{"paper":{"title":"Toward World Modeling of Physiological Signals with Chaos-Theoretic Balancing and Latent Dynamics","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"NormWear-2 models physiological signals and interventions as joint latent dynamics for multi-scale forecasting.","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Andrew Campbell, Lanshuang Zhang, Md Mofijul Islam, Peter Kotanko, Rakesh Malhotra, Siwei Zhao, Subhasis Dasgupta, Tauhidur Rahman, Xi Chen, Yuliang Chen, Yunfei Luo","submitted_at":"2026-05-14T23:06:15Z","abstract_excerpt":"Physiological time series signals reflect complex, multi-scale dynamical processes of the human body. Existing modeling studies focus on static tasks such as classification, event forecasting, or short-horizon next step prediction, while long-horizon signal-level forecasting and predictive nature of physiological signals remain underexplored. We introduce NormWear-2, a world model that encodes both multivariate physiological signals and clinical intervention variables into a shared latent space and models their joint temporal evolution as a dynamical system. Our approach combines inference fro"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"NormWear-2 achieves the best overall forecasting performance across time, frequency, and latent representation domains, with significant improvements over state-of-the-art time series foundation models, while maintaining competitive downstream representation quality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That chaos-theoretic balancing of dynamical regime diversity during pretraining produces more robust latent representations that generalize across heterogeneous temporal resolutions, intervention regimes, and real-world datasets from daily life to clinical settings.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"NormWear-2 encodes physiological signals and interventions into a shared latent space, models their joint evolution as a dynamical system, and uses chaos-theoretic balancing during pretraining to achieve superior multi-scale forecasting on diverse real-world datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"NormWear-2 models physiological signals and interventions as joint latent dynamics for multi-scale forecasting.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"26f8cdc116deadbf6b1730a9b2c2ff6c05916d415f5f52f5fa65fd31efd90577"},"source":{"id":"2605.15465","kind":"arxiv","version":1},"verdict":{"id":"d4336ec0-a25b-4fc5-a9be-8a8461b5a68a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T15:01:01.320146Z","strongest_claim":"NormWear-2 achieves the best overall forecasting performance across time, frequency, and latent representation domains, with significant improvements over state-of-the-art time series foundation models, while maintaining competitive downstream representation quality.","one_line_summary":"NormWear-2 encodes physiological signals and interventions into a shared latent space, models their joint evolution as a dynamical system, and uses chaos-theoretic balancing during pretraining to achieve superior multi-scale forecasting on diverse real-world datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That chaos-theoretic balancing of dynamical regime diversity during pretraining produces more robust latent representations that generalize across heterogeneous temporal resolutions, intervention regimes, and real-world datasets from daily life to clinical settings.","pith_extraction_headline":"NormWear-2 models physiological signals and interventions as joint latent dynamics for multi-scale forecasting."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15465/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T15:31:17.721929Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T15:22:28.645885Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:10:43.967112Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.093872Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.414352Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.667460Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"08fb1e4b7a927fa225f1b2dfa824a1b8ba0d8c2844b4a8da2541c6fd195b1c33"},"references":{"count":18,"sample":[{"doi":"","year":null,"title":"Chronos-2: From Univariate to Universal Forecasting","work_id":"c00ac266-1edf-4787-a2b3-23692973b1b8","ref_index":1,"cited_arxiv_id":"2510.15821","is_internal_anchor":true},{"doi":"","year":null,"title":"Tirex: Zero-shot forecasting across long and short horizons with enhanced in-context learning","work_id":"f4cb314e-2bc7-4049-b5cd-2f3fc97ab790","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"T., Jiang, J., Jayaraman, P., Parekh, A., Nadkarni, G","work_id":"6e710015-bbe8-4422-afb4-b9b30ce242be","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Masked Autoencoders Are Scalable Vision Learners","work_id":"0747476e-5bd0-4596-908f-391611d9364e","ref_index":4,"cited_arxiv_id":"2111.06377","is_internal_anchor":true},{"doi":"","year":null,"title":"arXiv preprint arXiv:2312.05230 , year=","work_id":"0013b495-df2d-40d8-a3b8-4fdfadd5a424","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":18,"snapshot_sha256":"cccd1f07f24b6aba7898609d4ca552812c803641108b9e3e5884307de6b6cc3b","internal_anchors":3},"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"}