{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VEHGQ3SNIANXULE3HAVADS2G6B","short_pith_number":"pith:VEHGQ3SN","schema_version":"1.0","canonical_sha256":"a90e686e4d401b7a2c9b382a01cb46f0586b7a7d1f6dc572987d227c4e8fd92b","source":{"kind":"arxiv","id":"2403.09898","version":2},"attestation_state":"computed","paper":{"title":"TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Md Atik Ahamed, Qiang Cheng","submitted_at":"2024-03-14T22:19:37Z","abstract_excerpt":"Long-term time-series forecasting remains challenging due to the difficulty in capturing long-term dependencies, achieving linear scalability, and maintaining computational efficiency. We introduce TimeMachine, an innovative model that leverages Mamba, a state-space model, to capture long-term dependencies in multivariate time series data while maintaining linear scalability and small memory footprints. TimeMachine exploits the unique properties of time series data to produce salient contextual cues at multi-scales and leverage an innovative integrated quadruple-Mamba architecture to unify the"},"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":"2403.09898","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-14T22:19:37Z","cross_cats_sorted":[],"title_canon_sha256":"c023c31c913916388904343f4fb49db9843bfa9acd88e5b6b11b9e0c075e8740","abstract_canon_sha256":"2fb137e7b529b93d121946cc2f01aeda24dac50bbd32d234d00a1a5b2e9363f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:22.746334Z","signature_b64":"PrwnrZTuzJwbp8E8G0//MlHhJpewV10TAR/Ng1ixFaTPwqw88hN6Bik8NVJCOMhJRa6GQVsVE1mjZJnPTLB5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a90e686e4d401b7a2c9b382a01cb46f0586b7a7d1f6dc572987d227c4e8fd92b","last_reissued_at":"2026-07-05T08:58:22.745822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:22.745822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Md Atik Ahamed, Qiang Cheng","submitted_at":"2024-03-14T22:19:37Z","abstract_excerpt":"Long-term time-series forecasting remains challenging due to the difficulty in capturing long-term dependencies, achieving linear scalability, and maintaining computational efficiency. We introduce TimeMachine, an innovative model that leverages Mamba, a state-space model, to capture long-term dependencies in multivariate time series data while maintaining linear scalability and small memory footprints. TimeMachine exploits the unique properties of time series data to produce salient contextual cues at multi-scales and leverage an innovative integrated quadruple-Mamba architecture to unify the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09898","kind":"arxiv","version":2},"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/2403.09898/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":"2403.09898","created_at":"2026-07-05T08:58:22.745878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09898v2","created_at":"2026-07-05T08:58:22.745878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09898","created_at":"2026-07-05T08:58:22.745878+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEHGQ3SNIANX","created_at":"2026-07-05T08:58:22.745878+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEHGQ3SNIANXULE3","created_at":"2026-07-05T08:58:22.745878+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEHGQ3SN","created_at":"2026-07-05T08:58:22.745878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08896","citing_title":"FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01129","citing_title":"A Survey of Mamba","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23222","citing_title":"Dataset-Driven Channel Masks in Transformers for Multivariate Time Series","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEHGQ3SNIANXULE3HAVADS2G6B","json":"https://pith.science/pith/VEHGQ3SNIANXULE3HAVADS2G6B.json","graph_json":"https://pith.science/api/pith-number/VEHGQ3SNIANXULE3HAVADS2G6B/graph.json","events_json":"https://pith.science/api/pith-number/VEHGQ3SNIANXULE3HAVADS2G6B/events.json","paper":"https://pith.science/paper/VEHGQ3SN"},"agent_actions":{"view_html":"https://pith.science/pith/VEHGQ3SNIANXULE3HAVADS2G6B","download_json":"https://pith.science/pith/VEHGQ3SNIANXULE3HAVADS2G6B.json","view_paper":"https://pith.science/paper/VEHGQ3SN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09898&json=true","fetch_graph":"https://pith.science/api/pith-number/VEHGQ3SNIANXULE3HAVADS2G6B/graph.json","fetch_events":"https://pith.science/api/pith-number/VEHGQ3SNIANXULE3HAVADS2G6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEHGQ3SNIANXULE3HAVADS2G6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEHGQ3SNIANXULE3HAVADS2G6B/action/storage_attestation","attest_author":"https://pith.science/pith/VEHGQ3SNIANXULE3HAVADS2G6B/action/author_attestation","sign_citation":"https://pith.science/pith/VEHGQ3SNIANXULE3HAVADS2G6B/action/citation_signature","submit_replication":"https://pith.science/pith/VEHGQ3SNIANXULE3HAVADS2G6B/action/replication_record"}},"created_at":"2026-07-05T08:58:22.745878+00:00","updated_at":"2026-07-05T08:58:22.745878+00:00"}