{"id":"W2059705044","doi":"10.1016/j.jglr.2015.01.001","title":"Challenges in tracking harmful algal blooms: A synthesis of evidence from Lake Erie","year":2015,"lang":"en","type":"article","venue":"Journal of Great Lakes Research","topic":"Aquatic Ecosystems and Phytoplankton Dynamics","field":"Environmental Science","cited_by":193,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Leverage (statistics); Harm; Ambiguity; Algal bloom; Computer science; Environmental resource management; Environmental planning; Geography; Environmental science; Ecology; Political science; Biology; Artificial intelligence; Phytoplankton","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00445411,0.0001091547,0.0003730483,0.0001572475,0.00004257892,0.00003560161,0.000532391,0.00009298134,0.0007104108],"category_scores_gemma":[0.00198096,0.0000762772,0.00008172141,0.000300199,0.0001935896,0.0004413441,0.0001485379,0.00043508,0.00005683857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001989019,"about_ca_system_score_gemma":0.00009820946,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005189046,"about_ca_topic_score_gemma":0.03926142,"domain_scores_codex":[0.9970542,0.0005019746,0.0005726665,0.0001919895,0.00136389,0.0003152537],"domain_scores_gemma":[0.9978105,0.001325493,0.0002535736,0.0002617587,0.0001312585,0.0002174072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005186175,0.0002984084,0.8586391,0.0001158054,0.00008205131,0.0005428362,0.008326462,0.001561073,0.003207903,0.00006797683,0.001909644,0.1247301],"study_design_scores_gemma":[0.002579646,0.002235714,0.8956078,0.007041304,0.00009925897,0.0004839782,0.01545885,0.02079791,0.009562524,0.004895343,0.04047453,0.0007632106],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928768,0.002099841,0.00005446687,0.0008625695,0.000100657,0.0001217812,0.00002872363,0.000003385444,0.003851821],"genre_scores_gemma":[0.9979149,0.00131294,0.0005363294,0.000004993582,0.0001179156,0.000005666093,6.622886e-7,0.00001236351,0.00009423009],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1239669,"threshold_uncertainty_score":0.9782696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3057761017116767,"score_gpt":0.3771513718033057,"score_spread":0.07137527009162903,"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."}}