{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001372534,0.00007910096,0.0001469906,0.0003871003,0.0003911293,0.0003050638,0.000532549,0.00002322592,0.00002003873],"category_scores_gemma":[0.0004035665,0.00007236873,0.00007495679,0.0003836616,0.00001233926,0.003762683,0.0001184186,0.0001453417,0.0000031133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001273232,"about_ca_system_score_gemma":0.000261686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.180123e-7,"about_ca_topic_score_gemma":1.865474e-9,"domain_scores_codex":[0.9987886,0.00004227799,0.000596447,0.0000549298,0.0003892084,0.000128514],"domain_scores_gemma":[0.9982639,0.0001609919,0.001038398,0.0001216419,0.0003693256,0.0000457583],"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":[0.00006167477,0.00009563615,0.0000783818,0.0002516328,0.00002908659,0.000005456703,0.005789625,0.1650135,0.0002085344,0.0004897791,0.06346024,0.7645165],"study_design_scores_gemma":[0.0004455329,0.0002588845,0.00003398982,0.00007432785,0.00001047296,0.000255722,0.00006484507,0.9913046,0.0004994277,0.005424316,0.001523454,0.0001043752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005405689,0.00005556586,0.992204,0.0007792015,0.0001921304,0.0001361708,0.000001700993,0.001001694,0.0002238584],"genre_scores_gemma":[0.1298629,0.000001683576,0.8696832,0.000367255,0.00003034154,0.00002408543,0.000006254357,0.000005146414,0.00001913275],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8262911,"threshold_uncertainty_score":0.300829,"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."}}