Pith Number

pith:U7RVE3AU

pith:2026:U7RVE3AUQEPREVVNNRTK5QKFGK

not attested not anchored not stored refs resolved

CAX-Agent: A Lightweight Agent Harness for Reliable APDL Automation

Chenying Lin, Haiyan Qiang, Liang Yu, Ran Wang, Yichen Hai, Yi He

A model-driven recovery policy inside a lightweight agent harness raises APDL automation completion rates above 92 percent.

arxiv:2605.15218 v1 · 2026-05-12 · cs.AI · cs.CE

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{U7RVE3AUQEPREVVNNRTK5QKFGK}

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

Model_only achieves the best completion rate (0.9267), task score (3.59/4), total score (9.16/10), and zero-intervention rate (0.84), outperforming rule_only (0.7733, 3.17/4, 7.03/10, 0.00) and no_recovery (0.6933, 2.74/4, 5.60/10, 0.00) with large effect sizes (Cliff's delta = 0.81-0.87).

C2weakest assumption

The benchmark uses deliberately simple geometries to isolate recovery-policy effects, and the observed performance differences will hold when the same recovery ladder is applied to more complex real-world geometries and loading conditions.

C3one line summary

CAX-Agent is a three-layer agent harness for MAPDL automation whose model-driven recovery policy reaches 0.93 task completion and 0.84 zero-intervention rate on 50 simple structural benchmarks, outperforming rule-only and no-recovery baselines.

References

26 extracted · 26 resolved · 2 Pith anchors

[1] Attention is all you need, 2017

[2] BERT: Pre- training of deep bidirectional transformers for language understanding, 2019

[3] Language models are few-shot learners, 2020

[4] ReAct: Synergizing reasoning and acting in language models 2023

[5] From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Execution 2026 · arXiv:2604.11378

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:46.802905Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a7e3526c14811f1256ad6c66aec14532b406bdd7bc55603454a15ac88f504cf4

Aliases

arxiv: 2605.15218 · arxiv_version: 2605.15218v1 · doi: 10.48550/arxiv.2605.15218 · pith_short_12: U7RVE3AUQEPR · pith_short_16: U7RVE3AUQEPREVVN · pith_short_8: U7RVE3AU

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/U7RVE3AUQEPREVVNNRTK5QKFGK \
  | 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: a7e3526c14811f1256ad6c66aec14532b406bdd7bc55603454a15ac88f504cf4

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "43d9bc2322eb4186c4a223c1a780b89edee68b5bb103b026ffa31054e51298f0",
    "cross_cats_sorted": [
      "cs.CE"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-12T14:46:34Z",
    "title_canon_sha256": "fdeabf1fe4f03f0d34e956887d9e9eebb2c56eca3eb762a55267cba9dfecb2fd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15218",
    "kind": "arxiv",
    "version": 1
  }
}