{"id":"W4213240734","doi":"10.2197/ipsjjip.30.155","title":"Automatic Optimize-time Validation for Binary Optimizers","year":2022,"lang":"en","type":"article","venue":"Journal of Information Processing","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Computer science; Binary number; Compatibility (geochemistry); Code (set theory); Binary code; Code coverage; Program optimization; Source code; Dead code; Redundant code; Programming language; Code generation; Set (abstract data type); Operating system; Software; Arithmetic","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":[0.004561274,0.002026228,0.001181074,0.002149395,0.0007700238,0.001895122,0.002899928,0.001300298,0.004225542],"category_scores_gemma":[0.02437568,0.001434847,0.00156026,0.000952537,0.00134378,0.003546176,0.00228335,0.002111157,0.001696758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001348057,"about_ca_system_score_gemma":0.002473033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002176536,"about_ca_topic_score_gemma":0.00234322,"domain_scores_codex":[0.9882141,0.003520744,0.001065622,0.001593609,0.004585607,0.001020235],"domain_scores_gemma":[0.9696978,0.01044701,0.004186561,0.01005933,0.005208204,0.0004011446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00353832,0.0009416516,0.03437649,0.001406629,0.0004174531,0.0008403498,0.001027507,0.06402336,0.2238345,0.02056714,0.02436932,0.6246573],"study_design_scores_gemma":[0.0003009955,0.0008796665,0.009010457,0.0002365697,0.000231804,0.0007847724,0.0001226845,0.5781445,0.3698395,0.01208596,0.02807302,0.0002899682],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08296435,0.0005748293,0.8142666,0.0003408225,0.0002129387,0.0004091627,0.0004498844,0.09664445,0.004136993],"genre_scores_gemma":[0.5144867,0.0001879837,0.4656629,0.0005835468,0.00009211758,0.0005038165,0.001728354,0.01279177,0.003962812],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004561274,"threshold_uncertainty_score":0.0241226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01353373715607724,"score_gpt":0.2568205463823833,"score_spread":0.243286809226306,"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."}}