{"id":"W2099837874","doi":"","title":"Human Cluster Evaluation and Formal Quality Measures: A Comparative Study","year":2012,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Cluster analysis; Computer science; Data mining; Disjoint sets; Partition (number theory); Consistency (knowledge bases); Set (abstract data type); Contrast (vision); Fuzzy clustering; Machine learning; Artificial intelligence; Mathematics","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","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.002028275,0.0002983805,0.000329488,0.0001947246,0.00041311,0.001902399,0.0008659447,0.00008850599,0.00004301046],"category_scores_gemma":[0.0002516622,0.0002646511,0.00007546345,0.0005219232,0.0001094631,0.01980172,0.001452565,0.0004880386,0.0004020334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000853089,"about_ca_system_score_gemma":0.00008012195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003982845,"about_ca_topic_score_gemma":0.000002575374,"domain_scores_codex":[0.9962032,0.0006391473,0.0005149242,0.0005490059,0.001291075,0.0008026795],"domain_scores_gemma":[0.9983273,0.0002097465,0.0001519998,0.0006941162,0.0001393738,0.0004774993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002804374,0.004001961,0.7236201,0.0001611201,0.0003427644,0.00002138131,0.008246342,0.0002841777,0.000562335,0.01234148,0.001065968,0.249072],"study_design_scores_gemma":[0.01200511,0.002029253,0.8519214,0.0001933298,0.00008894042,0.0001174672,0.003368408,0.04657215,0.003675143,0.03502295,0.04161376,0.003392031],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9353544,0.0002734657,0.05553489,0.0002311326,0.0001264537,0.001267936,0.0001324914,0.0004028976,0.0066764],"genre_scores_gemma":[0.9935379,0.00000120083,0.005737447,0.0001491683,0.0001350589,0.0001115465,0.00005066396,0.00002919351,0.0002478367],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2456799,"threshold_uncertainty_score":0.9999806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09701167708169886,"score_gpt":0.3631882371902808,"score_spread":0.2661765601085819,"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."}}