{"id":"W3199460270","doi":"10.1007/s10618-021-00794-0","title":"A Lagrangian-based score for assessing the quality of pairwise constraints in semi-supervised clustering","year":2021,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis","funders":"","keywords":"Cluster analysis; Pairwise comparison; Constrained clustering; Constraint (computer-aided design); Computer science; Data mining; Machine learning; Key (lock); Artificial intelligence; Correlation clustering; Mathematics; CURE data 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":[0.001607284,0.0001442458,0.0002822106,0.00008961801,0.0001476194,0.0003723658,0.0009940519,0.00005641292,0.000002117516],"category_scores_gemma":[0.001006422,0.0001180857,0.00004869586,0.0004501407,0.0002246939,0.001106621,0.001248342,0.0001393381,6.314744e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003560221,"about_ca_system_score_gemma":0.0005108404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003202657,"about_ca_topic_score_gemma":0.0003202177,"domain_scores_codex":[0.9982212,0.000268043,0.0003843379,0.0005912976,0.000203161,0.0003320257],"domain_scores_gemma":[0.9968937,0.001642455,0.00009996482,0.001167895,0.0001347189,0.00006123979],"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":[0.000067413,0.0004205743,0.01724934,0.001723821,0.00007033429,0.00006724065,0.00604334,0.0009657841,0.01205446,0.000834706,0.0002627594,0.9602402],"study_design_scores_gemma":[0.001474216,0.00003318837,0.008626503,0.0006840639,0.00000891727,0.0000123411,0.002641491,0.9840835,0.001859452,0.0001096422,0.0002269839,0.0002396406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2461658,0.000988783,0.7516652,0.0002489079,0.0001768349,0.0001919093,0.0002699879,0.00003170306,0.0002608434],"genre_scores_gemma":[0.9248499,0.00002156734,0.074669,0.00005598625,0.00005413613,0.00002741309,0.0001829803,0.00001491169,0.00012408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9831178,"threshold_uncertainty_score":0.4815394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1432772631699324,"score_gpt":0.4071249385868225,"score_spread":0.2638476754168901,"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."}}