{"id":"W4402391272","doi":"10.23889/ijpds.v9i5.2864","title":"Exploring Text Classification Systems for Automatically Coding Historical Occupations and Causes of Death","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Economic and Social Research Council","keywords":"Coding (social sciences); Computer science; Natural language processing; Information retrieval; Data science; Sociology; Social science","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":[],"consensus_categories":[],"category_scores_codex":[0.003123297,0.00006393321,0.0001168582,0.0004569476,0.000642177,0.0006253299,0.0006227663,0.00002509375,0.000008207904],"category_scores_gemma":[0.00261095,0.00005776864,0.00005289818,0.0003904547,0.0001104509,0.002584737,0.00007810712,0.00006415601,0.000001007108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004754678,"about_ca_system_score_gemma":0.0003343205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006655654,"about_ca_topic_score_gemma":0.00009188284,"domain_scores_codex":[0.9982973,0.00006219299,0.0004495347,0.0002623353,0.0007873492,0.0001412287],"domain_scores_gemma":[0.9978114,0.0009616854,0.0001921232,0.0001200762,0.0008163378,0.00009838619],"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":[0.0000212545,0.00003635129,0.007637703,0.00003983831,0.00006253314,0.000001048054,0.00120089,0.001159828,0.0007074776,0.9342743,0.0006913895,0.05416742],"study_design_scores_gemma":[0.000177746,0.00003501042,0.05760539,0.0001772348,0.00006889058,0.00001696308,0.0007117391,0.8649659,0.00002005303,0.01619862,0.05988154,0.0001409375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08246567,0.0004025295,0.9080558,0.002887378,0.005378975,0.0003234674,0.0001834764,0.00005947498,0.0002432432],"genre_scores_gemma":[0.9729191,0.0002411824,0.02591188,0.00001302507,0.0006058129,0.00002708201,0.00008749712,0.000005845141,0.0001885847],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9180757,"threshold_uncertainty_score":0.6030071,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5370092133463087,"score_gpt":0.5151466273038554,"score_spread":0.02186258604245328,"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."}}