{"id":"W4401282765","doi":"10.1007/978-3-031-66997-2_3","title":"Using General Large Language Models to Classify Mathematical Documents","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Mathematics, Computing, and Information Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Information retrieval; Programming language","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001173865,0.0005633803,0.0005952229,0.001066387,0.0002967824,0.001750893,0.002777642,0.0002748546,0.00005498519],"category_scores_gemma":[0.00005365369,0.0004912883,0.0001548341,0.0006929216,0.000178553,0.001396965,0.002502742,0.0007119684,0.000273071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003816653,"about_ca_system_score_gemma":0.0004216073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007268265,"about_ca_topic_score_gemma":0.000006918105,"domain_scores_codex":[0.9958399,0.00001815809,0.0008925809,0.001132291,0.001267858,0.0008492023],"domain_scores_gemma":[0.9978809,0.0001608234,0.0002929547,0.001178937,0.0002070526,0.0002793191],"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":[0.000001982621,0.00004184251,0.000001358821,0.000468233,0.00002173085,0.00008799491,0.01510768,0.1269057,0.0001096854,0.7497887,0.00009398544,0.1073711],"study_design_scores_gemma":[0.00008143183,0.00002343738,2.903161e-7,0.0006229853,0.000006240673,0.00005888352,0.000001053895,0.6051819,0.0002444301,0.3930483,0.0003851163,0.0003460068],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002054197,0.0002571958,0.9713448,0.0002814297,0.001301781,0.0003852523,0.000006223107,0.0002947899,0.02592307],"genre_scores_gemma":[0.03512627,0.000006575604,0.9594113,0.002375666,0.0005277959,0.000006960871,0.000003892641,0.0000524982,0.002489101],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4782762,"threshold_uncertainty_score":0.9997539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03733455946854739,"score_gpt":0.302462580135229,"score_spread":0.2651280206666816,"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."}}