{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TMFANRORGOH5ZNOD4QMVRFMWUL","short_pith_number":"pith:TMFANROR","schema_version":"1.0","canonical_sha256":"9b0a06c5d1338fdcb5c3e419589596a2e463ba8079a3bf990fa623fc8640f77d","source":{"kind":"arxiv","id":"2202.02403","version":3},"attestation_state":"computed","paper":{"title":"Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Nathanael C. Yoder, Sercan O. Arik, Tomas Pfister","submitted_at":"2022-02-04T21:54:10Z","abstract_excerpt":"Real-world time-series datasets often violate the assumptions of standard supervised learning for forecasting -- their distributions evolve over time, rendering the conventional training and model selection procedures suboptimal. In this paper, we propose a novel method, Self-Adaptive Forecasting (SAF), to modify the training of time-series forecasting models to improve their performance on forecasting tasks with such non-stationary time-series data. SAF integrates a self-adaptation stage prior to forecasting based on `backcasting', i.e. predicting masked inputs backward in time. This is a for"},"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":"2202.02403","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-04T21:54:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c3061f1965e931b97993b3ff2e5679640e911f57cc792c072048f28338d95896","abstract_canon_sha256":"24a7105de8e59ec9a7f0d18e6f389c293ce5992213f4faf87e34eafb68968b5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:40.163575Z","signature_b64":"rAZ+09QmnsfG2wdatg6J4Qy3uUxuuB0mPFkZhC2yaTYchSfatIVj0xqfQ+3KaQVxVC019Y+cjSQq8u7zq6njAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b0a06c5d1338fdcb5c3e419589596a2e463ba8079a3bf990fa623fc8640f77d","last_reissued_at":"2026-07-05T05:00:40.163179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:40.163179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Nathanael C. Yoder, Sercan O. Arik, Tomas Pfister","submitted_at":"2022-02-04T21:54:10Z","abstract_excerpt":"Real-world time-series datasets often violate the assumptions of standard supervised learning for forecasting -- their distributions evolve over time, rendering the conventional training and model selection procedures suboptimal. In this paper, we propose a novel method, Self-Adaptive Forecasting (SAF), to modify the training of time-series forecasting models to improve their performance on forecasting tasks with such non-stationary time-series data. SAF integrates a self-adaptation stage prior to forecasting based on `backcasting', i.e. predicting masked inputs backward in time. This is a for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02403","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/2202.02403/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":"2202.02403","created_at":"2026-07-05T05:00:40.163234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.02403v3","created_at":"2026-07-05T05:00:40.163234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02403","created_at":"2026-07-05T05:00:40.163234+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMFANRORGOH5","created_at":"2026-07-05T05:00:40.163234+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMFANRORGOH5ZNOD","created_at":"2026-07-05T05:00:40.163234+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMFANROR","created_at":"2026-07-05T05:00:40.163234+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/TMFANRORGOH5ZNOD4QMVRFMWUL","json":"https://pith.science/pith/TMFANRORGOH5ZNOD4QMVRFMWUL.json","graph_json":"https://pith.science/api/pith-number/TMFANRORGOH5ZNOD4QMVRFMWUL/graph.json","events_json":"https://pith.science/api/pith-number/TMFANRORGOH5ZNOD4QMVRFMWUL/events.json","paper":"https://pith.science/paper/TMFANROR"},"agent_actions":{"view_html":"https://pith.science/pith/TMFANRORGOH5ZNOD4QMVRFMWUL","download_json":"https://pith.science/pith/TMFANRORGOH5ZNOD4QMVRFMWUL.json","view_paper":"https://pith.science/paper/TMFANROR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.02403&json=true","fetch_graph":"https://pith.science/api/pith-number/TMFANRORGOH5ZNOD4QMVRFMWUL/graph.json","fetch_events":"https://pith.science/api/pith-number/TMFANRORGOH5ZNOD4QMVRFMWUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMFANRORGOH5ZNOD4QMVRFMWUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMFANRORGOH5ZNOD4QMVRFMWUL/action/storage_attestation","attest_author":"https://pith.science/pith/TMFANRORGOH5ZNOD4QMVRFMWUL/action/author_attestation","sign_citation":"https://pith.science/pith/TMFANRORGOH5ZNOD4QMVRFMWUL/action/citation_signature","submit_replication":"https://pith.science/pith/TMFANRORGOH5ZNOD4QMVRFMWUL/action/replication_record"}},"created_at":"2026-07-05T05:00:40.163234+00:00","updated_at":"2026-07-05T05:00:40.163234+00:00"}