{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FPYA5PP4MY6PETO376KAJDHYTL","short_pith_number":"pith:FPYA5PP4","schema_version":"1.0","canonical_sha256":"2bf00ebdfc663cf24ddbff94048cf89aeb72c98b44aec4f618a6a3db0b4c4790","source":{"kind":"arxiv","id":"2205.14415","version":4},"attestation_state":"computed","paper":{"title":"Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Haixu Wu, Jianmin Wang, Mingsheng Long, Yong Liu","submitted_at":"2022-05-28T12:27:27Z","abstract_excerpt":"Transformers have shown great power in time series forecasting due to their global-range modeling ability. However, their performance can degenerate terribly on non-stationary real-world data in which the joint distribution changes over time. Previous studies primarily adopt stationarization to attenuate the non-stationarity of original series for better predictability. But the stationarized series deprived of inherent non-stationarity can be less instructive for real-world bursty events forecasting. This problem, termed over-stationarization in this paper, leads Transformers to generate indis"},"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":"2205.14415","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-28T12:27:27Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"b818f7b84135a9c29a6bb25aa1379452e12c58dbb921953bccbda2277d182f6f","abstract_canon_sha256":"1a1bcc71e9278c25303d29d58fc37239da93e27618d07a28a72936a450ac57c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:46.083278Z","signature_b64":"wITHAma1Vo01tGlTq6nDRDS6EPErD61TelRuUc9oXYkqynZdOA9WD16ZrJaM4gFaJ3SgPLH6G38i+ax8wbSfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bf00ebdfc663cf24ddbff94048cf89aeb72c98b44aec4f618a6a3db0b4c4790","last_reissued_at":"2026-07-05T07:15:46.082712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:46.082712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Haixu Wu, Jianmin Wang, Mingsheng Long, Yong Liu","submitted_at":"2022-05-28T12:27:27Z","abstract_excerpt":"Transformers have shown great power in time series forecasting due to their global-range modeling ability. However, their performance can degenerate terribly on non-stationary real-world data in which the joint distribution changes over time. Previous studies primarily adopt stationarization to attenuate the non-stationarity of original series for better predictability. But the stationarized series deprived of inherent non-stationarity can be less instructive for real-world bursty events forecasting. This problem, termed over-stationarization in this paper, leads Transformers to generate indis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14415","kind":"arxiv","version":4},"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/2205.14415/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":"2205.14415","created_at":"2026-07-05T07:15:46.082777+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14415v4","created_at":"2026-07-05T07:15:46.082777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14415","created_at":"2026-07-05T07:15:46.082777+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPYA5PP4MY6P","created_at":"2026-07-05T07:15:46.082777+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPYA5PP4MY6PETO3","created_at":"2026-07-05T07:15:46.082777+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPYA5PP4","created_at":"2026-07-05T07:15:46.082777+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.06063","citing_title":"TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15774","citing_title":"Time Series Forecasting Through the Lens of Dynamics","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPYA5PP4MY6PETO376KAJDHYTL","json":"https://pith.science/pith/FPYA5PP4MY6PETO376KAJDHYTL.json","graph_json":"https://pith.science/api/pith-number/FPYA5PP4MY6PETO376KAJDHYTL/graph.json","events_json":"https://pith.science/api/pith-number/FPYA5PP4MY6PETO376KAJDHYTL/events.json","paper":"https://pith.science/paper/FPYA5PP4"},"agent_actions":{"view_html":"https://pith.science/pith/FPYA5PP4MY6PETO376KAJDHYTL","download_json":"https://pith.science/pith/FPYA5PP4MY6PETO376KAJDHYTL.json","view_paper":"https://pith.science/paper/FPYA5PP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14415&json=true","fetch_graph":"https://pith.science/api/pith-number/FPYA5PP4MY6PETO376KAJDHYTL/graph.json","fetch_events":"https://pith.science/api/pith-number/FPYA5PP4MY6PETO376KAJDHYTL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPYA5PP4MY6PETO376KAJDHYTL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPYA5PP4MY6PETO376KAJDHYTL/action/storage_attestation","attest_author":"https://pith.science/pith/FPYA5PP4MY6PETO376KAJDHYTL/action/author_attestation","sign_citation":"https://pith.science/pith/FPYA5PP4MY6PETO376KAJDHYTL/action/citation_signature","submit_replication":"https://pith.science/pith/FPYA5PP4MY6PETO376KAJDHYTL/action/replication_record"}},"created_at":"2026-07-05T07:15:46.082777+00:00","updated_at":"2026-07-05T07:15:46.082777+00:00"}