{"id":"W2166290337","doi":"10.1186/1471-2288-3-18","title":"How does correlation structure differ between real and fabricated data-sets?","year":2003,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Population Health Research Institute; McMaster University","funders":"Shiraz University; Shiraz University of Medical Sciences; McMaster University","keywords":"Correlation; Data set; Set (abstract data type); Correlation coefficient; Statistics; Data mining; Pearson product-moment correlation coefficient; Misconduct; Computer science; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1279639,0.0001786839,0.0006296146,0.0003621969,0.0003470515,0.0002823856,0.001841364,0.0004839163,0.002146587],"category_scores_gemma":[0.4940703,0.00009412664,0.00005690762,0.0009426007,0.001262025,0.0002897707,0.0008124649,0.001152717,0.00004761652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006474154,"about_ca_system_score_gemma":0.0006000768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001506882,"about_ca_topic_score_gemma":0.0006638402,"domain_scores_codex":[0.9432103,0.04566177,0.0008612231,0.001392214,0.008049086,0.0008253783],"domain_scores_gemma":[0.8460153,0.1495313,0.0002382957,0.002276126,0.0009666468,0.0009723126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001428909,0.00008509574,0.6715367,0.00006251816,0.00005919229,0.00001991747,0.0004321679,0.00000639207,0.001974785,0.01262783,0.01889576,0.2941568],"study_design_scores_gemma":[0.001354296,0.0003442551,0.4251802,0.00005004795,0.00003670724,0.00002063699,0.002297207,0.003706325,0.001401627,0.4671018,0.09819328,0.0003135848],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5922698,0.0003056614,0.39537,0.009644175,0.0006638045,0.0005914786,0.00008988853,0.00003498371,0.001030121],"genre_scores_gemma":[0.923272,0.0003454381,0.07417823,0.0001486861,0.0002853158,0.00001936426,0.00007933628,0.00001426273,0.001657443],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.454474,"threshold_uncertainty_score":0.9987656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8378742148671262,"score_gpt":0.607124913089742,"score_spread":0.2307493017773842,"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."}}