{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QI3MFUSGSGNU2DDQVGBIPNLO3X","short_pith_number":"pith:QI3MFUSG","schema_version":"1.0","canonical_sha256":"8236c2d246919b4d0c70a98287b56eddc5c78ccf786916f952c0edb69709b05f","source":{"kind":"arxiv","id":"2403.19021","version":2},"attestation_state":"computed","paper":{"title":"IDGenRec: LLM-RecSys Alignment with Textual ID Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Juntao Tan, Shuyuan Xu, Wenyue Hua, Yingqiang Ge, Yongfeng Zhang, Zelong Li","submitted_at":"2024-03-27T21:22:37Z","abstract_excerpt":"Generative recommendation based on Large Language Models (LLMs) have transformed the traditional ranking-based recommendation style into a text-to-text generation paradigm. However, in contrast to standard NLP tasks that inherently operate on human vocabulary, current research in generative recommendations struggles to effectively encode recommendation items within the text-to-text framework using concise yet meaningful ID representations. To better align LLMs with recommendation needs, we propose IDGen, representing each item as a unique, concise, semantically rich, platform-agnostic textual "},"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":"2403.19021","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-03-27T21:22:37Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"1b6781fad1d16156329a100f48d4c79d79a0723b91f979a2aad74f5805cf141a","abstract_canon_sha256":"fef445d45d30f42f81c427b34ce565d03b378610a038fb4418e5bda9d9550342"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:10.813292Z","signature_b64":"1EnqzoO87tw5WLYdlT4lua9AtTgYgSAVywXcfYJfjslRIhPdtaxAuQo7UU+LmkIhmU29jRUmV/F/1ci55MZkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8236c2d246919b4d0c70a98287b56eddc5c78ccf786916f952c0edb69709b05f","last_reissued_at":"2026-07-05T08:20:10.812880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:10.812880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IDGenRec: LLM-RecSys Alignment with Textual ID Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Juntao Tan, Shuyuan Xu, Wenyue Hua, Yingqiang Ge, Yongfeng Zhang, Zelong Li","submitted_at":"2024-03-27T21:22:37Z","abstract_excerpt":"Generative recommendation based on Large Language Models (LLMs) have transformed the traditional ranking-based recommendation style into a text-to-text generation paradigm. However, in contrast to standard NLP tasks that inherently operate on human vocabulary, current research in generative recommendations struggles to effectively encode recommendation items within the text-to-text framework using concise yet meaningful ID representations. To better align LLMs with recommendation needs, we propose IDGen, representing each item as a unique, concise, semantically rich, platform-agnostic textual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19021","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/2403.19021/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":"2403.19021","created_at":"2026-07-05T08:20:10.812943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19021v2","created_at":"2026-07-05T08:20:10.812943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19021","created_at":"2026-07-05T08:20:10.812943+00:00"},{"alias_kind":"pith_short_12","alias_value":"QI3MFUSGSGNU","created_at":"2026-07-05T08:20:10.812943+00:00"},{"alias_kind":"pith_short_16","alias_value":"QI3MFUSGSGNU2DDQ","created_at":"2026-07-05T08:20:10.812943+00:00"},{"alias_kind":"pith_short_8","alias_value":"QI3MFUSG","created_at":"2026-07-05T08:20:10.812943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QI3MFUSGSGNU2DDQVGBIPNLO3X","json":"https://pith.science/pith/QI3MFUSGSGNU2DDQVGBIPNLO3X.json","graph_json":"https://pith.science/api/pith-number/QI3MFUSGSGNU2DDQVGBIPNLO3X/graph.json","events_json":"https://pith.science/api/pith-number/QI3MFUSGSGNU2DDQVGBIPNLO3X/events.json","paper":"https://pith.science/paper/QI3MFUSG"},"agent_actions":{"view_html":"https://pith.science/pith/QI3MFUSGSGNU2DDQVGBIPNLO3X","download_json":"https://pith.science/pith/QI3MFUSGSGNU2DDQVGBIPNLO3X.json","view_paper":"https://pith.science/paper/QI3MFUSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19021&json=true","fetch_graph":"https://pith.science/api/pith-number/QI3MFUSGSGNU2DDQVGBIPNLO3X/graph.json","fetch_events":"https://pith.science/api/pith-number/QI3MFUSGSGNU2DDQVGBIPNLO3X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QI3MFUSGSGNU2DDQVGBIPNLO3X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QI3MFUSGSGNU2DDQVGBIPNLO3X/action/storage_attestation","attest_author":"https://pith.science/pith/QI3MFUSGSGNU2DDQVGBIPNLO3X/action/author_attestation","sign_citation":"https://pith.science/pith/QI3MFUSGSGNU2DDQVGBIPNLO3X/action/citation_signature","submit_replication":"https://pith.science/pith/QI3MFUSGSGNU2DDQVGBIPNLO3X/action/replication_record"}},"created_at":"2026-07-05T08:20:10.812943+00:00","updated_at":"2026-07-05T08:20:10.812943+00:00"}