{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.008362029,0.0007842016,0.0009623496,0.00106798,0.0002996183,0.00100836,0.01784068,0.000336576,0.006507755],"category_scores_gemma":[0.002120078,0.000618624,0.0001784463,0.0001954573,0.0001721265,0.00125861,0.01855476,0.0006192611,0.01799403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001361343,"about_ca_system_score_gemma":0.0001337556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001927938,"about_ca_topic_score_gemma":0.0001058554,"domain_scores_codex":[0.9889292,0.000191776,0.00150035,0.00400666,0.004810438,0.00056157],"domain_scores_gemma":[0.9738069,0.002864663,0.000950892,0.02209486,0.0001245713,0.0001581362],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005904352,0.00005153367,0.000004794743,0.0001051247,0.0005296001,0.00004244718,0.000008525432,0.0001997772,7.130486e-7,0.3284066,0.5070807,0.1635112],"study_design_scores_gemma":[0.0002036048,0.00003545998,0.000148158,0.0003164482,0.0004167624,0.000001681151,0.00005552093,0.002345416,0.00001071156,0.03369021,0.9620867,0.0006893088],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000002377499,0.0003172774,0.02171309,0.002603491,0.00143029,0.001834968,0.01670818,0.0001137396,0.9552766],"genre_scores_gemma":[0.001123905,0.0006733661,0.01307906,0.003391396,0.0006715358,0.00004629557,0.02784432,0.0001596056,0.9530105],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.455006,"threshold_uncertainty_score":0.9996265,"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."}}