{"id":"W1769669223","doi":"10.1007/978-3-642-01307-2_19","title":"A Statistical Approach for Binary Vectors Modeling and Clustering","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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; Cluster analysis; Feature selection; Artificial intelligence; Binary number; Pattern recognition (psychology); Selection (genetic algorithm); Feature (linguistics); Statistical model; Data mining; Model selection; Machine learning; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001086341,0.0004793749,0.0005666934,0.0005194606,0.0002591083,0.0004822048,0.001482768,0.0003103112,0.000001630951],"category_scores_gemma":[0.00006818336,0.0004281317,0.00008921073,0.0002413979,0.0003000799,0.0003887328,0.0007906717,0.0005724481,9.285581e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001269185,"about_ca_system_score_gemma":0.0002536881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000082088,"about_ca_topic_score_gemma":0.000005822263,"domain_scores_codex":[0.9967896,0.000038544,0.000427737,0.001614662,0.0004892724,0.0006402221],"domain_scores_gemma":[0.9983559,0.0003827207,0.0001259487,0.0007937123,0.0001269876,0.000214793],"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":[0.0000083817,0.00001636996,0.000001305232,0.00006565985,0.000005657068,0.0000186443,0.0003332411,0.07153239,0.00005001862,0.05617904,0.000005608772,0.8717837],"study_design_scores_gemma":[0.0001676942,0.0001541314,0.00000469774,0.0001008332,0.000007019555,0.0000498599,4.894939e-8,0.7174839,0.00002640704,0.2815771,0.00006871195,0.0003597007],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001111931,0.0005688382,0.9966798,0.0002266429,0.0004655106,0.0005402475,0.000008054955,0.0001121515,0.001387643],"genre_scores_gemma":[0.01844343,0.0000363443,0.980342,0.0007459644,0.0002871311,0.00001317813,0.000006095053,0.00002880484,0.00009703288],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.871424,"threshold_uncertainty_score":0.9998171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03145556207775663,"score_gpt":0.2785284090659048,"score_spread":0.2470728469881481,"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."}}