| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| pages | 9 items | ||
| README.md | 1.24 kB xet | 14701b8d | |
| bucket-icon.svg | 413 Bytes xet | d4ec272e | |
| index.html | 1.83 kB xet | e96f68d8 | |
| logbook.css | 29.6 kB xet | 5fb6b340 | |
| logbook.js | 77.3 kB xet | 1834eba5 | |
| logbook.json | 2.15 kB xet | 8a49e8c4 | |
| style.css | 388 Bytes xet | d037bfaf | |
| trackio-logo-light.png | 30 kB xet | b97882f7 | |
| trackio-logo.png | 55.6 kB xet | 46a44770 | |
| trackio-wordmark-dark.png | 89.8 kB xet | 286a3107 |
Six Sinkhorn diffusion certificates
This frozen, unpublished package audits all six operative anchored claims for Sinkhorn Normalization of Diffusion Kernels (LJdacnMXkr, arXiv 2507.06161v2). The conservative prerelease forecast is 12/12; that is not an official score.
The evidence combines finite matrix identities for symmetric diagonal scaling, Gaussian/exponential refinement grids, an explicit 0.1% iteration audit, joint diffusion-axiom checks, three irregular data modalities, and a source-locked Stanford Armadillo spectral comparison. Eight destructive controls are executed, not merely described.
Run locally with CPU-only settings:
CUDA_VISIBLE_DEVICES='' PYTORCH_ENABLE_MPS_FALLBACK=0 \
OMP_NUM_THREADS=1 OPENBLAS_NUM_THREADS=1 MKL_NUM_THREADS=1 \
python reproduction/run_tests.py
Future artifact Bucket: https://huggingface.co/buckets/neonforestmist/sinkhorn-normalization-diffusion-kernels-repro-artifacts
The USE_IT_LOCK forbids publication or consumption until the user explicitly says USE IT.
- Total size
- 0 Bytes
- Files
- 11
- Last updated
- Jul 23
- Pre-warmed CDN
- US EU US EU