{"id":"W1599200063","doi":"10.1007/s10115-015-0871-2","title":"Partial materialization for online analytical processing over multi-tagged document collections","year":2015,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Centroid; Information retrieval; Medoid; Document clustering; Digital library; Data mining; Artificial intelligence; Cluster analysis","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":[],"consensus_categories":[],"category_scores_codex":[0.0003281436,0.0001034401,0.0001631879,0.000136552,0.0002269442,0.0003851953,0.00008555238,0.00005211215,0.000001369922],"category_scores_gemma":[0.00007502371,0.00008570332,0.00002216714,0.0003215932,0.00002203087,0.004519872,0.00006864893,0.00003081387,0.00001583588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007795891,"about_ca_system_score_gemma":0.0001290636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000341365,"about_ca_topic_score_gemma":0.00001434823,"domain_scores_codex":[0.9991027,0.00003982036,0.0004512005,0.0001232565,0.0001326592,0.0001503918],"domain_scores_gemma":[0.9991637,0.00001898916,0.0001668677,0.0001591272,0.0003958255,0.00009548399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001355981,0.0002753879,0.0004576423,0.001677187,0.00007665205,0.000001145334,0.02292644,0.002523885,0.0001778904,0.8740367,0.0445534,0.05315813],"study_design_scores_gemma":[0.000744401,0.00004687144,0.00006260084,0.00005496607,0.000004933818,0.000009152409,0.0002892494,0.4612496,0.00008198141,0.00002040201,0.5373421,0.00009372511],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002171287,0.0002650388,0.9950373,0.00003879578,0.001035633,0.0004999951,0.00006143301,0.0001128099,0.0007777095],"genre_scores_gemma":[0.8922313,0.00006840146,0.09832422,0.000257217,0.001352745,0.0008552352,0.001123852,0.00003098243,0.005756054],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8967131,"threshold_uncertainty_score":0.3714447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04078338301597355,"score_gpt":0.3180951839573361,"score_spread":0.2773118009413625,"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."}}