{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N7DZCOL2YU2BPWXCD2SYQ42OAR","short_pith_number":"pith:N7DZCOL2","schema_version":"1.0","canonical_sha256":"6fc791397ac53417dae21ea588734e045635326154e33883a5d610c6c77e53b8","source":{"kind":"arxiv","id":"2402.02592","version":2},"attestation_state":"computed","paper":{"title":"Unified Training of Universal Time Series Forecasting Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akshat Kumar, Caiming Xiong, Chenghao Liu, Doyen Sahoo, Gerald Woo, Silvio Savarese","submitted_at":"2024-02-04T20:00:45Z","abstract_excerpt":"Deep learning for time series forecasting has traditionally operated within a one-model-per-dataset framework, limiting its potential to leverage the game-changing impact of large pre-trained models. The concept of universal forecasting, emerging from pre-training on a vast collection of time series datasets, envisions a single Large Time Series Model capable of addressing diverse downstream forecasting tasks. However, constructing such a model poses unique challenges specific to time series data: i) cross-frequency learning, ii) accommodating an arbitrary number of variates for multivariate t"},"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":"2402.02592","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T20:00:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5072432225c8ba51124696a516bf76085e4f71ac70ed233c8cc7c90bfecda85e","abstract_canon_sha256":"2c30ecc2144e6519e8cfbea9c7d36ee80b918bc60d5ff488c4da2abe8b49b6a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:49.321016Z","signature_b64":"jYieXrQ3vTfaYL8WC9RAoWP/IFoUWQY1PnlqdJVBNPlgpNslar2M0SeHTDHP7chueTiJtWiOLKVBARNaYW0vCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fc791397ac53417dae21ea588734e045635326154e33883a5d610c6c77e53b8","last_reissued_at":"2026-07-05T08:21:49.320518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:49.320518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Training of Universal Time Series Forecasting Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akshat Kumar, Caiming Xiong, Chenghao Liu, Doyen Sahoo, Gerald Woo, Silvio Savarese","submitted_at":"2024-02-04T20:00:45Z","abstract_excerpt":"Deep learning for time series forecasting has traditionally operated within a one-model-per-dataset framework, limiting its potential to leverage the game-changing impact of large pre-trained models. The concept of universal forecasting, emerging from pre-training on a vast collection of time series datasets, envisions a single Large Time Series Model capable of addressing diverse downstream forecasting tasks. However, constructing such a model poses unique challenges specific to time series data: i) cross-frequency learning, ii) accommodating an arbitrary number of variates for multivariate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02592","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/2402.02592/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":"2402.02592","created_at":"2026-07-05T08:21:49.320580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02592v2","created_at":"2026-07-05T08:21:49.320580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02592","created_at":"2026-07-05T08:21:49.320580+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7DZCOL2YU2B","created_at":"2026-07-05T08:21:49.320580+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7DZCOL2YU2BPWXC","created_at":"2026-07-05T08:21:49.320580+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7DZCOL2","created_at":"2026-07-05T08:21:49.320580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24996","citing_title":"From Forecasting Leaderboards to Deployment Decisions: A Fail-Closed Certification Protocol","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01918","citing_title":"Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis","ref_index":103,"is_internal_anchor":false},{"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":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11482","citing_title":"Building Social World Models with Large Language Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10868","citing_title":"When Do Autoregressive Sequence Models Forecast Physical Wavefields? A Controlled Study on Synthetic Seismograms","ref_index":18,"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":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09954","citing_title":"Does Normalization Choice Matter for Causal Large Time-Series Models?","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00154","citing_title":"EVOTS: Evolutionary Transformer Search for Time Series Forecasting","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27527","citing_title":"Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction with NightLANP","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11130","citing_title":"HEPA: A Self-Supervised Horizon-Conditioned Event Predictive Architecture for Time Series","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24381","citing_title":"Assessing the Operational Viability of Foundation Models for Time Series Forecasting","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25141","citing_title":"LLM Agent Based Renewable Energy Forecasting Using Edge and IoT Data A Review of Solar Wind Weather and Grid Aware Decision Support","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2407.13278","citing_title":"Deep Time Series Models: A Comprehensive Survey and Benchmark","ref_index":201,"is_internal_anchor":false},{"citing_arxiv_id":"2502.00816","citing_title":"Sundial: A Family of Highly Capable Time Series Foundation Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2510.06063","citing_title":"TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15752","citing_title":"Forecasting megaelectron-volt electron flux in the Earth's outer radiation belt using supervised machine learning algorithms and a timeseries foundation model","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01101","citing_title":"TSVer: A Benchmark for Fact Verification Against Time-Series Evidence","ref_index":54,"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":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11130","citing_title":"HEPA: A Self-Supervised Horizon-Conditioned Event Predictive Architecture for Time Series","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2403.07815","citing_title":"Chronos: Learning the Language of Time Series","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11130","citing_title":"HEPA: A Self-Supervised Horizon-Conditioned Event Predictive Architecture for Time Series","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08857","citing_title":"RareCP: Regime-Aware Retrieval for Efficient Conformal Prediction","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10038","citing_title":"TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09032","citing_title":"A Quantum Inspired Variational Kernel and Explainable AI Framework for Cross Region Solar and Wind Energy Forecasting","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11529","citing_title":"TempusBench: An Evaluation Framework for Time-Series Forecasting","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7DZCOL2YU2BPWXCD2SYQ42OAR","json":"https://pith.science/pith/N7DZCOL2YU2BPWXCD2SYQ42OAR.json","graph_json":"https://pith.science/api/pith-number/N7DZCOL2YU2BPWXCD2SYQ42OAR/graph.json","events_json":"https://pith.science/api/pith-number/N7DZCOL2YU2BPWXCD2SYQ42OAR/events.json","paper":"https://pith.science/paper/N7DZCOL2"},"agent_actions":{"view_html":"https://pith.science/pith/N7DZCOL2YU2BPWXCD2SYQ42OAR","download_json":"https://pith.science/pith/N7DZCOL2YU2BPWXCD2SYQ42OAR.json","view_paper":"https://pith.science/paper/N7DZCOL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02592&json=true","fetch_graph":"https://pith.science/api/pith-number/N7DZCOL2YU2BPWXCD2SYQ42OAR/graph.json","fetch_events":"https://pith.science/api/pith-number/N7DZCOL2YU2BPWXCD2SYQ42OAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7DZCOL2YU2BPWXCD2SYQ42OAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7DZCOL2YU2BPWXCD2SYQ42OAR/action/storage_attestation","attest_author":"https://pith.science/pith/N7DZCOL2YU2BPWXCD2SYQ42OAR/action/author_attestation","sign_citation":"https://pith.science/pith/N7DZCOL2YU2BPWXCD2SYQ42OAR/action/citation_signature","submit_replication":"https://pith.science/pith/N7DZCOL2YU2BPWXCD2SYQ42OAR/action/replication_record"}},"created_at":"2026-07-05T08:21:49.320580+00:00","updated_at":"2026-07-05T08:21:49.320580+00:00"}