{"id":"W3000988915","doi":"10.1145/3241380","title":"A Visual Analytics Approach for Interactive Document Clustering","year":2019,"lang":"en","type":"article","venue":"ACM Transactions on Interactive Intelligent Systems","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Visual analytics; Analytics; Visualization; Data mining; Set (abstract data type); Process (computing); Key (lock); Document clustering; Information retrieval; Machine learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003685283,0.0003735707,0.0004613288,0.000548444,0.000177151,0.0005924416,0.001323643,0.0001151464,0.0001324275],"category_scores_gemma":[0.00008052364,0.0003467116,0.0003145206,0.0005467867,0.00003529459,0.001264085,0.00007089291,0.0003524434,0.0003839062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004746245,"about_ca_system_score_gemma":0.00007314712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008607833,"about_ca_topic_score_gemma":0.000009324389,"domain_scores_codex":[0.9973935,0.000158907,0.0007192438,0.0008392105,0.0004593663,0.0004297651],"domain_scores_gemma":[0.9973384,0.0006767043,0.0003303326,0.001090388,0.000394603,0.0001695362],"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":[0.001767865,0.005400411,0.0003583561,0.001223037,0.004076652,0.00002262644,0.01238576,0.8272731,0.0032434,0.0369083,0.002700349,0.1046402],"study_design_scores_gemma":[0.0005303529,0.0007565391,0.00001127853,0.0002124486,0.00005277712,0.00003178875,0.003091688,0.9747273,0.007443064,0.0002344116,0.01246641,0.0004419621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008428596,0.00002451156,0.9932811,0.0001629536,0.002397943,0.001281422,0.00005578177,0.0001945891,0.001758901],"genre_scores_gemma":[0.9765475,0.00003378612,0.0178108,0.0003311362,0.0001003694,0.0002765628,0.00006790931,0.0000447325,0.004787202],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9757047,"threshold_uncertainty_score":0.9998985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03359866520823913,"score_gpt":0.3349496390108793,"score_spread":0.3013509738026401,"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."}}