{"id":"W4319150617","doi":"10.1145/3526072.3527531","title":"AmbieGen tool at the SBST 2022 tool competition","year":2022,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Context (archaeology); Competition (biology); Test (biology); Computer science; Reliability engineering; Simulation; 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":[0.00335218,0.002640295,0.0007921053,0.003056145,0.0004666339,0.001580851,0.002474256,0.001398817,0.02676683],"category_scores_gemma":[0.0111469,0.0006646123,0.001481516,0.001206307,0.0005853645,0.001046361,0.001940798,0.001866174,0.007179057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006523908,"about_ca_system_score_gemma":0.001690191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003341187,"about_ca_topic_score_gemma":0.003723023,"domain_scores_codex":[0.997141,0.000979293,0.0001632753,0.0003202649,0.001136734,0.0002593849],"domain_scores_gemma":[0.9950368,0.002843416,0.0002149511,0.0006417914,0.0010667,0.0001963768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001223091,0.0009880395,0.006677868,0.001985957,0.0004359994,0.001149305,0.0003929344,0.2633659,0.01555036,0.02402689,0.2302651,0.4539385],"study_design_scores_gemma":[0.0008960871,0.001115588,0.003932288,0.0005093551,0.0001509049,0.0008255744,0.0001774694,0.7085005,0.03238185,0.02203523,0.229309,0.0001662059],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06800251,0.001408626,0.6991726,0.0008421697,0.0009328565,0.001440487,0.01470387,0.1527706,0.06072624],"genre_scores_gemma":[0.3119304,0.0005571462,0.5582268,0.000720207,0.00008983715,0.002453621,0.08133043,0.02281506,0.02187643],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02676683,"threshold_uncertainty_score":0.089544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004407132927205286,"score_gpt":0.1721165674259611,"score_spread":0.1677094344987558,"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."}}