{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01390309,0.0006851031,0.001091392,0.009476112,0.002060998,0.006618198,0.003656475,0.002085701,0.001640121],"category_scores_gemma":[0.0419899,0.0008308578,0.001709775,0.008170858,0.004766228,0.01194413,0.003890372,0.002333399,0.0005721552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002061581,"about_ca_system_score_gemma":0.003962697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005096863,"about_ca_topic_score_gemma":0.008244184,"domain_scores_codex":[0.9923078,0.004762702,0.0005637589,0.001133036,0.001071629,0.0001610127],"domain_scores_gemma":[0.9349718,0.05580135,0.002469856,0.004367623,0.001692471,0.0006968648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001860787,0.0006328508,0.03241539,0.001927558,0.0004636096,0.0008660603,0.01445977,0.04784452,0.002504122,0.4691202,0.009642643,0.4199372],"study_design_scores_gemma":[0.00002897912,0.00005113171,0.003587082,0.0004112572,0.00007110813,0.0003019943,0.002842905,0.2459813,0.002149476,0.7218283,0.02267632,0.00007018732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05992879,0.004234287,0.9193732,0.01015656,0.0001204366,0.0003820919,0.001033411,0.0004518792,0.004319407],"genre_scores_gemma":[0.2624412,0.002909687,0.7296272,0.0006167408,0.0002858176,0.0005644921,0.001206351,0.0001125842,0.002235849],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01390309,"threshold_uncertainty_score":0.0735274,"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."}}