{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WUQXYRQQXEII567JHE2MSRNUMW","short_pith_number":"pith:WUQXYRQQ","schema_version":"1.0","canonical_sha256":"b5217c4610b9108efbe93934c945b465a47e128161b6eb138e6034c4962497ff","source":{"kind":"arxiv","id":"2405.01762","version":2},"attestation_state":"computed","paper":{"title":"EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bang Liu, Di Niu, Jiao He, Keith G. Mills, Shengyao Lu","submitted_at":"2024-05-02T21:55:12Z","abstract_excerpt":"Understanding and explaining the predictions of Graph Neural Networks (GNNs), is crucial for enhancing their safety and trustworthiness. Subgraph-level explanations are gaining attention for their intuitive appeal. However, most existing subgraph-level explainers face efficiency challenges in explaining GNNs due to complex search processes. The key challenge is to find a balance between intuitiveness and efficiency while ensuring transparency. Additionally, these explainers usually induce subgraphs by nodes, which may introduce less-intuitive disconnected nodes in the subgraph-level explanatio"},"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":"2405.01762","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T21:55:12Z","cross_cats_sorted":[],"title_canon_sha256":"fbdb67b99e77410e376faf21fb388fd03ff6dbdc0672ebe6e27e65d1a7c70832","abstract_canon_sha256":"0e4260246530f99e00285fe4928cdfc0ebaaa8d1851b4ceb3a8235daecac382c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:44.523286Z","signature_b64":"ucf42lqV2EOsjMjMAYnei1WgAykpCMy1pv/Q+180GwlSo1XcSGnYRV29V2i8JJrK24EDcQncKWedJElNrrc+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5217c4610b9108efbe93934c945b465a47e128161b6eb138e6034c4962497ff","last_reissued_at":"2026-07-05T08:19:44.522873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:44.522873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bang Liu, Di Niu, Jiao He, Keith G. Mills, Shengyao Lu","submitted_at":"2024-05-02T21:55:12Z","abstract_excerpt":"Understanding and explaining the predictions of Graph Neural Networks (GNNs), is crucial for enhancing their safety and trustworthiness. Subgraph-level explanations are gaining attention for their intuitive appeal. However, most existing subgraph-level explainers face efficiency challenges in explaining GNNs due to complex search processes. The key challenge is to find a balance between intuitiveness and efficiency while ensuring transparency. Additionally, these explainers usually induce subgraphs by nodes, which may introduce less-intuitive disconnected nodes in the subgraph-level explanatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01762","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/2405.01762/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":"2405.01762","created_at":"2026-07-05T08:19:44.522940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.01762v2","created_at":"2026-07-05T08:19:44.522940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01762","created_at":"2026-07-05T08:19:44.522940+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUQXYRQQXEII","created_at":"2026-07-05T08:19:44.522940+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUQXYRQQXEII567J","created_at":"2026-07-05T08:19:44.522940+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUQXYRQQ","created_at":"2026-07-05T08:19:44.522940+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/WUQXYRQQXEII567JHE2MSRNUMW","json":"https://pith.science/pith/WUQXYRQQXEII567JHE2MSRNUMW.json","graph_json":"https://pith.science/api/pith-number/WUQXYRQQXEII567JHE2MSRNUMW/graph.json","events_json":"https://pith.science/api/pith-number/WUQXYRQQXEII567JHE2MSRNUMW/events.json","paper":"https://pith.science/paper/WUQXYRQQ"},"agent_actions":{"view_html":"https://pith.science/pith/WUQXYRQQXEII567JHE2MSRNUMW","download_json":"https://pith.science/pith/WUQXYRQQXEII567JHE2MSRNUMW.json","view_paper":"https://pith.science/paper/WUQXYRQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.01762&json=true","fetch_graph":"https://pith.science/api/pith-number/WUQXYRQQXEII567JHE2MSRNUMW/graph.json","fetch_events":"https://pith.science/api/pith-number/WUQXYRQQXEII567JHE2MSRNUMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUQXYRQQXEII567JHE2MSRNUMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUQXYRQQXEII567JHE2MSRNUMW/action/storage_attestation","attest_author":"https://pith.science/pith/WUQXYRQQXEII567JHE2MSRNUMW/action/author_attestation","sign_citation":"https://pith.science/pith/WUQXYRQQXEII567JHE2MSRNUMW/action/citation_signature","submit_replication":"https://pith.science/pith/WUQXYRQQXEII567JHE2MSRNUMW/action/replication_record"}},"created_at":"2026-07-05T08:19:44.522940+00:00","updated_at":"2026-07-05T08:19:44.522940+00:00"}