{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TUJUY2I6OAC55XMCFU6CCIK225","short_pith_number":"pith:TUJUY2I6","schema_version":"1.0","canonical_sha256":"9d134c691e7005dedd822d3c21215ad77939b395270c18d485deecfd1c27643d","source":{"kind":"arxiv","id":"2211.13236","version":2},"attestation_state":"computed","paper":{"title":"MEGAN: Multi-Explanation Graph Attention Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jonas Teufel, Luca Torresi, Pascal Friederich, Patrick Reiser","submitted_at":"2022-11-23T16:10:13Z","abstract_excerpt":"We propose a multi-explanation graph attention network (MEGAN). Unlike existing graph explainability methods, our network can produce node and edge attributional explanations along multiple channels, the number of which is independent of task specifications. This proves crucial to improve the interpretability of graph regression predictions, as explanations can be split into positive and negative evidence w.r.t to a reference value. Additionally, our attention-based network is fully differentiable and explanations can actively be trained in an explanation-supervised manner. We first validate o"},"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":"2211.13236","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-23T16:10:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a4a50e26d65a446d735e3e801c0d6ecd1c233eaf5da31676a904786486cea18f","abstract_canon_sha256":"6d57ae1435e85c0492176bc9c47610db020e27289ff57f86c05a08c241039feb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:14.921236Z","signature_b64":"pBCoaJeLnGWo9VBE0n91uvkmqeBEvUF/bEam6DKUOiLaaOhS3KptsTK02DV8g3s2w0qvXA9dnLWo+incdQSCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d134c691e7005dedd822d3c21215ad77939b395270c18d485deecfd1c27643d","last_reissued_at":"2026-07-05T07:46:14.920796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:14.920796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MEGAN: Multi-Explanation Graph Attention Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jonas Teufel, Luca Torresi, Pascal Friederich, Patrick Reiser","submitted_at":"2022-11-23T16:10:13Z","abstract_excerpt":"We propose a multi-explanation graph attention network (MEGAN). Unlike existing graph explainability methods, our network can produce node and edge attributional explanations along multiple channels, the number of which is independent of task specifications. This proves crucial to improve the interpretability of graph regression predictions, as explanations can be split into positive and negative evidence w.r.t to a reference value. Additionally, our attention-based network is fully differentiable and explanations can actively be trained in an explanation-supervised manner. We first validate o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13236","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/2211.13236/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":"2211.13236","created_at":"2026-07-05T07:46:14.920855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.13236v2","created_at":"2026-07-05T07:46:14.920855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13236","created_at":"2026-07-05T07:46:14.920855+00:00"},{"alias_kind":"pith_short_12","alias_value":"TUJUY2I6OAC5","created_at":"2026-07-05T07:46:14.920855+00:00"},{"alias_kind":"pith_short_16","alias_value":"TUJUY2I6OAC55XMC","created_at":"2026-07-05T07:46:14.920855+00:00"},{"alias_kind":"pith_short_8","alias_value":"TUJUY2I6","created_at":"2026-07-05T07:46:14.920855+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20082","citing_title":"Concept Graph Convolutions: Message Passing in the Concept Space","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TUJUY2I6OAC55XMCFU6CCIK225","json":"https://pith.science/pith/TUJUY2I6OAC55XMCFU6CCIK225.json","graph_json":"https://pith.science/api/pith-number/TUJUY2I6OAC55XMCFU6CCIK225/graph.json","events_json":"https://pith.science/api/pith-number/TUJUY2I6OAC55XMCFU6CCIK225/events.json","paper":"https://pith.science/paper/TUJUY2I6"},"agent_actions":{"view_html":"https://pith.science/pith/TUJUY2I6OAC55XMCFU6CCIK225","download_json":"https://pith.science/pith/TUJUY2I6OAC55XMCFU6CCIK225.json","view_paper":"https://pith.science/paper/TUJUY2I6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.13236&json=true","fetch_graph":"https://pith.science/api/pith-number/TUJUY2I6OAC55XMCFU6CCIK225/graph.json","fetch_events":"https://pith.science/api/pith-number/TUJUY2I6OAC55XMCFU6CCIK225/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TUJUY2I6OAC55XMCFU6CCIK225/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TUJUY2I6OAC55XMCFU6CCIK225/action/storage_attestation","attest_author":"https://pith.science/pith/TUJUY2I6OAC55XMCFU6CCIK225/action/author_attestation","sign_citation":"https://pith.science/pith/TUJUY2I6OAC55XMCFU6CCIK225/action/citation_signature","submit_replication":"https://pith.science/pith/TUJUY2I6OAC55XMCFU6CCIK225/action/replication_record"}},"created_at":"2026-07-05T07:46:14.920855+00:00","updated_at":"2026-07-05T07:46:14.920855+00:00"}