pith. sign in
Pith Number

pith:EWMYL7WV

pith:2026:EWMYL7WVOJYAWNTTWXMMX7CK5I
not attested not anchored not stored refs pending

The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment

Barry L. Bentley, Fiona Carroll, Shasha Yu

Execution and refusal act as separable behavioral dimensions in tool-using language models, redistributing differently across risk contexts and autonomy levels.

arxiv:2604.12116 v2 · 2026-04-13 · cs.AI · cs.SE

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{EWMYL7WVOJYAWNTTWXMMX7CK5I}

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

Empirical results show that execution and refusal constitute separable behavioral dimensions whose joint distribution varies systematically across regimes and autonomy levels. The A-R representation makes cross-sectional behavioral profiles, scaffold-induced transitions, and coordination variability directly observable.

C2weakest assumption

That the four normative regimes (Control, Gray, Dilemma, Malicious) and three autonomy configurations (direct execution, planning, reflection) adequately represent relevant real-world organizational contexts and that the A-R metrics reliably capture meaningful, generalizable behavioral differences.

C3one line summary

Execution and refusal in tool-using LLM agents form separable behavioral dimensions whose joint distribution shifts systematically with normative regimes and autonomy scaffolding.

Receipt and verification
First computed 2026-05-26T01:03:29.984481Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

259985fed572700b3673b5d8cbfc4aea00ba6b3578991a8a9372d23d56250de4

Aliases

arxiv: 2604.12116 · arxiv_version: 2604.12116v2 · doi: 10.48550/arxiv.2604.12116 · pith_short_12: EWMYL7WVOJYA · pith_short_16: EWMYL7WVOJYAWNTT · pith_short_8: EWMYL7WV
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/EWMYL7WVOJYAWNTTWXMMX7CK5I \
  | 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: 259985fed572700b3673b5d8cbfc4aea00ba6b3578991a8a9372d23d56250de4
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "65176e97a3e31aaf128995d612f254b53f20d3a3924387653e62382151cd9824",
    "cross_cats_sorted": [
      "cs.SE"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-04-13T22:50:21Z",
    "title_canon_sha256": "b14931b78d837fd5b633f62f140b951456facbb7a1e7b460bcf990a50ceb946c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.12116",
    "kind": "arxiv",
    "version": 2
  }
}