{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:56DKATJ7SB72QYWQM6ROYRO2ZG","short_pith_number":"pith:56DKATJ7","schema_version":"1.0","canonical_sha256":"ef86a04d3f907fa862d067a2ec45dac9963d5753b095b5ae6b6b549a9ed2539f","source":{"kind":"arxiv","id":"2412.04107","version":2},"attestation_state":"computed","paper":{"title":"Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jie Jiang, Junwei Pan, Maolin Wang, Pengyue Jia, Wanyu Wang, Xiangyu Zhao, Xiaotian Li, Yuhao Wang, Zhixiang Feng","submitted_at":"2024-12-05T12:17:56Z","abstract_excerpt":"Sequential Recommendation (SR) aims to leverage the sequential patterns in users' historical interactions to accurately track their preferences. However, the primary reliance of existing SR methods on collaborative data results in challenges such as the cold-start problem and sub-optimal performance. Concurrently, despite the proven effectiveness of large language models (LLMs), their integration into commercial recommender systems is impeded by issues such as high inference latency, incomplete capture of all distribution statistics, and catastrophic forgetting. To address these issues, we int"},"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":"2412.04107","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-05T12:17:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d29d1fbc06792b8c6b799efa1081e87b775ac0a334c3c21c043fa359617a3293","abstract_canon_sha256":"c8649a2385c77583ab644e86113f8ac1d407185c76ca843ce201b92a6b0eda52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:14.294239Z","signature_b64":"HjyTRRMndWnpfsjStEa9JkK/PD8Mvunu/gUHILY+KfZM37PG0ACDZVfmcWRbx+55yQxeSOZejg851MWMSn5/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef86a04d3f907fa862d067a2ec45dac9963d5753b095b5ae6b6b549a9ed2539f","last_reissued_at":"2026-07-05T10:54:14.293742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:14.293742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jie Jiang, Junwei Pan, Maolin Wang, Pengyue Jia, Wanyu Wang, Xiangyu Zhao, Xiaotian Li, Yuhao Wang, Zhixiang Feng","submitted_at":"2024-12-05T12:17:56Z","abstract_excerpt":"Sequential Recommendation (SR) aims to leverage the sequential patterns in users' historical interactions to accurately track their preferences. However, the primary reliance of existing SR methods on collaborative data results in challenges such as the cold-start problem and sub-optimal performance. Concurrently, despite the proven effectiveness of large language models (LLMs), their integration into commercial recommender systems is impeded by issues such as high inference latency, incomplete capture of all distribution statistics, and catastrophic forgetting. To address these issues, we int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04107","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/2412.04107/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":"2412.04107","created_at":"2026-07-05T10:54:14.293805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04107v2","created_at":"2026-07-05T10:54:14.293805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04107","created_at":"2026-07-05T10:54:14.293805+00:00"},{"alias_kind":"pith_short_12","alias_value":"56DKATJ7SB72","created_at":"2026-07-05T10:54:14.293805+00:00"},{"alias_kind":"pith_short_16","alias_value":"56DKATJ7SB72QYWQ","created_at":"2026-07-05T10:54:14.293805+00:00"},{"alias_kind":"pith_short_8","alias_value":"56DKATJ7","created_at":"2026-07-05T10:54:14.293805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13432","citing_title":"Large Language Model Enhanced Recommender Systems: A Survey","ref_index":77,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/56DKATJ7SB72QYWQM6ROYRO2ZG","json":"https://pith.science/pith/56DKATJ7SB72QYWQM6ROYRO2ZG.json","graph_json":"https://pith.science/api/pith-number/56DKATJ7SB72QYWQM6ROYRO2ZG/graph.json","events_json":"https://pith.science/api/pith-number/56DKATJ7SB72QYWQM6ROYRO2ZG/events.json","paper":"https://pith.science/paper/56DKATJ7"},"agent_actions":{"view_html":"https://pith.science/pith/56DKATJ7SB72QYWQM6ROYRO2ZG","download_json":"https://pith.science/pith/56DKATJ7SB72QYWQM6ROYRO2ZG.json","view_paper":"https://pith.science/paper/56DKATJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04107&json=true","fetch_graph":"https://pith.science/api/pith-number/56DKATJ7SB72QYWQM6ROYRO2ZG/graph.json","fetch_events":"https://pith.science/api/pith-number/56DKATJ7SB72QYWQM6ROYRO2ZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56DKATJ7SB72QYWQM6ROYRO2ZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56DKATJ7SB72QYWQM6ROYRO2ZG/action/storage_attestation","attest_author":"https://pith.science/pith/56DKATJ7SB72QYWQM6ROYRO2ZG/action/author_attestation","sign_citation":"https://pith.science/pith/56DKATJ7SB72QYWQM6ROYRO2ZG/action/citation_signature","submit_replication":"https://pith.science/pith/56DKATJ7SB72QYWQM6ROYRO2ZG/action/replication_record"}},"created_at":"2026-07-05T10:54:14.293805+00:00","updated_at":"2026-07-05T10:54:14.293805+00:00"}