Pith Number

pith:JODJGSCK

pith:2026:JODJGSCKEKSH5YNKWKMLYRQFUD

not attested not anchored not stored refs resolved

Sustaining AI safety: Control-theoretic external impossibility, intrinsic necessity, and structural requirements

James M. Mazzu

Control theory proves that no externally enforced strategy can sustain AI safety once system effects exceed bounded external counteraction.

arxiv:2605.12963 v1 · 2026-05-13 · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{JODJGSCKEKSH5YNKWKMLYRQFUD}

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

Under explicit premises including a reachability condition, once the system's effects exceed what bounded external control can counteract, no strategy that depends in any degree on continued external enforcement can sustain AI safety. This failure is structural across the entire externally enforced class.

C2weakest assumption

The reachability condition and other explicit premises that allow the control-theoretic model to conclude that external effects are bounded while system effects are not; if this modeling assumption does not hold for real AI systems, the impossibility result does not apply.

C3one line summary

External control strategies are structurally impossible for sustaining AI safety beyond bounded capability thresholds; any remaining viable strategies must be intrinsic with stable safety-compatible objectives.

References

2 extracted · 2 resolved · 2 Pith anchors

[1] Concrete Problems in AI Safety 2016 · arXiv:1606.06565

[2] AGI Safety Literature Review 2018 · arXiv:1805.01109

Receipt and verification

First computed	2026-05-18T03:09:09.110468Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4b8693484a22a47ee1aab298bc4605a0d3edd62e7f4b9537e9ae8a677d0c6dbd

Aliases

arxiv: 2605.12963 · arxiv_version: 2605.12963v1 · doi: 10.48550/arxiv.2605.12963 · pith_short_12: JODJGSCKEKSH · pith_short_16: JODJGSCKEKSH5YNK · pith_short_8: JODJGSCK

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/JODJGSCKEKSH5YNKWKMLYRQFUD \
  | 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: 4b8693484a22a47ee1aab298bc4605a0d3edd62e7f4b9537e9ae8a677d0c6dbd

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "056d428a781d59dc93c9a962438ba6f677c9b906fd6e9aa84701bb160f0b0e95",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T03:56:04Z",
    "title_canon_sha256": "b7ed01a9f4a031c6dee004ef956fd01e15e89288c3e1155589a158f52eb39ef4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12963",
    "kind": "arxiv",
    "version": 1
  }
}