{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5CGGRUPQ6ITGPJXYFNX7ALBJAT","short_pith_number":"pith:5CGGRUPQ","schema_version":"1.0","canonical_sha256":"e88c68d1f0f22667a6f82b6ff02c2904ca5525e445b185a37b02517722a865ea","source":{"kind":"arxiv","id":"2305.06587","version":3},"attestation_state":"computed","paper":{"title":"Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Xiong, Flora D. Salim, Guangsi Shi, Liang Zhao, Lingfei Wu, Ming Jin, Qingsong Wen, Shirui Pan, Tian Zhou, Yuan-Fang Li","submitted_at":"2023-05-11T05:56:38Z","abstract_excerpt":"Time series forecasting has remained a focal point due to its vital applications in sectors such as energy management and transportation planning. Spectral-temporal graph neural network is a promising abstraction underlying most time series forecasting models that are based on graph neural networks (GNNs). However, more is needed to know about the underpinnings of this branch of methods. In this paper, we establish a theoretical framework that unravels the expressive power of spectral-temporal GNNs. Our results show that linear spectral-temporal GNNs are universal under mild assumptions, and t"},"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":"2305.06587","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-11T05:56:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4bf85f06138c4297419125b3a1a321e965d85fb83eec46df11c4d0c1ca17e8c6","abstract_canon_sha256":"70e7a0b2bf7b8cb0d29d9916bc75f244e1c10e4ac277542146495b898b986dc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:31.800327Z","signature_b64":"htwZkJqrYedGGCX8Uhwl4J5wDEM3is4UZ7xvHKuqOiHvCp6t9yicqfqcT+cVX+kuyd1FSX+4iaui+rgboswyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e88c68d1f0f22667a6f82b6ff02c2904ca5525e445b185a37b02517722a865ea","last_reissued_at":"2026-07-05T10:18:31.799932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:31.799932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Xiong, Flora D. Salim, Guangsi Shi, Liang Zhao, Lingfei Wu, Ming Jin, Qingsong Wen, Shirui Pan, Tian Zhou, Yuan-Fang Li","submitted_at":"2023-05-11T05:56:38Z","abstract_excerpt":"Time series forecasting has remained a focal point due to its vital applications in sectors such as energy management and transportation planning. Spectral-temporal graph neural network is a promising abstraction underlying most time series forecasting models that are based on graph neural networks (GNNs). However, more is needed to know about the underpinnings of this branch of methods. In this paper, we establish a theoretical framework that unravels the expressive power of spectral-temporal GNNs. Our results show that linear spectral-temporal GNNs are universal under mild assumptions, and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06587","kind":"arxiv","version":3},"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/2305.06587/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":"2305.06587","created_at":"2026-07-05T10:18:31.799984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.06587v3","created_at":"2026-07-05T10:18:31.799984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06587","created_at":"2026-07-05T10:18:31.799984+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CGGRUPQ6ITG","created_at":"2026-07-05T10:18:31.799984+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CGGRUPQ6ITGPJXY","created_at":"2026-07-05T10:18:31.799984+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CGGRUPQ","created_at":"2026-07-05T10:18:31.799984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05768","citing_title":"Real-E: A Foundation Benchmark for Advancing Robust and Generalizable Electricity Forecasting","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CGGRUPQ6ITGPJXYFNX7ALBJAT","json":"https://pith.science/pith/5CGGRUPQ6ITGPJXYFNX7ALBJAT.json","graph_json":"https://pith.science/api/pith-number/5CGGRUPQ6ITGPJXYFNX7ALBJAT/graph.json","events_json":"https://pith.science/api/pith-number/5CGGRUPQ6ITGPJXYFNX7ALBJAT/events.json","paper":"https://pith.science/paper/5CGGRUPQ"},"agent_actions":{"view_html":"https://pith.science/pith/5CGGRUPQ6ITGPJXYFNX7ALBJAT","download_json":"https://pith.science/pith/5CGGRUPQ6ITGPJXYFNX7ALBJAT.json","view_paper":"https://pith.science/paper/5CGGRUPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.06587&json=true","fetch_graph":"https://pith.science/api/pith-number/5CGGRUPQ6ITGPJXYFNX7ALBJAT/graph.json","fetch_events":"https://pith.science/api/pith-number/5CGGRUPQ6ITGPJXYFNX7ALBJAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CGGRUPQ6ITGPJXYFNX7ALBJAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CGGRUPQ6ITGPJXYFNX7ALBJAT/action/storage_attestation","attest_author":"https://pith.science/pith/5CGGRUPQ6ITGPJXYFNX7ALBJAT/action/author_attestation","sign_citation":"https://pith.science/pith/5CGGRUPQ6ITGPJXYFNX7ALBJAT/action/citation_signature","submit_replication":"https://pith.science/pith/5CGGRUPQ6ITGPJXYFNX7ALBJAT/action/replication_record"}},"created_at":"2026-07-05T10:18:31.799984+00:00","updated_at":"2026-07-05T10:18:31.799984+00:00"}