{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EPJDA2BKSDR2TYIP73POPHS7SK","short_pith_number":"pith:EPJDA2BK","schema_version":"1.0","canonical_sha256":"23d230682a90e3a9e10ffedee79e5f92a12c7d38a600619bd2185089d46417a7","source":{"kind":"arxiv","id":"2408.04713","version":4},"attestation_state":"computed","paper":{"title":"DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonio Norelli, Jingcheng Wu, Michael Bronstein, Volker Tresp, Yifeng Li, Yuan He, Yunpu Ma, Zifeng Ding","submitted_at":"2024-08-08T18:25:14Z","abstract_excerpt":"Learning useful representations for continuous-time dynamic graphs (CTDGs) is challenging, due to the concurrent need to span long node interaction histories and grasp nuanced temporal details. In particular, two problems emerge: (1) Encoding longer histories requires more computational resources, making it crucial for CTDG models to maintain low computational complexity to ensure efficiency; (2) Meanwhile, more powerful models are needed to identify and select the most critical temporal information within the extended context provided by longer histories. To address these problems, we propose"},"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":"2408.04713","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-08T18:25:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"32a5b8fe56cad01c2d3703e11b7eb2426b40baabccce114f12cf42342ce13203","abstract_canon_sha256":"3853f34831831088dc5a77f5a58250fbdb5f80b52a05b4e1679f51d4b2bd4afc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:22.124520Z","signature_b64":"ndK6Xa5mkeEuZI2AUQz7Fd719GzcqJGEGqWcTrozGNvFmVxSoVdGF84FExzMn83gq4iEyrItedVphNiQFeT5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23d230682a90e3a9e10ffedee79e5f92a12c7d38a600619bd2185089d46417a7","last_reissued_at":"2026-07-05T11:17:22.124032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:22.124032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonio Norelli, Jingcheng Wu, Michael Bronstein, Volker Tresp, Yifeng Li, Yuan He, Yunpu Ma, Zifeng Ding","submitted_at":"2024-08-08T18:25:14Z","abstract_excerpt":"Learning useful representations for continuous-time dynamic graphs (CTDGs) is challenging, due to the concurrent need to span long node interaction histories and grasp nuanced temporal details. In particular, two problems emerge: (1) Encoding longer histories requires more computational resources, making it crucial for CTDG models to maintain low computational complexity to ensure efficiency; (2) Meanwhile, more powerful models are needed to identify and select the most critical temporal information within the extended context provided by longer histories. To address these problems, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04713","kind":"arxiv","version":4},"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/2408.04713/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":"2408.04713","created_at":"2026-07-05T11:17:22.124091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04713v4","created_at":"2026-07-05T11:17:22.124091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04713","created_at":"2026-07-05T11:17:22.124091+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPJDA2BKSDR2","created_at":"2026-07-05T11:17:22.124091+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPJDA2BKSDR2TYIP","created_at":"2026-07-05T11:17:22.124091+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPJDA2BK","created_at":"2026-07-05T11:17:22.124091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04672","citing_title":"Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2503.18970","citing_title":"Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State- Space Architectures from S4 to Mamba","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17411","citing_title":"DuConTE: Dual-Granularity Text Encoder with Topology-Constrained Attention for Text-attributed Graphs","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EPJDA2BKSDR2TYIP73POPHS7SK","json":"https://pith.science/pith/EPJDA2BKSDR2TYIP73POPHS7SK.json","graph_json":"https://pith.science/api/pith-number/EPJDA2BKSDR2TYIP73POPHS7SK/graph.json","events_json":"https://pith.science/api/pith-number/EPJDA2BKSDR2TYIP73POPHS7SK/events.json","paper":"https://pith.science/paper/EPJDA2BK"},"agent_actions":{"view_html":"https://pith.science/pith/EPJDA2BKSDR2TYIP73POPHS7SK","download_json":"https://pith.science/pith/EPJDA2BKSDR2TYIP73POPHS7SK.json","view_paper":"https://pith.science/paper/EPJDA2BK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04713&json=true","fetch_graph":"https://pith.science/api/pith-number/EPJDA2BKSDR2TYIP73POPHS7SK/graph.json","fetch_events":"https://pith.science/api/pith-number/EPJDA2BKSDR2TYIP73POPHS7SK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPJDA2BKSDR2TYIP73POPHS7SK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPJDA2BKSDR2TYIP73POPHS7SK/action/storage_attestation","attest_author":"https://pith.science/pith/EPJDA2BKSDR2TYIP73POPHS7SK/action/author_attestation","sign_citation":"https://pith.science/pith/EPJDA2BKSDR2TYIP73POPHS7SK/action/citation_signature","submit_replication":"https://pith.science/pith/EPJDA2BKSDR2TYIP73POPHS7SK/action/replication_record"}},"created_at":"2026-07-05T11:17:22.124091+00:00","updated_at":"2026-07-05T11:17:22.124091+00:00"}