{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FAG3CSYQAESGN2OR7CAOGSAUY3","short_pith_number":"pith:FAG3CSYQ","schema_version":"1.0","canonical_sha256":"280db14b10012466e9d1f880e34814c6f35875a31e5ca5b166489fa6eebbf6ef","source":{"kind":"arxiv","id":"2306.04791","version":1},"attestation_state":"computed","paper":{"title":"XInsight: Revealing Model Insights for GNNs with Flow-based Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ayesh Madushanka, Corey Clark, Elfi Kraka, Eli Laird","submitted_at":"2023-06-07T21:25:32Z","abstract_excerpt":"Progress in graph neural networks has grown rapidly in recent years, with many new developments in drug discovery, medical diagnosis, and recommender systems. While this progress is significant, many networks are `black boxes' with little understanding of the `what' exactly the network is learning. Many high-stakes applications, such as drug discovery, require human-intelligible explanations from the models so that users can recognize errors and discover new knowledge. Therefore, the development of explainable AI algorithms is essential for us to reap the benefits of AI.\n  We propose an explai"},"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":"2306.04791","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T21:25:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bb8e13037ebde92bc4de0abda3b7fd185354e0de0242fd4a8de5d51bebc9ebe6","abstract_canon_sha256":"33517f40bca85a3ffe02a052fbad9e184b3f5876811b299566fed1178cd3ba8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:41.821595Z","signature_b64":"sEXZa4cQuI6lz93ol5eJ/uhlbXGLFSXstWGK4WIgYwg0vRkN1nIVe38ERT0BSRyeFmDn6cau/yN13NufIWEdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"280db14b10012466e9d1f880e34814c6f35875a31e5ca5b166489fa6eebbf6ef","last_reissued_at":"2026-07-05T06:18:41.821163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:41.821163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XInsight: Revealing Model Insights for GNNs with Flow-based Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ayesh Madushanka, Corey Clark, Elfi Kraka, Eli Laird","submitted_at":"2023-06-07T21:25:32Z","abstract_excerpt":"Progress in graph neural networks has grown rapidly in recent years, with many new developments in drug discovery, medical diagnosis, and recommender systems. While this progress is significant, many networks are `black boxes' with little understanding of the `what' exactly the network is learning. Many high-stakes applications, such as drug discovery, require human-intelligible explanations from the models so that users can recognize errors and discover new knowledge. Therefore, the development of explainable AI algorithms is essential for us to reap the benefits of AI.\n  We propose an explai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04791","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/2306.04791/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":"2306.04791","created_at":"2026-07-05T06:18:41.821224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04791v1","created_at":"2026-07-05T06:18:41.821224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04791","created_at":"2026-07-05T06:18:41.821224+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAG3CSYQAESG","created_at":"2026-07-05T06:18:41.821224+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAG3CSYQAESGN2OR","created_at":"2026-07-05T06:18:41.821224+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAG3CSYQ","created_at":"2026-07-05T06:18:41.821224+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/FAG3CSYQAESGN2OR7CAOGSAUY3","json":"https://pith.science/pith/FAG3CSYQAESGN2OR7CAOGSAUY3.json","graph_json":"https://pith.science/api/pith-number/FAG3CSYQAESGN2OR7CAOGSAUY3/graph.json","events_json":"https://pith.science/api/pith-number/FAG3CSYQAESGN2OR7CAOGSAUY3/events.json","paper":"https://pith.science/paper/FAG3CSYQ"},"agent_actions":{"view_html":"https://pith.science/pith/FAG3CSYQAESGN2OR7CAOGSAUY3","download_json":"https://pith.science/pith/FAG3CSYQAESGN2OR7CAOGSAUY3.json","view_paper":"https://pith.science/paper/FAG3CSYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04791&json=true","fetch_graph":"https://pith.science/api/pith-number/FAG3CSYQAESGN2OR7CAOGSAUY3/graph.json","fetch_events":"https://pith.science/api/pith-number/FAG3CSYQAESGN2OR7CAOGSAUY3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAG3CSYQAESGN2OR7CAOGSAUY3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAG3CSYQAESGN2OR7CAOGSAUY3/action/storage_attestation","attest_author":"https://pith.science/pith/FAG3CSYQAESGN2OR7CAOGSAUY3/action/author_attestation","sign_citation":"https://pith.science/pith/FAG3CSYQAESGN2OR7CAOGSAUY3/action/citation_signature","submit_replication":"https://pith.science/pith/FAG3CSYQAESGN2OR7CAOGSAUY3/action/replication_record"}},"created_at":"2026-07-05T06:18:41.821224+00:00","updated_at":"2026-07-05T06:18:41.821224+00:00"}