{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B5CV3WT5QJSE34RLSI7XO265YC","short_pith_number":"pith:B5CV3WT5","schema_version":"1.0","canonical_sha256":"0f455dda7d82644df22b923f776bddc087d9c313942247550175f67f5a5ecbb7","source":{"kind":"arxiv","id":"2605.28175","version":1},"attestation_state":"computed","paper":{"title":"Mixture-of-Experts Knowledge Graph Retrieval-Augmented Generation for Multi-Agent LLM-based Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chengyi Liu, See-kiong Ng, Shanru Lin, Shijie Wang, Wenqi Fan, Xu Xin, Yujuan Ding","submitted_at":"2026-05-27T08:56:57Z","abstract_excerpt":"Large language models (LLMs) have recently been adopted for recommendations due to their ability to understand user intent and item semantics. However, LLM-based recommender systems often rely on parametric knowledge and suffer from outdated knowledge, motivating knowledge graph retrieval-augmented generation (KG-RAG) to ground recommendations on structured, up-to-date KGs. Despite this promise, effective KG-RAG in recommendations faces great challenges. First, users' queries vary in complexity and require KG knowledge at different granularities, whereas existing methods adopt a one-size-fits-"},"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":"2605.28175","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-27T08:56:57Z","cross_cats_sorted":[],"title_canon_sha256":"69e2647f2dcc8d2c8b607d67c0fa45f4f7c3e1ae6ab42197fb1c9da08370f3cf","abstract_canon_sha256":"2fb80bdd2148028f6f5b8606cbf564b0ccb81d694eed1391503949eb7c3e4656"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:01.288348Z","signature_b64":"ZeVjtgY7Olk94/5DxG1RrkHEbTfYEPuW5byiY1a3wAjzxV14topypDgm/ErNJM98eFpZyvMcmBFCv+GvOkfFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f455dda7d82644df22b923f776bddc087d9c313942247550175f67f5a5ecbb7","last_reissued_at":"2026-05-28T01:05:01.287928Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:01.287928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixture-of-Experts Knowledge Graph Retrieval-Augmented Generation for Multi-Agent LLM-based Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chengyi Liu, See-kiong Ng, Shanru Lin, Shijie Wang, Wenqi Fan, Xu Xin, Yujuan Ding","submitted_at":"2026-05-27T08:56:57Z","abstract_excerpt":"Large language models (LLMs) have recently been adopted for recommendations due to their ability to understand user intent and item semantics. However, LLM-based recommender systems often rely on parametric knowledge and suffer from outdated knowledge, motivating knowledge graph retrieval-augmented generation (KG-RAG) to ground recommendations on structured, up-to-date KGs. Despite this promise, effective KG-RAG in recommendations faces great challenges. First, users' queries vary in complexity and require KG knowledge at different granularities, whereas existing methods adopt a one-size-fits-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28175","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/2605.28175/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":"2605.28175","created_at":"2026-05-28T01:05:01.287987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28175v1","created_at":"2026-05-28T01:05:01.287987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28175","created_at":"2026-05-28T01:05:01.287987+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5CV3WT5QJSE","created_at":"2026-05-28T01:05:01.287987+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5CV3WT5QJSE34RL","created_at":"2026-05-28T01:05:01.287987+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5CV3WT5","created_at":"2026-05-28T01:05:01.287987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5CV3WT5QJSE34RLSI7XO265YC","json":"https://pith.science/pith/B5CV3WT5QJSE34RLSI7XO265YC.json","graph_json":"https://pith.science/api/pith-number/B5CV3WT5QJSE34RLSI7XO265YC/graph.json","events_json":"https://pith.science/api/pith-number/B5CV3WT5QJSE34RLSI7XO265YC/events.json","paper":"https://pith.science/paper/B5CV3WT5"},"agent_actions":{"view_html":"https://pith.science/pith/B5CV3WT5QJSE34RLSI7XO265YC","download_json":"https://pith.science/pith/B5CV3WT5QJSE34RLSI7XO265YC.json","view_paper":"https://pith.science/paper/B5CV3WT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28175&json=true","fetch_graph":"https://pith.science/api/pith-number/B5CV3WT5QJSE34RLSI7XO265YC/graph.json","fetch_events":"https://pith.science/api/pith-number/B5CV3WT5QJSE34RLSI7XO265YC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5CV3WT5QJSE34RLSI7XO265YC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5CV3WT5QJSE34RLSI7XO265YC/action/storage_attestation","attest_author":"https://pith.science/pith/B5CV3WT5QJSE34RLSI7XO265YC/action/author_attestation","sign_citation":"https://pith.science/pith/B5CV3WT5QJSE34RLSI7XO265YC/action/citation_signature","submit_replication":"https://pith.science/pith/B5CV3WT5QJSE34RLSI7XO265YC/action/replication_record"}},"created_at":"2026-05-28T01:05:01.287987+00:00","updated_at":"2026-05-28T01:05:01.287987+00:00"}