Datasets:
The dataset viewer is not available for this dataset.
Error code: JWTInvalidSignature
Exception: InvalidSignatureError
Message: Signature verification failed
Traceback: Traceback (most recent call last):
File "/src/libs/libapi/src/libapi/jwt_token.py", line 286, in validate_jwt
decoded = jwt.decode(
jwt=token,
...<2 lines>...
options=options,
)
File "/usr/local/lib/python3.14/site-packages/jwt/api_jwt.py", line 368, in decode
decoded = self.decode_complete(
jwt,
...<8 lines>...
leeway=leeway,
)
File "/usr/local/lib/python3.14/site-packages/jwt/api_jwt.py", line 265, in decode_complete
decoded = self._jws.decode_complete(
jwt,
...<3 lines>...
detached_payload=detached_payload,
)
File "/usr/local/lib/python3.14/site-packages/jwt/api_jws.py", line 270, in decode_complete
self._verify_signature(
~~~~~~~~~~~~~~~~~~~~~~^
signing_input,
^^^^^^^^^^^^^^
...<4 lines>...
options=merged_options,
^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "/usr/local/lib/python3.14/site-packages/jwt/api_jws.py", line 417, in _verify_signature
raise InvalidSignatureError("Signature verification failed")
jwt.exceptions.InvalidSignatureError: Signature verification failedNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
SCBench Problems
This dataset contains SlopCodeBench (SCBench) problem checkpoints for evaluating coding agents under iterative specification refinement.
Source repository: https://github.com/SprocketLab/scb-problems.git
Source revision: ba1f7fec544dae4ff274d2447d9b65aebfbc5196
Dataset summary
- Language subsets:
python,js,cpp,rust,java - Problems: 36 problems
- Rows: 980 rows
- Columns:
problem,Checkpoint number,language,difficulty,tags,instruction,tests
Rows per subset:
python: 196 rowsjs: 196 rowscpp: 196 rowsrust: 196 rowsjava: 196 rows
Category distribution:
- developer-tools: 8
- web: 7
- data-processing: 6
- cli-tools: 5
- algorithms: 2
- configuration-management: 2
- dsl: 2
- databases: 1
- file-systems: 1
- networking: 1
- simulation: 1
Difficulty distribution:
- Easy: 12
- Hard: 12
- Medium: 12
Using the tests field
Each row includes a tests value containing a complete Bash test runner
for that checkpoint. Save it as a file, then run it against a submission
directory whose contents implement the entry file named in the
instruction field.
Test script examples
Write and run one checkpoint from Python:
from pathlib import Path
import subprocess
from datasets import load_dataset
dataset = load_dataset("gabeorlanski/slopcodebench", "python", split="test")
row = dataset[0]
test_path = Path("test.sh")
test_path.write_text(row["tests"])
test_path.chmod(0o755)
subprocess.run(["bash", str(test_path), "/path/to/submission"], check=True)
Run a saved test script directly:
bash test.sh /path/to/submission
Use a local problems checkout to avoid cloning:
SCB_PROBLEMS_REPO=/path/to/scb-problems bash test.sh /path/to/submission
Keep the temporary workspace for debugging:
SCB_KEEP_WORKDIR=1 bash test.sh /path/to/submission
The runner creates a temporary workspace, copies the submission into it,
materializes the relevant checkpoint tests and static assets, installs
Python test dependencies in a virtual environment, and invokes pytest.
Set SCB_PROBLEMS_REPO to an existing problems checkout to
avoid cloning. Set SCB_KEEP_WORKDIR=1 to keep the temporary
workspace for debugging.
For cpp, rust, and java subsets, the runner compiles the declared
source file with g++, rustc, or javac before running the Python
test harness. The js subset expects node to be available.
- Downloads last month
- 31