{"id":"W2949681560","doi":"10.48550/arxiv.1703.07309","title":"Phytoplankton Hotspot Prediction With an Unsupervised Spatial Community Model","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Woods Hole Oceanographic Institution; Natural Sciences and Engineering Research Council of Canada; National Oceanic and Atmospheric Administration; Cooperative Institute for the North Atlantic Region; Northeast Fisheries Science Center; National Aeronautics and Space Administration","keywords":"Computer science; Taxon; Hotspot (geology); Bayesian probability; Artificial intelligence; Geography; Cartography; Ecology; Geology; Geophysics; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001152174,0.0006273089,0.0009800568,0.001695351,0.0005304418,0.0006600576,0.001845176,0.001200979,0.0008563453],"category_scores_gemma":[0.002893007,0.0005499704,0.0009624106,0.001082571,0.0005824166,0.001403674,0.001028043,0.001076506,0.0003406844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009386896,"about_ca_system_score_gemma":0.0008520668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01958629,"about_ca_topic_score_gemma":0.02446747,"domain_scores_codex":[0.9995864,0.000107835,0.00002154845,0.0001724701,0.00005106239,0.0000605551],"domain_scores_gemma":[0.9982583,0.001025184,0.0002377335,0.0001343239,0.0002292234,0.0001152438],"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":[0.000290421,0.0002057999,0.02489653,0.0000778873,0.0001343479,0.0001458993,0.000166167,0.9211513,0.002220284,0.003016491,0.00263809,0.04505685],"study_design_scores_gemma":[0.000005988516,0.000005502572,0.0005662591,0.000001759865,0.000003423748,0.000007053149,0.000007586527,0.9982053,0.00008265694,0.001063462,0.00004845656,0.000002529958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5262684,0.0005634674,0.4679064,0.0008334055,0.00005397317,0.0001234859,0.001363719,0.001227443,0.001659605],"genre_scores_gemma":[0.9445753,0.0001260586,0.05211852,0.0001103812,0.00006588131,0.00009122297,0.001573619,0.00005434687,0.001284567],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01958629,"threshold_uncertainty_score":0.0389446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07441491258780109,"score_gpt":0.1950473394031339,"score_spread":0.1206324268153328,"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."}}