{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LWDHOVKOYEATKGFP2BV6JSA5M5","short_pith_number":"pith:LWDHOVKO","schema_version":"1.0","canonical_sha256":"5d8677554ec1013518afd06be4c81d6762d989fe3b14bcecf5615a0d7a55f47c","source":{"kind":"arxiv","id":"2406.09130","version":1},"attestation_state":"computed","paper":{"title":"Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"B. Aditya Prakash, Chao Zhang, Haoxin Liu, Harshavardhan Kamarthi, Lingkai Kong, Zhiyuan Zhao","submitted_at":"2024-06-13T14:01:34Z","abstract_excerpt":"Time-series forecasting (TSF) finds broad applications in real-world scenarios. Due to the dynamic nature of time-series data, it is crucial to equip TSF models with out-of-distribution (OOD) generalization abilities, as historical training data and future test data can have different distributions. In this paper, we aim to alleviate the inherent OOD problem in TSF via invariant learning. We identify fundamental challenges of invariant learning for TSF. First, the target variables in TSF may not be sufficiently determined by the input due to unobserved core variables in TSF, breaking the conve"},"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":"2406.09130","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T14:01:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f8c270d8df44f7a83f86cc062681e3f649da587deb794682b746a41cf6b4f1b2","abstract_canon_sha256":"6852e7b5a0fdce528d2bcfe6604526b66a01a9354b6e5e5d5e0252113a92451f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:28.531920Z","signature_b64":"2Cp30FPK9AloRzk/6mKKZ/E/HaAiDno6J7AssrnSt5VdG7s17UcgdFWYqx2JUSHxWE7dwA4Mq8eJVOmpn4GvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d8677554ec1013518afd06be4c81d6762d989fe3b14bcecf5615a0d7a55f47c","last_reissued_at":"2026-07-05T08:31:28.531443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:28.531443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"B. Aditya Prakash, Chao Zhang, Haoxin Liu, Harshavardhan Kamarthi, Lingkai Kong, Zhiyuan Zhao","submitted_at":"2024-06-13T14:01:34Z","abstract_excerpt":"Time-series forecasting (TSF) finds broad applications in real-world scenarios. Due to the dynamic nature of time-series data, it is crucial to equip TSF models with out-of-distribution (OOD) generalization abilities, as historical training data and future test data can have different distributions. In this paper, we aim to alleviate the inherent OOD problem in TSF via invariant learning. We identify fundamental challenges of invariant learning for TSF. First, the target variables in TSF may not be sufficiently determined by the input due to unobserved core variables in TSF, breaking the conve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09130","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/2406.09130/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":"2406.09130","created_at":"2026-07-05T08:31:28.531501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09130v1","created_at":"2026-07-05T08:31:28.531501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09130","created_at":"2026-07-05T08:31:28.531501+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWDHOVKOYEAT","created_at":"2026-07-05T08:31:28.531501+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWDHOVKOYEATKGFP","created_at":"2026-07-05T08:31:28.531501+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWDHOVKO","created_at":"2026-07-05T08:31:28.531501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02138","citing_title":"VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecasting","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08005","citing_title":"STEPS: A Temporal Smooth Error Propagation Solver on the Manifolds for Test-Time Adaptation in Time Series Forecasting","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05335","citing_title":"Cross-Machine Anomaly Detection Leveraging Pre-trained Time-series Model","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWDHOVKOYEATKGFP2BV6JSA5M5","json":"https://pith.science/pith/LWDHOVKOYEATKGFP2BV6JSA5M5.json","graph_json":"https://pith.science/api/pith-number/LWDHOVKOYEATKGFP2BV6JSA5M5/graph.json","events_json":"https://pith.science/api/pith-number/LWDHOVKOYEATKGFP2BV6JSA5M5/events.json","paper":"https://pith.science/paper/LWDHOVKO"},"agent_actions":{"view_html":"https://pith.science/pith/LWDHOVKOYEATKGFP2BV6JSA5M5","download_json":"https://pith.science/pith/LWDHOVKOYEATKGFP2BV6JSA5M5.json","view_paper":"https://pith.science/paper/LWDHOVKO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09130&json=true","fetch_graph":"https://pith.science/api/pith-number/LWDHOVKOYEATKGFP2BV6JSA5M5/graph.json","fetch_events":"https://pith.science/api/pith-number/LWDHOVKOYEATKGFP2BV6JSA5M5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWDHOVKOYEATKGFP2BV6JSA5M5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWDHOVKOYEATKGFP2BV6JSA5M5/action/storage_attestation","attest_author":"https://pith.science/pith/LWDHOVKOYEATKGFP2BV6JSA5M5/action/author_attestation","sign_citation":"https://pith.science/pith/LWDHOVKOYEATKGFP2BV6JSA5M5/action/citation_signature","submit_replication":"https://pith.science/pith/LWDHOVKOYEATKGFP2BV6JSA5M5/action/replication_record"}},"created_at":"2026-07-05T08:31:28.531501+00:00","updated_at":"2026-07-05T08:31:28.531501+00:00"}