{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01505408,0.001058207,0.001743086,0.0035039,0.002920154,0.003954797,0.004128224,0.002669991,0.007084384],"category_scores_gemma":[0.1044309,0.001770999,0.00340268,0.002074528,0.004951473,0.01033326,0.007297263,0.006681955,0.0007621842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002196276,"about_ca_system_score_gemma":0.00413935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00175511,"about_ca_topic_score_gemma":0.00335752,"domain_scores_codex":[0.9820742,0.008854955,0.001065359,0.001948595,0.004696113,0.001360729],"domain_scores_gemma":[0.8925902,0.07769182,0.002426331,0.01960009,0.006425959,0.001265643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001285398,0.0006695865,0.0108869,0.0006979504,0.0003464109,0.0007728109,0.001288696,0.1478646,0.00623122,0.680572,0.007770889,0.1416136],"study_design_scores_gemma":[0.0001207533,0.0002061137,0.0004789463,0.0001224042,0.0002066792,0.0002594336,0.000310658,0.4911818,0.009867196,0.4942693,0.002921962,0.00005482426],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04099009,0.0001579042,0.9504751,0.00127841,0.0001337621,0.0002173183,0.0001083306,0.001671633,0.004967432],"genre_scores_gemma":[0.5864574,0.00008663375,0.410265,0.0004092775,0.00007987944,0.0001880393,0.0002817057,0.000681517,0.001550557],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01505408,"threshold_uncertainty_score":0.07961452,"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."}}