{"meta":{"query_hash":"4aff13888555","filters":{"topic":"Stochastic Gradient Optimization Techniques"},"cohort_total":271,"direct_labels_cover":1,"predictions_cover":271,"exported":271,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/4aff13888555","api":"https://metacan.xera.ac/api/v1/cohort?topic=Stochastic+Gradient+Optimization+Techniques"},"results":[{"id":"W1019179880","doi":"10.1007/bfb0033577","title":"Simulation trees for functional estimation via the phantom method","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in control and information sciences","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Imaging phantom; Estimation; Computer science; Mathematics; Artificial intelligence; Nuclear medicine; Medicine; Engineering","score_opus":0.021515487565046957,"score_gpt":0.284849832596839,"score_spread":0.26333434503179204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1019179880","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.9748465e-7,0.00023440954,0.99174654,0.0024197458,0.00023995804,0.0007958378,0.000014221256,0.00011031735,0.0044380655],"genre_scores_gemma":[0.2971886,0.00006378906,0.6960202,0.005682346,0.00030518865,0.0002121212,0.00007114507,0.000015244285,0.00044135455],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985863,0.000027470154,0.00049870845,0.00025453005,0.00045233834,0.00018063148],"domain_scores_gemma":[0.99677587,0.002357784,0.00039470146,0.00020160119,0.00023452305,0.000035549383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009995945,0.00021612711,0.0002203508,0.00043567034,0.00035212797,0.0004009213,0.0004110062,0.00018316873,0.000017869068],"category_scores_gemma":[0.0005358855,0.00014557144,0.0000698408,0.00018136621,0.00015648785,0.0025073886,0.00005156965,0.00015675649,0.0000056088775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007220025,0.0000016837623,0.0000022230831,0.000004988058,0.0000045637416,2.100713e-8,0.00018341097,0.5266902,0.000001535046,0.103125244,0.000012098927,0.36996683],"study_design_scores_gemma":[0.00036962033,0.0000826855,0.000046054014,0.000029395042,0.000012507938,0.0000043330297,0.0000014705869,0.86664486,0.000024235487,0.12303685,0.009596144,0.00015187358],"about_ca_topic_score_codex":0.000007659432,"about_ca_topic_score_gemma":0.000014573173,"teacher_disagreement_score":0.36981496,"about_ca_system_score_codex":0.00005613051,"about_ca_system_score_gemma":0.00009127053,"threshold_uncertainty_score":0.5936231},"labels":[],"label_agreement":null},{"id":"W104184427","doi":"","title":"On the importance of initialization and momentum in deep learning","year":2013,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3536,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Initialization; Momentum (technical analysis); Computer science; Recurrent neural network; Gradient descent; Stochastic gradient descent; Deep learning; Artificial intelligence; Deep neural networks; Artificial neural network; Schedule; Machine learning; Mathematical optimization; Algorithm; Mathematics","score_opus":0.011693136064989037,"score_gpt":0.22391151371799048,"score_spread":0.21221837765300144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W104184427","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05500136,0.000010946651,0.9404649,0.0005269944,0.000018414097,0.00015574785,2.5563963e-8,0.000053373824,0.0037681956],"genre_scores_gemma":[0.98265105,0.000006136241,0.017047614,0.00021326734,0.0000018837391,0.000026716161,3.584272e-7,0.0000021523247,0.000050822044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996276,0.000025747631,0.000110617664,0.00009328776,0.00008250206,0.000060230013],"domain_scores_gemma":[0.9996784,0.0001065753,0.000051521336,0.00011595067,0.000035412308,0.000012154345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011157334,0.000035989593,0.000043355016,0.00006281249,0.00002220192,0.000029113135,0.00013543617,0.000014707768,0.000055049644],"category_scores_gemma":[0.000107891756,0.000024402347,0.0000056247864,0.00019831024,0.000021187258,0.00015462576,0.00005310318,0.00003851052,0.0000028434295],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.9807892e-7,0.000012173703,0.006798732,0.0000021749302,0.000001048733,1.7278865e-7,0.00040454313,0.0012674525,0.0000965872,0.9894918,0.00010181744,0.0018230675],"study_design_scores_gemma":[0.000096883276,0.00007968167,0.011169826,0.000015604644,5.0054547e-7,0.0000010297379,0.00007039798,0.89801717,0.001653556,0.088828765,0.000010307973,0.000056270033],"about_ca_topic_score_codex":0.000020895455,"about_ca_topic_score_gemma":0.0000036103156,"teacher_disagreement_score":0.9276497,"about_ca_system_score_codex":0.000008172693,"about_ca_system_score_gemma":0.0000040950335,"threshold_uncertainty_score":0.09950988},"labels":[],"label_agreement":null},{"id":"W1522301498","doi":"10.48550/arxiv.1412.6980","title":"Adam: A Method for Stochastic Optimization","year":2014,"lang":"en","type":"preprint","venue":"UvA-DARE (University of Amsterdam)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":84783,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Mathematical optimization; Computer science; Diagonal; Convergence (economics); Stochastic optimization; Rate of convergence; Optimization problem; Mathematics; Key (lock); Machine learning","score_opus":0.01871386613063046,"score_gpt":0.24853192227985582,"score_spread":0.22981805614922535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1522301498","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005417171,0.00005344178,0.9958817,0.0009196664,0.0006145442,0.0011842235,0.00009409319,0.0005319989,0.0006662039],"genre_scores_gemma":[0.012946368,0.000012618242,0.98624074,0.00011547676,0.000057802143,0.000008538424,0.00013574088,0.000031255706,0.00045146263],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978779,0.00014824509,0.00030263563,0.0009203286,0.00041134676,0.0003395215],"domain_scores_gemma":[0.996911,0.00034000693,0.0007094637,0.0012076356,0.0006800198,0.00015187527],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050026993,0.00035032711,0.0006264208,0.0005694396,0.00022230846,0.00009625836,0.0021996247,0.0003871946,0.000049257647],"category_scores_gemma":[0.0001479519,0.00046282224,0.00032012528,0.0003383566,0.000111509755,0.0003277988,0.0019006957,0.00029109692,0.0000069418584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047703084,0.00007990128,0.000004534395,0.00029633433,0.00010248418,0.0000036016468,0.0017317575,0.9580553,0.000018910509,0.021451812,0.0029235044,0.01528413],"study_design_scores_gemma":[0.0006399584,0.00019324527,0.00003088517,0.00027107855,0.00010225668,0.0000048653947,0.00013040834,0.989318,0.000047625814,0.008305665,0.00052999455,0.0004260092],"about_ca_topic_score_codex":0.00013116955,"about_ca_topic_score_gemma":0.000014170208,"teacher_disagreement_score":0.031262685,"about_ca_system_score_codex":0.00016216467,"about_ca_system_score_gemma":0.00022657105,"threshold_uncertainty_score":0.9997823},"labels":[],"label_agreement":null},{"id":"W1579917626","doi":"10.48550/arxiv.1301.3545","title":"Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Hessian matrix; Boltzmann machine; Metric (unit); Mathematics; Computer science; Mathematical optimization; Algorithm; Gradient method; Applied mathematics; Artificial intelligence; Deep learning; Engineering","score_opus":0.08939302955471162,"score_gpt":0.20256160827600928,"score_spread":0.11316857872129765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1579917626","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022069082,0.00016720848,0.97441846,0.000119906304,0.0011402738,0.0008942084,0.000037330883,0.00044571405,0.0007078386],"genre_scores_gemma":[0.83143693,0.000047401143,0.16768628,0.00005290911,0.00005228044,0.000009527701,0.000025690295,0.000024337422,0.0006646212],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979902,0.00006910235,0.00037724015,0.0010062985,0.00015073208,0.00040645452],"domain_scores_gemma":[0.99688643,0.0002358336,0.00059123815,0.0016271871,0.0005143863,0.00014490646],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031368918,0.00036490517,0.0005334517,0.00093162205,0.00012140593,0.00009415012,0.002835695,0.00023115259,0.000013786227],"category_scores_gemma":[0.0003987106,0.00039296527,0.00036367544,0.00089260924,0.00012764813,0.00038677914,0.0024674707,0.00038318237,0.000006356734],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019224748,0.00010587606,0.000290474,0.00020855565,0.00017490625,0.000019288878,0.0006880366,0.09514103,0.000077340585,0.8977412,0.0023774388,0.0031566573],"study_design_scores_gemma":[0.00046532368,0.00009612943,0.00031903826,0.00010208668,0.000059113994,0.0000040021405,0.00003737854,0.80700684,0.0004297146,0.19101019,0.000101586695,0.00036862263],"about_ca_topic_score_codex":0.00014145457,"about_ca_topic_score_gemma":0.000009909915,"teacher_disagreement_score":0.8093679,"about_ca_system_score_codex":0.0001645898,"about_ca_system_score_gemma":0.00013421685,"threshold_uncertainty_score":0.99985224},"labels":[],"label_agreement":null},{"id":"W1589610332","doi":"10.1023/a:1008347431468","title":"Central Limit Theorems for Stochastic Optimization Algorithms Using Infinitesimal Perturbation Analysis","year":2000,"lang":"en","type":"article","venue":"Discrete Event Dynamic Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Mathematics; Queue; Mathematical optimization; Constant (computer programming); Convergence (economics); Context (archaeology); Asymptotically optimal algorithm; Rate of convergence; Perturbation (astronomy); Applied mathematics; Computer science; Key (lock)","score_opus":0.013175682301082887,"score_gpt":0.268686991798461,"score_spread":0.2555113094973781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1589610332","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002295808,0.00014024416,0.99500227,0.00008262162,0.0005190351,0.0012682278,0.00007891823,0.0004382895,0.00017460325],"genre_scores_gemma":[0.81390417,0.000011405026,0.18484098,0.00003980266,0.0000942562,0.00019376051,0.0003683025,0.00003752956,0.0005098214],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974839,0.00015131732,0.0006801608,0.0006644948,0.00047844215,0.0005416533],"domain_scores_gemma":[0.9984779,0.00020920443,0.00031054445,0.0006364299,0.0002124603,0.00015346463],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044698143,0.0003100029,0.00042202865,0.0004991396,0.00026130275,0.00035037982,0.00064970413,0.00013957487,0.000046743407],"category_scores_gemma":[0.0000950393,0.0002956122,0.0002877753,0.0013806685,0.000056363202,0.0006017668,0.000058188398,0.00009477014,0.0000041228113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015958612,0.00003908609,0.00005175728,0.000018804965,0.000163207,9.686511e-7,0.0005210208,0.985169,0.000016097036,0.012249542,0.000011100313,0.0017434863],"study_design_scores_gemma":[0.00040560472,0.00010808965,0.000099582925,0.0000661633,0.00024898708,0.000013341365,0.00008705268,0.9976388,0.0000066526463,0.00095738063,0.00001941525,0.00034893226],"about_ca_topic_score_codex":0.00008072839,"about_ca_topic_score_gemma":0.000003528209,"teacher_disagreement_score":0.8116083,"about_ca_system_score_codex":0.00031599603,"about_ca_system_score_gemma":0.00007777981,"threshold_uncertainty_score":0.9999496},"labels":[],"label_agreement":null},{"id":"W1627731299","doi":"10.1145/2746241","title":"Sparse Sums of Positive Semidefinite Matrices","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Algorithms","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Algebraic number; Positive-definite matrix; Graph; Preprocessor; Time complexity; Estimator; Spectral properties; Satisfiability","score_opus":0.04235669537589582,"score_gpt":0.27406983562542225,"score_spread":0.23171314024952644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1627731299","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060397084,0.000069820286,0.99680346,0.00056587753,0.00037400535,0.00019513158,0.000028119322,0.00033567142,0.0010239314],"genre_scores_gemma":[0.19512711,0.000040999264,0.8044309,0.00015561469,0.000019100202,0.000037356876,0.0000039026204,0.000014542446,0.00017047189],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882483,0.00004996295,0.00026473362,0.0002974045,0.0003697921,0.00019325555],"domain_scores_gemma":[0.9985592,0.00019481828,0.000113668895,0.0007421237,0.00025066524,0.00013951803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021647429,0.00014315745,0.00017513474,0.0003180934,0.000069765825,0.000046621968,0.0008158256,0.00007329854,0.000016554664],"category_scores_gemma":[0.00006226384,0.0001391824,0.000077845776,0.0007893485,0.000067064655,0.0003787157,0.00002119034,0.00013612898,0.000045314275],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012851265,0.0015445444,0.0002036943,0.000057543562,0.00034893295,0.0000700466,0.009343895,0.060633026,0.0009009324,0.0695389,0.0024723734,0.8547576],"study_design_scores_gemma":[0.0039944346,0.0036720017,0.0014540668,0.0003912023,0.00019800189,0.00029374813,0.00086847437,0.64526784,0.22711577,0.11345945,0.0015032886,0.0017817093],"about_ca_topic_score_codex":0.00009556544,"about_ca_topic_score_gemma":0.0000031044183,"teacher_disagreement_score":0.8529759,"about_ca_system_score_codex":0.00006115257,"about_ca_system_score_gemma":0.000077293014,"threshold_uncertainty_score":0.5675694},"labels":[],"label_agreement":null},{"id":"W1772464306","doi":"10.48550/arxiv.1502.04390","title":"Equilibrated adaptive learning rates for non-convex optimization","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":152,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Preconditioner; Hessian matrix; Saddle point; Computer science; Mathematical optimization; Rate of convergence; Curvature; Eigenvalues and eigenvectors; Convergence (economics); Stochastic gradient descent; Scheme (mathematics); Adaptive learning; Regular polygon; Convex optimization; Artificial neural network; Artificial intelligence; Applied mathematics; Mathematics; Iterative method; Mathematical analysis","score_opus":0.09230213855191799,"score_gpt":0.21112369324746097,"score_spread":0.11882155469554298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1772464306","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035869584,0.000007729024,0.9937822,0.00005023585,0.00015450467,0.00034623907,0.0000016442453,0.0005067092,0.0015637678],"genre_scores_gemma":[0.85117316,0.0000051901848,0.14795454,0.00005426109,0.000020810634,0.0000029614969,0.000012410622,0.0000134722395,0.00076322205],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990431,0.00005872872,0.00012560957,0.00046472353,0.0000641186,0.0002437404],"domain_scores_gemma":[0.99890083,0.000119570665,0.0001329519,0.00029121625,0.00039938788,0.00015606353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021285853,0.00014274332,0.00014917548,0.00019817062,0.00012520554,0.000076962955,0.0005728839,0.0000832528,0.00001014058],"category_scores_gemma":[0.0001428082,0.000163866,0.000055259017,0.00087592873,0.00005857089,0.0009301857,0.00018354133,0.00009619129,0.00001966904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033366014,0.000024834426,0.00039415443,0.0000025649363,0.000014136868,0.0000072828425,0.00019902334,0.88714176,0.000025789293,0.11171568,0.00033930308,0.000102113125],"study_design_scores_gemma":[0.00069346436,0.0002868574,0.00001716607,0.000014176645,0.000012947055,0.0000019992729,0.00014874306,0.99057055,0.0010352323,0.006966951,0.000059980226,0.00019196152],"about_ca_topic_score_codex":0.000011956655,"about_ca_topic_score_gemma":8.777441e-7,"teacher_disagreement_score":0.84758615,"about_ca_system_score_codex":0.000106214444,"about_ca_system_score_gemma":0.000118026925,"threshold_uncertainty_score":0.6682262},"labels":[],"label_agreement":null},{"id":"W1844261860","doi":"10.48550/arxiv.1301.3584","title":"Revisiting Natural Gradient for Deep Networks","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; DeepMind; Compute Canada","keywords":"Natural (archaeology); Computer science; Artificial intelligence; Geology; Paleontology","score_opus":0.04715239288676829,"score_gpt":0.1881851438096175,"score_spread":0.14103275092284923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1844261860","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004412605,0.00021891849,0.99186504,0.00010934032,0.0011932458,0.00095435465,0.000004002484,0.0007332132,0.00050928484],"genre_scores_gemma":[0.9029092,0.00008853307,0.09605441,0.00014584785,0.00018816166,0.000013067558,0.000036314344,0.000026766276,0.0005376695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979527,0.0000740993,0.00026653585,0.0011442436,0.000079773235,0.0004826764],"domain_scores_gemma":[0.99774665,0.00022269512,0.0003816529,0.0011180557,0.00037075515,0.00016021165],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024880515,0.00034659807,0.00035197366,0.00027585388,0.00021169416,0.00022801159,0.0019572894,0.00026742305,0.00001321476],"category_scores_gemma":[0.00009892904,0.00039570135,0.00027552337,0.0004758696,0.00007775766,0.0003771284,0.0016858989,0.00049505517,0.00001607843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062448503,0.000018647643,0.00012945062,0.000050130577,0.000043818414,0.000016272683,0.000080337355,0.4973638,0.0000022974484,0.49928686,0.000436723,0.0025653997],"study_design_scores_gemma":[0.00022624648,0.000031774325,0.000104276514,0.000120141856,0.00003961826,0.0000040665095,0.0000152505945,0.942128,0.00002480735,0.05676876,0.00013593,0.00040112532],"about_ca_topic_score_codex":0.000033252243,"about_ca_topic_score_gemma":0.000002876273,"teacher_disagreement_score":0.8984966,"about_ca_system_score_codex":0.00025221903,"about_ca_system_score_gemma":0.00006220053,"threshold_uncertainty_score":0.9998495},"labels":[],"label_agreement":null},{"id":"W1966777587","doi":"10.1137/1.9781611973082.109","title":"Low Rank Matrix-valued Chernoff Bounds and Approximate Matrix Multiplication","year":2011,"lang":"en","type":"preprint","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Rank (graph theory); Matrix (chemical analysis); Matrix norm; Matrix multiplication; Mathematics; Combinatorics; Row; Discrete mathematics; Low-rank approximation; Algorithm; Computer science; Pure mathematics; Eigenvalues and eigenvectors","score_opus":0.0230979240330087,"score_gpt":0.2793052350851867,"score_spread":0.256207311052178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966777587","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011392598,0.0002587923,0.9908146,0.00022796023,0.00044089105,0.0012855673,0.000009293903,0.0018993238,0.0039242585],"genre_scores_gemma":[0.076918945,0.00013402627,0.9204792,0.00010362179,0.00007081928,0.000412622,0.00004497974,0.000047542133,0.0017882603],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749327,0.000079223995,0.0005479281,0.0011422862,0.00037025407,0.0003670687],"domain_scores_gemma":[0.9974683,0.000059784103,0.00041096602,0.001642451,0.00025188975,0.00016661624],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005144308,0.00042652924,0.00042615575,0.0003368491,0.00013196534,0.00048633193,0.0014845802,0.00042392118,0.00005184938],"category_scores_gemma":[0.000086339656,0.00040777662,0.000117483665,0.00027297018,0.00011841092,0.00031356403,0.002172752,0.00038794414,0.0000432966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042114563,0.00038172706,0.00032061618,0.00075547036,0.00013651025,0.000008433167,0.0029065548,0.0022448506,0.00087655656,0.9762019,0.002382629,0.013742663],"study_design_scores_gemma":[0.0004459846,0.000055166867,0.00030729256,0.00012467476,0.000030897416,0.000022571123,0.00001260479,0.910361,0.006250953,0.08169019,0.00009853955,0.00060015253],"about_ca_topic_score_codex":0.00012414268,"about_ca_topic_score_gemma":0.000003160804,"teacher_disagreement_score":0.9081161,"about_ca_system_score_codex":0.00010266988,"about_ca_system_score_gemma":0.00011197601,"threshold_uncertainty_score":0.9998374},"labels":[],"label_agreement":null},{"id":"W2007755560","doi":"10.1007/s10208-014-9220-1","title":"Improved Bounds on Sample Size for Implicit Matrix Trace Estimators","year":2014,"lang":"en","type":"article","venue":"Foundations of Computational Mathematics","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Ciência sem Fronteiras; Natural Sciences and Engineering Research Council of Canada","keywords":"TRACE (psycholinguistics); Estimator; Upper and lower bounds; Gaussian; Matrix (chemical analysis); Unit vector; Monte Carlo method; Probabilistic logic; Multivariate random variable","score_opus":0.01812313942802826,"score_gpt":0.3075835547097815,"score_spread":0.28946041528175326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007755560","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002398886,0.0000036438246,0.9955588,0.0005431486,0.00016765992,0.00059674296,0.00004152388,0.00027479298,0.00041482903],"genre_scores_gemma":[0.22747351,3.7561156e-7,0.7722277,0.00007305151,0.000029185934,0.00010299376,0.000028635719,0.00001783797,0.00004669142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859077,0.000026458923,0.000570579,0.00027796684,0.0003369539,0.00019726895],"domain_scores_gemma":[0.99213713,0.0064492333,0.00038960093,0.00045285467,0.000500246,0.00007093728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038843733,0.0001742041,0.00025899685,0.00019975622,0.00021508979,0.00015201324,0.00060707564,0.000061046354,0.000019708797],"category_scores_gemma":[0.0026251907,0.00017682707,0.00011406902,0.00038063715,0.000076972254,0.00025897965,0.00007451947,0.00006527811,0.000011225076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000378448,0.00018051604,0.0000072065423,0.000066060835,0.000020244765,2.8443104e-8,0.00026390806,0.07546687,0.00007711651,0.9219153,0.00030691508,0.0016920296],"study_design_scores_gemma":[0.00023073325,0.00015151853,0.00009603035,0.000022349694,0.000009044073,0.0000029897542,0.000008300345,0.5406338,0.00020231557,0.45837197,0.00017504067,0.00009593689],"about_ca_topic_score_codex":0.0000050419667,"about_ca_topic_score_gemma":8.71406e-7,"teacher_disagreement_score":0.4651669,"about_ca_system_score_codex":0.000059042643,"about_ca_system_score_gemma":0.00011113534,"threshold_uncertainty_score":0.7210799},"labels":[],"label_agreement":null},{"id":"W2012368965","doi":"10.1145/1837210.1837238","title":"Cache friendly sparse matrix-vector multiplication","year":2010,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge; Western University","funders":"","keywords":"Computer science; Multiplication (music); Parallel computing; Matrix multiplication; Cache-oblivious algorithm; Locality; Cache; Kernel (algebra); Context (archaeology); Cache algorithms; Conjugate gradient method; Sparse matrix; Algorithm; Theoretical computer science; CPU cache; Mathematics; Discrete mathematics","score_opus":0.012193781257375018,"score_gpt":0.2626093437592976,"score_spread":0.2504155625019226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012368965","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004062206,0.0000050937497,0.98816043,0.0009266407,0.00038049518,0.00022449787,0.0000010147143,0.0010187437,0.005220895],"genre_scores_gemma":[0.444358,7.3462127e-7,0.5549903,0.00008977389,0.000032774577,0.000034159453,0.0000021248911,0.0000055737723,0.00048659573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918205,0.000013274214,0.00016015326,0.00029953898,0.00017398027,0.0001710042],"domain_scores_gemma":[0.99898726,0.00006250892,0.000064702814,0.0006877342,0.00011027172,0.000087516084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015097008,0.00009536257,0.00007699368,0.00010022459,0.000073934294,0.000098139855,0.0006718831,0.000071089446,0.000116065334],"category_scores_gemma":[0.00012131383,0.000084514795,0.000034080724,0.0003124631,0.000034039695,0.00032652993,0.00013648972,0.0001347564,0.00013928472],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013306515,0.000060532984,0.0004994601,0.0000025451598,0.000003942211,0.0000011462595,0.00016599063,0.00005532261,0.02287494,0.96483153,0.0035920863,0.007911152],"study_design_scores_gemma":[0.00040369708,0.000106605956,0.004715369,0.0000059779304,0.000006690764,0.000040820858,0.000016011225,0.8832256,0.087975085,0.012253937,0.01082092,0.0004292745],"about_ca_topic_score_codex":0.000036649988,"about_ca_topic_score_gemma":0.000015331658,"teacher_disagreement_score":0.9525776,"about_ca_system_score_codex":0.00001549673,"about_ca_system_score_gemma":0.00003115806,"threshold_uncertainty_score":0.34464133},"labels":[],"label_agreement":null},{"id":"W2075660001","doi":"10.1007/s10107-014-0800-2","title":"On the complexity analysis of randomized block-coordinate descent methods","year":2014,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":215,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mathematics; Convex function; Separable space; Block (permutation group theory); Convex optimization; Combinatorics; Coordinate descent; Rate of convergence; Convergence (economics); Function (biology); Regular polygon; Sequence (biology); Descent (aeronautics); Convex analysis; Applied mathematics; Mathematical optimization; Computer science; Mathematical analysis","score_opus":0.05267368180101976,"score_gpt":0.33118716997368663,"score_spread":0.27851348817266686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075660001","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00081685965,0.000008067515,0.9955142,0.0008979005,0.0000357045,0.0006780686,3.4957824e-7,0.00024047977,0.0018083388],"genre_scores_gemma":[0.37857825,3.6135827e-7,0.62122744,0.00008218199,0.0000041650583,0.00008871078,6.7617685e-7,0.0000053004596,0.0000129179625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978027,0.0007435334,0.0005740855,0.0002719849,0.00036732692,0.00024036999],"domain_scores_gemma":[0.9945124,0.004290627,0.00027550396,0.00072174316,0.00012992862,0.000069844915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051497733,0.00015158631,0.0007754383,0.00024244736,0.00010899151,0.00011166138,0.0007620528,0.000046573274,0.000040409886],"category_scores_gemma":[0.0036789607,0.000088526765,0.0003888361,0.0011814003,0.00040494226,0.000057754718,0.00020200739,0.000120407356,0.000007031981],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005467836,0.00011837385,0.0000019912125,0.000020139722,0.00023904283,1.9254757e-7,0.00041348714,0.00034004299,0.00001734136,0.97959685,0.000012405171,0.019185448],"study_design_scores_gemma":[0.001380626,0.000033348802,0.0000052444357,0.000025716932,0.00021786331,8.7812924e-7,0.000010146351,0.6328008,0.00080009544,0.364635,0.000020172705,0.00007007139],"about_ca_topic_score_codex":0.0000052759387,"about_ca_topic_score_gemma":3.8662733e-7,"teacher_disagreement_score":0.6324608,"about_ca_system_score_codex":0.000023941375,"about_ca_system_score_gemma":0.000008192895,"threshold_uncertainty_score":0.44043255},"labels":[],"label_agreement":null},{"id":"W2081907865","doi":"10.1080/00949650213533","title":"Estimating the Optimum of a Stochastic System using Simulation","year":2002,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Kamloops Art Gallery","funders":"","keywords":"Estimator; Mathematics; Mathematical optimization; Least-squares function approximation; Function (biology); Stochastic approximation; Algorithm; Applied mathematics; Statistics; Computer science","score_opus":0.04640954706566746,"score_gpt":0.3178117589430788,"score_spread":0.2714022118774113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081907865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01037701,0.00004952475,0.98907804,0.000056707,0.00020358988,0.00016674754,0.0000033339104,0.00003677073,0.000028298751],"genre_scores_gemma":[0.59112424,2.1388759e-7,0.40882513,0.000013061076,0.00003110936,4.3980296e-7,7.152533e-7,0.0000042199104,8.6063324e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852604,0.00012606614,0.00070232013,0.00012313998,0.00041590605,0.000106526975],"domain_scores_gemma":[0.9969826,0.0015878007,0.00070944853,0.00010104219,0.00055324024,0.000065894375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044539932,0.00010078762,0.00021060424,0.00018749517,0.00013821379,0.000097053184,0.00015569227,0.000043091863,0.000005387831],"category_scores_gemma":[0.0004951392,0.00007630279,0.000038095262,0.00029479974,0.00006657016,0.00038567363,0.0000415279,0.00011304463,8.0982045e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008156071,0.00002385635,0.000018488803,0.000029595396,0.000011377792,0.0000020387688,0.00050922215,0.97154075,0.000016639446,0.016205397,0.0000058277574,0.011628623],"study_design_scores_gemma":[0.00034758996,0.00014827584,0.00029903703,0.00009921977,0.000031494466,0.00003954008,0.000044673103,0.99399054,0.0000053346225,0.0049222372,7.660093e-7,0.000071290226],"about_ca_topic_score_codex":0.000002569267,"about_ca_topic_score_gemma":6.623862e-8,"teacher_disagreement_score":0.58074725,"about_ca_system_score_codex":0.00006062243,"about_ca_system_score_gemma":0.000019894236,"threshold_uncertainty_score":0.31115377},"labels":[],"label_agreement":null},{"id":"W2113717009","doi":"10.1007/s10107-006-0031-2","title":"Large-scale semidefinite programming via a saddle point Mirror-Prox algorithm","year":2006,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Office of Naval Research; National Science Foundation","keywords":"Semidefinite programming; Saddle point; Mathematics; Semidefinite embedding; Algorithm; Scale (ratio); Numerical analysis; Mathematical optimization; Positive-definite matrix; Quadratically constrained quadratic program; Quadratic programming; Mathematical analysis; Geometry","score_opus":0.012556340445406806,"score_gpt":0.24420694903262774,"score_spread":0.23165060858722095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113717009","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004882547,0.00009593792,0.9937113,0.00041754157,0.00012614185,0.0011716192,0.0000032423186,0.002220098,0.0017658573],"genre_scores_gemma":[0.026495479,9.882792e-7,0.97245586,0.000117223244,0.000066882865,0.00051201315,0.000020666621,0.000054408363,0.00027645283],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965224,0.00008051203,0.0008249875,0.0007760664,0.0007287619,0.0010672488],"domain_scores_gemma":[0.99819934,0.0002369817,0.00025614392,0.00088850845,0.00019492379,0.00022408347],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009639736,0.00039877286,0.00046319986,0.0002449166,0.00031704502,0.00056346715,0.0009393806,0.00018108224,0.0000572184],"category_scores_gemma":[0.0001476562,0.00036605776,0.00021814,0.0010001236,0.000141881,0.00054510805,0.00050735974,0.00031479588,0.00018483178],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007351208,0.002061595,0.00019652225,0.0003669706,0.000055537268,0.0001293616,0.0031869237,0.00005088414,0.00031866145,0.42359746,0.0005248816,0.56950384],"study_design_scores_gemma":[0.0007157003,0.00027650225,0.00004331862,0.00025317585,0.00004374983,0.0002932923,0.000243637,0.6696009,0.0021268437,0.31761995,0.007945371,0.0008375375],"about_ca_topic_score_codex":0.00003370466,"about_ca_topic_score_gemma":0.000007909218,"teacher_disagreement_score":0.66955006,"about_ca_system_score_codex":0.000112429756,"about_ca_system_score_gemma":0.00004099541,"threshold_uncertainty_score":0.9998791},"labels":[],"label_agreement":null},{"id":"W2119200797","doi":"","title":"An Accelerated Proximal Coordinate Gradient Method","year":2014,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mathematical optimization; Dual (grammatical number); Convergence (economics); Proximal Gradient Methods; Computer science; Convex optimization; Empirical risk minimization; Minification; Coordinate descent; Gradient method; Regular polygon; Stochastic gradient descent; Rate of convergence; Convex function; Applied mathematics; Mathematics; Artificial intelligence; Artificial neural network; Key (lock); Geometry","score_opus":0.02352433827712829,"score_gpt":0.2919534599160039,"score_spread":0.2684291216388756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119200797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002102811,0.000019957115,0.9935266,0.0002030271,0.00050488726,0.00045008128,0.0000017353989,0.0013812786,0.0018096165],"genre_scores_gemma":[0.88010657,5.2824845e-7,0.1192678,0.00037000782,0.0000561703,0.000119170356,0.000028038063,0.000009885726,0.00004181172],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830264,0.00015889067,0.0006036137,0.00023937656,0.00039704193,0.00029846837],"domain_scores_gemma":[0.99841803,0.00003922756,0.00045099572,0.00041588003,0.00053940795,0.00013644635],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00076052,0.00018983304,0.00020829654,0.00030107595,0.0002847428,0.0014921457,0.0007632442,0.000087705965,0.000002449939],"category_scores_gemma":[0.00009459895,0.00016479938,0.000032353037,0.0007069946,0.000028005903,0.007238344,0.000071994604,0.00013712741,0.000023646327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027951579,0.00012373047,0.0003372301,0.00061544497,0.000017862047,0.0000017175516,0.00711765,0.16165121,0.0012795974,0.29263395,0.0017143199,0.5344793],"study_design_scores_gemma":[0.00024668564,0.00016595448,0.00013885579,0.000049231367,0.000003845661,0.00005569261,0.000068202105,0.99536383,0.001340981,0.00041877077,0.001944933,0.00020299961],"about_ca_topic_score_codex":0.000026230251,"about_ca_topic_score_gemma":2.757803e-7,"teacher_disagreement_score":0.8780038,"about_ca_system_score_codex":0.00006400134,"about_ca_system_score_gemma":0.00005162963,"threshold_uncertainty_score":0.9995444},"labels":[],"label_agreement":null},{"id":"W2135778653","doi":"10.1007/s10107-006-0025-0","title":"A modified nearly exact method for solving low-rank trust region subproblem","year":2006,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Science Foundation","keywords":"Trust region; Mathematics; Rank (graph theory); Numerical analysis; Applied mathematics; Mathematical optimization; Combinatorics; Computer science; Mathematical analysis","score_opus":0.02650424937890863,"score_gpt":0.2813552625777429,"score_spread":0.2548510131988343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135778653","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043299218,0.000031469786,0.995329,0.0004650336,0.00007339139,0.0013325675,7.1107894e-7,0.0011051967,0.0012295884],"genre_scores_gemma":[0.10110004,4.5751702e-7,0.8980189,0.00005525133,0.00006931136,0.00048353392,0.000004815743,0.000032881377,0.000234823],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979539,0.000045947432,0.00055658724,0.00053370185,0.00033740993,0.0005724351],"domain_scores_gemma":[0.9984154,0.00055579434,0.00019685831,0.0005731146,0.00015153685,0.000107310436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007941181,0.00024012008,0.0003366508,0.00016192357,0.00022395932,0.00048553644,0.0006731593,0.0001264683,0.00000635541],"category_scores_gemma":[0.00032490244,0.00021468135,0.00017077786,0.00046070837,0.00006211348,0.00039790204,0.00015341047,0.00013910254,0.000011774889],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009041588,0.00023388387,0.000013912986,0.00024455096,0.000013579918,0.00000790697,0.00040704882,0.0011167771,0.00023897177,0.9226399,0.00030449632,0.074769914],"study_design_scores_gemma":[0.0003140315,0.00010031278,0.000007916974,0.000105647036,0.000015743166,0.000034006323,0.000015530364,0.7066007,0.0012272625,0.29111996,0.00024039239,0.0002184932],"about_ca_topic_score_codex":0.000021564547,"about_ca_topic_score_gemma":0.0000011517037,"teacher_disagreement_score":0.7054839,"about_ca_system_score_codex":0.00007464216,"about_ca_system_score_gemma":0.00003466574,"threshold_uncertainty_score":0.8754452},"labels":[],"label_agreement":null},{"id":"W2150394007","doi":"","title":"From PAC-Bayes Bounds to KL Regularization","year":2009,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Coordinate descent; Regularization (linguistics); Mathematics; Boosting (machine learning); Upper and lower bounds; Convex function; Algorithm; Proximal gradient methods for learning; Bayes' theorem; Regular polygon; Elastic net regularization; Mathematical optimization; Applied mathematics; Kullback–Leibler divergence; Computer science; Convex optimization; Artificial intelligence; Regression; Convex combination; Statistics; Bayesian probability; Mathematical analysis","score_opus":0.00881585654239763,"score_gpt":0.2416711849258008,"score_spread":0.23285532838340317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150394007","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006388806,0.000010311567,0.98502785,0.004522943,0.00015538017,0.00015517161,0.0000012720199,0.00086621585,0.008621968],"genre_scores_gemma":[0.24060647,0.0000013271479,0.7558082,0.002413848,0.000060491297,0.000008081223,0.000009201379,0.0000044403027,0.0010879887],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991685,0.000017287099,0.00015063965,0.0003026238,0.00020752901,0.00015340542],"domain_scores_gemma":[0.9992816,0.000030138466,0.000037001104,0.00047743047,0.00008244249,0.000091420225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007998468,0.00008991687,0.000087250875,0.00012524152,0.00006705132,0.00019939436,0.0005034961,0.000045586952,0.000054250708],"category_scores_gemma":[0.00006983694,0.00008376847,0.000025411999,0.0004877561,0.000009874011,0.00032902954,0.00007114716,0.000036071124,0.000055527722],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031109441,0.00005409124,0.00007090838,6.3107547e-7,0.0000048785196,0.0000023500402,0.0008038064,0.00079915905,0.0020751501,0.9361187,0.017612532,0.04245464],"study_design_scores_gemma":[0.00028853046,0.00042390515,0.0049254294,0.00003318897,0.000006858875,0.0000050416324,0.0000286281,0.25437298,0.042283576,0.69258285,0.004584362,0.0004646633],"about_ca_topic_score_codex":0.000027206408,"about_ca_topic_score_gemma":0.000001781168,"teacher_disagreement_score":0.25357383,"about_ca_system_score_codex":0.000033897453,"about_ca_system_score_gemma":0.000021380494,"threshold_uncertainty_score":0.3415979},"labels":[],"label_agreement":null},{"id":"W2161012868","doi":"10.1287/ijoc.1090.0346","title":"<b>From