Buckets:
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| configs | 1 items | ||
| logbook | 9 items | ||
| outputs | 24 items | ||
| paper_source | 106 items | ||
| poster | 12 items | ||
| scripts | 7 items | ||
| BUNDLE_MANIFEST.md | 1.16 kB xet | 173f8c36 | |
| JOBS.md | 1.26 kB xet | 4e37f1d2 | |
| README.md | 2.42 kB xet | 1d9f746e | |
| RESULT_CRITERIA.md | 1.28 kB xet | 959b0bdd | |
| challenge_README.md | 21.1 kB xet | c7260330 | |
| poster_embed.html | 666 kB xet | a0ba1735 |
Reproduction: What Makes a Strong Model?
Independent reproduction of ICML 2026 paper #23301 / arXiv:2606.01292 / OpenReview ykWN4LG9vE.
The authors did not link runnable code in the paper or arXiv source as of 2026-07-21. This bundle therefore implements the diagonal spectral mechanisms from the paper and a scaled real-architecture proxy independently.
Scope
scripts/core_repro.py: exact diagonal population dynamics for Theorems 1, 3, and 5, plus a Monte Carlo teacher-SGD / population-student experiment for weak-to-strong early stopping.scripts/architecture_spectra.py: scaled Figure 2(c) proxy using 1,000 images fromdeedax/UTK-Face-Revisedand pretrained ResNet18, ResNet50, and ViT-B/16 features.scripts/spectrum_fit_diagnostics.py: log-log $R^2$ diagnostics for the persisted architecture spectra.paper_source/: official arXiv v1 source used to recover formulas and experiment details.outputs/: local smoke-test and downloaded Hugging Face Job results..trackio/logbook/: canonical challenge logbook.
The full UTKFace training panels and ImageNet-based Figure 3(c,d) were not rerun: the paper does not release code/checkpoints, and those panels require several full pretrained feature sweeps and training runs. The architecture experiment here is explicitly a scaled proxy, not a full replication.
Local rerun
uv venv .venv
UV_CACHE_DIR="$PWD/.uv-cache" uv pip install --python .venv/bin/python numpy
.venv/bin/python scripts/core_repro.py --output outputs/core --reps 64 --seed 23301
The real-architecture proxy is a PEP 723 script and can be run with:
uv run scripts/architecture_spectra.py --output outputs/architecture --samples 1000 --batch-size 32
Hugging Face runs and artifacts
- Results bucket: https://huggingface.co/buckets/SabaPivot/repro-what-makes-a-strong-model-results
- Jobs canary: https://huggingface.co/jobs/SabaPivot/6a5f1ee413e6ef894d549757
- Core T4 run: https://huggingface.co/jobs/SabaPivot/6a5f2044d09dc1f57c6bed22
- Architecture T4 first attempt (audited output-directory failure): https://huggingface.co/jobs/SabaPivot/6a5f205113e6ef894d549760
- Architecture T4 successful retry: https://huggingface.co/jobs/SabaPivot/6a5f2198d09dc1f57c6bed3c
- UTKFace dataset: https://huggingface.co/datasets/deedax/UTK-Face-Revised
All repository-specific generated files stay under this reproduction directory.
- Total size
- 7.38 MB
- Files
- 175
- Last updated
- Jul 21
- Pre-warmed CDN
- US EU US EU