Metraipolis › archive › dc_2beb514a2a24

UTS at CheckThat! 2026: Cite-Frame Engineering for Generated Fact-Checking Articles — arXiv:2608.24466

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.24466
License (as archived)
CC0-1.0
Archived
2026-10-18T06:20:55.840Z
SHA-256 of the archived text
aacfbccab1539c9d33db401fd3db61536d5963359de5bcfa0b35624ab17ee013
Stable URL of this page
https://metraipolis.com/documento/dc_2beb514a2a24

How to cite

UTS at CheckThat! 2026: Cite-Frame Engineering for Generated Fact-Checking Articles — arXiv:2608.24466 — arXiv (en), https://arxiv.org/abs/2608.24466 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2beb514a2a24 (Metraipolis archive dc_2beb514a2a24, sha256 aacfbccab1539c9d33db401fd3db61536d5963359de5bcfa0b35624ab17ee013)
BibTeX
@misc{dc2beb514a2a24,
  title = {UTS at CheckThat! 2026: Cite-Frame Engineering for Generated Fact-Checking Articles — arXiv:2608.24466},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.24466},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2beb514a2a24; sha256 aacfbccab1539c9d33db401fd3db61536d5963359de5bcfa0b35624ab17ee013},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24466. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

CheckThat! 2026 Task 3 asks systems to generate fact-checking articles, graded by an unweighted mean of four sub-metrics (M4). Our UTS submission placed 2nd of 11 teams (M4 = 0.484). The shipped system is a deterministic stub drafter wrapped by two single-lever interventions: a domain-attribution cite frame (HostCite) and a shadow-validated anchor picker (ShadowVal) that use Llama-3.2:1B only as a per-cite validator, never as a body-prose generator. The stack lifts M4 by +0.027 over the stub on the WatClaimCheck validation split, beats the field on entailment and coverage, and follows two design rules our ablation matrix made unambiguous. Scorer conservatism: credit only tokens the references entail - templates pay; LLM prose, reviewer names, and raw evidence all fail. Auxiliary anchor signals are miscalibrated against the Llama judge: every anchor proxy we tried (cross-encoder, length, lead position) picks anchors the judge rejects - gate on the judge itself. The remaining +0.062 gap to the winner sits on citation precision/recall (0.299 vs 0.671), consistent with a selective-emission policy that drops low-confidence cites.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.CL).
Categorie arXiv: Digital Libraries (cs.DL) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.24466 — 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 2026-10-18T06:17:29.412Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).