{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01602347,0.001441052,0.002742829,0.006182106,0.001795741,0.003748446,0.003964273,0.003704021,0.002633402],"category_scores_gemma":[0.05293308,0.0006531999,0.001552213,0.004523213,0.003716595,0.004442091,0.003937851,0.002532433,0.0007130142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002280107,"about_ca_system_score_gemma":0.003606672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003588218,"about_ca_topic_score_gemma":0.004316756,"domain_scores_codex":[0.986406,0.005164179,0.00112966,0.001355385,0.005344044,0.0006007172],"domain_scores_gemma":[0.9651881,0.01971111,0.003819011,0.002310764,0.007411675,0.001559316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001416416,0.0006294053,0.03132525,0.00108296,0.001120738,0.00045871,0.0005473424,0.6068634,0.01169892,0.06800734,0.01257355,0.2642759],"study_design_scores_gemma":[0.0000809103,0.0002673114,0.002241407,0.00005343985,0.00006120275,0.0001639113,0.00009352922,0.9710988,0.001951778,0.02332013,0.0006028145,0.00006478135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04499508,0.0003877762,0.9511561,0.0004508108,0.00008828169,0.0001691873,0.0004561699,0.0005238377,0.001772753],"genre_scores_gemma":[0.5308143,0.0002264346,0.4647467,0.0002531692,0.0001788002,0.000344751,0.00184731,0.0002314432,0.001356971],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01602347,"threshold_uncertainty_score":0.08474123,"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."}}