{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XGRNUMWNSXMZAROAJGM6OTFEVK","short_pith_number":"pith:XGRNUMWN","schema_version":"1.0","canonical_sha256":"b9a2da32cd95d99045c04999e74ca4aa9cd71bb0c6d6d5d117c21cbb472fe817","source":{"kind":"arxiv","id":"2409.16040","version":4},"attestation_state":"computed","paper":{"title":"Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dianqi Li, Ming Jin, Qingsong Wen, Shiyu Wang, Xiaoming Shi, Yuqi Nie, Zhou Ye","submitted_at":"2024-09-24T12:42:18Z","abstract_excerpt":"Deep learning for time series forecasting has seen significant advancements over the past decades. However, despite the success of large-scale pre-training in language and vision domains, pre-trained time series models remain limited in scale and operate at a high cost, hindering the development of larger capable forecasting models in real-world applications. In response, we introduce Time-MoE, a scalable and unified architecture designed to pre-train larger, more capable forecasting foundation models while reducing inference costs. By leveraging a sparse mixture-of-experts (MoE) design, Time-"},"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":"2409.16040","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-24T12:42:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b2d1a1c26a1cbe4d30c3eddc5c9940774095096611ab548cc68e704ddd9f7a7b","abstract_canon_sha256":"f622890e63ea140310699db4a5c6fac3059cc667172c73a9924bf807041efeba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:39.961000Z","signature_b64":"8zeSTwUEsWyROZGz5F58595Sf6aEwd2mbRhwieYBGSKEbKOqqMX358kd2EE2THA2JgZg+wTlzC4Z8XQxYwoMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9a2da32cd95d99045c04999e74ca4aa9cd71bb0c6d6d5d117c21cbb472fe817","last_reissued_at":"2026-07-05T10:20:39.960457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:39.960457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dianqi Li, Ming Jin, Qingsong Wen, Shiyu Wang, Xiaoming Shi, Yuqi Nie, Zhou Ye","submitted_at":"2024-09-24T12:42:18Z","abstract_excerpt":"Deep learning for time series forecasting has seen significant advancements over the past decades. However, despite the success of large-scale pre-training in language and vision domains, pre-trained time series models remain limited in scale and operate at a high cost, hindering the development of larger capable forecasting models in real-world applications. In response, we introduce Time-MoE, a scalable and unified architecture designed to pre-train larger, more capable forecasting foundation models while reducing inference costs. By leveraging a sparse mixture-of-experts (MoE) design, Time-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16040","kind":"arxiv","version":4},"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/2409.16040/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":"2409.16040","created_at":"2026-07-05T10:20:39.960524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.16040v4","created_at":"2026-07-05T10:20:39.960524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16040","created_at":"2026-07-05T10:20:39.960524+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGRNUMWNSXMZ","created_at":"2026-07-05T10:20:39.960524+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGRNUMWNSXMZAROA","created_at":"2026-07-05T10:20:39.960524+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGRNUMWN","created_at":"2026-07-05T10:20:39.960524+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01966","citing_title":"Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13024","citing_title":"CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11268","citing_title":"LakeFM: Toward a Foundation Model for Aquatic Ecosystems Using Irregular Multivariate Multi-depth Time Series Data","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09954","citing_title":"Does Normalization Choice Matter for Causal Large Time-Series Models?","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08630","citing_title":"Tyan-WP: A Wind Power Foundation Model for Ultra-Short-Term Probabilistic Forecasting","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00358","citing_title":"PRISM: Prioritized Channel Importance with Semi-supervised Domain Adaptation for Cross-Subject EEG Emotion Recognition","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24381","citing_title":"Assessing the Operational Viability of Foundation Models for Time Series Forecasting","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01289","citing_title":"Feature to Dynamics: Feature-space to Autoregression strategy for Zero-shot Time Series Forecasting","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15105","citing_title":"Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2508.12247","citing_title":"STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series Prediction","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21975","citing_title":"Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2508.12247","citing_title":"STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series Prediction","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17340","citing_title":"Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11512","citing_title":"From Time Series Analysis to Question Answering: A Survey in the LLM Era","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22403","citing_title":"MoveFM-R: Advancing Mobility Foundation Models via Language-driven Semantic Reasoning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25826","citing_title":"Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2512.20761","citing_title":"TS-Arena -- A Live Forecast Pre-Registration Platform","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04791","citing_title":"Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13711","citing_title":"MILM: Large Language Models for Multimodal Irregular Time Series with Informative Sampling","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10330","citing_title":"Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss Integration","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08199","citing_title":"Beyond Static Forecasting: Unleashing the Power of World Models for Mobile Traffic Extrapolation","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGRNUMWNSXMZAROAJGM6OTFEVK","json":"https://pith.science/pith/XGRNUMWNSXMZAROAJGM6OTFEVK.json","graph_json":"https://pith.science/api/pith-number/XGRNUMWNSXMZAROAJGM6OTFEVK/graph.json","events_json":"https://pith.science/api/pith-number/XGRNUMWNSXMZAROAJGM6OTFEVK/events.json","paper":"https://pith.science/paper/XGRNUMWN"},"agent_actions":{"view_html":"https://pith.science/pith/XGRNUMWNSXMZAROAJGM6OTFEVK","download_json":"https://pith.science/pith/XGRNUMWNSXMZAROAJGM6OTFEVK.json","view_paper":"https://pith.science/paper/XGRNUMWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.16040&json=true","fetch_graph":"https://pith.science/api/pith-number/XGRNUMWNSXMZAROAJGM6OTFEVK/graph.json","fetch_events":"https://pith.science/api/pith-number/XGRNUMWNSXMZAROAJGM6OTFEVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGRNUMWNSXMZAROAJGM6OTFEVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGRNUMWNSXMZAROAJGM6OTFEVK/action/storage_attestation","attest_author":"https://pith.science/pith/XGRNUMWNSXMZAROAJGM6OTFEVK/action/author_attestation","sign_citation":"https://pith.science/pith/XGRNUMWNSXMZAROAJGM6OTFEVK/action/citation_signature","submit_replication":"https://pith.science/pith/XGRNUMWNSXMZAROAJGM6OTFEVK/action/replication_record"}},"created_at":"2026-07-05T10:20:39.960524+00:00","updated_at":"2026-07-05T10:20:39.960524+00:00"}