{"id":"W4253082290","doi":"10.1037/e527382013-003","title":"High Quality Analytics with Poor Quality Data","year":2012,"lang":"en","type":"dataset","venue":"PsycEXTRA Dataset","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Quality (philosophy); Analytics; Data quality; Computer science; Data science; Data analysis; Data mining; Business; Marketing","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":[],"category_scores_codex":[0.001731967,0.0005366816,0.0006597838,0.0001899638,0.0002980647,0.0003950677,0.007867639,0.0003567478,0.0004528193],"category_scores_gemma":[0.00007459123,0.0004493566,0.00007392999,0.0007725681,0.0001835017,0.001055511,0.002301176,0.0007508027,0.0009484282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007399677,"about_ca_system_score_gemma":0.0001831336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004190939,"about_ca_topic_score_gemma":0.001068908,"domain_scores_codex":[0.9958442,0.0002778773,0.0009133389,0.00154035,0.000813974,0.0006102435],"domain_scores_gemma":[0.9864113,0.0002149929,0.0008323333,0.0120867,0.0001074442,0.0003472149],"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":[0.00001329566,0.0002740858,0.00001056672,0.00009018977,0.00007573416,0.000005136354,0.000002195197,0.000001247419,0.000005928673,0.002625027,0.9946877,0.002208911],"study_design_scores_gemma":[0.000221913,0.00006112854,0.0002782195,0.00002297026,0.0001156225,0.0000314648,0.000005259501,0.00007915014,0.00004758447,0.0003574844,0.9980955,0.0006837717],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000002614283,0.00008446114,0.2011362,0.0006495413,0.0001872402,0.0003603136,0.7973437,0.0002172992,0.00001862789],"genre_scores_gemma":[0.00007424586,0.0001694774,0.04244759,0.001065178,0.0003566826,0.00008851095,0.9557356,0.00002079646,0.00004188368],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1586886,"threshold_uncertainty_score":0.9998295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1232503504945862,"score_gpt":0.3961428459929356,"score_spread":0.2728924954983494,"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."}}