{"id":"W2994711059","doi":"10.1002/stvr.1721","title":"Leveraging metamorphic testing to automatically detect inconsistencies in code generator families","year":2019,"lang":"en","type":"article","venue":"Software Testing Verification and Reliability","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Software quality; Oracle; Software; Leverage (statistics); Regression testing; Code (set theory); Code coverage; Unreachable code; Software development; Code generation; Programming language; Redundant code; Software construction; Set (abstract data type); Operating system; Artificial intelligence","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002001292,0.0002723082,0.0003881939,0.0002713242,0.0002233855,0.0002329327,0.0006089333,0.0001229892,0.000003856164],"category_scores_gemma":[0.02494671,0.0002525929,0.00004626013,0.001487493,0.0001059209,0.000327642,0.0003531842,0.0003040622,0.00004518104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001458521,"about_ca_system_score_gemma":0.0002463042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004311439,"about_ca_topic_score_gemma":0.00001188851,"domain_scores_codex":[0.997443,0.0002155186,0.0006381865,0.0009389655,0.0003471924,0.0004171457],"domain_scores_gemma":[0.9947007,0.003336112,0.0001974934,0.001136562,0.0004458889,0.0001832364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007048522,0.00007850052,0.88073,0.0002335309,0.000006837165,0.000006950198,0.001243892,0.001569211,0.003856068,0.0002216704,0.0002358661,0.1118104],"study_design_scores_gemma":[0.0003309694,0.000237423,0.7676047,0.0004172467,0.00001266913,0.00004986554,0.00004680414,0.2091079,0.001236007,0.02008365,0.0002381691,0.0006346508],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7547442,0.00008471105,0.2352684,0.0003811302,0.0001679172,0.0005106825,0.00000302064,0.008630551,0.0002093776],"genre_scores_gemma":[0.5078698,0.000001461708,0.4917551,0.0002826804,0.00001312113,0.00004517073,0.000001230338,0.00001221928,0.00001920475],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2564867,"threshold_uncertainty_score":0.9999926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03641849049665075,"score_gpt":0.2574023251371866,"score_spread":0.2209838346405358,"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."}}