the Editor</b>—Special Cluster on High-Throughput Optimization","year":2009,"lang":"en","type":"article","venue":"INFORMS journal on computing","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Throughput; Computer science; Cluster (spacecraft); Volume (thermodynamics); Computer network; Telecommunications","score_opus":0.011059547167431322,"score_gpt":0.24904338042663587,"score_spread":0.23798383325920455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161012868","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00152395,0.000008566746,0.9803592,0.005581033,0.009094932,0.00019328734,0.0000015391735,0.0002664285,0.002971058],"genre_scores_gemma":[0.33060572,0.000023470431,0.57888275,0.021193555,0.06917256,0.0000029764585,0.000013418628,0.00003080451,0.000074760326],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979759,0.000059939302,0.00058287766,0.00026741155,0.0007475827,0.000366307],"domain_scores_gemma":[0.99825925,0.0004530797,0.00048013538,0.00046288365,0.0002226382,0.00012200285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057955214,0.00023199008,0.00020110732,0.0001704531,0.00062602124,0.0008671911,0.0012470344,0.000104131985,0.000031269712],"category_scores_gemma":[0.00024631323,0.00014907356,0.00010716091,0.00042910528,0.0000377791,0.00078570825,0.00014755834,0.0005924095,0.000052034575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026002961,0.000053609478,0.00001577713,6.108765e-7,0.000013037956,0.000007724803,0.0010316052,0.83684856,0.0000021648193,0.031203594,0.058323886,0.07247342],"study_design_scores_gemma":[0.00086529966,0.0008460982,0.0006725906,0.00020037434,0.000007971793,0.00007626035,0.00004580662,0.97234076,0.00021098828,0.0166911,0.007717038,0.00032570717],"about_ca_topic_score_codex":0.00000533641,"about_ca_topic_score_gemma":2.5369383e-7,"teacher_disagreement_score":0.40147647,"about_ca_system_score_codex":0.00018014623,"about_ca_system_score_gemma":0.000075260876,"threshold_uncertainty_score":0.8362344},"labels":[],"label_agreement":null},{"id":"W2170419304","doi":"","title":"An interior-point stochastic approximation method and an L1-regularized delta rule","year":2008,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Stochastic approximation; Regularization (linguistics); Approximation algorithm; Mathematical optimization; Stability (learning theory); Interior point method; Computer science; Point (geometry); Mathematics; Applied mathematics; Artificial intelligence; Machine learning; Key (lock)","score_opus":0.022528562209251993,"score_gpt":0.2911057188669787,"score_spread":0.26857715665772675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170419304","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01247557,0.000011510695,0.9857453,0.00016993794,0.00009505739,0.00035265507,0.0000017764964,0.00088209397,0.00026606524],"genre_scores_gemma":[0.3142771,0.0000016342466,0.6854304,0.00016537606,0.00002067554,0.00003795111,0.000010630427,0.0000111373265,0.00004507237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985801,0.00013918053,0.0002879253,0.0005230998,0.00024161294,0.00022811131],"domain_scores_gemma":[0.9988128,0.000070933485,0.000103592705,0.0006829074,0.0001405958,0.00018918359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004318724,0.00017607886,0.00020495213,0.00022177982,0.00018637876,0.00014889026,0.0005620727,0.00007833136,0.000031393905],"category_scores_gemma":[0.00007914987,0.00016039211,0.000031960048,0.00030274253,0.000083391045,0.0013306366,0.0001689796,0.00009149501,0.00000559056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009335132,0.00062403356,0.00025287046,0.000047644346,0.00006568165,0.00002942529,0.014532681,0.0124990605,0.038040847,0.81941324,0.0005386558,0.11386251],"study_design_scores_gemma":[0.00035472028,0.00026873618,0.00042252115,0.000010409246,0.0000061906153,0.00015240393,0.000037230842,0.9682829,0.0055495556,0.024697145,0.0000049302253,0.00021330111],"about_ca_topic_score_codex":0.00004829326,"about_ca_topic_score_gemma":0.0000032980317,"teacher_disagreement_score":0.9557838,"about_ca_system_score_codex":0.000038083388,"about_ca_system_score_gemma":0.000042510623,"threshold_uncertainty_score":0.65406},"labels":[],"label_agreement":null},{"id":"W2314313325","doi":"10.1007/s00446-016-0266-y","title":"A simple approach for adapting continuous load balancing processes to discrete settings","year":2016,"lang":"en","type":"article","venue":"Distributed Computing","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Load balancing (electrical power); Computer science; Mathematics; Asymptotically optimal algorithm; Discrete mathematics; Algorithm; Mathematical optimization; Grid","score_opus":0.012486289752887219,"score_gpt":0.24905113146082808,"score_spread":0.23656484170794087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2314313325","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022889008,0.000034817323,0.99464,0.00058371125,0.000088357214,0.00081480277,0.00010673179,0.0012477644,0.00019489275],"genre_scores_gemma":[0.6291704,4.0873599e-7,0.37041965,0.00018958168,0.000076173026,0.00006372694,0.00004960727,0.000018231754,0.000012199439],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976512,0.00004266454,0.0004742627,0.0007675821,0.000360521,0.0007037738],"domain_scores_gemma":[0.99782073,0.0005460851,0.0002780185,0.0004881392,0.0006815667,0.00018546982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006527297,0.0002625181,0.00032145824,0.00010274008,0.0003387746,0.0002680263,0.0010236013,0.000074996606,0.0000022411912],"category_scores_gemma":[0.0019685095,0.00020765908,0.00008140319,0.00087556924,0.00004288368,0.0003015104,0.00038676275,0.000081211154,0.0000055760765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030833622,0.00096350466,0.024137834,0.0022644238,0.0005364775,0.00005501111,0.012876777,0.14076385,0.046226133,0.25172538,0.07769522,0.44244704],"study_design_scores_gemma":[0.001098974,0.00029051566,0.00049398554,0.00038762524,0.000021712107,0.000029161556,0.000222557,0.9757745,0.014582623,0.0029778655,0.0032961692,0.0008242714],"about_ca_topic_score_codex":0.00000987089,"about_ca_topic_score_gemma":6.224941e-7,"teacher_disagreement_score":0.8350107,"about_ca_system_score_codex":0.00020733324,"about_ca_system_score_gemma":0.00015496316,"threshold_uncertainty_score":0.84680915},"labels":[],"label_agreement":null},{"id":"W2347186258","doi":"10.20382/jocg.v10i1a3","title":"Minimax Rates for Estimating the Dimension of a Manifold","year":2016,"lang":"en","type":"article","venue":"Journal of Computational Geometry (Carleton University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Samsung; National Science Foundation","keywords":"Combinatorics; Mathematics; Upper and lower bounds; Minimax; Dimension (graph theory); Bounding overwatch; Embedding; Lemma (botany); Manifold (fluid mechanics); Probability distribution; Distribution (mathematics); Omega; Order (exchange); Discrete mathematics; Mathematical analysis; Statistics; Mathematical optimization; Computer science","score_opus":0.015565488803360757,"score_gpt":0.2464128874285505,"score_spread":0.23084739862518974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2347186258","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02874272,0.00002546003,0.96948344,0.0012100976,0.00024223342,0.00011979132,0.000005244491,0.000022578199,0.00014845144],"genre_scores_gemma":[0.4807972,0.0000030533606,0.5189899,0.00004740432,0.00003686553,1.9800144e-7,5.694703e-7,0.000004118971,0.00012068822],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990538,0.000050991508,0.00031175523,0.00012215617,0.0003431429,0.00011818905],"domain_scores_gemma":[0.9971112,0.0012040179,0.0006396044,0.0001336684,0.00085533323,0.000056195862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003663197,0.000088408255,0.00017419607,0.0006204002,0.00010269151,0.000027131158,0.0006471408,0.00003664063,0.0000075806147],"category_scores_gemma":[0.00022482863,0.0000570459,0.00013495208,0.00070805673,0.000058649955,0.00045542946,0.00011628068,0.000057244473,0.0000010447758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021454222,0.00023119977,0.0015754823,0.0000625784,0.0002774185,0.000042112075,0.00056232006,0.24251378,0.0034949633,0.7130112,0.0037378208,0.03427656],"study_design_scores_gemma":[0.0049223737,0.001966066,0.006696316,0.00071118196,0.00016064008,0.00035305825,0.00030390488,0.8388153,0.012810676,0.12937008,0.0033557136,0.0005347129],"about_ca_topic_score_codex":0.0000015705067,"about_ca_topic_score_gemma":1.5687003e-7,"teacher_disagreement_score":0.5963015,"about_ca_system_score_codex":0.00007602316,"about_ca_system_score_gemma":0.00012290575,"threshold_uncertainty_score":0.23262644},"labels":[],"label_agreement":null},{"id":"W2400062642","doi":"10.1016/j.neucom.2019.11.021","title":"Annealed gradient descent for deep learning","year":2019,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"MNIST database; Stochastic gradient descent; Deep learning; Computer science; Artificial intelligence; Gradient descent; Convex function; Schedule; Stochastic optimization; Convergence (economics); Convex optimization; Pattern recognition (psychology); Artificial neural network; Regular polygon; Mathematical optimization; Mathematics","score_opus":0.010798208818750835,"score_gpt":0.23116459440710593,"score_spread":0.22036638558835508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400062642","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045069806,0.000027968543,0.95197886,0.00015520709,0.0005594048,0.0006847915,1.9464657e-7,0.00081631687,0.0007074593],"genre_scores_gemma":[0.72114164,0.0000017712689,0.27838948,0.00027929284,0.000056501387,0.000025272411,0.0000022394486,0.000018604622,0.000085227504],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861604,0.000049972627,0.0002534497,0.0004971233,0.00019704452,0.0003863923],"domain_scores_gemma":[0.9990625,0.00026096305,0.00015025372,0.00032781996,0.0001161568,0.000082338345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002499851,0.00014803515,0.00016510965,0.00013924182,0.00017611252,0.00013435732,0.0005979,0.000042536023,0.0000054509856],"category_scores_gemma":[0.0001127599,0.00015345664,0.00008530615,0.0003149254,0.000013360364,0.00017552634,0.00025069524,0.00015382077,0.000033609205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003123074,0.00024365663,0.018684052,0.00020706606,0.000040213614,0.000016562488,0.0030669456,0.4254333,0.0052073607,0.25482312,0.0006044804,0.291642],"study_design_scores_gemma":[0.00037139014,0.00023186307,0.0014060385,0.000028604407,0.0000030774838,0.00001667839,0.000012937782,0.9935584,0.0013151942,0.0009394316,0.0019464147,0.00016995144],"about_ca_topic_score_codex":0.0000018794183,"about_ca_topic_score_gemma":2.0247664e-7,"teacher_disagreement_score":0.6760718,"about_ca_system_score_codex":0.00004328804,"about_ca_system_score_gemma":0.000017505634,"threshold_uncertainty_score":0.625778},"labels":[],"label_agreement":null},{"id":"W2525766229","doi":"10.1109/tnet.2015.2480418","title":"An Asynchronous Fixed-Point Algorithm for Resource Sharing With Coupled Objectives","year":2015,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Networking","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Alberta","funders":"","keywords":"Computer science; Subgradient method; Mathematical optimization; Distributed algorithm; Asynchronous communication; Convergence (economics); Gradient descent; Resource allocation; Distributed computing; Algorithm; Mathematics","score_opus":0.030646572589519035,"score_gpt":0.26949438514312657,"score_spread":0.23884781255360754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2525766229","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037989847,0.00005509657,0.99673647,0.00014791547,0.00066764664,0.00069548836,0.0000052931387,0.0010503073,0.0002618814],"genre_scores_gemma":[0.30943605,0.0000058694213,0.6897684,0.00016817766,0.00024813449,0.00026841607,0.0000058095966,0.000045717512,0.000053456217],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980967,0.00005483804,0.00029388352,0.00072584156,0.00035479572,0.0004739094],"domain_scores_gemma":[0.99810266,0.00023376953,0.0001422336,0.0010735118,0.00020366,0.0002441478],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048262297,0.0002689134,0.00025301837,0.00025235227,0.0003954134,0.00027480125,0.0010550062,0.0001058693,0.0000043704827],"category_scores_gemma":[0.000012667414,0.0002575111,0.000081410355,0.00063179387,0.00006989832,0.0005670036,0.000014313884,0.00024347624,0.0000039757992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000779942,0.0002633525,0.00003886256,0.00001001941,0.00008117153,0.000010380755,0.0022411144,0.6782054,0.000052414467,0.0008565834,0.00013173763,0.318031],"study_design_scores_gemma":[0.0008398566,0.0010079477,0.000016855533,0.000111058514,0.000029299337,0.00004458191,0.000168822,0.9926643,0.0012322457,0.0030939702,0.00044637354,0.0003446956],"about_ca_topic_score_codex":0.000037926613,"about_ca_topic_score_gemma":0.000028191065,"teacher_disagreement_score":0.31768632,"about_ca_system_score_codex":0.00023004637,"about_ca_system_score_gemma":0.00010577267,"threshold_uncertainty_score":0.9999877},"labels":[],"label_agreement":null},{"id":"W2537671543","doi":"10.1109/globalsip.2013.6736958","title":"A sparse randomized Kaczmarz algorithm","year":2013,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Overdetermined system; Underdetermined system; Convergence (economics); Linear system; Speedup; Mathematics; Algorithm; Compressed sensing; System of linear equations; Sparse matrix; Computer science; Mathematical optimization; Applied mathematics; Parallel computing","score_opus":0.008814091336683528,"score_gpt":0.21398606552515087,"score_spread":0.20517197418846733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2537671543","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000040588537,0.000022054448,0.9752512,0.0010247598,0.00018880665,0.0006474226,2.069355e-7,0.00088971405,0.021935258],"genre_scores_gemma":[0.010952557,0.0000072224657,0.98579335,0.0007404691,0.0000227979,0.0002677004,0.0000011309152,0.000006478561,0.002208316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991056,0.00006146946,0.00021769687,0.00023806453,0.00018704569,0.00019017453],"domain_scores_gemma":[0.9991218,0.00018718012,0.00005948782,0.00041860543,0.0001261604,0.000086758075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002642061,0.000101762904,0.00021729991,0.00011435101,0.00004556128,0.0001705756,0.00054520037,0.000038450802,0.0005094495],"category_scores_gemma":[0.00011801833,0.00007589524,0.00007777442,0.00026601367,0.000060811322,0.0004740496,0.00016189173,0.000051934796,0.0004994361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047746576,0.00006675556,0.000007928985,0.000002736362,0.000027807238,0.000003029435,0.00027533292,0.00008289372,0.00005477703,0.8195977,0.024576267,0.155257],"study_design_scores_gemma":[0.013426866,0.000018012335,0.00001571606,0.0000046045907,0.0000032632997,0.000009369277,0.000005340403,0.91259027,0.00082127657,0.07273061,0.00024717682,0.00012748837],"about_ca_topic_score_codex":0.000105301115,"about_ca_topic_score_gemma":3.2593275e-7,"teacher_disagreement_score":0.9125074,"about_ca_system_score_codex":0.000016518556,"about_ca_system_score_gemma":0.000020379699,"threshold_uncertainty_score":0.6419407},"labels":[],"label_agreement":null},{"id":"W2556540011","doi":"","title":"Convex Two-Layer Modeling with Latent Structure","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Waterloo","funders":"","keywords":"Inference; Computer science; Artificial intelligence; Maximum a posteriori estimation; Normalization (sociology); A priori and a posteriori; Structured prediction; Latent variable; Representation (politics); Machine learning; Algorithm; Mathematical optimization; Mathematics; Maximum likelihood; Statistics","score_opus":0.020898063017602327,"score_gpt":0.23722487203319947,"score_spread":0.21632680901559714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2556540011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010084499,0.000035091572,0.98787665,0.0003714748,0.00027952093,0.00028907397,0.0000039981014,0.0006531985,0.0004065171],"genre_scores_gemma":[0.9817044,0.0000010804494,0.017947275,0.0002162152,0.00003848145,0.000033118573,0.000004652375,0.000007936883,0.00004681021],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878585,0.000023722023,0.00040801795,0.0001648023,0.0003962053,0.00022136973],"domain_scores_gemma":[0.99893165,0.000020211299,0.00027759382,0.0002701619,0.00042678323,0.00007360991],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012015206,0.00015337374,0.00014773071,0.00017174146,0.00015035781,0.0005333885,0.00039918997,0.000055078537,0.000004048096],"category_scores_gemma":[0.000025379846,0.00008757972,0.000019449346,0.00031106954,0.000027818556,0.0049142637,0.000059831254,0.00007346408,0.000014981032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044571625,0.000023056402,0.0007911422,0.00040360412,0.000029923582,0.0000043043683,0.0041193655,0.7415978,0.0024705355,0.13103552,0.0005005286,0.11897969],"study_design_scores_gemma":[0.0004089742,0.00004854539,0.000016444483,0.00019319686,0.0000034130373,0.00007929371,0.00003354241,0.99779564,0.0008112885,0.0003374402,0.000111607624,0.0001606168],"about_ca_topic_score_codex":0.000012672121,"about_ca_topic_score_gemma":5.046486e-7,"teacher_disagreement_score":0.9716199,"about_ca_system_score_codex":0.00006639275,"about_ca_system_score_gemma":0.00006623774,"threshold_uncertainty_score":0.5143478},"labels":[],"label_agreement":null},{"id":"W2588576771","doi":"10.1109/allerton.2016.7852337","title":"Anytime coding for distributed computation","year":2016,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Matrix multiplication; Computation; Coding (social sciences); Theoretical computer science; Distributed computing; Latency (audio); Parallel computing; Algorithm; Mathematics","score_opus":0.022634756769156706,"score_gpt":0.26648205479246795,"score_spread":0.24384729802331123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588576771","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006439385,0.000002876836,0.9968102,0.0016693088,0.00011493343,0.00021559217,0.000009508362,0.000648272,0.00046490645],"genre_scores_gemma":[0.3189384,0.0000011883535,0.68073064,0.00009889933,0.00001497154,0.000033226224,0.0000065013196,0.000003987738,0.00017219539],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994853,0.00000891597,0.00011708036,0.00017651645,0.00008537597,0.0001268248],"domain_scores_gemma":[0.99945986,0.00020334941,0.000045334476,0.00014083584,0.000111782974,0.00003883541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010442289,0.000055998076,0.00006135096,0.00005490288,0.000056133445,0.000045322307,0.00023145374,0.000023765491,0.000010543157],"category_scores_gemma":[0.00009916438,0.00003705685,0.000026738182,0.00014508556,0.000016957974,0.00026057597,0.00005492393,0.000010023748,0.00001379932],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039449665,0.000025725694,0.00007821764,0.000004701474,0.000007391201,4.3432073e-7,0.00004065185,0.00023582498,0.0033531098,0.932003,0.017832479,0.046414472],"study_design_scores_gemma":[0.00085864664,0.0001580073,0.00042423446,0.000037427566,0.0000042485603,0.000006869255,0.0000043433997,0.861374,0.035329502,0.0997818,0.0017862663,0.0002346564],"about_ca_topic_score_codex":0.0000010713343,"about_ca_topic_score_gemma":2.0243559e-7,"teacher_disagreement_score":0.86113816,"about_ca_system_score_codex":0.00003643908,"about_ca_system_score_gemma":0.000014818668,"threshold_uncertainty_score":0.15111344},"labels":[],"label_agreement":null},{"id":"W2593397662","doi":"10.48550/arxiv.1703.02403","title":"On Structured Prediction Theory with Calibrated Convex Surrogate Losses","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Mathematical optimization; Structured prediction; Stochastic gradient descent; Convex optimization; Regular polygon; Context (archaeology); Convex function; Minification; Consistency (knowledge bases); Intuition; Artificial intelligence; Machine learning; Mathematics; Artificial neural network","score_opus":0.04456457467752397,"score_gpt":0.181467611568874,"score_spread":0.13690303689135003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593397662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05704505,0.000013452142,0.9383777,0.000049296512,0.00055719813,0.00047329464,0.000054733588,0.0009689679,0.0024603454],"genre_scores_gemma":[0.9943485,0.000032645283,0.004467716,0.00006875963,0.00003544748,0.0000026588905,0.000046882822,0.000026458596,0.0009708876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981144,0.00017433384,0.0001681126,0.0011054069,0.00014731781,0.00029040585],"domain_scores_gemma":[0.99712986,0.00015858491,0.00045158918,0.0018464727,0.00026254167,0.00015096703],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021114267,0.00036506166,0.00032536115,0.00032202783,0.00028901864,0.0002751992,0.001936411,0.00031047378,0.000040359657],"category_scores_gemma":[0.00008785954,0.00034911346,0.000094980336,0.00029373495,0.00027379894,0.00047566625,0.0008293691,0.0004966689,0.000017718396],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012099284,0.000047769878,0.0009227329,0.000033278306,0.0001067571,0.00015894872,0.00013796514,0.26697826,0.0000099671515,0.7310249,0.00027728116,0.00018108901],"study_design_scores_gemma":[0.0007108975,0.00025735248,0.0015287679,0.00024468102,0.00008004405,0.000010571517,0.00002121729,0.6215866,0.00094097696,0.37409934,0.000042316253,0.0004771699],"about_ca_topic_score_codex":0.00005525072,"about_ca_topic_score_gemma":0.0000132578725,"teacher_disagreement_score":0.9373035,"about_ca_system_score_codex":0.00015575704,"about_ca_system_score_gemma":0.00023884344,"threshold_uncertainty_score":0.9998961},"labels":[],"label_agreement":null},{"id":"W2596625124","doi":"","title":"Nearly-tight VC-dimension bounds for piecewise linear neural networks","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"","keywords":"Dimension (graph theory); Upper and lower bounds; Piecewise linear function; Mathematics; Combinatorics; Omega; Piecewise; VC dimension; Function (biology); Range (aeronautics); Artificial neural network; Discrete mathematics; Mathematical analysis; Physics; Computer science","score_opus":0.06326245405350339,"score_gpt":0.20354528134638178,"score_spread":0.1402828272928784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2596625124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027220227,0.000018415565,0.97062594,0.00021637871,0.00055841904,0.0003144592,0.0000027261701,0.00037407145,0.0006693476],"genre_scores_gemma":[0.9717298,0.000014702656,0.026898624,0.00014356036,0.00008850531,0.0000019382694,0.000005224355,0.000015644466,0.001102011],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879944,0.000032463042,0.00013872512,0.0006020685,0.000066902816,0.00036038682],"domain_scores_gemma":[0.99807036,0.00009710233,0.00021858093,0.0012620484,0.00019456964,0.00015735258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018130007,0.00017838393,0.00017721907,0.00012431564,0.00084986974,0.0002551481,0.0015431134,0.000115786286,0.00001007241],"category_scores_gemma":[0.00009214447,0.00019397175,0.00012187829,0.00022363379,0.00015445265,0.0010300899,0.00048341815,0.00013402282,0.000012795717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008181243,0.00012294106,0.0033638228,0.000014638481,0.000045549437,0.000102276565,0.00016125958,0.3793272,0.00007724849,0.61124927,0.0023620152,0.0030919565],"study_design_scores_gemma":[0.0005854048,0.00014291308,0.0007297173,0.00001467289,0.000020479163,0.0000045777,0.00000573312,0.9901335,0.00021045479,0.0075056464,0.00042482305,0.00022205987],"about_ca_topic_score_codex":0.000034235924,"about_ca_topic_score_gemma":0.000008474907,"teacher_disagreement_score":0.94450957,"about_ca_system_score_codex":0.00006659669,"about_ca_system_score_gemma":0.00003609918,"threshold_uncertainty_score":0.79099387},"labels":[],"label_agreement":null},{"id":"W2597452529","doi":"10.48550/arxiv.1703.04782","title":"Online Learning Rate Adaptation with Hypergradient Descent","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Stochastic gradient descent; Gradient descent; Rate of convergence; Range (aeronautics); Computation; Convergence (economics); Adaptation (eye); Online machine learning; Descent (aeronautics); Mode (computer interface); Artificial intelligence; Mathematical optimization; Machine learning; Algorithm; Active learning (machine learning); Mathematics; Artificial neural network; Key (lock)","score_opus":0.08496107352918601,"score_gpt":0.19461228294031724,"score_spread":0.10965120941113123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2597452529","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060915418,0.00003321239,0.93696177,0.00011634029,0.00030296962,0.0003523991,0.00000627147,0.00062017416,0.00069143367],"genre_scores_gemma":[0.94970524,0.00013650602,0.048772637,0.000038234324,0.000040829753,0.0000022532174,0.000049221162,0.000023845538,0.0012312345],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998225,0.00013806442,0.00017533835,0.0010269987,0.000116767456,0.00031784843],"domain_scores_gemma":[0.99769425,0.00006836835,0.00052025716,0.0012435652,0.00031562318,0.00015796123],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022504567,0.0003200913,0.00028888424,0.00029851013,0.00034817867,0.00022895502,0.0016901344,0.00018121302,0.00000761917],"category_scores_gemma":[0.00008785023,0.00033324288,0.00010510423,0.00026511398,0.0001269188,0.0004057326,0.0011466285,0.00059094845,0.000018021108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002551047,0.000118688324,0.00089470536,0.000028688766,0.000061295104,0.00014682344,0.00033046002,0.912534,0.000007518436,0.08421464,0.00004148088,0.0015961874],"study_design_scores_gemma":[0.00039263314,0.00016022882,0.0015681592,0.000205117,0.000065211825,0.000007233202,0.00006192622,0.9862784,0.000079323436,0.010560882,0.00020901096,0.00041185317],"about_ca_topic_score_codex":0.00013293736,"about_ca_topic_score_gemma":0.0000525245,"teacher_disagreement_score":0.88878983,"about_ca_system_score_codex":0.0002549296,"about_ca_system_score_gemma":0.00018879016,"threshold_uncertainty_score":0.99991196},"labels":[],"label_agreement":null},{"id":"W2604117713","doi":"10.48550/arxiv.1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":250,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Overfitting; Generalization; Computer science; Artificial neural network; Maxima and minima; Regularization (linguistics); Early stopping; Artificial intelligence; Machine learning; Algorithm; Test data; Mathematics","score_opus":0.14490765418862314,"score_gpt":0.23700132353814402,"score_spread":0.09209366934952087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604117713","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01650597,0.000035129313,0.98086035,0.00009569692,0.00075276534,0.0009936951,0.000047002017,0.000639743,0.000069649745],"genre_scores_gemma":[0.8133399,0.000011371972,0.18584861,0.00007663408,0.00011640779,0.000004698823,0.00047252473,0.000047845366,0.00008203855],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970118,0.00008291841,0.0003086447,0.0018117148,0.00017013433,0.0006148114],"domain_scores_gemma":[0.99537617,0.00021516361,0.00079843367,0.0031135846,0.00029583034,0.00020080383],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039507356,0.00049927377,0.0005068003,0.00031489096,0.0006699547,0.00065449113,0.0048542954,0.00031308306,0.0000017689017],"category_scores_gemma":[0.00011841837,0.0005474736,0.00013280976,0.0003447445,0.0002556049,0.00075898546,0.003103528,0.0004539636,0.0000012564088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003760473,0.000030242358,0.00021153876,0.000034669018,0.00009721989,0.0000518093,0.00047384296,0.9752072,0.0000010268403,0.022000544,0.00008177815,0.0017725172],"study_design_scores_gemma":[0.0006078413,0.000119752636,0.00011883896,0.00014495313,0.00014907923,0.000025231917,0.00007298929,0.9947014,0.0000052847836,0.0034366162,0.000009113763,0.0006089124],"about_ca_topic_score_codex":0.00008638726,"about_ca_topic_score_gemma":0.000031673364,"teacher_disagreement_score":0.7968339,"about_ca_system_score_codex":0.00016578723,"about_ca_system_score_gemma":0.00017040226,"threshold_uncertainty_score":0.9996977},"labels":[],"label_agreement":null},{"id":"W2740620148","doi":"10.48550/arxiv.1708.00768","title":"Streaming kernel regression with provably adaptive mean, variance, and regularization","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université Laval","funders":"","keywords":"Regularization (linguistics); Kernel regression; Regression; Computer science; Variance (accounting); Statistics; Kernel (algebra); Mathematics; Econometrics; Artificial intelligence; Discrete mathematics; Economics","score_opus":0.048922980596073806,"score_gpt":0.19064659149997468,"score_spread":0.14172361090390087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740620148","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005169966,0.000040017432,0.9909943,0.00006301026,0.00017569511,0.0005481183,0.000008180495,0.0004154682,0.0025852735],"genre_scores_gemma":[0.9069938,0.0000935455,0.09058133,0.000020309719,0.00003360638,0.000003816641,0.000017544326,0.000022995066,0.0022330387],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815696,0.00008585359,0.00015630203,0.0012049875,0.0001389735,0.00025693656],"domain_scores_gemma":[0.9974988,0.000055347795,0.0005854935,0.0014216085,0.00030726485,0.00013147465],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001896053,0.00033167913,0.00030508783,0.00027269672,0.00035732932,0.00027002132,0.0012253061,0.00026727296,0.0000033368121],"category_scores_gemma":[0.000049314734,0.00031649138,0.00005298579,0.00028197988,0.0001983883,0.0007354995,0.0015121399,0.00035708988,0.000002190457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098214645,0.00008891542,0.0015382521,0.00008896308,0.00011376985,0.00023006728,0.0007039049,0.10205054,0.000030392957,0.89228255,0.00013877463,0.0026356785],"study_design_scores_gemma":[0.00044783315,0.00014005524,0.00075051514,0.00062691467,0.00006391625,0.000012638756,0.00004193217,0.9116363,0.00023807026,0.08559781,0.00002495697,0.00041903162],"about_ca_topic_score_codex":0.00008051541,"about_ca_topic_score_gemma":0.000018628461,"teacher_disagreement_score":0.9018238,"about_ca_system_score_codex":0.00014377582,"about_ca_system_score_gemma":0.00019648147,"threshold_uncertainty_score":0.9999287},"labels":[],"label_agreement":null},{"id":"W2750933313","doi":"","title":"Distributed Second-Order Optimization using Kronecker-Factored Approximations","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Stochastic gradient descent; Computer science; Computation; Overhead (engineering); Artificial neural network; Curvature; Algorithm; Machine learning; Scaling; Artificial intelligence; Mathematical optimization; Mathematics","score_opus":0.08007162583441403,"score_gpt":0.35911400772572205,"score_spread":0.27904238189130803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750933313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003326474,0.0000025585862,0.96762484,0.002297752,0.00060098764,0.0002812279,0.00003258543,0.00030381078,0.025529735],"genre_scores_gemma":[0.70612127,0.000008581649,0.29238847,0.000050478153,0.000059480604,0.00005980489,0.00022857406,0.000016254618,0.0010670803],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823004,0.00009106645,0.0003743034,0.00055014016,0.000518096,0.00023634153],"domain_scores_gemma":[0.99741155,0.00013262714,0.000560761,0.0008626862,0.0009269862,0.00010540107],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00018936043,0.000195645,0.00016275051,0.0002949791,0.001078124,0.001440318,0.0015179005,0.00009151713,0.0008622464],"category_scores_gemma":[0.0015278208,0.00021289614,0.00007445255,0.0002123238,0.00013737915,0.0014811622,0.00033361473,0.00029787322,0.000050224324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012554414,0.00013252799,0.0043354584,0.0000045526813,0.00007767584,0.000007299893,0.000788675,0.5831189,0.00061323715,0.40832716,0.00022317309,0.0023587472],"study_design_scores_gemma":[0.00036499972,0.000040217452,0.0039764936,0.00004411042,0.000009361835,0.000012070261,0.000105298626,0.99003595,0.0004701712,0.0044340855,0.0002909507,0.0002162613],"about_ca_topic_score_codex":0.0000660471,"about_ca_topic_score_gemma":0.000008406027,"teacher_disagreement_score":0.7027948,"about_ca_system_score_codex":0.0001397017,"about_ca_system_score_gemma":0.00015142499,"threshold_uncertainty_score":0.9995963},"labels":[],"label_agreement":null},{"id":"W2754127623","doi":"10.1007/s11081-017-9366-1","title":"Best practices for comparing optimization algorithms","year":2017,"lang":"en","type":"article","venue":"Optimization and Engineering","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":189,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Benchmarking; Best practice; Process (computing); Task (project management); Financial engineering; Optimization algorithm","score_opus":0.056139760934673856,"score_gpt":0.2990190674639251,"score_spread":0.24287930652925124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754127623","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000058915593,0.000053581945,0.99759686,0.0004025373,0.00032968193,0.0002784219,0.000001588433,0.00031440204,0.0009640133],"genre_scores_gemma":[0.02902005,0.00010475069,0.97054714,0.000025527257,0.00006278026,0.00006673351,0.000012685463,0.00001920399,0.00014114715],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922276,0.000006771187,0.0001816479,0.00028870575,0.000116428695,0.00018368174],"domain_scores_gemma":[0.99896675,0.00006903446,0.0003274887,0.00041866777,0.00013664215,0.00008140705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018707401,0.00013391358,0.00014283445,0.00012412107,0.00043019204,0.0007685301,0.00043371928,0.000064030566,0.0000048615916],"category_scores_gemma":[0.0005426955,0.00014656554,0.000027236914,0.000083391154,0.000019560017,0.0013498614,0.00015076116,0.000060794802,9.4346524e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016787154,0.000014013768,0.00008574624,0.000020688583,0.000008840594,4.4935837e-7,0.00007060734,0.98717827,0.000019274155,0.010601511,0.000027667827,0.001971285],"study_design_scores_gemma":[0.00032595877,0.00003701278,0.000048923714,0.000039963616,0.000010583464,0.0000081959,0.000008808262,0.9987237,0.00016961795,0.000034642922,0.00042158918,0.00017101792],"about_ca_topic_score_codex":0.0000188879,"about_ca_topic_score_gemma":9.991131e-7,"teacher_disagreement_score":0.028961133,"about_ca_system_score_codex":0.000024757273,"about_ca_system_score_gemma":0.000015655216,"threshold_uncertainty_score":0.74109536},"labels":[],"label_agreement":null},{"id":"W2774777068","doi":"10.1007/s11590-018-1325-z","title":"“Active-set complexity” of proximal gradient: How long does it take to find the sparsity pattern?","year":2018,"lang":"en","type":"article","venue":"Optimization Letters","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Separable space; Proximal Gradient Methods; Minification; Convex function; Computational intelligence; Regular polygon; Function (biology); Convex optimization","score_opus":0.0346326266348508,"score_gpt":0.25041753848601944,"score_spread":0.21578491185116866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774777068","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0086319,0.0000022743168,0.9408438,0.049103767,0.00038913506,0.00066191587,0.000026829379,0.00017243475,0.00016790899],"genre_scores_gemma":[0.62499905,0.0000031993754,0.36582547,0.0087129045,0.00015279365,0.000063440435,0.00003561095,0.00002585881,0.0001816539],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998348,0.00011598979,0.00028050033,0.00048517738,0.00043896883,0.00033138518],"domain_scores_gemma":[0.9984865,0.00008567516,0.00027185207,0.0007491958,0.00030091446,0.000105849715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026001895,0.000210105,0.00021042157,0.00022607567,0.00027725066,0.00019582377,0.001098386,0.000056429726,0.00008881811],"category_scores_gemma":[0.000113384194,0.00015254889,0.00007254673,0.0007613869,0.0004034216,0.0005101622,0.0003252211,0.00011392435,0.000013629573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002091848,0.00070169184,0.013698436,0.00015969542,0.0003699553,0.000033493994,0.03635349,0.7820023,0.004780303,0.043803565,0.09725877,0.020629138],"study_design_scores_gemma":[0.00064885226,0.00034735014,0.011598259,0.00010052102,0.000034375676,0.000018774494,0.00015486646,0.9619675,0.023119364,0.00032258953,0.0011154426,0.00057208777],"about_ca_topic_score_codex":0.00003877901,"about_ca_topic_score_gemma":0.000023934223,"teacher_disagreement_score":0.61636716,"about_ca_system_score_codex":0.0000736001,"about_ca_system_score_gemma":0.000027780077,"threshold_uncertainty_score":0.62207633},"labels":[],"label_agreement":null},{"id":"W2780752111","doi":"10.1007/s10589-020-00220-z","title":"Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods","year":2020,"lang":"en","type":"preprint","venue":"Computational