{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SJMXGVBCRDOJN4JEGPNJFXLXXB","short_pith_number":"pith:SJMXGVBC","schema_version":"1.0","canonical_sha256":"925973542288dc96f12433da92dd77b861d9d5d9830c5968b0d566e61a733ea4","source":{"kind":"arxiv","id":"2305.07001","version":1},"attestation_state":"computed","paper":{"title":"Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Ji-Rong Wen, Junjie Zhang, Leyu Lin, Ruobing Xie, Wayne Xin Zhao, Yupeng Hou","submitted_at":"2023-05-11T17:39:07Z","abstract_excerpt":"In the past decades, recommender systems have attracted much attention in both research and industry communities, and a large number of studies have been devoted to developing effective recommendation models. Basically speaking, these models mainly learn the underlying user preference from historical behavior data, and then estimate the user-item matching relationships for recommendations. Inspired by the recent progress on large language models (LLMs), we take a different approach to developing the recommendation models, considering recommendation as instruction following by LLMs. The key ide"},"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":"2305.07001","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-11T17:39:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b379fff5d94c378df3ef94036c463997611785bc0c54ae3a4d9ab06d73fa1512","abstract_canon_sha256":"a63bfd23d41e4e0bb58c416677fa1563f635899d9e2e5b216d20206cfe54f091"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:18.432240Z","signature_b64":"v3HoJBqeI7NcS5wo1LYV6cV5nkXIgCaU19QRB/aeQ8W48zNGpE0iN67bO7IDMeGw5HL5/z3DHS2JjurELwGVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"925973542288dc96f12433da92dd77b861d9d5d9830c5968b0d566e61a733ea4","last_reissued_at":"2026-07-05T06:09:18.431831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:18.431831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Ji-Rong Wen, Junjie Zhang, Leyu Lin, Ruobing Xie, Wayne Xin Zhao, Yupeng Hou","submitted_at":"2023-05-11T17:39:07Z","abstract_excerpt":"In the past decades, recommender systems have attracted much attention in both research and industry communities, and a large number of studies have been devoted to developing effective recommendation models. Basically speaking, these models mainly learn the underlying user preference from historical behavior data, and then estimate the user-item matching relationships for recommendations. Inspired by the recent progress on large language models (LLMs), we take a different approach to developing the recommendation models, considering recommendation as instruction following by LLMs. The key ide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07001","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/2305.07001/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":"2305.07001","created_at":"2026-07-05T06:09:18.431887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.07001v1","created_at":"2026-07-05T06:09:18.431887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07001","created_at":"2026-07-05T06:09:18.431887+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJMXGVBCRDOJ","created_at":"2026-07-05T06:09:18.431887+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJMXGVBCRDOJN4JE","created_at":"2026-07-05T06:09:18.431887+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJMXGVBC","created_at":"2026-07-05T06:09:18.431887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27856","citing_title":"Fine-Tuned LLM as a Complementary Predictor Improving Ads System","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2403.03952","citing_title":"Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21969","citing_title":"LLM Retrieval for Stable and Predictable Ad Recommendations","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14401","citing_title":"Agentic Recommender System with Hierarchical Belief-State Memory","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14401","citing_title":"Agentic Recommender System with Hierarchical Belief-State Memory","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJMXGVBCRDOJN4JEGPNJFXLXXB","json":"https://pith.science/pith/SJMXGVBCRDOJN4JEGPNJFXLXXB.json","graph_json":"https://pith.science/api/pith-number/SJMXGVBCRDOJN4JEGPNJFXLXXB/graph.json","events_json":"https://pith.science/api/pith-number/SJMXGVBCRDOJN4JEGPNJFXLXXB/events.json","paper":"https://pith.science/paper/SJMXGVBC"},"agent_actions":{"view_html":"https://pith.science/pith/SJMXGVBCRDOJN4JEGPNJFXLXXB","download_json":"https://pith.science/pith/SJMXGVBCRDOJN4JEGPNJFXLXXB.json","view_paper":"https://pith.science/paper/SJMXGVBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.07001&json=true","fetch_graph":"https://pith.science/api/pith-number/SJMXGVBCRDOJN4JEGPNJFXLXXB/graph.json","fetch_events":"https://pith.science/api/pith-number/SJMXGVBCRDOJN4JEGPNJFXLXXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJMXGVBCRDOJN4JEGPNJFXLXXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJMXGVBCRDOJN4JEGPNJFXLXXB/action/storage_attestation","attest_author":"https://pith.science/pith/SJMXGVBCRDOJN4JEGPNJFXLXXB/action/author_attestation","sign_citation":"https://pith.science/pith/SJMXGVBCRDOJN4JEGPNJFXLXXB/action/citation_signature","submit_replication":"https://pith.science/pith/SJMXGVBCRDOJN4JEGPNJFXLXXB/action/replication_record"}},"created_at":"2026-07-05T06:09:18.431887+00:00","updated_at":"2026-07-05T06:09:18.431887+00:00"}