Pith Number

pith:NOPV3HN2

pith:2026:NOPV3HN2HREVXAEXB7O6ZM5XUJ

not attested not anchored not stored refs pending

Adaptive Domain Models: Bayesian Evolution, Warm Rotation, and Principled Training for Geometric and Neuromorphic AI

Houston Haynes

Composing dimensional types, hypergraphs, and posit arithmetic produces training with memory bounded to twice inference while preserving grades and exact gradients.

arxiv:2603.18104 v5 · 2026-03-18 · cs.AI · cs.DC · cs.LG · cs.NE

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{NOPV3HN2HREVXAEXB7O6ZM5XUJ}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Their composition enables depth-independent training memory bounded to approximately twice the inference footprint, grade-preserving weight updates, and exact gradient accumulation, applicable uniformly to loss-function-optimized and spike-timing-dependent neuromorphic models.

C2weakest assumption

That the three prior results (Dimensional Type System, Program Hypergraph, and b-posit 2026 standard) compose without loss of the stated invariants and that the b-posit format is tractable on conventional hardware targets.

C3one line summary

The paper claims that composing the Dimensional Type System, Program Hypergraph, and b-posit 2026 standard yields depth-independent training memory at ~2x inference, grade-preserving updates, Bayesian distillation for domain adaptation, and warm rotation for uninterrupted deployment.

Formal links

2 machine-checked theorem links

Cited by

3 papers in Pith

Negative and Fractional Types in the Fidelity Framework

Fixed-Point Scaffolding in the Clef Programming Language

Decidable By Construction: Design-Time Verification for Trustworthy AI

Receipt and verification

First computed	2026-06-19T16:09:56.894439Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

6b9f5d9dba3c495b80970fddecb3b7a2778e0d4c9e5c6c2b00575091b39a46b6

Aliases

arxiv: 2603.18104 · arxiv_version: 2603.18104v5 · doi: 10.48550/arxiv.2603.18104 · pith_short_12: NOPV3HN2HREV · pith_short_16: NOPV3HN2HREVXAEX · pith_short_8: NOPV3HN2

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/NOPV3HN2HREVXAEXB7O6ZM5XUJ \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 6b9f5d9dba3c495b80970fddecb3b7a2778e0d4c9e5c6c2b00575091b39a46b6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "cd549f8355349039040587c0edaed65bf7d42e5c37ab20dabcb7b1240ace4efa",
    "cross_cats_sorted": [
      "cs.DC",
      "cs.LG",
      "cs.NE"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-03-18T12:36:19Z",
    "title_canon_sha256": "43c888efd00b472565231c89d9febd1d9191c9df6b1e12335185b82864bf548a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.18104",
    "kind": "arxiv",
    "version": 5
  }
}