{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4FCMBXGOODN32B2JI5PV4MLDDU","short_pith_number":"pith:4FCMBXGO","schema_version":"1.0","canonical_sha256":"e144c0dcce70dbbd0749475f5e31631d242743203a1e15ecb2b69ca19199f0be","source":{"kind":"arxiv","id":"2509.02217","version":1},"attestation_state":"computed","paper":{"title":"ST-Hyper: Learning High-Order Dependencies Across Multiple Spatial-Temporal Scales for Multivariate Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Binqing Wu, Jianlong Huang, Ling Chen, Zongjiang Shang","submitted_at":"2025-09-02T11:37:08Z","abstract_excerpt":"In multivariate time series (MTS) forecasting, many deep learning based methods have been proposed for modeling dependencies at multiple spatial (inter-variate) or temporal (intra-variate) scales. However, existing methods may fail to model dependencies across multiple spatial-temporal scales (ST-scales, i.e., scales that jointly consider spatial and temporal scopes). In this work, we propose ST-Hyper to model the high-order dependencies across multiple ST-scales through adaptive hypergraph modeling. Specifically, we introduce a Spatial-Temporal Pyramid Modeling (STPM) module to extract featur"},"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":"2509.02217","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T11:37:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad88927641cc6206d2f15fcf412845394d5e162d7b16e1c9b9e85512120a5a7b","abstract_canon_sha256":"7f17e35eda8ba1784614832690f723c74dfde145c82c1ac54b29b63e6800c3b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:34.268731Z","signature_b64":"nUO0RguvrAMdyCn8u2Ko1NvqrDfhh4Wcf8mFJnmVDjDxhcIIVKColkZ69xJaoLOGD0KvZx19r8l/tFXcUnGWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e144c0dcce70dbbd0749475f5e31631d242743203a1e15ecb2b69ca19199f0be","last_reissued_at":"2026-07-05T12:03:34.268311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:34.268311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ST-Hyper: Learning High-Order Dependencies Across Multiple Spatial-Temporal Scales for Multivariate Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Binqing Wu, Jianlong Huang, Ling Chen, Zongjiang Shang","submitted_at":"2025-09-02T11:37:08Z","abstract_excerpt":"In multivariate time series (MTS) forecasting, many deep learning based methods have been proposed for modeling dependencies at multiple spatial (inter-variate) or temporal (intra-variate) scales. However, existing methods may fail to model dependencies across multiple spatial-temporal scales (ST-scales, i.e., scales that jointly consider spatial and temporal scopes). In this work, we propose ST-Hyper to model the high-order dependencies across multiple ST-scales through adaptive hypergraph modeling. Specifically, we introduce a Spatial-Temporal Pyramid Modeling (STPM) module to extract featur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02217","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/2509.02217/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":"2509.02217","created_at":"2026-07-05T12:03:34.268386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02217v1","created_at":"2026-07-05T12:03:34.268386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02217","created_at":"2026-07-05T12:03:34.268386+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FCMBXGOODN3","created_at":"2026-07-05T12:03:34.268386+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FCMBXGOODN32B2J","created_at":"2026-07-05T12:03:34.268386+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FCMBXGO","created_at":"2026-07-05T12:03:34.268386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03852","citing_title":"MillGNN: Learning Multi-Scale Lead-Lag Dependencies for Multi-Variate Time Series Forecasting","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4FCMBXGOODN32B2JI5PV4MLDDU","json":"https://pith.science/pith/4FCMBXGOODN32B2JI5PV4MLDDU.json","graph_json":"https://pith.science/api/pith-number/4FCMBXGOODN32B2JI5PV4MLDDU/graph.json","events_json":"https://pith.science/api/pith-number/4FCMBXGOODN32B2JI5PV4MLDDU/events.json","paper":"https://pith.science/paper/4FCMBXGO"},"agent_actions":{"view_html":"https://pith.science/pith/4FCMBXGOODN32B2JI5PV4MLDDU","download_json":"https://pith.science/pith/4FCMBXGOODN32B2JI5PV4MLDDU.json","view_paper":"https://pith.science/paper/4FCMBXGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02217&json=true","fetch_graph":"https://pith.science/api/pith-number/4FCMBXGOODN32B2JI5PV4MLDDU/graph.json","fetch_events":"https://pith.science/api/pith-number/4FCMBXGOODN32B2JI5PV4MLDDU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FCMBXGOODN32B2JI5PV4MLDDU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FCMBXGOODN32B2JI5PV4MLDDU/action/storage_attestation","attest_author":"https://pith.science/pith/4FCMBXGOODN32B2JI5PV4MLDDU/action/author_attestation","sign_citation":"https://pith.science/pith/4FCMBXGOODN32B2JI5PV4MLDDU/action/citation_signature","submit_replication":"https://pith.science/pith/4FCMBXGOODN32B2JI5PV4MLDDU/action/replication_record"}},"created_at":"2026-07-05T12:03:34.268386+00:00","updated_at":"2026-07-05T12:03:34.268386+00:00"}