{"id":"W2767239194","doi":"10.1558/jch.31662","title":"Mining the Past – Data-Intensive Knowledge Discovery in the Study of Historical Textual Traditions","year":2018,"lang":"en","type":"article","venue":"Journal of Cognitive Historiography","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Digitization; Data science; Praise; Computer science; Field (mathematics); Reading (process); Comparative historical research; Big data; Scope (computer science); Sociology; Data mining; Social science; Political science; Psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.002864857,0.00009756217,0.0002879721,0.0005495072,0.0005235031,0.00004875017,0.0006884907,0.00003490598,0.00002463983],"category_scores_gemma":[0.001067476,0.00005705027,0.0002378363,0.001855647,0.0005585974,0.0003751024,0.00003801678,0.0002566622,0.000001613512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001569898,"about_ca_system_score_gemma":0.0001841665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006577438,"about_ca_topic_score_gemma":0.005080829,"domain_scores_codex":[0.9970888,0.001452337,0.0005219824,0.0001506367,0.0006373246,0.0001488644],"domain_scores_gemma":[0.9942009,0.003426262,0.0005367381,0.0001613553,0.001623336,0.00005144255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004004284,0.004088608,0.09102723,0.000008298724,0.0008826242,0.00006831957,0.7842979,0.000006053815,0.00002191164,0.00355683,0.07560063,0.04004113],"study_design_scores_gemma":[0.001375501,0.001759883,0.2476159,0.0001306442,0.001009149,0.00002099818,0.593662,0.00005460418,0.000001907909,0.002600492,0.1515521,0.0002168131],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9750037,0.001865637,0.006206732,0.002184367,0.001560434,0.0003396862,0.00002563374,0.000006502562,0.01280737],"genre_scores_gemma":[0.9979897,0.00004270098,0.0002052731,0.00012427,0.001490169,0.000004688813,0.000003719062,0.000005044021,0.0001344982],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1906359,"threshold_uncertainty_score":0.4026415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.124700867661771,"score_gpt":0.3935506063984692,"score_spread":0.2688497387366982,"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."}}