{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NJST6CGY5BPLCBYJGLFRGWZMEK","short_pith_number":"pith:NJST6CGY","schema_version":"1.0","canonical_sha256":"6a653f08d8e85eb1070932cb135b2c228dfc03d4cb8c789d71d52af2a51681e3","source":{"kind":"arxiv","id":"2410.13117","version":2},"attestation_state":"computed","paper":{"title":"Preference Diffusion for Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"An Zhang, Guoqing Hu, Hong Qian, Shuo Liu, Tat-Seng Chua","submitted_at":"2024-10-17T01:02:04Z","abstract_excerpt":"Recommender systems predict personalized item rankings based on user preference distributions derived from historical behavior data. Recently, diffusion models (DMs) have gained attention in recommendation for their ability to model complex distributions, yet current DM-based recommenders often rely on traditional objectives like mean squared error (MSE) or recommendation objectives, which are not optimized for personalized ranking tasks or fail to fully leverage DM's generative potential. To address this, we propose PreferDiff, a tailored optimization objective for DM-based recommenders. Pref"},"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":"2410.13117","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-17T01:02:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d959f9f4993088423a8289b0c04c80d6b9d93188d383e7b5d9f0bc93418764fe","abstract_canon_sha256":"681710c2fc32fb8cfdd91ed4ccc0a6eb9eae64aef5d1028500b090225a92d25c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:26.712665Z","signature_b64":"B5W0OcsSz/OAR926hvo8J3AJyAVzCpw5RdlJV5ANF57/DD0OtFlllYugey4cBHaNZDflLPjca7o6c3dFZyRnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a653f08d8e85eb1070932cb135b2c228dfc03d4cb8c789d71d52af2a51681e3","last_reissued_at":"2026-07-05T10:51:26.712187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:26.712187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preference Diffusion for Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"An Zhang, Guoqing Hu, Hong Qian, Shuo Liu, Tat-Seng Chua","submitted_at":"2024-10-17T01:02:04Z","abstract_excerpt":"Recommender systems predict personalized item rankings based on user preference distributions derived from historical behavior data. Recently, diffusion models (DMs) have gained attention in recommendation for their ability to model complex distributions, yet current DM-based recommenders often rely on traditional objectives like mean squared error (MSE) or recommendation objectives, which are not optimized for personalized ranking tasks or fail to fully leverage DM's generative potential. To address this, we propose PreferDiff, a tailored optimization objective for DM-based recommenders. Pref"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13117","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/2410.13117/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":"2410.13117","created_at":"2026-07-05T10:51:26.712239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13117v2","created_at":"2026-07-05T10:51:26.712239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13117","created_at":"2026-07-05T10:51:26.712239+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJST6CGY5BPL","created_at":"2026-07-05T10:51:26.712239+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJST6CGY5BPLCBYJ","created_at":"2026-07-05T10:51:26.712239+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJST6CGY","created_at":"2026-07-05T10:51:26.712239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13943","citing_title":"Language Representation Favored Zero-Shot Cross-Domain Cognitive Diagnosis","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NJST6CGY5BPLCBYJGLFRGWZMEK","json":"https://pith.science/pith/NJST6CGY5BPLCBYJGLFRGWZMEK.json","graph_json":"https://pith.science/api/pith-number/NJST6CGY5BPLCBYJGLFRGWZMEK/graph.json","events_json":"https://pith.science/api/pith-number/NJST6CGY5BPLCBYJGLFRGWZMEK/events.json","paper":"https://pith.science/paper/NJST6CGY"},"agent_actions":{"view_html":"https://pith.science/pith/NJST6CGY5BPLCBYJGLFRGWZMEK","download_json":"https://pith.science/pith/NJST6CGY5BPLCBYJGLFRGWZMEK.json","view_paper":"https://pith.science/paper/NJST6CGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13117&json=true","fetch_graph":"https://pith.science/api/pith-number/NJST6CGY5BPLCBYJGLFRGWZMEK/graph.json","fetch_events":"https://pith.science/api/pith-number/NJST6CGY5BPLCBYJGLFRGWZMEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJST6CGY5BPLCBYJGLFRGWZMEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJST6CGY5BPLCBYJGLFRGWZMEK/action/storage_attestation","attest_author":"https://pith.science/pith/NJST6CGY5BPLCBYJGLFRGWZMEK/action/author_attestation","sign_citation":"https://pith.science/pith/NJST6CGY5BPLCBYJGLFRGWZMEK/action/citation_signature","submit_replication":"https://pith.science/pith/NJST6CGY5BPLCBYJGLFRGWZMEK/action/replication_record"}},"created_at":"2026-07-05T10:51:26.712239+00:00","updated_at":"2026-07-05T10:51:26.712239+00:00"}