File size: 2,319 Bytes
8392c40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 | ---
license: mit
---
# SWE-Bench Trajectory Eval Bundle (v2)
Airgapped-ready bundle for the trajectory-probe downstream eval.
## Changes from v1
- **django dropped** (230 base_commits × 5 agents = 1139 trajectories removed).
django's blobs were too slow to prefetch at scale; the other 11 repos
give 1317 trajectories which is plenty.
- **Sparse-checkout blobs only**. For each (repo, base_commit), only the
files any trajectory's patch touches are fetched. Dramatically smaller
than the v1 "full-tree" approach; still enough for the graph encoder
to see the patched files + their containing package.
## Contents (570 MB compressed)
- `specs.jsonl`: 1317 SWE-Bench Verified agent trajectories (down from
2456). 46% resolved. 11 repos, 269 unique base_commits.
- `repos/`: 11 blobless clones with sparse-checkout already configured
per base_commit. Working trees on-disk reflect the UNION of touched
paths across all trajectories for each base_commit.
- `graphjepa/`: pipeline code (trajectory_pipeline with `extract_patch_paths`
and `set_sparse_paths`, trajectory_realize, trajectory_probe, checks).
- `harvest.log`.
## Dataset
| Repo | Trajs | Resolved |
|---|---|---|
| sympy/sympy | 370 | 48% |
| sphinx-doc/sphinx | 207 | 32% |
| matplotlib | 167 | 41% |
| scikit-learn | 158 | 70% |
| astropy | 110 | 42% |
| pydata/xarray | 108 | 51% |
| pytest-dev/pytest | 95 | 49% |
| pylint-dev/pylint | 49 | 22% |
| psf/requests | 38 | 61% |
| mwaskom/seaborn | 10 | 0% |
| pallets/flask | 5 | 80% |
| **total** | **1317** | **46%** |
## Downstream workflow (on airgapped big)
```bash
huggingface-cli download IDMedicine/code-graph-trajeval-v2 traj_full_bundle.tar.gz \
--local-dir outputs/traj_real
cd /opt/train/code-transformer/code-transformer
tar -xzf outputs/traj_real/traj_full_bundle.tar.gz
rsync -a traj_full/graphjepa/ graphjepa/
mkdir -p outputs/traj_real
cp traj_full/specs.jsonl outputs/traj_real/
mv traj_full/repos outputs/traj_real/repos
export BERT_MODEL_PATH=/opt/train/datasets/bert-base-uncased
GPUS=0,2,3,4,5,6,7 bash graphjepa/scripts/trajectory_full.sh
tail -f outputs/traj_real/logs/prebuild_shard*_gpu*.log
```
Because the clone already has the right blobs prefetched on laptop,
the airgapped big machine can checkout every base_commit without any
network access.
|