{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VBGIHAVTWX6MV7P4SEVJX3ISEV","short_pith_number":"pith:VBGIHAVT","schema_version":"1.0","canonical_sha256":"a84c8382b3b5fccafdfc912a9bed12255e6f58522584ea21dc98e9f72504f601","source":{"kind":"arxiv","id":"2308.11200","version":1},"attestation_state":"computed","paper":{"title":"SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feiyu Zhao, Haotong Zhang, Ruichao Mo, Shengsheng Lin, Weiwei Lin, Wentai Wu","submitted_at":"2023-08-22T05:23:04Z","abstract_excerpt":"RNN-based methods have faced challenges in the Long-term Time Series Forecasting (LTSF) domain when dealing with excessively long look-back windows and forecast horizons. Consequently, the dominance in this domain has shifted towards Transformer, MLP, and CNN approaches. The substantial number of recurrent iterations are the fundamental reasons behind the limitations of RNNs in LTSF. To address these issues, we propose two novel strategies to reduce the number of iterations in RNNs for LTSF tasks: Segment-wise Iterations and Parallel Multi-step Forecasting (PMF). RNNs that combine these strate"},"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":"2308.11200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-22T05:23:04Z","cross_cats_sorted":[],"title_canon_sha256":"ee53e0577caf4044f71bfb8f341453462506b0617e045048b8792ba5025cbaa0","abstract_canon_sha256":"bc8a4027aa3c3175297441f831737a06e7b4f4907099f66db795a494b1e1dc4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:31.037683Z","signature_b64":"UZ5Z9KOMg3PydC8gErw8JgPVlSuzG/j9gqzvYItnDrO8Dar0xuwX3bgGDVVlUljULz5WgNUkWTfCAQ3J/3K1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a84c8382b3b5fccafdfc912a9bed12255e6f58522584ea21dc98e9f72504f601","last_reissued_at":"2026-07-05T06:43:31.037088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:31.037088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feiyu Zhao, Haotong Zhang, Ruichao Mo, Shengsheng Lin, Weiwei Lin, Wentai Wu","submitted_at":"2023-08-22T05:23:04Z","abstract_excerpt":"RNN-based methods have faced challenges in the Long-term Time Series Forecasting (LTSF) domain when dealing with excessively long look-back windows and forecast horizons. Consequently, the dominance in this domain has shifted towards Transformer, MLP, and CNN approaches. The substantial number of recurrent iterations are the fundamental reasons behind the limitations of RNNs in LTSF. To address these issues, we propose two novel strategies to reduce the number of iterations in RNNs for LTSF tasks: Segment-wise Iterations and Parallel Multi-step Forecasting (PMF). RNNs that combine these strate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11200","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/2308.11200/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":"2308.11200","created_at":"2026-07-05T06:43:31.037153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.11200v1","created_at":"2026-07-05T06:43:31.037153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11200","created_at":"2026-07-05T06:43:31.037153+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBGIHAVTWX6M","created_at":"2026-07-05T06:43:31.037153+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBGIHAVTWX6MV7P4","created_at":"2026-07-05T06:43:31.037153+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBGIHAVT","created_at":"2026-07-05T06:43:31.037153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26193","citing_title":"Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18834","citing_title":"FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22365","citing_title":"TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23239","citing_title":"AdaMamba: Adaptive Frequency-Gated Mamba for Long-Term Time Series Forecasting","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00322","citing_title":"Federated Weather Modeling on Sensor Data","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15791","citing_title":"Convolutionally Low-Rank Models with Modified Quantile Regression for Interval Time Series Forecasting","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VBGIHAVTWX6MV7P4SEVJX3ISEV","json":"https://pith.science/pith/VBGIHAVTWX6MV7P4SEVJX3ISEV.json","graph_json":"https://pith.science/api/pith-number/VBGIHAVTWX6MV7P4SEVJX3ISEV/graph.json","events_json":"https://pith.science/api/pith-number/VBGIHAVTWX6MV7P4SEVJX3ISEV/events.json","paper":"https://pith.science/paper/VBGIHAVT"},"agent_actions":{"view_html":"https://pith.science/pith/VBGIHAVTWX6MV7P4SEVJX3ISEV","download_json":"https://pith.science/pith/VBGIHAVTWX6MV7P4SEVJX3ISEV.json","view_paper":"https://pith.science/paper/VBGIHAVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.11200&json=true","fetch_graph":"https://pith.science/api/pith-number/VBGIHAVTWX6MV7P4SEVJX3ISEV/graph.json","fetch_events":"https://pith.science/api/pith-number/VBGIHAVTWX6MV7P4SEVJX3ISEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBGIHAVTWX6MV7P4SEVJX3ISEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBGIHAVTWX6MV7P4SEVJX3ISEV/action/storage_attestation","attest_author":"https://pith.science/pith/VBGIHAVTWX6MV7P4SEVJX3ISEV/action/author_attestation","sign_citation":"https://pith.science/pith/VBGIHAVTWX6MV7P4SEVJX3ISEV/action/citation_signature","submit_replication":"https://pith.science/pith/VBGIHAVTWX6MV7P4SEVJX3ISEV/action/replication_record"}},"created_at":"2026-07-05T06:43:31.037153+00:00","updated_at":"2026-07-05T06:43:31.037153+00:00"}