{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I474IDWKIB4GZZTZWHFIMZXP2A","short_pith_number":"pith:I474IDWK","schema_version":"1.0","canonical_sha256":"473fc40eca40786ce679b1ca8666efd003878db7db7bb3f229d446d5167fa492","source":{"kind":"arxiv","id":"2504.06636","version":1},"attestation_state":"computed","paper":{"title":"BBQRec: Behavior-Bind Quantization for Multi-Modal Sequential Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Kaiyuan Li, Kun Gai, Peng Jiang, Rui Xiang, Xialong Liu, Yanhua Cheng, Yong Bai, Yongxiang Tang","submitted_at":"2025-04-09T07:19:48Z","abstract_excerpt":"Multi-modal sequential recommendation systems leverage auxiliary signals (e.g., text, images) to alleviate data sparsity in user-item interactions. While recent methods exploit large language models to encode modalities into discrete semantic IDs for autoregressive prediction, we identify two critical limitations: (1) Existing approaches adopt fragmented quantization, where modalities are independently mapped to semantic spaces misaligned with behavioral objectives, and (2) Over-reliance on semantic IDs disrupts inter-modal semantic coherence, thereby weakening the expressive power of multi-mo"},"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":"2504.06636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-09T07:19:48Z","cross_cats_sorted":[],"title_canon_sha256":"e5555bfcb6e02f695909009102d16a3c40816b15a882fabe597ea7d4820a4bba","abstract_canon_sha256":"43f2acf726e80b76f76e791aedb5d12171f896159a907f45ed2aa9a0a4e6e576"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:30.272526Z","signature_b64":"u4JA6FGW68gBShLMWQO0XBDZhmTC3AfZNo9FEC09p+rJLtv84TEueksWzFz3o4H4j/d9pCmbWZV6bQbsL+2VCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"473fc40eca40786ce679b1ca8666efd003878db7db7bb3f229d446d5167fa492","last_reissued_at":"2026-07-05T10:46:30.272023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:30.272023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BBQRec: Behavior-Bind Quantization for Multi-Modal Sequential Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Kaiyuan Li, Kun Gai, Peng Jiang, Rui Xiang, Xialong Liu, Yanhua Cheng, Yong Bai, Yongxiang Tang","submitted_at":"2025-04-09T07:19:48Z","abstract_excerpt":"Multi-modal sequential recommendation systems leverage auxiliary signals (e.g., text, images) to alleviate data sparsity in user-item interactions. While recent methods exploit large language models to encode modalities into discrete semantic IDs for autoregressive prediction, we identify two critical limitations: (1) Existing approaches adopt fragmented quantization, where modalities are independently mapped to semantic spaces misaligned with behavioral objectives, and (2) Over-reliance on semantic IDs disrupts inter-modal semantic coherence, thereby weakening the expressive power of multi-mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06636","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/2504.06636/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":"2504.06636","created_at":"2026-07-05T10:46:30.272074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.06636v1","created_at":"2026-07-05T10:46:30.272074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06636","created_at":"2026-07-05T10:46:30.272074+00:00"},{"alias_kind":"pith_short_12","alias_value":"I474IDWKIB4G","created_at":"2026-07-05T10:46:30.272074+00:00"},{"alias_kind":"pith_short_16","alias_value":"I474IDWKIB4GZZTZ","created_at":"2026-07-05T10:46:30.272074+00:00"},{"alias_kind":"pith_short_8","alias_value":"I474IDWK","created_at":"2026-07-05T10:46:30.272074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31693","citing_title":"ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21987","citing_title":"Generative Conversational Recommender System","ref_index":16,"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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05329","citing_title":"Semantic Trimming and Auxiliary Multi-step Prediction for Generative Recommendation","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I474IDWKIB4GZZTZWHFIMZXP2A","json":"https://pith.science/pith/I474IDWKIB4GZZTZWHFIMZXP2A.json","graph_json":"https://pith.science/api/pith-number/I474IDWKIB4GZZTZWHFIMZXP2A/graph.json","events_json":"https://pith.science/api/pith-number/I474IDWKIB4GZZTZWHFIMZXP2A/events.json","paper":"https://pith.science/paper/I474IDWK"},"agent_actions":{"view_html":"https://pith.science/pith/I474IDWKIB4GZZTZWHFIMZXP2A","download_json":"https://pith.science/pith/I474IDWKIB4GZZTZWHFIMZXP2A.json","view_paper":"https://pith.science/paper/I474IDWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.06636&json=true","fetch_graph":"https://pith.science/api/pith-number/I474IDWKIB4GZZTZWHFIMZXP2A/graph.json","fetch_events":"https://pith.science/api/pith-number/I474IDWKIB4GZZTZWHFIMZXP2A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I474IDWKIB4GZZTZWHFIMZXP2A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I474IDWKIB4GZZTZWHFIMZXP2A/action/storage_attestation","attest_author":"https://pith.science/pith/I474IDWKIB4GZZTZWHFIMZXP2A/action/author_attestation","sign_citation":"https://pith.science/pith/I474IDWKIB4GZZTZWHFIMZXP2A/action/citation_signature","submit_replication":"https://pith.science/pith/I474IDWKIB4GZZTZWHFIMZXP2A/action/replication_record"}},"created_at":"2026-07-05T10:46:30.272074+00:00","updated_at":"2026-07-05T10:46:30.272074+00:00"}