{"id":"W4399061142","doi":"10.1145/3663529.3663787","title":"On Polyglot Program Testing","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Polyglot; Computer science; Programming language","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":[0.0001691778,0.00007634931,0.00005186807,0.00009164226,0.00005309535,0.0003870739,0.0003563314,0.00002564256,0.000006178237],"category_scores_gemma":[0.0003624459,0.00005741829,0.00002571146,0.0005322036,0.00001410692,0.0001279819,0.0001014508,0.00009990131,0.0001643737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001790919,"about_ca_system_score_gemma":0.00003834056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004150711,"about_ca_topic_score_gemma":3.064085e-7,"domain_scores_codex":[0.9993341,0.00001262063,0.00008228583,0.0002667387,0.000136331,0.0001679196],"domain_scores_gemma":[0.9990124,0.000605127,0.000008827987,0.0003046835,0.00002567128,0.00004325465],"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":[1.912176e-7,0.00002457003,0.0001502818,0.000009179953,0.000002137253,0.00003093766,0.00003122939,0.000003916623,0.00001485936,0.1077463,0.041377,0.8506094],"study_design_scores_gemma":[0.00003269294,0.0004236988,0.0007083385,0.0002328369,0.000002200349,0.00007583864,5.16215e-7,0.6156969,0.0008032051,0.3753782,0.006444263,0.0002013155],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003165671,0.0001437039,0.7056999,0.001058064,0.000416181,0.0001709497,2.858626e-7,0.2182638,0.07108137],"genre_scores_gemma":[0.4347162,2.74295e-7,0.5644736,0.0003193946,0.00003551762,0.00002336527,1.950653e-7,0.00000633226,0.0004250746],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8504081,"threshold_uncertainty_score":0.3732563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04053516960178625,"score_gpt":0.3158553354438702,"score_spread":0.2753201658420839,"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."}}