{"id":"W4385477002","doi":"10.1002/cyto.a.24776","title":"<scp>flowSim</scp> : Near duplicate detection for flow cytometry data","year":2023,"lang":"en","type":"article","venue":"Cytometry Part A","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Terry Fox Research Institute","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Overfitting; Computer science; Cluster analysis; Bivariate analysis; Redundancy (engineering); Data mining; Pattern recognition (psychology); Artificial intelligence; Preprocessor; Machine learning; Artificial neural network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004884607,0.0002446175,0.0002433584,0.0001984915,0.0002653807,0.0001078166,0.0006330328,0.0002917851,0.00001029789],"category_scores_gemma":[0.0006144568,0.0002532623,0.0001514133,0.001038715,0.00009358642,0.00001474076,0.0002719321,0.0001481471,0.0001857911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002325963,"about_ca_system_score_gemma":0.00006866635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001312428,"about_ca_topic_score_gemma":0.00003819752,"domain_scores_codex":[0.9981459,0.00004020655,0.000299502,0.0007760499,0.0001972874,0.0005410386],"domain_scores_gemma":[0.9984327,0.00009938843,0.00008359967,0.001124034,0.00009380883,0.0001664524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006927905,0.0001076724,0.006023058,0.0001035452,0.0001579169,0.000006193969,0.00005755025,0.0001974608,0.9387921,0.000003971055,0.03689502,0.01758622],"study_design_scores_gemma":[0.0009499394,0.0003044428,0.003658112,0.00001496871,0.00006171511,0.00001314368,0.00006751179,0.02447435,0.3065365,0.00003966446,0.6636969,0.0001828001],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9523118,0.0004996693,0.04424031,0.00007865769,0.001134246,0.0004478916,0.0006000162,0.0001846252,0.0005027919],"genre_scores_gemma":[0.9908751,0.0002870099,0.001758149,0.000272856,0.001110325,0.00009745504,0.002777777,0.00008772703,0.002733587],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6322557,"threshold_uncertainty_score":0.999992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05699497155382704,"score_gpt":0.2922918264205779,"score_spread":0.2352968548667508,"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."}}