Metraipolis › archive › dc_da88df23ba06
Generative Retrieval under Real-Time Supply Constraints in Local Commerce — arXiv:2611.06323
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06323
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:29:21.153Z
- SHA-256 of the archived text
b0671279334ef5d9f2f300cf5d226cca27b252daf5a4715114dfeda81988d8ef- Stable URL of this page
https://metraipolis.com/documento/dc_da88df23ba06
How to cite
Generative Retrieval under Real-Time Supply Constraints in Local Commerce — arXiv:2611.06323 — arXiv (en), https://arxiv.org/abs/2611.06323 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da88df23ba06 (Metraipolis archive dc_da88df23ba06, sha256 b0671279334ef5d9f2f300cf5d226cca27b252daf5a4715114dfeda81988d8ef)
BibTeX
@misc{dcda88df23ba06,
title = {Generative Retrieval under Real-Time Supply Constraints in Local Commerce — arXiv:2611.06323},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06323},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da88df23ba06; sha256 b0671279334ef5d9f2f300cf5d226cca27b252daf5a4715114dfeda81988d8ef},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06323. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generative retrieval predicts semantic identifiers for candidate entities. In local retail and food delivery, candidates must also be serviceable for a particular user at a particular time. Location, weather, and traffic reshape merchant and product supply, so a catalog-valid identifier may be infeasible for the current request. Post-generation filtering removes such candidates only after beam capacity and inference computation have been spent. We study retrieval over an explicitly materialized, request-time supply snapshot, where short output sequences leave little opportunity to amortize online constraint preparation. Our RTP-LLM pipeline compiles eligible residual-quantization identifiers into a compressed sparse row prefix index, overlaps CPU compilation with model prefill, and shares the uploaded index across beams. Legal expansions retain original-model log probabilities, and constraint states follow selected beam parents. We formalize snapshot-relative identifier validity and distinguish it from entity-level eligibility and freshness. The implementation generates three-token merchant identifiers. Historical evidence covers daily catalog constraints and subsequent request-scoped serving evaluations. In one matched-beam daily-constraint case, filtered merchants decrease from 170 of 299 candidates to 29 of 299; residual distance filtering motivates request-specific constraints. A different-host comparison with 30,000 supplied entries reports a 0.6 ms service-side latency increment, while client measurements expose additional request costs. Captured requests from three geographic settings characterize behavior across supply sizes and output widths. These observations span development stages and measurement boundaries. They establish a practical implementation and identify bottlenecks, but do not establish compute savings at matched retrieval quality. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2611.06323 — 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 2026-11-05T18:19:33.956Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).