{"id":"W4417268018","doi":"10.1103/cn64-gs6b","title":"Double Descent in Quantum Kernel Methods","year":2025,"lang":"en","type":"article","venue":"PRX Quantum","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Waterloo","funders":"European Commission; Natural Sciences and Engineering Research Council of Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute for Advanced Research","keywords":"Counterintuitive; Stochastic gradient descent; Quantum; Context (archaeology); Feature (linguistics); Kernel (algebra); Artificial neural network; Kernel method; Gradient descent","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002322183,0.0004492949,0.0007920729,0.0005234568,0.000573828,0.001383396,0.001060331,0.001105795,0.002603242],"category_scores_gemma":[0.01091979,0.0004339427,0.0004625202,0.0005000512,0.0020514,0.002418824,0.001804934,0.001613703,0.000581641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008726802,"about_ca_system_score_gemma":0.0009343557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001795626,"about_ca_topic_score_gemma":0.001617505,"domain_scores_codex":[0.9987044,0.0006690021,0.00004970764,0.0001373796,0.0003279019,0.0001114913],"domain_scores_gemma":[0.9969226,0.00179836,0.000201721,0.0005996979,0.0003404556,0.0001372358],"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":[0.0001020387,0.00005123484,0.00107608,0.0001080572,0.00004886103,0.0001314807,0.0001468814,0.2807287,0.002869386,0.6793357,0.002540629,0.03286096],"study_design_scores_gemma":[0.00000628985,0.00001780217,0.0001030073,0.000008245867,0.000002430211,0.00002006284,0.000009443497,0.8960632,0.0004465091,0.1026383,0.0006774574,0.000007144443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03510717,0.0004097849,0.9582731,0.0008117976,0.00008302641,0.00002386379,0.00003609835,0.0003039475,0.004951215],"genre_scores_gemma":[0.8256242,0.0004307657,0.1669268,0.0004178779,0.000104196,0.0001146651,0.0000923461,0.0003017788,0.005987261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002603242,"threshold_uncertainty_score":0.012281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0204598585638807,"score_gpt":0.3288902125595206,"score_spread":0.3084303539956398,"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."}}