{"id":"W3092008126","doi":"10.1016/j.patter.2020.100109","title":"Artificial Intelligence Meets Citizen Science to Supercharge Ecological Monitoring","year":2020,"lang":"en","type":"review","venue":"Patterns","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":105,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Australian Research Council","keywords":"Citizen science; Process (computing); Supercharge; Resource (disambiguation); Identification (biology); Computer science; Ecology; Data science; Business; Knowledge management; Environmental resource management; Environmental science","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003307864,0.0003329919,0.0006555826,0.00007146884,0.0002402664,0.0001557623,0.001124019,0.0001411486,0.06034986],"category_scores_gemma":[0.0001905765,0.0002760591,0.0002100079,0.0008670609,0.0002384788,0.000116327,0.00112506,0.0003022874,0.02278056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001490367,"about_ca_system_score_gemma":0.00004133708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005626244,"about_ca_topic_score_gemma":0.0000393305,"domain_scores_codex":[0.99744,0.00006275223,0.0004560636,0.0008206585,0.0006044287,0.0006160712],"domain_scores_gemma":[0.9990262,0.00007218034,0.00009116236,0.0003346292,0.00001297095,0.0004628928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001482066,0.00005941515,0.0006072444,0.0002960629,0.000006329177,0.00004353443,0.0001516586,7.158309e-7,0.00005005196,0.0003121353,0.0003378313,0.9981335],"study_design_scores_gemma":[0.000008305749,0.00006138573,0.001354399,0.0004789686,0.00004584288,0.00001448439,0.0002383506,0.000004603634,0.0001907513,0.00002796001,0.9971886,0.0003863561],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01108092,0.9484904,0.001481468,0.002413214,0.00484293,0.003672117,0.00206942,0.000646523,0.02530302],"genre_scores_gemma":[0.01042452,0.988739,0.00007061791,0.0001775634,0.0002864125,0.0001639647,0.00004834251,0.00002833141,0.00006126708],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9977472,"threshold_uncertainty_score":0.9999692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1853064585088444,"score_gpt":0.3752881186204372,"score_spread":0.1899816601115928,"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."}}