{"id":"W2785374143","doi":"10.1002/cjs.11795","title":"Clustering and semi‐supervised classification for clickstream data via mixture models","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Canada Research Chairs; E.W.R. Steacie Memorial Fund","keywords":"Clickstream; Computer science; Mixture model; Cluster analysis; Machine learning; Artificial intelligence; Unsupervised learning; Data mining; Markov chain; Web page","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0008860772,0.0001055427,0.0001988745,0.000215839,0.0001463409,0.0001916828,0.0008180888,0.00007167948,0.000003628375],"category_scores_gemma":[0.0001765422,0.00009686126,0.00002551418,0.0002247306,0.0000432358,0.0004504837,0.00006696701,0.0001478325,0.000001757752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004389052,"about_ca_system_score_gemma":0.0005396147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001946285,"about_ca_topic_score_gemma":0.002336306,"domain_scores_codex":[0.9989425,0.00006502788,0.0003659217,0.0002202143,0.0001389767,0.0002673423],"domain_scores_gemma":[0.9984033,0.0002264763,0.0001826225,0.0004885359,0.0002354695,0.0004636342],"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":[0.000008622288,0.000007328131,0.0001426335,0.00009080673,0.00004917083,0.0001298693,0.001455319,0.000579775,0.000397279,0.09709099,0.07956646,0.8204818],"study_design_scores_gemma":[0.0002274316,0.00004964229,0.0005036815,0.00002787112,0.00001833839,0.00008387009,0.00002917763,0.8904728,0.00001349317,0.1044794,0.003993013,0.0001013128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002534778,0.0001614623,0.9971333,0.001197951,0.0004039794,0.0001114107,0.0006160814,0.00001108116,0.0001113203],"genre_scores_gemma":[0.07648467,0.00007803053,0.9228559,0.0002525729,0.0001417596,0.000002043239,0.00006216927,0.00001430164,0.0001086212],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.889893,"threshold_uncertainty_score":0.3949887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09815003102868965,"score_gpt":0.2989763110525442,"score_spread":0.2008262800238546,"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."}}