{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JK47XW7YTMINOJ26HJ4E5OXRFZ","short_pith_number":"pith:JK47XW7Y","schema_version":"1.0","canonical_sha256":"4ab9fbdbf89b10d7275e3a784ebaf12e698bbaa9c45767a62b2f7ef866719776","source":{"kind":"arxiv","id":"2605.19822","version":1},"attestation_state":"computed","paper":{"title":"ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Feng Xia, Hongjiang Chen, Huaming Wu, Huan Liu, Pengfei Jiao, Shirui Pan, Xin Zheng, Zhidong Zhao","submitted_at":"2026-05-19T13:16:22Z","abstract_excerpt":"Temporal graph neural networks (TGNNs) have gained significant traction for solving real-world temporal graph tasks. However, their interpretability remains limited, as most TGNNs fail to identify which historical interactions most influence a given prediction. Despite promising progress on interpretable TGNNs, existing methods predominantly focus on previously seen historical interactions, which we term stability patterns, while overlooking newly emerging first-time interactions, which we term transition patterns. Both types of patterns are essential for faithful temporal explanations. To add"},"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":"2605.19822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T13:16:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"831632705f97184f423b349be80040a8e6fe9202b54b9e8185d40880d313233b","abstract_canon_sha256":"0173afbdfc1eae5c0ad8601e18f392b0ee4283a833e294e4835e867d15defa38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:06:16.320575Z","signature_b64":"lrH9gtn6uncjZBc2Xoz9jf/0jJ0ZvURNG0621QwK8L8+Rv8XsOXllGsx2Z5MVMyV99TdVIMiLz1JJT6x0wpgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ab9fbdbf89b10d7275e3a784ebaf12e698bbaa9c45767a62b2f7ef866719776","last_reissued_at":"2026-05-20T01:06:16.319808Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:06:16.319808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Feng Xia, Hongjiang Chen, Huaming Wu, Huan Liu, Pengfei Jiao, Shirui Pan, Xin Zheng, Zhidong Zhao","submitted_at":"2026-05-19T13:16:22Z","abstract_excerpt":"Temporal graph neural networks (TGNNs) have gained significant traction for solving real-world temporal graph tasks. However, their interpretability remains limited, as most TGNNs fail to identify which historical interactions most influence a given prediction. Despite promising progress on interpretable TGNNs, existing methods predominantly focus on previously seen historical interactions, which we term stability patterns, while overlooking newly emerging first-time interactions, which we term transition patterns. Both types of patterns are essential for faithful temporal explanations. To add"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19822","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/2605.19822/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":"2605.19822","created_at":"2026-05-20T01:06:16.319929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19822v1","created_at":"2026-05-20T01:06:16.319929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19822","created_at":"2026-05-20T01:06:16.319929+00:00"},{"alias_kind":"pith_short_12","alias_value":"JK47XW7YTMIN","created_at":"2026-05-20T01:06:16.319929+00:00"},{"alias_kind":"pith_short_16","alias_value":"JK47XW7YTMINOJ26","created_at":"2026-05-20T01:06:16.319929+00:00"},{"alias_kind":"pith_short_8","alias_value":"JK47XW7Y","created_at":"2026-05-20T01:06:16.319929+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/JK47XW7YTMINOJ26HJ4E5OXRFZ","json":"https://pith.science/pith/JK47XW7YTMINOJ26HJ4E5OXRFZ.json","graph_json":"https://pith.science/api/pith-number/JK47XW7YTMINOJ26HJ4E5OXRFZ/graph.json","events_json":"https://pith.science/api/pith-number/JK47XW7YTMINOJ26HJ4E5OXRFZ/events.json","paper":"https://pith.science/paper/JK47XW7Y"},"agent_actions":{"view_html":"https://pith.science/pith/JK47XW7YTMINOJ26HJ4E5OXRFZ","download_json":"https://pith.science/pith/JK47XW7YTMINOJ26HJ4E5OXRFZ.json","view_paper":"https://pith.science/paper/JK47XW7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19822&json=true","fetch_graph":"https://pith.science/api/pith-number/JK47XW7YTMINOJ26HJ4E5OXRFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JK47XW7YTMINOJ26HJ4E5OXRFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JK47XW7YTMINOJ26HJ4E5OXRFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JK47XW7YTMINOJ26HJ4E5OXRFZ/action/storage_attestation","attest_author":"https://pith.science/pith/JK47XW7YTMINOJ26HJ4E5OXRFZ/action/author_attestation","sign_citation":"https://pith.science/pith/JK47XW7YTMINOJ26HJ4E5OXRFZ/action/citation_signature","submit_replication":"https://pith.science/pith/JK47XW7YTMINOJ26HJ4E5OXRFZ/action/replication_record"}},"created_at":"2026-05-20T01:06:16.319929+00:00","updated_at":"2026-05-20T01:06:16.319929+00:00"}