{"id":"W4206207168","doi":"10.1007/978-3-030-92124-8_2","title":"Validating Safety Arguments with Lean","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Safety Systems Engineering in Autonomy","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Leverage (statistics); Automated theorem proving; Lean manufacturing; Software engineering; Gas meter prover; Programming language; Artificial intelligence; Mathematical proof; Manufacturing engineering; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003415438,0.0004926939,0.0004896725,0.0003607682,0.00009150018,0.0001551212,0.0007243769,0.0002199368,0.00006186507],"category_scores_gemma":[0.00002475914,0.0004695768,0.00006970132,0.0003308849,0.0001698371,0.0001679381,0.0002140951,0.0007109037,0.00003280899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006332304,"about_ca_system_score_gemma":0.0001674282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006190961,"about_ca_topic_score_gemma":0.00002129588,"domain_scores_codex":[0.9977777,0.000006945318,0.0004340435,0.0007017488,0.0005677299,0.0005118246],"domain_scores_gemma":[0.9987515,0.0001921936,0.00008107755,0.0007744893,0.00008829224,0.0001124637],"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":[0.000001550028,0.000003101687,0.00005096965,0.0001204735,0.000029792,0.00007828348,0.0001955476,0.9224467,0.0001765962,0.001015522,0.000006093045,0.07587542],"study_design_scores_gemma":[0.000546447,0.00008985593,0.0002025005,0.003368481,0.00002861209,0.0002682308,7.020583e-7,0.972409,0.00566461,0.002544992,0.01322437,0.00165224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001944058,0.0004860985,0.9822695,0.00003344695,0.001689287,0.0002556885,0.000006905982,0.0003958184,0.01466884],"genre_scores_gemma":[0.5508597,0.00007029065,0.4456982,0.0002690058,0.001327854,0.00002423628,0.00004681489,0.0003347771,0.001369113],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5506653,"threshold_uncertainty_score":0.9997756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009532352927065292,"score_gpt":0.1992087816333465,"score_spread":0.1896764287062812,"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."}}