{"id":"W4404514810","doi":"10.1145/3689944.3696162","title":"BinEq - A Benchmark of Compiled Java Programs to Assess Alternative Builds","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Java; Benchmark (surveying); Programming language; Software engineering; Operating system; Geography; Cartography","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":[0.0004442084,0.0001170995,0.0001861065,0.0002359345,0.00005004452,0.00008755173,0.0009558942,0.00003793319,0.000008801628],"category_scores_gemma":[0.0002374133,0.0000976955,0.00005370728,0.001441975,0.00003241951,0.0001369766,0.0005143299,0.00007497561,0.00006125811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000205176,"about_ca_system_score_gemma":0.00004172198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003135547,"about_ca_topic_score_gemma":0.000007830027,"domain_scores_codex":[0.9988311,0.00004753901,0.0002205947,0.0003271986,0.0003119574,0.0002616251],"domain_scores_gemma":[0.9988116,0.0003216872,0.00007230919,0.0005325477,0.0001635563,0.00009830223],"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":[0.00001994058,0.0004943468,0.1178301,0.000108954,0.00009919903,0.0001129773,0.003096222,0.0003627865,0.001974968,0.0979443,0.3295534,0.4484028],"study_design_scores_gemma":[0.001144676,0.002743389,0.08343832,0.0007849112,0.00002419194,0.00005606725,0.00006666634,0.5388699,0.04587035,0.3141125,0.01136758,0.001521572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08257225,0.000008348736,0.8923448,0.0009108861,0.0002884861,0.0003734319,0.000002430947,0.018816,0.004683382],"genre_scores_gemma":[0.5739671,0.000001509162,0.4254395,0.000210123,0.0000281022,0.000049542,0.000004703055,0.000007782233,0.0002916859],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.538507,"threshold_uncertainty_score":0.3983907,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1024521892520282,"score_gpt":0.3377391067043839,"score_spread":0.2352869174523557,"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."}}