{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XBRYRSVQOPLEJDJRDI66LNXGGJ","short_pith_number":"pith:XBRYRSVQ","schema_version":"1.0","canonical_sha256":"b86388cab073d6448d311a3de5b6e6326ec115dca58e0290aaea5ce285b25425","source":{"kind":"arxiv","id":"2405.19062","version":2},"attestation_state":"computed","paper":{"title":"Invariant Graph Representations for Continuous-Time Dynamic Graphs Under Distribution Shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hanning Yuan, Kaiyu Feng, Lanting Fang, Shanshan Feng, Yawei Zhang, Yulian Yang","submitted_at":"2024-05-29T13:09:33Z","abstract_excerpt":"Continuous-Time Dynamic Graphs (CTDGs) enable fine-grained modeling of evolving relational systems. However, most existing CTDG representation learning methods are tailored to in-distribution settings and exhibit limited robustness under out-of-distribution (OOD) shifts. Although recent causal approaches learn invariant representations via interventions, they are primarily designed for static or discrete-time graphs and become computationally prohibitive for CTDGs due to the combinatorial explosion of structural and temporal variations. To address these challenges, we propose CIR, a framework "},"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":"2405.19062","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T13:09:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"59087eadd58359fba5482e285251938f8fd841c54df9a8e429b05a3f655d5301","abstract_canon_sha256":"aace7aa73b0b1ffe94c3834c2153c484144b8acccb589f82ccb503eef97ca748"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:55.522159Z","signature_b64":"moAwRQbMrAAjqjBDkco/M3cz4yFshvU9CexJayNfA1fqvFGDJdmBKh7f9EVEuYCm3vGCM0nXqsx3JCbLK5fLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b86388cab073d6448d311a3de5b6e6326ec115dca58e0290aaea5ce285b25425","last_reissued_at":"2026-06-24T01:14:55.521681Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:55.521681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Invariant Graph Representations for Continuous-Time Dynamic Graphs Under Distribution Shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hanning Yuan, Kaiyu Feng, Lanting Fang, Shanshan Feng, Yawei Zhang, Yulian Yang","submitted_at":"2024-05-29T13:09:33Z","abstract_excerpt":"Continuous-Time Dynamic Graphs (CTDGs) enable fine-grained modeling of evolving relational systems. However, most existing CTDG representation learning methods are tailored to in-distribution settings and exhibit limited robustness under out-of-distribution (OOD) shifts. Although recent causal approaches learn invariant representations via interventions, they are primarily designed for static or discrete-time graphs and become computationally prohibitive for CTDGs due to the combinatorial explosion of structural and temporal variations. To address these challenges, we propose CIR, a framework "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19062","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/2405.19062/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":"2405.19062","created_at":"2026-06-24T01:14:55.521738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19062v2","created_at":"2026-06-24T01:14:55.521738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19062","created_at":"2026-06-24T01:14:55.521738+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBRYRSVQOPLE","created_at":"2026-06-24T01:14:55.521738+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBRYRSVQOPLEJDJR","created_at":"2026-06-24T01:14:55.521738+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBRYRSVQ","created_at":"2026-06-24T01:14:55.521738+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBRYRSVQOPLEJDJRDI66LNXGGJ","json":"https://pith.science/pith/XBRYRSVQOPLEJDJRDI66LNXGGJ.json","graph_json":"https://pith.science/api/pith-number/XBRYRSVQOPLEJDJRDI66LNXGGJ/graph.json","events_json":"https://pith.science/api/pith-number/XBRYRSVQOPLEJDJRDI66LNXGGJ/events.json","paper":"https://pith.science/paper/XBRYRSVQ"},"agent_actions":{"view_html":"https://pith.science/pith/XBRYRSVQOPLEJDJRDI66LNXGGJ","download_json":"https://pith.science/pith/XBRYRSVQOPLEJDJRDI66LNXGGJ.json","view_paper":"https://pith.science/paper/XBRYRSVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19062&json=true","fetch_graph":"https://pith.science/api/pith-number/XBRYRSVQOPLEJDJRDI66LNXGGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XBRYRSVQOPLEJDJRDI66LNXGGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBRYRSVQOPLEJDJRDI66LNXGGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBRYRSVQOPLEJDJRDI66LNXGGJ/action/storage_attestation","attest_author":"https://pith.science/pith/XBRYRSVQOPLEJDJRDI66LNXGGJ/action/author_attestation","sign_citation":"https://pith.science/pith/XBRYRSVQOPLEJDJRDI66LNXGGJ/action/citation_signature","submit_replication":"https://pith.science/pith/XBRYRSVQOPLEJDJRDI66LNXGGJ/action/replication_record"}},"created_at":"2026-06-24T01:14:55.521738+00:00","updated_at":"2026-06-24T01:14:55.521738+00:00"}