{"id":"W4403764051","doi":"10.3390/data9110122","title":"Towards a Taxonomy Machine: A Training Set of 5.6 Million Arthropod Images","year":2024,"lang":"en","type":"article","venue":"Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Guelph","funders":"Ministry of Colleges and Universities; Canada First Research Excellence Fund; Ministero dello Sviluppo Economico; Ontario Ministry of Economic Development, Job Creation and Trade; Guanacaste Dry Forest Conservation Fund; Genome Canada; Ontario Genomics; Forest Conservation Fund; Polar Knowledge Canada","keywords":"Taxonomy (biology); Arthropod; Artificial intelligence; Set (abstract data type); Training set; Computer science; Natural language processing; Ecology; Biology; Programming language","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000163947,0.00006749753,0.00007881739,0.00001721131,0.0000334235,0.00003579914,0.000322776,0.00002387751,0.06093298],"category_scores_gemma":[0.00002546245,0.00005705849,0.00002413082,0.0001757456,0.0001210842,0.0002296097,0.0004250814,0.00005905686,0.0009168705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006461256,"about_ca_system_score_gemma":0.00000936678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003368736,"about_ca_topic_score_gemma":0.0001476953,"domain_scores_codex":[0.9993692,0.00001418367,0.0001097192,0.0002322657,0.000145897,0.0001287019],"domain_scores_gemma":[0.9995313,0.00001385115,0.00002083517,0.000389773,0.000002120147,0.00004207306],"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":[0.00001191363,0.00004817065,0.001810535,0.00006396097,0.00002890798,0.00003581526,0.0006381955,0.000003969784,0.006176194,0.0008649079,0.7482016,0.2421158],"study_design_scores_gemma":[0.00009071879,0.00001885993,0.005814762,0.00001768717,0.00001169442,0.00001088668,0.001016578,0.001070777,0.0008127402,0.00004373847,0.9910085,0.00008312127],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3168084,0.007988499,0.01325974,0.01100025,0.001937096,0.001353144,0.155206,0.0007052075,0.4917417],"genre_scores_gemma":[0.9923546,0.0003642346,0.0006607677,0.0001362887,0.00005346219,0.00001669758,0.006077916,0.00001064957,0.0003253644],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6755462,"threshold_uncertainty_score":0.999861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1436977197374064,"score_gpt":0.3139530033199601,"score_spread":0.1702552835825537,"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."}}