Optimization and Applications","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Iterated function; Stochastic gradient descent; Momentum (technical analysis); Mathematics; Rate of convergence; Stochastic optimization; Applied mathematics; Ball (mathematics); Stochastic approximation; Mathematical optimization; Mathematical analysis; Computer science; Finance; Artificial neural network","score_opus":0.033326208747696866,"score_gpt":0.320718223472419,"score_spread":0.28739201472472214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2780752111","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004345071,0.0006967129,0.98711014,0.0072042686,0.00015906835,0.0041815736,0.0001172377,0.0004604736,0.00002710493],"genre_scores_gemma":[0.027492907,0.00009651434,0.96823573,0.0003606078,0.00010503281,0.0030527415,0.00054647797,0.000056141263,0.000053820128],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99721515,0.00010781935,0.00066424545,0.0013445485,0.00032432974,0.00034390317],"domain_scores_gemma":[0.9975739,0.00056249794,0.0005161942,0.00042853956,0.00051265553,0.00040621992],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003620624,0.0004925378,0.00049969036,0.00038050316,0.000475334,0.00056233385,0.00046020452,0.0002034921,0.00000562027],"category_scores_gemma":[0.00015800887,0.0005460698,0.000081440376,0.0004554356,0.00024148733,0.00028881835,0.001053603,0.00030584045,0.0000012756902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011269296,0.00008090597,0.0000055148475,0.00013598196,0.000051341114,2.324287e-7,0.00040548676,0.7572226,0.00001757167,0.23924333,0.00034763993,0.0024781316],"study_design_scores_gemma":[0.0006245241,0.00010274387,0.0000784949,0.000071451555,0.00008461512,0.0000216245,0.00004485656,0.85967594,0.000019999019,0.13869628,0.00015150136,0.0004279684],"about_ca_topic_score_codex":0.0000060484936,"about_ca_topic_score_gemma":5.745082e-7,"teacher_disagreement_score":0.102453336,"about_ca_system_score_codex":0.000116782525,"about_ca_system_score_gemma":0.00019229748,"threshold_uncertainty_score":0.99969906},"labels":[],"label_agreement":null},{"id":"W2782985982","doi":"10.1109/icmla.2017.0-166","title":"Anytime Exploitation of Stragglers in Synchronous Stochastic Gradient Descent","year":2017,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Descent (aeronautics); Stochastic gradient descent; Artificial intelligence; Engineering; Aerospace engineering; Artificial neural network","score_opus":0.02369414696757149,"score_gpt":0.2663900930483598,"score_spread":0.24269594608078832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782985982","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028530495,0.000017298047,0.96930707,0.00022625983,0.00018967834,0.00029957684,0.0000010137086,0.00012823919,0.0013003506],"genre_scores_gemma":[0.8380984,0.0000033163128,0.16178867,0.000021030031,0.000007141605,0.000026504995,9.836714e-7,0.0000060992174,0.000047818077],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989508,0.00002228731,0.000294671,0.00028487868,0.00023415427,0.00021323226],"domain_scores_gemma":[0.99874985,0.000054752134,0.0002353017,0.00079750124,0.00009444455,0.000068156645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021114039,0.000112962916,0.00016215963,0.00021822145,0.00010368949,0.00010271576,0.0009386703,0.00004308442,0.000018504634],"category_scores_gemma":[0.00018304559,0.00010974176,0.000040567433,0.00012363566,0.00009265427,0.0005567284,0.0001770268,0.000065001346,0.000008163403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041317046,0.00089365884,0.0032968398,0.000084025116,0.000046528356,0.000028379123,0.00572758,0.077403575,0.003418939,0.8374604,0.00058501563,0.071013734],"study_design_scores_gemma":[0.0010463083,0.00042247097,0.05784495,0.00019949846,0.000009533526,0.000013871126,0.00018516801,0.9079193,0.009648311,0.022290451,0.0000067085034,0.00041344698],"about_ca_topic_score_codex":0.000116778516,"about_ca_topic_score_gemma":0.000021849966,"teacher_disagreement_score":0.8305157,"about_ca_system_score_codex":0.00009347636,"about_ca_system_score_gemma":0.000055963115,"threshold_uncertainty_score":0.44751394},"labels":[],"label_agreement":null},{"id":"W2788204593","doi":"10.1145/3152494.3152498","title":"Are saddles good enough for neural networks","year":2018,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Maxima and minima; MNIST database; Degeneracy (biology); Artificial neural network; Saddle point; Gradient descent; Computer science; Saddle; Convergence (economics); Perspective (graphical); Work (physics); Deep neural networks; Artificial intelligence; Mathematical optimization; Machine learning; Mathematics; Engineering; Geometry; Economics; Mathematical analysis","score_opus":0.027691926277695213,"score_gpt":0.2642360515460286,"score_spread":0.23654412526833338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788204593","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021559924,0.00002315578,0.994754,0.0010371222,0.00044421677,0.00025635635,0.000001407624,0.00067004137,0.0025981106],"genre_scores_gemma":[0.48297322,0.0000010031779,0.5148148,0.001173188,0.0002339634,0.000053051637,0.0000017410963,0.000009166238,0.000739853],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992763,0.0000123271475,0.00013208277,0.00025629767,0.00009814337,0.00022483927],"domain_scores_gemma":[0.9992712,0.00007005822,0.00009364168,0.00035131283,0.00015917853,0.00005462369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009671448,0.000090533664,0.000092915296,0.000054072563,0.00012076936,0.00010132191,0.0005462008,0.000047459034,0.000024946256],"category_scores_gemma":[0.00006147298,0.00007755117,0.000042366948,0.0002203086,0.000052958596,0.00022419528,0.00013123135,0.000037058668,0.000008442456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008707285,0.00006369791,0.00049385335,0.0000068006425,0.000015053724,0.0000016980753,0.00023454387,0.0042022895,0.000022373455,0.9292123,0.041438196,0.024300542],"study_design_scores_gemma":[0.0001295582,0.00015038277,0.00036524396,0.0000061337278,0.0000024773024,0.000005236533,0.000010338205,0.9900397,0.00078351714,0.005845263,0.0025479374,0.000114219336],"about_ca_topic_score_codex":0.000003945502,"about_ca_topic_score_gemma":0.000006594973,"teacher_disagreement_score":0.9858374,"about_ca_system_score_codex":0.000014691529,"about_ca_system_score_gemma":0.000007873714,"threshold_uncertainty_score":0.31624448},"labels":[],"label_agreement":null},{"id":"W2795626670","doi":"10.48550/arxiv.1804.00325","title":"Aggregated Momentum: Stability Through Passive Damping","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Momentum (technical analysis); Convergence (economics); Quadratic equation; BETA (programming language); Gradient descent; Stability (learning theory); Physics; Instability; Rate of convergence; Curvature; Control theory (sociology); Applied mathematics; Mathematics; Mathematical analysis; Computer science; Classical mechanics; Mechanics; Geometry; Telecommunications","score_opus":0.10121386303783678,"score_gpt":0.205414326185407,"score_spread":0.10420046314757023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795626670","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0590766,0.000026835021,0.9348478,0.00014131861,0.0008424426,0.0006016249,0.00001970713,0.0011516311,0.0032920914],"genre_scores_gemma":[0.962381,0.00009001599,0.03695837,0.00011493696,0.00007286703,0.0000048087168,0.000031831012,0.000025235837,0.00032092843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972205,0.00018336865,0.0003147631,0.0016434096,0.00016503934,0.00047291076],"domain_scores_gemma":[0.9965769,0.00013300979,0.00050504314,0.0021002493,0.00052456005,0.00016023077],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023618378,0.00041802673,0.00040373614,0.00023428434,0.00023431638,0.00018054954,0.0024867472,0.00035490296,0.000111791676],"category_scores_gemma":[0.00013241477,0.00049045077,0.00020295504,0.0009543593,0.0003134238,0.00067379,0.003399587,0.0004960961,0.00008367431],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006897609,0.00049591006,0.002517266,0.00024891598,0.00038104475,0.00034072073,0.0031588771,0.09576351,0.00013238538,0.89210874,0.0040441933,0.0007394427],"study_design_scores_gemma":[0.00043910785,0.00013028695,0.00020803549,0.00022387372,0.000063683176,0.00000436513,0.00008666505,0.6834265,0.003920813,0.31041124,0.00032605353,0.00075935596],"about_ca_topic_score_codex":0.00012327766,"about_ca_topic_score_gemma":0.000008536789,"teacher_disagreement_score":0.9033044,"about_ca_system_score_codex":0.0005256378,"about_ca_system_score_gemma":0.00025794614,"threshold_uncertainty_score":0.9997547},"labels":[],"label_agreement":null},{"id":"W2798888671","doi":"","title":"Linear Stochastic Approximation: How Far Does Constant Step-Size and Iterate Averaging Go?","year":2018,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Constant (computer programming); Applied mathematics; Computer science","score_opus":0.06654015255569296,"score_gpt":0.3147389566761767,"score_spread":0.24819880412048373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798888671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052965333,0.000011400716,0.9943765,0.0024453797,0.00072922866,0.00022691417,0.000115306546,0.00012803233,0.0014375966],"genre_scores_gemma":[0.69769967,0.000054227996,0.30153742,0.00034082407,0.000118031065,0.00001908534,0.000012987212,0.000009031702,0.00020873289],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845994,0.00006295521,0.0003585904,0.0004942582,0.00039190464,0.00023237504],"domain_scores_gemma":[0.9982053,0.00050780026,0.0001800627,0.00023633863,0.0007482029,0.00012228733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027907005,0.00021287506,0.00018282002,0.00016933962,0.00022028708,0.0007357004,0.00043223248,0.00006523228,0.0001235996],"category_scores_gemma":[0.0007130423,0.00018029491,0.000019754481,0.00016484373,0.00045050678,0.0003654795,0.00017458953,0.00015399454,0.00003476945],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032175867,0.000034804187,0.0000142677845,0.0000066228367,0.000017548811,0.0000074406425,0.00077454007,0.00008187721,0.00032781204,0.92907655,0.00008335652,0.06954303],"study_design_scores_gemma":[0.000042123913,0.00019539167,0.00003071262,0.000062108375,0.000006176498,0.000019398132,0.00024401277,0.7577154,0.0015895653,0.2397873,0.00011630413,0.0001915195],"about_ca_topic_score_codex":0.0000137735115,"about_ca_topic_score_gemma":0.000028213575,"teacher_disagreement_score":0.7576335,"about_ca_system_score_codex":0.000039700935,"about_ca_system_score_gemma":0.000071513125,"threshold_uncertainty_score":0.7352213},"labels":[],"label_agreement":null},{"id":"W2808411657","doi":"10.1101/348557","title":"Hyperparameter-free optimizer of stochastic gradient descent that incorporates unit correction and moment estimation","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Hyperparameter; Stochastic gradient descent; Benchmark (surveying); Computer science; Gradient descent; Moment (physics); Rate of convergence; Convergence (economics); Artificial intelligence; Mathematical optimization; Artificial neural network; Machine learning; Mathematics; Key (lock)","score_opus":0.022843793325641258,"score_gpt":0.22389735747941175,"score_spread":0.2010535641537705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808411657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09987178,0.00022954907,0.89587134,0.00013841766,0.0021278197,0.001080046,0.000044370823,0.00063239393,0.0000042805946],"genre_scores_gemma":[0.6491726,0.00004055814,0.35044485,0.00003476864,0.00005445492,0.00019915639,5.5420907e-7,0.000050192135,0.0000028849008],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969138,0.00015318459,0.00070053525,0.0011488779,0.0006315631,0.0004520318],"domain_scores_gemma":[0.99563825,0.00015632689,0.0010325445,0.0020738808,0.00082916865,0.00026983453],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006934313,0.0005930611,0.00063537405,0.00070201745,0.00019724967,0.00032469825,0.0012828605,0.00038050377,0.000009510964],"category_scores_gemma":[0.00037992466,0.0006292506,0.00010803715,0.0007048461,0.00034160988,0.0004093636,0.0016715922,0.00041979775,0.000008325319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008110614,0.006295134,0.020833882,0.005622266,0.0029488706,0.00017252372,0.0015129154,0.6466145,0.16844888,0.13313994,0.012733938,0.0008661236],"study_design_scores_gemma":[0.0006944179,0.00031215802,0.007055553,0.00094749645,0.0001366103,2.2446403e-7,0.000003281021,0.8725068,0.11706182,0.00036747064,0.000030398029,0.00088374334],"about_ca_topic_score_codex":0.000042151885,"about_ca_topic_score_gemma":0.0000010306734,"teacher_disagreement_score":0.5493008,"about_ca_system_score_codex":0.00030504636,"about_ca_system_score_gemma":0.00030328953,"threshold_uncertainty_score":0.9996159},"labels":[],"label_agreement":null},{"id":"W2809745351","doi":"10.1109/isit.2018.8437871","title":"Exploitation of Stragglers in Coded Computation","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Exploit; Computation; Matrix multiplication; Block (permutation group theory); Algorithm; Code (set theory); Coding (social sciences); Matrix (chemical analysis); Parallel computing; Theoretical computer science; Mathematics; Statistics","score_opus":0.0393994696151646,"score_gpt":0.2957110805484088,"score_spread":0.25631161093324417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809745351","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073958607,0.000015184816,0.98868656,0.00013317636,0.0003806406,0.00041223955,0.0000029326272,0.000276886,0.002696542],"genre_scores_gemma":[0.44835564,0.0000063685184,0.5515241,0.000026885078,0.00001101428,0.00003075986,0.000018778328,0.0000061061714,0.00002034328],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998735,0.000057957048,0.00043772225,0.0003785521,0.00026845347,0.00012228044],"domain_scores_gemma":[0.9989446,0.000085963635,0.0002997315,0.00037203464,0.00026592158,0.000031786636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026383912,0.0001364666,0.0002126335,0.0004413841,0.000014442082,0.000052516552,0.0005833963,0.00014417132,0.000014997914],"category_scores_gemma":[0.00007167776,0.00014471005,0.000046586134,0.00031848447,0.000055406752,0.00017975528,0.00043414364,0.00013484403,0.000005055867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030792336,0.00053556147,0.0013641099,0.00049834396,0.00007312892,0.000007651661,0.00977771,0.5871382,0.00062361034,0.35919753,0.008385628,0.03236775],"study_design_scores_gemma":[0.00017574901,0.00006949839,0.0012777809,0.00013740678,0.0000029963123,8.0433165e-7,0.00003359502,0.8822881,0.003522868,0.11233367,0.0000030907784,0.00015443092],"about_ca_topic_score_codex":0.00007150412,"about_ca_topic_score_gemma":0.000013155179,"teacher_disagreement_score":0.44095978,"about_ca_system_score_codex":0.000074128984,"about_ca_system_score_gemma":0.00010390756,"threshold_uncertainty_score":0.5901105},"labels":[],"label_agreement":null},{"id":"W2809954131","doi":"10.1109/isit.2018.8437473","title":"Hierarchical Coded Computation","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Computation; Erasure; Matrix multiplication; Algorithm; Erasure code; Multiplication (music); Partition (number theory); Matrix (chemical analysis); Coding (social sciences); Theoretical computer science; Decoding methods; Mathematics","score_opus":0.02971116508146374,"score_gpt":0.29204057061263194,"score_spread":0.2623294055311682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809954131","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016713631,0.000016153841,0.9792156,0.0009277593,0.000955194,0.00036499873,0.0000032759137,0.0017248492,0.01662503],"genre_scores_gemma":[0.05411563,0.000005727968,0.9449546,0.0003989222,0.0001180538,0.00005096195,0.00003713674,0.000013631039,0.0003053352],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847215,0.00006663345,0.00029742284,0.000620466,0.00034224064,0.000201095],"domain_scores_gemma":[0.99874496,0.00009335097,0.00014722336,0.00067487423,0.0002443318,0.000095236996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021710963,0.0001965649,0.00020828671,0.00022309143,0.00006914485,0.000261692,0.0011798157,0.00021859321,0.000044086955],"category_scores_gemma":[0.0000730244,0.00018611281,0.00007882005,0.00020086428,0.000092072616,0.00011255362,0.0019744171,0.00030758104,0.00008788696],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007900665,0.00016538946,0.00006129634,0.000077711156,0.000060518363,0.000010790068,0.00067855226,0.015290327,0.00003534749,0.8695055,0.08572029,0.028386327],"study_design_scores_gemma":[0.00007521896,0.000045930334,0.00009873551,0.00003264551,0.0000036493295,0.000005263239,7.2782643e-7,0.74715036,0.00045144936,0.2517355,0.00021780237,0.00018271996],"about_ca_topic_score_codex":0.000012112815,"about_ca_topic_score_gemma":9.417479e-7,"teacher_disagreement_score":0.73186004,"about_ca_system_score_codex":0.0000636155,"about_ca_system_score_gemma":0.00012649593,"threshold_uncertainty_score":0.758946},"labels":[],"label_agreement":null},{"id":"W2810910646","doi":"10.1016/j.neucom.2018.06.002","title":"Mini-batch algorithms with Barzilai–Borwein update step","year":2018,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Stochastic gradient descent; Computer science; Sequence (biology); Algorithm; Regular polygon; Mathematical optimization; State (computer science); Stochastic optimization; Batch processing; Mathematics; Artificial intelligence","score_opus":0.011153209356397279,"score_gpt":0.23798865904669106,"score_spread":0.2268354496902938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810910646","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008616522,0.000011990018,0.98613447,0.0006156045,0.00041162202,0.0002871697,8.192511e-7,0.0011552909,0.0027665333],"genre_scores_gemma":[0.24884138,0.0000012924398,0.74964774,0.0011553875,0.0002494641,0.000012488938,0.0000018165478,0.000027161208,0.00006326229],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808604,0.0000692872,0.00029640988,0.0006865695,0.000391727,0.00046996176],"domain_scores_gemma":[0.99866587,0.000121035926,0.00016989029,0.0006593922,0.00024698264,0.00013685292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023285569,0.000228986,0.00019633808,0.00017679982,0.00028391898,0.0002358702,0.0010367429,0.000057427817,0.00001625935],"category_scores_gemma":[0.000046045563,0.00020395423,0.00004146666,0.00082101446,0.00012105089,0.0003095317,0.00042251017,0.0001746194,0.00009441825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007975509,0.0004957139,0.0040145125,0.000089252804,0.00011765742,0.00037367616,0.005006361,0.0048739356,0.0018388394,0.18194869,0.022743916,0.7784177],"study_design_scores_gemma":[0.0005756919,0.00063892995,0.0012346994,0.00006937099,0.000009195447,0.0001488356,0.000022119886,0.9831917,0.0069678547,0.0011140425,0.005604826,0.0004227291],"about_ca_topic_score_codex":0.0000123706295,"about_ca_topic_score_gemma":0.0000019537358,"teacher_disagreement_score":0.9783178,"about_ca_system_score_codex":0.000029665409,"about_ca_system_score_gemma":0.000060352813,"threshold_uncertainty_score":0.8317012},"labels":[],"label_agreement":null},{"id":"W2886166822","doi":"10.5430/air.v7n2p26","title":"Proposal of security preserving machine learning of IoT","year":2018,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cloud computing; Computer science; Server; Computation; Distributed computing; Information leakage; Enhanced Data Rates for GSM Evolution; Terminal (telecommunication); Cloud computing security; Limit (mathematics); Computer security; Artificial intelligence; Computer network; Operating system; Algorithm; Mathematics","score_opus":0.13175287832320842,"score_gpt":0.4080679640283466,"score_spread":0.2763150857051382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886166822","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041146412,0.00006847293,0.955317,0.00036732995,0.00010714965,0.00033751878,0.0000021072995,0.000108614986,0.0025453565],"genre_scores_gemma":[0.93468976,0.0000146785615,0.06515364,0.0000044724657,0.00006152846,0.000014438814,0.0000010536031,0.000009161584,0.000051253955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975617,0.000339487,0.00048957387,0.0003485156,0.000861256,0.00039945697],"domain_scores_gemma":[0.99729025,0.00045190591,0.00013758913,0.0005600575,0.0014729464,0.0000872232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026724588,0.000094754694,0.00018061725,0.0004363471,0.00018774321,0.000058316873,0.0013797324,0.00007219402,0.0001467201],"category_scores_gemma":[0.0018213568,0.0000889469,0.00005072648,0.0016174515,0.0006864862,0.00018948255,0.00080079073,0.00035142875,0.000041109943],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046052686,0.00023058854,0.0007901277,0.000068448346,0.00001558313,0.0000029205846,0.0057222475,0.00070746656,0.02784285,0.9188537,0.00008247679,0.045637522],"study_design_scores_gemma":[0.000007143934,0.00040512232,0.00001550169,0.000036293666,8.7409614e-7,0.0000013818055,0.00014228134,0.3990399,0.4671948,0.1330701,0.000037161488,0.0000494583],"about_ca_topic_score_codex":0.0005019651,"about_ca_topic_score_gemma":0.000060838258,"teacher_disagreement_score":0.89354336,"about_ca_system_score_codex":0.00003589708,"about_ca_system_score_gemma":0.00018286773,"threshold_uncertainty_score":0.36271492},"labels":[],"label_agreement":null},{"id":"W2889576094","doi":"","title":"Stochastic Nested Variance Reduced Gradient Descent for Nonconvex Optimization.","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Variance reduction; Gradient descent; Combinatorics; Nabla symbol; Stationary point; Function (biology); Stochastic gradient descent; Applied mathematics; Mathematical analysis; Computer science; Physics; Statistics; Omega","score_opus":0.02298046378812457,"score_gpt":0.2619998012515888,"score_spread":0.2390193374634642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889576094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032609404,0.000055153374,0.9949181,0.00037202268,0.0016970802,0.0013037879,0.000007898361,0.00093718944,0.000382695],"genre_scores_gemma":[0.7961357,0.0000012997505,0.20253107,0.000469617,0.00022905071,0.00046391794,0.00005106004,0.000018969984,0.000099304794],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806154,0.0000441304,0.0008001485,0.00030090948,0.00040534456,0.00038793666],"domain_scores_gemma":[0.9973581,0.00007121187,0.00064328464,0.00042201817,0.0013698081,0.00013559013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037093417,0.0002352642,0.00023732534,0.0003205022,0.00049472135,0.000979458,0.0006885989,0.000108488006,0.0000044152966],"category_scores_gemma":[0.00025702186,0.00022108339,0.00005429094,0.00083007425,0.00009180659,0.0040028943,0.00008882546,0.00009370263,0.000022950793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004590099,0.00006301144,0.000014721891,0.00038194202,0.000018854562,5.3145385e-7,0.0043021142,0.9316582,0.00014258867,0.041114368,0.0027714395,0.019486343],"study_design_scores_gemma":[0.0004851334,0.00020131994,0.000025441528,0.0001614027,0.000009879445,0.00005136108,0.000083830026,0.9976058,0.000356826,0.00019579279,0.0005703549,0.00025288112],"about_ca_topic_score_codex":0.000010767326,"about_ca_topic_score_gemma":3.278502e-7,"teacher_disagreement_score":0.7958096,"about_ca_system_score_codex":0.00015350313,"about_ca_system_score_gemma":0.00016208718,"threshold_uncertainty_score":0.94449365},"labels":[],"label_agreement":null},{"id":"W2894459442","doi":"10.48550/arxiv.1809.09354","title":"Accelerated Coordinate Descent with Arbitrary Sampling and Best Rates for Minibatches","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Coordinate descent; Lipschitz continuity; Empirical risk minimization; Mathematics; Stochastic gradient descent; Sampling (signal processing); Minification; Gradient descent; Mathematical optimization; Computer science; Combinatorics; Applied mathematics; Algorithm; Artificial intelligence; Pure mathematics","score_opus":0.15415910014870657,"score_gpt":0.24054776777654432,"score_spread":0.08638866762783776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894459442","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17203791,0.000036570236,0.826511,0.00007235304,0.00016369592,0.0006319238,0.00001733867,0.00030396547,0.00022521551],"genre_scores_gemma":[0.8383983,0.000076886594,0.16110617,0.00006368137,0.00004162079,0.000007785293,0.000026487907,0.000025108453,0.0002540045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834335,0.00004228949,0.00017654344,0.0010473437,0.00006633613,0.00032413728],"domain_scores_gemma":[0.9984042,0.00017570594,0.000242463,0.00064500346,0.00038494295,0.00014766556],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016535478,0.00032609495,0.0003106779,0.0002633477,0.00020917406,0.0002323858,0.0009279734,0.00020659484,0.000006233231],"category_scores_gemma":[0.00003853746,0.00033335437,0.00006841872,0.00042615528,0.00021332633,0.0003399747,0.0008649925,0.00023082641,0.000004560761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010091735,0.0014291251,0.027579216,0.0015711492,0.0013809229,0.0003680585,0.0036082545,0.25695542,0.00041234418,0.6991409,0.0019334035,0.004612031],"study_design_scores_gemma":[0.0009650681,0.0005831524,0.0006654342,0.00045707726,0.00013762937,0.000013548993,0.000119800185,0.9310961,0.0034066718,0.06159962,0.00014382265,0.00081208936],"about_ca_topic_score_codex":0.000048789872,"about_ca_topic_score_gemma":0.000009704214,"teacher_disagreement_score":0.6741407,"about_ca_system_score_codex":0.00009845977,"about_ca_system_score_gemma":0.00016734924,"threshold_uncertainty_score":0.99991184},"labels":[],"label_agreement":null},{"id":"W2894591993","doi":"10.1109/allerton.2018.8635903","title":"Anytime Stochastic Gradient Descent: A Time to Hear from all the Workers","year":2018,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Stochastic gradient descent; Exploit; Computation; Convergence (economics); Node (physics); Distributed computing; Focus (optics); Acceleration; Algorithm; Artificial intelligence; Computer security; Artificial neural network","score_opus":0.01617655381045896,"score_gpt":0.23892246683512786,"score_spread":0.2227459130246689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894591993","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016706605,0.000019690742,0.9894232,0.004543613,0.00026053409,0.0005574867,0.0000039671995,0.0007274958,0.0027933335],"genre_scores_gemma":[0.3236048,8.1934513e-7,0.66500556,0.0074700443,0.00026840196,0.00011495027,0.000007663199,0.000037468726,0.0034902964],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983991,0.00005860076,0.00024390426,0.0005169059,0.00036441657,0.00041709084],"domain_scores_gemma":[0.9984329,0.00017388401,0.000064997774,0.0009654193,0.00013898312,0.00022384823],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002446552,0.00019022632,0.00015696678,0.00013071271,0.000181793,0.00021010647,0.0013678817,0.000053146145,0.0006155111],"category_scores_gemma":[0.00010984683,0.00013264896,0.000063256535,0.0006248078,0.00012578667,0.00019734673,0.00046419192,0.00009702584,0.0036904518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020318538,0.0008324484,0.0003188636,0.000009659587,0.00046089423,0.000029848878,0.023771904,0.013526792,0.0050802794,0.14326295,0.7517296,0.060773563],"study_design_scores_gemma":[0.0005347032,0.00089128845,0.0012789081,0.00010810317,0.00003799214,0.000023335137,0.00008148056,0.96755415,0.0034905705,0.014422743,0.010823195,0.0007535309],"about_ca_topic_score_codex":0.00015611463,"about_ca_topic_score_gemma":0.0000102286385,"teacher_disagreement_score":0.95402735,"about_ca_system_score_codex":0.0000864831,"about_ca_system_score_gemma":0.00004505644,"threshold_uncertainty_score":0.9970853},"labels":[],"label_agreement":null},{"id":"W2894812324","doi":"10.1016/j.disopt.2023.100795","title":"Principled deep neural network training through linear programming","year":2023,"lang":"en","type":"article","venue":"Discrete Optimization","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Office of Naval Research; Institut de Valorisation des Données; National Science Foundation","keywords":"Computer science; Deep learning; Polyhedron; Artificial intelligence; Artificial neural network; Linear programming; Perspective (graphical); Dependency (UML); Task (project management); Representation (politics); Sample (material); Function (biology); Machine learning; Mathematical optimization; Algorithm; Theoretical computer science; Mathematics; Geometry","score_opus":0.04017734624734458,"score_gpt":0.28953988569646294,"score_spread":0.24936253944911835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894812324","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018716636,0.000043001615,0.9942153,0.0005607739,0.00044080243,0.0005386477,0.0000013956223,0.0027904457,0.0012224321],"genre_scores_gemma":[0.0510679,0.000033822012,0.9480601,0.00019422658,0.0001787391,0.00014782441,0.00015803779,0.000040776198,0.00011857728],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811596,0.00007808072,0.00037567952,0.00051254,0.00035684067,0.00056092936],"domain_scores_gemma":[0.9990093,0.000089962574,0.00018315912,0.00049106666,0.00013462105,0.00009184995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033787166,0.00021283544,0.00020516536,0.00013799955,0.00031384945,0.00022274887,0.00061590096,0.000098809134,0.000019169529],"category_scores_gemma":[0.00017221863,0.00021190051,0.00008418348,0.0024165388,0.000051872332,0.000908109,0.00027599023,0.0001361203,0.000024165289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038621306,0.000008088374,0.00008195752,0.0000070557835,0.000010488972,0.0000059983986,0.0016123524,0.955761,0.000003943111,0.03175353,0.00008937803,0.01066234],"study_design_scores_gemma":[0.00023197614,0.00007015122,0.000072384144,0.000025248455,0.0000091109805,0.0000075908233,0.0000997778,0.99723095,0.000038056925,0.001479221,0.00049361074,0.00024191254],"about_ca_topic_score_codex":0.000004824495,"about_ca_topic_score_gemma":0.0000017812581,"teacher_disagreement_score":0.050880734,"about_ca_system_score_codex":0.000044143882,"about_ca_system_score_gemma":0.000035976063,"threshold_uncertainty_score":0.86410517},"labels":[],"label_agreement":null},{"id":"W2895642264","doi":"10.1007/978-3-030-01424-7_39","title":"Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"Institut de Valorisation des Données; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; European Commission","keywords":"Maxima and minima; Stochastic gradient descent; Generalization; Computer science; Range (aeronautics); Convergence (economics); Gradient descent; Artificial neural network; Rate of convergence; Generalization error; Set (abstract data type); Artificial intelligence; Key (lock); Algorithm; Applied mathematics; Mathematics; Mathematical analysis; Materials science","score_opus":0.011149413033879854,"score_gpt":0.24113535986571816,"score_spread":0.22998594683183832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895642264","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008125589,0.00018128287,0.9959135,0.0008395359,0.00076170464,0.0009890228,0.00002021612,0.0002874828,0.00019466637],"genre_scores_gemma":[0.25688535,0.000021768974,0.7391149,0.0028334376,0.0001566171,0.000061025083,0.000017447406,0.00008393528,0.00082551944],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947426,0.00008936595,0.0010060981,0.0020214487,0.0012864432,0.00085407624],"domain_scores_gemma":[0.99575776,0.00097102404,0.0007165701,0.0014456114,0.0007395667,0.0003694698],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001164942,0.00074266194,0.00080679904,0.00073223293,0.00027713572,0.00039555223,0.0035003861,0.000343514,0.000074890195],"category_scores_gemma":[0.0007695914,0.00072704215,0.00014258377,0.0010809649,0.00090063794,0.00049057725,0.0013518145,0.000688307,0.00003869861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002155259,0.0006291287,0.00026606102,0.0003535072,0.00024145881,0.00005355411,0.04015973,0.38965264,0.07318499,0.017597692,0.01475913,0.46288657],"study_design_scores_gemma":[0.0007465543,0.0019934452,0.000094184434,0.0011345455,0.000039450944,0.0000356413,0.0000014940017,0.8859174,0.058152985,0.049109306,0.0010005891,0.0017743813],"about_ca_topic_score_codex":0.000039100294,"about_ca_topic_score_gemma":0.000008392635,"teacher_disagreement_score":0.49626476,"about_ca_system_score_codex":0.00045399964,"about_ca_system_score_gemma":0.000419982,"threshold_uncertainty_score":0.99951804},"labels":[],"label_agreement":null},{"id":"W2896830491","doi":"10.1287/ijoo.2022.0072","title":"A Subsampling Line-Search Method with Second-Order Results","year":2022,"lang":"en","type":"article","venue":"INFORMS Journal on Optimization","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Agence Nationale de la Recherche","keywords":"Line search; Computer science; Context (archaeology); Mathematical optimization; Function (biology); Sample (material); Line (geometry); Saddle point; Reduction (mathematics); Algorithm; Artificial intelligence; Mathematics; Path (computing)","score_opus":0.028408940318962666,"score_gpt":0.29410412738804687,"score_spread":0.2656951870690842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896830491","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026126197,0.000014162336,0.9943375,0.0008951443,0.00029430175,0.00028029282,0.000010096687,0.00024885108,0.0036583645],"genre_scores_gemma":[0.014569799,0.000018407185,0.98378396,0.000922017,0.00006824269,0.000040922867,0.000029821917,0.000024960016,0.0005418668],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977881,0.00010558956,0.0005658838,0.0002913955,0.0009079797,0.00034105076],"domain_scores_gemma":[0.99830735,0.00019014537,0.00039840478,0.00042159145,0.00052926276,0.00015326872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014785656,0.0001835239,0.00018333709,0.000672436,0.0007438437,0.00042574535,0.0008455968,0.00004976045,0.0002389446],"category_scores_gemma":[0.000175012,0.0001465406,0.00005727664,0.0014725169,0.000025160325,0.0010692024,0.00024774132,0.00065107737,0.000006542438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014820747,0.000050331713,0.000010831785,0.000003166425,0.000019104435,0.000015548794,0.0009021129,0.98198336,0.000007081179,0.01086562,0.0003429713,0.005651662],"study_design_scores_gemma":[0.0011386514,0.0011597747,0.000015439515,0.000023529072,0.0000056069207,0.0005809899,0.00012854235,0.9935711,0.00049368915,0.00063265854,0.002027291,0.00022275373],"about_ca_topic_score_codex":0.000004303354,"about_ca_topic_score_gemma":8.5248405e-7,"teacher_disagreement_score":0.014308537,"about_ca_system_score_codex":0.00025085753,"about_ca_system_score_gemma":0.0002716569,"threshold_uncertainty_score":0.5975752},"labels":[],"label_agreement":null},{"id":"W2898859254","doi":"10.48550/arxiv.1810.12805","title":"Piecewise Strong Convexity of Neural Networks","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Maxima and minima; Piecewise; Mathematics; Convexity; Artificial neural network; Differentiable function; Stochastic gradient descent; Norm (philosophy); Applied mathematics; Regularization (linguistics); Open set; Convex function; Regular polygon; Gradient descent; Mathematical optimization; Mathematical analysis; Computer science; Pure mathematics; Artificial intelligence; Geometry","score_opus":0.07283423281946094,"score_gpt":0.1943522013176432,"score_spread":0.12151796849818225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898859254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026363237,0.000033513876,0.97065014,0.000029850398,0.00077045965,0.00031373353,0.000009805373,0.0004127122,0.0014165224],"genre_scores_gemma":[0.9859583,0.000030676223,0.013687149,0.000041043386,0.00006988084,0.0000010241669,0.000012514195,0.000015130155,0.00018430085],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983626,0.000108786895,0.00025744172,0.00085845246,0.00009772598,0.00031497353],"domain_scores_gemma":[0.99761516,0.00009482959,0.00043886338,0.0013679464,0.00034217988,0.00014104857],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021081696,0.00027473836,0.00035350118,0.0002547173,0.00008634735,0.00005925059,0.0020944858,0.0002835847,0.00003964592],"category_scores_gemma":[0.000044015982,0.0003268635,0.00018044091,0.000545754,0.00030218193,0.00028113858,0.0023329183,0.00040491557,0.0000078873645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001848535,0.000073054915,0.0022328077,0.00003819959,0.00005710368,0.00003542081,0.000100033765,0.7625285,0.0000026881432,0.2339612,0.0005019031,0.0004506445],"study_design_scores_gemma":[0.00021300084,0.00008497881,0.00043519287,0.0000541472,0.000036334663,0.0000022752522,0.000009975634,0.9763373,0.00010924845,0.022436818,0.00001373913,0.00026699156],"about_ca_topic_score_codex":0.00006601235,"about_ca_topic_score_gemma":0.000006008912,"teacher_disagreement_score":0.959595,"about_ca_system_score_codex":0.00010976391,"about_ca_system_score_gemma":0.00009580335,"threshold_uncertainty_score":0.99991834},"labels":[],"label_agreement":null},{"id":"W2900457592","doi":"","title":"Deep Nets