Pith Number

pith:SNLLFWZH

pith:2026:SNLLFWZHO6OEU2YHEZNIXQSRDA

not attested not anchored not stored refs pending

ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Models

Guanran Luo, Jingqi Gao, Meihong Wang, Qingqiang Wu, Wentao Qiu, Zhongquan Jian

ANCHOR builds dense hierarchical factor spaces from LLMs via iterative generation and clustering to support reliable Bayesian probability estimates.

arxiv:2605.10328 v3 · 2026-05-11 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{SNLLFWZHO6OEU2YHEZNIXQSRDA}

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

Experiments show that ANCHOR markedly reduces ``unknown'' predictions and produces more reliable probability estimates than direct LLM baselines, achieving state-of-the-art performance while significantly reducing time and token overhead.

C2weakest assumption

The assumption that iterative LLM generation plus clustering will reliably produce a hierarchical factor space that captures latent dependencies without introducing new noise or spurious correlations that degrade the causal Bayesian network.

C3one line summary

ANCHOR constructs dense hierarchical factor spaces via LLM generation and clustering, then augments Naive Bayes with a causal Bayesian network to reduce unknown predictions and improve reliability of LLM-based probability estimates.

Cited by

2 papers in Pith

DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory

MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution

Receipt and verification

First computed	2026-06-03T01:05:51.280944Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9356b2db27779c4a6b07265a8bc25118167eedd71a0c13f3c73f4510be488250

Aliases

arxiv: 2605.10328 · arxiv_version: 2605.10328v3 · doi: 10.48550/arxiv.2605.10328 · pith_short_12: SNLLFWZHO6OE · pith_short_16: SNLLFWZHO6OEU2YH · pith_short_8: SNLLFWZH

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/SNLLFWZHO6OEU2YHEZNIXQSRDA \
  | 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: 9356b2db27779c4a6b07265a8bc25118167eedd71a0c13f3c73f4510be488250

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "68406647a8d798eea679b65c0f1ba61071b8760fd32e256afd00f2c9b94a3545",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-11T10:31:53Z",
    "title_canon_sha256": "8b28f1cf0c8f09ddde178cbc61f4e5207d45f781fd0e9a2d57dd9bd9da745e54"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.10328",
    "kind": "arxiv",
    "version": 3
  }
}