{"id":"W4318541608","doi":"10.1145/3575693.3575740","title":"Compilation Consistency Modulo Debug Information","year":2023,"lang":"en","type":"article","venue":"","topic":"Security and Verification in Computing","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Debugger; Debugging; Compiler; Background debug mode interface; Programming language; Consistency (knowledge bases); Kernel (algebra); Operating system; Artificial intelligence; Mathematics","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":[0.007858938,0.0009874019,0.001122909,0.00145918,0.002068238,0.004519265,0.002382531,0.001478298,0.008456647],"category_scores_gemma":[0.04291907,0.001313092,0.001482602,0.001226929,0.003777146,0.01126502,0.008019452,0.004996717,0.002828734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001426545,"about_ca_system_score_gemma":0.004670118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002471478,"about_ca_topic_score_gemma":0.002145464,"domain_scores_codex":[0.9863804,0.003181123,0.001550626,0.003014707,0.004049811,0.001823439],"domain_scores_gemma":[0.9499929,0.01604106,0.00260519,0.02211728,0.008419826,0.0008237289],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001157829,0.0002208318,0.01171915,0.001099911,0.0002006212,0.001475623,0.002501499,0.02639442,0.02321373,0.6970785,0.04605102,0.188887],"study_design_scores_gemma":[0.0002658658,0.000230699,0.002692741,0.0003768788,0.0002784927,0.001536526,0.0004374592,0.05003351,0.06552062,0.7586014,0.1198362,0.0001895318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07847057,0.001437847,0.8260774,0.0041935,0.001419485,0.0003964095,0.00244019,0.02285896,0.06270558],"genre_scores_gemma":[0.7185247,0.0008973711,0.238762,0.003439069,0.0009230715,0.0006663257,0.003950489,0.01052225,0.02231465],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008456647,"threshold_uncertainty_score":0.0415625,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02617515102354573,"score_gpt":0.2511043353250854,"score_spread":0.2249291843015396,"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."}}