{"id":"W4320020468","doi":"10.22148/001c.57764","title":"Theory-Driven Statistics for the Digital Humanities: Presenting Pitfalls and a Practical Guide by the Example of the Reformation","year":2023,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Data Analysis with R","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Credibility; Test (biology); Digital humanities; Statistical hypothesis testing; Bridge (graph theory); Protestantism; Logistic regression; Psychology; Data science; Computer science; Epistemology; Sociology; Political science; Statistics; Mathematics; Philosophy; Library science; Machine learning; Law","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00109689,0.00009091635,0.0001675441,0.00004073494,0.0003030867,0.0005903346,0.0007734401,0.00002509136,0.000002606635],"category_scores_gemma":[0.001322743,0.0000335173,0.0001208716,0.0003494263,0.0001496267,0.001017493,0.000309857,0.000178757,0.000002046769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003017134,"about_ca_system_score_gemma":0.00005851512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002250974,"about_ca_topic_score_gemma":0.00001846846,"domain_scores_codex":[0.9986001,0.0000981947,0.0005416098,0.00008780719,0.0005128516,0.0001593854],"domain_scores_gemma":[0.9970455,0.001358344,0.0007801916,0.0003144228,0.0004687303,0.00003283931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004187014,0.0000923163,0.001253985,0.00008898859,0.001177312,0.00001200459,0.01391767,0.00390124,0.0005530226,0.3678944,0.6001877,0.01087956],"study_design_scores_gemma":[0.000674113,0.0002111994,0.00455327,0.00008564604,0.0006743566,0.0003024296,0.01143233,0.7311493,0.0004541889,0.02986357,0.2203587,0.0002408826],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04303492,0.0001883911,0.9413465,0.0137474,0.0003556176,0.0004066337,0.0002647705,0.0000274893,0.0006282443],"genre_scores_gemma":[0.9784455,0.000281515,0.01474481,0.0006389774,0.0003338495,0.000006391003,0.00003406791,0.00001642726,0.005498432],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9354106,"threshold_uncertainty_score":0.5692611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05892745187518311,"score_gpt":0.3221062691223329,"score_spread":0.2631788172471498,"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."}}