{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DJG3BQJTCGBNWUZZDMAF55F3RU","short_pith_number":"pith:DJG3BQJT","schema_version":"1.0","canonical_sha256":"1a4db0c1331182db53391b005ef4bb8d040d29aa2862b3889635ae6d35ad5c95","source":{"kind":"arxiv","id":"2503.02453","version":1},"attestation_state":"computed","paper":{"title":"Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jie Li, Kai Chen, Lin Liu, Shuanglong Li, Yi Li, Yue Ding, Yuhao Yang, Zhaopeng Li, Zhi Ji, Zhonglin Mo, Zijian Zhang","submitted_at":"2025-03-04T10:00:05Z","abstract_excerpt":"Generative models have recently gained attention in recommendation systems by directly predicting item identifiers from user interaction sequences. However, existing methods suffer from significant information loss due to the separation of stages such as quantization and sequence modeling, hindering their ability to achieve the modeling precision and accuracy of sequential dense retrieval techniques. Integrating generative and dense retrieval methods remains a critical challenge. To address this, we introduce the Cascaded Organized Bi-Represented generAtive retrieval (COBRA) framework, which i"},"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":"2503.02453","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-03-04T10:00:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bb46c420f8e1dfae0d1db640f327662d2a63ee4e5723bb46f87e18de223db0f7","abstract_canon_sha256":"75f66423b1d670b771d8aa85a1a2a09675a9b8b307c71dc2f9beb7171a29b899"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:05.786022Z","signature_b64":"Q9PifL62MrHB4uEzxZSeI0sVImS8EZCTWgz4g6jcijum1DCDObqkvo3Gn327tECjJNmQ4qNd1m8wmreBnl9DCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a4db0c1331182db53391b005ef4bb8d040d29aa2862b3889635ae6d35ad5c95","last_reissued_at":"2026-07-05T10:24:05.785429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:05.785429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jie Li, Kai Chen, Lin Liu, Shuanglong Li, Yi Li, Yue Ding, Yuhao Yang, Zhaopeng Li, Zhi Ji, Zhonglin Mo, Zijian Zhang","submitted_at":"2025-03-04T10:00:05Z","abstract_excerpt":"Generative models have recently gained attention in recommendation systems by directly predicting item identifiers from user interaction sequences. However, existing methods suffer from significant information loss due to the separation of stages such as quantization and sequence modeling, hindering their ability to achieve the modeling precision and accuracy of sequential dense retrieval techniques. Integrating generative and dense retrieval methods remains a critical challenge. To address this, we introduce the Cascaded Organized Bi-Represented generAtive retrieval (COBRA) framework, which i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02453","kind":"arxiv","version":1},"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/2503.02453/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":"2503.02453","created_at":"2026-07-05T10:24:05.785517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02453v1","created_at":"2026-07-05T10:24:05.785517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02453","created_at":"2026-07-05T10:24:05.785517+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJG3BQJTCGBN","created_at":"2026-07-05T10:24:05.785517+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJG3BQJTCGBNWUZZ","created_at":"2026-07-05T10:24:05.785517+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJG3BQJT","created_at":"2026-07-05T10:24:05.785517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28368","citing_title":"EvoRec: Self Evolving Agentic Recommender Systems","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2601.18664","citing_title":"S$^2$GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18771","citing_title":"LWGR: Lagrangian-Constrained Personalized World Knowledge for Generative Recommendation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17779","citing_title":"Learning Variable-Length Tokenization for Generative Recommendation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26085","citing_title":"AgenticRS-Architecture: System Design for Agentic Recommender Systems","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02684","citing_title":"MBGR: Multi-Business Prediction for Generative Recommendation at Meituan","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11447","citing_title":"Conditional Memory Enhanced Item Representation for Generative Recommendation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23156","citing_title":"Birds of a Feather Cluster Nearby: a Proximity-Aware Geo-Codebook for Local Service Recommendation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05096","citing_title":"CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14878","citing_title":"GenRec: A Preference-Oriented Generative Framework for Large-Scale Recommendation","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJG3BQJTCGBNWUZZDMAF55F3RU","json":"https://pith.science/pith/DJG3BQJTCGBNWUZZDMAF55F3RU.json","graph_json":"https://pith.science/api/pith-number/DJG3BQJTCGBNWUZZDMAF55F3RU/graph.json","events_json":"https://pith.science/api/pith-number/DJG3BQJTCGBNWUZZDMAF55F3RU/events.json","paper":"https://pith.science/paper/DJG3BQJT"},"agent_actions":{"view_html":"https://pith.science/pith/DJG3BQJTCGBNWUZZDMAF55F3RU","download_json":"https://pith.science/pith/DJG3BQJTCGBNWUZZDMAF55F3RU.json","view_paper":"https://pith.science/paper/DJG3BQJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02453&json=true","fetch_graph":"https://pith.science/api/pith-number/DJG3BQJTCGBNWUZZDMAF55F3RU/graph.json","fetch_events":"https://pith.science/api/pith-number/DJG3BQJTCGBNWUZZDMAF55F3RU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJG3BQJTCGBNWUZZDMAF55F3RU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJG3BQJTCGBNWUZZDMAF55F3RU/action/storage_attestation","attest_author":"https://pith.science/pith/DJG3BQJTCGBNWUZZDMAF55F3RU/action/author_attestation","sign_citation":"https://pith.science/pith/DJG3BQJTCGBNWUZZDMAF55F3RU/action/citation_signature","submit_replication":"https://pith.science/pith/DJG3BQJTCGBNWUZZDMAF55F3RU/action/replication_record"}},"created_at":"2026-07-05T10:24:05.785517+00:00","updated_at":"2026-07-05T10:24:05.785517+00:00"}