{"id":"W4412462026","doi":"10.1017/dap.2025.10005","title":"Tracing institutional change in the officer corps using textual data from a military school: promise, pitfalls, and ethical considerations","year":2025,"lang":"en","type":"article","venue":"Data & Policy","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Department of National Defence","funders":"","keywords":"Officer; Tracing; Engineering ethics; Political science; Engineering; Law; Computer science","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":[0.001800956,0.00008342742,0.0001407094,0.0001668344,0.000727151,0.0001375864,0.0006660292,0.000107234,0.0001089631],"category_scores_gemma":[0.003885789,0.00006827257,0.00001800103,0.0005986186,0.0003741182,0.0004713117,0.0005276053,0.0003488729,0.000006371314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006110003,"about_ca_system_score_gemma":0.001410677,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1720931,"about_ca_topic_score_gemma":0.1111428,"domain_scores_codex":[0.998228,0.0007051624,0.0002321648,0.0003743992,0.0002905605,0.0001697079],"domain_scores_gemma":[0.9980084,0.001258098,0.00003863755,0.0005795262,0.00005105183,0.00006424744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00003515739,0.0002233999,0.01135942,0.00002482569,0.0001572822,0.00003222068,0.01918874,0.0001731593,0.00008281565,0.9235928,0.01558642,0.02954379],"study_design_scores_gemma":[0.001334226,0.00001735222,0.4217957,0.0002491076,0.0003191996,0.00001474363,0.009416266,0.2864546,0.000003145603,0.1632083,0.1166644,0.0005228957],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6709614,0.006120556,0.01925555,0.27633,0.0004252424,0.001651291,0.01411471,0.0001261231,0.01101505],"genre_scores_gemma":[0.9725152,0.0001045878,0.01337657,0.01037679,0.0008464548,0.00001040064,0.002737684,0.000003415313,0.00002884936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7603844,"threshold_uncertainty_score":0.9050766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3016082156529764,"score_gpt":0.488675662911369,"score_spread":0.1870674472583926,"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."}}