{"id":"W2901065680","doi":"10.1007/s10489-018-1333-9","title":"Model selection and application to high-dimensional count data clustering","year":2018,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Burstiness; Cluster analysis; Model selection; Count data; Dirichlet distribution; Multinomial distribution; Novelty; Selection (genetic algorithm); Data mining; Algorithm; Artificial intelligence; Pattern recognition (psychology); Statistics; Mathematics; Poisson distribution","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":[0.0004602369,0.0001236905,0.0001150175,0.00006610372,0.000162886,0.00009051255,0.0008235142,0.00005945551,0.000005316194],"category_scores_gemma":[0.00001304044,0.0001174677,0.000008390824,0.0003003365,0.00004576027,0.0002452584,0.0007978483,0.00009515282,0.00008482507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003008492,"about_ca_system_score_gemma":0.00004253701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005142781,"about_ca_topic_score_gemma":0.00006430568,"domain_scores_codex":[0.9987125,0.00001638859,0.0001840166,0.0006839788,0.0001924645,0.0002106751],"domain_scores_gemma":[0.9989427,0.00003990863,0.00005012793,0.000771064,0.00008565298,0.0001105072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001316776,0.00001788578,0.000002801245,0.00000630145,0.000005399189,1.981261e-7,0.0002669531,0.004198687,0.02212848,0.3952254,0.0005329,0.5776018],"study_design_scores_gemma":[0.00002616709,0.00003248772,0.00002673935,0.00000614117,0.000003531612,0.00000798991,0.000002385,0.9098114,0.0168499,0.07245517,0.0006430059,0.0001350407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001340443,0.00001915499,0.9969177,0.000323879,0.0001009741,0.0002585733,0.000003903549,0.0001042654,0.0009310799],"genre_scores_gemma":[0.4760773,0.000004850611,0.5231302,0.0006577748,0.00007171996,0.00002095641,0.000003378039,0.000005528057,0.0000282469],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9056128,"threshold_uncertainty_score":0.4790193,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04075433305424717,"score_gpt":0.3080225558592062,"score_spread":0.267268222804959,"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."}}