{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZB4K4QLJNUCGIBOMCEV2KWSZPO","short_pith_number":"pith:ZB4K4QLJ","schema_version":"1.0","canonical_sha256":"c878ae41696d046405cc112ba55a597bb109813ba9845c09777d9e150827bbe2","source":{"kind":"arxiv","id":"2407.15351","version":2},"attestation_state":"computed","paper":{"title":"LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Dongsheng Luo, Hua Wei, Jennifer Neville, Jiaxing Zhang, Jiayi Liu","submitted_at":"2024-07-22T03:36:38Z","abstract_excerpt":"Recent studies seek to provide Graph Neural Network (GNN) interpretability via multiple unsupervised learning models. Due to the scarcity of datasets, current methods easily suffer from learning bias. To solve this problem, we embed a Large Language Model (LLM) as knowledge into the GNN explanation network to avoid the learning bias problem. We inject LLM as a Bayesian Inference (BI) module to mitigate learning bias. The efficacy of the BI module has been proven both theoretically and experimentally. We conduct experiments on both synthetic and real-world datasets. The innovation of our work l"},"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":"2407.15351","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-22T03:36:38Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2103f295637d3bb5c4fc0db5d277a35f5134bc11beb762ebf84d79dec0e9daec","abstract_canon_sha256":"7e96cbdc69d81633849e3d34a01156ad357868278bd3e67b39f05cdca7307115"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:23.026786Z","signature_b64":"oh5lJbQwmiAKdDX+y9k2UAwErKJIPEHOLUoczknZZ61Nzr2bYy9RQCXluKKTNjxDNFtI4hFN1Kp+YlNgEYdyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c878ae41696d046405cc112ba55a597bb109813ba9845c09777d9e150827bbe2","last_reissued_at":"2026-07-05T08:47:23.026287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:23.026287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Dongsheng Luo, Hua Wei, Jennifer Neville, Jiaxing Zhang, Jiayi Liu","submitted_at":"2024-07-22T03:36:38Z","abstract_excerpt":"Recent studies seek to provide Graph Neural Network (GNN) interpretability via multiple unsupervised learning models. Due to the scarcity of datasets, current methods easily suffer from learning bias. To solve this problem, we embed a Large Language Model (LLM) as knowledge into the GNN explanation network to avoid the learning bias problem. We inject LLM as a Bayesian Inference (BI) module to mitigate learning bias. The efficacy of the BI module has been proven both theoretically and experimentally. We conduct experiments on both synthetic and real-world datasets. The innovation of our work l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15351","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/2407.15351/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":"2407.15351","created_at":"2026-07-05T08:47:23.026360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15351v2","created_at":"2026-07-05T08:47:23.026360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15351","created_at":"2026-07-05T08:47:23.026360+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZB4K4QLJNUCG","created_at":"2026-07-05T08:47:23.026360+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZB4K4QLJNUCGIBOM","created_at":"2026-07-05T08:47:23.026360+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZB4K4QLJ","created_at":"2026-07-05T08:47:23.026360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.07117","citing_title":"From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZB4K4QLJNUCGIBOMCEV2KWSZPO","json":"https://pith.science/pith/ZB4K4QLJNUCGIBOMCEV2KWSZPO.json","graph_json":"https://pith.science/api/pith-number/ZB4K4QLJNUCGIBOMCEV2KWSZPO/graph.json","events_json":"https://pith.science/api/pith-number/ZB4K4QLJNUCGIBOMCEV2KWSZPO/events.json","paper":"https://pith.science/paper/ZB4K4QLJ"},"agent_actions":{"view_html":"https://pith.science/pith/ZB4K4QLJNUCGIBOMCEV2KWSZPO","download_json":"https://pith.science/pith/ZB4K4QLJNUCGIBOMCEV2KWSZPO.json","view_paper":"https://pith.science/paper/ZB4K4QLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15351&json=true","fetch_graph":"https://pith.science/api/pith-number/ZB4K4QLJNUCGIBOMCEV2KWSZPO/graph.json","fetch_events":"https://pith.science/api/pith-number/ZB4K4QLJNUCGIBOMCEV2KWSZPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZB4K4QLJNUCGIBOMCEV2KWSZPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZB4K4QLJNUCGIBOMCEV2KWSZPO/action/storage_attestation","attest_author":"https://pith.science/pith/ZB4K4QLJNUCGIBOMCEV2KWSZPO/action/author_attestation","sign_citation":"https://pith.science/pith/ZB4K4QLJNUCGIBOMCEV2KWSZPO/action/citation_signature","submit_replication":"https://pith.science/pith/ZB4K4QLJNUCGIBOMCEV2KWSZPO/action/replication_record"}},"created_at":"2026-07-05T08:47:23.026360+00:00","updated_at":"2026-07-05T08:47:23.026360+00:00"}