{"id":"W4410895585","doi":"10.22541/essoar.174860961.13866020/v1","title":"Probabilistic Data Assimilation for Ensemble Distribution Projections with Generative Machine Learning: A Lorenz '96 Proof-of-Concept","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Science Foundation","keywords":"Generative grammar; Probabilistic logic; Data assimilation; Ensemble learning; Generative model; Artificial intelligence; Mathematics; Computer science; Assimilation (phonology); Distribution (mathematics); Machine learning; Calculus (dental); Econometrics; Geography; Philosophy; Mathematical analysis; Linguistics; Meteorology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002846871,0.0009997422,0.0007599751,0.0004145739,0.0005320137,0.001201792,0.001236242,0.001020717,0.003696293],"category_scores_gemma":[0.006919024,0.0005703573,0.001137279,0.0006274772,0.001133641,0.001791763,0.003991019,0.002817371,0.0008376657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006996942,"about_ca_system_score_gemma":0.001619981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003959623,"about_ca_topic_score_gemma":0.002194122,"domain_scores_codex":[0.9991682,0.0003058087,0.00002675579,0.0001361991,0.0003011189,0.00006191208],"domain_scores_gemma":[0.9986013,0.0007030527,0.0001100489,0.0002402318,0.000267833,0.00007758407],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008854668,0.00007715647,0.001012563,0.0001096695,0.00009044073,0.0001611479,0.000101495,0.772805,0.003651019,0.1609104,0.00265893,0.05833354],"study_design_scores_gemma":[0.000009285546,0.00001294095,0.00009525071,0.00001019294,0.000003929134,0.00002848529,0.000005594501,0.9698517,0.0008047989,0.02797098,0.00119768,0.000009149637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004370146,0.00008172799,0.9927019,0.0003378968,0.00004811272,0.00004303905,0.00007909754,0.0003140882,0.002023984],"genre_scores_gemma":[0.4493454,0.0005564039,0.5433097,0.0003661513,0.0002081681,0.0003265203,0.0006208245,0.0004449793,0.00482184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003959623,"threshold_uncertainty_score":0.01505584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08687768781836243,"score_gpt":0.2909399928899937,"score_spread":0.2040623050716313,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}