Buckets:
24.9 MB
150 files
Updated 20 days ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| outputs | 47 items | ||
| poster | 13 items | ||
| scripts | 10 items | ||
| DEVIATIONS.md | 2.6 kB xet | b2383a12 | |
| FEASIBILITY_AND_EVIDENCE_PLAN.md | 8.05 kB xet | ace6176e | |
| MANIFEST_DIGEST.txt | 91 Bytes xet | 8b63612a | |
| POSTER_BUILD_NOTES.md | 1.22 kB xet | 13fe24cb | |
| README.md | 2.32 kB xet | 0ee975bc | |
| SHA256SUMS.json | 9 kB xet | c37cf294 | |
| validate_bundle.py | 1.03 kB xet | b9cc8f5d |
Reproduction bundle v1 — Stable Deep RL via Isotropic Gaussian Representations (arXiv:2602.19373, OpenReview gc7Gg18ejz)
Clean successor to v0 (removed 52 HF download-cache metadata/lock entries under
outputs/_dl/, incl. 25 zero-byte files; added integrity manifest, validator,
and figure-provenance manifest).
Contents
scripts/— all reproduction scripts (Claims 1–4 numerical checks, the self-containedcifar_repro.pyGPU grid,claim5_analyze.py, canonical-data builder)outputs/— per-claim raw evidence: 12 GPU-run CSVs + 12 covariance-spectra NPZs (claim5_gpu/), local-check CSVs/JSON, figures (PNG + self-contained HTML)poster/— gate-passing 60×36in poster:poster.html(source),poster_preview.pdf(print),poster_preview.png,poster_embed.html(logbook embed, 9 hotspots),GATE_REPORT.json(all 13 style rules enabled, zero warnings),style_check.json,FIGURE_PROVENANCE.json(every poster figure is REPRODUCTION-GENERATED — none are paper crops; each maps to its generating script, raw evidence, sha256, and natural px)FEASIBILITY_AND_EVIDENCE_PLAN.md,DEVIATIONS.md,POSTER_BUILD_NOTES.md
Integrity
SHA256SUMS.json— deterministic manifest (sorted relpaths → sha256) with entry/byte counts and the credential-scan resultMANIFEST_DIGEST.txt— sha256 ofSHA256SUMS.json(the artifact-version digest)validate_bundle.py— re-hashes every entry, flags missing/mismatched/extra files:python3 validate_bundle.py(exit 0 iff clean)
Excluded replaceable inputs (regeneration commands)
- CIFAR-10 canonical 10k subset:
hf download ProCreations/isogaussian-drl-repro cifar10k.npz --type datasetor rebuild from the md5-verified canonical tarball viascripts/build_canonical_npz.py - Paper PDF: https://arxiv.org/pdf/2602.19373v3
- Authors' code: https://github.com/asahebpa/IsoGaussian-DRL
Provenance
- GPU run (12 configs × 100 epochs): https://huggingface.co/jobs/ProCreations/6a587cef85d9643ce16d5eb3 (t4-small, 1h24m, COMPLETED, ≈$0.56; total paid spend incl. cpu-basic dry-run ≈$0.57)
- Raw results mirror: https://huggingface.co/datasets/ProCreations/isogaussian-drl-repro (
claim5_gpu/) - Intermediates: https://huggingface.co/buckets/ProCreations/isogaussian-repro-work
- Total size
- 24.9 MB
- Files
- 150
- Last updated
- Jul 16
- Pre-warmed CDN
- US EU US EU