{"id":"W2992135859","doi":"10.1002/ece3.5767","title":"Design patterns for wildlife‐related camera trap image analysis","year":2019,"lang":"en","type":"article","venue":"Ecology and Evolution","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":125,"is_retracted":false,"has_abstract":true,"ca_institutions":"Freshwater Fisheries Society of BC; BC Research (Canada); University of British Columbia; Parks Canada; University of Calgary","funders":"","keywords":"Computer science; Workflow; Software; Software design pattern; Consistency (knowledge bases); Image (mathematics); Trap (plumbing); Software design; Camera trap; Image processing; Data mining; Artificial intelligence; Wildlife; Computer vision; Software development; Ecology; Database; Programming language; 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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000177244,0.00006827348,0.0001173692,0.00003648735,0.0001081144,0.000009505581,0.00005248459,0.00009470752,0.03052478],"category_scores_gemma":[0.00001324263,0.00006501971,0.00005504328,0.0001798991,0.00007462386,0.0001049588,0.00002827345,0.00004775499,0.0008482275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002168339,"about_ca_system_score_gemma":0.000003723578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000743265,"about_ca_topic_score_gemma":0.000288536,"domain_scores_codex":[0.9994112,0.00004442768,0.0001080775,0.0001994685,0.00005120469,0.0001856791],"domain_scores_gemma":[0.999763,0.00005009819,0.00004742513,0.00008969335,0.000006680352,0.00004317731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003450202,0.00005080094,0.9903517,0.000004970973,0.00007584714,6.982678e-7,0.0001252641,0.0002810477,0.003334216,0.0004967029,0.00511787,0.000126393],"study_design_scores_gemma":[0.0003925994,0.0001037382,0.9926623,7.170447e-7,0.000106448,0.000002604152,0.000280409,0.004959919,0.00006753406,0.0002566871,0.00108325,0.00008382636],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9867253,0.00001939312,0.0106381,0.0005464421,0.0001304807,0.0002469403,0.00003665405,0.00002742731,0.001629291],"genre_scores_gemma":[0.9987187,0.00002433584,0.0001292367,0.0002249167,0.000007067112,0.00002919459,0.00009700251,0.000003703074,0.0007658411],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02967655,"threshold_uncertainty_score":0.9999297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01314745838452769,"score_gpt":0.2299678187967118,"score_spread":0.2168203604121841,"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."}}