Pith Number

pith:ZZDXTWYH

pith:2026:ZZDXTWYHRWI6LK3OBPS25E5OPI

not attested not anchored not stored refs resolved

BoostTaxo: Zero-Shot Taxonomy Induction via Boosting-Style Agentic Reasoning and Constraint-Aware Calibration

Leizhen Wang, Yancheng Ling, Zhenliang Ma, Zhenlin Qin

BoostTaxo induces taxonomies from domain terms using a boosting-style LLM framework in zero-shot settings.

arxiv:2605.12520 v1 · 2026-04-03 · cs.CL · 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{ZZDXTWYHRWI6LK3OBPS25E5OPI}

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

The unified BoostTaxo is evaluated on three public benchmark datasets, namely WordNet, DBLP, and SemEval-Sci, and achieves superior or comparable performance to state-of-the-art methods in zero-shot taxonomy induction.

C2weakest assumption

That the combination of retrieval-augmented definition refinement, hybrid parent candidate selection, and structure-aware score calibration will consistently produce reliable taxonomies without inheriting biases from the underlying LLMs or requiring domain-specific tuning.

C3one line summary

BoostTaxo introduces a boosting-style LLM framework for zero-shot taxonomy induction that uses hybrid candidate selection and constraint-aware calibration to achieve superior or comparable performance to prior methods on WordNet, DBLP, and SemEval-Sci benchmarks.

References

49 extracted · 49 resolved · 2 Pith anchors

[1] Hiexpan: Task-guided taxonomy construction by hierarchical tree expansion, 2018

[2] Setexpan: Corpus- based set expansion via context feature selection and rank ensemble, 2017

[3] Automatic taxonomy con- struction from keywords, 2012

[4] An intent taxonomy for questions asked in web search, 2021

[5] Efficiently answering technical questions—a knowledge graph approach, 2017

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-18T03:10:02.874357Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ce4779db078d91e5ab6e0be5ae93ae7a2a52a5ec041bc88f809c8ac02fe1afab

Aliases

arxiv: 2605.12520 · arxiv_version: 2605.12520v1 · doi: 10.48550/arxiv.2605.12520 · pith_short_12: ZZDXTWYHRWI6 · pith_short_16: ZZDXTWYHRWI6LK3O · pith_short_8: ZZDXTWYH

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/ZZDXTWYHRWI6LK3OBPS25E5OPI \
  | 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: ce4779db078d91e5ab6e0be5ae93ae7a2a52a5ec041bc88f809c8ac02fe1afab

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "192bb05c0d5e629b19cc051fc5296880f609973a97c8e2cbacd7bc5c61b0eff6",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-04-03T15:48:09Z",
    "title_canon_sha256": "b3bc6026544cb384b698180c1e1ac584d68c99aa5ce90e352a19592fcb7bc781"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12520",
    "kind": "arxiv",
    "version": 1
  }
}