{"id":"W3023289215","doi":"10.1101/2020.04.29.067892","title":"A Model Selection Approach to Hierarchical Shape Clustering with an Application to Cell Shapes","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Hierarchical clustering; Computer science; Selection (genetic algorithm); Data mining; Consensus clustering; Model selection; Inference; Single-linkage clustering; Dendrogram; Artificial intelligence; Set (abstract data type); Perspective (graphical); Fuzzy clustering; Machine learning; Pattern recognition (psychology); CURE data clustering algorithm; Population","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009307247,0.001035215,0.001444659,0.002551264,0.001189516,0.001529755,0.00287032,0.001618216,0.001840253],"category_scores_gemma":[0.01755678,0.0006203321,0.001993332,0.002050438,0.001919215,0.0008883042,0.002512201,0.001801713,0.000490594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001852389,"about_ca_system_score_gemma":0.001519921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007405748,"about_ca_topic_score_gemma":0.005823862,"domain_scores_codex":[0.995285,0.00302461,0.0001621008,0.0004700969,0.0008976038,0.0001607165],"domain_scores_gemma":[0.9874188,0.008906936,0.0007713392,0.0006791155,0.001925536,0.0002982952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006676527,0.00005586768,0.001836691,0.00009598789,0.0001398575,0.0001609736,0.0001735476,0.8791796,0.001917319,0.07892681,0.001388848,0.03605772],"study_design_scores_gemma":[0.000004621583,0.00001451855,0.0001077802,0.00000495972,0.00000543293,0.00001147846,0.000009038685,0.9827458,0.0002259025,0.0166,0.000264553,0.000005879089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004028132,0.0000777548,0.9951975,0.0001948912,0.00001328738,0.00003646769,0.0000323272,0.00009972922,0.0003199764],"genre_scores_gemma":[0.3170704,0.0002542158,0.6784036,0.000301778,0.0001780703,0.0005756166,0.0005073408,0.0002914158,0.002417527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009307247,"threshold_uncertainty_score":0.04922205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04031930145151131,"score_gpt":0.255010786242476,"score_spread":0.2146914847909647,"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."}}