{"id":"W3016677020","doi":"10.1109/access.2020.2988120","title":"Sampling for Big Data Profiling: A Survey","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Big data; Profiling (computer programming); Computer science; Data mining; Metadata; Data science; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.006171965,0.00009752527,0.0002182492,0.00007066128,0.000129071,0.00114125,0.005399233,0.00003534901,0.000045391],"category_scores_gemma":[0.01014495,0.00007524111,0.00003934333,0.0006918478,0.00003878419,0.001110565,0.001447626,0.00007209623,0.0001975674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006999652,"about_ca_system_score_gemma":0.00006302812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002023039,"about_ca_topic_score_gemma":0.00043169,"domain_scores_codex":[0.997651,0.0001813812,0.0004838168,0.0007543503,0.0007075651,0.0002218503],"domain_scores_gemma":[0.9961928,0.001932618,0.0001763211,0.001384221,0.0001865129,0.0001275536],"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":[0.0002146106,0.0000887995,0.01535173,0.00007531729,0.00005492886,0.000004175305,0.0002814014,0.0003132237,0.0002969754,0.00151542,0.7099242,0.2718793],"study_design_scores_gemma":[0.0006323175,0.00006245152,0.01217787,0.00001035389,0.00002298731,3.849714e-7,0.0003109142,0.01089509,0.001923339,0.01252791,0.9611356,0.0003007712],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02941288,0.00005265144,0.9578327,0.005223901,0.00249732,0.0006966401,0.003237004,0.00008345741,0.0009634763],"genre_scores_gemma":[0.9820813,0.00001809275,0.00579613,0.00892619,0.00148747,0.00004579995,0.001136868,0.00002248342,0.0004856446],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9526684,"threshold_uncertainty_score":0.9999821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9190001080756124,"score_gpt":0.5835216452442223,"score_spread":0.33547846283139,"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."}}