{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GTY6YYEJBM5PS2QTLVHJEPS36Z","short_pith_number":"pith:GTY6YYEJ","schema_version":"1.0","canonical_sha256":"34f1ec60890b3af96a135d4e923e5bf660e2fb1e0221caba2b3bfe7e80e78200","source":{"kind":"arxiv","id":"2302.11636","version":1},"attestation_state":"computed","paper":{"title":"Do We Really Need Complicated Model Architectures For Temporal Networks?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Baichuan Yuan, Hanghang Tong, Hao Wu, Jian Kang, Mehrdad Mahdavi, Si Zhang, Weilin Cong, Xin Zhou","submitted_at":"2023-02-22T20:24:35Z","abstract_excerpt":"Recurrent neural network (RNN) and self-attention mechanism (SAM) are the de facto methods to extract spatial-temporal information for temporal graph learning. Interestingly, we found that although both RNN and SAM could lead to a good performance, in practice neither of them is always necessary. In this paper, we propose GraphMixer, a conceptually and technically simple architecture that consists of three components: (1) a link-encoder that is only based on multi-layer perceptrons (MLP) to summarize the information from temporal links, (2) a node-encoder that is only based on neighbor mean-po"},"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":"2302.11636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-22T20:24:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"33ae51214fabb58e6781dd0e7ec02c3f063967cbda88a356d09c9c483bef610e","abstract_canon_sha256":"fb624b054a13a0010d94bcf8bc4bb08ce2a78f591f46fffc67d6f21a419bfb7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:54.365331Z","signature_b64":"z7LNktct7Zj/BT4GhYlMSa9ggxTBbwdIjOMSvhiS4f3ln1FF0EUeuwB2kSv/EA7Q41XxbiPSCaJDni8JBLYhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34f1ec60890b3af96a135d4e923e5bf660e2fb1e0221caba2b3bfe7e80e78200","last_reissued_at":"2026-07-05T05:44:54.364849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:54.364849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do We Really Need Complicated Model Architectures For Temporal Networks?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Baichuan Yuan, Hanghang Tong, Hao Wu, Jian Kang, Mehrdad Mahdavi, Si Zhang, Weilin Cong, Xin Zhou","submitted_at":"2023-02-22T20:24:35Z","abstract_excerpt":"Recurrent neural network (RNN) and self-attention mechanism (SAM) are the de facto methods to extract spatial-temporal information for temporal graph learning. Interestingly, we found that although both RNN and SAM could lead to a good performance, in practice neither of them is always necessary. In this paper, we propose GraphMixer, a conceptually and technically simple architecture that consists of three components: (1) a link-encoder that is only based on multi-layer perceptrons (MLP) to summarize the information from temporal links, (2) a node-encoder that is only based on neighbor mean-po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11636","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/2302.11636/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":"2302.11636","created_at":"2026-07-05T05:44:54.364905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.11636v1","created_at":"2026-07-05T05:44:54.364905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11636","created_at":"2026-07-05T05:44:54.364905+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTY6YYEJBM5P","created_at":"2026-07-05T05:44:54.364905+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTY6YYEJBM5PS2QT","created_at":"2026-07-05T05:44:54.364905+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTY6YYEJ","created_at":"2026-07-05T05:44:54.364905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29453","citing_title":"Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2411.11259","citing_title":"Graph Retention Networks for Dynamic Graphs","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21916","citing_title":"A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTY6YYEJBM5PS2QTLVHJEPS36Z","json":"https://pith.science/pith/GTY6YYEJBM5PS2QTLVHJEPS36Z.json","graph_json":"https://pith.science/api/pith-number/GTY6YYEJBM5PS2QTLVHJEPS36Z/graph.json","events_json":"https://pith.science/api/pith-number/GTY6YYEJBM5PS2QTLVHJEPS36Z/events.json","paper":"https://pith.science/paper/GTY6YYEJ"},"agent_actions":{"view_html":"https://pith.science/pith/GTY6YYEJBM5PS2QTLVHJEPS36Z","download_json":"https://pith.science/pith/GTY6YYEJBM5PS2QTLVHJEPS36Z.json","view_paper":"https://pith.science/paper/GTY6YYEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.11636&json=true","fetch_graph":"https://pith.science/api/pith-number/GTY6YYEJBM5PS2QTLVHJEPS36Z/graph.json","fetch_events":"https://pith.science/api/pith-number/GTY6YYEJBM5PS2QTLVHJEPS36Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTY6YYEJBM5PS2QTLVHJEPS36Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTY6YYEJBM5PS2QTLVHJEPS36Z/action/storage_attestation","attest_author":"https://pith.science/pith/GTY6YYEJBM5PS2QTLVHJEPS36Z/action/author_attestation","sign_citation":"https://pith.science/pith/GTY6YYEJBM5PS2QTLVHJEPS36Z/action/citation_signature","submit_replication":"https://pith.science/pith/GTY6YYEJBM5PS2QTLVHJEPS36Z/action/replication_record"}},"created_at":"2026-07-05T05:44:54.364905+00:00","updated_at":"2026-07-05T05:44:54.364905+00:00"}