{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AQ4RV7GY2MMTWTFOTNOX7P7FLG","short_pith_number":"pith:AQ4RV7GY","schema_version":"1.0","canonical_sha256":"04391afcd8d3193b4cae9b5d7fbfe559af0f35fef5c85a2ef47b8fdb28217e89","source":{"kind":"arxiv","id":"2605.31010","version":1},"attestation_state":"computed","paper":{"title":"MoG: Mixture of Experts for Graph-based Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuang Zhou, Di Yin, Linhao Luo, Siyu An, Xiao Huang, Xing Sun, Zheng Yuan","submitted_at":"2026-05-29T08:43:12Z","abstract_excerpt":"Retrieval-augmented generation is intensively studied to ground large language models on external evidence. However, retrieving from a unified knowledge base could inevitably introduce irrelevant information that may mislead generation for complex reasoning. Inspired by the conditional computation of mixture of experts (MoE), where a router sparsely selects specialized experts alongside shared ones for each input, we propose \\textbf{M}ixture \\textbf{o}f experts for \\textbf{G}raph-based Retrieval-Augmented Generation, i.e., \\textbf{MoG}. It organizes knowledge into two core components: (i) dive"},"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":"2605.31010","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T08:43:12Z","cross_cats_sorted":[],"title_canon_sha256":"b752fe1a22c31432b2baf5458cfe1988ee68848adf8b11ba64faaf4fa5396b6c","abstract_canon_sha256":"d2c8489cb9290ccd3686000da06fd385442c80c7ed8313ea6a2e5fb7a16c5dfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:30.541376Z","signature_b64":"Ay/Al5ZV+beieG+jK6IkLI5g2OUUW7XbdIH3LvtKp66hnyECS/gq13GemJZMcAh7ffl9IHsVEY7/mLuxoMm3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04391afcd8d3193b4cae9b5d7fbfe559af0f35fef5c85a2ef47b8fdb28217e89","last_reissued_at":"2026-06-01T01:03:30.540556Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:30.540556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoG: Mixture of Experts for Graph-based Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuang Zhou, Di Yin, Linhao Luo, Siyu An, Xiao Huang, Xing Sun, Zheng Yuan","submitted_at":"2026-05-29T08:43:12Z","abstract_excerpt":"Retrieval-augmented generation is intensively studied to ground large language models on external evidence. However, retrieving from a unified knowledge base could inevitably introduce irrelevant information that may mislead generation for complex reasoning. Inspired by the conditional computation of mixture of experts (MoE), where a router sparsely selects specialized experts alongside shared ones for each input, we propose \\textbf{M}ixture \\textbf{o}f experts for \\textbf{G}raph-based Retrieval-Augmented Generation, i.e., \\textbf{MoG}. It organizes knowledge into two core components: (i) dive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31010","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/2605.31010/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":"2605.31010","created_at":"2026-06-01T01:03:30.540672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31010v1","created_at":"2026-06-01T01:03:30.540672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31010","created_at":"2026-06-01T01:03:30.540672+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQ4RV7GY2MMT","created_at":"2026-06-01T01:03:30.540672+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQ4RV7GY2MMTWTFO","created_at":"2026-06-01T01:03:30.540672+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQ4RV7GY","created_at":"2026-06-01T01:03:30.540672+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/AQ4RV7GY2MMTWTFOTNOX7P7FLG","json":"https://pith.science/pith/AQ4RV7GY2MMTWTFOTNOX7P7FLG.json","graph_json":"https://pith.science/api/pith-number/AQ4RV7GY2MMTWTFOTNOX7P7FLG/graph.json","events_json":"https://pith.science/api/pith-number/AQ4RV7GY2MMTWTFOTNOX7P7FLG/events.json","paper":"https://pith.science/paper/AQ4RV7GY"},"agent_actions":{"view_html":"https://pith.science/pith/AQ4RV7GY2MMTWTFOTNOX7P7FLG","download_json":"https://pith.science/pith/AQ4RV7GY2MMTWTFOTNOX7P7FLG.json","view_paper":"https://pith.science/paper/AQ4RV7GY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31010&json=true","fetch_graph":"https://pith.science/api/pith-number/AQ4RV7GY2MMTWTFOTNOX7P7FLG/graph.json","fetch_events":"https://pith.science/api/pith-number/AQ4RV7GY2MMTWTFOTNOX7P7FLG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQ4RV7GY2MMTWTFOTNOX7P7FLG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQ4RV7GY2MMTWTFOTNOX7P7FLG/action/storage_attestation","attest_author":"https://pith.science/pith/AQ4RV7GY2MMTWTFOTNOX7P7FLG/action/author_attestation","sign_citation":"https://pith.science/pith/AQ4RV7GY2MMTWTFOTNOX7P7FLG/action/citation_signature","submit_replication":"https://pith.science/pith/AQ4RV7GY2MMTWTFOTNOX7P7FLG/action/replication_record"}},"created_at":"2026-06-01T01:03:30.540672+00:00","updated_at":"2026-06-01T01:03:30.540672+00:00"}