Metraipolis › archive › dc_bbfff6b7aa5b

Critic's Eye: Review-Grounded Graph Reasoning for Long-Form Motif Discovery — arXiv:2610.35011

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.35011
License (as archived)
CC0-1.0
Archived
2026-10-27T07:58:24.671Z
SHA-256 of the archived text
469a217192b8546c18af19404f15648e4da8833e36fee1443e947ee7b487dc0e
Stable URL of this page
https://metraipolis.com/documento/dc_bbfff6b7aa5b

How to cite

Critic's Eye: Review-Grounded Graph Reasoning for Long-Form Motif Discovery — arXiv:2610.35011 — arXiv (en), https://arxiv.org/abs/2610.35011 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bbfff6b7aa5b (Metraipolis archive dc_bbfff6b7aa5b, sha256 469a217192b8546c18af19404f15648e4da8833e36fee1443e947ee7b487dc0e)
BibTeX
@misc{dcbbfff6b7aa5b,
  title = {Critic's Eye: Review-Grounded Graph Reasoning for Long-Form Motif Discovery — arXiv:2610.35011},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.35011},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bbfff6b7aa5b; sha256 469a217192b8546c18af19404f15648e4da8833e36fee1443e947ee7b487dc0e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.35011. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep narrative understanding requires distinguishing what happens from how it is presented, moving beyond the chronological fabula to decode the sjuzet, the discursive organization through which themes are staged. We study this through the recurrence of literary motifs (blood in Macbeth, for instance), where symbolic significance emerges not from local cues, but through repetition-with-variation across the whole work. We operationalize this setting as Computational Motif Discovery, a transductive task that predicts missing line-motif links using the full narrative structure of a play. We propose Critic's Eye, which models the work as a heterogeneous Narrative Topology Graph and performs discriminative inference over global structural evidence. Critic's Eye achieves 84.8% Hit@5 on our benchmark, nearly quadrupling state-of-the-art proprietary foundation models (Gemini-3-pro-preview, ~22.6%). Our analysis reveals that despite massive scaling, sequence-based models hit a "semantic ceiling", struggling to resolve dispersed dependencies. These findings suggest that explicit structural priors are a far more effective inductive bias than parameter scaling for decoding the complex architecture of long-form literature.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.35011 — 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 2026-10-27T07:55:30.729Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).