{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JQWPEUVBJXBYTCHRSEUXEFBMWQ","short_pith_number":"pith:JQWPEUVB","schema_version":"1.0","canonical_sha256":"4c2cf252a14dc38988f1912972142cb432bca5c8acb6dc2a9ff2f3d0d8293472","source":{"kind":"arxiv","id":"2411.03596","version":3},"attestation_state":"computed","paper":{"title":"Enhancing the Expressivity of Temporal Graph Networks through Source-Target Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benedict Aaron Tjandra, Federico Barbero, Michael Bronstein","submitted_at":"2024-11-06T01:20:24Z","abstract_excerpt":"Despite the successful application of Temporal Graph Networks (TGNs) for tasks such as dynamic node classification and link prediction, they still perform poorly on the task of dynamic node affinity prediction -- where the goal is to predict 'how much' two nodes will interact in the future. In fact, simple heuristic approaches such as persistent forecasts and moving averages over ground-truth labels significantly and consistently outperform TGNs. Building on this observation, we find that computing heuristics over messages is an equally competitive approach, outperforming TGN and all current t"},"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":"2411.03596","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T01:20:24Z","cross_cats_sorted":[],"title_canon_sha256":"199c03539dc5f54c1cc2c239e4f6416d7d494df392617dbd2a55d3ec9e4d4ff0","abstract_canon_sha256":"790f6a103ac8cc94435e55473cf7d770eb6cace1f712280a0677cc5b394ee1ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:44.292019Z","signature_b64":"BH0qgqSTiRHFxkzFYCko0reu950Cu/XMIIrzpurrm3REj1a//6FLIacLFyZclo8gNcHoCFlQ8URtrBALIEyoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c2cf252a14dc38988f1912972142cb432bca5c8acb6dc2a9ff2f3d0d8293472","last_reissued_at":"2026-07-05T09:41:44.291474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:44.291474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing the Expressivity of Temporal Graph Networks through Source-Target Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benedict Aaron Tjandra, Federico Barbero, Michael Bronstein","submitted_at":"2024-11-06T01:20:24Z","abstract_excerpt":"Despite the successful application of Temporal Graph Networks (TGNs) for tasks such as dynamic node classification and link prediction, they still perform poorly on the task of dynamic node affinity prediction -- where the goal is to predict 'how much' two nodes will interact in the future. In fact, simple heuristic approaches such as persistent forecasts and moving averages over ground-truth labels significantly and consistently outperform TGNs. Building on this observation, we find that computing heuristics over messages is an equally competitive approach, outperforming TGN and all current t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03596","kind":"arxiv","version":3},"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/2411.03596/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":"2411.03596","created_at":"2026-07-05T09:41:44.291532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03596v3","created_at":"2026-07-05T09:41:44.291532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03596","created_at":"2026-07-05T09:41:44.291532+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQWPEUVBJXBY","created_at":"2026-07-05T09:41:44.291532+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQWPEUVBJXBYTCHR","created_at":"2026-07-05T09:41:44.291532+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQWPEUVB","created_at":"2026-07-05T09:41:44.291532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10071","citing_title":"Temporal Sheaf Neural Networks with Dynamic Orthogonal Transport","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JQWPEUVBJXBYTCHRSEUXEFBMWQ","json":"https://pith.science/pith/JQWPEUVBJXBYTCHRSEUXEFBMWQ.json","graph_json":"https://pith.science/api/pith-number/JQWPEUVBJXBYTCHRSEUXEFBMWQ/graph.json","events_json":"https://pith.science/api/pith-number/JQWPEUVBJXBYTCHRSEUXEFBMWQ/events.json","paper":"https://pith.science/paper/JQWPEUVB"},"agent_actions":{"view_html":"https://pith.science/pith/JQWPEUVBJXBYTCHRSEUXEFBMWQ","download_json":"https://pith.science/pith/JQWPEUVBJXBYTCHRSEUXEFBMWQ.json","view_paper":"https://pith.science/paper/JQWPEUVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03596&json=true","fetch_graph":"https://pith.science/api/pith-number/JQWPEUVBJXBYTCHRSEUXEFBMWQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JQWPEUVBJXBYTCHRSEUXEFBMWQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQWPEUVBJXBYTCHRSEUXEFBMWQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQWPEUVBJXBYTCHRSEUXEFBMWQ/action/storage_attestation","attest_author":"https://pith.science/pith/JQWPEUVBJXBYTCHRSEUXEFBMWQ/action/author_attestation","sign_citation":"https://pith.science/pith/JQWPEUVBJXBYTCHRSEUXEFBMWQ/action/citation_signature","submit_replication":"https://pith.science/pith/JQWPEUVBJXBYTCHRSEUXEFBMWQ/action/replication_record"}},"created_at":"2026-07-05T09:41:44.291532+00:00","updated_at":"2026-07-05T09:41:44.291532+00:00"}