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: IndexError
Message: list index out of range
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1859, in _prepare_split_single
original_shard_lengths[original_shard_id] += len(table)
~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^
IndexError: list index out of range
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 1694, 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 1880, 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.
turn_id string | action_kind string | source string | stratum string | corpus_epoch int64 | prompt_tail string | max_tokens int64 | temperature float64 | n_parsed int64 | rollouts list |
|---|---|---|---|---|---|---|---|---|---|
Textualize__textual.5ffaabc2.pr_1352__8614fd71:13 | tool_call | swelego | null | 40 | our of
</tool_response><|im_end|>
<|im_start|>assistant
<think>
| 1,792 | 0.8 | 0 | [
{
"raw": "The bug is in `_merge_bindings` in `/testbed/src/textual/dom.py`.\n\nThe problem: `BINDINGS: ClassVar[list[BindingType]] = []` is defined on `DOMNode`. When a subclass doesn't define its own `BINDINGS`, `base.BINDINGS` resolves via attribute lookup to the nearest base class that *does* define `BINDING... |
adamchainz__apig-wsgi.36d7ca35.pr_93__5ef67762:12 | tool_call | scaleswe | null | 40 | ed: OK
</tool_response><|im_end|>
<|im_start|>assistant
<think>
| 1,792 | 0.8 | 0 | [
{
"raw": "Everything is working normally. Here's a summary of the changes:\n\n1. `src/apig_wsgi.py`:\n - Added a `DEFAULT_NON_BINARY_CONTENT_TYPE_PREFIXES` tuple containing `text/`, `application/json`, and `application/vnd.api+json`\n - `make_lambda_handler` now accepts `non_binary_content_type_prefixes=Non... |
aio-libs__aiohttp.4fe754a8.pr_7890__bdc18ece:5 | tool_call | swerebench_v2 | king_fail:0552 | 40 | s. -->
</tool_response><|im_end|>
<|im_start|>assistant
<think>
| 1,792 | 0.8 | 1 | [
{
"raw": "Let me understand the issue:\n\n1. In `WebSocketWriter._send_frame`, when compression is enabled (notakeover), `self._compressobj` is a shared `ZLibCompressor` instance.\n2. When `await compressobj.compress(message)` is called, if the data is larger than `max_sync_chunk_size`, it runs in the executor,... |
aiohttp.0bb95b19.pr_14123055__65176d1a:14 | bash | r2e_gym | king_fail:0857 | 40 | 439
440
</output><|im_end|>
<|im_start|>assistant
<think>
| 1,792 | 0.8 | 2 | [
{
"raw": "Next, I'll check whether there are any existing CRLF validation helpers in the codebase, for example in `web_response.py` or `helpers.py`.\n</think>\n\n```bash\ngrep -rn \"\\\\\\\\\\\\\\\\r\\\\\\\\\\\\\\\\n\\|'\\\\\\\\r\\\\\\\\n'\\|\\\"\\\\\\\\r\\\\\\\\n\\\"\" aiohttp/*.py | head -20\n```",
"finis... |
aiohttp.0bb95b19.pr_14123055__65176d1a:15 | bash | r2e_gym | king_fail:0857 | 40 | rt bool(resp)
</output><|im_end|>
<|im_start|>assistant
<think>
| 1,792 | 0.8 | 3 | [
{
"raw": "Alright, I'll write a fix. The plan:\n\n1. Change the signature of `link` to `Optional[StrOrURL] = None`.\n2. Inside `__init__`, normalize: if `link` is `None` or an empty string → `self._link = None`, and don't set the Link header. Otherwise, validate that it's a str or URL (a non-empty string), and ... |
aiohttp.28d5ecf1.pr_9298968__9d9ee77a:37 | bash | r2e_gym | completion:0465 | 40 | l file served
</output><|im_end|>
<|im_start|>assistant
<think>
| 1,792 | 0.8 | 3 | [
{
"raw": "Everything is working. Let me summarize the fixes:\n\n## Summary\n\n**Problem:** When a client sent `Accept-Encoding: gzip` and the corresponding `.gz` file was unavailable (e.g., deleted between the check and stat, or the stat mock raises OSError), `FileResponse.prepare()` would raise `FileNotFoundEr... |
aiohttp.77f39e11.pr_8855533__9d422a87:10 | tool_call | r2e_gym | king_fail:0417 | 40 | inue.]
</tool_response><|im_end|>
<|im_start|>assistant
<think>
| 1,792 | 0.8 | 1 | [{"raw":"Next, let's look at the continuation of the mixed binding test to understand what the expec(...TRUNCATED) |
alibaba__fastjson2.b194aeaf.pr_201__3edf1057:54 | tool_call | multiswe | king_recoverable:3279 | 40 | nore if not applicable.<|im_end|>
<|im_start|>assistant
<think>
| 1,792 | 0.8 | 1 | [{"raw":"The user wants me to implement the JSONB Spring Data Redis Serializer feature. Let me look (...TRUNCATED) |
app-sre__qontract-reconcile.97e75b09.pr_244__30f4a0d0:19 | tool_call | scaleswe | null | 40 | rge
OK
</tool_response><|im_end|>
<|im_start|>assistant
<think>
| 1,792 | 0.8 | 0 | [{"raw":"Everything is working. Let me summarize the changes.\n</think>\n\nDone. Both changes are im(...TRUNCATED) |
autobench_finance.185886cc.pr_16693458__f1ec2c84:3 | tool_call | affine_autobench | general:2720 | 40 | t": 8}
</tool_response><|im_end|>
<|im_start|>assistant
<think>
| 1,792 | 0.8 | 3 | [{"raw":"The Drive query for spreadsheets returned nothing. Maybe the spreadsheet is somewhere else,(...TRUNCATED) |
End of preview.
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
missing
Teacher rollouts (k=3, temperature 0.8, max_tokens 1792) with thought echo scores for
49,341 of the 49,341 Affine corpus-D turn_ids in
vuhaian/49k_missing (turn_ids.txt),
at corpus epoch 40 (manifest fe61418440d6, view duel_turns@v4).
Generation
- Teacher
Qwen/Qwen3.8-27B@1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0, vLLM 0.28.0, TP=1 x 32 replicas (4 x 8 H200) - Prompt
evalsrv.chat.gen_prompt(ends inside<think>); 3 samples per turn in onen=3request, max_tokens =[duel]max_thought_tokens 1024 + max_action_tokens 768 = 1792 - Split
evalsrv.chat.split_rollout: z = thought, y = action - Echo:
lp_thought= lpC(z|x), mean logprob per byte (VllmModel.score_thought);lp_own/lp_emptyare not computed (null)
Per turn: turn_id, action_kind, source, stratum, corpus_epoch, prompt_tail, max_tokens, temperature, n_parsed, rollouts[3]. Per rollout: raw (completion as sampled), reasoning,
content, z, y, parsed, finish_reason, prompt_tokens, completion_tokens,
think_closed, lp_thought, lp_own, lp_empty. Prompts are not stored.
Rows follow the order of turn_ids.txt.
Files
49k_missing_e40.jsonl: 49,341 turns49k_missing_e40.meta.json: teacher / sampling / echo / corpus stamps49k_missing_e40.errors.jsonl: 0 turn_ids without a row ({})
Stats
- 148,023 rollouts: 92.1% parsed, 89.7% closed
</think>, 12.5% hit max_tokens; 2,043 turns with 0/3 parsed - mean prompt 4,337 tokens, mean completion 513 tokens
- action_kind: bash 24,551, tool_call 15,097, text 8,674, terminus_json 880, boxed 139
- Downloads last month
- -