{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BOVCQJYY7D7UUNPUDUXH66V3HM","short_pith_number":"pith:BOVCQJYY","schema_version":"1.0","canonical_sha256":"0baa282718f8ff4a35f41d2e7f7abb3b242dd866280c9cb5e58477e6dcebf091","source":{"kind":"arxiv","id":"2605.21088","version":1},"attestation_state":"computed","paper":{"title":"Reviving Error Correction in Modern Deep Time-Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dai Do, Dung Nguyen, Hung Le, Huu Hiep Nguyen, Kien Do, Minh Hoang Nguyen","submitted_at":"2026-05-20T12:22:18Z","abstract_excerpt":"Modern deep-learning models have achieved remarkable success in time-series forecasting. Yet, their performance degrades in long-term prediction due to error accumulation in autoregressive inference, where predictions are recursively used as inputs. While classical error correction mechanisms (ECMs) have long been used in statistical methods, their applicability to deep learning models remains limited or ineffective. In this work, we revisit the error accumulation problem in deep time-series forecasting and investigate the role and necessity of ECMs in this new context. We propose a simple, ar"},"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":"2605.21088","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T12:22:18Z","cross_cats_sorted":[],"title_canon_sha256":"ad18c45288ba28b0f896df07ff7e6d5114cd8649389d837d521000d53e1c6abe","abstract_canon_sha256":"243e2f8617986c775d9e12a0854f28ef89381e9cdc4d2f72f00919f013d8e9fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:36.423201Z","signature_b64":"+E8xzD3zeOTSgWf+3s/QmmdWNGWUC+a7nn4uvC83qiMtg+TKm3fNxeT5GLcwbdK7fThJNTgwkI233HKQMJdyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0baa282718f8ff4a35f41d2e7f7abb3b242dd866280c9cb5e58477e6dcebf091","last_reissued_at":"2026-05-21T01:05:36.422458Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:36.422458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reviving Error Correction in Modern Deep Time-Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dai Do, Dung Nguyen, Hung Le, Huu Hiep Nguyen, Kien Do, Minh Hoang Nguyen","submitted_at":"2026-05-20T12:22:18Z","abstract_excerpt":"Modern deep-learning models have achieved remarkable success in time-series forecasting. Yet, their performance degrades in long-term prediction due to error accumulation in autoregressive inference, where predictions are recursively used as inputs. While classical error correction mechanisms (ECMs) have long been used in statistical methods, their applicability to deep learning models remains limited or ineffective. In this work, we revisit the error accumulation problem in deep time-series forecasting and investigate the role and necessity of ECMs in this new context. We propose a simple, ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21088","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/2605.21088/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":"2605.21088","created_at":"2026-05-21T01:05:36.422573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21088v1","created_at":"2026-05-21T01:05:36.422573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21088","created_at":"2026-05-21T01:05:36.422573+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOVCQJYY7D7U","created_at":"2026-05-21T01:05:36.422573+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOVCQJYY7D7UUNPU","created_at":"2026-05-21T01:05:36.422573+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOVCQJYY","created_at":"2026-05-21T01:05:36.422573+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/BOVCQJYY7D7UUNPUDUXH66V3HM","json":"https://pith.science/pith/BOVCQJYY7D7UUNPUDUXH66V3HM.json","graph_json":"https://pith.science/api/pith-number/BOVCQJYY7D7UUNPUDUXH66V3HM/graph.json","events_json":"https://pith.science/api/pith-number/BOVCQJYY7D7UUNPUDUXH66V3HM/events.json","paper":"https://pith.science/paper/BOVCQJYY"},"agent_actions":{"view_html":"https://pith.science/pith/BOVCQJYY7D7UUNPUDUXH66V3HM","download_json":"https://pith.science/pith/BOVCQJYY7D7UUNPUDUXH66V3HM.json","view_paper":"https://pith.science/paper/BOVCQJYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21088&json=true","fetch_graph":"https://pith.science/api/pith-number/BOVCQJYY7D7UUNPUDUXH66V3HM/graph.json","fetch_events":"https://pith.science/api/pith-number/BOVCQJYY7D7UUNPUDUXH66V3HM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOVCQJYY7D7UUNPUDUXH66V3HM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOVCQJYY7D7UUNPUDUXH66V3HM/action/storage_attestation","attest_author":"https://pith.science/pith/BOVCQJYY7D7UUNPUDUXH66V3HM/action/author_attestation","sign_citation":"https://pith.science/pith/BOVCQJYY7D7UUNPUDUXH66V3HM/action/citation_signature","submit_replication":"https://pith.science/pith/BOVCQJYY7D7UUNPUDUXH66V3HM/action/replication_record"}},"created_at":"2026-05-21T01:05:36.422573+00:00","updated_at":"2026-05-21T01:05:36.422573+00:00"}