Metraipolis › archive › dc_bd149ca05567

Understanding before verifying: Claim normalization for automated citation verification — arXiv:2608.30145

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.30145
License (as archived): CC0-1.0
Archived: 2026-10-17T09:44:16.945Z
SHA-256 of the archived text: 5cde00ecd8b2598987e9240b7d4b56b743486d61e039208a8ce5163ed4be3ce2
Stable URL of this page: https://metraipolis.com/documento/dc_bd149ca05567

How to cite

Understanding before verifying: Claim normalization for automated citation verification — arXiv:2608.30145 — arXiv (en), https://arxiv.org/abs/2608.30145 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd149ca05567 (Metraipolis archive dc_bd149ca05567, sha256 5cde00ecd8b2598987e9240b7d4b56b743486d61e039208a8ce5163ed4be3ce2)

BibTeX

@misc{dcbd149ca05567,
  title = {Understanding before verifying: Claim normalization for automated citation verification — arXiv:2608.30145},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30145},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd149ca05567; sha256 5cde00ecd8b2598987e9240b7d4b56b743486d61e039208a8ce5163ed4be3ce2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30145. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Citation accuracy has been studied for decades because of its importance to research reliability. Content-level citation verification assesses the reliability of scholarly claims. Recent work adopts a two-stage retrieval-classification framework inherited from fact-checking. However, this design overlooks the complexity of the raw citing claim and introduces three issues into the verification system, namely scope mismatch, perspective mismatch, and proposition entanglement. These issues increase the difficulty of retrieval and classification, thereby limiting model performance. Motivated by this gap, we propose claim normalization, which applies three rewriting strategies to the raw citing claim before retrieval and classification, allowing each downstream model to perform a single, well-defined task. Building on this method, we develop Claim-Normalized Citation Verification (CNCV), a new three-stage framework consisting of claim normalization, evidence retrieval with grounding, and citation classification. We evaluate CNCV across 18 classifiers using a factorial experiment on human-annotated citation instances. Compared with the prior two-stage framework, CNCV improves macro F1 by an average of 12% for encoders and 10% for generative LLMs, driven by improved evidence quality, the dominant factor identified in our experiments. Evidence retrieved from automatically normalized claims yields downstream classification performance statistically equivalent to that obtained with manually annotated evidence.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.30145 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T09:12:53.474Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).