{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R244TSYFS6SNYKDHO3QKC5E2OC","short_pith_number":"pith:R244TSYF","schema_version":"1.0","canonical_sha256":"8eb9c9cb0597a4dc286776e0a1749a70a7226948e0937447bb3977f62fcc8cc8","source":{"kind":"arxiv","id":"2306.05035","version":3},"attestation_state":"computed","paper":{"title":"Does Long-Term Series Forecasting Need Complex Attention and Extra Long Inputs?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daojun Liang, Dongfeng Yuan, Dongyang Li, Haixia Zhang, Minggao Zhang, Xiaoyan Ma","submitted_at":"2023-06-08T08:37:49Z","abstract_excerpt":"As Transformer-based models have achieved impressive performance on various time series tasks, Long-Term Series Forecasting (LTSF) tasks have also received extensive attention in recent years. However, due to the inherent computational complexity and long sequences demanding of Transformer-based methods, its application on LTSF tasks still has two major issues that need to be further investigated: 1) Whether the sparse attention mechanism designed by these methods actually reduce the running time on real devices; 2) Whether these models need extra long input sequences to guarantee their perfor"},"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":"2306.05035","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-08T08:37:49Z","cross_cats_sorted":[],"title_canon_sha256":"ca8309d8ddcb5310457ca06c4d9fceffecfa6f1da3468fad95ff37aca2280b80","abstract_canon_sha256":"37c4dc8a0ee8cc78fd4a1c968e5f47b4bd8cd96c072b6f15f08fcc5b082fe936"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:54.138749Z","signature_b64":"gswEQIcEAKKmirHnLL/uhAMlEP76JIERwz642ZF9LBZ8lIDWXgKBj/gGlBimq9jMg7sXt1itVF60qkS2KsleAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eb9c9cb0597a4dc286776e0a1749a70a7226948e0937447bb3977f62fcc8cc8","last_reissued_at":"2026-07-05T07:40:54.138216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:54.138216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Long-Term Series Forecasting Need Complex Attention and Extra Long Inputs?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daojun Liang, Dongfeng Yuan, Dongyang Li, Haixia Zhang, Minggao Zhang, Xiaoyan Ma","submitted_at":"2023-06-08T08:37:49Z","abstract_excerpt":"As Transformer-based models have achieved impressive performance on various time series tasks, Long-Term Series Forecasting (LTSF) tasks have also received extensive attention in recent years. However, due to the inherent computational complexity and long sequences demanding of Transformer-based methods, its application on LTSF tasks still has two major issues that need to be further investigated: 1) Whether the sparse attention mechanism designed by these methods actually reduce the running time on real devices; 2) Whether these models need extra long input sequences to guarantee their perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05035","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/2306.05035/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":"2306.05035","created_at":"2026-07-05T07:40:54.138274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05035v3","created_at":"2026-07-05T07:40:54.138274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05035","created_at":"2026-07-05T07:40:54.138274+00:00"},{"alias_kind":"pith_short_12","alias_value":"R244TSYFS6SN","created_at":"2026-07-05T07:40:54.138274+00:00"},{"alias_kind":"pith_short_16","alias_value":"R244TSYFS6SNYKDH","created_at":"2026-07-05T07:40:54.138274+00:00"},{"alias_kind":"pith_short_8","alias_value":"R244TSYF","created_at":"2026-07-05T07:40:54.138274+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10592","citing_title":"Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R244TSYFS6SNYKDHO3QKC5E2OC","json":"https://pith.science/pith/R244TSYFS6SNYKDHO3QKC5E2OC.json","graph_json":"https://pith.science/api/pith-number/R244TSYFS6SNYKDHO3QKC5E2OC/graph.json","events_json":"https://pith.science/api/pith-number/R244TSYFS6SNYKDHO3QKC5E2OC/events.json","paper":"https://pith.science/paper/R244TSYF"},"agent_actions":{"view_html":"https://pith.science/pith/R244TSYFS6SNYKDHO3QKC5E2OC","download_json":"https://pith.science/pith/R244TSYFS6SNYKDHO3QKC5E2OC.json","view_paper":"https://pith.science/paper/R244TSYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05035&json=true","fetch_graph":"https://pith.science/api/pith-number/R244TSYFS6SNYKDHO3QKC5E2OC/graph.json","fetch_events":"https://pith.science/api/pith-number/R244TSYFS6SNYKDHO3QKC5E2OC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R244TSYFS6SNYKDHO3QKC5E2OC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R244TSYFS6SNYKDHO3QKC5E2OC/action/storage_attestation","attest_author":"https://pith.science/pith/R244TSYFS6SNYKDHO3QKC5E2OC/action/author_attestation","sign_citation":"https://pith.science/pith/R244TSYFS6SNYKDHO3QKC5E2OC/action/citation_signature","submit_replication":"https://pith.science/pith/R244TSYFS6SNYKDHO3QKC5E2OC/action/replication_record"}},"created_at":"2026-07-05T07:40:54.138274+00:00","updated_at":"2026-07-05T07:40:54.138274+00:00"}