{"id":"W4293162521","doi":"10.1007/978-3-031-01865-7","title":"Data Profiling","year":2019,"lang":"en","type":"book","venue":"Synthesis lectures on data management","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Profiling (computer programming); Metadata; Computer science; Data science; Research data; World Wide Web; Data curation; Operating system","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","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.01361095,0.0009136091,0.001284865,0.001257517,0.0002945078,0.001956939,0.03777334,0.0003673314,0.003236155],"category_scores_gemma":[0.005112842,0.0006961924,0.0001882511,0.0004685948,0.0001864591,0.001390988,0.03289611,0.0007316042,0.0193261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002514999,"about_ca_system_score_gemma":0.0002414231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001873983,"about_ca_topic_score_gemma":0.0001497763,"domain_scores_codex":[0.9859703,0.0006627204,0.001696584,0.005292401,0.005559565,0.0008184701],"domain_scores_gemma":[0.9552925,0.004005121,0.001065864,0.03933178,0.0001148148,0.0001898949],"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":[0.00005692779,0.00009038895,0.000001716783,0.0002405244,0.0005268548,0.00007113835,0.000009299678,0.00007012799,4.611643e-7,0.04317814,0.7421225,0.2136319],"study_design_scores_gemma":[0.0001896178,0.00004313553,0.00003151882,0.0003725532,0.000519564,0.0000018361,0.0001100456,0.001016701,0.00001818708,0.02571482,0.9712011,0.0007809812],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00000124987,0.0005940887,0.008694728,0.00236543,0.002053004,0.002297109,0.03575313,0.000208703,0.9480326],"genre_scores_gemma":[0.0001193377,0.0007710083,0.006012856,0.003915519,0.0006724437,0.00007500972,0.03261295,0.0001405135,0.9556804],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2290786,"threshold_uncertainty_score":0.9995489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4345880521667448,"score_gpt":0.4454418407113966,"score_spread":0.0108537885446518,"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."}}