{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006394613,0.002588283,0.001027293,0.00340373,0.0009919442,0.001140042,0.002761512,0.002236231,0.01169944],"category_scores_gemma":[0.001873061,0.0003756677,0.00142813,0.003531507,0.0004891906,0.0009408959,0.001728764,0.001608628,0.01281858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001711744,"about_ca_system_score_gemma":0.001474395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03253153,"about_ca_topic_score_gemma":0.08248547,"domain_scores_codex":[0.9991826,0.0001031555,0.00006854515,0.0002513847,0.000259363,0.0001350461],"domain_scores_gemma":[0.9994036,0.0001045031,0.00006187814,0.0001504278,0.0001821097,0.00009746661],"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":[0.0003788746,0.0003977397,0.007967458,0.001564088,0.0002019393,0.0003641154,0.0001211524,0.003054685,0.004758892,0.0008645292,0.9400209,0.04030571],"study_design_scores_gemma":[0.0004972776,0.0002748271,0.06508559,0.0004698783,0.0001679451,0.001304722,0.0007135632,0.01849011,0.009157983,0.002478821,0.9011808,0.0001784906],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01443422,0.0007572738,0.001089484,0.0002496961,0.00009991029,0.0001391516,0.977977,0.00228229,0.002970987],"genre_scores_gemma":[0.00484738,0.00008053419,0.002225202,0.0000597201,0.000009338331,0.0001141257,0.9918345,0.00004851858,0.0007806252],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03253153,"threshold_uncertainty_score":0.06468433,"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."}}