Proofs, Formulas & Doctrine
Collection
Snapshot-indexed Lean 4 proofs, canonical formulas, doctrine, thesis, and the Ouroboros self-verifying-loop work. Claims apply only to recorded commit • 12 items • Updated
CARD honesty (SZL cookie): This Hub entry is a card / doctrine / kernel / witness surface. It does not claim production neural weights unless a MEASURED train receipt is linked below. States used:
NOT_TRAINED·CARD_ONLY·MEASURED·UNAVAILABLE·NOT_CLAIMED. Production promote requires StephenGO WEIGHT <model-id>. Soft Shield: Control before action. Evidence after.
Control before action. Evidence after.
Product · Proof · GitHub · HF org
szl-ouroboros has moved to the kernel repository
This model repository holds no loadable build and no weights. The kernels library
(0.16 and later) loads kernels only from the kernel repository:
https://huggingface.co/kernels/SZLHOLDINGS/szl-ouroboros
# pip install "kernels>=0.17.2" torch
from kernels import get_kernel
ouroboros = get_kernel("SZLHOLDINGS/szl-ouroboros", version=1, trust_remote_code=True)
The source of truth is szl-holdings/szl-ouroboros.
Its hf-kernel-publish workflow builds the kernel, verifies it through get_kernel, and
then updates this pointer. Commits of this model repository are not kernel revisions.
The provenance, audit and BOM records kept here describe earlier publications.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support