sub-acc-2026/weave-bench}},
year = {2026}
}
- Downloads last month
- 771