{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01077486,0.001247945,0.0009963191,0.002865188,0.001396899,0.005795697,0.002861403,0.002173507,0.0252911],"category_scores_gemma":[0.06622028,0.001302802,0.002392659,0.001536325,0.005109966,0.009544941,0.007533795,0.004853132,0.006094528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002032198,"about_ca_system_score_gemma":0.002735952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00145942,"about_ca_topic_score_gemma":0.002397383,"domain_scores_codex":[0.9855278,0.006371823,0.0006758031,0.001573168,0.005051923,0.000799525],"domain_scores_gemma":[0.9342391,0.0512595,0.001659135,0.00774374,0.004611946,0.000486542],"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":[0.0002709655,0.0001945193,0.001840483,0.0003998508,0.0001144636,0.0003963046,0.0008618365,0.02353736,0.003127409,0.8157981,0.01396798,0.1394907],"study_design_scores_gemma":[0.00003801054,0.00003905078,0.0002108203,0.0002053447,0.00004863579,0.00009984653,0.0003132994,0.06878573,0.006247652,0.9024617,0.02152457,0.00002539574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01754016,0.0003410387,0.9123054,0.00259534,0.0003617599,0.0001901632,0.0006760962,0.004254274,0.06173578],"genre_scores_gemma":[0.3939669,0.0004754713,0.5782804,0.001159332,0.0002610804,0.0002721088,0.002331157,0.001781537,0.02147206],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0252911,"threshold_uncertainty_score":0.08460718,"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."}}