{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZIZIQJBNMATCUJDGLOPY4MMTZH","short_pith_number":"pith:ZIZIQJBN","schema_version":"1.0","canonical_sha256":"ca3288242d60262a24665b9f8e3193c9fb800eaf7553ed37971258078d038479","source":{"kind":"arxiv","id":"2401.04829","version":3},"attestation_state":"computed","paper":{"title":"GNNShap: Scalable and Accurate GNN Explanation using Shapley Values","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Ariful Azad, Selahattin Akkas","submitted_at":"2024-01-09T21:26:33Z","abstract_excerpt":"Graph neural networks (GNNs) are popular machine learning models for graphs with many applications across scientific domains. However, GNNs are considered black box models, and it is challenging to understand how the model makes predictions. Game theoric Shapley value approaches are popular explanation methods in other domains but are not well-studied for graphs. Some studies have proposed Shapley value based GNN explanations, yet they have several limitations: they consider limited samples to approximate Shapley values; some mainly focus on small and large coalition sizes, and they are an ord"},"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":"2401.04829","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-09T21:26:33Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"41ddd1910b3c207d2a1856ed9f5c16118a980ea9ddaf31314e1e1240bb8e249e","abstract_canon_sha256":"a8015d4c0bde3857596ad261303eba0d1813dd55f2895525fd4b8310ff654c3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:01.724634Z","signature_b64":"gZZxGHVxzUCXbew4rxijBdqrp01cEwj0DtPDywwEyN+XUlf/8TiHpYTLaNY2rqjAx/ORYrcg1YVJow9CPeouCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca3288242d60262a24665b9f8e3193c9fb800eaf7553ed37971258078d038479","last_reissued_at":"2026-07-05T10:02:01.724161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:01.724161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GNNShap: Scalable and Accurate GNN Explanation using Shapley Values","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Ariful Azad, Selahattin Akkas","submitted_at":"2024-01-09T21:26:33Z","abstract_excerpt":"Graph neural networks (GNNs) are popular machine learning models for graphs with many applications across scientific domains. However, GNNs are considered black box models, and it is challenging to understand how the model makes predictions. Game theoric Shapley value approaches are popular explanation methods in other domains but are not well-studied for graphs. Some studies have proposed Shapley value based GNN explanations, yet they have several limitations: they consider limited samples to approximate Shapley values; some mainly focus on small and large coalition sizes, and they are an ord"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04829","kind":"arxiv","version":3},"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/2401.04829/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":"2401.04829","created_at":"2026-07-05T10:02:01.724223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04829v3","created_at":"2026-07-05T10:02:01.724223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04829","created_at":"2026-07-05T10:02:01.724223+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZIZIQJBNMATC","created_at":"2026-07-05T10:02:01.724223+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZIZIQJBNMATCUJDG","created_at":"2026-07-05T10:02:01.724223+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZIZIQJBN","created_at":"2026-07-05T10:02:01.724223+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/ZIZIQJBNMATCUJDGLOPY4MMTZH","json":"https://pith.science/pith/ZIZIQJBNMATCUJDGLOPY4MMTZH.json","graph_json":"https://pith.science/api/pith-number/ZIZIQJBNMATCUJDGLOPY4MMTZH/graph.json","events_json":"https://pith.science/api/pith-number/ZIZIQJBNMATCUJDGLOPY4MMTZH/events.json","paper":"https://pith.science/paper/ZIZIQJBN"},"agent_actions":{"view_html":"https://pith.science/pith/ZIZIQJBNMATCUJDGLOPY4MMTZH","download_json":"https://pith.science/pith/ZIZIQJBNMATCUJDGLOPY4MMTZH.json","view_paper":"https://pith.science/paper/ZIZIQJBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04829&json=true","fetch_graph":"https://pith.science/api/pith-number/ZIZIQJBNMATCUJDGLOPY4MMTZH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZIZIQJBNMATCUJDGLOPY4MMTZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZIZIQJBNMATCUJDGLOPY4MMTZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZIZIQJBNMATCUJDGLOPY4MMTZH/action/storage_attestation","attest_author":"https://pith.science/pith/ZIZIQJBNMATCUJDGLOPY4MMTZH/action/author_attestation","sign_citation":"https://pith.science/pith/ZIZIQJBNMATCUJDGLOPY4MMTZH/action/citation_signature","submit_replication":"https://pith.science/pith/ZIZIQJBNMATCUJDGLOPY4MMTZH/action/replication_record"}},"created_at":"2026-07-05T10:02:01.724223+00:00","updated_at":"2026-07-05T10:02:01.724223+00:00"}