{"id":"W2606743718","doi":"10.23889/ijpds.v1i1.77","title":"Record Linkage Project Process Model","year":2017,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Record linkage; Linkage (software); Linked data; Process (computing); Computer science; Session (web analytics); Information retrieval; Data science; World Wide Web; Sociology; Demography; Population","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.01135714,0.0001068604,0.0001463597,0.0005224733,0.001819384,0.006660319,0.01555542,0.00003343205,0.00005683291],"category_scores_gemma":[0.01798168,0.00008035814,0.00006165093,0.0002125059,0.0002660735,0.01389422,0.001789433,0.0001473989,0.00005029878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008861575,"about_ca_system_score_gemma":0.0003398525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001801591,"about_ca_topic_score_gemma":0.0002247026,"domain_scores_codex":[0.9949563,0.00003968858,0.0007442303,0.0006753781,0.003327294,0.0002571563],"domain_scores_gemma":[0.9952112,0.0001672157,0.001126978,0.001856646,0.001519129,0.0001188322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002445891,0.0002326289,0.03467113,0.00001268578,0.00006067905,0.00002124669,0.0006382818,0.006795037,0.0002689573,0.08766887,0.09542748,0.7739584],"study_design_scores_gemma":[0.0005165318,0.00003498214,0.02574414,0.00004005649,0.00001103789,0.00002877112,0.000255613,0.708342,0.00004650674,0.1749393,0.08984951,0.0001915207],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1784778,0.00001981959,0.7775746,0.01666674,0.01467734,0.0009197402,0.002683436,0.00006785558,0.008912673],"genre_scores_gemma":[0.9714758,0.00002812597,0.02450772,0.0004779174,0.0005618097,0.00001094538,0.000208951,0.000007956995,0.002720761],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.792998,"threshold_uncertainty_score":0.999898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5924316145985103,"score_gpt":0.6150809603045536,"score_spread":0.02264934570604327,"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."}}