{"id":"W4392781618","doi":"10.48550/arxiv.2403.07059","title":"Better than classical? The subtle art of benchmarking quantum machine\\n learning models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; University of Toronto; Innovation, Science and Economic Development Canada","keywords":"Benchmarking; Quantum; Computer science; Artificial intelligence; Cognitive science; Psychology; Physics; Economics; Quantum mechanics; Management","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020274,0.0002187657,0.0002303424,0.000107913,0.0001806363,0.0001304099,0.00155545,0.0001425876,0.0000150858],"category_scores_gemma":[0.000003601764,0.0001775307,0.0002429357,0.0005325395,0.0001149308,0.0001380288,0.002742747,0.001085557,0.00006312571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004764311,"about_ca_system_score_gemma":0.00006689862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007778501,"about_ca_topic_score_gemma":0.00005059315,"domain_scores_codex":[0.9985967,0.0001118199,0.0001882663,0.0007426218,0.0001031294,0.0002575166],"domain_scores_gemma":[0.9986156,0.0001655374,0.0001856557,0.0008951365,0.0000628897,0.00007523409],"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":[0.000003611825,0.00002781963,0.0003742923,0.00003875215,0.00004798355,0.00003177095,0.0001185872,0.4708237,0.00004540029,0.5260305,0.001385721,0.001071853],"study_design_scores_gemma":[0.0000483359,0.00001647383,0.00009816494,0.00006667191,0.00003701175,0.000001877148,0.0000100744,0.7818284,0.00002908455,0.2152628,0.002448556,0.0001525421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1831803,0.0002178698,0.8073652,0.002181771,0.0005385554,0.0003090205,0.00001474995,0.0002408218,0.005951799],"genre_scores_gemma":[0.9968284,0.0001394243,0.000508994,0.0001099486,0.0001299381,0.000002023746,0.00001363965,0.0000162515,0.002251374],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8136482,"threshold_uncertainty_score":0.723949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08025898080473734,"score_gpt":0.1894861551547899,"score_spread":0.1092271743500526,"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."}}