pith:MWPN56BT
Effect-Transparent Governance for AI Workflow Architectures: Semantic Preservation, Expressive Minimality, and Decidability Boundaries
Effect-level governance can be imposed on AI workflow architectures without reducing their internal computational expressivity or changing permitted behaviors.
arxiv:2605.01030 v3 · 2026-05-01 · cs.AI · cs.LO · cs.PL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{MWPN56BTMJAFJ4JQUUUH35EGFD}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
effect-level governance can be imposed without reducing internal computational expressivity... semantic transparency: on all executions where governance permits, the governed interpretation is observationally equivalent (modulo governance-only events) to the ungoverned interpretation.
That the Interaction Trees model with the defined governance operator G accurately captures all relevant effectful behaviors of real AI workflow architectures, including oracle queries, and that the operator mediates every effect without omission.
A Rocq formalization of 12,000 lines proves that effect governance in AI workflows preserves Turing completeness, expressivity, and observational equivalence to ungoverned executions.
Receipt and verification
| First computed | 2026-05-27T01:05:55.521775Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
659edef833624054f130a5287df48628ea033924e5f72d11418b636322208f83
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/MWPN56BTMJAFJ4JQUUUH35EGFD \
| 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: 659edef833624054f130a5287df48628ea033924e5f72d11418b636322208f83
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "84fd25fb9e1fc013e5d1cc0c7f787b6b13dbece210d9bdfafdce437cf3427937",
"cross_cats_sorted": [
"cs.LO",
"cs.PL"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-05-01T18:52:47Z",
"title_canon_sha256": "e30a1dd55300f8b8a7790e84b87e40f416dd23a74626c5256542f415fafd1f7a"
},
"schema_version": "1.0",
"source": {
"id": "2605.01030",
"kind": "arxiv",
"version": 3
}
}