{"id":"W4377293016","doi":"10.1111/ele.14239","title":"Getting the bugs out of <scp>AI</scp> : Advancing ecological research on arthropods through computer vision","year":2023,"lang":"en","type":"review","venue":"Ecology Letters","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Citizen science; Deep learning; Artificial intelligence; Computer science; Entomology; Data science; Ecology; Scale (ratio); Field (mathematics); Machine learning; Biology; Cartography; Geography","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":[0.001684826,0.0003311644,0.0008841477,0.00009075153,0.0004946967,0.00004710853,0.0007870408,0.000398082,0.005199918],"category_scores_gemma":[0.000362968,0.000215845,0.0003609918,0.0005673468,0.0011908,0.0000911645,0.00106531,0.001217246,0.008859016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001301343,"about_ca_system_score_gemma":0.00002925909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003685513,"about_ca_topic_score_gemma":0.0004272892,"domain_scores_codex":[0.9962926,0.0009554148,0.0006075331,0.0006899304,0.0005447895,0.000909743],"domain_scores_gemma":[0.9961491,0.002913949,0.0003254549,0.0005096205,0.00002015389,0.0000816882],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004174032,0.0002891361,0.0003572744,0.00104283,0.0001334597,0.0001762063,0.0004905884,0.0001223986,0.00006754773,0.0005786571,0.9184664,0.07827128],"study_design_scores_gemma":[0.0001279475,0.0003014248,0.004959896,0.0004564045,0.00005649721,0.00001195095,0.0003151321,0.00002300154,0.000004314274,0.00005510996,0.9935848,0.000103535],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.1358577,0.6486982,0.0009568745,0.09950849,0.02282801,0.01591027,0.0009918115,0.001597836,0.07365081],"genre_scores_gemma":[0.0003255247,0.9875876,0.0001651882,0.01040078,0.0004494133,0.0002066696,0.0001944876,0.0000753912,0.0005949566],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.3388894,"threshold_uncertainty_score":0.9957095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1351354625513679,"score_gpt":0.4155005450337214,"score_spread":0.2803650824823535,"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."}}