{"id":"W4385315846","doi":"10.1364/cleo_fs.2023.fm3a.4","title":"Benchmarking Machine Learning-Derived W State Witnesses on NISQ Hardware","year":2023,"lang":"en","type":"article","venue":"","topic":"Quantum Information and Cryptography","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmarking; IBM; Computer science; Fidelity; State (computer science); Noise (video); Computer hardware; Computer engineering; Parallel computing; Programming language; Artificial intelligence; Telecommunications; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002232088,0.0004743078,0.0004908665,0.0004633782,0.000683531,0.0008275037,0.001470857,0.001071606,0.009326956],"category_scores_gemma":[0.01333035,0.0002062423,0.0003222564,0.0006456299,0.001315609,0.002390325,0.001667685,0.001337206,0.0008434572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006223557,"about_ca_system_score_gemma":0.0009956288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005804778,"about_ca_topic_score_gemma":0.0009343868,"domain_scores_codex":[0.9979001,0.0004814196,0.0001224851,0.0002723701,0.0009856399,0.0002378509],"domain_scores_gemma":[0.9955115,0.002010719,0.0003822096,0.001286764,0.0006607166,0.0001481584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003065814,0.0009364391,0.01052433,0.001154805,0.000394211,0.000800223,0.0006214759,0.296894,0.1609845,0.3248742,0.01312148,0.1866285],"study_design_scores_gemma":[0.0001645974,0.0008642547,0.001933392,0.00006049906,0.00003109722,0.000198712,0.000178495,0.7946926,0.1585597,0.03777073,0.005474435,0.00007159086],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5743929,0.0003408305,0.403855,0.0008969638,0.0003972663,0.0002146721,0.000554825,0.00336909,0.01597845],"genre_scores_gemma":[0.9599602,0.00004355362,0.03819,0.00008885065,0.00001727087,0.00006465742,0.000287009,0.0001416374,0.001206834],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009326956,"threshold_uncertainty_score":0.03120178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01581022258292821,"score_gpt":0.234301144199998,"score_spread":0.2184909216170698,"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."}}