{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VLCMU65G42DGAPZUVMFHJ3H3P6","short_pith_number":"pith:VLCMU65G","schema_version":"1.0","canonical_sha256":"aac4ca7ba6e686603f34ab0a74ecfb7f9298b5914353884581f889fad951c2c4","source":{"kind":"arxiv","id":"2505.18120","version":1},"attestation_state":"computed","paper":{"title":"Bidirectional Knowledge Distillation for Enhancing 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":"Dongsheng Li, Guangping Zhang, Hansu Gu, Jiahao Liu, Jiongran Wu, Li Shang, Mingzhe Han, Ning Gu, Peng Zhang, Tun Lu","submitted_at":"2025-05-23T17:21:14Z","abstract_excerpt":"Large language models (LLMs) have demonstrated exceptional performance in understanding and generating semantic patterns, making them promising candidates for sequential recommendation tasks. However, when combined with conventional recommendation models (CRMs), LLMs often face challenges related to high inference costs and static knowledge transfer methods. In this paper, we propose a novel mutual distillation framework, LLMD4Rec, that fosters dynamic and bidirectional knowledge exchange between LLM-centric and CRM-based recommendation systems. Unlike traditional unidirectional distillation m"},"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":"2505.18120","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-23T17:21:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"53c97fbc553ab1f144168b3a018f8d54633a8414f009d4bdea0041d6e58e3ac8","abstract_canon_sha256":"b38d186f022ff9767e4d478378ae4220b77df3cb27d75f8025383833606280eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:36.885929Z","signature_b64":"VmbGPwguuC59eDysXPHKK0gamROZLsHQfnj/uSAXfSv5zfjvzZO6DcTmFdnMNbRydSs4ep2fLKdVhPaRfc6lCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aac4ca7ba6e686603f34ab0a74ecfb7f9298b5914353884581f889fad951c2c4","last_reissued_at":"2026-07-05T11:08:36.885459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:36.885459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bidirectional Knowledge Distillation for Enhancing 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":"Dongsheng Li, Guangping Zhang, Hansu Gu, Jiahao Liu, Jiongran Wu, Li Shang, Mingzhe Han, Ning Gu, Peng Zhang, Tun Lu","submitted_at":"2025-05-23T17:21:14Z","abstract_excerpt":"Large language models (LLMs) have demonstrated exceptional performance in understanding and generating semantic patterns, making them promising candidates for sequential recommendation tasks. However, when combined with conventional recommendation models (CRMs), LLMs often face challenges related to high inference costs and static knowledge transfer methods. In this paper, we propose a novel mutual distillation framework, LLMD4Rec, that fosters dynamic and bidirectional knowledge exchange between LLM-centric and CRM-based recommendation systems. Unlike traditional unidirectional distillation m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18120","kind":"arxiv","version":1},"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/2505.18120/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":"2505.18120","created_at":"2026-07-05T11:08:36.885513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18120v1","created_at":"2026-07-05T11:08:36.885513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18120","created_at":"2026-07-05T11:08:36.885513+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLCMU65G42DG","created_at":"2026-07-05T11:08:36.885513+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLCMU65G42DGAPZU","created_at":"2026-07-05T11:08:36.885513+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLCMU65G","created_at":"2026-07-05T11:08:36.885513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20065","citing_title":"From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLCMU65G42DGAPZUVMFHJ3H3P6","json":"https://pith.science/pith/VLCMU65G42DGAPZUVMFHJ3H3P6.json","graph_json":"https://pith.science/api/pith-number/VLCMU65G42DGAPZUVMFHJ3H3P6/graph.json","events_json":"https://pith.science/api/pith-number/VLCMU65G42DGAPZUVMFHJ3H3P6/events.json","paper":"https://pith.science/paper/VLCMU65G"},"agent_actions":{"view_html":"https://pith.science/pith/VLCMU65G42DGAPZUVMFHJ3H3P6","download_json":"https://pith.science/pith/VLCMU65G42DGAPZUVMFHJ3H3P6.json","view_paper":"https://pith.science/paper/VLCMU65G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18120&json=true","fetch_graph":"https://pith.science/api/pith-number/VLCMU65G42DGAPZUVMFHJ3H3P6/graph.json","fetch_events":"https://pith.science/api/pith-number/VLCMU65G42DGAPZUVMFHJ3H3P6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLCMU65G42DGAPZUVMFHJ3H3P6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLCMU65G42DGAPZUVMFHJ3H3P6/action/storage_attestation","attest_author":"https://pith.science/pith/VLCMU65G42DGAPZUVMFHJ3H3P6/action/author_attestation","sign_citation":"https://pith.science/pith/VLCMU65G42DGAPZUVMFHJ3H3P6/action/citation_signature","submit_replication":"https://pith.science/pith/VLCMU65G42DGAPZUVMFHJ3H3P6/action/replication_record"}},"created_at":"2026-07-05T11:08:36.885513+00:00","updated_at":"2026-07-05T11:08:36.885513+00:00"}