{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FJOXPW3U4SWVU2UOWLMWZOGUDP","short_pith_number":"pith:FJOXPW3U","schema_version":"1.0","canonical_sha256":"2a5d77db74e4ad5a6a8eb2d96cb8d41bfc21e61c29822c7ee6930fc199efc0a9","source":{"kind":"arxiv","id":"2506.19282","version":1},"attestation_state":"computed","paper":{"title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.LG","authors_text":"Xiaoning Ren, Yang Zhou","submitted_at":"2025-06-24T03:31:43Z","abstract_excerpt":"In dynamic graphs, preserving temporal continuity is critical. However, Memory-based Dynamic Graph Neural Networks (MDGNNs) trained with large batches often disrupt event sequences, leading to temporal information loss. This discontinuity not only deteriorates temporal modeling but also hinders optimization by increasing the difficulty of parameter convergence. Our theoretical study quantifies this through a Lipschitz upper bound, showing that large batch sizes enlarge the parameter search space. In response, we propose BADGNN, a novel batch-agnostic framework consisting of two core components"},"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":"2506.19282","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T03:31:43Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"da2108cb61e2e6463ecd7917c5993153432b25b11957e78dac0f7dc947f39665","abstract_canon_sha256":"4bff3a3e22155a68aad41b95760451568d93125368c953e67a179c78e1d921af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:12.647804Z","signature_b64":"MvSjEA3sGZnzQt2Nup7ZzLxMnAj+cSlpjBo/+wVVTk/84sIthRaLY5v6rbWDtsRuBTV30BLO6qNQ3x9fK6xVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a5d77db74e4ad5a6a8eb2d96cb8d41bfc21e61c29822c7ee6930fc199efc0a9","last_reissued_at":"2026-07-05T11:26:12.647397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:12.647397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.LG","authors_text":"Xiaoning Ren, Yang Zhou","submitted_at":"2025-06-24T03:31:43Z","abstract_excerpt":"In dynamic graphs, preserving temporal continuity is critical. However, Memory-based Dynamic Graph Neural Networks (MDGNNs) trained with large batches often disrupt event sequences, leading to temporal information loss. This discontinuity not only deteriorates temporal modeling but also hinders optimization by increasing the difficulty of parameter convergence. Our theoretical study quantifies this through a Lipschitz upper bound, showing that large batch sizes enlarge the parameter search space. In response, we propose BADGNN, a novel batch-agnostic framework consisting of two core components"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19282","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/2506.19282/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":"2506.19282","created_at":"2026-07-05T11:26:12.647455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19282v1","created_at":"2026-07-05T11:26:12.647455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19282","created_at":"2026-07-05T11:26:12.647455+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJOXPW3U4SWV","created_at":"2026-07-05T11:26:12.647455+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJOXPW3U4SWVU2UO","created_at":"2026-07-05T11:26:12.647455+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJOXPW3U","created_at":"2026-07-05T11:26:12.647455+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/FJOXPW3U4SWVU2UOWLMWZOGUDP","json":"https://pith.science/pith/FJOXPW3U4SWVU2UOWLMWZOGUDP.json","graph_json":"https://pith.science/api/pith-number/FJOXPW3U4SWVU2UOWLMWZOGUDP/graph.json","events_json":"https://pith.science/api/pith-number/FJOXPW3U4SWVU2UOWLMWZOGUDP/events.json","paper":"https://pith.science/paper/FJOXPW3U"},"agent_actions":{"view_html":"https://pith.science/pith/FJOXPW3U4SWVU2UOWLMWZOGUDP","download_json":"https://pith.science/pith/FJOXPW3U4SWVU2UOWLMWZOGUDP.json","view_paper":"https://pith.science/paper/FJOXPW3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19282&json=true","fetch_graph":"https://pith.science/api/pith-number/FJOXPW3U4SWVU2UOWLMWZOGUDP/graph.json","fetch_events":"https://pith.science/api/pith-number/FJOXPW3U4SWVU2UOWLMWZOGUDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJOXPW3U4SWVU2UOWLMWZOGUDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJOXPW3U4SWVU2UOWLMWZOGUDP/action/storage_attestation","attest_author":"https://pith.science/pith/FJOXPW3U4SWVU2UOWLMWZOGUDP/action/author_attestation","sign_citation":"https://pith.science/pith/FJOXPW3U4SWVU2UOWLMWZOGUDP/action/citation_signature","submit_replication":"https://pith.science/pith/FJOXPW3U4SWVU2UOWLMWZOGUDP/action/replication_record"}},"created_at":"2026-07-05T11:26:12.647455+00:00","updated_at":"2026-07-05T11:26:12.647455+00:00"}