{"id":"W6930188873","doi":"10.5278/a289ba89-0ffc-4d30-8eb2-8da54dc80e7a","title":"Bioscan-5M: A Multimodal Dataset for Insect Biodiversity","year":2024,"lang":"en","type":"dataset","venue":"Aalborg University Library","topic":"Phytochemistry and Biological Activities","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Simon Fraser University; Vector Institute; University of Waterloo","funders":"","keywords":"Barcode; Cluster analysis; Benchmark (surveying); DNA barcoding; Feature (linguistics); Embedding; Pattern recognition (psychology); Feature extraction; Feature vector","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":[],"category_scores_codex":[0.00005482283,0.0003545721,0.000354853,0.00003537635,0.0003555056,0.0001218408,0.001032744,0.0005476808,0.001198415],"category_scores_gemma":[0.00002295747,0.0001609215,0.0002706635,0.0003716687,0.0002022539,0.0005153668,0.0008779614,0.000397266,0.0006220731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003759598,"about_ca_system_score_gemma":0.00004627728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004476198,"about_ca_topic_score_gemma":0.0002623482,"domain_scores_codex":[0.9985678,0.0000740157,0.0001319447,0.0007039682,0.0001451138,0.0003772066],"domain_scores_gemma":[0.999176,0.0003695125,0.0001072409,0.0001506056,0.00001839904,0.000178262],"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":[0.0002196352,0.0001355709,0.000130838,0.0001102784,0.00007586633,0.00008807151,0.000003558241,7.409525e-8,0.001969423,0.000003924494,0.9965914,0.0006713962],"study_design_scores_gemma":[0.0001682695,0.0002555784,0.000517251,0.00005357985,0.0001138873,0.000004688885,0.0001243143,0.000002151091,0.001461059,0.00009769564,0.9967583,0.0004431927],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0232858,0.0001135214,1.225919e-7,0.001529375,0.000233986,0.0003286138,0.9742175,0.0001418103,0.0001492249],"genre_scores_gemma":[0.001874746,0.0003398105,0.00002723834,0.0005890907,0.000431824,0.000002258013,0.9962147,9.880944e-7,0.0005193706],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02199713,"threshold_uncertainty_score":0.9997146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02491834682066897,"score_gpt":0.1920439401484934,"score_spread":0.1671255933278244,"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."}}