{"id":"W4385301350","doi":"10.1109/sbft59156.2023.00011","title":"RIGAA at the SBFT 2023 Tool Competition - Cyber-Physical Systems Track","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Context (archaeology); Track (disk drive); Competition (biology); Reinforcement learning; Cyber-physical system; Artificial intelligence; Operating system; Geology; Ecology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004801143,0.0001163293,0.0001322662,0.00006188053,0.0002588051,0.0002180713,0.0006480635,0.00004149275,0.00001756273],"category_scores_gemma":[0.0001286337,0.00007464168,0.00007099768,0.000623266,0.00005749906,0.0001648248,0.000346301,0.0001145166,0.00169278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004744055,"about_ca_system_score_gemma":0.00002278424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002271299,"about_ca_topic_score_gemma":0.00001294087,"domain_scores_codex":[0.998856,0.00009445882,0.0001564744,0.0003113655,0.0003210809,0.0002606319],"domain_scores_gemma":[0.9983497,0.0008185885,0.00005143347,0.0006813928,0.0000544257,0.000044423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002891545,0.00006804142,0.001041983,0.00003414002,0.00001558549,0.00003494125,0.0004889318,0.0004286761,0.0006258832,0.1656657,0.8215784,0.01001479],"study_design_scores_gemma":[0.0002896146,0.0002294966,0.0169569,0.0001709186,0.00001392923,0.0001171797,0.0000375366,0.8541585,0.002178455,0.09240314,0.03282005,0.0006242963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3650282,0.000115569,0.4995379,0.005764729,0.002085373,0.0009370744,0.00001924374,0.09597356,0.03053838],"genre_scores_gemma":[0.9817901,0.000004924315,0.006334028,0.0003342113,0.0002559889,0.00009354056,0.00001418239,0.00001554652,0.0111575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8537298,"threshold_uncertainty_score":0.9990845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02585882803850791,"score_gpt":0.2706075501039039,"score_spread":0.2447487220653959,"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."}}