{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T726ULALAK6QWYIEF5PIV6UDCY","short_pith_number":"pith:T726ULAL","schema_version":"1.0","canonical_sha256":"9ff5ea2c0b02bd0b61042f5e8afa8316023273bf9274d3ff0aaee651b7478ffc","source":{"kind":"arxiv","id":"2310.10688","version":4},"attestation_state":"computed","paper":{"title":"A decoder-only foundation model for time-series forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A pretrained decoder-only model achieves zero-shot time-series forecasting accuracy close to supervised state-of-the-art on public datasets.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhimanyu Das, Rajat Sen, Weihao Kong, Yichen Zhou","submitted_at":"2023-10-14T17:01:37Z","abstract_excerpt":"Motivated by recent advances in large language models for Natural Language Processing (NLP), we design a time-series foundation model for forecasting whose out-of-the-box zero-shot performance on a variety of public datasets comes close to the accuracy of state-of-the-art supervised forecasting models for each individual dataset. Our model is based on pretraining a patched-decoder style attention model on a large time-series corpus, and can work well across different forecasting history lengths, prediction lengths and temporal granularities."},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2310.10688","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-14T17:01:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"31a7eeb94075a0e05297d422c2bed9f02bf491c86a716ee0d88d6c0f99fe6f79","abstract_canon_sha256":"158e8eda001db7062a81be372093f942fbdacbbcd4f2612e0411ad77a415d4ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:47.022008Z","signature_b64":"lyq/tFLVfzTqeBOTttlKG2RuPqmCygASIucR4bvR+a3sdB+89GnImfh/aNeeCBWtkfz2CMO6jCkN9iHDow+DAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ff5ea2c0b02bd0b61042f5e8afa8316023273bf9274d3ff0aaee651b7478ffc","last_reissued_at":"2026-05-17T23:38:47.021386Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:47.021386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A decoder-only foundation model for time-series forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A pretrained decoder-only model achieves zero-shot time-series forecasting accuracy close to supervised state-of-the-art on public datasets.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhimanyu Das, Rajat Sen, Weihao Kong, Yichen Zhou","submitted_at":"2023-10-14T17:01:37Z","abstract_excerpt":"Motivated by recent advances in large language models for Natural Language Processing (NLP), we design a time-series foundation model for forecasting whose out-of-the-box zero-shot performance on a variety of public datasets comes close to the accuracy of state-of-the-art supervised forecasting models for each individual dataset. Our model is based on pretraining a patched-decoder style attention model on a large time-series corpus, and can work well across different forecasting history lengths, prediction lengths and temporal granularities."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our model ... whose out-of-the-box zero-shot performance on a variety of public datasets comes close to the accuracy of state-of-the-art supervised forecasting models for each individual dataset.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That pretraining on the chosen large time-series corpus produces representations that generalize to unseen datasets and varying temporal granularities without any fine-tuning or dataset-specific adaptation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A pretrained decoder-only patched transformer achieves near state-of-the-art zero-shot forecasting performance across diverse time series datasets and settings.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A pretrained decoder-only model achieves zero-shot time-series forecasting accuracy close to supervised state-of-the-art on public datasets.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"10432633a53889c67bddf3d7ba4be692d7d259a10dd2e0708d31c6f361e56127"},"source":{"id":"2310.10688","kind":"arxiv","version":4},"verdict":{"id":"a11669d4-0631-4026-827e-a3a9dde075c0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T18:02:54.453677Z","strongest_claim":"our model ... whose out-of-the-box zero-shot performance on a variety of public datasets comes close to the accuracy of state-of-the-art supervised forecasting models for each individual dataset.","one_line_summary":"A pretrained decoder-only patched transformer achieves near state-of-the-art zero-shot forecasting performance across diverse time series datasets and settings.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That pretraining on the chosen large time-series corpus produces representations that generalize to unseen datasets and varying temporal granularities without any fine-tuning or dataset-specific adaptation.","pith_extraction_headline":"A pretrained decoder-only model achieves zero-shot time-series forecasting accuracy close to supervised state-of-the-art on public datasets."