{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QPXDRLKKPEWLK6AJKDOFYDWHS4","short_pith_number":"pith:QPXDRLKK","schema_version":"1.0","canonical_sha256":"83ee38ad4a792cb5780950dc5c0ec797139724552a0557e279747ed440b77eea","source":{"kind":"arxiv","id":"2510.15821","version":1},"attestation_state":"computed","paper":{"title":"Chronos-2: From Univariate to Universal Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Chronos-2 is a pretrained model that performs zero-shot forecasting on univariate, multivariate, and covariate-informed tasks via group attention for in-context learning.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdul Fatir Ansari, Andreas Auer, Boran Han, Danielle C. Maddix, George Karypis, Hao Wang, Huibin Shen, Huzefa Rangwala, Jaris K\\\"uken, Junming Yin, Lorenzo Stella, Michael Bohlke-Schneider, Mononito Goswami, Nick Erickson, Oleksandr Shchur, Pablo Guerron, Pedro Mercado, Prateek Mutalik Desai, Shubham Kapoor, Syama Sundar Rangapuram, Tony Hu, Xiyuan Zhang, Yuyang Wang","submitted_at":"2025-10-17T17:00:53Z","abstract_excerpt":"Pretrained time series models have enabled inference-only forecasting systems that produce accurate predictions without task-specific training. However, existing approaches largely focus on univariate forecasting, limiting their applicability in real-world scenarios where multivariate data and covariates play a crucial role. We present Chronos-2, a pretrained model capable of handling univariate, multivariate, and covariate-informed forecasting tasks in a zero-shot manner. Chronos-2 employs a group attention mechanism that facilitates in-context learning (ICL) through efficient information sha"},"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":true},"canonical_record":{"source":{"id":"2510.15821","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-17T17:00:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"28ca181e7696ebac4a0c600f8e9e2e755a69e19d619f88ce76a950491e57ee7b","abstract_canon_sha256":"3b420ee178cd8597525b773210382240a681b46bf9b6cb94e0d80d91e8f47ab3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:05.143883Z","signature_b64":"pQVX0DEAlecllo63utcFEJk7wZD5E6KuRXzP38zNXoiMfSjINHwDwaVJn5xZoxuB1BuzLiKx2pYY51XPyMbiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83ee38ad4a792cb5780950dc5c0ec797139724552a0557e279747ed440b77eea","last_reissued_at":"2026-05-17T23:39:05.143189Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:05.143189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chronos-2: From Univariate to Universal Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Chronos-2 is a pretrained model that performs zero-shot forecasting on univariate, multivariate, and covariate-informed tasks via group attention for in-context learning.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdul Fatir Ansari, Andreas Auer, Boran Han, Danielle C. Maddix, George Karypis, Hao Wang, Huibin Shen, Huzefa Rangwala, Jaris K\\\"uken, Junming Yin, Lorenzo Stella, Michael Bohlke-Schneider, Mononito Goswami, Nick Erickson, Oleksandr Shchur, Pablo Guerron, Pedro Mercado, Prateek Mutalik Desai, Shubham Kapoor, Syama Sundar Rangapuram, Tony Hu, Xiyuan Zhang, Yuyang Wang","submitted_at":"2025-10-17T17:00:53Z","abstract_excerpt":"Pretrained time series models have enabled inference-only forecasting systems that produce accurate predictions without task-specific training. However, existing approaches largely focus on univariate forecasting, limiting their applicability in real-world scenarios where multivariate data and covariates play a crucial role. We present Chronos-2, a pretrained model capable of handling univariate, multivariate, and covariate-informed forecasting tasks in a zero-shot manner. Chronos-2 employs a group attention mechanism that facilitates in-context learning (ICL) through efficient information sha"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Chronos-2 delivers state-of-the-art performance across three comprehensive benchmarks: fev-bench, GIFT-Eval, and Chronos Benchmark II. On fev-bench, which emphasizes multivariate and covariate-informed forecasting, Chronos-2's universal ICL capabilities lead to substantial improvements over existing models. On tasks involving covariates, it consistently outperforms baselines by a wide margin.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That training exclusively on synthetic datasets that impose diverse multivariate structures on univariate series will produce a model whose in-context learning generalizes to real-world multivariate and covariate distributions without domain-specific fine-tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Chronos-2 adds group attention to a pretrained time series model so it can do zero-shot forecasting on univariate, multivariate, and covariate tasks by learning from synthetic data that imposes multivariate structure on univariate series.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Chronos-2 is a pretrained model that performs zero-shot forecasting on univariate, multivariate, and covariate-informed tasks via group attention for in-context learning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cfeb3e3e3f87fbc782e3bd6e00f12fb47fae3f0e95f8bdb5e36acf269eb258b1"},"source":{"id":"2510.15821","kind":"arxiv","version":1},"verdict":{"id":"1170fea0-5829-416e-8693-adc371965820","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:16:12.885791Z","strongest_claim":"Chronos-2 delivers state-of-the-art performance across three comprehensive benchmarks: fev-bench, GIFT-Eval, and Chronos Benchmark II. On fev-bench, which emphasizes multivariate and covariate-informed forecasting, Chronos-2's universal ICL capabilities lead to substantial improvements over existing models. On tasks involving covariates, it consistently outperforms baselines by a wide margin.","one_line_summary":"Chronos-2 adds group attention to a pretrained time series model so it can do zero-shot forecasting on univariate, multivariate, and covariate tasks by learning from synthetic data that imposes multivariate structure on univariate series.