{"id":"W4401340787","doi":"10.1017/s0003055424000716","title":"Improving Probabilistic Models In Text Classification Via Active Learning","year":2024,"lang":"en","type":"article","venue":"American Political Science Review","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Probabilistic logic; Computer science; Artificial intelligence; Machine learning; Active learning (machine learning)","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":[0.0124189,0.001952449,0.00231292,0.004124125,0.001293087,0.004002045,0.004840783,0.00367309,0.00211393],"category_scores_gemma":[0.03643945,0.001255774,0.002333747,0.004024054,0.002268812,0.00986562,0.002895389,0.005844644,0.001731423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00169967,"about_ca_system_score_gemma":0.001287508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003023472,"about_ca_topic_score_gemma":0.003339045,"domain_scores_codex":[0.9936249,0.003513157,0.0003229778,0.001131088,0.001169537,0.0002382471],"domain_scores_gemma":[0.9594457,0.03439226,0.001494199,0.001990162,0.002377112,0.0003005062],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002447686,0.0004423134,0.003429341,0.0005089668,0.0003228534,0.0001066049,0.0004839759,0.5134125,0.002464269,0.05263698,0.009784319,0.4161632],"study_design_scores_gemma":[0.00001703552,0.00001653662,0.0001060099,0.00001923802,0.00001688207,0.00001293606,0.00001088731,0.9717733,0.0005122487,0.02672327,0.0007810074,0.00001048203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005632955,0.001292623,0.9903882,0.0008349752,0.0001202189,0.00006312302,0.00008591839,0.0007452183,0.0008368035],"genre_scores_gemma":[0.3455737,0.002865253,0.642529,0.001239965,0.001528004,0.0008252331,0.001206215,0.0004378821,0.003794751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0124189,"threshold_uncertainty_score":0.06567818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03848909323123417,"score_gpt":0.328479701192705,"score_spread":0.2899906079614708,"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."}}