{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WCK6DXAGUKOYX4HTH3H33EXJWC","short_pith_number":"pith:WCK6DXAG","schema_version":"1.0","canonical_sha256":"b095e1dc06a29d8bf0f33ecfbd92e9b08242427a0f2335c4f65eea2855d9fc87","source":{"kind":"arxiv","id":"2608.07333","version":1},"attestation_state":"computed","paper":{"title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen Shao, Danai Koutra, Tobias K\\\"afer, Yue Wang, Zhanbo Huang, Zhenyi Zhu, Zonghan Wu","submitted_at":"2026-08-07T15:28:45Z","abstract_excerpt":"Modeling multivariate time series by representing them as graphs, where individual series act as nodes and pairwise temporal corre- lations serve as edges, has gained significant traction. Recent advances in Graph Neural Networks (GNNs) have demonstrated strong perfor- mance by assuming a static graph topology and aggregating information from neighboring series. In this work, we investigate the representa- tional power of GNNs for forecasting under both static and dynamic settings (i.e., when pairwise correlations evolve drastically over time) and identify critical limitations in current archi"},"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":"2608.07333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T15:28:45Z","cross_cats_sorted":[],"title_canon_sha256":"66ec147ec320cb3636eb568a00de19f94b91ceb877b1722b949192be4235a472","abstract_canon_sha256":"5378604752d741494190ee857b145c2c056decae32b953afd4e8b8f6948d6064"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:15:02.646602Z","signature_b64":"SlKq6kSpqJxjPjaAHqYlKPQFDef73EGby7oyyXuQqo1XDnbfaijDqaVb0SZQcjmqIxBwoV2/lar1HK/i5K1bCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b095e1dc06a29d8bf0f33ecfbd92e9b08242427a0f2335c4f65eea2855d9fc87","last_reissued_at":"2026-08-10T01:15:02.642237Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:15:02.642237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen Shao, Danai Koutra, Tobias K\\\"afer, Yue Wang, Zhanbo Huang, Zhenyi Zhu, Zonghan Wu","submitted_at":"2026-08-07T15:28:45Z","abstract_excerpt":"Modeling multivariate time series by representing them as graphs, where individual series act as nodes and pairwise temporal corre- lations serve as edges, has gained significant traction. Recent advances in Graph Neural Networks (GNNs) have demonstrated strong perfor- mance by assuming a static graph topology and aggregating information from neighboring series. In this work, we investigate the representa- tional power of GNNs for forecasting under both static and dynamic settings (i.e., when pairwise correlations evolve drastically over time) and identify critical limitations in current archi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07333","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/2608.07333/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":"2608.07333","created_at":"2026-08-10T01:15:02.643362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07333v1","created_at":"2026-08-10T01:15:02.643362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07333","created_at":"2026-08-10T01:15:02.643362+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCK6DXAGUKOY","created_at":"2026-08-10T01:15:02.643362+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCK6DXAGUKOYX4HT","created_at":"2026-08-10T01:15:02.643362+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCK6DXAG","created_at":"2026-08-10T01:15:02.643362+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/WCK6DXAGUKOYX4HTH3H33EXJWC","json":"https://pith.science/pith/WCK6DXAGUKOYX4HTH3H33EXJWC.json","graph_json":"https://pith.science/api/pith-number/WCK6DXAGUKOYX4HTH3H33EXJWC/graph.json","events_json":"https://pith.science/api/pith-number/WCK6DXAGUKOYX4HTH3H33EXJWC/events.json","paper":"https://pith.science/paper/WCK6DXAG"},"agent_actions":{"view_html":"https://pith.science/pith/WCK6DXAGUKOYX4HTH3H33EXJWC","download_json":"https://pith.science/pith/WCK6DXAGUKOYX4HTH3H33EXJWC.json","view_paper":"https://pith.science/paper/WCK6DXAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07333&json=true","fetch_graph":"https://pith.science/api/pith-number/WCK6DXAGUKOYX4HTH3H33EXJWC/graph.json","fetch_events":"https://pith.science/api/pith-number/WCK6DXAGUKOYX4HTH3H33EXJWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCK6DXAGUKOYX4HTH3H33EXJWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCK6DXAGUKOYX4HTH3H33EXJWC/action/storage_attestation","attest_author":"https://pith.science/pith/WCK6DXAGUKOYX4HTH3H33EXJWC/action/author_attestation","sign_citation":"https://pith.science/pith/WCK6DXAGUKOYX4HTH3H33EXJWC/action/citation_signature","submit_replication":"https://pith.science/pith/WCK6DXAGUKOYX4HTH3H33EXJWC/action/replication_record"}},"created_at":"2026-08-10T01:15:02.643362+00:00","updated_at":"2026-08-10T01:15:02.643362+00:00"}