{"id":"W3163471686","doi":"10.1177/19400829211014740","title":"The Smart Forest Conundrum: Contextualizing Pitfalls of Sensors and AI in Conservation Science for Tropical Forests","year":2021,"lang":"en","type":"article","venue":"Tropical Conservation Science","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Operationalization; Work (physics); Big data; Citizen science; Field (mathematics); Tropical forest; Biodiversity; Environmental resource management; Biodiversity conservation; Ecosystem services; Business; Computer science; Agroforestry; Ecology; Ecosystem; Environmental science; Engineering","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0006783648,0.0001194313,0.0001809087,0.00006190488,0.0006492496,0.0002049211,0.0003755345,0.00005215657,0.0002535904],"category_scores_gemma":[0.002502813,0.00009492913,0.00004137073,0.001380438,0.004861569,0.0005895825,0.0002424786,0.0001107451,0.00001680136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003384759,"about_ca_system_score_gemma":0.0002417922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000254598,"about_ca_topic_score_gemma":0.008663667,"domain_scores_codex":[0.9978847,0.00006216239,0.0004401217,0.0004721304,0.0006932474,0.0004476459],"domain_scores_gemma":[0.9986159,0.0005358302,0.000143543,0.0002841286,0.0002723174,0.0001482524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004327061,0.00003749997,0.868721,0.000008848682,0.000001287486,0.000001631673,0.000131417,0.00001033991,0.03241067,0.09766708,0.0004915197,0.0004754494],"study_design_scores_gemma":[0.0006581819,0.00006661232,0.9737458,0.00001666463,0.000004781562,0.000009143161,0.0008646939,0.007258745,0.007731897,0.001597153,0.007930729,0.0001156174],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9851586,0.0000370569,0.00136049,0.01217159,0.0001378877,0.0003274991,0.00001404658,0.00001780505,0.0007749812],"genre_scores_gemma":[0.9974565,0.00003252098,0.0003474206,0.001973957,0.0000101866,0.00003457383,0.000005973438,0.000005035692,0.0001338653],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1050248,"threshold_uncertainty_score":0.9978466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04456157142622454,"score_gpt":0.3050369772237677,"score_spread":0.2604754057975431,"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."}}