{"id":"W4288870185","doi":"10.1007/978-3-031-01865-7_7","title":"Profiling Non-Relational Data","year":2019,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on data management","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Profiling (computer programming); Computer science; Relational database; XML; Big data; Data type; Data science; Data mining; World Wide Web; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002729213,0.0008780779,0.0007222851,0.002598916,0.0007024418,0.006059555,0.001819066,0.0007325292,0.01837455],"category_scores_gemma":[0.008541511,0.0008144804,0.0006110155,0.004484198,0.0008820936,0.01076677,0.002811851,0.001758576,0.0116798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00105968,"about_ca_system_score_gemma":0.0008383883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008043583,"about_ca_topic_score_gemma":0.001649418,"domain_scores_codex":[0.9975483,0.0003479526,0.0001305856,0.0005075237,0.001345554,0.0001200762],"domain_scores_gemma":[0.9965478,0.001422521,0.0001275467,0.001281305,0.0005111482,0.000109637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005947972,0.00005921993,0.001293308,0.0003640057,0.00003446601,0.0001236528,0.000525474,0.003880434,0.009500325,0.2199353,0.06769543,0.6965289],"study_design_scores_gemma":[0.000007472931,0.00003712289,0.001760016,0.0003376419,0.00003137909,0.0006459926,0.0004021368,0.04096919,0.02413295,0.3997117,0.5319034,0.00006098714],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006306296,0.00558653,0.902797,0.002702312,0.0008379847,0.0001258805,0.00227132,0.005170106,0.07420251],"genre_scores_gemma":[0.1073878,0.008717021,0.6827199,0.001414467,0.0007299351,0.0002324348,0.009139308,0.003318782,0.1863403],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01837455,"threshold_uncertainty_score":0.06146902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3872945890214914,"score_gpt":0.4096235086479726,"score_spread":0.0223289196264812,"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."}}