{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5Y3QNJQRGW6MMWVLWDLQC4QAF3","short_pith_number":"pith:5Y3QNJQR","schema_version":"1.0","canonical_sha256":"ee3706a61135bcc65aabb0d70172002ecaecb5e6afccf87390390c76d845f3ed","source":{"kind":"arxiv","id":"2411.18814","version":2},"attestation_state":"computed","paper":{"title":"Unifying Generative and Dense Retrieval for Sequential Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bo Long, Fabian Paischer, Hamid Eghbalzadeh, Jiacheng Li, Kaveh Hassani, Liu Yang, Nima Noorshams, Robert D Nowak, Sem Park, Shuai Shao, Xiaoli Gao, Xue Feng, Yun He, Zhang Gabriel Li","submitted_at":"2024-11-27T23:36:59Z","abstract_excerpt":"Sequential dense retrieval models utilize advanced sequence learning techniques to compute item and user representations, which are then used to rank relevant items for a user through inner product computation between the user and all item representations. However, this approach requires storing a unique representation for each item, resulting in significant memory requirements as the number of items grow. In contrast, the recently proposed generative retrieval paradigm offers a promising alternative by directly predicting item indices using a generative model trained on semantic IDs that enca"},"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":"2411.18814","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-11-27T23:36:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd427cfc8ed2acd3ba5afc1ca1d0ef58a09d3f25daf2cfff0e7750750a632f04","abstract_canon_sha256":"e848025a2225979692656d7cefd62aca76364728523629bf78a3cb52d8e5c146"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:58.909153Z","signature_b64":"NfXtc9qUZ4MsCirL74ZpM4tRTVab+rbHTXMf2Jh3//IxnXOyhdTgg0g644i31j8dns7N6f0HdnueiWL7ILliAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee3706a61135bcc65aabb0d70172002ecaecb5e6afccf87390390c76d845f3ed","last_reissued_at":"2026-07-05T09:45:58.908677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:58.908677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Generative and Dense Retrieval for Sequential Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bo Long, Fabian Paischer, Hamid Eghbalzadeh, Jiacheng Li, Kaveh Hassani, Liu Yang, Nima Noorshams, Robert D Nowak, Sem Park, Shuai Shao, Xiaoli Gao, Xue Feng, Yun He, Zhang Gabriel Li","submitted_at":"2024-11-27T23:36:59Z","abstract_excerpt":"Sequential dense retrieval models utilize advanced sequence learning techniques to compute item and user representations, which are then used to rank relevant items for a user through inner product computation between the user and all item representations. However, this approach requires storing a unique representation for each item, resulting in significant memory requirements as the number of items grow. In contrast, the recently proposed generative retrieval paradigm offers a promising alternative by directly predicting item indices using a generative model trained on semantic IDs that enca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18814","kind":"arxiv","version":2},"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/2411.18814/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":"2411.18814","created_at":"2026-07-05T09:45:58.908737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18814v2","created_at":"2026-07-05T09:45:58.908737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18814","created_at":"2026-07-05T09:45:58.908737+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Y3QNJQRGW6M","created_at":"2026-07-05T09:45:58.908737+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Y3QNJQRGW6MMWVL","created_at":"2026-07-05T09:45:58.908737+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Y3QNJQR","created_at":"2026-07-05T09:45:58.908737+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25147","citing_title":"TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00422","citing_title":"UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13648","citing_title":"Sequential Data Augmentation for Generative Recommendation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18771","citing_title":"LWGR: Lagrangian-Constrained Personalized World Knowledge for Generative Recommendation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2603.14259","citing_title":"GenRecEdit: Adapting Model Editing for Generative Recommendation with Cold-Start Items","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12617","citing_title":"MLPs are Efficient Distilled Generative Recommenders","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11447","citing_title":"Conditional Memory Enhanced Item Representation for Generative Recommendation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06331","citing_title":"Expressiveness Limits of Autoregressive Semantic ID Generation in Generative Recommendation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22881","citing_title":"MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05096","citing_title":"CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06981","citing_title":"Bridging Textual Profiles and Latent User Embeddings for Personalization","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13273","citing_title":"Mitigating Collaborative Semantic ID Staleness in Generative Retrieval","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Y3QNJQRGW6MMWVLWDLQC4QAF3","json":"https://pith.science/pith/5Y3QNJQRGW6MMWVLWDLQC4QAF3.json","graph_json":"https://pith.science/api/pith-number/5Y3QNJQRGW6MMWVLWDLQC4QAF3/graph.json","events_json":"https://pith.science/api/pith-number/5Y3QNJQRGW6MMWVLWDLQC4QAF3/events.json","paper":"https://pith.science/paper/5Y3QNJQR"},"agent_actions":{"view_html":"https://pith.science/pith/5Y3QNJQRGW6MMWVLWDLQC4QAF3","download_json":"https://pith.science/pith/5Y3QNJQRGW6MMWVLWDLQC4QAF3.json","view_paper":"https://pith.science/paper/5Y3QNJQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18814&json=true","fetch_graph":"https://pith.science/api/pith-number/5Y3QNJQRGW6MMWVLWDLQC4QAF3/graph.json","fetch_events":"https://pith.science/api/pith-number/5Y3QNJQRGW6MMWVLWDLQC4QAF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Y3QNJQRGW6MMWVLWDLQC4QAF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Y3QNJQRGW6MMWVLWDLQC4QAF3/action/storage_attestation","attest_author":"https://pith.science/pith/5Y3QNJQRGW6MMWVLWDLQC4QAF3/action/author_attestation","sign_citation":"https://pith.science/pith/5Y3QNJQRGW6MMWVLWDLQC4QAF3/action/citation_signature","submit_replication":"https://pith.science/pith/5Y3QNJQRGW6MMWVLWDLQC4QAF3/action/replication_record"}},"created_at":"2026-07-05T09:45:58.908737+00:00","updated_at":"2026-07-05T09:45:58.908737+00:00"}