{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P5VLGYMK4BUPXMQSB75R3B2GL2","short_pith_number":"pith:P5VLGYMK","schema_version":"1.0","canonical_sha256":"7f6ab3618ae068fbb2120ffb1d87465e940cae6be2241969deeaf667eb1b8c7b","source":{"kind":"arxiv","id":"2602.05663","version":2},"attestation_state":"computed","paper":{"title":"Coarse-to-Fine Long-term Interest Modeling for Generative Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bin Zeng, ChengCheng Guo, Cheng Yang, Han Li, Ji Liu, Junda She, Kun Gai, Kuo Cai, Qiang Luo, Ruiming Tang, Shiteng Cao, Zhiheng Li","submitted_at":"2026-02-05T13:48:33Z","abstract_excerpt":"Leveraging long-term user behavioral patterns is a key trajectory for enhancing the accuracy of modern recommender systems. While generative recommender systems have emerged as a transformative paradigm, they face hurdles in effectively modeling extensive historical sequences. To address this challenge, we propose GLASS, a novel framework that integrates long-term user interests into the generative process via SID-Tier and Semantic Search. We first introduce SID-Tier, a module that maps long-term interactions into a unified interest vector to enhance the prediction of the initial SID token. Un"},"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":"2602.05663","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-02-05T13:48:33Z","cross_cats_sorted":[],"title_canon_sha256":"baf6a4d333be3f9fa20e55a58f5ac0e9f79f6b5f8e940951b707e29d4d193e31","abstract_canon_sha256":"d494da5b382391c7abf33c1fb851eed982bead971e00c853ae69ea91e8f3d50b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:23:04.774253Z","signature_b64":"GkwjXWjI7SNHgzmN8lIo5lPpBnYQipORTqRqjrUAKN3v9oxlpsmhs9X2FJqEjCUIfTB3oTHAAVveS1CIymAoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f6ab3618ae068fbb2120ffb1d87465e940cae6be2241969deeaf667eb1b8c7b","last_reissued_at":"2026-07-24T01:23:04.773264Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:23:04.773264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coarse-to-Fine Long-term Interest Modeling for Generative Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bin Zeng, ChengCheng Guo, Cheng Yang, Han Li, Ji Liu, Junda She, Kun Gai, Kuo Cai, Qiang Luo, Ruiming Tang, Shiteng Cao, Zhiheng Li","submitted_at":"2026-02-05T13:48:33Z","abstract_excerpt":"Leveraging long-term user behavioral patterns is a key trajectory for enhancing the accuracy of modern recommender systems. While generative recommender systems have emerged as a transformative paradigm, they face hurdles in effectively modeling extensive historical sequences. To address this challenge, we propose GLASS, a novel framework that integrates long-term user interests into the generative process via SID-Tier and Semantic Search. We first introduce SID-Tier, a module that maps long-term interactions into a unified interest vector to enhance the prediction of the initial SID token. Un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.05663","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/2602.05663/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":"2602.05663","created_at":"2026-07-24T01:23:04.773746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.05663v2","created_at":"2026-07-24T01:23:04.773746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.05663","created_at":"2026-07-24T01:23:04.773746+00:00"},{"alias_kind":"pith_short_12","alias_value":"P5VLGYMK4BUP","created_at":"2026-07-24T01:23:04.773746+00:00"},{"alias_kind":"pith_short_16","alias_value":"P5VLGYMK4BUPXMQS","created_at":"2026-07-24T01:23:04.773746+00:00"},{"alias_kind":"pith_short_8","alias_value":"P5VLGYMK","created_at":"2026-07-24T01:23:04.773746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.05096","citing_title":"CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P5VLGYMK4BUPXMQSB75R3B2GL2","json":"https://pith.science/pith/P5VLGYMK4BUPXMQSB75R3B2GL2.json","graph_json":"https://pith.science/api/pith-number/P5VLGYMK4BUPXMQSB75R3B2GL2/graph.json","events_json":"https://pith.science/api/pith-number/P5VLGYMK4BUPXMQSB75R3B2GL2/events.json","paper":"https://pith.science/paper/P5VLGYMK"},"agent_actions":{"view_html":"https://pith.science/pith/P5VLGYMK4BUPXMQSB75R3B2GL2","download_json":"https://pith.science/pith/P5VLGYMK4BUPXMQSB75R3B2GL2.json","view_paper":"https://pith.science/paper/P5VLGYMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.05663&json=true","fetch_graph":"https://pith.science/api/pith-number/P5VLGYMK4BUPXMQSB75R3B2GL2/graph.json","fetch_events":"https://pith.science/api/pith-number/P5VLGYMK4BUPXMQSB75R3B2GL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P5VLGYMK4BUPXMQSB75R3B2GL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P5VLGYMK4BUPXMQSB75R3B2GL2/action/storage_attestation","attest_author":"https://pith.science/pith/P5VLGYMK4BUPXMQSB75R3B2GL2/action/author_attestation","sign_citation":"https://pith.science/pith/P5VLGYMK4BUPXMQSB75R3B2GL2/action/citation_signature","submit_replication":"https://pith.science/pith/P5VLGYMK4BUPXMQSB75R3B2GL2/action/replication_record"}},"created_at":"2026-07-24T01:23:04.773746+00:00","updated_at":"2026-07-24T01:23:04.773746+00:00"}