{"id":"W4411580073","doi":"10.1016/j.engappai.2025.111442","title":"A decomposition–integration interval prediction strategy for iron ore shipping freight rates with reinforcement learning","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; Key Technologies Research and Development Program; National Natural Science Foundation of China","keywords":"Computer science; Reinforcement learning; Interval (graph theory); Decomposition; Iron ore; Artificial intelligence; Reinforcement; Operations research; Composite material; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001609314,0.0001590964,0.0001504686,0.0002095599,0.0001306695,0.00004890524,0.0001384187,0.0000720199,0.00001169947],"category_scores_gemma":[0.00003209644,0.0001613737,0.00005090306,0.0004109096,0.00002851219,0.0001384042,0.00001422887,0.0002032486,0.000003247723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007403688,"about_ca_system_score_gemma":0.00002075239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001486163,"about_ca_topic_score_gemma":0.00002137556,"domain_scores_codex":[0.9991175,0.000008370902,0.0004205718,0.0001770317,0.00009067257,0.0001858545],"domain_scores_gemma":[0.9994897,0.0001402311,0.0000562181,0.0001608882,0.0001151316,0.00003788164],"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":[0.00001546424,0.00001459908,0.00003594477,0.0001386311,0.00003134086,1.020184e-7,0.0001761952,0.9138367,0.01780407,0.03441795,0.00001431271,0.03351468],"study_design_scores_gemma":[0.00002727403,0.00007452795,0.00004757378,0.0002418341,0.00002368127,0.000001147194,0.0002466491,0.7955486,0.2025393,0.0005626107,0.0005728098,0.0001140613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02449356,0.0001446381,0.9737056,0.00002135229,0.0001148221,0.0003807184,0.000007864854,0.0002931509,0.0008382858],"genre_scores_gemma":[0.9856826,0.000027618,0.01356198,0.000003475536,0.00008525974,0.0004480818,0.0001013397,0.00002325322,0.00006636967],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9611891,"threshold_uncertainty_score":0.6580627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0174399316271588,"score_gpt":0.26740276989058,"score_spread":0.2499628382634212,"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."}}