{"id":"W1881830221","doi":"10.1111/coin.12064","title":"Document Clustering With Dual Supervision Through Feature Reweighting","year":2015,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Feature (linguistics); Brown clustering; Artificial intelligence; Pairwise comparison; Correlation clustering; Pattern recognition (psychology); Fuzzy clustering; Consensus clustering; Data mining; Conceptual clustering; Machine learning; Canopy clustering algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002121207,0.0001579239,0.0001269802,0.00008918119,0.0001425519,0.0002984332,0.0006972788,0.0000655879,0.00001359674],"category_scores_gemma":[0.000064504,0.0001244577,0.00003183646,0.0005138105,0.0000897615,0.001072017,0.0003722766,0.0001681345,0.0001262852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009938571,"about_ca_system_score_gemma":0.0001123177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001429206,"about_ca_topic_score_gemma":0.000004808185,"domain_scores_codex":[0.9985623,0.00003686202,0.0002242806,0.0004220202,0.0005302088,0.0002242868],"domain_scores_gemma":[0.9990165,0.0001370786,0.0001089059,0.0003658402,0.0002914594,0.00008021694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002758804,0.00006838173,0.0005005694,0.00001790349,0.00002572777,0.00003707669,0.002940456,0.1840316,0.00004589419,0.7090959,0.004680601,0.09852829],"study_design_scores_gemma":[0.0003105182,0.0003880777,0.0007132747,0.0001097651,0.000007191028,0.0001640523,0.001323656,0.5287066,0.005800617,0.4459996,0.0159581,0.0005185931],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003365144,0.0002686328,0.9883863,0.004954608,0.0002490197,0.0001416742,8.786894e-7,0.0004997524,0.002133942],"genre_scores_gemma":[0.5979967,0.00001088224,0.4013847,0.0002457411,0.00003859177,0.00001448647,0.000009100088,0.000006551547,0.0002932383],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5946316,"threshold_uncertainty_score":0.5075239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05995408911021713,"score_gpt":0.3051056388127768,"score_spread":0.2451515497025597,"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."}}