{"id":"W4400680658","doi":"10.1109/saner60148.2024.00073","title":"Exploring Strategies for Guiding Symbolic Analysis with Machine Learning Prediction","year":2024,"lang":"en","type":"article","venue":"","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence","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":[0.0002484264,0.0000500813,0.00007012696,0.00008370836,0.0003974,0.0002534852,0.00004409339,0.00002277546,0.0001476713],"category_scores_gemma":[0.00002469055,0.00003241761,0.0000632699,0.0006549927,0.00002478928,0.0008789712,0.000006085181,0.00004158277,0.000006675829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005559998,"about_ca_system_score_gemma":0.00004709171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00391173,"about_ca_topic_score_gemma":0.005980862,"domain_scores_codex":[0.9994712,0.00003215816,0.0000735764,0.0001333679,0.0001459918,0.000143665],"domain_scores_gemma":[0.9998394,0.000037682,0.00001366086,0.00003469576,0.0000418736,0.00003273707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00005376105,0.00003227024,0.01169043,0.0001397505,0.00169138,0.00001647235,0.2613764,0.02407334,0.00434043,0.6447006,0.0007722432,0.05111295],"study_design_scores_gemma":[0.0004093832,0.0003522901,0.005394106,0.0001796952,0.002228985,0.000003580986,0.6539079,0.168247,0.0008450063,0.003203456,0.1646241,0.0006044569],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8675542,0.001322235,0.06530502,0.0007896821,0.0002730426,0.0002788694,0.000008125208,0.001041173,0.06342762],"genre_scores_gemma":[0.994846,0.000135372,0.0003710195,0.00001093958,0.0002739222,0.00004687958,0.00002409671,0.000004778229,0.004286934],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6414971,"threshold_uncertainty_score":0.5913392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1188347034996133,"score_gpt":0.3150860572539407,"score_spread":0.1962513537543274,"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."}}