{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SYRHTJWL2V3PEJ22FLTAC3TTYJ","short_pith_number":"pith:SYRHTJWL","schema_version":"1.0","canonical_sha256":"962279a6cbd576f2275a2ae6016e73c26e1a50644f86c7c4e8a4dc438e992602","source":{"kind":"arxiv","id":"2310.15978","version":2},"attestation_state":"computed","paper":{"title":"Graph Deep Learning for Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrea Cini, Cesare Alippi, Daniele Zambon, Ivan Marisca","submitted_at":"2023-10-24T16:26:38Z","abstract_excerpt":"Graph deep learning methods have become popular tools to process collections of correlated time series. Unlike traditional multivariate forecasting methods, graph-based predictors leverage pairwise relationships by conditioning forecasts on graphs spanning the time series collection. The conditioning takes the form of architectural inductive biases on the forecasting architecture, resulting in a family of models called spatiotemporal graph neural networks. These biases allow for training global forecasting models on large collections of time series while localizing predictions w.r.t. each elem"},"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":"2310.15978","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-24T16:26:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1401e3894bd84fc961ef895857756142c7e7042197dfe42187d88039ff2955b1","abstract_canon_sha256":"fe4cb026b2eac730bc79e1b76266df23501df76216ea75d64bdb548d61c9ff8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:48.040549Z","signature_b64":"F2SQ39ryfecuilN2V0yjnYPQjLOB3NiooFwTnuUeB8ecj1xzTdDUuQLZ94Gob6+UCnSqk8RJz6nmnfPQ4FrnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"962279a6cbd576f2275a2ae6016e73c26e1a50644f86c7c4e8a4dc438e992602","last_reissued_at":"2026-07-05T11:16:48.040055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:48.040055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Deep Learning for Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrea Cini, Cesare Alippi, Daniele Zambon, Ivan Marisca","submitted_at":"2023-10-24T16:26:38Z","abstract_excerpt":"Graph deep learning methods have become popular tools to process collections of correlated time series. Unlike traditional multivariate forecasting methods, graph-based predictors leverage pairwise relationships by conditioning forecasts on graphs spanning the time series collection. The conditioning takes the form of architectural inductive biases on the forecasting architecture, resulting in a family of models called spatiotemporal graph neural networks. These biases allow for training global forecasting models on large collections of time series while localizing predictions w.r.t. each elem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15978","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/2310.15978/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":"2310.15978","created_at":"2026-07-05T11:16:48.040111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15978v2","created_at":"2026-07-05T11:16:48.040111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15978","created_at":"2026-07-05T11:16:48.040111+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYRHTJWL2V3P","created_at":"2026-07-05T11:16:48.040111+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYRHTJWL2V3PEJ22","created_at":"2026-07-05T11:16:48.040111+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYRHTJWL","created_at":"2026-07-05T11:16:48.040111+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.13469","citing_title":"Interpreting Temporal Graph Neural Networks with Koopman Theory","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19172","citing_title":"Bridge: Retrieval-Augmented Spatiotemporal Modeling for Urban Delivery Demand","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2507.13305","citing_title":"Boosting Team Modeling through Tempo-Relational Representation Learning","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SYRHTJWL2V3PEJ22FLTAC3TTYJ","json":"https://pith.science/pith/SYRHTJWL2V3PEJ22FLTAC3TTYJ.json","graph_json":"https://pith.science/api/pith-number/SYRHTJWL2V3PEJ22FLTAC3TTYJ/graph.json","events_json":"https://pith.science/api/pith-number/SYRHTJWL2V3PEJ22FLTAC3TTYJ/events.json","paper":"https://pith.science/paper/SYRHTJWL"},"agent_actions":{"view_html":"https://pith.science/pith/SYRHTJWL2V3PEJ22FLTAC3TTYJ","download_json":"https://pith.science/pith/SYRHTJWL2V3PEJ22FLTAC3TTYJ.json","view_paper":"https://pith.science/paper/SYRHTJWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15978&json=true","fetch_graph":"https://pith.science/api/pith-number/SYRHTJWL2V3PEJ22FLTAC3TTYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/SYRHTJWL2V3PEJ22FLTAC3TTYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYRHTJWL2V3PEJ22FLTAC3TTYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYRHTJWL2V3PEJ22FLTAC3TTYJ/action/storage_attestation","attest_author":"https://pith.science/pith/SYRHTJWL2V3PEJ22FLTAC3TTYJ/action/author_attestation","sign_citation":"https://pith.science/pith/SYRHTJWL2V3PEJ22FLTAC3TTYJ/action/citation_signature","submit_replication":"https://pith.science/pith/SYRHTJWL2V3PEJ22FLTAC3TTYJ/action/replication_record"}},"created_at":"2026-07-05T11:16:48.040111+00:00","updated_at":"2026-07-05T11:16:48.040111+00:00"}