{"id":"W4383371856","doi":"10.1016/j.cola.2023.101223","title":"Model consistency as a heuristic for eventual correctness","year":2023,"lang":"en","type":"article","venue":"Journal of Computer Languages","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Correctness; Computer science; Consistency (knowledge bases); Assertion; Heuristics; Intuition; Theoretical computer science; Programming language; Artificial intelligence; Cognitive science; Psychology","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":[0.0004681689,0.0001482637,0.0002981194,0.0003044991,0.00005696945,0.00009825208,0.0008808628,0.00006146082,0.000002458657],"category_scores_gemma":[0.00003369014,0.0001292512,0.000181497,0.0002894937,0.00002440152,0.0002846585,0.0001960875,0.0001649962,0.00001209812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004027611,"about_ca_system_score_gemma":0.0001343526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002837897,"about_ca_topic_score_gemma":5.729453e-7,"domain_scores_codex":[0.998823,0.00003644779,0.0003939829,0.0001795909,0.0003157229,0.0002512508],"domain_scores_gemma":[0.9988371,0.000234794,0.0002208694,0.0003221374,0.0002777509,0.0001073815],"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":[0.00005679151,0.0002041795,0.0002099246,0.0002416398,0.0002248636,0.0009001466,0.006246411,0.2203232,0.0009908563,0.254163,0.09378198,0.422657],"study_design_scores_gemma":[0.000372037,0.0002974034,0.0002086358,0.0001228302,0.0000151576,0.0003568137,0.00001155076,0.9869097,0.0005529185,0.006397448,0.004575168,0.0001802823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01880287,0.0001700374,0.9793392,0.0003598653,0.0007002504,0.0001375829,0.000004729591,0.0004428389,0.00004260943],"genre_scores_gemma":[0.2721649,0.0000225641,0.7270965,0.0001924676,0.000272967,0.00001057445,0.000002039637,0.00001933585,0.0002186714],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7665866,"threshold_uncertainty_score":0.5270712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02117095997389035,"score_gpt":0.2961003219863029,"score_spread":0.2749293620124125,"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."}}