{"id":"W2006981561","doi":"10.1145/2351476.2351500","title":"Mining probabilistic datasets vertically","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Probabilistic logic; Data mining; Uncertain data; Set (abstract data type); Database transaction; Data set; Representation (politics); A priori and a posteriori; Artificial intelligence; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.0001710219,0.00005231711,0.00004914254,0.00001910426,0.00006733525,0.00008244913,0.0005153861,0.00001615021,0.00003971832],"category_scores_gemma":[0.00005751876,0.00004240978,0.00001184574,0.0001565824,0.00001944481,0.0005701474,0.0002438132,0.00003327607,0.0003352167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001201343,"about_ca_system_score_gemma":0.00001698047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008843467,"about_ca_topic_score_gemma":0.000001370645,"domain_scores_codex":[0.9994159,0.0000103355,0.00009585617,0.0001509308,0.0001028188,0.0002240972],"domain_scores_gemma":[0.9992474,0.00006527456,0.00001519322,0.0005360863,0.00001344259,0.0001225422],"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":[4.606073e-7,0.0001841797,0.0007380146,0.000006255183,0.00000734416,0.00000114057,0.0003540934,0.000003375467,0.00020884,0.7308866,0.07314572,0.194464],"study_design_scores_gemma":[0.0003200929,0.00006811869,0.02045418,0.00001994215,0.0000184437,0.00006506346,0.00007370368,0.2938526,0.001305161,0.003215469,0.6800736,0.0005336531],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004228424,0.0000265386,0.985132,0.001102629,0.0001499835,0.00008185801,0.00002604486,0.0002002085,0.009052344],"genre_scores_gemma":[0.241532,0.000001076081,0.7574894,0.0005971002,0.00008173473,0.00002783657,0.00006336758,0.000004060183,0.0002034133],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7276711,"threshold_uncertainty_score":0.4308645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02797830933118894,"score_gpt":0.2764063718074993,"score_spread":0.2484280624763104,"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."}}