{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TMC73HYS4YE6RPRIAOYZFO5PCK","short_pith_number":"pith:TMC73HYS","schema_version":"1.0","canonical_sha256":"9b05fd9f12e609e8be2803b192bbaf1285c332d1cdb018b1e5e9996cc92c168f","source":{"kind":"arxiv","id":"2405.03562","version":2},"attestation_state":"computed","paper":{"title":"ID-centric Pre-training for Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Fuzhen Zhuang, Leyu Lin, Ruobing Xie, Xu Zhang, Yiqing Wu, Yongjun Xu, Zhanhui Kang, Zhao Zhang","submitted_at":"2024-05-06T15:34:31Z","abstract_excerpt":"Classical sequential recommendation models generally adopt ID embeddings to store knowledge learned from user historical behaviors and represent items. However, these unique IDs are challenging to be transferred to new domains. With the thriving of pre-trained language model (PLM), some pioneer works adopt PLM for pre-trained recommendation, where modality information (e.g., text) is considered universal across domains via PLM. Unfortunately, the behavioral information in ID embeddings is still verified to be dominating in PLM-based recommendation models compared to modality information and th"},"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":"2405.03562","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-06T15:34:31Z","cross_cats_sorted":[],"title_canon_sha256":"d2efaa88d33d7cc60328774f2de4861961c7a65a8745e31072d1f5ce4aaeac4e","abstract_canon_sha256":"5afe12330d6938c4a32c3d9e723fdbb3ec0c59de469d436d24854cb8284639b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:29.112584Z","signature_b64":"t8YdzG99U2vxf9YM8+j9Zb4bGN4HzQ+uztrPUpmPCpDQ/Qt7ybteY9eDoWTa5pPeXRMaNUqVa9rt8BELhZJ3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b05fd9f12e609e8be2803b192bbaf1285c332d1cdb018b1e5e9996cc92c168f","last_reissued_at":"2026-07-05T08:16:29.112140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:29.112140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ID-centric Pre-training for Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Fuzhen Zhuang, Leyu Lin, Ruobing Xie, Xu Zhang, Yiqing Wu, Yongjun Xu, Zhanhui Kang, Zhao Zhang","submitted_at":"2024-05-06T15:34:31Z","abstract_excerpt":"Classical sequential recommendation models generally adopt ID embeddings to store knowledge learned from user historical behaviors and represent items. However, these unique IDs are challenging to be transferred to new domains. With the thriving of pre-trained language model (PLM), some pioneer works adopt PLM for pre-trained recommendation, where modality information (e.g., text) is considered universal across domains via PLM. Unfortunately, the behavioral information in ID embeddings is still verified to be dominating in PLM-based recommendation models compared to modality information and th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03562","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/2405.03562/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":"2405.03562","created_at":"2026-07-05T08:16:29.112203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03562v2","created_at":"2026-07-05T08:16:29.112203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03562","created_at":"2026-07-05T08:16:29.112203+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMC73HYS4YE6","created_at":"2026-07-05T08:16:29.112203+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMC73HYS4YE6RPRI","created_at":"2026-07-05T08:16:29.112203+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMC73HYS","created_at":"2026-07-05T08:16:29.112203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.06308","citing_title":"PRECISE: Pre-training Sequential Recommenders with Collaborative and Semantic Information","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMC73HYS4YE6RPRIAOYZFO5PCK","json":"https://pith.science/pith/TMC73HYS4YE6RPRIAOYZFO5PCK.json","graph_json":"https://pith.science/api/pith-number/TMC73HYS4YE6RPRIAOYZFO5PCK/graph.json","events_json":"https://pith.science/api/pith-number/TMC73HYS4YE6RPRIAOYZFO5PCK/events.json","paper":"https://pith.science/paper/TMC73HYS"},"agent_actions":{"view_html":"https://pith.science/pith/TMC73HYS4YE6RPRIAOYZFO5PCK","download_json":"https://pith.science/pith/TMC73HYS4YE6RPRIAOYZFO5PCK.json","view_paper":"https://pith.science/paper/TMC73HYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03562&json=true","fetch_graph":"https://pith.science/api/pith-number/TMC73HYS4YE6RPRIAOYZFO5PCK/graph.json","fetch_events":"https://pith.science/api/pith-number/TMC73HYS4YE6RPRIAOYZFO5PCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMC73HYS4YE6RPRIAOYZFO5PCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMC73HYS4YE6RPRIAOYZFO5PCK/action/storage_attestation","attest_author":"https://pith.science/pith/TMC73HYS4YE6RPRIAOYZFO5PCK/action/author_attestation","sign_citation":"https://pith.science/pith/TMC73HYS4YE6RPRIAOYZFO5PCK/action/citation_signature","submit_replication":"https://pith.science/pith/TMC73HYS4YE6RPRIAOYZFO5PCK/action/replication_record"}},"created_at":"2026-07-05T08:16:29.112203+00:00","updated_at":"2026-07-05T08:16:29.112203+00:00"}