{"id":"W4403935722","doi":"10.1145/3652620.3687807","title":"Multi-step Iterative Automated Domain Modeling with Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Mitacs","keywords":"Computer science; Domain (mathematical analysis); Modeling language; Programming language; Software; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003194892,0.002218061,0.001249982,0.002966858,0.0009397138,0.00277989,0.003631158,0.001382202,0.004395714],"category_scores_gemma":[0.01088331,0.001104902,0.003904413,0.001876696,0.0008175833,0.004381361,0.004548786,0.002881444,0.00311501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001742578,"about_ca_system_score_gemma":0.003299255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006827815,"about_ca_topic_score_gemma":0.01567559,"domain_scores_codex":[0.9958621,0.00157596,0.0003232071,0.0008998883,0.001157736,0.0001809628],"domain_scores_gemma":[0.9922059,0.004516276,0.000422313,0.001761839,0.000917927,0.0001757281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002941503,0.0007178242,0.004136529,0.001199602,0.0003216937,0.0009196051,0.001882516,0.1241509,0.02506336,0.02661953,0.02171173,0.7929826],"study_design_scores_gemma":[0.00007218474,0.00008511778,0.0005443009,0.00007479493,0.000082779,0.0003214166,0.0004226378,0.9359236,0.01367725,0.0277944,0.02094723,0.00005425787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007125612,0.0002412617,0.9755083,0.0002512156,0.00002259914,0.0003416287,0.00053771,0.01485661,0.001115016],"genre_scores_gemma":[0.05633166,0.0002062043,0.9371024,0.0002136148,0.00001537406,0.0004414764,0.003385804,0.0008075561,0.00149586],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006827815,"threshold_uncertainty_score":0.01689643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02422182949653289,"score_gpt":0.2824591520901971,"score_spread":0.2582373225936642,"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."}}