{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DCM375YTPKO5WAQBKO7YR6EEC2","short_pith_number":"pith:DCM375YT","schema_version":"1.0","canonical_sha256":"1899bff7137a9ddb020153bf88f884169c1bfd408df218829722b59cf73326ad","source":{"kind":"arxiv","id":"2502.04910","version":1},"attestation_state":"computed","paper":{"title":"On the Power of Heuristics in Temporal Graphs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Filip Cornell, Gabriela Zarzar Gandler, Lele Cao, Oleg Smirnov","submitted_at":"2025-02-07T13:28:31Z","abstract_excerpt":"Dynamic graph datasets often exhibit strong temporal patterns, such as recency, which prioritizes recent interactions, and popularity, which favors frequently occurring nodes. We demonstrate that simple heuristics leveraging only these patterns can perform on par or outperform state-of-the-art neural network models under standard evaluation protocols. To further explore these dynamics, we introduce metrics that quantify the impact of recency and popularity across datasets. Our experiments on BenchTemp and the Temporal Graph Benchmark show that our approaches achieve state-of-the-art performanc"},"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":"2502.04910","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T13:28:31Z","cross_cats_sorted":[],"title_canon_sha256":"e3bdd0b0817b2c51555af413ce7207b6685f8323164683ae31995682ffec0b69","abstract_canon_sha256":"515704dfaf91d3e2da34b8c47d7c4c3057df78b30b6641e318578227f8868943"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:59.358960Z","signature_b64":"aiKp+8r9AXrCAv6xXeLyOCwoanUNZTj9M8EXcUbNeRtmDZYQfQmBb5tPf0Z6npSlwv69qjAm/AjhMLYP58mFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1899bff7137a9ddb020153bf88f884169c1bfd408df218829722b59cf73326ad","last_reissued_at":"2026-07-05T10:10:59.358443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:59.358443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Power of Heuristics in Temporal Graphs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Filip Cornell, Gabriela Zarzar Gandler, Lele Cao, Oleg Smirnov","submitted_at":"2025-02-07T13:28:31Z","abstract_excerpt":"Dynamic graph datasets often exhibit strong temporal patterns, such as recency, which prioritizes recent interactions, and popularity, which favors frequently occurring nodes. We demonstrate that simple heuristics leveraging only these patterns can perform on par or outperform state-of-the-art neural network models under standard evaluation protocols. To further explore these dynamics, we introduce metrics that quantify the impact of recency and popularity across datasets. Our experiments on BenchTemp and the Temporal Graph Benchmark show that our approaches achieve state-of-the-art performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04910","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/2502.04910/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":"2502.04910","created_at":"2026-07-05T10:10:59.358512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04910v1","created_at":"2026-07-05T10:10:59.358512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04910","created_at":"2026-07-05T10:10:59.358512+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCM375YTPKO5","created_at":"2026-07-05T10:10:59.358512+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCM375YTPKO5WAQB","created_at":"2026-07-05T10:10:59.358512+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCM375YT","created_at":"2026-07-05T10:10:59.358512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11873","citing_title":"Maximizing Reachability via Shifting of Temporal Paths","ref_index":231,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DCM375YTPKO5WAQBKO7YR6EEC2","json":"https://pith.science/pith/DCM375YTPKO5WAQBKO7YR6EEC2.json","graph_json":"https://pith.science/api/pith-number/DCM375YTPKO5WAQBKO7YR6EEC2/graph.json","events_json":"https://pith.science/api/pith-number/DCM375YTPKO5WAQBKO7YR6EEC2/events.json","paper":"https://pith.science/paper/DCM375YT"},"agent_actions":{"view_html":"https://pith.science/pith/DCM375YTPKO5WAQBKO7YR6EEC2","download_json":"https://pith.science/pith/DCM375YTPKO5WAQBKO7YR6EEC2.json","view_paper":"https://pith.science/paper/DCM375YT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04910&json=true","fetch_graph":"https://pith.science/api/pith-number/DCM375YTPKO5WAQBKO7YR6EEC2/graph.json","fetch_events":"https://pith.science/api/pith-number/DCM375YTPKO5WAQBKO7YR6EEC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCM375YTPKO5WAQBKO7YR6EEC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCM375YTPKO5WAQBKO7YR6EEC2/action/storage_attestation","attest_author":"https://pith.science/pith/DCM375YTPKO5WAQBKO7YR6EEC2/action/author_attestation","sign_citation":"https://pith.science/pith/DCM375YTPKO5WAQBKO7YR6EEC2/action/citation_signature","submit_replication":"https://pith.science/pith/DCM375YTPKO5WAQBKO7YR6EEC2/action/replication_record"}},"created_at":"2026-07-05T10:10:59.358512+00:00","updated_at":"2026-07-05T10:10:59.358512+00:00"}