{"id":"W4387965192","doi":"10.1007/s10661-023-11945-9","title":"A simple framework for maximizing camera trap detections using experimental trials","year":2023,"lang":"en","type":"article","venue":"Environmental Monitoring and Assessment","topic":"Wildlife Ecology and Conservation","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Natural Resources and Forestry","funders":"Ontario Ministry of Natural Resources and Forestry; Ministry of Natural Resources","keywords":"Camera trap; Computer science; Camera resectioning; Computer vision; Artificial intelligence; Remote sensing; Environmental science; Ecology; Geography; Habitat","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005755146,0.0001701239,0.0002292107,0.00004705037,0.0006512654,0.00004750182,0.00008742332,0.0001050038,0.0002979341],"category_scores_gemma":[0.0000369601,0.0001730165,0.00009227897,0.0001200488,0.0001102878,0.0001956531,0.000138133,0.0001600283,0.000032892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000319577,"about_ca_system_score_gemma":0.000008326384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000547509,"about_ca_topic_score_gemma":0.000001130625,"domain_scores_codex":[0.9987136,0.0001085233,0.0003028018,0.0003628208,0.0001907055,0.0003215652],"domain_scores_gemma":[0.9992835,0.0003462773,0.0001207543,0.0001494111,8.701119e-7,0.00009921415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000338328,0.0001551341,0.8674981,0.000007171838,0.00005452554,0.000005396259,0.0004023251,0.00212354,0.1179938,0.0001421562,0.000168736,0.01141524],"study_design_scores_gemma":[0.0007321307,0.0002094065,0.9631238,0.00002554913,0.0000619161,0.000008202221,0.003199137,0.006256931,0.0214338,0.002030923,0.002594584,0.0003236498],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9933302,0.0000633387,0.005235579,0.0001757745,0.000569715,0.0004415859,0.00001956199,0.00008445146,0.00007978389],"genre_scores_gemma":[0.9777351,0.00005570135,0.02151915,0.00004725964,0.0002424097,0.0002641233,0.00001608686,0.00002381031,0.00009636836],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09656005,"threshold_uncertainty_score":0.705541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07726678811339992,"score_gpt":0.3644354360296977,"score_spread":0.2871686479162978,"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."}}