{"id":"W2951101154","doi":"10.1109/icstw.2019.00029","title":"Using Imprecise Test Oracles Modelled by FSM","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Oracle; Nondeterministic algorithm; Computer science; Context (archaeology); Finite-state machine; Conformance testing; Set (abstract data type); Test case; Theoretical computer science; Algorithm; Machine learning; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0001871321,0.0001101642,0.0001263466,0.00006133123,0.00006057223,0.0001376269,0.0006079732,0.00005302432,0.00003176584],"category_scores_gemma":[0.0001251749,0.00009263414,0.00003835282,0.0002246623,0.00001548027,0.0003063253,0.0002447055,0.00008069485,0.0001268565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002753439,"about_ca_system_score_gemma":0.00003824672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001943612,"about_ca_topic_score_gemma":6.60496e-7,"domain_scores_codex":[0.9991453,0.00001833128,0.0001409115,0.0003105647,0.0001705058,0.0002143518],"domain_scores_gemma":[0.998876,0.0003517048,0.00004929433,0.0006016337,0.00005937562,0.0000619583],"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":[0.00001479008,0.000736149,0.130136,0.00008863401,0.00004194018,0.00003170309,0.001023938,0.002660292,0.07771545,0.01734326,0.5943714,0.1758364],"study_design_scores_gemma":[0.0001332252,0.00005467401,0.00006946889,0.00002651056,0.000002093472,0.0000166044,0.00000121043,0.9689022,0.005709073,0.02405296,0.0008421489,0.0001897843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05567899,0.00007404525,0.9278482,0.0001251458,0.0001218776,0.0001237187,0.000001355904,0.01051677,0.005509941],"genre_scores_gemma":[0.5360222,0.000002020894,0.4627354,0.0002372005,0.00001208628,0.00000263926,6.429165e-7,0.000008269535,0.0009795566],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.966242,"threshold_uncertainty_score":0.3777511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02773029397782683,"score_gpt":0.2731334433065795,"score_spread":0.2454031493287526,"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."}}