{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O7TQM2J73ZMRVPNI66ST7KIHTN","short_pith_number":"pith:O7TQM2J7","schema_version":"1.0","canonical_sha256":"77e706693fde591abda8f7a53fa9079b5a9161bbbfcd6586707317a68156242d","source":{"kind":"arxiv","id":"2402.04284","version":2},"attestation_state":"computed","paper":{"title":"PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuan Wu, Difan Zou, Junwei Su","submitted_at":"2024-02-06T01:34:56Z","abstract_excerpt":"Memory-based Dynamic Graph Neural Networks (MDGNNs) are a family of dynamic graph neural networks that leverage a memory module to extract, distill, and memorize long-term temporal dependencies, leading to superior performance compared to memory-less counterparts. However, training MDGNNs faces the challenge of handling entangled temporal and structural dependencies, requiring sequential and chronological processing of data sequences to capture accurate temporal patterns. During the batch training, the temporal data points within the same batch will be processed in parallel, while their tempor"},"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":"2402.04284","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T01:34:56Z","cross_cats_sorted":[],"title_canon_sha256":"2edbf0c73346b68b5f3118d5b2440943b87e7933d6fe74a6a2e843ff242df55a","abstract_canon_sha256":"69e1afaa0c0bdd546e0f13a4b0bb4251d39fc450e07dd35da59c5a63f8883a84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:17.771562Z","signature_b64":"s1L9pYy7zvbYnJYGcyKqad0b9O0M7UfsiltwU1QOBXQrYCzRKgeNqCf8bsd8yvt0iTC9toHgJt4JjvTzrbkyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77e706693fde591abda8f7a53fa9079b5a9161bbbfcd6586707317a68156242d","last_reissued_at":"2026-07-05T07:49:17.771029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:17.771029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuan Wu, Difan Zou, Junwei Su","submitted_at":"2024-02-06T01:34:56Z","abstract_excerpt":"Memory-based Dynamic Graph Neural Networks (MDGNNs) are a family of dynamic graph neural networks that leverage a memory module to extract, distill, and memorize long-term temporal dependencies, leading to superior performance compared to memory-less counterparts. However, training MDGNNs faces the challenge of handling entangled temporal and structural dependencies, requiring sequential and chronological processing of data sequences to capture accurate temporal patterns. During the batch training, the temporal data points within the same batch will be processed in parallel, while their tempor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04284","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/2402.04284/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":"2402.04284","created_at":"2026-07-05T07:49:17.771086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04284v2","created_at":"2026-07-05T07:49:17.771086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04284","created_at":"2026-07-05T07:49:17.771086+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7TQM2J73ZMR","created_at":"2026-07-05T07:49:17.771086+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7TQM2J73ZMRVPNI","created_at":"2026-07-05T07:49:17.771086+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7TQM2J7","created_at":"2026-07-05T07:49:17.771086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.11259","citing_title":"Graph Retention Networks for Dynamic Graphs","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7TQM2J73ZMRVPNI66ST7KIHTN","json":"https://pith.science/pith/O7TQM2J73ZMRVPNI66ST7KIHTN.json","graph_json":"https://pith.science/api/pith-number/O7TQM2J73ZMRVPNI66ST7KIHTN/graph.json","events_json":"https://pith.science/api/pith-number/O7TQM2J73ZMRVPNI66ST7KIHTN/events.json","paper":"https://pith.science/paper/O7TQM2J7"},"agent_actions":{"view_html":"https://pith.science/pith/O7TQM2J73ZMRVPNI66ST7KIHTN","download_json":"https://pith.science/pith/O7TQM2J73ZMRVPNI66ST7KIHTN.json","view_paper":"https://pith.science/paper/O7TQM2J7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04284&json=true","fetch_graph":"https://pith.science/api/pith-number/O7TQM2J73ZMRVPNI66ST7KIHTN/graph.json","fetch_events":"https://pith.science/api/pith-number/O7TQM2J73ZMRVPNI66ST7KIHTN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7TQM2J73ZMRVPNI66ST7KIHTN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7TQM2J73ZMRVPNI66ST7KIHTN/action/storage_attestation","attest_author":"https://pith.science/pith/O7TQM2J73ZMRVPNI66ST7KIHTN/action/author_attestation","sign_citation":"https://pith.science/pith/O7TQM2J73ZMRVPNI66ST7KIHTN/action/citation_signature","submit_replication":"https://pith.science/pith/O7TQM2J73ZMRVPNI66ST7KIHTN/action/replication_record"}},"created_at":"2026-07-05T07:49:17.771086+00:00","updated_at":"2026-07-05T07:49:17.771086+00:00"}