{"id":"W4405250503","doi":"10.2139/ssrn.5049599","title":"Deep Learning Method for Collembola Identification Using Single Species and Community Combinations Images","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Collembola Taxonomy and Ecology Studies","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Identification (biology); Artificial intelligence; Deep learning; Computer science; Pattern recognition (psychology); Geography; Ecology; Biology","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003436578,0.0002174987,0.0003437779,0.00005632154,0.002689048,0.0003700606,0.0002788291,0.0001958714,0.00001764538],"category_scores_gemma":[0.0003260066,0.0001103121,0.0001841204,0.0001809928,0.0001005401,0.0000788126,0.0005846675,0.004187503,0.000002592926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006371124,"about_ca_system_score_gemma":0.000157792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000278019,"about_ca_topic_score_gemma":0.01211653,"domain_scores_codex":[0.997722,0.0005932324,0.0003651782,0.0002671178,0.0001138448,0.000938663],"domain_scores_gemma":[0.9984936,0.0008958868,0.0003067635,0.00005742156,0.0001974797,0.00004891103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003562337,0.002401095,0.01077068,0.0006725887,0.004880878,0.000009297592,0.005366737,0.003742086,0.1972654,0.1175023,0.001415416,0.6556172],"study_design_scores_gemma":[0.0004984917,0.001087068,0.02348079,0.0001375551,0.0006495556,0.000262175,0.04819765,0.007756547,0.000626842,0.9080417,0.008574762,0.0006869307],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9754394,0.009431015,0.009296999,0.003714493,0.0006298546,0.0006552943,0.00005037198,0.00008489985,0.000697697],"genre_scores_gemma":[0.9940658,0.002351185,0.000966537,0.00002432923,0.0003241261,0.00005408801,0.00005991994,0.000003136086,0.002150943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7905393,"threshold_uncertainty_score":0.9986093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04476812056551541,"score_gpt":0.2836306295720595,"score_spread":0.2388625090065441,"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."}}