{"id":"W2783291455","doi":"10.1109/bigdata.2017.8258218","title":"Identifying and mitigating risks to the quality of open data in the post-truth era","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Open data; Big data; Data science; Transparency (behavior); Data quality; Computer science; Analytics; Quality (philosophy); Ground truth; Open government; Data analysis; Computer security; Data mining; World Wide Web; Business","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":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.03920368,0.00006246542,0.0001724603,0.0000463754,0.0005354271,0.003627425,0.01193347,0.00001690277,0.0001212846],"category_scores_gemma":[0.01764186,0.00002817027,0.00001863766,0.0001427226,0.0001310835,0.001608004,0.01209337,0.00009947277,0.00005325972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003960458,"about_ca_system_score_gemma":0.00002197999,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02513248,"about_ca_topic_score_gemma":0.02539778,"domain_scores_codex":[0.9973143,0.0006941358,0.0005681882,0.0004142594,0.0008755143,0.0001335681],"domain_scores_gemma":[0.9926149,0.002327967,0.0003672974,0.004572899,0.00008069791,0.00003628487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006594879,0.0001261035,0.07537943,0.00003714636,0.00003834463,0.000005779663,0.017668,0.00000842843,0.0002086722,0.3228677,0.04948779,0.5341067],"study_design_scores_gemma":[0.0002099384,0.00001471437,0.9161479,0.00002112935,0.000005856883,5.674567e-7,0.03856423,0.0001757661,0.00005620597,0.02826043,0.01647194,0.00007132733],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.901267,0.00003642471,0.003587736,0.0459471,0.0002495371,0.0007721086,0.0003304059,0.000006294751,0.04780339],"genre_scores_gemma":[0.9948019,0.000007161921,0.002258038,0.002381642,0.0000221608,0.000007061384,0.00001408956,0.000002056163,0.0005058633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8407685,"threshold_uncertainty_score":0.9974069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7811195203369069,"score_gpt":0.6219168215022497,"score_spread":0.1592026988346572,"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."}}