Don't Learn via Memorization","year":2017,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Polytechnique Montréal; Université de Montréal","funders":"","keywords":"Memorization; Computer science; Artificial intelligence; Mathematics education; Psychology","score_opus":0.011662509674400618,"score_gpt":0.2350985713370607,"score_spread":0.22343606166266008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900457592","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012256919,0.00022063022,0.9868866,0.0057612644,0.0004439383,0.00076336367,0.0000037328439,0.002337821,0.0023569246],"genre_scores_gemma":[0.4969817,0.00007068028,0.5005857,0.0012334038,0.0001111411,0.00029737013,0.000012743124,0.000051200903,0.0006560368],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99724936,0.000107880085,0.0005121181,0.0007697531,0.00057066174,0.0007902519],"domain_scores_gemma":[0.99566513,0.00008960735,0.0005944917,0.003024285,0.00026939067,0.00035709678],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006618925,0.00039607813,0.00036495106,0.00047967085,0.0011221459,0.0012015444,0.0031453618,0.0003105792,0.000040382412],"category_scores_gemma":[0.0005720302,0.0004176061,0.0001620698,0.00040789196,0.00016314515,0.0017325623,0.00094798754,0.0003788025,0.00004414974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055576733,0.00047688256,0.029958997,0.00004949791,0.000100963094,0.00015741512,0.0009766407,0.027020605,0.009118276,0.6630765,0.005377751,0.26363087],"study_design_scores_gemma":[0.00038973909,0.00014177663,0.0180308,0.000036798443,0.000015834468,0.00011128442,0.000013173623,0.94566876,0.011259174,0.022485835,0.001340358,0.00050647685],"about_ca_topic_score_codex":0.002491662,"about_ca_topic_score_gemma":0.0005842545,"teacher_disagreement_score":0.9186481,"about_ca_system_score_codex":0.0003376894,"about_ca_system_score_gemma":0.00014568598,"threshold_uncertainty_score":0.9998353},"labels":[],"label_agreement":null},{"id":"W2912255742","doi":"10.1007/978-3-030-10928-8_21","title":"MASAGA: A Linearly-Convergent Stochastic First-Order Method for Optimization on Manifolds","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Rate of convergence; Stochastic gradient descent; Variance reduction; Riemannian manifold; Convergence (economics); Manifold (fluid mechanics); Applied mathematics; Eigenvalues and eigenvectors; Computer science; Mathematical optimization; Stochastic optimization; Mathematics; Variance (accounting); Gradient descent; Convex function; Regular polygon; Mathematical analysis; Key (lock); Artificial intelligence; Statistics; Geometry","score_opus":0.019134214433650144,"score_gpt":0.2667438314597867,"score_spread":0.24760961702613654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912255742","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.054117e-7,0.00009459993,0.99250484,0.0013192698,0.0028303121,0.002008594,0.000017278324,0.0004193365,0.0008052544],"genre_scores_gemma":[0.0013611311,0.000014404009,0.99521226,0.0021225305,0.0003063836,0.000084218176,0.000023875911,0.00007908976,0.0007961358],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952486,0.00003644522,0.00072171417,0.0021282507,0.0010932756,0.0007716742],"domain_scores_gemma":[0.9955671,0.0013163373,0.0004884938,0.0017238493,0.0007072856,0.00019692109],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009915797,0.0007395722,0.00069656345,0.0013308271,0.000295652,0.00051032816,0.0029713265,0.00048191196,0.00005463355],"category_scores_gemma":[0.0003559296,0.00070602214,0.00020541629,0.0008430041,0.0002287601,0.00048123888,0.00086827495,0.0005643563,0.00004474459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014276601,0.00003570937,0.0000019353506,0.000046214584,0.000014789592,0.0000055617675,0.00020199812,0.9023377,0.0000038913176,0.061548993,0.00007037184,0.03571861],"study_design_scores_gemma":[0.00046533582,0.0005859187,0.0000052073974,0.0003998291,0.000018574392,0.000025123687,9.8693135e-8,0.9584059,0.00018103443,0.038768772,0.0004271201,0.0007170452],"about_ca_topic_score_codex":0.000011334377,"about_ca_topic_score_gemma":0.000016726079,"teacher_disagreement_score":0.05606829,"about_ca_system_score_codex":0.0005010555,"about_ca_system_score_gemma":0.000617011,"threshold_uncertainty_score":0.9995391},"labels":[],"label_agreement":null},{"id":"W2914374088","doi":"10.71781/10005","title":"Learning-Based Matheuristic Solution Methods for Stochastic Network Design","year":2018,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Centre interuniversitaire de recherche sur les reseaux d'entreprise, la logistique et le transport; Université de Montréal; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer science; Artificial intelligence","score_opus":0.06925165681994905,"score_gpt":0.3883390833009908,"score_spread":0.31908742648104177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914374088","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000099551235,0.00010147505,0.9949647,0.000035660003,0.00129077,0.0025608954,0.0000049361774,0.00005168442,0.0009799071],"genre_scores_gemma":[0.00066538295,0.0000018178104,0.99304014,0.000027655758,0.00016775343,0.0006760902,0.0004310671,0.000058364007,0.0049317074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99762255,0.0003354893,0.00047988925,0.0008666588,0.00022948427,0.00046594732],"domain_scores_gemma":[0.9972244,0.00095682876,0.00061939354,0.00063043414,0.00045819776,0.00011072691],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019913882,0.00036143998,0.00044808115,0.00020803482,0.00041815965,0.0006269624,0.0020180463,0.00032519348,0.00021308487],"category_scores_gemma":[0.0009797027,0.0003782887,0.00011973421,0.0004630802,0.000044789547,0.00025734765,0.00015309447,0.00024665825,0.00010740092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032585787,0.00014662571,5.992045e-7,0.00007498098,0.000099707766,0.0000026522553,0.0017231824,0.2532497,0.00016065057,0.0021393693,0.008431431,0.73364526],"study_design_scores_gemma":[0.00035541,0.0006956512,0.0000046975465,0.0002677144,0.000093301154,0.0000026753448,0.000023696275,0.9828007,0.0017917703,0.009259517,0.0042622937,0.0004425361],"about_ca_topic_score_codex":0.000006163435,"about_ca_topic_score_gemma":0.0000060707225,"teacher_disagreement_score":0.7332027,"about_ca_system_score_codex":0.00011289555,"about_ca_system_score_gemma":0.0004907367,"threshold_uncertainty_score":0.9998669},"labels":[],"label_agreement":null},{"id":"W2922019075","doi":"10.1109/lsp.2019.2921446","title":"Convolutional Analysis Operator Learning: Dependence on Training Data","year":2019,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; W. M. Keck Foundation","keywords":"Operator (biology); Filter (signal processing); Training (meteorology); Training set; Pattern recognition (psychology); Convolutional neural network; Series (stratigraphy); Upper and lower bounds","score_opus":0.04774172891518412,"score_gpt":0.2748918543182899,"score_spread":0.22715012540310575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922019075","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026815582,0.000030017292,0.9709954,0.0011358472,0.00015313286,0.00014376442,0.0000046818736,0.0004009869,0.00032056635],"genre_scores_gemma":[0.9280846,7.8976905e-7,0.06925391,0.0024534287,0.000067139255,0.00001073517,0.000029801564,0.00001409255,0.00008548273],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978717,0.00008271309,0.0002692126,0.00081549486,0.0006218945,0.00033900124],"domain_scores_gemma":[0.99887085,0.00014515639,0.00017368737,0.00061259733,0.000102347665,0.00009534915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004919922,0.00018894486,0.00023841979,0.0003801032,0.00018461491,0.00036128183,0.0017178794,0.0000591751,0.000057206475],"category_scores_gemma":[0.00004883956,0.00018443879,0.000062565254,0.0011708656,0.0000697743,0.0009847521,0.0001676804,0.0003051919,0.000075810414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003679211,0.000119935765,0.0056348173,0.00005847638,0.00034804206,0.00004196541,0.0023339102,0.89698744,0.049090717,0.005165089,0.0024358856,0.03774695],"study_design_scores_gemma":[0.00019849307,0.00007168149,0.00043217812,0.00005634919,0.000046724614,0.000009037656,0.00003436992,0.99705344,0.0015086043,0.000106074905,0.00021377442,0.00026928395],"about_ca_topic_score_codex":0.0000074209547,"about_ca_topic_score_gemma":6.3373545e-7,"teacher_disagreement_score":0.9017415,"about_ca_system_score_codex":0.0000668703,"about_ca_system_score_gemma":0.000151486,"threshold_uncertainty_score":0.75211954},"labels":[],"label_agreement":null},{"id":"W2945563437","doi":"10.48550/arxiv.1905.10259","title":"Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Binary number; Computer science; Differentiable function; Artificial neural network; Generalization; Artificial intelligence; Deep neural networks; Activation function; Binary Independence Model; Bayesian probability; Bayesian network; Machine learning; Mathematics","score_opus":0.03541511775381253,"score_gpt":0.1810671450932165,"score_spread":0.14565202733940397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945563437","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06307699,0.00011215573,0.93428075,0.00010302028,0.00068206794,0.00059752865,0.000006157235,0.0006905264,0.0004507845],"genre_scores_gemma":[0.98641795,0.00017790502,0.012614743,0.00018999982,0.000058464862,0.0000018594864,0.000030212675,0.000032874093,0.00047601634],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977602,0.00018468314,0.000230992,0.0012914273,0.00009969228,0.00043300277],"domain_scores_gemma":[0.9978817,0.00013465127,0.00031699397,0.0013009512,0.00014261168,0.00022309208],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016644206,0.0004222895,0.0004297253,0.00037618497,0.00015470386,0.00019912857,0.0014607374,0.00042233153,0.000026759217],"category_scores_gemma":[0.000030855957,0.00047922437,0.00014887961,0.0006737232,0.00013719003,0.00044446762,0.0023002892,0.00062657014,0.000007178064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038967133,0.000044670396,0.0017498861,0.000033758995,0.0000660336,0.00015928528,0.00011960096,0.9623428,0.0000463545,0.034655,0.00020401485,0.0005396471],"study_design_scores_gemma":[0.0005412255,0.000072717776,0.0006090714,0.000045610566,0.000041973977,0.000013140103,0.000014531554,0.9892626,0.00009078408,0.008793255,0.000026251659,0.00048886245],"about_ca_topic_score_codex":0.000081692655,"about_ca_topic_score_gemma":0.000005415957,"teacher_disagreement_score":0.9233409,"about_ca_system_score_codex":0.00015896792,"about_ca_system_score_gemma":0.00006492728,"threshold_uncertainty_score":0.99976593},"labels":[],"label_agreement":null},{"id":"W2947651699","doi":"10.48550/arxiv.1905.13200","title":"Exploiting Uncertainty of Loss Landscape for Stochastic Optimization","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Stochastic optimization; Computer science; Mathematical optimization; Mathematics","score_opus":0.061233371703100774,"score_gpt":0.1982979884960701,"score_spread":0.13706461679296933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947651699","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054207104,0.000024771036,0.9924033,0.000035593548,0.0004957513,0.0009081708,0.000042756958,0.00033688272,0.00033205585],"genre_scores_gemma":[0.9086919,0.000020903266,0.09092101,0.000026360995,0.000037619153,0.000007014741,0.0000684936,0.000023612702,0.00020311055],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983773,0.00005793207,0.00030092744,0.000865304,0.000108992164,0.00028954275],"domain_scores_gemma":[0.9975737,0.00031004334,0.00055650936,0.0009774092,0.000495943,0.000086420296],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025447737,0.00027317545,0.00039530548,0.00038741872,0.00008371869,0.00006121851,0.0013737242,0.00024965117,0.000017131804],"category_scores_gemma":[0.00015924027,0.0003257293,0.00020024886,0.0004911518,0.000073709285,0.0002863325,0.0009720587,0.00021651114,0.000005016997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023552691,0.000039884206,0.00013890298,0.0001096993,0.000037721158,0.000003488886,0.00013940105,0.8915189,0.00000469383,0.10782345,0.000083172235,0.00007716329],"study_design_scores_gemma":[0.0004985975,0.00008931133,0.000015126864,0.00017466082,0.00005323823,0.0000018951667,0.00005885151,0.9839149,0.00009535983,0.014786121,0.000005184969,0.0003067602],"about_ca_topic_score_codex":0.000022751707,"about_ca_topic_score_gemma":0.0000016020888,"teacher_disagreement_score":0.9032712,"about_ca_system_score_codex":0.00012711126,"about_ca_system_score_gemma":0.00019984605,"threshold_uncertainty_score":0.9999195},"labels":[],"label_agreement":null},{"id":"W2948831929","doi":"10.1609/aaai.v34i04.5727","title":"A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control","year":2020,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"King Abdullah University of Science and Technology","keywords":"Sampling (signal processing); Mathematical optimization; Computer science; Convergence (economics); Convex function; Function (biology); Derivative (finance); Regular polygon; Sample (material); Derivative-free optimization; Acceleration; Minification; Convex optimization; Control (management); Algorithm; Mathematics; Optimization problem; Artificial intelligence","score_opus":0.07210470146840367,"score_gpt":0.31624839202100435,"score_spread":0.24414369055260068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948831929","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014749168,0.000023820508,0.99135786,0.004614535,0.00015947263,0.0014773158,0.0000122568135,0.0003143719,0.0005654544],"genre_scores_gemma":[0.544778,0.000008323692,0.45458,0.0003852181,0.00003636239,0.00015816723,0.0000013234086,0.000027736938,0.000024862025],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970382,0.00010935122,0.0007075926,0.0011417719,0.0006391233,0.00036400315],"domain_scores_gemma":[0.9964182,0.0006337003,0.0009819008,0.00055280543,0.0012156143,0.00019782527],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013031573,0.00047261582,0.00059330644,0.000253195,0.000262311,0.0004891256,0.0028298427,0.0001870464,0.000020157944],"category_scores_gemma":[0.0050161947,0.0003662496,0.00009281573,0.0007787906,0.00025114088,0.00025427624,0.0018503706,0.0009888936,0.000003933205],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023722049,0.00004139923,0.000030488438,0.000072882816,0.00004420416,3.8751406e-7,0.0031269323,0.27948678,0.0012149139,0.7087638,0.000016890795,0.006964142],"study_design_scores_gemma":[0.00005252474,0.00037625062,0.000029236822,0.00054810685,0.00004244668,0.000005202968,0.00038445444,0.6475975,0.011842293,0.33878148,0.0000024097276,0.00033809769],"about_ca_topic_score_codex":0.0000146584625,"about_ca_topic_score_gemma":0.000002385696,"teacher_disagreement_score":0.5433031,"about_ca_system_score_codex":0.000078051584,"about_ca_system_score_gemma":0.00020438849,"threshold_uncertainty_score":0.99987894},"labels":[],"label_agreement":null},{"id":"W2948930516","doi":"10.48550/arxiv.1906.03532","title":"Reducing the variance in online optimization by transporting past gradients","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of British Columbia","funders":"","keywords":"Variance (accounting); Computer science; Econometrics; Environmental science; Statistics; Mathematics; Economics","score_opus":0.04322426133291139,"score_gpt":0.190104723853462,"score_spread":0.1468804625205506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948930516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033738773,0.00004643877,0.96418685,0.00024667944,0.0005245624,0.00058821694,0.000027440125,0.00028400728,0.00035701794],"genre_scores_gemma":[0.95908624,0.00012385214,0.040113647,0.00011056868,0.000037209167,0.0000028041961,0.00009987829,0.000023473773,0.0004023536],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979802,0.00012919887,0.00036348947,0.0010476582,0.00012596443,0.000353496],"domain_scores_gemma":[0.9980863,0.00011050876,0.00045827008,0.0011374545,0.00013190153,0.00007559456],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034487672,0.0002893699,0.00029243398,0.0002748013,0.000121875775,0.0001048531,0.0019658587,0.00022428905,0.000011398779],"category_scores_gemma":[0.000049186783,0.0002921745,0.0001106047,0.0010116742,0.00007477464,0.0003949442,0.000609611,0.00058572873,0.0000061017377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007395329,0.000092142975,0.0025368815,0.000026706432,0.000016593505,0.0000192328,0.00037598662,0.9808432,0.000009394683,0.015724909,0.00015702478,0.00019052054],"study_design_scores_gemma":[0.0003124407,0.000027601922,0.00087588746,0.00020445735,0.00002195255,0.0000022176516,0.00005057395,0.9946383,0.000032338008,0.003499553,0.00003389615,0.0003007336],"about_ca_topic_score_codex":0.0001825151,"about_ca_topic_score_gemma":0.000016779491,"teacher_disagreement_score":0.92534745,"about_ca_system_score_codex":0.00025460016,"about_ca_system_score_gemma":0.00010798936,"threshold_uncertainty_score":0.99995303},"labels":[],"label_agreement":null},{"id":"W2951500940","doi":"10.48550/arxiv.1812.09404","title":"Derandomized Distributed Multi-resource Allocation with Little Communication Overhead","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Resource allocation; Computer science; Overhead (engineering); The Internet; Multiplicative function; Resource (disambiguation); Distributed computing; Mathematical optimization; Mathematics; Computer network","score_opus":0.056890581519929595,"score_gpt":0.19712802923068767,"score_spread":0.14023744771075808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951500940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014788342,0.00004877062,0.98279256,0.00019059003,0.00009589994,0.00074968307,0.000025597754,0.0007759353,0.0005326346],"genre_scores_gemma":[0.88800585,0.00006177409,0.111236975,0.00007473164,0.000022648186,0.000009347204,0.00028706845,0.000022657945,0.00027896283],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981896,0.0002828483,0.00025324276,0.0008700882,0.00013067298,0.0002735201],"domain_scores_gemma":[0.9966846,0.00021658943,0.00044722145,0.0020675657,0.0004496692,0.00013436597],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034795963,0.00031596347,0.00035649852,0.00023585133,0.0002482838,0.00017926398,0.0020325438,0.00026144,0.00001824288],"category_scores_gemma":[0.00010948802,0.00032955976,0.00011628838,0.0006468487,0.00023233544,0.00035768197,0.0013816655,0.0003760878,0.000030201149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000961178,0.00074525486,0.0020211975,0.0001338344,0.00043560105,0.000052072926,0.0014569301,0.7244014,0.000045304052,0.26511323,0.0035870094,0.0010469841],"study_design_scores_gemma":[0.003491926,0.00007389113,0.0004209262,0.00019572565,0.00007911883,0.0000048693164,0.000039021008,0.9847391,0.0003252338,0.009854595,0.0003270174,0.00044857958],"about_ca_topic_score_codex":0.00011476683,"about_ca_topic_score_gemma":0.000035845336,"teacher_disagreement_score":0.8732175,"about_ca_system_score_codex":0.00028505118,"about_ca_system_score_gemma":0.00016039902,"threshold_uncertainty_score":0.99991566},"labels":[],"label_agreement":null},{"id":"W2951536758","doi":"10.48550/arxiv.1810.02976","title":"Anytime Stochastic Gradient Descent: A Time to Hear from all the Workers","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Stochastic gradient descent; Exploit; Computation; Node (physics); Convergence (economics); Focus (optics); Set (abstract data type); Distributed computing; Algorithm; Artificial intelligence; Computer security","score_opus":0.05485075728300471,"score_gpt":0.18793639689062192,"score_spread":0.1330856396076172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951536758","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02067821,0.000035826444,0.975444,0.00064891257,0.00058908487,0.0010349321,0.000041161355,0.00077114487,0.00075670914],"genre_scores_gemma":[0.9514287,0.000011384975,0.04494963,0.0009119615,0.00019710981,0.000012600216,0.000047600133,0.000058492868,0.0023825252],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971448,0.00018762707,0.00029475492,0.0015619576,0.00022208704,0.000588783],"domain_scores_gemma":[0.99653333,0.00024756184,0.00027952297,0.0023082986,0.00025217753,0.0003790863],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003231444,0.0004767909,0.00039957993,0.00036755906,0.00024549494,0.00025883195,0.0037311062,0.00027119572,0.00021793517],"category_scores_gemma":[0.000108245564,0.00045048108,0.0002383364,0.000915942,0.00023053723,0.0002288197,0.003525157,0.0005087472,0.0016552075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013439692,0.00029006472,0.0002652176,0.000023697296,0.0004600467,0.0001551102,0.0025671455,0.93281054,0.0000597306,0.03265313,0.029819386,0.0007615144],"study_design_scores_gemma":[0.0003305824,0.00017532201,0.00042263165,0.0002530183,0.00013133591,0.0000051770394,0.000039472317,0.95914763,0.00008836849,0.037895225,0.0008057802,0.00070542796],"about_ca_topic_score_codex":0.0003113874,"about_ca_topic_score_gemma":0.000013749396,"teacher_disagreement_score":0.9307505,"about_ca_system_score_codex":0.00044049416,"about_ca_system_score_gemma":0.00018646994,"threshold_uncertainty_score":0.9997947},"labels":[],"label_agreement":null},{"id":"W2951650375","doi":"10.48550/arxiv.1206.5533","title":"Practical recommendations for gradient-based training of deep architectures","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":271,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Debugging; Artificial intelligence; Deep learning; Artificial neural network; Machine learning; Deep neural networks; Context (archaeology); Training (meteorology); Scale (ratio)","score_opus":0.18005271214046442,"score_gpt":0.2611330049116545,"score_spread":0.08108029277119005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951650375","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018157085,0.000014961717,0.99554425,0.0008042344,0.00047899096,0.00058928254,0.000033451553,0.00029622507,0.00042289557],"genre_scores_gemma":[0.6022209,0.000003727624,0.39760625,0.00006345764,0.000028120807,0.0000067373253,0.00003196294,0.000012137263,0.000026736425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858004,0.00011416389,0.00026111482,0.0006232539,0.00008392167,0.00033748886],"domain_scores_gemma":[0.9977517,0.00062901044,0.00043287702,0.0008027812,0.00022868883,0.00015495492],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033462854,0.00023277992,0.0003013367,0.0004159581,0.000119835284,0.0000425948,0.0009232948,0.00020004003,0.000024094588],"category_scores_gemma":[0.0002561188,0.00027060052,0.00022365943,0.00039832352,0.00012030959,0.00015423226,0.00048817397,0.00032735034,0.0000027373674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033715685,0.00019919756,0.00018043828,0.00009231453,0.000078845886,0.0000060900247,0.00093814556,0.23371924,0.0000156713,0.7610767,0.00044406185,0.0032155924],"study_design_scores_gemma":[0.00038715743,0.00008379469,0.00007690728,0.000070933944,0.000088428336,0.0000037108935,0.00007618962,0.92886513,0.00051089545,0.069239885,0.0003021808,0.00029477532],"about_ca_topic_score_codex":0.000016452288,"about_ca_topic_score_gemma":0.000009031143,"teacher_disagreement_score":0.6951459,"about_ca_system_score_codex":0.00011184862,"about_ca_system_score_gemma":0.00020613974,"threshold_uncertainty_score":0.9999746},"labels":[],"label_agreement":null},{"id":"W2951894832","doi":"10.48550/arxiv.1002.4464","title":"Deterministic Sample Sort For GPUs","year":2010,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"sort; Merge sort; Computer science; Sorting algorithm; Parallel computing; Sorting; Sample (material); Merge (version control); Algorithm","score_opus":0.08110920168694707,"score_gpt":0.20661268336132643,"score_spread":0.12550348167437936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951894832","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074235806,0.000008166264,0.98931473,0.000054760363,0.0011333266,0.00068094913,0.00008334218,0.00067884964,0.00062228163],"genre_scores_gemma":[0.76931113,0.000013897425,0.22996551,0.00008577815,0.00007684906,0.000009878904,0.00004544954,0.000023342915,0.00046818284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982864,0.0000348599,0.00020561155,0.0010449712,0.00007844717,0.00034966107],"domain_scores_gemma":[0.99754184,0.00040080497,0.00026045024,0.0013899832,0.00024624632,0.00016068765],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019277036,0.0002886281,0.00029605872,0.00029375416,0.00017037746,0.00014261535,0.002115039,0.00037052057,0.000024808614],"category_scores_gemma":[0.00026493904,0.0003510154,0.00021120069,0.00030763223,0.000111938665,0.00019449016,0.0013747195,0.00043788383,0.00001719872],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002185925,0.00009620096,0.00041212715,0.00009208723,0.000050227154,0.00004936079,0.00015093434,0.059303187,0.00004010502,0.93735385,0.000644397,0.001785647],"study_design_scores_gemma":[0.00022902303,0.00006333195,0.00007867558,0.000029575636,0.00004207312,0.0000039386223,0.000005566206,0.72593325,0.0002409292,0.27212673,0.00091148826,0.0003353812],"about_ca_topic_score_codex":0.00005762954,"about_ca_topic_score_gemma":0.00002333467,"teacher_disagreement_score":0.76188755,"about_ca_system_score_codex":0.00010963275,"about_ca_system_score_gemma":0.00021824896,"threshold_uncertainty_score":0.9998942},"labels":[],"label_agreement":null},{"id":"W2959756691","doi":"10.48550/arxiv.1907.04164","title":"Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Quadratic equation; Artificial neural network; Stochastic gradient descent; Gradient descent; Computer science; Acceleration; Batch processing; Simple (philosophy); Momentum (technical analysis); Mathematical optimization; Algorithm; Mathematics; Artificial intelligence","score_opus":0.03901067719968814,"score_gpt":0.1875669450614755,"score_spread":0.14855626786178736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2959756691","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11270893,0.000057499725,0.8801127,0.00021107437,0.00073142094,0.0007873273,0.000046159203,0.000628569,0.0047163283],"genre_scores_gemma":[0.9473842,0.00006885463,0.04822747,0.00027308863,0.00008187971,0.000009741536,0.00009937994,0.00005460961,0.0038007817],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963819,0.00017814345,0.00043322213,0.0022020126,0.00028618617,0.0005185486],"domain_scores_gemma":[0.9956245,0.00027770794,0.00055421,0.0026778528,0.00061691675,0.00024883257],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013605699,0.0006531458,0.0006760088,0.00051574595,0.00023055803,0.00030399146,0.003391873,0.0006236581,0.00014129902],"category_scores_gemma":[0.000057585876,0.00072927965,0.00020216857,0.0012164799,0.000080398706,0.00082623295,0.004180228,0.00075568433,0.0009117454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023890083,0.00012000561,0.003098143,0.00008291457,0.00013914035,0.000029020872,0.00081161835,0.9685947,0.000088102905,0.025779042,0.0012054276,0.000028033473],"study_design_scores_gemma":[0.0004889295,0.000040500832,0.001030671,0.00017696097,0.000092760245,0.0000028120878,0.000020506772,0.94067127,0.00022843605,0.05644464,0.000043954406,0.00075855263],"about_ca_topic_score_codex":0.00047854483,"about_ca_topic_score_gemma":0.00039032882,"teacher_disagreement_score":0.83467525,"about_ca_system_score_codex":0.0005845025,"about_ca_system_score_gemma":0.00037843818,"threshold_uncertainty_score":0.9998662},"labels":[],"label_agreement":null},{"id":"W2962705652","doi":"","title":"Stop wasting my gradients: practical SVRG","year":2015,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Convergence (economics); Variance (accounting); Computation; Generalization; Rate of convergence; Selection (genetic algorithm); Mathematical optimization; Algorithm; Artificial intelligence; Applied mathematics; Mathematics; Channel (broadcasting)","score_opus":0.06114805913386867,"score_gpt":0.3037481648630557,"score_spread":0.24260010572918705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962705652","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001601855,0.00008462458,0.9902751,0.0006812838,0.0010510096,0.00034390282,0.0000015279967,0.0010814567,0.0048792823],"genre_scores_gemma":[0.9259959,0.0000014681516,0.07315734,0.00049303955,0.00011193536,0.0000906589,0.000018728993,0.0000114122895,0.000119515425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815917,0.000068127985,0.0006315282,0.00019162489,0.00064577,0.00030376838],"domain_scores_gemma":[0.99821186,0.00005878915,0.0005000603,0.00031214053,0.0007154971,0.00020162403],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00061000616,0.00016762136,0.00017606113,0.00025527712,0.00019347142,0.0011539395,0.00046938396,0.00008381435,0.0000012840305],"category_scores_gemma":[0.0006864557,0.00014897705,0.000031291274,0.000660646,0.000042030453,0.008841286,0.00014756339,0.00017582857,0.00007374894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006956046,0.000311449,0.0028372428,0.0016755465,0.000058034966,0.000037254522,0.053300746,0.14680032,0.00014427079,0.5064913,0.058678135,0.22959615],"study_design_scores_gemma":[0.0003184941,0.00007770128,0.000036294423,0.00011107238,0.0000045403567,0.00022267376,0.00064419,0.99303323,0.00011346746,0.0003524507,0.0048955223,0.00019038432],"about_ca_topic_score_codex":0.000015663509,"about_ca_topic_score_gemma":1.504029e-7,"teacher_disagreement_score":0.9243941,"about_ca_system_score_codex":0.00013884234,"about_ca_system_score_gemma":0.00018907587,"threshold_uncertainty_score":0.99988294},"labels":[],"label_agreement":null},{"id":"W2963002787","doi":"","title":"Improved asynchronous parallel optimization analysis for stochastic incremental methods","year":2018,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Asynchronous communication; Stochastic optimization; Mathematical optimization; Parallel computing; Mathematics","score_opus":0.016860085166690648,"score_gpt":0.27402702185919564,"score_spread":0.257166936692505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963002787","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031337512,0.00010090208,0.99387574,0.0015267471,0.00014770123,0.0006814308,0.000013687786,0.0005752724,0.0027651598],"genre_scores_gemma":[0.16811557,0.000012621788,0.8309131,0.000119132375,0.000020494763,0.00016959223,0.0001149303,0.000023471066,0.00051103526],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99622345,0.0018267124,0.0005086523,0.0007631632,0.00027951595,0.0003984866],"domain_scores_gemma":[0.9940244,0.00139855,0.00040633781,0.0015814746,0.0024153437,0.00017390071],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0046095415,0.00025052807,0.00032134762,0.00046996507,0.00052458065,0.0003967041,0.0014442678,0.00012571015,0.00009232231],"category_scores_gemma":[0.001729412,0.00026828592,0.00021311022,0.0016577496,0.00023419179,0.00043456245,0.00049153576,0.00012260645,0.000008049813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005526165,0.0010929642,0.00048503873,0.000054425724,0.0009030165,0.0000011477175,0.012367542,0.0626773,0.006837939,0.7886847,0.0006649961,0.12617566],"study_design_scores_gemma":[0.00050885417,0.0000034651885,0.0001720859,0.000050495753,0.0001041555,0.0000037908064,0.000028616678,0.9756498,0.02026375,0.0027552552,0.00018510186,0.00027465113],"about_ca_topic_score_codex":0.0001781898,"about_ca_topic_score_gemma":0.00015968802,"teacher_disagreement_score":0.91297245,"about_ca_system_score_codex":0.00014133369,"about_ca_system_score_gemma":0.00013383053,"threshold_uncertainty_score":0.99997693},"labels":[],"label_agreement":null},{"id":"W2963114935","doi":"","title":"Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields","year":2015,"lang":"en","type":"article","venue":"ANU Open Research (Australian National University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Convergence (economics); Computer science; CRFS; Sampling (signal processing); Algorithm; Sampling scheme; Conditional random field; Stochastic gradient descent; Mathematical optimization; Rate of convergence; Mathematics; Artificial intelligence; Estimator; Statistics; Artificial neural network; Key (lock)","score_opus":0.2458712651436055,"score_gpt":0.40742902618338767,"score_spread":0.16155776103978217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963114935","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014617472,0.0000015246084,0.9790561,0.003658092,0.00015022919,0.0013077263,0.000066087385,0.00007506645,0.015538989],"genre_scores_gemma":[0.3058046,0.0000025948732,0.65824115,0.00026569093,0.00012616297,0.0000788991,0.00026851805,0.000019631867,0.03519276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750733,0.000178073,0.00021638916,0.00052006124,0.0010841128,0.0004940429],"domain_scores_gemma":[0.9965829,0.000859487,0.000095670046,0.0002738305,0.0018128757,0.00037519934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028548,0.0001512217,0.00021691257,0.00075783493,0.00043793977,0.0003642613,0.0021103541,0.000118296484,0.0000610423],"category_scores_gemma":[0.00062590337,0.0001671321,0.00008914406,0.0012576565,0.00013626092,0.0013383502,0.00056947634,0.0003051812,0.000026944112],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016881751,0.00009875879,0.0000070598603,0.000009015572,0.000054668973,0.000027947068,0.00115856,0.035373535,0.000021367354,0.90129757,0.0609516,0.00083112356],"study_design_scores_gemma":[0.007988707,0.00077546283,0.000094508076,0.00007177379,0.000015988871,0.000052629304,0.0012077664,0.5687389,0.0005718249,0.3782289,0.04173256,0.0005210064],"about_ca_topic_score_codex":0.00015165265,"about_ca_topic_score_gemma":0.000023475865,"teacher_disagreement_score":0.5333653,"about_ca_system_score_codex":0.00046925334,"about_ca_system_score_gemma":0.0010000655,"threshold_uncertainty_score":0.6815449},"labels":[],"label_agreement":null},{"id":"W2963179285","doi":"","title":"A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds.","year":2017,"lang":"en","type":"article","venue":"Spiral (Imperial College London)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematical proof; Regret; Computer science; Mathematical optimization; Generalization; Modular design; Convex analysis; Gradient descent; Convex optimization; Regular polygon; Theoretical computer science; Mathematics; Artificial intelligence; Machine learning; Artificial neural network","score_opus":0.012336999946321557,"score_gpt":0.2446377531609609,"score_spread":0.23230075321463933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963179285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015888365,0.000079684374,0.97936285,0.00025899964,0.00047375797,0.00059705524,0.0001425726,0.00014271833,0.0030540067],"genre_scores_gemma":[0.6369246,0.000017308712,0.3627191,0.00008340989,0.00007783783,0.00004777679,0.00002644932,0.00001471071,0.000088765446],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785167,0.000092128095,0.00053728186,0.000696923,0.00049729407,0.00032471216],"domain_scores_gemma":[0.9975712,0.000104949584,0.0006174401,0.001054518,0.00048618534,0.00016572051],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035259945,0.00030013613,0.00066990696,0.0005570293,0.0007199773,0.0004009672,0.0011395566,0.00016016688,0.000060476472],"category_scores_gemma":[0.00016151773,0.00031047742,0.00020072232,0.00083617284,0.00034065827,0.0011079352,0.00060303236,0.0001368289,0.0000024001474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037384353,0.00027697222,0.0021108503,0.000028693594,0.001662111,0.00003487964,0.0013969353,0.3695666,0.002144225,0.6215463,0.00016948851,0.0006890717],"study_design_scores_gemma":[0.0012719254,0.00035375715,0.011272934,0.00002494845,0.00027780523,0.000008800296,0.000025221712,0.9820232,0.0011099428,0.0032515384,0.00003612434,0.00034382107],"about_ca_topic_score_codex":0.00017862426,"about_ca_topic_score_gemma":0.000014681407,"teacher_disagreement_score":0.6210363,"about_ca_system_score_codex":0.00009728806,"about_ca_system_score_gemma":0.00020167111,"threshold_uncertainty_score":0.99993473},"labels":[],"label_agreement":null},{"id":"W2963248893","doi":"10.1007/978-3-319-46128-1_50","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":832,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Convexity; Rate of convergence; Applied mathematics; Mathematics; Stochastic gradient descent; Convergence (economics); Gradient descent; Mathematical proof; Generalization; Simple (philosophy); Convex function; Regular polygon; Mathematical optimization; Computer science; Mathematical analysis; Artificial neural network; Artificial