{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002578969,0.0001728446,0.000149597,0.0001289287,0.00009142308,0.00042694,0.0004550624,0.00005903711,0.00002079233],"category_scores_gemma":[0.000004159365,0.0001226468,0.0000461565,0.0003326053,0.00001076455,0.001010933,0.0002012216,0.0001655466,0.00006075455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005187052,"about_ca_system_score_gemma":0.00007572334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001041098,"about_ca_topic_score_gemma":0.0001022075,"domain_scores_codex":[0.9986007,0.00004814733,0.0002005225,0.000542768,0.0002557505,0.0003520987],"domain_scores_gemma":[0.9993281,0.00003415579,0.00001820152,0.0004809129,0.00005352568,0.0000851433],"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":[0.000005131706,0.00006590825,0.000007618432,0.00005745724,0.00006472617,0.0003340535,0.02280643,0.4839374,0.001279367,0.4869599,0.0002457678,0.004236263],"study_design_scores_gemma":[0.0003060168,0.00002188682,9.261541e-7,0.00008229286,0.000004105802,0.00002588376,0.0004928445,0.9974252,0.000137533,0.001225134,0.00008518597,0.0001930144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02557901,0.0003820851,0.9663934,0.000349101,0.0001469552,0.0001688152,0.000004886815,0.003168496,0.003807305],"genre_scores_gemma":[0.5298046,0.000001556793,0.4692585,0.0001723494,0.00002652397,0.00001252689,0.000002493563,0.0000118056,0.0007096333],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5134878,"threshold_uncertainty_score":0.5001391,"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."}}