{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OTST63AWPLKSMHMPEBJGJ2XBZM","short_pith_number":"pith:OTST63AW","schema_version":"1.0","canonical_sha256":"74e53f6c167ad5261d8f205264eae1cb3e34e3a0658d66e546ff20adfade23c2","source":{"kind":"arxiv","id":"2206.04038","version":4},"attestation_state":"computed","paper":{"title":"Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amin Shabani, Amir Abdi, Lili Meng, Tristan Sylvain","submitted_at":"2022-06-08T17:54:26Z","abstract_excerpt":"The performance of time series forecasting has recently been greatly improved by the introduction of transformers. In this paper, we propose a general multi-scale framework that can be applied to the state-of-the-art transformer-based time series forecasting models (FEDformer, Autoformer, etc.). By iteratively refining a forecasted time series at multiple scales with shared weights, introducing architecture adaptations, and a specially-designed normalization scheme, we are able to achieve significant performance improvements, from 5.5% to 38.5% across datasets and transformer architectures, wi"},"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":"2206.04038","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-08T17:54:26Z","cross_cats_sorted":[],"title_canon_sha256":"dcd0f8cba16cfdd802e02b66f46afbfcbaba9c1bae86c5805afcd2d1900faa22","abstract_canon_sha256":"b6fbca6b361c7ce5201f25a6f8542fcefe291cfb7528c7a624d350d7a4b7efc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:14.905024Z","signature_b64":"7mpLaXwbd9X4RFEIcYfmRZsct3EogXaS3CwVNcveC07Zkx9I7nb5biIwai71kPd792dhpA4Rv04G5rKghqydDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74e53f6c167ad5261d8f205264eae1cb3e34e3a0658d66e546ff20adfade23c2","last_reissued_at":"2026-07-05T05:39:14.904485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:14.904485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amin Shabani, Amir Abdi, Lili Meng, Tristan Sylvain","submitted_at":"2022-06-08T17:54:26Z","abstract_excerpt":"The performance of time series forecasting has recently been greatly improved by the introduction of transformers. In this paper, we propose a general multi-scale framework that can be applied to the state-of-the-art transformer-based time series forecasting models (FEDformer, Autoformer, etc.). By iteratively refining a forecasted time series at multiple scales with shared weights, introducing architecture adaptations, and a specially-designed normalization scheme, we are able to achieve significant performance improvements, from 5.5% to 38.5% across datasets and transformer architectures, wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04038","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/2206.04038/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":"2206.04038","created_at":"2026-07-05T05:39:14.904546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04038v4","created_at":"2026-07-05T05:39:14.904546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04038","created_at":"2026-07-05T05:39:14.904546+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTST63AWPLKS","created_at":"2026-07-05T05:39:14.904546+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTST63AWPLKSMHMP","created_at":"2026-07-05T05:39:14.904546+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTST63AW","created_at":"2026-07-05T05:39:14.904546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10292","citing_title":"LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTST63AWPLKSMHMPEBJGJ2XBZM","json":"https://pith.science/pith/OTST63AWPLKSMHMPEBJGJ2XBZM.json","graph_json":"https://pith.science/api/pith-number/OTST63AWPLKSMHMPEBJGJ2XBZM/graph.json","events_json":"https://pith.science/api/pith-number/OTST63AWPLKSMHMPEBJGJ2XBZM/events.json","paper":"https://pith.science/paper/OTST63AW"},"agent_actions":{"view_html":"https://pith.science/pith/OTST63AWPLKSMHMPEBJGJ2XBZM","download_json":"https://pith.science/pith/OTST63AWPLKSMHMPEBJGJ2XBZM.json","view_paper":"https://pith.science/paper/OTST63AW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04038&json=true","fetch_graph":"https://pith.science/api/pith-number/OTST63AWPLKSMHMPEBJGJ2XBZM/graph.json","fetch_events":"https://pith.science/api/pith-number/OTST63AWPLKSMHMPEBJGJ2XBZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTST63AWPLKSMHMPEBJGJ2XBZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTST63AWPLKSMHMPEBJGJ2XBZM/action/storage_attestation","attest_author":"https://pith.science/pith/OTST63AWPLKSMHMPEBJGJ2XBZM/action/author_attestation","sign_citation":"https://pith.science/pith/OTST63AWPLKSMHMPEBJGJ2XBZM/action/citation_signature","submit_replication":"https://pith.science/pith/OTST63AWPLKSMHMPEBJGJ2XBZM/action/replication_record"}},"created_at":"2026-07-05T05:39:14.904546+00:00","updated_at":"2026-07-05T05:39:14.904546+00:00"}