{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SDHCDAUG5IT6QO6LVFKOE5DD6S","short_pith_number":"pith:SDHCDAUG","schema_version":"1.0","canonical_sha256":"90ce218286ea27e83bcba954e27463f4b62cd30e7df04fe57c58ca63dfe7b1ee","source":{"kind":"arxiv","id":"2405.16440","version":1},"attestation_state":"computed","paper":{"title":"MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Xiuding Cai, Xueyao Wang, Yaoyao Zhu, Yu Yao","submitted_at":"2024-05-26T05:50:17Z","abstract_excerpt":"In recent years, Transformers have become the de-facto architecture for long-term sequence forecasting (LTSF), but faces challenges such as quadratic complexity and permutation invariant bias. A recent model, Mamba, based on selective state space models (SSMs), has emerged as a competitive alternative to Transformer, offering comparable performance with higher throughput and linear complexity related to sequence length. In this study, we analyze the limitations of current Mamba in LTSF and propose four targeted improvements, leading to MambaTS. We first introduce variable scan along time to 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":"2405.16440","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T05:50:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d1e58c7ad0281a8599e25be22104b42b3e538c8e62bb3bd645316f7a041a60a5","abstract_canon_sha256":"e74f24e56970631b83ab201637ffa2f81bc306d53f437ab5f57f6d18bdb97119"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:30.402464Z","signature_b64":"dmaXFox3Crd+xGxK62cxpAGNtq7yBB7meHtoHTXF+JX3agqR8GlV5pW900oD2FJWuK7glHmjpcDIYl5EFvpcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90ce218286ea27e83bcba954e27463f4b62cd30e7df04fe57c58ca63dfe7b1ee","last_reissued_at":"2026-07-05T08:23:30.401984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:30.401984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Xiuding Cai, Xueyao Wang, Yaoyao Zhu, Yu Yao","submitted_at":"2024-05-26T05:50:17Z","abstract_excerpt":"In recent years, Transformers have become the de-facto architecture for long-term sequence forecasting (LTSF), but faces challenges such as quadratic complexity and permutation invariant bias. A recent model, Mamba, based on selective state space models (SSMs), has emerged as a competitive alternative to Transformer, offering comparable performance with higher throughput and linear complexity related to sequence length. In this study, we analyze the limitations of current Mamba in LTSF and propose four targeted improvements, leading to MambaTS. We first introduce variable scan along time to ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16440","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/2405.16440/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":"2405.16440","created_at":"2026-07-05T08:23:30.402042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16440v1","created_at":"2026-07-05T08:23:30.402042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16440","created_at":"2026-07-05T08:23:30.402042+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDHCDAUG5IT6","created_at":"2026-07-05T08:23:30.402042+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDHCDAUG5IT6QO6L","created_at":"2026-07-05T08:23:30.402042+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDHCDAUG","created_at":"2026-07-05T08:23:30.402042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2508.12247","citing_title":"STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series Prediction","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2503.18970","citing_title":"Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to Mamba","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2508.12247","citing_title":"STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series Prediction","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2601.05527","citing_title":"DeMa: Dual-Path Delay-Aware Mamba for Efficient Multivariate Time Series Analysis","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDHCDAUG5IT6QO6LVFKOE5DD6S","json":"https://pith.science/pith/SDHCDAUG5IT6QO6LVFKOE5DD6S.json","graph_json":"https://pith.science/api/pith-number/SDHCDAUG5IT6QO6LVFKOE5DD6S/graph.json","events_json":"https://pith.science/api/pith-number/SDHCDAUG5IT6QO6LVFKOE5DD6S/events.json","paper":"https://pith.science/paper/SDHCDAUG"},"agent_actions":{"view_html":"https://pith.science/pith/SDHCDAUG5IT6QO6LVFKOE5DD6S","download_json":"https://pith.science/pith/SDHCDAUG5IT6QO6LVFKOE5DD6S.json","view_paper":"https://pith.science/paper/SDHCDAUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16440&json=true","fetch_graph":"https://pith.science/api/pith-number/SDHCDAUG5IT6QO6LVFKOE5DD6S/graph.json","fetch_events":"https://pith.science/api/pith-number/SDHCDAUG5IT6QO6LVFKOE5DD6S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDHCDAUG5IT6QO6LVFKOE5DD6S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDHCDAUG5IT6QO6LVFKOE5DD6S/action/storage_attestation","attest_author":"https://pith.science/pith/SDHCDAUG5IT6QO6LVFKOE5DD6S/action/author_attestation","sign_citation":"https://pith.science/pith/SDHCDAUG5IT6QO6LVFKOE5DD6S/action/citation_signature","submit_replication":"https://pith.science/pith/SDHCDAUG5IT6QO6LVFKOE5DD6S/action/replication_record"}},"created_at":"2026-07-05T08:23:30.402042+00:00","updated_at":"2026-07-05T08:23:30.402042+00:00"}