{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UMHIU6IP577AME5SSZYO2QNWXZ","short_pith_number":"pith:UMHIU6IP","schema_version":"1.0","canonical_sha256":"a30e8a790feffe0613b29670ed41b6be44fc8b0d7b3ac57c88a5a7a94385c688","source":{"kind":"arxiv","id":"2308.10835","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Recommender Systems with Large Language Model Reasoning Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hongyan Hao, James Y Zhang, Jinjie Gu, Jun Zhou, Longfei Li, Qing Cui, Sheng Li, Simeng Wang, Siqiao Xue, Xin Ouyang, Yan Wang, Yue Shen, Zhixuan Chu","submitted_at":"2023-08-21T16:35:19Z","abstract_excerpt":"Recommendation systems aim to provide users with relevant suggestions, but often lack interpretability and fail to capture higher-level semantic relationships between user behaviors and profiles. In this paper, we propose a novel approach that leverages large language models (LLMs) to construct personalized reasoning graphs. These graphs link a user's profile and behavioral sequences through causal and logical inferences, representing the user's interests in an interpretable way. Our approach, LLM reasoning graphs (LLMRG), has four components: chained graph reasoning, divergent extension, self"},"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":"2308.10835","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-08-21T16:35:19Z","cross_cats_sorted":[],"title_canon_sha256":"91f60e89147c47ed35d7552f058b5c43b6ff3cc368f91f94fb4d4410c524841b","abstract_canon_sha256":"431509905fa88fd4b580f0c72691b6be08b1c179f90356aa5d9cdce539caa8cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:12.596275Z","signature_b64":"ypwdbHVjr6B0C9WFA956TNYDPy+ZJro/BBv8xqiGrvj6Q8uZImh3vwZ0lNFnPTVvcCRVyOE9RgOkNNTI3Yr0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a30e8a790feffe0613b29670ed41b6be44fc8b0d7b3ac57c88a5a7a94385c688","last_reissued_at":"2026-07-05T07:37:12.595782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:12.595782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Recommender Systems with Large Language Model Reasoning Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hongyan Hao, James Y Zhang, Jinjie Gu, Jun Zhou, Longfei Li, Qing Cui, Sheng Li, Simeng Wang, Siqiao Xue, Xin Ouyang, Yan Wang, Yue Shen, Zhixuan Chu","submitted_at":"2023-08-21T16:35:19Z","abstract_excerpt":"Recommendation systems aim to provide users with relevant suggestions, but often lack interpretability and fail to capture higher-level semantic relationships between user behaviors and profiles. In this paper, we propose a novel approach that leverages large language models (LLMs) to construct personalized reasoning graphs. These graphs link a user's profile and behavioral sequences through causal and logical inferences, representing the user's interests in an interpretable way. Our approach, LLM reasoning graphs (LLMRG), has four components: chained graph reasoning, divergent extension, self"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10835","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/2308.10835/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":"2308.10835","created_at":"2026-07-05T07:37:12.595841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10835v2","created_at":"2026-07-05T07:37:12.595841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10835","created_at":"2026-07-05T07:37:12.595841+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMHIU6IP577A","created_at":"2026-07-05T07:37:12.595841+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMHIU6IP577AME5S","created_at":"2026-07-05T07:37:12.595841+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMHIU6IP","created_at":"2026-07-05T07:37:12.595841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27856","citing_title":"Fine-Tuned LLM as a Complementary Predictor Improving Ads System","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01728","citing_title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":101,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UMHIU6IP577AME5SSZYO2QNWXZ","json":"https://pith.science/pith/UMHIU6IP577AME5SSZYO2QNWXZ.json","graph_json":"https://pith.science/api/pith-number/UMHIU6IP577AME5SSZYO2QNWXZ/graph.json","events_json":"https://pith.science/api/pith-number/UMHIU6IP577AME5SSZYO2QNWXZ/events.json","paper":"https://pith.science/paper/UMHIU6IP"},"agent_actions":{"view_html":"https://pith.science/pith/UMHIU6IP577AME5SSZYO2QNWXZ","download_json":"https://pith.science/pith/UMHIU6IP577AME5SSZYO2QNWXZ.json","view_paper":"https://pith.science/paper/UMHIU6IP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10835&json=true","fetch_graph":"https://pith.science/api/pith-number/UMHIU6IP577AME5SSZYO2QNWXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/UMHIU6IP577AME5SSZYO2QNWXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMHIU6IP577AME5SSZYO2QNWXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMHIU6IP577AME5SSZYO2QNWXZ/action/storage_attestation","attest_author":"https://pith.science/pith/UMHIU6IP577AME5SSZYO2QNWXZ/action/author_attestation","sign_citation":"https://pith.science/pith/UMHIU6IP577AME5SSZYO2QNWXZ/action/citation_signature","submit_replication":"https://pith.science/pith/UMHIU6IP577AME5SSZYO2QNWXZ/action/replication_record"}},"created_at":"2026-07-05T07:37:12.595841+00:00","updated_at":"2026-07-05T07:37:12.595841+00:00"}