},"references":{"count":23,"sample":[{"doi":"","year":null,"title":"On the benefits of maximum likelihood estimation for regression and forecasting","work_id":"a1639cb9-9c45-4bbb-9fc4-a097a401eeb7","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Conditional time series forecast- ing with convolutional neural networks","work_id":"7f4b6e11-19a1-4dc6-b780-879e5a12fe12","ref_index":2,"cited_arxiv_id":"1703.04691","is_internal_anchor":true},{"doi":"","year":null,"title":"Tsmixer: An all-mlp architecture for time series forecasting","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"[COO+23] Cristian Challu, Kin G. Olivares, Boris N. Oreshkin, Federico Garza, Max Mergenthaler, and Artur Dubrawski. NHITS: Neural Hierarchical Interpolation for Time Series forecasting. In The Associ","work_id":"c851a0e6-3482-457d-b72a-65e82a9a81bb","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Llm4ts: Two-stage fine-tuning for time-series forecasting with pre-trained llms","work_id":"b6995864-2702-40f5-8597-58a3119807ef","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":23,"snapshot_sha256":"eec9f8030303f29cee0c17c1753bb68be8846bc45c61685defb4c3fa6952f8ac","internal_anchors":7},"formal_canon":{"evidence_count":3,"snapshot_sha256":"a718f7ccf92f77ac4bbf7b962f3352106e146d48b5ee9484b04cc7d5ac4acebe"},"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":"2310.10688","created_at":"2026-05-17T23:38:47.021475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10688v4","created_at":"2026-05-17T23:38:47.021475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10688","created_at":"2026-05-17T23:38:47.021475+00:00"},{"alias_kind":"pith_short_12","alias_value":"T726ULALAK6Q","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"T726ULALAK6QWYIE","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"T726ULAL","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":26,"sample":[{"citing_arxiv_id":"2411.07207","citing_title":"General Geospatial Inference with a Population Dynamics Foundation Model","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22684","citing_title":"ChronoVAE-HOPE: Beyond Attention -- A Next-Generation VAE Foundation Model for Specialized Time Series Classification","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2510.06063","citing_title":"TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18657","citing_title":"KairosHope: A Next-Generation Time-Series Foundation Model for Specialized Classification via Dual-Memory Architecture","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19462","citing_title":"Quantifying the Pre-training Dividend: Generative versus Latent Self-Supervised Learning for Time Series Foundation Models","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20119","citing_title":"Toto 2.0: Time Series Forecasting Enters the Scaling Era","ref_index":14,"is_internal_anchor":true},{"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":23,"is_internal_anchor":true},{"citing_arxiv_id":"2603.04791","citing_title":"Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14069","citing_title":"SurF: A Generative Model for Multivariate Irregular Time Series Forecasting","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13711","citing_title":"MILM: Large Language Models for Multimodal Irregular Time Series with Informative Sampling","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14199","citing_title":"PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2403.07815","citing_title":"Chronos: Learning the Language of Time Series","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.28149","citing_title":"Explainable Load Forecasting with Covariate-Informed Time Series Foundation Models","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08857","citing_title":"RareCP: Regime-Aware Retrieval for Efficient Conformal Prediction","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08539","citing_title":"Continuity Laws for Sequential Models","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05064","citing_title":"Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10038","citing_title":"TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06473","citing_title":"MICA: Multivariate Infini Compressive Attention for Time Series Forecasting","ref_index":12,"is_internal_anchor":true},{"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":39,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22328","citing_title":"FETS Benchmark: Foundation Models Outperform Dataset-specific Machine Learning in Energy Time Series Forecasting","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18576","citing_title":"Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07675","citing_title":"FactoryBench: Evaluating Industrial Machine Understanding","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05064","citing_title":"Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06473","citing_title":"MICA: Multivariate Infini Compressive Attention for Time Series Forecasting","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14994","citing_title":"Degradation-aware Predictive Energy Management for Fuel Cell-Battery Ship Power System with Data-driven Load Forecasting","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T726ULALAK6QWYIEF5PIV6UDCY","json":"https://pith.science/pith/T726ULALAK6QWYIEF5PIV6UDCY.json","graph_json":"https://pith.science/api/pith-number/T726ULALAK6QWYIEF5PIV6UDCY/graph.json","events_json":"https://pith.science/api/pith-number/T726ULALAK6QWYIEF5PIV6UDCY/events.json","paper":"https://pith.science/paper/T726ULAL"},"agent_actions":{"view_html":"https://pith.science/pith/T726ULALAK6QWYIEF5PIV6UDCY","download_json":"https://pith.science/pith/T726ULALAK6QWYIEF5PIV6UDCY.json","view_paper":"https://pith.science/paper/T726ULAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10688&json=true","fetch_graph":"https://pith.science/api/pith-number/T726ULALAK6QWYIEF5PIV6UDCY/graph.json","fetch_events":"https://pith.science/api/pith-number/T726ULALAK6QWYIEF5PIV6UDCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T726ULALAK6QWYIEF5PIV6UDCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T726ULALAK6QWYIEF5PIV6UDCY/action/storage_attestation","attest_author":"https://pith.science/pith/T726ULALAK6QWYIEF5PIV6UDCY/action/author_attestation","sign_citation":"https://pith.science/pith/T726ULALAK6QWYIEF5PIV6UDCY/action/citation_signature","submit_replication":"https://pith.science/pith/T726ULALAK6QWYIEF5PIV6UDCY/action/replication_record"}},"created_at":"2026-05-17T23:38:47.021475+00:00","updated_at":"2026-05-17T23:38:47.021475+00:00"}