{"id":"W4400720994","doi":"10.1101/2024.07.15.600863","title":"Towards a Taxonomy Machine – A Training Set of 5.6 Million Arthropod Images","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","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":"","keywords":"Taxonomy (biology); Arthropod; Training set; Computer science; Set (abstract data type); Artificial intelligence; Natural language processing; Ecology; Biology; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002319811,0.001247372,0.001051254,0.002628129,0.0009877232,0.001791751,0.001962625,0.002258806,0.004254114],"category_scores_gemma":[0.006160879,0.0008406538,0.001457073,0.001961424,0.0006511115,0.002067253,0.001616207,0.001579965,0.00434575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001033135,"about_ca_system_score_gemma":0.001051261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006479466,"about_ca_topic_score_gemma":0.006237773,"domain_scores_codex":[0.9987411,0.0002463344,0.00009022924,0.0004561639,0.0003316091,0.0001345504],"domain_scores_gemma":[0.9980452,0.0004382775,0.0001169696,0.0006293168,0.0006347207,0.0001355235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000918507,0.001305036,0.04172698,0.001107886,0.0005912011,0.0005571757,0.0003326239,0.06447502,0.04337895,0.003192594,0.1522665,0.6901475],"study_design_scores_gemma":[0.0002076886,0.0007377314,0.07954983,0.0004239203,0.0002855541,0.001042248,0.0007540617,0.7972608,0.03831715,0.0113688,0.06994224,0.0001099131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.6848927,0.007534286,0.1734163,0.004069005,0.001429755,0.0009005971,0.0952189,0.01980678,0.01273167],"genre_scores_gemma":[0.431314,0.001216465,0.3845383,0.0007383269,0.0003396396,0.0005377932,0.1752746,0.0004513728,0.005589603],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.006479466,"threshold_uncertainty_score":0.01423138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03775960855035671,"score_gpt":0.2393306735394695,"score_spread":0.2015710649891128,"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."}}