{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DGXNSAFFGWQNUP3W6SZI7X4QMF","short_pith_number":"pith:DGXNSAFF","schema_version":"1.0","canonical_sha256":"19aed900a535a0da3f76f4b28fdf90614800a97cdd6d103f8323b95896874320","source":{"kind":"arxiv","id":"2306.01958","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Explainability of Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Charu Aggarwal, Jaspal Jannu, Jaykumar Kakkad, Kartik Sharma, Sourav Medya","submitted_at":"2023-06-02T23:36:49Z","abstract_excerpt":"Graph neural networks (GNNs) are powerful graph-based deep-learning models that have gained significant attention and demonstrated remarkable performance in various domains, including natural language processing, drug discovery, and recommendation systems. However, combining feature information and combinatorial graph structures has led to complex non-linear GNN models. Consequently, this has increased the challenges of understanding the workings of GNNs and the underlying reasons behind their predictions. To address this, numerous explainability methods have been proposed to shed light on the"},"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":"2306.01958","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T23:36:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cda2d50b0dc93f0dc527dcc6dcb879a7b83dad0fc7c97b357cb4c84630c5105d","abstract_canon_sha256":"e7a770ef8dced2781f573802bb58bbe13f099876be143ae79476ffebbf575cce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:11.476777Z","signature_b64":"6NvZXjgc2JkTsM7ntessUuKkL7WqNxCTXy1qDvYlXsTskD4iyPOirX9D57ijTufi21mDLdQrkDceNX32/MqgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19aed900a535a0da3f76f4b28fdf90614800a97cdd6d103f8323b95896874320","last_reissued_at":"2026-07-05T06:17:11.476393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:11.476393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Explainability of Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Charu Aggarwal, Jaspal Jannu, Jaykumar Kakkad, Kartik Sharma, Sourav Medya","submitted_at":"2023-06-02T23:36:49Z","abstract_excerpt":"Graph neural networks (GNNs) are powerful graph-based deep-learning models that have gained significant attention and demonstrated remarkable performance in various domains, including natural language processing, drug discovery, and recommendation systems. However, combining feature information and combinatorial graph structures has led to complex non-linear GNN models. Consequently, this has increased the challenges of understanding the workings of GNNs and the underlying reasons behind their predictions. To address this, numerous explainability methods have been proposed to shed light on the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01958","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/2306.01958/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":"2306.01958","created_at":"2026-07-05T06:17:11.476473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01958v1","created_at":"2026-07-05T06:17:11.476473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01958","created_at":"2026-07-05T06:17:11.476473+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGXNSAFFGWQN","created_at":"2026-07-05T06:17:11.476473+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGXNSAFFGWQNUP3W","created_at":"2026-07-05T06:17:11.476473+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGXNSAFF","created_at":"2026-07-05T06:17:11.476473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2210.15304","citing_title":"Explaining the Explainers in Graph Neural Networks: a Comparative Study","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2405.00577","citing_title":"Discovering robust biomarkers of psychiatric disorders from resting-state functional MRI via graph neural networks: A systematic review","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2407.20067","citing_title":"xAI-Drop: Don't Use What You Cannot Explain","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2505.12437","citing_title":"A method for the systematic generation of graph XAI benchmarks via Weisfeiler-Leman coloring","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19915","citing_title":"LLM Agents Make Collective Belief Dynamics Programmable: Challenges and Research Directions","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DGXNSAFFGWQNUP3W6SZI7X4QMF","json":"https://pith.science/pith/DGXNSAFFGWQNUP3W6SZI7X4QMF.json","graph_json":"https://pith.science/api/pith-number/DGXNSAFFGWQNUP3W6SZI7X4QMF/graph.json","events_json":"https://pith.science/api/pith-number/DGXNSAFFGWQNUP3W6SZI7X4QMF/events.json","paper":"https://pith.science/paper/DGXNSAFF"},"agent_actions":{"view_html":"https://pith.science/pith/DGXNSAFFGWQNUP3W6SZI7X4QMF","download_json":"https://pith.science/pith/DGXNSAFFGWQNUP3W6SZI7X4QMF.json","view_paper":"https://pith.science/paper/DGXNSAFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01958&json=true","fetch_graph":"https://pith.science/api/pith-number/DGXNSAFFGWQNUP3W6SZI7X4QMF/graph.json","fetch_events":"https://pith.science/api/pith-number/DGXNSAFFGWQNUP3W6SZI7X4QMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGXNSAFFGWQNUP3W6SZI7X4QMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGXNSAFFGWQNUP3W6SZI7X4QMF/action/storage_attestation","attest_author":"https://pith.science/pith/DGXNSAFFGWQNUP3W6SZI7X4QMF/action/author_attestation","sign_citation":"https://pith.science/pith/DGXNSAFFGWQNUP3W6SZI7X4QMF/action/citation_signature","submit_replication":"https://pith.science/pith/DGXNSAFFGWQNUP3W6SZI7X4QMF/action/replication_record"}},"created_at":"2026-07-05T06:17:11.476473+00:00","updated_at":"2026-07-05T06:17:11.476473+00:00"}