{"id":"W1966037453","doi":"10.1109/bigdata.congress.2013.59","title":"RSenter: Tool for Topics and Terms Extraction from Unstructured Data Debris","year":2013,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Unstructured data; Information retrieval; NoSQL; Cluster analysis; Schema (genetic algorithms); Data mining; World Wide Web; Data science; Database; Big data","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":[0.00006029507,0.00006403073,0.0000861573,0.00003041202,0.00006143956,0.0003659631,0.0005755559,0.00003217605,0.00006236602],"category_scores_gemma":[0.00003734629,0.00004870584,0.00001859892,0.00005916362,0.00001270227,0.00119846,0.0002920532,0.00003507539,0.00001739844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004843197,"about_ca_system_score_gemma":0.000007750942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000646972,"about_ca_topic_score_gemma":0.00005464148,"domain_scores_codex":[0.9993653,0.00001165259,0.0001140316,0.0003316072,0.00007417272,0.0001032194],"domain_scores_gemma":[0.9990384,0.00005623768,0.00003780707,0.0008061741,0.00002395043,0.00003740906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001345954,0.00001421292,0.005173851,0.000004981578,0.0000441208,0.000001285156,0.00008699179,0.000001695974,0.00220748,0.001267708,0.04850484,0.9426915],"study_design_scores_gemma":[0.0005884927,0.00004338579,0.05300366,0.0000152817,0.00005555224,0.00001388573,0.00009870638,0.8356556,0.002870175,0.009433906,0.09788301,0.0003383527],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1114666,0.00002964391,0.8861695,0.001623175,0.0001609176,0.00009654483,0.00004917502,0.00007328423,0.0003311594],"genre_scores_gemma":[0.5377694,0.00002027203,0.4594506,0.000546722,0.0002428906,0.00001174857,0.0003324745,0.000005327318,0.001620526],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9423531,"threshold_uncertainty_score":0.352899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02802969159274242,"score_gpt":0.2717855098497026,"score_spread":0.2437558182569601,"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."}}