intelligence; Geometry","score_opus":0.0238326173554937,"score_gpt":0.2977316453413589,"score_spread":0.2738990279858652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963248893","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000073331685,0.0006734192,0.9947411,0.0014122755,0.0013119174,0.00081345596,0.000011918417,0.00016680459,0.0007958202],"genre_scores_gemma":[0.07764057,0.00017022363,0.92069274,0.0010224972,0.00016355196,0.00003963078,0.0000034739478,0.000037947488,0.00022934163],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964291,0.00011903558,0.00072062184,0.0013287142,0.00083717814,0.00056539],"domain_scores_gemma":[0.9963624,0.0010322646,0.00060194446,0.0014127372,0.0004192298,0.00017143041],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015867588,0.0005125259,0.0005615324,0.0007158026,0.00027041635,0.00016007156,0.0024411161,0.00025332777,0.000023198738],"category_scores_gemma":[0.00015204451,0.00034005588,0.00012536516,0.0006332943,0.0020630588,0.00043885622,0.0012386204,0.00044977578,0.0000061861206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009153763,0.000043007003,0.000049921986,0.00006360839,0.000031313215,0.000010807304,0.0009960788,0.00513365,0.0007814504,0.7871828,0.000024332714,0.20567389],"study_design_scores_gemma":[0.00039816985,0.0004960743,0.00026736196,0.0007569331,0.000031857526,0.00015539194,0.0000010576729,0.45967585,0.023067487,0.5138304,0.0005275907,0.0007918123],"about_ca_topic_score_codex":0.000012821197,"about_ca_topic_score_gemma":0.000009078291,"teacher_disagreement_score":0.4545422,"about_ca_system_score_codex":0.00021607817,"about_ca_system_score_gemma":0.00032652833,"threshold_uncertainty_score":0.99990517},"labels":[],"label_agreement":null},{"id":"W2964019998","doi":"","title":"Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines","year":2013,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Boltzmann machine; Hessian matrix; Metric (unit); Mathematics; Partition function (quantum field theory); Mathematical optimization; Computer science; Convergence (economics); Gradient method; Algorithm; Applied mathematics; Artificial intelligence; Artificial neural network; Physics; Engineering","score_opus":0.028807108107858435,"score_gpt":0.2505782524245614,"score_spread":0.22177114431670295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964019998","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018473346,0.00009905181,0.99340594,0.0009033086,0.0004243859,0.0005804509,0.0000026650666,0.0003721092,0.0023647752],"genre_scores_gemma":[0.35929602,0.00000193654,0.6399919,0.00017206665,0.000022069222,0.000095334704,0.0000025602928,0.000007740603,0.0004103675],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988994,0.000016597656,0.00031988203,0.00027877506,0.00022962719,0.00025570113],"domain_scores_gemma":[0.9987428,0.00017508167,0.00014041248,0.0005831014,0.0002872537,0.0000713418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020892204,0.00012955212,0.00020410233,0.0003562635,0.00006290544,0.00007650595,0.00092498533,0.00003944653,0.00003533489],"category_scores_gemma":[0.0005137136,0.00010251385,0.00010232514,0.00054149434,0.000040103994,0.00044084905,0.00027271706,0.0000627628,0.000006718928],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032351131,0.00007968019,0.00019118,0.00004237493,0.00004279572,5.997068e-7,0.0011483305,0.00033363877,0.0019271971,0.89557374,0.024959864,0.07569739],"study_design_scores_gemma":[0.0005124127,0.00021959968,0.001655362,0.000023098284,0.000008451142,0.00001140828,0.00006163798,0.88650817,0.009849563,0.10063565,0.00027368026,0.00024096068],"about_ca_topic_score_codex":0.00008262932,"about_ca_topic_score_gemma":0.0000038039125,"teacher_disagreement_score":0.88617456,"about_ca_system_score_codex":0.000024204346,"about_ca_system_score_gemma":0.000024308423,"threshold_uncertainty_score":0.41803935},"labels":[],"label_agreement":null},{"id":"W2964106020","doi":"","title":"Coordinate Descent Converges Faster with the Gauss-Southwell Rule Than Random Selection","year":2015,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Discovery Air (Canada); University of British Columbia","funders":"","keywords":"Gauss; Selection (genetic algorithm); Lipschitz continuity; Coordinate descent; Convergence (economics); Rate of convergence; Computer science; Mathematics; Mathematical economics; Algorithm; Mathematical optimization; Applied mathematics; Artificial intelligence; Key (lock); Pure mathematics","score_opus":0.017992121045973548,"score_gpt":0.219382107153064,"score_spread":0.20138998610709044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964106020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053656274,0.000016348436,0.9873879,0.0017468918,0.00016801243,0.00034308888,5.5510804e-7,0.000497027,0.0044745337],"genre_scores_gemma":[0.9332813,0.0000020875182,0.0636261,0.00044735824,0.000032219665,0.000048387177,0.0000017723451,0.000011724608,0.0025490175],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901617,0.00007388552,0.0001322668,0.0002650946,0.00029453106,0.00021806014],"domain_scores_gemma":[0.9992068,0.00006056397,0.000079159945,0.00031251946,0.00023961278,0.000101340345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033747495,0.00013330505,0.00012132055,0.00007430434,0.00010163303,0.00017157133,0.00047415317,0.000037892903,0.000025798645],"category_scores_gemma":[0.00002556383,0.00007380202,0.000030554806,0.000385309,0.00006501769,0.00029511043,0.00010992071,0.00008807873,0.00005511968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013688261,0.0009267715,0.042391784,0.00007327844,0.0004894096,0.000042952994,0.029624753,0.033998545,0.0016242557,0.65635544,0.20800923,0.025094748],"study_design_scores_gemma":[0.009181005,0.0013240473,0.0038693598,0.00007516897,0.000071184055,0.00021599988,0.0012284106,0.9120473,0.05356002,0.009409697,0.007917015,0.0011007941],"about_ca_topic_score_codex":0.00004926018,"about_ca_topic_score_gemma":0.000017981705,"teacher_disagreement_score":0.9279157,"about_ca_system_score_codex":0.000047840684,"about_ca_system_score_gemma":0.000059201448,"threshold_uncertainty_score":0.3009559},"labels":[],"label_agreement":null},{"id":"W2965944281","doi":"","title":"Tight analyses for non-smooth stochastic gradient descent","year":2019,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Lipschitz continuity; Stochastic gradient descent; Differentiable function; Combinatorics; Convex function; Gradient descent; Upper and lower bounds; Regular polygon; Discrete mathematics; Applied mathematics; Mathematical analysis; Computer science","score_opus":0.046909930151894284,"score_gpt":0.3102476221312967,"score_spread":0.26333769197940243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965944281","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060600974,0.000023284674,0.98706836,0.00017230009,0.0004085263,0.00064156717,0.000001672178,0.00045465736,0.0051695625],"genre_scores_gemma":[0.9603824,0.000005460807,0.03630149,0.00018377019,0.00003467724,0.000107962165,0.000009469995,0.00002459272,0.0029501542],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837416,0.00011417377,0.0002524087,0.00058969716,0.00027565975,0.00039390562],"domain_scores_gemma":[0.99828565,0.00056103466,0.000192769,0.00062022917,0.00021812318,0.00012221323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059471664,0.00023545053,0.0002738703,0.00027811583,0.00016795647,0.00016645079,0.0008620302,0.00008204028,0.00012983945],"category_scores_gemma":[0.00031783176,0.00020784055,0.000116426876,0.0002920722,0.000072149865,0.00019566697,0.0001487141,0.0002522494,0.00019560958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052765852,0.00007526689,0.00007659453,0.000021953478,0.000028117021,0.0000013416072,0.0007526672,0.025002956,0.001196654,0.9558377,0.00020626909,0.016747704],"study_design_scores_gemma":[0.00071746396,0.0010969717,0.00058489945,0.00025072266,0.000026561313,0.0000045723223,0.00018635292,0.9044617,0.0023414257,0.08919884,0.00063734525,0.00049313245],"about_ca_topic_score_codex":0.0000020741409,"about_ca_topic_score_gemma":4.294957e-7,"teacher_disagreement_score":0.95432234,"about_ca_system_score_codex":0.00007927304,"about_ca_system_score_gemma":0.00010558959,"threshold_uncertainty_score":0.84754914},"labels":[],"label_agreement":null},{"id":"W2969451120","doi":"","title":"A Lyapunov analysis for accelerated gradient methods: From deterministic to stochastic case","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Lyapunov function; Ode; Discretization; Mathematics; Applied mathematics; Ordinary differential equation; Stochastic gradient descent; Stochastic differential equation; Connection (principal bundle); Gradient descent; Acceleration; Convergence (economics); Mathematical analysis; Computer science; Differential equation; Nonlinear system; Physics","score_opus":0.15412939823436725,"score_gpt":0.27313917530757603,"score_spread":0.11900977707320878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969451120","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03490209,0.000023637942,0.9616124,0.0000482561,0.00078584417,0.0017115027,0.00023229205,0.00059819844,0.00008575544],"genre_scores_gemma":[0.6822278,0.0000031864129,0.31726488,0.00011261563,0.000033767286,0.000023312918,0.00007998543,0.000027818714,0.00022664],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99648035,0.00025207587,0.00045595397,0.0021441283,0.00012523969,0.0005422599],"domain_scores_gemma":[0.995338,0.0010286721,0.00046372885,0.002280855,0.0005129775,0.0003757277],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045118693,0.0005447525,0.0009023073,0.0014455615,0.00020426774,0.00029013556,0.0021647,0.00034850065,0.00003625191],"category_scores_gemma":[0.0003326752,0.0006384572,0.00054223475,0.0025164583,0.000068372974,0.00023567548,0.0020651298,0.00035865346,0.000039645925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004737597,0.00008622416,0.00013379258,0.000030575553,0.00075730693,0.0004357357,0.00046683126,0.9739652,0.000021892538,0.023188194,0.00009371866,0.00077312783],"study_design_scores_gemma":[0.00041061876,0.00014990315,0.00015464314,0.000058125126,0.001218525,0.0000209704,0.000056948003,0.97229254,0.000114442984,0.024818862,0.000031838877,0.00067255995],"about_ca_topic_score_codex":0.00046389815,"about_ca_topic_score_gemma":0.00008300879,"teacher_disagreement_score":0.6473257,"about_ca_system_score_codex":0.0004202396,"about_ca_system_score_gemma":0.00023061858,"threshold_uncertainty_score":0.99960667},"labels":[],"label_agreement":null},{"id":"W2970250826","doi":"","title":"Piecewise Strong Convexity of Neural Networks","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Maxima and minima; Piecewise; Convexity; Artificial neural network; Mathematics; Differentiable function; Stochastic gradient descent; Convex function; Applied mathematics; Norm (philosophy); Open set; Regularization (linguistics); Mathematical optimization; Regular polygon; Algorithm; Computer science; Mathematical analysis; Discrete mathematics; Artificial intelligence; Geometry","score_opus":0.014168538568912753,"score_gpt":0.23486229634571243,"score_spread":0.22069375777679967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970250826","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014616271,0.00011353622,0.9815039,0.00008003061,0.0009248306,0.00048660333,0.0000023498544,0.0004238013,0.0018486918],"genre_scores_gemma":[0.996072,0.0000013329905,0.0036662521,0.00012880586,0.00003055703,0.0000259374,0.0000139013655,0.0000061753053,0.000055048076],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985529,0.000042636988,0.0006501456,0.00015092352,0.0003748732,0.0002284912],"domain_scores_gemma":[0.99853635,0.000044088127,0.00062420947,0.00035262527,0.0003781165,0.00006461831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026121645,0.00014440392,0.00022469672,0.00018618272,0.00008069936,0.0003580443,0.00056244544,0.00008267094,0.000006170826],"category_scores_gemma":[0.00003733877,0.00012985515,0.000045512872,0.00048784114,0.000039874325,0.00435501,0.000110345354,0.00013801844,0.000015199749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001874127,0.000033125896,0.0034610997,0.00068455585,0.000013211556,6.485996e-7,0.001829195,0.8838913,0.000079541016,0.048335142,0.0005792625,0.061074197],"study_design_scores_gemma":[0.00023423982,0.00007322687,0.0003140458,0.000075896365,0.0000030007159,0.00001954891,0.000092620074,0.99871975,0.00014880106,0.000047441248,0.00014394315,0.00012749636],"about_ca_topic_score_codex":0.00002141172,"about_ca_topic_score_gemma":1.697679e-7,"teacher_disagreement_score":0.98145574,"about_ca_system_score_codex":0.000040402138,"about_ca_system_score_gemma":0.000043361964,"threshold_uncertainty_score":0.5295339},"labels":[],"label_agreement":null},{"id":"W2970271714","doi":"","title":"A Latent Variational Framework for Stochastic Optimization","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Stochastic optimization; Stochastic gradient descent; Stochastic differential equation; Mathematical optimization; Computer science; Gradient descent; Continuous-time stochastic process; Inference; Stochastic process; Optimization problem; Stochastic approximation; Mathematics; Applied mathematics; Artificial intelligence; Key (lock); Artificial neural network","score_opus":0.016983820967495705,"score_gpt":0.2520262587933482,"score_spread":0.23504243782585252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970271714","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012314403,0.00003957573,0.9963022,0.00033893026,0.0011570345,0.0011669939,0.000008174342,0.0006075506,0.00025641135],"genre_scores_gemma":[0.5087524,6.742993e-7,0.4903635,0.00035764588,0.00007285744,0.00029012832,0.00007439361,0.0000113699925,0.00007702309],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986007,0.000024939112,0.00054493453,0.00019974979,0.00039849296,0.00023119143],"domain_scores_gemma":[0.9984705,0.00013901548,0.00047894267,0.00027393,0.0005731543,0.0000644556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002767799,0.00015382987,0.000170812,0.00024894066,0.00016857314,0.0007990105,0.00043127657,0.000116699965,0.000010245507],"category_scores_gemma":[0.00019521001,0.00014458396,0.000047811696,0.00047024857,0.000014270753,0.0038430681,0.000060584567,0.00010191878,0.00004187481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061826495,0.000008781175,0.000020276606,0.00010339745,0.0000039947836,3.156055e-8,0.00044367107,0.7920122,0.0000033436863,0.20515023,0.00008855006,0.0021593429],"study_design_scores_gemma":[0.00028908264,0.00007756399,0.00003563812,0.00012386152,0.0000049994924,0.000015302703,0.000030726795,0.9961075,0.00001497769,0.002981613,0.00014980114,0.00016891753],"about_ca_topic_score_codex":0.000003839809,"about_ca_topic_score_gemma":3.1135908e-8,"teacher_disagreement_score":0.50862926,"about_ca_system_score_codex":0.00009113903,"about_ca_system_score_gemma":0.0000981482,"threshold_uncertainty_score":0.77048767},"labels":[],"label_agreement":null},{"id":"W2970990876","doi":"","title":"Reducing the variance in online optimization by transporting past gradients","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of British Columbia","funders":"","keywords":"Hessian matrix; Estimator; Computer science; Iterated function; Variance (accounting); Variance reduction; Convergence (economics); Mathematical optimization; Rate of convergence; Optimization problem; Applied mathematics; Algorithm; Mathematics; Statistics; Mathematical analysis","score_opus":0.011025963739625494,"score_gpt":0.2322976399575386,"score_spread":0.2212716762179131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970990876","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020453312,0.00009600173,0.9769901,0.00050810864,0.0005556022,0.0006244872,0.0000058026535,0.0003196105,0.00044697922],"genre_scores_gemma":[0.98220485,0.000004829013,0.017248424,0.00029603203,0.00003241377,0.00005308179,0.000075444004,0.000008967543,0.00007592427],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983845,0.000052358693,0.00075935165,0.00019627588,0.00035773148,0.00024978505],"domain_scores_gemma":[0.9988894,0.00004091948,0.0005525481,0.00029504648,0.00018112178,0.00004096752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041243076,0.00014617215,0.00016192975,0.00018268409,0.00014743338,0.00051881216,0.00058011216,0.00006703775,0.0000028902866],"category_scores_gemma":[0.00004618775,0.000114040326,0.000026831976,0.0008805835,0.000021886592,0.004233804,0.000041358286,0.00017065227,0.00000873395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040326636,0.000022728198,0.0013167142,0.00012317722,0.0000022039897,2.8730213e-7,0.0026726038,0.9851574,0.0000736268,0.0015110243,0.00021249677,0.008903719],"study_design_scores_gemma":[0.00025548929,0.000029518918,0.00046928282,0.00020829076,0.00000199117,0.0000159248,0.00024990801,0.99827963,0.000055769833,0.00002473791,0.00027696823,0.00013246744],"about_ca_topic_score_codex":0.00005537036,"about_ca_topic_score_gemma":8.540974e-7,"teacher_disagreement_score":0.9617516,"about_ca_system_score_codex":0.000085269974,"about_ca_system_score_gemma":0.00004205406,"threshold_uncertainty_score":0.50029176},"labels":[],"label_agreement":null},{"id":"W2971055146","doi":"","title":"Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Initialization; Jacobian matrix and determinant; Gradient descent; Maxima and minima; Parameterized complexity; Convergence (economics); Artificial neural network; Applied mathematics; Mathematics; Computer science; Mathematical optimization; Algorithm; Mathematical analysis; Artificial intelligence","score_opus":0.032225588059849056,"score_gpt":0.17981089824644833,"score_spread":0.14758531018659926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971055146","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32050866,0.000016012249,0.67833406,0.000014147453,0.00058308477,0.00037248418,0.0000028165912,0.00011525216,0.000053506228],"genre_scores_gemma":[0.9857384,0.000012380547,0.013893821,0.000074078984,0.000012825233,0.0000016740495,0.000005247383,0.0000094923125,0.0002520929],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989135,0.000041450974,0.00018440944,0.00049293606,0.000071448376,0.0002962081],"domain_scores_gemma":[0.9988788,0.00014404263,0.00019111254,0.0005414121,0.00015521492,0.00008943759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011605739,0.0001565507,0.00021934537,0.00014380473,0.000059729246,0.000028456376,0.00083991216,0.000062804254,0.00002117215],"category_scores_gemma":[0.00002802358,0.00016767278,0.00014389888,0.0005820592,0.00007773385,0.00038148725,0.00022487214,0.00010001134,0.0000053178264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015496848,0.00011765418,0.011216833,0.000041780644,0.00005275336,0.0000123827,0.00016331357,0.50061005,0.0009284229,0.48573112,0.00018505777,0.00078565435],"study_design_scores_gemma":[0.0007407904,0.00019495058,0.001450069,0.000018805571,0.0000145529575,0.0000028214831,0.000017208175,0.994463,0.000883524,0.0020069429,0.00002493814,0.0001823937],"about_ca_topic_score_codex":0.000017395432,"about_ca_topic_score_gemma":0.0000022584595,"teacher_disagreement_score":0.66522974,"about_ca_system_score_codex":0.00007714796,"about_ca_system_score_gemma":0.000025362382,"threshold_uncertainty_score":0.68374974},"labels":[],"label_agreement":null},{"id":"W2971899460","doi":"10.48550/arxiv.1909.00843","title":"Simple and optimal high-probability bounds for strongly-convex stochastic gradient descent","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Stochastic gradient descent; Simple (philosophy); Mathematics; Rate of convergence; Convex function; Applied mathematics; Generalization; Convergence (economics); Gradient descent; Regular polygon; Mathematical optimization; Computer science; Artificial neural network; Mathematical analysis","score_opus":0.057569341749089654,"score_gpt":0.1974791108620137,"score_spread":0.13990976911292405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971899460","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18153985,0.00003719891,0.8157301,0.000059255635,0.0005954064,0.0015087173,0.000067900226,0.0004085129,0.00005306903],"genre_scores_gemma":[0.9433139,0.000016314352,0.056288622,0.000041709933,0.00004713309,0.000016766591,0.00005887553,0.000030389538,0.00018626789],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997091,0.00009077195,0.00033579278,0.0017556486,0.00014665684,0.0005801098],"domain_scores_gemma":[0.99722844,0.00027642015,0.00035205402,0.0015364017,0.00033979822,0.0002668769],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003680247,0.0004738611,0.0005480553,0.00030701663,0.00021925491,0.00023438991,0.0015109977,0.0003250906,0.000014803699],"category_scores_gemma":[0.00011689067,0.00055048574,0.00020825957,0.00034970976,0.00024295607,0.0003542939,0.0021795197,0.00041253882,0.00001016618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004302073,0.00010207337,0.0005068305,0.00012180216,0.000059552793,0.0000070826104,0.00012374841,0.66462886,0.0000059450936,0.33405095,0.00016365993,0.00018649423],"study_design_scores_gemma":[0.0007390586,0.00025745793,0.00088835694,0.00006175516,0.000086778,0.00000306767,0.000027411983,0.8700152,0.00006740158,0.12728639,0.000051630526,0.0005154526],"about_ca_topic_score_codex":0.00010405468,"about_ca_topic_score_gemma":0.0000123592645,"teacher_disagreement_score":0.76177406,"about_ca_system_score_codex":0.00048319955,"about_ca_system_score_gemma":0.00025565104,"threshold_uncertainty_score":0.99969465},"labels":[],"label_agreement":null},{"id":"W2979200953","doi":"10.1109/isit44484.2020.9174521","title":"Optimizing the Transition Waste in Coded Elastic Computing","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Joins; Computer science; Distributed computing; Spare part; Cloud computing; Redundancy (engineering); Scalability; Virtual machine; Computation; Theoretical computer science; Parallel computing; Algorithm; Database","score_opus":0.03043746479869193,"score_gpt":0.25882606794198143,"score_spread":0.22838860314328951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979200953","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047067512,0.00005658077,0.9907723,0.005223014,0.00051407085,0.000655785,0.0000024648818,0.0007887549,0.0015163736],"genre_scores_gemma":[0.5198281,0.000008135933,0.4793451,0.0006862437,0.00006659032,0.00003059474,0.000010790545,0.000014781217,0.000009668542],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808836,0.00013741903,0.0004835022,0.00067717204,0.00033216213,0.00028136343],"domain_scores_gemma":[0.9987703,0.00026476398,0.00018789343,0.0006241488,0.00008302392,0.00006984803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000370257,0.00026299673,0.00030464728,0.00019238233,0.000100803765,0.00030788514,0.0015384058,0.0001587753,0.000009414957],"category_scores_gemma":[0.00008546792,0.00020943317,0.00010520598,0.00049334485,0.000051568975,0.0001381817,0.0011996684,0.0007007436,0.000010176762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041974695,0.000027939093,0.000003890203,0.000055472035,0.000015033433,0.000012472707,0.0062614004,0.93515116,0.00008809779,0.05620327,0.00026729083,0.0019097993],"study_design_scores_gemma":[0.000165761,0.00002911128,0.000020262592,0.00019970442,0.000008894203,0.0000062364174,0.00011845121,0.98349565,0.0007015058,0.0150227165,0.0000072869348,0.00022442192],"about_ca_topic_score_codex":0.000040949195,"about_ca_topic_score_gemma":0.000007110393,"teacher_disagreement_score":0.51935744,"about_ca_system_score_codex":0.00009980154,"about_ca_system_score_gemma":0.0001026874,"threshold_uncertainty_score":0.8540437},"labels":[],"label_agreement":null},{"id":"W2980003999","doi":"10.48550/arxiv.1910.04920","title":"Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of British Columbia","funders":"","keywords":"Hessian matrix; Mathematics; Convergence (economics); Applied mathematics; Broyden–Fletcher–Goldfarb–Shanno algorithm; Rate of convergence; Parameterized complexity; Mathematical optimization; Algorithm; Computer science","score_opus":0.05628495253693658,"score_gpt":0.23376804892028577,"score_spread":0.1774830963833492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980003999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008901864,0.00007833938,0.9878223,0.00006764419,0.0011210102,0.00056583487,0.00001272419,0.00042399578,0.0010063094],"genre_scores_gemma":[0.8529297,0.00002962035,0.145257,0.00013743721,0.000027888967,0.0000025907698,0.000015687034,0.000024533323,0.0015755091],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979162,0.00020739634,0.00026186486,0.001199875,0.0001003555,0.0003142916],"domain_scores_gemma":[0.99789953,0.00025341447,0.0003354494,0.0010522335,0.00030328883,0.00015608956],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003416444,0.00036187394,0.00037844866,0.00045504206,0.00011508208,0.0001642052,0.0011093969,0.0003459701,0.00016349314],"category_scores_gemma":[0.00007165856,0.00042478266,0.000099081786,0.00061875005,0.000150779,0.00042752753,0.0020237488,0.0005091942,0.000041695926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019014878,0.000049605896,0.00029440343,0.00009222332,0.00010953124,0.000015741041,0.000682671,0.6748422,0.00008552032,0.32263374,0.00020280897,0.00097254984],"study_design_scores_gemma":[0.00028621918,0.00006212711,0.0004375843,0.00007297946,0.00004678607,0.000010337938,0.00008934677,0.9165988,0.000062943494,0.08188931,0.000029033588,0.00041454952],"about_ca_topic_score_codex":0.00003615903,"about_ca_topic_score_gemma":0.000012146458,"teacher_disagreement_score":0.8440279,"about_ca_system_score_codex":0.0001633616,"about_ca_system_score_gemma":0.00020206794,"threshold_uncertainty_score":0.9998204},"labels":[],"label_agreement":null},{"id":"W2981188016","doi":"10.48550/arxiv.1910.07512","title":"On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Minimax; Mathematical optimization; Convergence (economics); Gradient descent; Mathematics; Optimization problem; Ridge; Computer science; Artificial intelligence; Artificial neural network","score_opus":0.05757981876166046,"score_gpt":0.17996773570436522,"score_spread":0.12238791694270476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981188016","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018047055,0.000028414417,0.9864745,0.00012457451,0.00068558246,0.0009160143,0.000011026183,0.0006751596,0.009280025],"genre_scores_gemma":[0.87995625,0.000053533135,0.11813341,0.00030467095,0.000052253,0.000008113682,0.000054419903,0.00004076698,0.0013965927],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755925,0.00016467652,0.0002726795,0.0013860528,0.00020748416,0.0004098785],"domain_scores_gemma":[0.9969852,0.0002496393,0.00039100545,0.0020089147,0.00024036157,0.00012488406],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036121515,0.0004175942,0.00036335216,0.00041089294,0.00022923281,0.00025650943,0.0028611156,0.0003533805,0.000021017599],"category_scores_gemma":[0.00011856128,0.00040673514,0.00024901854,0.000837515,0.00011963395,0.00034065155,0.0019794242,0.00062508974,0.000065038825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015735179,0.00007524327,0.0000558386,0.000030997435,0.000039220817,0.00001449265,0.00015504149,0.75427383,0.0000013490335,0.24444169,0.0008007229,0.000095854106],"study_design_scores_gemma":[0.0003885665,0.00009052055,0.000029682918,0.00010709525,0.0000476847,0.0000042834713,0.000032549462,0.9848799,0.000041159332,0.013900852,0.0000509732,0.0004267421],"about_ca_topic_score_codex":0.000034643403,"about_ca_topic_score_gemma":0.0000015959139,"teacher_disagreement_score":0.87815154,"about_ca_system_score_codex":0.0003100823,"about_ca_system_score_gemma":0.00023323928,"threshold_uncertainty_score":0.9998385},"labels":[],"label_agreement":null},{"id":"W2989651853","doi":"10.1609/aaai.v34i04.5793","title":"On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning","year":2020,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Implementation; Compression (physics); Quantization (signal processing); Convergence (economics); Compression ratio; Rate of convergence; Data compression; Bounded function; Algorithm; Data compression ratio; Upper and lower bounds; Artificial intelligence; Theoretical computer science; Image compression; Mathematics; Telecommunications; Engineering; Image processing; Channel (broadcasting)","score_opus":0.11402986330989107,"score_gpt":0.3676228565956723,"score_spread":0.2535929932857812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989651853","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0082567725,0.000010377584,0.9580546,0.03197071,0.000043347674,0.0012055796,0.00007256174,0.000067859764,0.00031819128],"genre_scores_gemma":[0.9731855,0.000042579257,0.026394555,0.00010266199,0.000019126885,0.00021367402,0.000028648145,0.000010567905,0.0000027012184],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979925,0.00012823928,0.00073229364,0.0004698808,0.00047222292,0.00020483272],"domain_scores_gemma":[0.99460894,0.0028817635,0.0010300147,0.0005797817,0.0008405991,0.00005891419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009787721,0.00023253297,0.00041270946,0.0001163424,0.00041652346,0.00032805544,0.002031564,0.00011005166,0.000026632782],"category_scores_gemma":[0.0034082485,0.00013371253,0.00021159695,0.00078062713,0.0008811556,0.00011161616,0.0014927704,0.00070243696,0.000001247866],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003675801,0.000053788688,0.0003479222,0.00003433613,0.00016313914,2.5444237e-8,0.0014353162,0.0006537785,0.00017555557,0.99453586,0.00003290034,0.0025306311],"study_design_scores_gemma":[0.000015954765,0.000118404096,0.00055811787,0.00009700931,0.00023457123,2.7901993e-7,0.0004734165,0.4162273,0.019819621,0.56235343,0.0000042143324,0.00009764512],"about_ca_topic_score_codex":0.000030805826,"about_ca_topic_score_gemma":0.0000062225286,"teacher_disagreement_score":0.9649287,"about_ca_system_score_codex":0.00003313709,"about_ca_system_score_gemma":0.00007434003,"threshold_uncertainty_score":0.5452639},"labels":[],"label_agreement":null},{"id":"W2993887252","doi":"10.1109/tac.2020.2966035","title":"Deep Teams: Decentralized Decision Making With Finite and Infinite Number of Agents","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Computation; Finite set; Invariant (physics); Probability distribution; Deep learning; Quantization (signal processing); LTI system theory; Function (biology); Computational complexity theory","score_opus":0.01307680213025223,"score_gpt":0.25983123745495906,"score_spread":0.24675443532470684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993887252","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007236967,0.000014650183,0.99127483,0.00035015016,0.000093191135,0.00049107964,0.000006997795,0.00042267103,0.000109485336],"genre_scores_gemma":[0.7520356,0.000009702091,0.24728309,0.0006085034,0.0000038445855,0.000043194646,2.6760364e-7,0.00001242961,0.0000033638544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866873,0.000065514316,0.00039611835,0.00030977232,0.00035493038,0.00020495166],"domain_scores_gemma":[0.9986163,0.00067385164,0.00017520634,0.00031490758,0.000093369476,0.00012638643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011127717,0.0001816111,0.00030502214,0.00012330708,0.00009834515,0.00007736963,0.00031511756,0.000060534636,0.0001383007],"category_scores_gemma":[0.0000513929,0.000155269,0.00006563227,0.0004902211,0.00006351973,0.00025837356,0.0000035596354,0.0001015971,0.00001879058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043656767,0.00047744837,0.0008192065,0.00019199247,0.00038171367,0.000037343696,0.006488196,0.30390176,0.00030666284,0.0035900327,0.00011698022,0.6832521],"study_design_scores_gemma":[0.0020635705,0.00019944883,0.00036035918,0.0001782217,0.00005554417,0.000019078909,0.00002907931,0.9958578,0.00046202383,0.000596094,0.000020285413,0.00015851665],"about_ca_topic_score_codex":0.000004555257,"about_ca_topic_score_gemma":0.0000035824676,"teacher_disagreement_score":0.74479866,"about_ca_system_score_codex":0.000030740935,"about_ca_system_score_gemma":0.000045396842,"threshold_uncertainty_score":0.63316864},"labels":[],"label_agreement":null},{"id":"W2994062025","doi":"10.1109/tac.2020.3045094","title":"Continuous-Time Discounted Mirror Descent Dynamics in Monotone Concave Games","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Monotone polygon; Monotonic function; Regular polygon; Dynamics (music); Descent (aeronautics); Type (biology); Gradient descent; Legendre polynomials","score_opus":0.010066671967609297,"score_gpt":0.22882168264944328,"score_spread":0.21875501068183398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994062025","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055867396,0.000014616651,0.98714316,0.004517699,0.00020940557,0.0011455716,0.00003893606,0.0011567675,0.00018711288],"genre_scores_gemma":[0.9624148,0.000004806566,0.035917744,0.0012915187,0.000007993436,0.0002461317,0.000002880947,0.000026012782,0.00008812453],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980992,0.00012391347,0.00057857187,0.000478845,0.00035793497,0.00036154475],"domain_scores_gemma":[0.9987997,0.00031150907,0.00016297628,0.00044881948,0.00009050515,0.00018653493],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017401148,0.00027244727,0.00047109977,0.00023827703,0.00009210688,0.00013554205,0.0006008779,0.000101865444,0.00012580206],"category_scores_gemma":[0.000041599862,0.00027012717,0.0001359986,0.0005914861,0.00007982102,0.00032490038,0.0000038947114,0.00020866422,0.00013888741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010539255,0.00797923,0.00095676776,0.0007758521,0.0017617301,0.0006203622,0.026042,0.21005875,0.03270875,0.0653368,0.0022616838,0.65044415],"study_design_scores_gemma":[0.002054017,0.00025874918,0.0001854135,0.000077432036,0.000032591222,0.000008975537,0.000078070974,0.9946838,0.0020722537,0.00026645174,0.00001769663,0.00026452125],"about_ca_topic_score_codex":0.000051328225,"about_ca_topic_score_gemma":0.000036742687,"teacher_disagreement_score":0.95682806,"about_ca_system_score_codex":0.00032827372,"about_ca_system_score_gemma":0.0000908654,"threshold_uncertainty_score":0.9999751},"labels":[],"label_agreement":null},{"id":"W2995291884","doi":"","title":"On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Minimax; Mathematical optimization; Convergence (economics); Gradient descent; Optimization problem; Computer science; Mathematics; Artificial intelligence; Artificial neural network","score_opus":0.06320326867818603,"score_gpt":0.3032700120988561,"score_spread":0.24006674342067008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995291884","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043884057,0.0000046172613,0.9272605,0.016818093,0.00025441073,0.0003082803,0.000005340498,0.00048443113,0.05442548],"genre_scores_gemma":[0.88577825,0.000015439482,0.11139618,0.0017517996,0.00011033065,0.00014760566,0.00009090768,0.000021256012,0.0006882107],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802,0.0001480536,0.0003337112,0.0006021139,0.0006866247,0.00020951802],"domain_scores_gemma":[0.9985223,0.00037164512,0.00022845788,0.0003629738,0.0003955539,0.00011908274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019175661,0.00018691359,0.00014257507,0.0001861039,0.00032244466,0.000503227,0.0012549318,0.00006385004,0.00019909817],"category_scores_gemma":[0.0013525332,0.00016445809,0.00009417839,0.00049525435,0.000081368555,0.00041114222,0.00022101248,0.0004088208,0.0001007115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020996145,0.000058433394,0.0001341532,0.000002571952,0.000029734274,0.0000035138494,0.0017543932,0.5620769,0.00009895205,0.4330623,0.0014071065,0.0013509329],"study_design_scores_gemma":[0.00034498062,0.00018091277,0.0001511923,0.00003179136,0.0000070489564,0.000006362327,0.0002617584,0.9956653,0.00021611365,0.0026436937,0.0003231193,0.00016772204],"about_ca_topic_score_codex":0.00001666061,"about_ca_topic_score_gemma":6.2273955e-7,"teacher_disagreement_score":0.88533944,"about_ca_system_score_codex":0.00006945648,"about_ca_system_score_gemma":0.00009741548,"threshold_uncertainty_score":0.67064065},"labels":[],"label_agreement":null},{"id":"W2995434136","doi":"10.48550/arxiv.1905.12558","title":"Limitations of the Empirical Fisher Approximation for Natural Gradient\\n Descent","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fisher information; Hessian matrix; Fisher kernel; Heuristics; Mathematics; Applied mathematics; Econometrics; Mathematical economics; Mathematical optimization; Statistics; Computer science; Artificial intelligence; Kernel method","score_opus":0.2954199039827467,"score_gpt":0.22897875683003072,"score_spread":0.06644114715271598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995434136","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045398314,0.000047317866,0.94764113,0.00053018285,0.002581779,0.0028758848,0.0000430706,0.00014820842,0.0007340957],"genre_scores_gemma":[0.9680316,0.00010605232,0.02976692,0.00015548615,0.00005056897,0.000012803014,0.000037022848,0.000032177115,0.0018073964],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99697965,0.00026614987,0.00060647,0.0013892741,0.00025148343,0.0005069967],"domain_scores_gemma":[0.99502355,0.0008445903,0.0010457286,0.0019230598,0.0010252035,0.00013787948],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041954438,0.00047883362,0.00051979197,0.00038232713,0.00035973443,0.00013306235,0.0028094687,0.00038119178,0.000013471729],"category_scores_gemma":[0.0005591364,0.00045375002,0.00069822546,0.0014706933,0.00039236958,0.00053944264,0.001684475,0.00058822165,0.000016961189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010114297,0.00046955713,0.004628053,0.00028843514,0.00019293113,0.0000026088633,0.002245918,0.6177351,0.000049792547,0.37100738,0.0016208229,0.0016582534],"study_design_scores_gemma":[0.00077034195,0.00014977173,0.0042899568,0.00023793119,0.00020993876,0.0000036675117,0.00016174726,0.9582177,0.0005732715,0.03448184,0.0004477348,0.00045614695],"about_ca_topic_score_codex":0.0000226636,"about_ca_topic_score_gemma":0.000014576729,"teacher_disagreement_score":0.92263323,"about_ca_system_score_codex":0.00049266836,"about_ca_system_score_gemma":0.00042338984,"threshold_uncertainty_score":0.99979144},"labels":[],"label_agreement":null},{"id":"W2995947286","doi":"10.1109/cwit.2019.8929896","title":"Hierarchical