{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A4NCPS2RHB3AHPR7VLSRQS7IVQ","short_pith_number":"pith:A4NCPS2R","schema_version":"1.0","canonical_sha256":"071a27cb51387603be3faae5184be8ac2056b80b81b48a91a7dd2f0a1d273b0d","source":{"kind":"arxiv","id":"2305.05065","version":3},"attestation_state":"computed","paper":{"title":"Recommender Systems with Generative Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Anima Singh, Ed H. Chi, Jonah Samost, Lichan Hong, Lukasz Heldt, Maciej Kula, Maheswaran Sathiamoorthy, Nikhil Mehta, Raghunandan H. Keshavan, Shashank Rajput, Trung Vu, Vinh Q. Tran, Yi Tay","submitted_at":"2023-05-08T21:48:17Z","abstract_excerpt":"Modern recommender systems perform large-scale retrieval by first embedding queries and item candidates in the same unified space, followed by approximate nearest neighbor search to select top candidates given a query embedding. In this paper, we propose a novel generative retrieval approach, where the retrieval model autoregressively decodes the identifiers of the target candidates. To that end, we create semantically meaningful tuple of codewords to serve as a Semantic ID for each item. Given Semantic IDs for items in a user session, a Transformer-based sequence-to-sequence model is trained "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.05065","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-08T21:48:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"412a90a5bd261c882ad27922624abbfccee635eeac892877d088dd44ef49fb03","abstract_canon_sha256":"6bef020d07200f9f72bdfee1a34081fe608f8c2094fc2fac18b2965d9efc1012"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:57.030265Z","signature_b64":"PGZ8mh7asKStmqOf22NpEQ0VzHPUtJzXJ/7BwaEXAAD29csaUwFiurcEHccIiCPVJVQJiXjSe9jush8w+iz/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"071a27cb51387603be3faae5184be8ac2056b80b81b48a91a7dd2f0a1d273b0d","last_reissued_at":"2026-07-05T07:08:57.029760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:57.029760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recommender Systems with Generative Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Anima Singh, Ed H. Chi, Jonah Samost, Lichan Hong, Lukasz Heldt, Maciej Kula, Maheswaran Sathiamoorthy, Nikhil Mehta, Raghunandan H. Keshavan, Shashank Rajput, Trung Vu, Vinh Q. Tran, Yi Tay","submitted_at":"2023-05-08T21:48:17Z","abstract_excerpt":"Modern recommender systems perform large-scale retrieval by first embedding queries and item candidates in the same unified space, followed by approximate nearest neighbor search to select top candidates given a query embedding. In this paper, we propose a novel generative retrieval approach, where the retrieval model autoregressively decodes the identifiers of the target candidates. To that end, we create semantically meaningful tuple of codewords to serve as a Semantic ID for each item. Given Semantic IDs for items in a user session, a Transformer-based sequence-to-sequence model is trained "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05065","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.05065/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.05065","created_at":"2026-07-05T07:08:57.029819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.05065v3","created_at":"2026-07-05T07:08:57.029819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05065","created_at":"2026-07-05T07:08:57.029819+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4NCPS2RHB3A","created_at":"2026-07-05T07:08:57.029819+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4NCPS2RHB3AHPR7","created_at":"2026-07-05T07:08:57.029819+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4NCPS2R","created_at":"2026-07-05T07:08:57.029819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07317","citing_title":"Gated Bidirectional Linear Attention for Generative Retrieval","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03221","citing_title":"VirtualMLE: A Virtual ML Engineer that Optimizes Sequential Recommenders","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27856","citing_title":"Fine-Tuned LLM as a Complementary Predictor Improving Ads System","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17779","citing_title":"Learning Variable-Length Tokenization for Generative Recommendation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11553","citing_title":"TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05096","citing_title":"CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10471","citing_title":"SID-Coord: Coordinating Semantic IDs for ID-based Ranking in Short-Video Search","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A4NCPS2RHB3AHPR7VLSRQS7IVQ","json":"https://pith.science/pith/A4NCPS2RHB3AHPR7VLSRQS7IVQ.json","graph_json":"https://pith.science/api/pith-number/A4NCPS2RHB3AHPR7VLSRQS7IVQ/graph.json","events_json":"https://pith.science/api/pith-number/A4NCPS2RHB3AHPR7VLSRQS7IVQ/events.json","paper":"https://pith.science/paper/A4NCPS2R"},"agent_actions":{"view_html":"https://pith.science/pith/A4NCPS2RHB3AHPR7VLSRQS7IVQ","download_json":"https://pith.science/pith/A4NCPS2RHB3AHPR7VLSRQS7IVQ.json","view_paper":"https://pith.science/paper/A4NCPS2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.05065&json=true","fetch_graph":"https://pith.science/api/pith-number/A4NCPS2RHB3AHPR7VLSRQS7IVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/A4NCPS2RHB3AHPR7VLSRQS7IVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4NCPS2RHB3AHPR7VLSRQS7IVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4NCPS2RHB3AHPR7VLSRQS7IVQ/action/storage_attestation","attest_author":"https://pith.science/pith/A4NCPS2RHB3AHPR7VLSRQS7IVQ/action/author_attestation","sign_citation":"https://pith.science/pith/A4NCPS2RHB3AHPR7VLSRQS7IVQ/action/citation_signature","submit_replication":"https://pith.science/pith/A4NCPS2RHB3AHPR7VLSRQS7IVQ/action/replication_record"}},"created_at":"2026-07-05T07:08:57.029819+00:00","updated_at":"2026-07-05T07:08:57.029819+00:00"}