{"id":"W1970187450","doi":"10.1145/2245276.2245457","title":"Enhancing semi-supervised document clustering with feature supervision","year":2012,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Cluster analysis; Computer science; Pairwise comparison; Feature (linguistics); Artificial intelligence; Brown clustering; Consensus clustering; Data mining; Correlation clustering; Fuzzy clustering; Pattern recognition (psychology); Conceptual clustering; Machine learning; Canopy clustering algorithm","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":[0.0002087986,0.0001481177,0.0001210689,0.0001041613,0.0001343272,0.00020607,0.0006499081,0.00008043425,0.00008960139],"category_scores_gemma":[0.00001372521,0.0001000395,0.00003327208,0.0003437129,0.00002646392,0.001603237,0.000369218,0.0001300709,0.0001179903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005694072,"about_ca_system_score_gemma":0.00001935672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001230499,"about_ca_topic_score_gemma":0.000016678,"domain_scores_codex":[0.9989169,0.00002245416,0.0001386889,0.0002646871,0.0002751246,0.0003820996],"domain_scores_gemma":[0.9991334,0.00004088059,0.00004490734,0.000643321,0.00004087629,0.00009658128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004979965,0.0003895046,0.03398388,0.0001598788,0.0001056892,0.00001437354,0.007739639,0.0001201627,0.1493775,0.3528917,0.0137748,0.4413931],"study_design_scores_gemma":[0.002152937,0.0005209711,0.02669153,0.0002296934,0.00003091601,0.0001276456,0.003560754,0.02235755,0.837027,0.002872779,0.102743,0.001685211],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04805485,0.0003157156,0.939625,0.004755608,0.0002395001,0.0001895513,2.364153e-7,0.001232095,0.005587413],"genre_scores_gemma":[0.8502005,0.000024627,0.1473631,0.0003066665,0.00004289685,0.00002303047,0.000001842636,0.000007860943,0.002029476],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8021457,"threshold_uncertainty_score":0.4079494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0141388141283832,"score_gpt":0.2425182503680033,"score_spread":0.2283794362396201,"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."}}