{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WBZZ2N63RYCU7IC4YXVOCJQGHR","short_pith_number":"pith:WBZZ2N63","schema_version":"1.0","canonical_sha256":"b0739d37db8e054fa05cc5eae126063c77c25f38863f53616a4b28894e260986","source":{"kind":"arxiv","id":"2311.05764","version":1},"attestation_state":"computed","paper":{"title":"Generative Explanations for Graph Neural Network: Methods and Evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jialin Chen, Junchi Yu, Kenza Amara, Rex Ying","submitted_at":"2023-11-09T22:07:15Z","abstract_excerpt":"Graph Neural Networks (GNNs) achieve state-of-the-art performance in various graph-related tasks. However, the black-box nature often limits their interpretability and trustworthiness. Numerous explainability methods have been proposed to uncover the decision-making logic of GNNs, by generating underlying explanatory substructures. In this paper, we conduct a comprehensive review of the existing explanation methods for GNNs from the perspective of graph generation. Specifically, we propose a unified optimization objective for generative explanation methods, comprising two sub-objectives: Attri"},"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":"2311.05764","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-09T22:07:15Z","cross_cats_sorted":[],"title_canon_sha256":"9ae6ad8cdbec8b79fa0a31c7720e328edd0a0f7cd158330b3a40b8c2b2ee8c05","abstract_canon_sha256":"f3ab3b4690f6256699591605921689f11ce298a2191e9751ea736f5f51d9ff0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:22.467967Z","signature_b64":"eQ4CvxfJ2Ci3RniGh+RxO23r7TngLXn3D1yCUx7yNkVIJXdI8tekPxOTcXSvo/EIAvEFBRoqyB404X69h1gkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0739d37db8e054fa05cc5eae126063c77c25f38863f53616a4b28894e260986","last_reissued_at":"2026-07-05T07:11:22.467585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:22.467585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Explanations for Graph Neural Network: Methods and Evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jialin Chen, Junchi Yu, Kenza Amara, Rex Ying","submitted_at":"2023-11-09T22:07:15Z","abstract_excerpt":"Graph Neural Networks (GNNs) achieve state-of-the-art performance in various graph-related tasks. However, the black-box nature often limits their interpretability and trustworthiness. Numerous explainability methods have been proposed to uncover the decision-making logic of GNNs, by generating underlying explanatory substructures. In this paper, we conduct a comprehensive review of the existing explanation methods for GNNs from the perspective of graph generation. Specifically, we propose a unified optimization objective for generative explanation methods, comprising two sub-objectives: Attri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05764","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/2311.05764/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":"2311.05764","created_at":"2026-07-05T07:11:22.467642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.05764v1","created_at":"2026-07-05T07:11:22.467642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05764","created_at":"2026-07-05T07:11:22.467642+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBZZ2N63RYCU","created_at":"2026-07-05T07:11:22.467642+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBZZ2N63RYCU7IC4","created_at":"2026-07-05T07:11:22.467642+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBZZ2N63","created_at":"2026-07-05T07:11:22.467642+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/WBZZ2N63RYCU7IC4YXVOCJQGHR","json":"https://pith.science/pith/WBZZ2N63RYCU7IC4YXVOCJQGHR.json","graph_json":"https://pith.science/api/pith-number/WBZZ2N63RYCU7IC4YXVOCJQGHR/graph.json","events_json":"https://pith.science/api/pith-number/WBZZ2N63RYCU7IC4YXVOCJQGHR/events.json","paper":"https://pith.science/paper/WBZZ2N63"},"agent_actions":{"view_html":"https://pith.science/pith/WBZZ2N63RYCU7IC4YXVOCJQGHR","download_json":"https://pith.science/pith/WBZZ2N63RYCU7IC4YXVOCJQGHR.json","view_paper":"https://pith.science/paper/WBZZ2N63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.05764&json=true","fetch_graph":"https://pith.science/api/pith-number/WBZZ2N63RYCU7IC4YXVOCJQGHR/graph.json","fetch_events":"https://pith.science/api/pith-number/WBZZ2N63RYCU7IC4YXVOCJQGHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBZZ2N63RYCU7IC4YXVOCJQGHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBZZ2N63RYCU7IC4YXVOCJQGHR/action/storage_attestation","attest_author":"https://pith.science/pith/WBZZ2N63RYCU7IC4YXVOCJQGHR/action/author_attestation","sign_citation":"https://pith.science/pith/WBZZ2N63RYCU7IC4YXVOCJQGHR/action/citation_signature","submit_replication":"https://pith.science/pith/WBZZ2N63RYCU7IC4YXVOCJQGHR/action/replication_record"}},"created_at":"2026-07-05T07:11:22.467642+00:00","updated_at":"2026-07-05T07:11:22.467642+00:00"}