coded matrix multiplication","year":2019,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Exploit; Matrix multiplication; Cloud computing; Coding (social sciences); Hierarchy; Multiplication (music); Matrix (chemical analysis); Distributed computing; Theoretical computer science; Computer security; Mathematics; Operating system","score_opus":0.010965208554065142,"score_gpt":0.2633271456321035,"score_spread":0.2523619370780384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995947286","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002868633,0.0000055025803,0.9831162,0.00083130656,0.000113047834,0.0002576594,3.351886e-7,0.0007109665,0.012096314],"genre_scores_gemma":[0.3983285,0.0000012106754,0.5990234,0.00021113455,0.000009135262,0.000017658924,0.000002185409,0.000003974565,0.0024027603],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936247,0.000016643462,0.000118914104,0.00023195798,0.00015155751,0.00011845814],"domain_scores_gemma":[0.999333,0.0000664175,0.000033917582,0.00046753176,0.00005204908,0.00004704652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000094566545,0.000059174035,0.00006631664,0.00007973793,0.00002558962,0.00005366952,0.00046806977,0.000036546615,0.000076401724],"category_scores_gemma":[0.00002675594,0.00005165071,0.000025371994,0.00022915794,0.0000131118,0.00020422548,0.00012469942,0.000054721397,0.0004467935],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014695543,0.000023170142,0.00051784836,0.0000025568786,0.0000020650775,2.3102253e-7,0.000066842855,0.00032393658,0.0017333042,0.99229336,0.00090142083,0.0041337814],"study_design_scores_gemma":[0.00023159893,0.000054726977,0.0012532576,0.0000051324673,9.608452e-7,0.0000066985704,0.0000034423779,0.9727542,0.0065877037,0.017520027,0.0014623512,0.000119933226],"about_ca_topic_score_codex":0.000004382325,"about_ca_topic_score_gemma":1.8202857e-7,"teacher_disagreement_score":0.97477335,"about_ca_system_score_codex":0.0000201971,"about_ca_system_score_gemma":0.00001714429,"threshold_uncertainty_score":0.5742776},"labels":[],"label_agreement":null},{"id":"W2996067004","doi":"","title":"Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Initialization; Generalization; Gradient descent; Layer (electronics); Artificial neural network; Population; Mathematics; Computer science; Flow (mathematics); Applied mathematics; Mathematical analysis; Artificial intelligence; Geometry; Chemistry","score_opus":0.08250555733982355,"score_gpt":0.3510375405511749,"score_spread":0.26853198321135135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996067004","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007542129,0.000008076632,0.9818614,0.0054417867,0.00029406187,0.00018404501,0.0000029706227,0.0003131048,0.004352426],"genre_scores_gemma":[0.9681268,0.000015664522,0.030745087,0.0007685212,0.00011642167,0.000033479682,0.00007537912,0.000013187723,0.00010550888],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984488,0.00016638126,0.0003780089,0.00042408978,0.00043515328,0.00014758854],"domain_scores_gemma":[0.998717,0.00010166043,0.00027326972,0.00027389085,0.0005111152,0.00012304183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013127393,0.0001351424,0.00014709088,0.00016495753,0.0000999498,0.00017559266,0.0007951525,0.000041850883,0.00021760802],"category_scores_gemma":[0.0003583629,0.0001413284,0.00006304714,0.0003961961,0.000054982625,0.00061536726,0.00014582412,0.00020751014,0.00001638034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000081086055,0.000041488776,0.0017287853,0.0000022003717,0.000017217419,0.0000022712013,0.0009353567,0.5710766,0.0011643596,0.42240793,0.00008383945,0.002531901],"study_design_scores_gemma":[0.00028815778,0.00020200569,0.0012879453,0.000018969356,0.0000067825567,0.000004952465,0.00007738733,0.9932674,0.00095682486,0.0037177277,0.0000443369,0.00012751487],"about_ca_topic_score_codex":0.00003468486,"about_ca_topic_score_gemma":0.0000024805267,"teacher_disagreement_score":0.96058464,"about_ca_system_score_codex":0.0000325418,"about_ca_system_score_gemma":0.00004535435,"threshold_uncertainty_score":0.57632047},"labels":[],"label_agreement":null},{"id":"W2997709794","doi":"10.1609/aaai.v34i04.5793","title":"On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning","year":2020,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Implementation; Quantization (signal processing); Compression (physics); Convergence (economics); Compression ratio; Rate of convergence; Data compression; Bounded function; Upper and lower bounds; Algorithm; Data compression ratio; Layer (electronics); Theoretical computer science; Artificial intelligence; Image compression; Mathematics; Telecommunications; Image processing; Engineering; Channel (broadcasting)","score_opus":0.038335804886319276,"score_gpt":0.3304518789392912,"score_spread":0.2921160740529719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997709794","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018652813,0.000006277202,0.9553685,0.04212432,0.0000033500894,0.00036786654,0.000017098428,0.00007797547,0.00016932611],"genre_scores_gemma":[0.8703065,0.0000048467755,0.12928312,0.0002815011,0.0000049143987,0.000055926117,0.000059002992,0.0000030623607,0.0000011589696],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991666,0.00021354732,0.00021894602,0.00015249653,0.00015336757,0.00009500634],"domain_scores_gemma":[0.9949459,0.00444269,0.00012618375,0.00034275744,0.00010086611,0.00004161599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003504139,0.00006573868,0.00012397293,0.000033557986,0.00025999692,0.00008478696,0.00036815228,0.000020582786,0.000035545403],"category_scores_gemma":[0.00095016725,0.000035966288,0.000059214424,0.0005676673,0.00019373705,0.000093118826,0.00020449211,0.00010991436,4.9922363e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052487767,0.000012943021,0.0018455116,0.0000020501245,0.00009172699,3.1644767e-8,0.0005091951,0.0005243181,0.000008552465,0.9964286,0.00010053069,0.0004713023],"study_design_scores_gemma":[0.0001591713,0.00013911276,0.007861538,0.000003294297,0.00018867251,3.3466077e-7,0.0003001508,0.9220063,0.00065242185,0.06857007,0.000059699436,0.000059235546],"about_ca_topic_score_codex":0.00000824741,"about_ca_topic_score_gemma":0.0000030171805,"teacher_disagreement_score":0.92785853,"about_ca_system_score_codex":0.0000073498627,"about_ca_system_score_gemma":0.000010749526,"threshold_uncertainty_score":0.19997123},"labels":[],"label_agreement":null},{"id":"W2998037822","doi":"10.24963/ijcai.2020/451","title":"pbSGD: Powered Stochastic Gradient Descent Methods for Accelerated Non-Convex Optimization","year":2020,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Stochastic gradient descent; Robustness (evolution); Rate of convergence; Benchmark (surveying); Mathematical optimization; Convergence (economics); Computer science; Gradient descent; Applied mathematics; Convex function; Nonlinear system; Stochastic optimization; Mathematics; Algorithm; Regular polygon; Artificial neural network; Artificial intelligence; Key (lock)","score_opus":0.06165611253987958,"score_gpt":0.3387991457714283,"score_spread":0.2771430332315487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998037822","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021580838,0.00004092196,0.994027,0.0024710959,0.0004094719,0.0014717557,0.000004330619,0.0010930046,0.0004608149],"genre_scores_gemma":[0.04690167,0.0000060148895,0.9507991,0.0018865215,0.000054844153,0.00023124243,0.00002866775,0.000032608463,0.00005930199],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980598,0.00008391745,0.00047885702,0.0007255552,0.0002247591,0.00042711996],"domain_scores_gemma":[0.99839914,0.00023161148,0.00018641957,0.0004691225,0.00039720346,0.00031649362],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034674973,0.00027494942,0.00033233597,0.00017160205,0.00016548751,0.00024261168,0.00095276337,0.00010715718,0.000091002854],"category_scores_gemma":[0.00045470256,0.00025950166,0.00011726525,0.00093643495,0.000044508884,0.00046885965,0.00025018593,0.00011491605,0.0000151506965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009040366,0.0002294644,0.000012360574,0.000070328715,0.00009831329,0.000003195982,0.0023900026,0.8408914,0.0037017378,0.11192786,0.005592846,0.034992084],"study_design_scores_gemma":[0.0006768589,0.00034185787,0.00001331146,0.0000150888645,0.000018027666,0.000004556271,0.000028487642,0.987285,0.00969128,0.0014058023,0.00021397043,0.00030576452],"about_ca_topic_score_codex":0.0000063578077,"about_ca_topic_score_gemma":2.9799364e-7,"teacher_disagreement_score":0.14639358,"about_ca_system_score_codex":0.00008793258,"about_ca_system_score_gemma":0.00009797231,"threshold_uncertainty_score":0.9999857},"labels":[],"label_agreement":null},{"id":"W2999758721","doi":"10.1137/21m1397854","title":"How to Trap a Gradient Flow","year":2024,"lang":"en","type":"preprint","venue":"SIAM Journal on Computing","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Azrieli Foundation; Microsoft Research","keywords":"Dimension (graph theory); Combinatorics; Mathematics; Logarithm; Gradient descent; Omega; Balanced flow; Upper and lower bounds; Function (biology); Polynomial; Domain (mathematical analysis); Binary logarithm; Discrete mathematics; Physics; Mathematical analysis; Computer science","score_opus":0.027508052989913663,"score_gpt":0.27600075768863036,"score_spread":0.2484927046987167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999758721","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020338024,0.00039003903,0.9748621,0.012029186,0.008198528,0.00047187542,0.0000056120634,0.0009114595,0.0010973834],"genre_scores_gemma":[0.31124797,0.000020313388,0.6860756,0.0010088758,0.0013126109,0.000014027852,0.0000031180823,0.00006118089,0.0002562904],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967391,0.0001472973,0.00062339846,0.0009603064,0.00089605316,0.00063385064],"domain_scores_gemma":[0.9977888,0.00018823569,0.0004086689,0.0008402543,0.00030404548,0.00046998102],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010045898,0.00050434854,0.000514071,0.0010836882,0.00029578563,0.003297692,0.0022741249,0.00021967867,0.0000057688085],"category_scores_gemma":[0.00024123599,0.0004556618,0.00039097323,0.00070383376,0.000030050422,0.00011852806,0.003055731,0.0023370765,0.00006220116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015660153,0.00016911849,0.000015512622,0.00022334726,0.00018127891,0.0007124736,0.004678656,0.51905036,0.00006118567,0.11242939,0.02776258,0.33470044],"study_design_scores_gemma":[0.00016016388,0.00036804832,0.000043111853,0.0020107885,0.000025148396,0.0005354777,0.000030465488,0.92273825,0.000343958,0.07052966,0.0026391498,0.000575793],"about_ca_topic_score_codex":0.0000019965505,"about_ca_topic_score_gemma":5.388684e-7,"teacher_disagreement_score":0.40368786,"about_ca_system_score_codex":0.00042712636,"about_ca_system_score_gemma":0.00026103726,"threshold_uncertainty_score":0.9999646},"labels":[],"label_agreement":null},{"id":"W3003571307","doi":"10.1109/icdm.2019.00198","title":"Elastic Bulk Synchronous Parallel Model for Distributed Deep Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); York University","funders":"","keywords":"Computer science; Synchronization (alternating current); Adaptability; Bulk synchronous parallel; Convergence (economics); Flexibility (engineering); Throughput; Parallel computing; Artificial intelligence; Distributed computing; Algorithm; Parallel algorithm; Channel (broadcasting); Wireless; Computer network; Mathematics","score_opus":0.0121083794301622,"score_gpt":0.23397732124147308,"score_spread":0.2218689418113109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003571307","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051563425,0.000021051237,0.9969076,0.00015684335,0.00014929652,0.0005048577,0.0000027980939,0.000858185,0.00088375376],"genre_scores_gemma":[0.4824694,0.0000022823701,0.5165007,0.00006849574,0.000010699048,0.00006659273,0.000017669536,0.000009793226,0.0008543652],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989699,0.000013960168,0.00019457098,0.00036205532,0.00016255955,0.00029696128],"domain_scores_gemma":[0.9991995,0.00017536701,0.000078135716,0.00035051437,0.000120733996,0.00007575054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012464928,0.0001307929,0.00015160513,0.00007904719,0.00009064665,0.00009776174,0.00054248207,0.000061840896,0.000032949978],"category_scores_gemma":[0.00011237765,0.00012067673,0.00006205091,0.00019173259,0.00001821965,0.0002605456,0.00014812457,0.000089683796,0.0000727109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000446143,0.000023290706,0.00009882135,0.0000102052,0.000007347483,3.108066e-7,0.00011664049,0.82041323,0.00004198173,0.17722976,0.00018625418,0.0018676935],"study_design_scores_gemma":[0.00034135135,0.00013469314,0.000049479742,0.000009315631,0.0000046066425,0.000004409157,0.0000082832175,0.98946184,0.00008677386,0.00960679,0.00012677349,0.00016570518],"about_ca_topic_score_codex":0.0000035507283,"about_ca_topic_score_gemma":0.0000011316655,"teacher_disagreement_score":0.48195377,"about_ca_system_score_codex":0.00006131974,"about_ca_system_score_gemma":0.00004044248,"threshold_uncertainty_score":0.4921054},"labels":[],"label_agreement":null},{"id":"W3015390534","doi":"10.1109/icassp40776.2020.9054587","title":"Gradient Delay Analysis in Asynchronous Distributed Optimization","year":2020,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Asynchronous communication; Computer science; Range (aeronautics); Focus (optics); Optimization problem; Mathematical optimization; Asynchronous system; Stochastic optimization; Gradient method; Distributed computing; Algorithm; Mathematics; Computer network; Telecommunications; Engineering","score_opus":0.014367848399936482,"score_gpt":0.22921250900910584,"score_spread":0.21484466060916935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015390534","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004678134,0.000018080935,0.9961303,0.0018385161,0.00003810937,0.00018274167,0.0000038378284,0.0005416353,0.00077896233],"genre_scores_gemma":[0.5309911,0.000005365915,0.46851167,0.00042288285,0.000007889344,0.000013274452,0.000039589908,0.000004261224,0.0000039980814],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988752,0.000041985804,0.00028643777,0.00039362864,0.0001981223,0.00020460397],"domain_scores_gemma":[0.9993753,0.000042762094,0.00007583625,0.00029771708,0.000076410666,0.0001319903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000105082145,0.00011671383,0.00019147155,0.00027575166,0.0000406163,0.00009234071,0.0005325508,0.000047896236,0.000082540515],"category_scores_gemma":[0.000096791686,0.000112274014,0.00007555974,0.0038003987,0.000020476606,0.0002926516,0.0001527061,0.00007323533,0.000011682826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021609287,0.000034815886,0.0025597077,0.0000019748377,0.00003432862,0.000007945674,0.00026078647,0.93704146,0.0000041439666,0.059454545,0.00015989013,0.0004382622],"study_design_scores_gemma":[0.000164839,0.00006132609,0.0011759871,0.000002140666,0.000025595014,0.0000015029597,0.000011946637,0.9978289,0.00019053329,0.00037509066,0.000030890395,0.00013126485],"about_ca_topic_score_codex":0.000045393852,"about_ca_topic_score_gemma":0.00001842496,"teacher_disagreement_score":0.53052324,"about_ca_system_score_codex":0.00008100528,"about_ca_system_score_gemma":0.000040452094,"threshold_uncertainty_score":0.4578401},"labels":[],"label_agreement":null},{"id":"W3015635872","doi":"10.1109/icassp40776.2020.9053999","title":"Anytime Minibatch with Delayed Gradients: System Performance and Convergence Analysis","year":2020,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Convergence (economics); Regret; MNIST database; Rate of convergence; Computer science; Cloud computing; Exploit; Asynchronous communication; Scheme (mathematics); Mathematical optimization; Complement (music); Mathematics; Key (lock); Operating system; Artificial intelligence","score_opus":0.009654474414950279,"score_gpt":0.19037646061348634,"score_spread":0.18072198619853608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015635872","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048282064,0.000022063197,0.9492328,0.00044998346,0.00003354815,0.00017232592,0.0000019662457,0.00061391335,0.001191335],"genre_scores_gemma":[0.791495,0.00000848765,0.20811929,0.0002831185,0.000007889611,0.000016693528,0.000002613046,0.000005366885,0.000061552826],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888635,0.00002353192,0.0002042929,0.00044419698,0.00024634364,0.00019529372],"domain_scores_gemma":[0.9992509,0.00003298332,0.000088466535,0.0003208949,0.00011839052,0.00018836514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000093918796,0.0001395103,0.00021392392,0.00013377813,0.000091233276,0.00008972549,0.0004580863,0.00003369767,0.000019263067],"category_scores_gemma":[0.000012163587,0.00010833449,0.00003401821,0.0016997148,0.000053571956,0.00041046832,0.00013363497,0.000057601264,0.000015828287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038571368,0.00032039604,0.36019635,0.0007911824,0.0042421096,0.00017516637,0.019893628,0.049315374,0.00075594237,0.53954536,0.008326017,0.016052756],"study_design_scores_gemma":[0.00019391364,0.00030484638,0.0022113072,0.000011745153,0.0000883194,0.0000142131485,0.000091308066,0.99592054,0.0009215853,0.000010604904,0.000059308186,0.00017228334],"about_ca_topic_score_codex":0.00002245754,"about_ca_topic_score_gemma":0.0000024511244,"teacher_disagreement_score":0.9466052,"about_ca_system_score_codex":0.00002578505,"about_ca_system_score_gemma":0.000024172787,"threshold_uncertainty_score":0.44177523},"labels":[],"label_agreement":null},{"id":"W3024230214","doi":"","title":"Stochastic Nested Variance Reduction for Nonconvex Optimization","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Variance reduction; Mathematics; Combinatorics; Nabla symbol; Gradient descent; Function (biology); Stationary point; Reduction (mathematics); Applied mathematics; Mathematical analysis; Computer science; Physics; Geometry; Statistics; Omega","score_opus":0.019737543993972165,"score_gpt":0.2620247578532457,"score_spread":0.24228721385927354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024230214","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012382498,0.00003273881,0.9953254,0.00029667633,0.0017965777,0.0009646842,0.00000465808,0.00095183594,0.0005035914],"genre_scores_gemma":[0.76555425,9.968331e-7,0.23325132,0.0002200434,0.0003731412,0.0003832098,0.000060629507,0.000016004191,0.00014041028],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985493,0.000034914545,0.000610432,0.00023565273,0.00030843643,0.00026126037],"domain_scores_gemma":[0.9978238,0.000040202438,0.00055980455,0.00031405783,0.0011862436,0.00007592399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003331871,0.00017131196,0.00017020135,0.00028851812,0.00041234877,0.00083737687,0.00044627883,0.00010647829,0.000003614937],"category_scores_gemma":[0.00017970553,0.00016643273,0.00003673452,0.0007467608,0.00007113203,0.005788488,0.00005173993,0.00007497474,0.00002040966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030600237,0.000025340365,0.0000041092517,0.00023336883,0.000009026398,1.3073237e-7,0.0027310117,0.93464696,0.00012955496,0.03290858,0.0015827809,0.02769854],"study_design_scores_gemma":[0.00034138115,0.00016029314,0.000007244253,0.0000987974,0.0000072337175,0.000070094415,0.00010026067,0.9978948,0.00034781778,0.00022899653,0.0005573545,0.00018569517],"about_ca_topic_score_codex":0.00000981629,"about_ca_topic_score_gemma":1.0803623e-7,"teacher_disagreement_score":0.7654304,"about_ca_system_score_codex":0.00009862714,"about_ca_system_score_gemma":0.000108366934,"threshold_uncertainty_score":0.80748445},"labels":[],"label_agreement":null},{"id":"W3033781806","doi":"10.1007/s10208-022-09554-y","title":"Halting Time is Predictable for Large Models: A Universality Property and Average-Case Analysis","year":2022,"lang":"en","type":"article","venue":"Foundations of Computational Mathematics","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Google (Canada)","funders":"","keywords":"Universality (dynamical systems); Mathematics; Case analysis; Property (philosophy); Probability distribution; Applied mathematics; Algorithm; Mathematical optimization; Statistics; Computer science; Artificial intelligence","score_opus":0.032035140737037074,"score_gpt":0.2679588309108773,"score_spread":0.23592369017384024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033781806","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034403603,0.000010584429,0.9948694,0.00037576412,0.000025136222,0.0005027202,0.00022779025,0.00012902344,0.00041918844],"genre_scores_gemma":[0.33271918,5.408518e-7,0.6667744,0.000056306366,0.000004745238,0.00007986654,0.00008611097,0.0000071415784,0.00027169473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886614,0.000046673536,0.00037507515,0.0002445673,0.00033120182,0.00013631734],"domain_scores_gemma":[0.99854845,0.0004857036,0.0002809779,0.00026505813,0.00037433876,0.000045477576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000534532,0.00009974584,0.00020998802,0.00034466982,0.00053735834,0.00008065807,0.00029520429,0.000020902327,0.00008802448],"category_scores_gemma":[0.000095164156,0.00009439337,0.000087674576,0.00088224217,0.000034459517,0.0004100869,0.0003105822,0.000059883143,0.0000013631687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029685052,0.00021103867,0.000025109952,0.00004867744,0.00014606012,0.0000020625155,0.0026422672,0.5964078,0.0000031328948,0.39990386,0.00035649497,0.00025054163],"study_design_scores_gemma":[0.00022313943,0.00005166528,0.000008019825,0.000005460804,0.000080888814,0.000046110345,0.00012174241,0.76273084,0.000009417437,0.23653974,0.00010401141,0.00007899945],"about_ca_topic_score_codex":0.00000987823,"about_ca_topic_score_gemma":8.338113e-7,"teacher_disagreement_score":0.32927883,"about_ca_system_score_codex":0.000068015994,"about_ca_system_score_gemma":0.0001151787,"threshold_uncertainty_score":0.413298},"labels":[],"label_agreement":null},{"id":"W3034386797","doi":"","title":"Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems","year":2020,"lang":"en","type":"article","venue":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Coordinate descent; Variance (accounting); Stochastic gradient descent; Mathematical optimization; Mathematics; Acceleration; Applied mathematics; Computer science; Algorithm; Artificial intelligence","score_opus":0.010610447985477783,"score_gpt":0.20336042538846896,"score_spread":0.19274997740299118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034386797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18152504,0.000044417302,0.8086773,0.008078621,0.000041799645,0.0005131181,0.0000012615964,0.0005765585,0.0005418672],"genre_scores_gemma":[0.70587444,0.000025303047,0.29399022,0.000044430082,0.000005032424,4.6887266e-7,3.1164046e-7,0.0000058626983,0.000053893058],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9971645,0.000025468593,0.00022167791,0.0013097661,0.00077697495,0.000501638],"domain_scores_gemma":[0.9967655,0.00005961569,0.00047900298,0.0006767863,0.0017431813,0.0002758996],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0007700532,0.000245786,0.00040032345,0.001985362,0.001965682,0.00011379383,0.0024473353,0.00021929671,0.0000011942207],"category_scores_gemma":[0.00019720709,0.00026353754,0.000022704238,0.011331068,0.008078024,0.001254933,0.0011563333,0.00032272516,0.0000012642771],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020719058,0.00020612717,0.020682396,0.00016781091,0.00009731247,0.00017342858,0.012541785,0.0035871218,0.76175493,0.12471344,0.000197136,0.075671345],"study_design_scores_gemma":[0.0049953912,0.0065202685,0.0060215374,0.0021480613,0.00035148728,0.001072224,0.035425495,0.29979584,0.6283956,0.006958845,0.0056183636,0.0026968636],"about_ca_topic_score_codex":0.0004068199,"about_ca_topic_score_gemma":0.00004880183,"teacher_disagreement_score":0.52434945,"about_ca_system_score_codex":0.00020780838,"about_ca_system_score_gemma":0.0011342963,"threshold_uncertainty_score":0.9999817},"labels":[],"label_agreement":null},{"id":"W3034426742","doi":"","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada); University of Alberta","funders":"","keywords":"Softmax function; Mathematics; Applied mathematics; Initialization; Rate of convergence; Bounded function; Entropy (arrow of time); Mathematical optimization; Computer science; Mathematical analysis; Physics; Artificial neural network; Artificial intelligence","score_opus":0.13212469095314747,"score_gpt":0.27314069128453417,"score_spread":0.1410160003313867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034426742","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006197568,0.000027790902,0.9888895,0.001235838,0.00043796643,0.00042040795,0.00002766654,0.0003030064,0.0024602264],"genre_scores_gemma":[0.9350761,0.00007126485,0.06426056,0.00044509623,0.000033704488,0.0000028089837,0.0000048555116,0.000011204405,0.00009437412],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980834,0.00034548764,0.0002599978,0.0008954284,0.00013512671,0.00028052804],"domain_scores_gemma":[0.9975074,0.0004341888,0.00041058706,0.0012689225,0.00022144256,0.00015743698],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035673042,0.00030206025,0.0003461068,0.00017908234,0.000116049145,0.00006247321,0.0028963322,0.00017089077,0.000028982993],"category_scores_gemma":[0.0005064196,0.00026901584,0.00022684579,0.0014885687,0.0002419018,0.00012468937,0.0021651762,0.0003534818,0.000025464085],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013581236,0.000043101118,0.00031526876,0.000026475576,0.000054320142,0.000016786402,0.00016042203,0.05896636,0.00001554106,0.9397418,0.0003832518,0.00026309854],"study_design_scores_gemma":[0.00010381372,0.00008669919,0.00029764685,0.000052905783,0.000024455841,0.0000015684985,0.000023966804,0.44975597,0.0013501048,0.5480401,0.000061691215,0.00020108021],"about_ca_topic_score_codex":0.00019931082,"about_ca_topic_score_gemma":0.0000034008904,"teacher_disagreement_score":0.92887855,"about_ca_system_score_codex":0.00029861965,"about_ca_system_score_gemma":0.00034537006,"threshold_uncertainty_score":0.9999762},"labels":[],"label_agreement":null},{"id":"W3034736247","doi":"10.24963/ijcai.2020/374","title":"SVRG for Policy Evaluation with Fewer Gradient Evaluations","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Reinforcement learning; Variance (accounting); Computer science; Convergence (economics); Function (biology); Artificial intelligence; Computation; Mathematical optimization; Gradient method; Bellman equation; Work (physics); Scale (ratio); Value (mathematics); Machine learning; Mathematics; Algorithm","score_opus":0.08629240404755965,"score_gpt":0.37203551811237995,"score_spread":0.2857431140648203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034736247","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008458542,0.000045815195,0.9731936,0.016897446,0.0004201157,0.004155879,0.00002662022,0.0009516062,0.004224343],"genre_scores_gemma":[0.16349418,0.00000865942,0.8313327,0.000987599,0.0002480184,0.0033956969,0.00021077057,0.000039283157,0.00028308618],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971249,0.00011373539,0.00041577534,0.0010070825,0.0010215539,0.00031693766],"domain_scores_gemma":[0.9968136,0.00015495913,0.00032380482,0.0011270999,0.0014089078,0.00017165065],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007831723,0.00033499103,0.00031541285,0.00044501762,0.00015360488,0.0003286213,0.0012120141,0.00017513876,0.00004251497],"category_scores_gemma":[0.00070751697,0.00028632864,0.00013905106,0.0006393028,0.000061599385,0.00021974885,0.00077186496,0.00023676119,0.000024275882],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016600876,0.00010070405,0.000023552524,0.00007637723,0.00010594948,6.857324e-7,0.0009912469,0.06618708,0.000031475738,0.89762056,0.008708293,0.026137464],"study_design_scores_gemma":[0.00042449796,0.00020820227,0.0001600348,0.000057040423,0.00007848739,0.0000037015877,0.000009475808,0.7536902,0.00046747757,0.24415982,0.00044347235,0.0002975867],"about_ca_topic_score_codex":0.00005683449,"about_ca_topic_score_gemma":0.000011874238,"teacher_disagreement_score":0.6875031,"about_ca_system_score_codex":0.0004692997,"about_ca_system_score_gemma":0.0016826601,"threshold_uncertainty_score":0.9999589},"labels":[],"label_agreement":null},{"id":"W3034995656","doi":"10.24963/ijcai.2020/452","title":"Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; University of Pennsylvania","keywords":"Stochastic gradient descent; Gradient descent; Computer science; Artificial neural network; Convergence (economics); Generalization; Closing (real estate); Artificial intelligence; Momentum (technical analysis); Gradient method; Stationary point; Deep learning; Rate of convergence; Algorithm; Mathematical optimization; Mathematics; Key (lock); Law","score_opus":0.10558419676324643,"score_gpt":0.3277355163136001,"score_spread":0.22215131955035367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034995656","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028854175,0.000102279075,0.9973274,0.0011508269,0.00012672547,0.00022791124,2.1386761e-7,0.00015105019,0.00062508776],"genre_scores_gemma":[0.4180883,0.000004112316,0.5812081,0.0006549247,0.000023851486,0.000011667891,0.0000014026098,0.0000053766807,0.0000022777238],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988931,0.00023527519,0.00030239148,0.00024437372,0.00014354112,0.00018136416],"domain_scores_gemma":[0.9993659,0.00018642536,0.00012696692,0.00020122888,0.000066423774,0.000053013944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039377945,0.000099817385,0.00015019417,0.00007403379,0.000053663152,0.000042241765,0.0004875549,0.000039399238,0.000008393087],"category_scores_gemma":[0.000112278154,0.00007416668,0.000045096258,0.00089334976,0.000047539404,0.00020122349,0.00014548203,0.00010775018,2.348321e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048979473,0.000010902122,0.000119838,0.0000024040355,0.0000060846414,0.0000011650286,0.00686337,0.6990012,0.00023174465,0.2447693,0.000033729153,0.048955344],"study_design_scores_gemma":[0.00011151376,0.00008564616,0.00017974037,0.000006975431,0.000003732308,0.0000027674762,0.00019541183,0.9956931,0.0008609448,0.0027670846,0.000012605108,0.00008051387],"about_ca_topic_score_codex":0.000020976262,"about_ca_topic_score_gemma":0.0000062125696,"teacher_disagreement_score":0.41779974,"about_ca_system_score_codex":0.000024337025,"about_ca_system_score_gemma":0.000014146059,"threshold_uncertainty_score":0.30244297},"labels":[],"label_agreement":null},{"id":"W3035353486","doi":"","title":"From Local SGD to Local Fixed Point Methods for Federated Learning","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Bottleneck; Computer science; Fixed point; Saddle point; Mathematical optimization; Context (archaeology); Computation; Operator (biology); Saddle; Convergence (economics); Theoretical computer science; Mathematics; Algorithm","score_opus":0.0574492059463758,"score_gpt":0.36364651826580796,"score_spread":0.30619731231943215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035353486","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033189383,0.000013552115,0.979477,0.016478518,0.00034979393,0.00030317227,0.000009814375,0.00069879857,0.0023374455],"genre_scores_gemma":[0.53988546,0.0000026538366,0.45795643,0.0017080401,0.00008692869,0.00005509888,0.000080075966,0.000020030435,0.00020525433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980202,0.00026415128,0.00037711448,0.0006981961,0.00036423307,0.0002761564],"domain_scores_gemma":[0.9984888,0.0005123981,0.0001821667,0.00015772825,0.0004248221,0.00023408358],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003992518,0.00024501543,0.0002628316,0.00017639132,0.00021243449,0.0004134484,0.000956311,0.00008850271,0.00034390666],"category_scores_gemma":[0.0014594318,0.00024728768,0.00009533363,0.00028910616,0.00004625535,0.0002679616,0.0003616457,0.000581141,0.000099059595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026251684,0.000062823994,0.00028451617,0.000009874116,0.00010521319,0.000012511882,0.002969939,0.3183586,0.0057472936,0.20534644,0.00055218564,0.46628806],"study_design_scores_gemma":[0.0004891355,0.0005643157,0.00006120176,0.00005304481,0.000005929494,0.000003235907,0.00019538152,0.9820394,0.004326643,0.004924962,0.0070733204,0.00026344325],"about_ca_topic_score_codex":0.00015700042,"about_ca_topic_score_gemma":0.0000057424754,"teacher_disagreement_score":0.6636808,"about_ca_system_score_codex":0.000116339186,"about_ca_system_score_gemma":0.00008206874,"threshold_uncertainty_score":0.9999979},"labels":[],"label_agreement":null},{"id":"W3035359320","doi":"10.48550/arxiv.2006.06587","title":"AdaS: Adaptive Scheduling of Stochastic Gradients","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Generalization; Artificial intelligence; Adaptive optimization; Stochastic gradient descent; Scheduling (production processes); Machine learning; Artificial neural network; Mathematical optimization; Algorithm; Mathematics","score_opus":0.09942448309067382,"score_gpt":0.19814584481332836,"score_spread":0.09872136172265454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035359320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012222409,0.000044292796,0.98564297,0.00007385686,0.0004728997,0.0004783157,0.000024998375,0.00042402922,0.00061625044],"genre_scores_gemma":[0.9139169,0.000012419972,0.085887596,0.000051435265,0.00003268915,0.0000022221368,0.000009494157,0.000022700564,0.00006455494],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997904,0.000099141915,0.0003259304,0.0011756786,0.00017101681,0.0003242463],"domain_scores_gemma":[0.9977045,0.00014116,0.00053528545,0.0010620313,0.00033351762,0.00022348593],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015186516,0.00035666322,0.000481488,0.0003994549,0.000089684116,0.000051736224,0.0022753517,0.0002480374,0.000013123636],"category_scores_gemma":[0.00014519168,0.00044080467,0.00023298056,0.0009429239,0.00016014019,0.00022440677,0.0024543456,0.00053652155,0.000021859736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023780014,0.000059855673,0.000066000975,0.000041247884,0.00007666361,0.000045527904,0.0003686213,0.5596314,0.0000261475,0.43950054,0.0000325758,0.00012765815],"study_design_scores_gemma":[0.00029561864,0.00013405277,0.000081340244,0.0001679677,0.000064437016,0.0000025992465,0.00007417932,0.8831847,0.00019081114,0.1154554,0.0000032302976,0.0003456998],"about_ca_topic_score_codex":0.000048500566,"about_ca_topic_score_gemma":0.0000026550338,"teacher_disagreement_score":0.9016945,"about_ca_system_score_codex":0.00018431677,"about_ca_system_score_gemma":0.00020834948,"threshold_uncertainty_score":0.9998044},"labels":[],"label_agreement":null},{"id":"W3035764496","doi":"","title":"A Provably Convergent and Practical Algorithm for Min-Max Optimization with Applications to GANs","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Lipschitz continuity; Oracle; Convergence (economics); Computer science; Gradient descent; Bounded function; Function (biology); Algorithm; Stochastic gradient descent; Mathematical optimization; Order (exchange); Mathematics; Applied mathematics; Artificial intelligence; Mathematical analysis","score_opus":0.05714080942242058,"score_gpt":0.2192986756334778,"score_spread":0.1621578662110572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035764496","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038678964,0.000016668382,0.99645746,0.00049061695,0.00010698987,0.0020868806,0.0000243651,0.00029527573,0.00013494912],"genre_scores_gemma":[0.04297189,0.0000510415,0.9562814,0.00017614325,0.00003228684,0.00010847747,0.000064784224,0.000022713797,0.00029122064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983219,0.000047847574,0.0001751105,0.0011075264,0.00010015345,0.00024745884],"domain_scores_gemma":[0.99813557,0.00013289221,0.00018731995,0.00076563825,0.00055859366,0.00021999177],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013875157,0.00024334413,0.00025216892,0.00023106903,0.00015323659,0.00020762371,0.00043606112,0.00016905196,0.000009572737],"category_scores_gemma":[0.000051170813,0.00027223266,0.0000645485,0.00065004925,0.000074165895,0.000310809,0.00077186694,0.00019141166,0.0000027808676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026045393,0.0002166224,0.00010037596,0.000092279726,0.000113760674,0.000060506838,0.00036869297,0.8404709,0.000008231305,0.15582332,0.00032693637,0.002392303],"study_design_scores_gemma":[0.0003389712,0.00014535915,0.00002198539,0.00006264805,0.000085410284,0.000021630207,0.00009847516,0.9961289,0.00017123563,0.0022290049,0.0003651009,0.00033125683],"about_ca_topic_score_codex":0.000023384568,"about_ca_topic_score_gemma":0.00001002509,"teacher_disagreement_score":0.155658,"about_ca_system_score_codex":0.00014864841,"about_ca_system_score_gemma":0.0003437016,"threshold_uncertainty_score":0.999973},"labels":[],"label_agreement":null},{"id":"W3035946931","doi":"10.48550/arxiv.2006.11077","title":"A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Bottleneck; Computer science; Overhead (engineering); Gas compressor; Transformation (genetics); Key (lock); Communication complexity; Distributed computing; Computer engineering; Mathematical optimization; Theoretical computer science; Mathematics; Embedded system; Engineering","score_opus":0.09560234657398782,"score_gpt":0.22523102904545428,"score_spread":0.12962868247146647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035946931","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012083095,0.00001254261,0.98347783,0.0020664115,0.00022467363,0.0010938039,0.000083265906,0.0006306242,0.00032775637],"genre_scores_gemma":[0.89026797,0.0000092783675,0.10893492,0.0003690143,0.000036095164,0.000020376046,0.00014937136,0.000024175395,0.00018879167],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981402,0.00013913706,0.00024499084,0.00103963,0.000115483526,0.00032053594],"domain_scores_gemma":[0.9976729,0.0002621678,0.00031807076,0.0011172208,0.00040303837,0.00022660925],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020132105,0.00029892515,0.00032386978,0.00024260214,0.00024936517,0.00016239136,0.0026861858,0.00016008242,0.000011961702],"category_scores_gemma":[0.00024149042,0.00036545598,0.00018677348,0.0007303024,0.00007915554,0.00013370298,0.00312523,0.0005116744,0.000048492057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023719467,0.00005354318,0.00014412134,0.00002644393,0.00005639676,0.000010376784,0.0007901622,0.86820567,0.000012818514,0.12960774,0.0008708206,0.00019817964],"study_design_scores_gemma":[0.00034575353,0.00009824044,0.00018527427,0.000100449106,0.00003719173,9.667194e-7,0.00008599467,0.9689871,0.00023371709,0.028731707,0.0008174854,0.00037613476],"about_ca_topic_score_codex":0.000047376754,"about_ca_topic_score_gemma":0.000004449645,"teacher_disagreement_score":0.8781849,"about_ca_system_score_codex":0.00030942517,"about_ca_system_score_gemma":0.00010552297,"threshold_uncertainty_score":0.9998797},"labels":[],"label_agreement":null},{"id":"W3036623140","doi":"10.1007/s10957-023-02297-y","title":"Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization","year":2023,"lang":"en","type":"article","venue":"Journal of Optimization Theory and Applications","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Global Collaborative Research, King Abdullah University of Science and Technology; Institut de Valorisation des Données; King Abdullah University of Science and Technology","keywords":"Mathematics; Convexity; Stochastic gradient descent; Convex function; Theory of computation; Convergence (economics); Mathematical optimization; Convex optimization; Applied mathematics; Variance (accounting); Regular polygon; Algorithm; Computer science; Artificial intelligence; Artificial neural network","score_opus":0.019978886667379847,"score_gpt":0.32969155642016446,"score_spread":0.3097126697527846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036623140","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018281734,0.00016959175,0.9987539,0.00022888262,0.00005432805,0.0004778955,0.0000138689265,0.000077907505,0.000040814644],"genre_scores_gemma":[0.04205905,0.00018779578,0.9574853,0.00006694868,0.000022384018,0.000088167006,0.00004231723,0.000012938355,0.000035079906],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987174,0.00018802234,0.00060249126,0.00021885437,0.00014219973,0.00013098164],"domain_scores_gemma":[0.9971714,0.0011890973,0.00070679764,0.00025150148,0.00057549414,0.00010569259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016519706,0.00012575115,0.00036234106,0.0010507714,0.00017988082,0.00007560514,0.00029275363,0.00006616234,0.000008030246],"category_scores_gemma":[0.00022007516,0.00011699053,0.00010293342,0.0022215152,0.00012409678,0.00029827925,0.00007895998,0.00007194743,1.5701272e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022782022,0.0000334548,0.000014203346,0.000012980867,0.00015190545,9.528527e-8,0.00025112292,0.721257,0.00013265325,0.27399802,0.000012956295,0.004112837],"study_design_scores_gemma":[0.00035625344,0.000100585574,0.00013922922,0.000018041888,0.0004541283,0.000007966722,0.000091039954,0.9735177,0.000269915,0.024892038,0.000045506185,0.00010755099],"about_ca_topic_score_codex":6.418002e-7,"about_ca_topic_score_gemma":8.722086e-8,"teacher_disagreement_score":0.25226074,"about_ca_system_score_codex":0.000021185433,"about_ca_system_score_gemma":0.000039552648,"threshold_uncertainty_score":0.47707352},"labels":[],"label_agreement":null},{"id":"W3037667206","doi":"","title":"DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate","year":2020,"lang":"en","type":"article","venue":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Science Foundation","keywords":"Asynchronous communication; Hessian matrix; Bounded function; Convergence (economics); Computer science; Distributed algorithm; Computation; Rate of convergence; Mathematical optimization; Dimension (graph theory); Empirical risk minimization; Node (physics); Algorithm; Mathematics; Applied mathematics; Distributed computing; Channel (broadcasting)","score_opus":0.007380128414547346,"score_gpt":0.18990669163490734,"score_spread":0.18252656322035998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037667206","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38881055,0.00008305809,0.60419345,0.0055974447,0.00008935527,0.0002928676,0.000007593245,0.0007110132,0.00021466655],"genre_scores_gemma":[0.89754647,0.000101219586,0.10223755,0.00006059089,0.0000058004202,2.9153432e-7,0.000001132917,0.000008025729,0.0000389454],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99651986,0.000060671868,0.0002968875,0.0015095192,0.0009191213,0.0006939297],"domain_scores_gemma":[0.99620587,0.00010362862,0.000511598,0.00081500795,0.0020640097,0.00029986366],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0013253269,0.00032213566,0.0005743398,0.0021193468,0.0025175142,0.000088077155,0.0034991188,0.00032577923,0.000004443685],"category_scores_gemma":[0.00037153444,0.0003589617,0.000048698217,0.010900546,0.028197898,0.0014164457,0.0019439794,0.0005283057,0.000002045355],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036568035,0.0005314654,0.053555638,0.000358653,0.00022786098,0.0014076785,0.011079368,0.0011397615,0.60881513,0.27451724,0.00034496488,0.047656577],"study_design_scores_gemma":[0.003932249,0.004323852,0.0044459235,0.0008758938,0.0002797251,0.0011756172,0.05647768,0.5156771,0.40196744,0.0048158737,0.0040370366,0.0019916345],"about_ca_topic_score_codex":0.00028257316,"about_ca_topic_score_gemma":0.000022021912,"teacher_disagreement_score":0.51453733,"about_ca_system_score_codex":0.00023111995,"about_ca_system_score_gemma":0.0010898547,"threshold_uncertainty_score":0.9998862},"labels":[],"label_agreement":null},{"id":"W3037824697","doi":"10.48550/arxiv.2006.13838","title":"Advances in Asynchronous Parallel and Distributed Optimization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Asynchronous communication; Computer science; Asynchrony (computer programming); Distributed computing; Context (archaeology); Stochastic optimization; Convergence (economics); Optimization problem; Mathematical optimization; Parallel computing; Algorithm; Computer network; Mathematics","score_opus":0.040121059172628905,"score_gpt":0.1889036506252838,"score_spread":0.1487825914526549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037824697","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00085917755,0.00021092719,0.99729055,0.00018265827,0.00014656379,0.00035569127,0.000017487588,0.00040689218,0.0005300759],"genre_scores_gemma":[0.87573093,0.0013726167,0.12273809,0.0000534438,0.00001634788,0.000002929707,0.00006129874,0.0000112829,0.000013057275],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985652,0.00007375711,0.00018869292,0.00089087733,0.00006721267,0.00021427931],"domain_scores_gemma":[0.99905103,0.000068401256,0.00019345839,0.0004821826,0.00008251012,0.00012240729],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00008736697,0.0002301726,0.0002657512,0.00021418436,0.00006368088,0.00009336126,0.0008227181,0.00017870762,0.000008241001],"category_scores_gemma":[0.00006774212,0.00028514705,0.00005223141,0.0006424545,0.00008393804,0.0005322299,0.0012029305,0.00030315696,0.0000043409577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010068518,0.000027001946,0.00092089875,0.000033094046,0.0000064479555,0.00006090636,0.0000847972,0.89017457,7.060265e-7,0.10828566,0.000021221438,0.00037465277],"study_design_scores_gemma":[0.00032200967,0.000044832675,0.0003470319,0.000064408254,0.000012584763,0.0000025862046,0.000020700849,0.9588437,0.000008127636,0.04002827,0.00003796681,0.00026779625],"about_ca_topic_score_codex":0.000023963034,"about_ca_topic_score_gemma":0.000008802845,"teacher_disagreement_score":0.87487173,"about_ca_system_score_codex":0.00015914152,"about_ca_system_score_gemma":0.00009109547,"threshold_uncertainty_score":0.99996006},"labels":[],"label_agreement":null},{"id":"W3037853175","doi":"","title":"Greed Meets Sparsity: Understanding and Improving Greedy Coordinate Descent for Sparse Optimization.","year":2020,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Coordinate descent; Greedy algorithm; Computer science; Mathematical optimization; Descent (aeronautics); Artificial intelligence; Algorithm; Mathematics; Engineering","score_opus":0.25451475130093054,"score_gpt":0.32385380956479615,"score_spread":0.0693390582638656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037853175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008022389,0.000011926556,0.9922473,0.006407197,0.00029448004,0.00033923596,0.00010850938,0.000114925475,0.00039622895],"genre_scores_gemma":[0.58456415,0.00007366334,0.41476735,0.00048579602,0.000044319604,0.000016042568,0.000022615597,0.00000899543,0.000017090402],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866873,0.000034210476,0.0003581752,0.00046007553,0.00027430552,0.00020447593],"domain_scores_gemma":[0.99891233,0.00029153543,0.00016561088,0.00012605329,0.00033938122,0.00016505917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020437484,0.00017436927,0.00017013759,0.0001325345,0.0001952646,0.00047596465,0.0003848333,0.000059036705,0.00003944391],"category_scores_gemma":[0.0005866662,0.00018293031,0.000023503262,0.0001490656,0.00014332678,0.00028265172,0.00016866151,0.00010781438,0.0000048745187],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057183293,0.000028204619,0.000024329916,0.000015537196,0.000017517392,0.0000062392396,0.0006282382,0.007087733,0.00017501632,0.96388507,0.000121215024,0.027953722],"study_design_scores_gemma":[0.00006405614,0.00024857328,0.000010395706,0.000029984616,0.000010093057,0.00000551979,0.0003389606,0.840924,0.00081091403,0.15735687,0.000032364107,0.00016825405],"about_ca_topic_score_codex":0.000019294012,"about_ca_topic_score_gemma":0.000012862308,"teacher_disagreement_score":0.83383626,"about_ca_system_score_codex":0.00006842691,"about_ca_system_score_gemma":0.00006018559,"threshold_uncertainty_score":0.74596816},"labels":[],"label_agreement":null},{"id":"W3080910898","doi":"10.48550/arxiv.2008.10898","title":"PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Simple (philosophy); Estimator; Probabilistic logic; Mathematical optimization; Applied mathematics; Mathematics; Computer science; Algorithm; Artificial intelligence; Statistics","score_opus":0.07104277370489873,"score_gpt":0.20591478191716436,"score_spread":0.13487200821226564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080910898","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003550673,0.000030353054,0.9933858,0.0002904219,0.0002672056,0.0015501424,0.000055088905,0.0007385836,0.00013175968],"genre_scores_gemma":[0.6014792,0.00003457444,0.39815816,0.000093974995,0.000041800104,0.000023351568,0.00007630202,0.000029922645,0.00006275185],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777204,0.000069011585,0.00029071575,0.0014087507,0.000103327555,0.00035618595],"domain_scores_gemma":[0.9981054,0.00021086296,0.00032502378,0.00078589725,0.00029198764,0.0002808473],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018670138,0.00038099173,0.0004113404,0.00023818103,0.00021518362,0.00021976094,0.0010958615,0.00024958287,0.000011948841],"category_scores_gemma":[0.00027695167,0.00045407895,0.00014815839,0.0004894558,0.00014977744,0.0003399786,0.0015156989,0.00029125216,0.0000048246243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024757435,0.000047301477,0.00007432296,0.00015066823,0.000035892568,0.000026406879,0.00017389607,0.80099165,0.0000054688667,0.19798337,0.00035561674,0.00013064845],"study_design_scores_gemma":[0.0005294637,0.00018568213,0.00003545922,0.000055901466,0.000087382636,0.0000064081705,0.000025230796,0.95000017,0.000051481857,0.048523985,0.000068542264,0.00043027176],"about_ca_topic_score_codex":0.000020829244,"about_ca_topic_score_gemma":0.0000020415382,"teacher_disagreement_score":0.5979285,"about_ca_system_score_codex":0.00019748377,"about_ca_system_score_gemma":0.00021080024,"threshold_uncertainty_score":0.9997911},"labels":[],"label_agreement":null},{"id":"W3082481594","doi":"10.14288/1.0394117","title":"Stochastic second-order optimization for over-parameterized machine learning models","year":2020,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Parameterized complexity; Computer science; Order (exchange); Artificial intelligence; Mathematical optimization; Machine learning; Mathematics; Algorithm; Economics","score_opus":0.020513611508402918,"score_gpt":0.1877184888105008,"score_spread":0.16720487730209788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082481594","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025380159,0.000048129863,0.97316074,0.00018157293,0.00007580517,0.00050870964,0.00007740619,0.0004066486,0.00016081135],"genre_scores_gemma":[0.62847346,0.0000108200575,0.37120515,0.00013021711,0.000011786464,0.0000026306323,0.00003542849,0.000014581165,0.00011591654],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988599,0.00004679781,0.00015989391,0.00049039477,0.00021760249,0.00022541398],"domain_scores_gemma":[0.9990446,0.00009978095,0.00019513782,0.0002225739,0.00029201907,0.00014586374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012159837,0.000061410006,0.00026628704,0.000056836645,0.00022738262,0.00017434696,0.0006357751,0.000088532965,0.00011626587],"category_scores_gemma":[0.00012640275,0.00021322581,0.000103453865,0.00051660446,0.00008666884,0.0007856727,0.00024092475,0.00012251831,0.0000025348852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032064483,0.000090110705,0.00008707944,0.00010919775,0.00005852552,0.000015288348,0.000864076,0.9044081,0.00018749305,0.00025029865,0.0009883574,0.09290943],"study_design_scores_gemma":[0.0012114022,0.0002261308,0.0021839465,0.000040897852,0.000020229008,0.000010291633,0.00007074224,0.99478906,0.0000016339118,0.0012002155,0.00003676544,0.00020869919],"about_ca_topic_score_codex":0.0019912906,"about_ca_topic_score_gemma":0.0015173472,"teacher_disagreement_score":0.6030933,"about_ca_system_score_codex":0.00004291507,"about_ca_system_score_gemma":0.00006743933,"threshold_uncertainty_score":0.86950964},"labels":[],"label_agreement":null},{"id":"W3091097978","doi":"10.1145/3452296.3472904","title":"Efficient sparse collective communication and its application to accelerate distributed deep learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"China Scholarship Council; King Abdullah University of Science and Technology","keywords":"Computer science; Focus (optics); Distributed computing; Scale (ratio); Artificial intelligence","score_opus":0.018227016392951257,"score_gpt":0.2550134356046615,"score_spread":0.23678641921171023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091097978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00885052,0.00010636891,0.9879081,0.0010203575,0.000022626353,0.00034299,0.000001530816,0.00033451227,0.0014129815],"genre_scores_gemma":[0.86094767,0.000014290798,0.1384776,0.00018942513,0.0000044821654,0.00011749786,0.000023443099,0.000005690063,0.00021993132],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991888,0.00008406676,0.00015015322,0.00030543067,0.00013668068,0.00013486766],"domain_scores_gemma":[0.99903065,0.00010800095,0.0000614565,0.0003451717,0.00037042514,0.000084296174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016074901,0.00008369364,0.0000945494,0.0000761513,0.0002245162,0.00013380687,0.00028499443,0.000036867583,0.000012627454],"category_scores_gemma":[0.00019536304,0.000087673856,0.000014791517,0.00094720325,0.000013191255,0.000082777115,0.0003838631,0.000087180735,0.000018920296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015495183,0.00023969158,0.00046662148,0.000016786225,0.000030559673,0.000004087422,0.0038908757,0.47130957,0.009848181,0.48954338,0.00049534463,0.024139421],"study_design_scores_gemma":[0.00013301437,0.00003221244,0.0014076676,0.000009835304,0.0000033910908,0.000007677604,0.00006992464,0.97937953,0.017561985,0.0009873527,0.00029853903,0.00010889004],"about_ca_topic_score_codex":0.0000060071566,"about_ca_topic_score_gemma":0.0000069241496,"teacher_disagreement_score":0.85209715,"about_ca_system_score_codex":0.000091559436,"about_ca_system_score_gemma":0.00004484086,"threshold_uncertainty_score":0.35752362},"labels":[],"label_agreement":null},{"id":"W3098536204","doi":"","title":"On the Optimal Weighted $\\ell_2$ Regularization in Overparameterized Linear Regression","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Combinatorics; Lambda; Star (game theory); Physics; Regularization (linguistics); Mathematics; Mathematical analysis; Quantum mechanics","score_opus":0.026903009874408267,"score_gpt":0.24682546761520707,"score_spread":0.2199224577407988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098536204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010406922,0.000028688595,0.98428,0.0030815687,0.00024000675,0.00061058,0.0000020908737,0.0005071372,0.0008429918],"genre_scores_gemma":[0.978441,0.0000032552384,0.019205922,0.002106553,0.0000504193,0.00009752904,0.000029770514,0.000010759663,0.00005477414],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984359,0.000112653106,0.0005978323,0.00020130469,0.00045753323,0.00019475612],"domain_scores_gemma":[0.9989407,0.00010362259,0.00043297518,0.00027218848,0.00018018037,0.00007029963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028517982,0.00016819093,0.00017667885,0.00017490532,0.00017635096,0.0005462496,0.0005685061,0.00009248213,0.000004874479],"category_scores_gemma":[0.00030618894,0.0001120351,0.00003507781,0.0010193964,0.000032760498,0.0025303978,0.00009622886,0.00020256934,0.00003142069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003051411,0.000115200455,0.00014970868,0.00067184295,0.000020838734,0.000010705942,0.021870583,0.47974095,0.0016614024,0.44055396,0.006067989,0.04883166],"study_design_scores_gemma":[0.00030434673,0.00010201452,0.000023962748,0.00017324342,0.0000018532635,0.000007605254,0.00008568927,0.9970643,0.0012473328,0.00039665741,0.00046327975,0.00012971231],"about_ca_topic_score_codex":0.0000046551854,"about_ca_topic_score_gemma":5.3832025e-8,"teacher_disagreement_score":0.9680341,"about_ca_system_score_codex":0.00005694096,"about_ca_system_score_gemma":0.00005249307,"threshold_uncertainty_score":0.5267498},"labels":[],"label_agreement":null},{"id":"W3102110737","doi":"10.48550/arxiv.2011.03351","title":"Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Affine transformation; Mathematics; Affine shape adaptation; Affine hull; Invariant (physics); Affine combination; Applied mathematics; Pure mathematics; Discrete mathematics; Affine space","score_opus":0.083074583290104,"score_gpt":0.20202475148785753,"score_spread":0.11895016819775353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102110737","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030400677,0.0000133709045,0.9660573,0.00020507195,0.00021959169,0.00032701794,0.00007674545,0.00039057128,0.0023096583],"genre_scores_gemma":[0.98338574,0.00003947272,0.016201722,0.0001283303,0.000018878438,0.0000014281638,0.0000685478,0.000015691288,0.00014018474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979126,0.00012832874,0.0003335937,0.0011729031,0.00019087899,0.0002616964],"domain_scores_gemma":[0.9974392,0.00018162755,0.00050438964,0.0014408259,0.0002474505,0.0001864873],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018767123,0.0003296826,0.000697116,0.001019716,0.00006740782,0.00006394847,0.002075883,0.00025472898,0.00012580743],"category_scores_gemma":[0.000098702236,0.00038327705,0.00037712042,0.0022552586,0.00011178944,0.00017381198,0.0015785024,0.0004454087,0.000023897004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027228767,0.00009073118,0.00070890685,0.000029446286,0.00073333236,0.000083354666,0.00020295354,0.6104158,0.000023993362,0.38728952,0.00028051753,0.00011417844],"study_design_scores_gemma":[0.0003024944,0.00014970542,0.002355427,0.00005372542,0.0006310923,5.00538e-7,0.000021751433,0.98392934,0.00035915404,0.011818771,0.000038452952,0.00033960186],"about_ca_topic_score_codex":0.00011912209,"about_ca_topic_score_gemma":0.000012540008,"teacher_disagreement_score":0.95298505,"about_ca_system_score_codex":0.00014993428,"about_ca_system_score_gemma":0.000174912,"threshold_uncertainty_score":0.9998619},"labels":[],"label_agreement":null},{"id":"W3103712156","doi":"10.48550/arxiv.2103.12243","title":"Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Variance reduction; Estimator; Sampling (signal processing); Mathematical optimization; Convergence (economics); Variance (accounting); Computer science; Importance sampling; Rate of convergence; Adaptive sampling; Mathematics; Algorithm; Key (lock); Statistics; Machine learning; Monte Carlo method","score_opus":0.09071579776244318,"score_gpt":0.20694646632688254,"score_spread":0.11623066856443937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103712156","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011193028,0.00006478715,0.98794687,0.000049321872,0.000058744557,0.00024648654,0.0000062492704,0.0002424874,0.00019200087],"genre_scores_gemma":[0.44367304,0.000032832224,0.55615115,0.00005647326,0.000012368742,0.0000016459418,0.00000838264,0.00001037225,0.000053761825],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888587,0.00003464277,0.00013932092,0.0006293858,0.00006591179,0.0002448422],"domain_scores_gemma":[0.9986042,0.0004545908,0.00014572343,0.0003555183,0.00033113977,0.0001088764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013207218,0.00015838126,0.000170736,0.00012675696,0.00025666275,0.0001190707,0.00026955694,0.00006482469,0.000006868799],"category_scores_gemma":[0.00016244367,0.00017556889,0.000042425138,0.0007029948,0.00006844606,0.00060512405,0.00015210715,0.00008078869,6.5269074e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036656165,0.00002752721,0.0020425555,0.000012765915,0.00002665956,0.000021158066,0.00011720466,0.7876565,0.00002642471,0.20954546,0.0000065030663,0.00048056824],"study_design_scores_gemma":[0.00057474495,0.00010247723,0.00023829321,0.000072946474,0.000033317152,0.000014366975,0.00021217857,0.99062437,0.00032273453,0.007526002,0.000039008868,0.0002395682],"about_ca_topic_score_codex":0.000010826653,"about_ca_topic_score_gemma":0.00001709215,"teacher_disagreement_score":0.43248,"about_ca_system_score_codex":0.00007837049,"about_ca_system_score_gemma":0.00011184071,"threshold_uncertainty_score":0.7159491},"labels":[],"label_agreement":null},{"id":"W3105596848","doi":"10.1007/s10107-022-01787-7","title":"Constrained stochastic blackbox optimization using a progressive barrier and probabilistic estimates","year":2022,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Polytechnique Montréal; Group for Research in Decision Analysis","funders":"","keywords":"Probabilistic logic; Mathematical optimization; Martingale (probability theory); Mathematics; Constraint (computer-aided design); Function (biology); Constrained optimization; Probability distribution; Convergence (economics); Computer science; Algorithm; Applied mathematics","score_opus":0.021589855361689163,"score_gpt":0.26737849543903996,"score_spread":0.2457886400773508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105596848","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016690216,0.00010146007,0.9959139,0.00014510272,0.00006694845,0.0013270151,0.0000038754724,0.0006643118,0.00010832444],"genre_scores_gemma":[0.2580793,1.9087648e-7,0.74139124,0.00004329291,0.000012608092,0.0004349166,0.0000053464414,0.000022164644,0.000010942012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812853,0.00008251204,0.00041616365,0.0004982738,0.00046248356,0.00041204775],"domain_scores_gemma":[0.9988158,0.000340604,0.00020138742,0.00036313824,0.000114649025,0.00016443098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047434357,0.00022722023,0.00028102685,0.00018337814,0.00052708824,0.00032252067,0.00043845113,0.000047049336,0.00013269857],"category_scores_gemma":[0.00081137137,0.00022034474,0.000052938816,0.00055404834,0.00027007915,0.00028609738,0.0006409451,0.00020108637,0.000002253316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011371393,0.00030314096,0.000020986616,0.00018030024,0.000040040315,0.00003576733,0.0021766345,0.63652635,0.00006134099,0.3479918,0.000010158859,0.012642108],"study_design_scores_gemma":[0.00024642315,0.0001740121,0.0000011816578,0.000057648303,0.00003381784,0.0003304735,0.00015263028,0.9401803,0.000026548372,0.058556896,0.0000086883365,0.00023137857],"about_ca_topic_score_codex":0.000001505539,"about_ca_topic_score_gemma":4.8060443e-8,"teacher_disagreement_score":0.30365396,"about_ca_system_score_codex":0.00011632853,"about_ca_system_score_gemma":0.00009081721,"threshold_uncertainty_score":0.8985397},"labels":[],"label_agreement":null},{"id":"W3106085430","doi":"","title":"Gradient Estimation with Stochastic Softmax Tricks","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Softmax function; Estimator; Gumbel distribution; Computer science; Latent variable; Algorithm; Artificial intelligence; Mathematics; Theoretical computer science; Machine learning; Artificial neural network; Statistics","score_opus":0.018544197203115984,"score_gpt":0.22380238714806924,"score_spread":0.20525818994495326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106085430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00072237453,0.000059189413,0.9957148,0.0010198333,0.0001998369,0.00055993034,0.0000026699036,0.0012217101,0.0004996634],"genre_scores_gemma":[0.94792354,5.0710554e-7,0.051122136,0.0007546582,0.000043210952,0.0001099352,0.000023350716,0.000010106348,0.000012532209],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984556,0.000031502346,0.0005293632,0.00021588018,0.00052557106,0.0002421084],"domain_scores_gemma":[0.99878424,0.0000388139,0.00045797435,0.00021754848,0.00033838485,0.00016302301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014282693,0.00019071613,0.0001955848,0.00019109437,0.00021861547,0.00088890345,0.00048690516,0.000060271566,0.0000021592807],"category_scores_gemma":[0.00013743095,0.00015421177,0.000029070552,0.00094032474,0.00003801444,0.004763487,0.000068066394,0.00013857555,0.00004499954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003530895,0.000025634788,0.000033936853,0.00043246502,0.000012750633,0.0000027751769,0.00875402,0.8223923,0.000025891508,0.020528778,0.0012110452,0.14654511],"study_design_scores_gemma":[0.00034143234,0.00020779335,0.000021060821,0.00008465518,0.000007577325,0.00006184882,0.00014131777,0.9984535,0.00009853656,0.0000950175,0.0002940281,0.00019323459],"about_ca_topic_score_codex":0.000008687055,"about_ca_topic_score_gemma":1.1900506e-7,"teacher_disagreement_score":0.9472012,"about_ca_system_score_codex":0.00006706872,"about_ca_system_score_gemma":0.00009524771,"threshold_uncertainty_score":0.85717165},"labels":[],"label_agreement":null},{"id":"W3110226276","doi":"10.3390/math11020480","title":"Neural Teleportation","year":2023,"lang":"en","type":"preprint","venue":"Mathematics","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Teleportation; Computer science; Artificial neural network; Representation (politics); Simple (philosophy); Maxima and minima; Function (biology); Process (computing); Theoretical computer science; Topology (electrical circuits); Artificial intelligence; Physics; Quantum entanglement; Mathematics; Quantum mechanics; Quantum; Quantum channel; Biology","score_opus":0.0691452604189421,"score_gpt":0.2978946641547034,"score_spread":0.2287494037357613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110226276","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000742318,0.000014788649,0.9944481,0.00047477323,0.00083418994,0.00038143006,0.000007032973,0.0021982729,0.00089904387],"genre_scores_gemma":[0.01932837,0.000009560913,0.97961354,0.00006789998,0.000061729064,0.00014499931,0.00003433572,0.00003867894,0.00070090353],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986828,0.000017295131,0.0004097345,0.0003537168,0.00035805823,0.00017841482],"domain_scores_gemma":[0.99840707,0.00012666475,0.00033690204,0.0009550274,0.00012329117,0.00005103975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025216016,0.00018551131,0.00022656743,0.00020304088,0.000047965543,0.00022639117,0.0009789433,0.00014975648,0.000008717387],"category_scores_gemma":[0.00025062592,0.00018116218,0.00008469875,0.0002451394,0.000022650554,0.00008392785,0.0009593306,0.00024209567,0.0001428474],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.96399e-7,0.00026865062,0.00011395564,0.0013261562,0.000096540585,0.00009075905,0.007382138,0.07871992,0.000064024774,0.8786724,0.024579266,0.008685153],"study_design_scores_gemma":[0.000026001684,0.000009872068,0.00003931182,0.000071579794,0.000007826488,0.000006309296,0.00001329245,0.68705577,0.00015839803,0.31244308,0.000029272001,0.00013931438],"about_ca_topic_score_codex":0.0000055959968,"about_ca_topic_score_gemma":0.0000011528326,"teacher_disagreement_score":0.6083358,"about_ca_system_score_codex":0.00004415309,"about_ca_system_score_gemma":0.000053801366,"threshold_uncertainty_score":0.7387579},"labels":[],"label_agreement":null},{"id":"W3110866490","doi":"10.1109/tsipn.2020.3044955","title":"Anytime Minibatch With Delayed Gradients","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Signal and Information Processing over Networks","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Science and Engineering Research Council; Huawei Technologies","keywords":"Asynchronous communication; Regret; Convergence (economics); Transmission (telecommunications); Range (aeronautics); Variable (mathematics); Convex optimization; Optimization problem","score_opus":0.009260081566282828,"score_gpt":0.20159326783426498,"score_spread":0.19233318626798215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110866490","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006980413,0.000025467849,0.9976397,0.00043140314,0.00007358665,0.0001918331,0.0000044932463,0.00038306575,0.00055236544],"genre_scores_gemma":[0.9597712,0.000021123651,0.037180964,0.002934964,0.000023267217,0.000033957545,0.0000056212366,0.000008156936,0.000020721549],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990473,0.000016491978,0.0002810287,0.0001905043,0.00026803202,0.00019667162],"domain_scores_gemma":[0.99942565,0.000032281256,0.00014192607,0.00011389228,0.00012680511,0.00015946406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000735498,0.00016236145,0.00013480958,0.00011409995,0.00026673512,0.00031624804,0.00021977117,0.00007442355,0.000027826356],"category_scores_gemma":[0.0000018119564,0.00013561302,0.000029661562,0.0006253967,0.000053144133,0.0036759505,0.0000033850079,0.00019691385,0.000009625692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026156323,0.000085724394,0.000031559248,0.000066476794,0.00005675028,0.000002813037,0.004196286,0.6286501,0.00002520019,0.0017128414,0.0011307499,0.36377993],"study_design_scores_gemma":[0.00048965734,0.00039369485,0.000046973928,0.000051072402,0.000015081169,0.0000131572015,0.00003480942,0.99731815,0.00082636235,0.00008754519,0.0005331147,0.00019037911],"about_ca_topic_score_codex":0.0000039508222,"about_ca_topic_score_gemma":4.114635e-7,"teacher_disagreement_score":0.96045876,"about_ca_system_score_codex":0.000022880218,"about_ca_system_score_gemma":0.00004677136,"threshold_uncertainty_score":0.55301386},"labels":[],"label_agreement":null},{"id":"W3111354771","doi":"10.1109/icc42927.2021.9500308","title":"Collaborative Coded Computation Offloading: An All-pay Auction Approach","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Ministry of Education","keywords":"Computer science; Computation; Computation offloading; Cloud computing; Enhanced Data Rates for GSM Evolution; Edge computing; Central processing unit; Edge device; Distributed computing; Operating system; Algorithm; Artificial intelligence","score_opus":0.03271318576506654,"score_gpt":0.29752402506021647,"score_spread":0.2648108392951499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111354771","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00063435937,0.000046581354,0.9909122,0.00047352177,0.0010909236,0.0009276623,0.000008634762,0.0016412102,0.0042648977],"genre_scores_gemma":[0.15178634,0.000018464494,0.8468231,0.00023006012,0.00008423373,0.0001827836,0.00062905677,0.000026461135,0.00021949026],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99717015,0.00028158474,0.0004944332,0.0012301158,0.0005413468,0.00028234313],"domain_scores_gemma":[0.99748164,0.00006769824,0.00039164975,0.000903435,0.0010077179,0.000147831],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039318268,0.00037071944,0.00041816066,0.00034068478,0.00013136244,0.0009728902,0.0009840527,0.00035990064,0.000017146871],"category_scores_gemma":[0.00007702184,0.000335993,0.000092809954,0.0008039159,0.000066588436,0.0007458163,0.0010078952,0.0004821296,0.0000060035136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018205814,0.00092422304,0.000057460195,0.00019031753,0.00029710963,0.000017852624,0.013149542,0.8338235,0.000644573,0.13322954,0.0066481675,0.010999524],"study_design_scores_gemma":[0.00019302584,0.000084467174,0.000104180675,0.00004199896,0.000025133573,0.000015643678,0.00032452084,0.98849183,0.0027991498,0.007419027,0.00007070128,0.00043032592],"about_ca_topic_score_codex":0.000068334484,"about_ca_topic_score_gemma":0.0000084837575,"teacher_disagreement_score":0.15466835,"about_ca_system_score_codex":0.00024006041,"about_ca_system_score_gemma":0.00042711943,"threshold_uncertainty_score":0.9999092},"labels":[],"label_agreement":null},{"id":"W3113785905","doi":"10.48550/arxiv.2012.15477","title":"Particle Dual Averaging: Optimization of Mean Field Neural Networks with Global Convergence Rate Analysis","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Convergence (economics); Artificial neural network; Rate of convergence; Mathematical optimization; Nonlinear system; Computer science; Empirical risk minimization; Inner loop; Applied mathematics; Mathematics; Artificial intelligence; Physics; Key (lock)","score_opus":0.04547622419307678,"score_gpt":0.19135388741438952,"score_spread":0.14587766322131274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113785905","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02146819,0.000016965725,0.9775102,0.00019168232,0.00016395333,0.00022572654,0.000008064431,0.00029437634,0.000120802404],"genre_scores_gemma":[0.9600177,0.000030511661,0.03973205,0.0001433694,0.000018384868,0.0000011655524,0.000020587635,0.000007946282,0.00002831803],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984524,0.00013447503,0.00024282419,0.0008155479,0.00011338278,0.00024133203],"domain_scores_gemma":[0.9983782,0.00009129499,0.0003722996,0.0007426106,0.00025990346,0.00015569675],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013363856,0.00023595721,0.0003634034,0.00012310159,0.000074878284,0.000076021075,0.0008991478,0.00013994882,0.00003501731],"category_scores_gemma":[0.000038206184,0.0002566934,0.0001626565,0.0023417869,0.00008576888,0.0002794245,0.0008639697,0.00022806058,0.0000015372665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043918466,0.000030369847,0.012119582,0.000013629655,0.00024686975,0.00006168452,0.00011957956,0.94857436,0.0000013943975,0.038694378,0.000023074152,0.0000711285],"study_design_scores_gemma":[0.000234352,0.00011846389,0.0006495407,0.000020336563,0.00035561825,0.0000017236489,0.00002326494,0.99657357,0.00013168638,0.0016405692,9.783198e-7,0.00024987746],"about_ca_topic_score_codex":0.00015005143,"about_ca_topic_score_gemma":0.000024596218,"teacher_disagreement_score":0.93854946,"about_ca_system_score_codex":0.00008938578,"about_ca_system_score_gemma":0.00008015096,"threshold_uncertainty_score":0.99998856},"labels":[],"label_agreement":null},{"id":"W3123224975","doi":"","title":"When does preconditioning help or hurt generalization","year":2021,"lang":"en","type":"article","venue":"Institutional Repositories DataBase (IRDB)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generalization; Reproducing kernel Hilbert space; Computer science; Matching (statistics); Kernel (algebra); Population; Variance (accounting); Algorithm; Applied mathematics; Hilbert space; Mathematical optimization; Mathematics; Statistics; Discrete