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That training exclusively on synthetic datasets that impose diverse multivariate structures on univariate series will produce a model whose in-context learning generalizes to real-world multivariate and covariate distributions without domain-specific fine-tuning.","pith_extraction_headline":"Chronos-2 is a pretrained model that performs zero-shot forecasting on univariate, multivariate, and covariate-informed tasks via group attention for in-context learning."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fdac3f6c2883ac05eb3b9f96a5ad70b7807745caa87a0287e60831ee245faa2a"},"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":"2510.15821","created_at":"2026-05-17T23:39:05.143296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.15821v1","created_at":"2026-05-17T23:39:05.143296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.15821","created_at":"2026-05-17T23:39:05.143296+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPXDRLKKPEWL","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPXDRLKKPEWLK6AJ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPXDRLKK","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":37,"internal_anchor_count":37,"sample":[{"citing_arxiv_id":"2605.20268","citing_title":"Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21395","citing_title":"Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6G","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15690","citing_title":"FRWKV+: Adaptive Periodic-Position Branch Interaction for Frequency-Space Linear Time Series Forecasting","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15549","citing_title":"CTF4Nuclear: Common Task Framework for Nuclear Fission and Fusion Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17045","citing_title":"Empirical evaluation of Time Series Foundation Models for Day-ahead and Imbalance Electricity Price Forecasting in Belgium","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20119","citing_title":"Toto 2.0: Time Series Forecasting Enters the Scaling Era","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15465","citing_title":"Toward World Modeling of Physiological Signals with Chaos-Theoretic Balancing and Latent Dynamics","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2512.20761","citing_title":"TS-Arena -- A Live Forecast Pre-Registration Platform","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2602.17683","citing_title":"Probabilistic NDVI Forecasting from Sparse Satellite Time Series and Weather Covariates","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08318","citing_title":"Is Flow Matching Just Trajectory Replay for Sequential Data?","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2602.12120","citing_title":"Forecasting Commencing Enrolments Under Data Sparsity: A Zero-Shot Time Series Foundation Models Framework for Higher Education Planning","ref_index":64,"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":3,"is_internal_anchor":true},{"citing_arxiv_id":"2603.22586","citing_title":"A Foundation Model for Instruction-Conditioned In-Context Time Series Tasks","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13986","citing_title":"TabPFN-3: Technical Report","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2603.25777","citing_title":"Challenges and opportunities for AI to help deliver fusion energy","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2603.22586","citing_title":"A Foundation Model for Instruction-Conditioned In-Context Time Series Tasks","ref_index":3,"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":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12200","citing_title":"Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11598","citing_title":"EpiCastBench: Datasets and Benchmarks for Multivariate Epidemic Forecasting","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05064","citing_title":"Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10822","citing_title":"Benchmarking Sensor-Fault Robustness in Forecasting","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":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06361","citing_title":"Preliminary Insights in Chronos Frequency Data Understanding and Reconstruction","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11529","citing_title":"TempusBench: An Evaluation Framework for Time-Series Forecasting","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10544","citing_title":"WaveMoE: A Wavelet-Enhanced Mixture-of-Experts Foundation Model for Time Series Forecasting","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPXDRLKKPEWLK6AJKDOFYDWHS4","json":"https://pith.science/pith/QPXDRLKKPEWLK6AJKDOFYDWHS4.json","graph_json":"https://pith.science/api/pith-number/QPXDRLKKPEWLK6AJKDOFYDWHS4/graph.json","events_json":"https://pith.science/api/pith-number/QPXDRLKKPEWLK6AJKDOFYDWHS4/events.json","paper":"https://pith.science/paper/QPXDRLKK"},"agent_actions":{"view_html":"https://pith.science/pith/QPXDRLKKPEWLK6AJKDOFYDWHS4","download_json":"https://pith.science/pith/QPXDRLKKPEWLK6AJKDOFYDWHS4.json","view_paper":"https://pith.science/paper/QPXDRLKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.15821&json=true","fetch_graph":"https://pith.science/api/pith-number/QPXDRLKKPEWLK6AJKDOFYDWHS4/graph.json","fetch_events":"https://pith.science/api/pith-number/QPXDRLKKPEWLK6AJKDOFYDWHS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPXDRLKKPEWLK6AJKDOFYDWHS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPXDRLKKPEWLK6AJKDOFYDWHS4/action/storage_attestation","attest_author":"https://pith.science/pith/QPXDRLKKPEWLK6AJKDOFYDWHS4/action/author_attestation","sign_citation":"https://pith.science/pith/QPXDRLKKPEWLK6AJKDOFYDWHS4/action/citation_signature","submit_replication":"https://pith.science/pith/QPXDRLKKPEWLK6AJKDOFYDWHS4/action/replication_record"}},"created_at":"2026-05-17T23:39:05.143296+00:00","updated_at":"2026-05-17T23:39:05.143296+00:00"}