{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2F4QFWYR73PZASDGPDP4J3ZOFO","short_pith_number":"pith:2F4QFWYR","schema_version":"1.0","canonical_sha256":"d17902db11fedf90486678dfc4ef2e2b95cf00d45e59e02c13c2bc857a7ebda5","source":{"kind":"arxiv","id":"2405.17473","version":2},"attestation_state":"computed","paper":{"title":"Repeat-Aware Neighbor Sampling for Dynamic Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Bowen Du, Junchen Ye, Tao Zou, Yuhao Mao","submitted_at":"2024-05-24T03:24:29Z","abstract_excerpt":"Dynamic graph learning equips the edges with time attributes and allows multiple links between two nodes, which is a crucial technology for understanding evolving data scenarios like traffic prediction and recommendation systems. Existing works obtain the evolving patterns mainly depending on the most recent neighbor sequences. However, we argue that whether two nodes will have interaction with each other in the future is highly correlated with the same interaction that happened in the past. Only considering the recent neighbors overlooks the phenomenon of repeat behavior and fails to accurate"},"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":"2405.17473","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T03:24:29Z","cross_cats_sorted":["cs.AI","cs.SI"],"title_canon_sha256":"ba1276fb187b626092b83e986172586ca671c192638f316030b502a280425aea","abstract_canon_sha256":"58ab87d7625cc485736d21a66cf7b6574a9ad4b0f8518a3c2529035ced805862"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:19.558707Z","signature_b64":"8ztgAyYpyolFLpk8OoHgJ6rHmiNdTCQ59EgtScrV8vW30p/hhNyrx5wmglbYsXY5Mi8o+kD7LS+RwFlHwMb+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d17902db11fedf90486678dfc4ef2e2b95cf00d45e59e02c13c2bc857a7ebda5","last_reissued_at":"2026-07-05T08:34:19.558276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:19.558276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Repeat-Aware Neighbor Sampling for Dynamic Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Bowen Du, Junchen Ye, Tao Zou, Yuhao Mao","submitted_at":"2024-05-24T03:24:29Z","abstract_excerpt":"Dynamic graph learning equips the edges with time attributes and allows multiple links between two nodes, which is a crucial technology for understanding evolving data scenarios like traffic prediction and recommendation systems. Existing works obtain the evolving patterns mainly depending on the most recent neighbor sequences. However, we argue that whether two nodes will have interaction with each other in the future is highly correlated with the same interaction that happened in the past. Only considering the recent neighbors overlooks the phenomenon of repeat behavior and fails to accurate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17473","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/2405.17473/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":"2405.17473","created_at":"2026-07-05T08:34:19.558346+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17473v2","created_at":"2026-07-05T08:34:19.558346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17473","created_at":"2026-07-05T08:34:19.558346+00:00"},{"alias_kind":"pith_short_12","alias_value":"2F4QFWYR73PZ","created_at":"2026-07-05T08:34:19.558346+00:00"},{"alias_kind":"pith_short_16","alias_value":"2F4QFWYR73PZASDG","created_at":"2026-07-05T08:34:19.558346+00:00"},{"alias_kind":"pith_short_8","alias_value":"2F4QFWYR","created_at":"2026-07-05T08:34:19.558346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00431","citing_title":"TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2F4QFWYR73PZASDGPDP4J3ZOFO","json":"https://pith.science/pith/2F4QFWYR73PZASDGPDP4J3ZOFO.json","graph_json":"https://pith.science/api/pith-number/2F4QFWYR73PZASDGPDP4J3ZOFO/graph.json","events_json":"https://pith.science/api/pith-number/2F4QFWYR73PZASDGPDP4J3ZOFO/events.json","paper":"https://pith.science/paper/2F4QFWYR"},"agent_actions":{"view_html":"https://pith.science/pith/2F4QFWYR73PZASDGPDP4J3ZOFO","download_json":"https://pith.science/pith/2F4QFWYR73PZASDGPDP4J3ZOFO.json","view_paper":"https://pith.science/paper/2F4QFWYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17473&json=true","fetch_graph":"https://pith.science/api/pith-number/2F4QFWYR73PZASDGPDP4J3ZOFO/graph.json","fetch_events":"https://pith.science/api/pith-number/2F4QFWYR73PZASDGPDP4J3ZOFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2F4QFWYR73PZASDGPDP4J3ZOFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2F4QFWYR73PZASDGPDP4J3ZOFO/action/storage_attestation","attest_author":"https://pith.science/pith/2F4QFWYR73PZASDGPDP4J3ZOFO/action/author_attestation","sign_citation":"https://pith.science/pith/2F4QFWYR73PZASDGPDP4J3ZOFO/action/citation_signature","submit_replication":"https://pith.science/pith/2F4QFWYR73PZASDGPDP4J3ZOFO/action/replication_record"}},"created_at":"2026-07-05T08:34:19.558346+00:00","updated_at":"2026-07-05T08:34:19.558346+00:00"}