{"id":"W7117174362","doi":"","title":"Detecting Flakiness in Quantum Software: A Dynamic Testing Approach","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; University of Maryland, Baltimore County","keywords":"Test suite; Software; Code (set theory); Suite; Quantum; Set (abstract data type); Work (physics); Characterization (materials science)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005968134,0.0007651636,0.001047918,0.005978652,0.0008203936,0.002092961,0.002661377,0.0008442758,0.001079589],"category_scores_gemma":[0.04003698,0.000728765,0.0008248024,0.00278864,0.00234165,0.004081982,0.002542149,0.001857593,0.0003092834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001151662,"about_ca_system_score_gemma":0.001205159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004684118,"about_ca_topic_score_gemma":0.005119467,"domain_scores_codex":[0.99318,0.001799277,0.0004121565,0.001941471,0.002192737,0.0004743676],"domain_scores_gemma":[0.9482596,0.02686389,0.0103748,0.008504668,0.004801527,0.001195419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007349093,0.0007391716,0.4712631,0.0006428708,0.0006862469,0.0009524992,0.003302952,0.1203747,0.06300402,0.01936893,0.002795184,0.3161354],"study_design_scores_gemma":[0.00005674182,0.0009624025,0.1772876,0.0001483157,0.0002693615,0.001249356,0.001014059,0.747533,0.02456492,0.04235262,0.004325961,0.0002356587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7590544,0.0007370469,0.2319211,0.000603774,0.00003728495,0.0001881467,0.0007437168,0.003103893,0.003610597],"genre_scores_gemma":[0.9695014,0.0001008527,0.02931517,0.00009184508,0.00001915846,0.00008652767,0.0003163204,0.0001598431,0.000408887],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.005978652,"threshold_uncertainty_score":0.03156292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02576202043430659,"score_gpt":0.2606151958650514,"score_spread":0.2348531754307448,"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."}}