{"id":"W2589068952","doi":"10.29173/cais150","title":"Performance in ART1-Like Document Clustering with Variable Similarity Thresholds","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cluster analysis; Similarity (geometry); Variable (mathematics); Implementation; Massively parallel; Document clustering; Data mining; Information retrieval; Parallel computing; Artificial intelligence; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005629395,0.0007715946,0.001406594,0.001558303,0.001262707,0.002275992,0.002632633,0.002342304,0.002278896],"category_scores_gemma":[0.02024513,0.000429845,0.0004056602,0.003248837,0.001207618,0.003596537,0.00130611,0.0008834642,0.001568728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001976933,"about_ca_system_score_gemma":0.001464621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01197254,"about_ca_topic_score_gemma":0.007453362,"domain_scores_codex":[0.9957733,0.001132147,0.0003210182,0.0008695904,0.001354147,0.0005498009],"domain_scores_gemma":[0.9870177,0.007265855,0.0006324956,0.002277266,0.002225727,0.0005809522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.01078217,0.001346012,0.01324526,0.000585968,0.0002697858,0.0002291736,0.0005842287,0.4647267,0.03060931,0.004929369,0.01191021,0.4607816],"study_design_scores_gemma":[0.0001558334,0.0009608453,0.004184025,0.00001275031,0.00003924265,0.0001679983,0.0001466702,0.9638686,0.02763873,0.001872772,0.0009084594,0.00004414014],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9027922,0.003245851,0.07410169,0.0005744097,0.0001909344,0.0001426035,0.0007043267,0.008475016,0.00977293],"genre_scores_gemma":[0.9353853,0.0003691097,0.05962455,0.0001167733,0.0000561702,0.00005019961,0.001384165,0.000232064,0.002781579],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01197254,"threshold_uncertainty_score":0.02977145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01507865651523827,"score_gpt":0.2154069153870535,"score_spread":0.2003282588718152,"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."}}