{"id":"W1560306350","doi":"10.1007/978-3-540-68125-0_44","title":"On Discrete Data Clustering","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Automatic summarization; Robustness (evolution); Mixture model; Computer science; Cluster analysis; Dirichlet distribution; Data mining; Flexibility (engineering); Multinomial distribution; Algorithm; Artificial intelligence; Mathematics; Statistics","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006022527,0.0004388323,0.0003898426,0.0005867813,0.0002857104,0.0004517695,0.007812252,0.0002420585,0.00001693152],"category_scores_gemma":[0.0001186506,0.0003750883,0.00007792106,0.0004962097,0.0006162905,0.0008581278,0.003635167,0.0007508587,0.0000909596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002096096,"about_ca_system_score_gemma":0.0003735584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001012304,"about_ca_topic_score_gemma":0.00001351046,"domain_scores_codex":[0.9961674,0.00002628156,0.0004344417,0.001838578,0.001033282,0.0005000334],"domain_scores_gemma":[0.9954281,0.0003357615,0.0002426979,0.003714315,0.0001395081,0.0001395881],"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":[0.000006430906,0.0000226435,0.000003646522,0.00002515325,0.000007076943,0.0001193935,0.0002425315,0.0008098234,0.0001586499,0.01417782,0.0002170473,0.9842098],"study_design_scores_gemma":[0.0001868004,0.0002283367,0.00005226209,0.0004715112,0.000005000493,0.0001522446,4.73526e-8,0.9063972,0.005413411,0.0735833,0.01262041,0.0008894458],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000002357221,0.0002663019,0.9908082,0.000989418,0.0008471022,0.0002772108,0.00001342204,0.0003556538,0.006440288],"genre_scores_gemma":[0.04653888,0.0005739063,0.9467992,0.003422181,0.0006479898,0.00001112001,0.00004469988,0.00006820114,0.001893882],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9833204,"threshold_uncertainty_score":0.9998701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04302979265660046,"score_gpt":0.2826356957170578,"score_spread":0.2396059030604573,"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."}}