{"id":"W4390833146","doi":"10.48550/arxiv.2401.05673","title":"Analyzing and Debugging Normative Requirements via Satisfiability Checking","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Safety Systems Engineering in Autonomy","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Royal Academy of Engineering; UK Research and Innovation","keywords":"Debugging; Computer science; Software engineering; Usability; Sociotechnical system; Normative; Redundancy (engineering); Workaround; USable; Underpinning; Human–computer interaction; Artificial intelligence; Programming language; Engineering; World Wide Web","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003557978,0.0004653598,0.0004728145,0.0003812189,0.00008270231,0.00009877078,0.0003462004,0.0002975357,0.00002624712],"category_scores_gemma":[0.00002695076,0.0005937738,0.0001558824,0.0004202529,0.00007308036,0.0001522177,0.0009152136,0.0009119001,0.00006647797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008352204,"about_ca_system_score_gemma":0.00005133059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001142819,"about_ca_topic_score_gemma":0.00002517429,"domain_scores_codex":[0.9983879,0.00005619059,0.0003573788,0.0007202092,0.00007584587,0.0004024205],"domain_scores_gemma":[0.9989687,0.00009763669,0.00009038101,0.0006352889,0.00005651969,0.0001514378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004965024,0.000008359037,0.006019074,0.001988192,0.0005349268,0.000106212,0.0006678884,0.9867172,0.0004627867,0.001948806,0.00005895194,0.001482663],"study_design_scores_gemma":[0.000189998,0.000008411236,0.003174544,0.0007120532,0.000209648,0.000007551069,0.00008243302,0.9870977,0.0002603921,0.007385077,0.0002614691,0.0006107605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7402475,0.001113678,0.2500004,0.00001797183,0.001581168,0.0004922871,0.00003600307,0.001529207,0.004981725],"genre_scores_gemma":[0.9988066,0.0001127685,0.0007422437,0.000005536505,0.0001126194,0.000003620302,0.0000147691,0.00008498096,0.0001168676],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2585591,"threshold_uncertainty_score":0.9996514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04071649257143994,"score_gpt":0.1780856331593179,"score_spread":0.137369140587878,"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."}}