{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CELERYDLAAW3RSZ5EGYWZQ2NME","short_pith_number":"pith:CELERYDL","schema_version":"1.0","canonical_sha256":"111648e06b002db8cb3d21b16cc34d611fa7184298f834fc5ad6c1c250b5c836","source":{"kind":"arxiv","id":"2301.02780","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dragomir Radev, Fang Wu, Siyuan Li, Stan Z. Li, Xurui Jin, Yinghui Jiang, Zhangming Niu","submitted_at":"2023-01-07T05:14:45Z","abstract_excerpt":"The success of graph neural networks (GNNs) provokes the question about explainability: ``Which fraction of the input graph is the most determinant of the prediction?'' Particularly, parametric explainers prevail in existing approaches because of their more robust capability to decipher the black-box (i.e., target GNNs). In this paper, based on the observation that graphs typically share some common motif patterns, we propose a novel non-parametric subgraph matching framework, dubbed MatchExplainer, to explore explanatory subgraphs. It couples the target graph with other counterpart instances "},"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":"2301.02780","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-07T05:14:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"04d17a1ca5280dca3f3d06e942fd2a2ac616ffff108c34c7110a9499329f2470","abstract_canon_sha256":"d2f780eb64bade7deaa6da506c2c911662ccff7fd390ae3382f0fc144a9dd2c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:36.277246Z","signature_b64":"LUOzS7sl+1rccIFd+ahz3Ne/S1O7mzZaAUm1WfxvyKwOvH8Zk1MBKnRKFDFwq01K6ZPMvzbOjhy2g0itcxwKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"111648e06b002db8cb3d21b16cc34d611fa7184298f834fc5ad6c1c250b5c836","last_reissued_at":"2026-07-05T07:07:36.276694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:36.276694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dragomir Radev, Fang Wu, Siyuan Li, Stan Z. Li, Xurui Jin, Yinghui Jiang, Zhangming Niu","submitted_at":"2023-01-07T05:14:45Z","abstract_excerpt":"The success of graph neural networks (GNNs) provokes the question about explainability: ``Which fraction of the input graph is the most determinant of the prediction?'' Particularly, parametric explainers prevail in existing approaches because of their more robust capability to decipher the black-box (i.e., target GNNs). In this paper, based on the observation that graphs typically share some common motif patterns, we propose a novel non-parametric subgraph matching framework, dubbed MatchExplainer, to explore explanatory subgraphs. It couples the target graph with other counterpart instances "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02780","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/2301.02780/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":"2301.02780","created_at":"2026-07-05T07:07:36.276778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.02780v2","created_at":"2026-07-05T07:07:36.276778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02780","created_at":"2026-07-05T07:07:36.276778+00:00"},{"alias_kind":"pith_short_12","alias_value":"CELERYDLAAW3","created_at":"2026-07-05T07:07:36.276778+00:00"},{"alias_kind":"pith_short_16","alias_value":"CELERYDLAAW3RSZ5","created_at":"2026-07-05T07:07:36.276778+00:00"},{"alias_kind":"pith_short_8","alias_value":"CELERYDL","created_at":"2026-07-05T07:07:36.276778+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/CELERYDLAAW3RSZ5EGYWZQ2NME","json":"https://pith.science/pith/CELERYDLAAW3RSZ5EGYWZQ2NME.json","graph_json":"https://pith.science/api/pith-number/CELERYDLAAW3RSZ5EGYWZQ2NME/graph.json","events_json":"https://pith.science/api/pith-number/CELERYDLAAW3RSZ5EGYWZQ2NME/events.json","paper":"https://pith.science/paper/CELERYDL"},"agent_actions":{"view_html":"https://pith.science/pith/CELERYDLAAW3RSZ5EGYWZQ2NME","download_json":"https://pith.science/pith/CELERYDLAAW3RSZ5EGYWZQ2NME.json","view_paper":"https://pith.science/paper/CELERYDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.02780&json=true","fetch_graph":"https://pith.science/api/pith-number/CELERYDLAAW3RSZ5EGYWZQ2NME/graph.json","fetch_events":"https://pith.science/api/pith-number/CELERYDLAAW3RSZ5EGYWZQ2NME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CELERYDLAAW3RSZ5EGYWZQ2NME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CELERYDLAAW3RSZ5EGYWZQ2NME/action/storage_attestation","attest_author":"https://pith.science/pith/CELERYDLAAW3RSZ5EGYWZQ2NME/action/author_attestation","sign_citation":"https://pith.science/pith/CELERYDLAAW3RSZ5EGYWZQ2NME/action/citation_signature","submit_replication":"https://pith.science/pith/CELERYDLAAW3RSZ5EGYWZQ2NME/action/replication_record"}},"created_at":"2026-07-05T07:07:36.276778+00:00","updated_at":"2026-07-05T07:07:36.276778+00:00"}