Metraipolis › archive › dc_cb6becf3a4bf

Beyond the Beam: Constructive Repair and Candidate Completion for Generative Recommendation — arXiv:2609.33745

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33745
License (as archived)
CC0-1.0
Archived
2026-10-07T23:49:49.514Z
SHA-256 of the archived text
357954fd4063bcd60e8734e81db185770bc9eaf97b811dde925edd26e6d096f6
Stable URL of this page
https://metraipolis.com/documento/dc_cb6becf3a4bf

How to cite

Beyond the Beam: Constructive Repair and Candidate Completion for Generative Recommendation — arXiv:2609.33745 — arXiv (en), https://arxiv.org/abs/2609.33745 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb6becf3a4bf (Metraipolis archive dc_cb6becf3a4bf, sha256 357954fd4063bcd60e8734e81db185770bc9eaf97b811dde925edd26e6d096f6)
BibTeX
@misc{dccb6becf3a4bf,
  title = {Beyond the Beam: Constructive Repair and Candidate Completion for Generative Recommendation — arXiv:2609.33745},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33745},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb6becf3a4bf; sha256 357954fd4063bcd60e8734e81db185770bc9eaf97b811dde925edd26e6d096f6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33745. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative recommenders retrieve items by generating identifiers, but a valid identifier can remain outside the beam after catalog expansion. This raises two connected questions: which failures can identifier assignment repair, and how should retrieval proceed beyond the initial beam? We characterize assignment repair with a fixed generator and retained old identifiers. Output-invariance certificates identify failures shared by all admissible assignments. Under a common effective prefix, coupled support and ranking constraints give the exact feasible interval of new-item counts for target recovery. Building on this characterization, Beyond the Beam (BB) obtains minimum-replacement repairs through an integral flow formulation, selects a shared map and adapts the generator. At inference, generative likelihood and collaborative evidence define one score for ranking, candidate priority and stopping. Retained prefix bounds guide candidate completion and certify its global Top-$K$ when the stopping condition is met. Exhaustive finite-catalog evaluation confirms construction in every feasible case. Across three Amazon Reviews categories and three random seeds, the full T5 procedure improves mean Recall@10 by 15.5--46.3% and NDCG@10 by 15.2--44.4% over the best-performing evaluated generative baseline for each dataset and metric. Matched controls show that shared construction and adaptation improve new-target ranking and certification efficiency on Beauty and Toys. Combined scoring and candidate completion improve NDCG@10 across all three datasets with both T5 and decoder-only LC-Rec.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.33745 — 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 2026-10-07T23:26:57.194Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).