{"id":"W3162387593","doi":"10.1039/d1ra02869c","title":"Rare bioparticle detection <i>via</i> deep metric learning","year":2021,"lang":"en","type":"article","venue":"RSC Advances","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Nautical Research Society","funders":"Ministry of Education, India; Ministry of Education - Singapore; National Research Foundation Singapore; National Research Foundation","keywords":"Metric (unit); Artificial intelligence; Deep neural networks; Deep learning; Artificial neural network; Computer science; Simple (philosophy); Pattern recognition (psychology); Machine learning; Engineering; Philosophy","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":[],"consensus_categories":[],"category_scores_codex":[0.0000634217,0.0001013816,0.0001078344,0.00008520266,0.000138416,0.0002859355,0.0002844918,0.00001699044,0.0000112828],"category_scores_gemma":[0.0002629581,0.0001019824,0.00006705603,0.001212595,0.00003449822,0.002078251,0.0001817524,0.00008063551,0.0001413776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002524538,"about_ca_system_score_gemma":0.00003126528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004233751,"about_ca_topic_score_gemma":0.00001379992,"domain_scores_codex":[0.9989877,0.00004586595,0.0001371257,0.0003416713,0.0002338663,0.0002537998],"domain_scores_gemma":[0.9993638,0.00008766017,0.00006057991,0.0002783013,0.0001029272,0.0001067207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004020698,0.0001286932,0.004741128,0.0000258243,0.0000130898,0.000107797,0.00008593625,0.002512778,0.01660035,0.001226657,0.00002162194,0.9745321],"study_design_scores_gemma":[0.0004885829,0.0001213754,0.002792174,0.00002873767,0.00002377166,0.0001393104,0.0001384757,0.03726543,0.8875879,0.01071542,0.06027049,0.0004283048],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0772991,0.01769685,0.8971049,0.0002989008,0.0005302436,0.00006920603,0.000001346569,0.0006637697,0.006335674],"genre_scores_gemma":[0.9806334,0.00006423756,0.01874851,0.00021094,0.00004655782,0.000009523558,0.000002293061,0.00000907445,0.0002754022],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9741038,"threshold_uncertainty_score":0.4158723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008272986701432996,"score_gpt":0.2381783762499563,"score_spread":0.2299053895485233,"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."}}