{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KR43MMWCODLNOOIY5OTAWHSQLO","short_pith_number":"pith:KR43MMWC","schema_version":"1.0","canonical_sha256":"5479b632c270d6d73918eba60b1e505ba97b35b49c83e1603af60fd1f11182d5","source":{"kind":"arxiv","id":"2506.05069","version":2},"attestation_state":"computed","paper":{"title":"Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Fengli Xu, Keyu Zhao, Yong Li","submitted_at":"2025-06-05T14:16:44Z","abstract_excerpt":"Driven by advances in Large Language Models (LLMs), integrating them into recommendation tasks has gained interest due to their strong semantic understanding and prompt flexibility. Prior work encoded user-item interactions or metadata into prompts for recommendations. In parallel, LLM reasoning, boosted by test-time scaling and reinforcement learning, has excelled in fields like mathematics and code, where reasoning traces and correctness signals are clear, enabling high performance and interpretability. However, directly applying these reasoning methods to recommendation is ineffective becau"},"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":"2506.05069","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-05T14:16:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc46ac9d12ff676df34d33920398cbac89ca233a4187568854def478c34e32ad","abstract_canon_sha256":"70d3f3a037bea5874fd3e076e7c3d2aa8f7443b3b48305a53fa97f6e4b6f6381"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:23.228851Z","signature_b64":"7qKMck2FoORdV63obLHho0btiuv/L5ygRp5ktoh4MFR7yEgaZISog6dwASgY7KplPaHk2VAqb/kLznId7EYKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5479b632c270d6d73918eba60b1e505ba97b35b49c83e1603af60fd1f11182d5","last_reissued_at":"2026-07-05T11:18:23.228371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:23.228371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Fengli Xu, Keyu Zhao, Yong Li","submitted_at":"2025-06-05T14:16:44Z","abstract_excerpt":"Driven by advances in Large Language Models (LLMs), integrating them into recommendation tasks has gained interest due to their strong semantic understanding and prompt flexibility. Prior work encoded user-item interactions or metadata into prompts for recommendations. In parallel, LLM reasoning, boosted by test-time scaling and reinforcement learning, has excelled in fields like mathematics and code, where reasoning traces and correctness signals are clear, enabling high performance and interpretability. However, directly applying these reasoning methods to recommendation is ineffective becau"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05069","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/2506.05069/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":"2506.05069","created_at":"2026-07-05T11:18:23.228428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05069v2","created_at":"2026-07-05T11:18:23.228428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05069","created_at":"2026-07-05T11:18:23.228428+00:00"},{"alias_kind":"pith_short_12","alias_value":"KR43MMWCODLN","created_at":"2026-07-05T11:18:23.228428+00:00"},{"alias_kind":"pith_short_16","alias_value":"KR43MMWCODLNOOIY","created_at":"2026-07-05T11:18:23.228428+00:00"},{"alias_kind":"pith_short_8","alias_value":"KR43MMWC","created_at":"2026-07-05T11:18:23.228428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14358","citing_title":"Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2510.27157","citing_title":"A Survey on Generative Recommendation: Data, Model, and Tasks","ref_index":236,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03671","citing_title":"User Simulator-Guided Multi-Turn Preference Optimization for Reasoning LLM-based Conversational Recommendation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26760","citing_title":"Factorized Latent Reasoning for LLM-based Recommendation","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KR43MMWCODLNOOIY5OTAWHSQLO","json":"https://pith.science/pith/KR43MMWCODLNOOIY5OTAWHSQLO.json","graph_json":"https://pith.science/api/pith-number/KR43MMWCODLNOOIY5OTAWHSQLO/graph.json","events_json":"https://pith.science/api/pith-number/KR43MMWCODLNOOIY5OTAWHSQLO/events.json","paper":"https://pith.science/paper/KR43MMWC"},"agent_actions":{"view_html":"https://pith.science/pith/KR43MMWCODLNOOIY5OTAWHSQLO","download_json":"https://pith.science/pith/KR43MMWCODLNOOIY5OTAWHSQLO.json","view_paper":"https://pith.science/paper/KR43MMWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05069&json=true","fetch_graph":"https://pith.science/api/pith-number/KR43MMWCODLNOOIY5OTAWHSQLO/graph.json","fetch_events":"https://pith.science/api/pith-number/KR43MMWCODLNOOIY5OTAWHSQLO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KR43MMWCODLNOOIY5OTAWHSQLO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KR43MMWCODLNOOIY5OTAWHSQLO/action/storage_attestation","attest_author":"https://pith.science/pith/KR43MMWCODLNOOIY5OTAWHSQLO/action/author_attestation","sign_citation":"https://pith.science/pith/KR43MMWCODLNOOIY5OTAWHSQLO/action/citation_signature","submit_replication":"https://pith.science/pith/KR43MMWCODLNOOIY5OTAWHSQLO/action/replication_record"}},"created_at":"2026-07-05T11:18:23.228428+00:00","updated_at":"2026-07-05T11:18:23.228428+00:00"}