mathematics","score_opus":0.02050156646347252,"score_gpt":0.26148438255871165,"score_spread":0.24098281609523914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123224975","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021940628,0.00015407686,0.9901135,0.00073258125,0.0033461668,0.00019794432,0.0001490659,0.0005962402,0.002516366],"genre_scores_gemma":[0.10848686,0.00008695352,0.8838874,0.0007730479,0.0011671223,0.00020822603,0.0021118037,0.000026941503,0.003251664],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979143,0.000086518805,0.0004504022,0.0006549064,0.00062136614,0.0002725048],"domain_scores_gemma":[0.9980841,0.00013466222,0.000171921,0.00082386524,0.0006487568,0.00013666868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019223183,0.00020777831,0.00018516608,0.00014263461,0.000686076,0.00053688535,0.0005379861,0.00008739935,0.00016802807],"category_scores_gemma":[0.0007589659,0.00017096112,0.000065381035,0.00058366195,0.00014955997,0.0023619563,0.00044810944,0.00013803247,0.000026005995],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019519624,0.00013806178,0.0010757162,0.000050531078,0.000053779044,0.0002708975,0.00035088038,0.0037943644,0.0042125266,0.9798188,0.009311201,0.0009036722],"study_design_scores_gemma":[0.0021017122,0.00028469332,0.0035917528,0.0012957177,0.00013777275,0.0040581007,0.00025101367,0.10432636,0.62812406,0.05475965,0.19877873,0.002290414],"about_ca_topic_score_codex":0.00007523216,"about_ca_topic_score_gemma":0.000054471217,"teacher_disagreement_score":0.9250592,"about_ca_system_score_codex":0.00021423501,"about_ca_system_score_gemma":0.00082281674,"threshold_uncertainty_score":0.69715923},"labels":[],"label_agreement":null},{"id":"W3129546243","doi":"10.1007/978-3-030-67661-2_3","title":"Adaptive Momentum Coefficient for Neural Network Optimization","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Momentum (technical analysis); Artificial neural network; Computer science; Convergence (economics); Rate of convergence; Mathematical optimization; Term (time); Algorithm; Mathematics; Artificial intelligence; Key (lock); Physics","score_opus":0.020382289840261098,"score_gpt":0.24335972441667206,"score_spread":0.22297743457641095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129546243","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014428919,0.0004532817,0.99377096,0.0006179416,0.0028034956,0.0011244364,0.000009805446,0.000353402,0.0008652462],"genre_scores_gemma":[0.0052604675,0.000027791652,0.9925783,0.001203419,0.00046409934,0.00007131538,0.00003169964,0.00004788946,0.00031498805],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99596196,0.00003604453,0.00060577516,0.001719414,0.0008840361,0.00079275103],"domain_scores_gemma":[0.9969373,0.00058407045,0.0004036364,0.0011922647,0.0007068795,0.00017587494],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006882623,0.00054576487,0.0005517593,0.00060832984,0.00035987518,0.0005793509,0.0023360911,0.0002983389,0.00002153428],"category_scores_gemma":[0.0001368638,0.0005503041,0.00017634977,0.0009923079,0.00042057136,0.0004471046,0.0011780624,0.00044162737,0.0000033361775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005473233,0.000021253523,0.0000018596751,0.000012201408,0.000008403665,0.000012869027,0.000142219,0.86732316,0.0000034603383,0.080004305,0.000076519216,0.05238827],"study_design_scores_gemma":[0.0002427536,0.00029276343,0.000002456443,0.0002499013,0.000011042826,0.00002921453,1.7037466e-7,0.95222676,0.00025384966,0.045918368,0.00024405579,0.0005286512],"about_ca_topic_score_codex":0.0000035605522,"about_ca_topic_score_gemma":0.0000068792206,"teacher_disagreement_score":0.084903605,"about_ca_system_score_codex":0.00042695316,"about_ca_system_score_gemma":0.00048786475,"threshold_uncertainty_score":0.9996948},"labels":[],"label_agreement":null},{"id":"W3133055021","doi":"10.48550/arxiv.1905.12938","title":"Stochastic Sign Descent Methods: New Algorithms and Better Theory","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Sign (mathematics); Algorithm; Computer science; Descent (aeronautics); Mathematics; Physics","score_opus":0.0735754354328065,"score_gpt":0.2261299429988945,"score_spread":0.15255450756608802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133055021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009902094,0.00016088808,0.99626327,0.00012444085,0.0007111687,0.0006482998,0.0000063035186,0.0005256029,0.0005698442],"genre_scores_gemma":[0.39134336,0.00006195602,0.60637313,0.0003362281,0.00008661597,0.00000245091,0.000009559843,0.00003772462,0.0017489503],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975905,0.00034743134,0.00023219566,0.0013346149,0.00011428616,0.0003809929],"domain_scores_gemma":[0.99752015,0.00048130404,0.00026928895,0.0013320417,0.00013832476,0.0002588743],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058741914,0.00040014856,0.00041356534,0.00040082753,0.00010397679,0.00017928162,0.0015815025,0.00031581163,0.000037252037],"category_scores_gemma":[0.00010970211,0.00044401607,0.00014430517,0.00042516994,0.0001319956,0.00032371428,0.0024882103,0.0005379509,0.000043108084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033646033,0.000081801125,0.00015924632,0.00007886583,0.00017374323,0.00009278608,0.00070462597,0.36751688,0.000033027223,0.59742606,0.0007117712,0.032987535],"study_design_scores_gemma":[0.0003254197,0.00006294662,0.00011271327,0.000101286205,0.00007485374,0.000013089458,0.000025327372,0.68562394,0.00011792882,0.31306243,0.00005146904,0.00042861278],"about_ca_topic_score_codex":0.000039009647,"about_ca_topic_score_gemma":8.886301e-7,"teacher_disagreement_score":0.39035314,"about_ca_system_score_codex":0.00018058138,"about_ca_system_score_gemma":0.00023037415,"threshold_uncertainty_score":0.99980116},"labels":[],"label_agreement":null},{"id":"W3161297530","doi":"10.1109/jsait.2021.3079856","title":"Asynchronous Delayed Optimization With Time-Varying Minibatches","year":2021,"lang":"en","type":"article","venue":"IEEE Journal on Selected Areas in Information Theory","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Huawei Technologies","keywords":"Asynchronous communication; Regret; Computer science; Variable (mathematics); Mathematical optimization; Process (computing); Mathematics","score_opus":0.006218310357429007,"score_gpt":0.21096753306189617,"score_spread":0.20474922270446716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161297530","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043043755,0.00002863608,0.99001116,0.00022337574,0.0002477939,0.00017191056,0.0000028587485,0.00024559762,0.0047643124],"genre_scores_gemma":[0.3581567,0.00008661558,0.639573,0.0017853269,0.00012396637,0.00004512704,0.00007605751,0.00003191156,0.00012133243],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982017,0.00024317001,0.00060479215,0.00017021573,0.0004814793,0.00029861895],"domain_scores_gemma":[0.99789226,0.00029946602,0.0004357223,0.00031267767,0.00094060204,0.00011927079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006273478,0.00019746528,0.00020667791,0.0005962812,0.00020846575,0.00044198014,0.00043766882,0.000106013715,0.00012023917],"category_scores_gemma":[0.00040646695,0.00017326426,0.000043821467,0.0015688359,0.000037526926,0.0026691288,0.000037572292,0.00039100312,0.000053346295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015944884,0.00009983509,0.000052431868,0.00000927477,0.000051040868,0.000039669478,0.0019008465,0.96250886,0.00010392316,0.023793358,0.00048478023,0.010796561],"study_design_scores_gemma":[0.001651795,0.0005340225,0.00021249782,0.0002977465,0.000020197285,0.0016357539,0.00015760266,0.9698656,0.01631114,0.0086649945,0.00016578297,0.00048284855],"about_ca_topic_score_codex":9.905759e-7,"about_ca_topic_score_gemma":5.778083e-7,"teacher_disagreement_score":0.35385233,"about_ca_system_score_codex":0.00026686545,"about_ca_system_score_gemma":0.00046074906,"threshold_uncertainty_score":0.7065511},"labels":[],"label_agreement":null},{"id":"W3166400281","doi":"10.48550/arxiv.2106.03696","title":"Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hessian matrix; Mathematics; Applied mathematics; Momentum (technical analysis); Hyperparameter; Quadratic equation; Stochastic optimization; Mathematical optimization; Algorithm","score_opus":0.0666013736102855,"score_gpt":0.23427141865928927,"score_spread":0.1676700450490038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166400281","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057201018,0.00003676145,0.9915036,0.000094477204,0.0005629704,0.00047436636,0.000033964505,0.0003628321,0.0012109005],"genre_scores_gemma":[0.7410585,0.000026814536,0.2583985,0.00004994079,0.000013863034,0.0000039680694,0.000046329536,0.000025647916,0.00037637737],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745554,0.0003257438,0.00039193407,0.0012358497,0.00019306738,0.00039787707],"domain_scores_gemma":[0.9968123,0.00029526133,0.0004883029,0.0018514534,0.00038315853,0.00016953047],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049595087,0.00039712325,0.00059648516,0.0005569864,0.00010575041,0.0000999361,0.0019096227,0.00033147744,0.000025051533],"category_scores_gemma":[0.00008946428,0.000478412,0.00028282753,0.0009849333,0.00010774431,0.000361996,0.0021460275,0.0005560146,0.000004848351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007283796,0.00014013641,0.000007755261,0.000049723727,0.0000472897,0.000019807729,0.00031325375,0.59307504,0.00000627518,0.4061633,0.000015448548,0.00015465326],"study_design_scores_gemma":[0.00023786258,0.00008345903,0.000012938896,0.00018615148,0.00006329104,0.0000023376147,0.00018147631,0.80472463,0.00015268617,0.19403541,7.0854725e-7,0.00031902868],"about_ca_topic_score_codex":0.000039375427,"about_ca_topic_score_gemma":0.00002465053,"teacher_disagreement_score":0.73533845,"about_ca_system_score_codex":0.0004139653,"about_ca_system_score_gemma":0.00025844752,"threshold_uncertainty_score":0.99976677},"labels":[],"label_agreement":null},{"id":"W3167021948","doi":"10.48550/arxiv.2106.03795","title":"Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Canada Research Chairs; University of Toronto","funders":"","keywords":"Pruning; Artificial neural network; Generalization; Compressibility; Computer science; Limit (mathematics); Compression (physics); Node (physics); Computation; Algorithm; Mathematics; Applied mathematics; Mathematical optimization; Artificial intelligence; Mathematical analysis; Physics","score_opus":0.05854675172088644,"score_gpt":0.19732979370042453,"score_spread":0.13878304197953809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167021948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3456908,0.00018110445,0.6534768,0.00001725975,0.00017078026,0.00025151068,0.000003339121,0.000099512334,0.000108947774],"genre_scores_gemma":[0.9827753,0.00014223471,0.016989958,0.000036644436,0.00001033339,0.0000013292847,0.000010513838,0.000008965416,0.00002474862],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998153,0.00021440451,0.00031499317,0.0009796809,0.00008556831,0.0002523701],"domain_scores_gemma":[0.9980819,0.00027183557,0.0003008524,0.0010644292,0.00017300916,0.00010797474],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000290514,0.0002349894,0.0004864072,0.00034908947,0.00004234841,0.000091968264,0.0009612984,0.0002569211,0.000010156978],"category_scores_gemma":[0.00011545544,0.00028542877,0.00011794707,0.0010093738,0.00016872709,0.00030470864,0.0022066492,0.00048320577,2.8129423e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043336564,0.00014098723,0.014180787,0.00007568812,0.000028931709,0.000090872425,0.00022831286,0.95639175,0.0000135974105,0.02833296,0.000023427297,0.00044935328],"study_design_scores_gemma":[0.0004663169,0.000040290946,0.006427227,0.00011000754,0.000017086402,0.0000030743438,0.00003543912,0.98402786,0.00014514568,0.008500104,0.0000012822411,0.00022618964],"about_ca_topic_score_codex":0.00028258865,"about_ca_topic_score_gemma":0.00004076531,"teacher_disagreement_score":0.6370845,"about_ca_system_score_codex":0.00012072205,"about_ca_system_score_gemma":0.00008677121,"threshold_uncertainty_score":0.99995977},"labels":[],"label_agreement":null},{"id":"W3167047574","doi":"","title":"Distributed Second Order Methods with Fast Rates and Compressed Communication","year":2021,"lang":"en","type":"article","venue":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Sublinear function; Hessian matrix; Newton's method; Rate of convergence; Computer science; Mathematical optimization; Regularization (linguistics); Convergence (economics); Local convergence; Algorithm; Quadratic equation; Newton's method in optimization; Iterative method; Applied mathematics; Mathematics; Artificial intelligence","score_opus":0.007462794298355328,"score_gpt":0.2176864445366946,"score_spread":0.21022365023833928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167047574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75067717,0.0005475224,0.24364917,0.003204514,0.00007700035,0.00025906606,0.0000077276,0.0005362466,0.0010416167],"genre_scores_gemma":[0.73825437,0.00018584834,0.26145414,0.000014988394,0.0000015685875,2.1361582e-7,0.0000012730907,0.0000044342883,0.0000831899],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977785,0.000060026632,0.00020997615,0.0009894307,0.0005224528,0.00043965835],"domain_scores_gemma":[0.99552333,0.00012907678,0.0004291381,0.0009400304,0.0028416351,0.000136769],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0010424774,0.00021694067,0.00041253588,0.0019028842,0.0026696406,0.00011266255,0.0021169807,0.0002699956,0.0000036884678],"category_scores_gemma":[0.0002880474,0.00024690712,0.000022616547,0.008278625,0.027505636,0.001177137,0.0022757081,0.00035757656,3.3135737e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067510155,0.00031953238,0.06018245,0.00020529672,0.0001460573,0.00026918342,0.0057842103,0.00011784664,0.63202524,0.24134475,0.00013602036,0.05940189],"study_design_scores_gemma":[0.003755258,0.001385968,0.021955347,0.0014088392,0.00027838384,0.0021547757,0.08901095,0.098099425,0.75815463,0.017255422,0.00474642,0.0017945997],"about_ca_topic_score_codex":0.00015050029,"about_ca_topic_score_gemma":0.00006197952,"teacher_disagreement_score":0.22408932,"about_ca_system_score_codex":0.00013499577,"about_ca_system_score_gemma":0.0007776941,"threshold_uncertainty_score":0.99999833},"labels":[],"label_agreement":null},{"id":"W3167824561","doi":"","title":"Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Mathematical optimization; Variance reduction; Computer science; Variance (accounting); Noise (video); Optimization problem; Baseline (sea); Focus (optics); Stochastic optimization; Curvature; Mathematics; Artificial intelligence; Image (mathematics)","score_opus":0.04983852392367744,"score_gpt":0.3330668308248156,"score_spread":0.28322830690113815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167824561","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036907106,0.000017709293,0.97306365,0.006929736,0.00035190652,0.00009306573,0.000008929947,0.00012792376,0.019038009],"genre_scores_gemma":[0.9618095,0.00006483805,0.03717952,0.0001790445,0.00015725881,0.000011334576,0.000045296725,0.000012147906,0.0005410436],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986513,0.00016137635,0.00027529706,0.0003272945,0.00043681174,0.00014791511],"domain_scores_gemma":[0.9988071,0.00016971029,0.0002544784,0.00031028368,0.0004128359,0.000045616518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028107845,0.00015098808,0.00013741068,0.00026973448,0.00017205272,0.00019556115,0.0005790874,0.00004993794,0.00028701432],"category_scores_gemma":[0.0007012482,0.00011749795,0.000097675846,0.0005473949,0.00005776765,0.00026432573,0.000120744524,0.00029367759,0.000006773283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014128308,0.000028919967,0.00011740963,0.0000014557453,0.00002446983,0.0000022302638,0.0002033629,0.4933438,0.00023465266,0.5047289,0.000028162327,0.001272508],"study_design_scores_gemma":[0.00023460713,0.00017864471,0.00015387556,0.000069951355,0.0000041459307,0.00003964693,0.00008357574,0.97424996,0.00079545524,0.024042573,0.00003585607,0.00011170831],"about_ca_topic_score_codex":0.00006600242,"about_ca_topic_score_gemma":0.0000013302503,"teacher_disagreement_score":0.96144044,"about_ca_system_score_codex":0.00026902568,"about_ca_system_score_gemma":0.00025702393,"threshold_uncertainty_score":0.47914273},"labels":[],"label_agreement":null},{"id":"W3168222560","doi":"10.48550/arxiv.2106.04881","title":"Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Ergodic theory; Generalization; Algorithm; Stochastic gradient descent; Dynamical systems theory; Mathematics; Computer science; Hessian matrix; Fractal; Artificial neural network; Bounded function; Invariant measure; Hyperparameter; Mathematical optimization; Applied mathematics; Artificial intelligence","score_opus":0.04562625423809228,"score_gpt":0.17653525846866253,"score_spread":0.13090900423057025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168222560","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08023774,0.00017671088,0.91875345,0.000027181162,0.00026917044,0.00031166218,0.000013065402,0.00018662923,0.00002440056],"genre_scores_gemma":[0.89206564,0.00006838699,0.10769396,0.000024279616,0.00002613648,0.0000012117497,0.00005046847,0.000016023208,0.00005386846],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864095,0.00008938135,0.0002303177,0.00074892584,0.00011891266,0.00017153312],"domain_scores_gemma":[0.9985145,0.000024640258,0.00033203643,0.0006129052,0.00043293674,0.000083013445],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007857647,0.00024625353,0.0002959433,0.00028299307,0.000090753885,0.00013039746,0.0006031702,0.0002595268,0.0000166728],"category_scores_gemma":[0.00007126689,0.00027371076,0.000068891124,0.00051483104,0.00011989041,0.00045713104,0.0010695508,0.00022676802,3.0812836e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005722275,0.000029409728,0.00008101762,0.00007567367,0.0000383185,0.000010022557,0.000388607,0.9797417,0.0002156529,0.019206269,0.0000073447513,0.00020026493],"study_design_scores_gemma":[0.00019794605,0.000034263685,0.00006378626,0.00016342013,0.00004887175,0.0000080464115,0.000052337207,0.994044,0.0019269068,0.0031986602,5.6232653e-7,0.00026119442],"about_ca_topic_score_codex":0.0000583377,"about_ca_topic_score_gemma":0.000004699138,"teacher_disagreement_score":0.8118279,"about_ca_system_score_codex":0.000086477456,"about_ca_system_score_gemma":0.0001608455,"threshold_uncertainty_score":0.9999715},"labels":[],"label_agreement":null},{"id":"W3168341135","doi":"","title":"Stochastic Sign Descent Methods: New Algorithms and Better Theory","year":2021,"lang":"en","type":"article","venue":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Stochastic gradient descent; Bounded function; Sign (mathematics); Node (physics); Gradient descent; Estimator; Algorithm; Key (lock); Mathematical optimization; Mathematics; Artificial intelligence; Artificial neural network","score_opus":0.009527541927325422,"score_gpt":0.21619264017169068,"score_spread":0.20666509824436527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168341135","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26166505,0.0008750538,0.7322752,0.0032563175,0.00023808025,0.0002821777,0.0000026164303,0.0006261836,0.00077934837],"genre_scores_gemma":[0.66275,0.0001730023,0.33685803,0.000038541082,0.0000072430107,1.7194783e-7,3.0636664e-7,0.0000067342235,0.0001659572],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9969342,0.00006757766,0.00026286044,0.0013726915,0.0007337021,0.0006289831],"domain_scores_gemma":[0.9966198,0.0001628902,0.00041693714,0.00087666506,0.0016784411,0.0002452176],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0017261556,0.00027448073,0.00048274288,0.0029331772,0.002345832,0.000111835965,0.0023045852,0.0003626186,0.0000041605767],"category_scores_gemma":[0.0005668167,0.00032984422,0.000045291374,0.0070715523,0.023735749,0.0011620139,0.0026872817,0.0004236345,9.7499e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000371062,0.00018562692,0.0072238296,0.000094352574,0.00009754374,0.0004202812,0.004418673,0.00006308774,0.3065019,0.2913598,0.00009193686,0.38950586],"study_design_scores_gemma":[0.0053452426,0.002362691,0.009136676,0.0023110972,0.0006547554,0.0062411167,0.092393436,0.10367234,0.5693077,0.20154233,0.0036112785,0.0034213706],"about_ca_topic_score_codex":0.00013836747,"about_ca_topic_score_gemma":0.000012274137,"teacher_disagreement_score":0.401085,"about_ca_system_score_codex":0.00020763966,"about_ca_system_score_gemma":0.0012470022,"threshold_uncertainty_score":0.99991536},"labels":[],"label_agreement":null},{"id":"W3169728738","doi":"10.1609/aaai.v36i7.20701","title":"Fast and Robust Online Inference with Stochastic Gradient Descent via Random Scaling","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Economic and Social Research Council; National Research Foundation of Korea; Seoul National University; National Research Foundation; Compute Canada; Ministry of Education; McMaster University","keywords":"Stochastic gradient descent; Resampling; Inference; Computer science; Leverage (statistics); Gradient descent; Mathematics; Algorithm; Artificial intelligence; Artificial neural network","score_opus":0.05517963036051056,"score_gpt":0.2658407778660295,"score_spread":0.21066114750551895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169728738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053518906,0.000025870091,0.9437989,0.0012778385,0.00021430677,0.00070033583,0.000010788555,0.00016690651,0.00028614613],"genre_scores_gemma":[0.96636087,0.000011360315,0.0332676,0.0001672818,0.000023566134,0.000109635694,0.0000015991546,0.000017062823,0.000040999854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766153,0.000032759355,0.00053399324,0.00063705177,0.0007529074,0.0003817559],"domain_scores_gemma":[0.9983855,0.00016692621,0.0004597007,0.0003262706,0.0005336916,0.00012790857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004844858,0.0002801089,0.00031918194,0.00023935638,0.0005172051,0.00020855715,0.0016700901,0.000043917367,0.00004283382],"category_scores_gemma":[0.00027882593,0.0002117124,0.00006704214,0.00095045625,0.0003541992,0.00030150588,0.00094403053,0.00043104234,0.0000033094236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031876232,0.0005484012,0.00021519203,0.00004781359,0.000034089553,0.0000017045884,0.0033911886,0.11385759,0.004021682,0.80402255,0.000032242042,0.0735088],"study_design_scores_gemma":[0.00012950123,0.00061331753,0.00011717618,0.00019268139,0.000024093457,0.00003659646,0.00085427787,0.9244642,0.020721922,0.05252336,0.0000051437364,0.0003177179],"about_ca_topic_score_codex":0.000042352454,"about_ca_topic_score_gemma":0.000008768707,"teacher_disagreement_score":0.912842,"about_ca_system_score_codex":0.00009809906,"about_ca_system_score_gemma":0.000105585605,"threshold_uncertainty_score":0.8633381},"labels":[],"label_agreement":null},{"id":"W3171596153","doi":"10.1109/jsac.2021.3087272","title":"LOSP: Overlap Synchronization Parallel With Local Compensation for Fast Distributed Training","year":2021,"lang":"en","type":"article","venue":"IEEE Journal on Selected Areas in Communications","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; Research Grants Council, University Grants Committee; China Postdoctoral Science Foundation; Impact Fund; Science, Technology and Innovation Commission of Shenzhen Municipality; National Natural Science Foundation of China","keywords":"Computer science; Scalability; Synchronization (alternating current); Computation; Speedup; Distributed computing; Overhead (engineering); Convergence (economics); Stochastic gradient descent; Rate of convergence; Compensation (psychology); Data synchronization; Mathematical optimization; Parallel computing; Algorithm; Key (lock); Computer network; Artificial intelligence; Artificial neural network","score_opus":0.03917666790837083,"score_gpt":0.2856775653390298,"score_spread":0.246500897430659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171596153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010796088,0.000087917695,0.99522555,0.0026319134,0.00012251908,0.0003316126,0.000020483818,0.00017892157,0.0003214924],"genre_scores_gemma":[0.6904431,0.00008722878,0.30896914,0.00018321478,0.000031112148,0.00006973521,0.00018191748,0.00001627365,0.00001825231],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983737,0.00026355547,0.00048551091,0.00026679496,0.00032017403,0.00029028903],"domain_scores_gemma":[0.996714,0.0006320817,0.0003110323,0.0009732004,0.0012578346,0.00011186813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031124818,0.00017302299,0.00023404193,0.0002478045,0.00046623335,0.00025902476,0.0010840526,0.000089931054,0.000007930944],"category_scores_gemma":[0.0003214473,0.00016786261,0.000052901327,0.0016908557,0.000098528864,0.000447622,0.000084619285,0.0004569,0.0000033023193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016545651,0.0015292075,0.002775835,0.00003165619,0.0002115296,0.000041305073,0.0036433304,0.60345227,0.0006457759,0.32545653,0.002215389,0.059831712],"study_design_scores_gemma":[0.001540602,0.00031531337,0.0033384198,0.00030634273,0.000024163339,0.00039101823,0.0002974968,0.98542947,0.0007112382,0.0065449993,0.0007999973,0.00030092502],"about_ca_topic_score_codex":0.00000458572,"about_ca_topic_score_gemma":0.000086336455,"teacher_disagreement_score":0.6893635,"about_ca_system_score_codex":0.00040673238,"about_ca_system_score_gemma":0.00057202694,"threshold_uncertainty_score":0.6845239},"labels":[],"label_agreement":null},{"id":"W3171665446","doi":"","title":"PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization","year":2021,"lang":"en","type":"article","venue":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Combinatorics; Omega; Upper and lower bounds; Estimator; Mathematics; Simple (philosophy); Convergence (economics); Matching (statistics); Rate of convergence; Discrete mathematics; Algorithm; Computer science; Physics; Mathematical analysis; Statistics","score_opus":0.0073489573888596334,"score_gpt":0.19621523438755087,"score_spread":0.18886627699869124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171665446","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59701467,0.00026711597,0.3986148,0.0024908565,0.00016163451,0.0005087483,0.000008237695,0.0005598901,0.00037408428],"genre_scores_gemma":[0.7386668,0.00012157397,0.26113257,0.000014078319,0.0000042499723,6.609977e-7,0.0000011021672,0.0000061729934,0.0000528202],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99731123,0.000023408424,0.0002601289,0.0012514925,0.0005932669,0.00056047196],"domain_scores_gemma":[0.9960494,0.00010666627,0.00042793574,0.00069864845,0.0025398154,0.00017754873],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0009459597,0.00023823096,0.00043129604,0.0022371332,0.0027597493,0.00010932513,0.0016608085,0.00030442455,0.0000020841635],"category_scores_gemma":[0.000666117,0.00029414264,0.000041989846,0.005676117,0.019514833,0.0011026799,0.0017022867,0.00024753893,3.0998643e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012365814,0.0006415374,0.033398535,0.0006615322,0.00016467842,0.0004905561,0.0068285367,0.0049207015,0.2840554,0.61145115,0.0002895365,0.05697416],"study_design_scores_gemma":[0.0027868354,0.0015225196,0.001998478,0.00068348256,0.00024025766,0.0012362907,0.028059876,0.84628236,0.09818829,0.016389132,0.001362511,0.0012499808],"about_ca_topic_score_codex":0.00008559857,"about_ca_topic_score_gemma":0.000015105211,"teacher_disagreement_score":0.84136164,"about_ca_system_score_codex":0.0002154155,"about_ca_system_score_gemma":0.0010367326,"threshold_uncertainty_score":0.99995106},"labels":[],"label_agreement":null},{"id":"W3175559358","doi":"10.1609/aaai.v35i1.16108","title":"Asynchronous Stochastic Gradient Descent for Extreme-Scale Recommender Systems","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Asynchronous communication; Stochastic gradient descent; Normalization (sociology); Terabyte; Recommender system; Scale (ratio); Machine learning; Data mining; Artificial neural network","score_opus":0.11355235592447331,"score_gpt":0.29060971179869205,"score_spread":0.17705735587421872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175559358","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040818825,0.000061960316,0.98997605,0.0021145004,0.0010826669,0.00088128325,0.000009980072,0.00018209346,0.0016095641],"genre_scores_gemma":[0.94700396,0.00002134054,0.05232482,0.00017001558,0.000071686605,0.00021843062,0.0000018016599,0.000021071097,0.00016686722],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978012,0.000022388016,0.00066559995,0.00066026795,0.00041294534,0.00043763526],"domain_scores_gemma":[0.9973258,0.00017115328,0.00042590572,0.00044200438,0.0015112244,0.00012395474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004506637,0.00026090108,0.00032738378,0.00013722651,0.00024909148,0.00034786898,0.001507938,0.000100192345,0.000027345852],"category_scores_gemma":[0.0005261689,0.00021571513,0.00016146398,0.0006587485,0.00015978063,0.00028082132,0.00036923133,0.00019883459,0.000017544946],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026908929,0.00024921037,0.000025713132,0.000067889974,0.000020631227,2.5616086e-7,0.0007950195,0.0017566994,0.006427264,0.9709616,0.00045284495,0.01921598],"study_design_scores_gemma":[0.000061253835,0.00028829518,0.000028534227,0.00043788485,0.00002773675,0.000019433317,0.000774284,0.5965352,0.26351857,0.137863,0.00010139744,0.00034440096],"about_ca_topic_score_codex":0.000016745169,"about_ca_topic_score_gemma":0.000006287926,"teacher_disagreement_score":0.94292206,"about_ca_system_score_codex":0.00014089006,"about_ca_system_score_gemma":0.00017312229,"threshold_uncertainty_score":0.8796607},"labels":[],"label_agreement":null},{"id":"W3189787503","doi":"10.1109/jsait.2021.3103494","title":"Compressing Gradients by Exploiting Temporal Correlation in Momentum-SGD","year":2021,"lang":"en","type":"article","venue":"IEEE Journal on Selected Areas in Information Theory","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Huawei Technologies","keywords":"Bottleneck; Computer science; Computation; Rate of convergence; Convergence (economics); Algorithm; Momentum (technical analysis); Mathematical optimization; Information bottleneck method; Compression (physics); Exploit; Norm (philosophy); Mathematics; Artificial intelligence; Telecommunications","score_opus":0.009529290614629546,"score_gpt":0.23181319729259658,"score_spread":0.22228390667796705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3189787503","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058906097,0.000046424717,0.93798405,0.00017416068,0.0006981412,0.00016470173,0.000003606049,0.00014734169,0.0018754893],"genre_scores_gemma":[0.9829719,0.00003171093,0.01615382,0.0006655114,0.000037416437,0.000021799924,0.000052150623,0.000010818593,0.000054850145],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997796,0.00034513813,0.0008812094,0.00016460152,0.00049241795,0.00032063134],"domain_scores_gemma":[0.9983969,0.00033162514,0.00053187273,0.00022134025,0.00041834998,0.000099912584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009373337,0.00017230783,0.00020055419,0.00077133905,0.00017425901,0.00040022892,0.00039561352,0.00010080653,0.000024294208],"category_scores_gemma":[0.0006619653,0.00017727856,0.00004371789,0.001487435,0.00002869854,0.0032630635,0.00004965105,0.0005661909,0.00001958586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044563392,0.0013282791,0.025735917,0.000108795146,0.00011673702,0.00020529993,0.028804801,0.41863927,0.0033837466,0.36028305,0.016831888,0.14411658],"study_design_scores_gemma":[0.0034905074,0.0002735909,0.0052255597,0.0010975507,0.00000990922,0.00048624864,0.0011141984,0.895459,0.021816295,0.069066495,0.001188775,0.00077184377],"about_ca_topic_score_codex":0.0000034671457,"about_ca_topic_score_gemma":0.0000012405876,"teacher_disagreement_score":0.9240658,"about_ca_system_score_codex":0.00040486295,"about_ca_system_score_gemma":0.00015675137,"threshold_uncertainty_score":0.722921},"labels":[],"label_agreement":null},{"id":"W3196726140","doi":"10.1109/isit45174.2021.9518254","title":"Differentially Quantized Gradient Descent","year":2021,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Russian Academy of Sciences; Natural Sciences and Engineering Research Council of Canada; Princeton University; Jet Propulsion Laboratory; Division of Mathematical Sciences; Moscow Institute of Physics and Technology; King Abdullah University of Science and Technology; University of Ottawa; Indian Institute of Science; University of Tehran; National Aeronautics and Space Administration; California Institute of Technology; Amgen; National Science Foundation","keywords":"Gradient descent; Stochastic gradient descent; Quantization (signal processing); Convergence (economics); Descent (aeronautics); Computer science; Algorithm; Mathematics; Discrete mathematics; Theoretical computer science; Combinatorics; Artificial intelligence; Physics","score_opus":0.01959072728710984,"score_gpt":0.24043840112537723,"score_spread":0.2208476738382674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196726140","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00256527,0.000052474294,0.9901201,0.00092058023,0.0004346019,0.00010052331,4.832936e-7,0.00067514525,0.005130791],"genre_scores_gemma":[0.41028887,0.00002149983,0.5880877,0.00047286955,0.000019264995,0.000016989294,0.0000048141083,0.000007737406,0.0010802882],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896896,0.000043527347,0.0001915272,0.00034085824,0.00024058533,0.00021453788],"domain_scores_gemma":[0.9991148,0.000043954817,0.00004422504,0.00054392795,0.00015878853,0.0000942992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000801963,0.00010374841,0.00012478538,0.00007206167,0.00007020156,0.00015458651,0.0004485155,0.000034816643,0.00015003311],"category_scores_gemma":[0.00006865621,0.00009245633,0.00006864666,0.00037160364,0.000020911131,0.00015445836,0.0002768303,0.000058184327,0.00004385854],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014916762,0.000120491124,0.00019269207,0.0000044584244,0.000012055107,0.00002385269,0.00011846617,0.0000484271,0.0021335909,0.9901888,0.0015697846,0.0055859103],"study_design_scores_gemma":[0.0020549404,0.0002474148,0.00888725,0.00009229683,0.00003355111,0.00023002077,0.00007533779,0.5144119,0.37103143,0.09633248,0.005471998,0.0011313803],"about_ca_topic_score_codex":0.0000057393036,"about_ca_topic_score_gemma":0.0000055424493,"teacher_disagreement_score":0.8938563,"about_ca_system_score_codex":0.00003438873,"about_ca_system_score_gemma":0.000064963264,"threshold_uncertainty_score":0.37702596},"labels":[],"label_agreement":null},{"id":"W3196800830","doi":"10.1007/s10915-021-01628-3","title":"Stochastic Gradient Descent with Polyak’s Learning Rate","year":2021,"lang":"en","type":"article","venue":"Journal of Scientific Computing","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Air Force Office of Scientific Research; Fundação para a Ciência e a Tecnologia; Institut de Valorisation des Données","keywords":"Stochastic gradient descent; Subgradient method; Mathematics; Constant (computer programming); Rate of convergence; Generalization; Gradient descent; Regular polygon; Descent (aeronautics); Applied mathematics; Convex function; Mathematical optimization; Convergence (economics); Artificial neural network; Mathematical analysis; Computer science; Artificial intelligence; Geometry","score_opus":0.014663824421353389,"score_gpt":0.23378888387716334,"score_spread":0.21912505945580996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196800830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08944787,0.00020835301,0.9081093,0.0004125206,0.0014932221,0.00007944539,2.7599677e-7,0.00010339283,0.00014558702],"genre_scores_gemma":[0.79907185,0.0000015882114,0.20056345,0.000055274682,0.000082453385,5.283486e-7,0.0000010270377,0.000011105507,0.00021272001],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977054,0.00016818731,0.0006029527,0.0004101444,0.00071707176,0.00039623718],"domain_scores_gemma":[0.9972362,0.0002425058,0.0007175788,0.0003643127,0.0012271437,0.00021227695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018048255,0.00016879837,0.0002808562,0.00042447186,0.00050856726,0.00089030573,0.0007614308,0.000036881273,0.000013862285],"category_scores_gemma":[0.00041906757,0.0001398229,0.00011493884,0.0015217568,0.00013506715,0.00046428465,0.00032714856,0.0003958033,0.000007046808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004928375,0.0005686044,0.0020050083,0.000068802474,0.00021095951,0.00093549147,0.0066715884,0.85143507,0.014636172,0.04176807,0.001825749,0.07982521],"study_design_scores_gemma":[0.0010076265,0.00045433562,0.0022435265,0.00072781777,0.000053130854,0.0024514885,0.00039511023,0.97921157,0.01030387,0.0019991267,0.0007245473,0.00042786254],"about_ca_topic_score_codex":0.0000014639314,"about_ca_topic_score_gemma":0.0000013534793,"teacher_disagreement_score":0.709624,"about_ca_system_score_codex":0.000136906,"about_ca_system_score_gemma":0.00041726176,"threshold_uncertainty_score":0.85852385},"labels":[],"label_agreement":null},{"id":"W3208237615","doi":"10.48550/arxiv.2110.15412","title":"Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Stochastic gradient descent; Bounded function; Convergence (economics); Adaptive stepsize; Regular polygon; Mathematical optimization; Descent (aeronautics); Mathematics; Convex function; Stochastic optimization; Computer science; Gradient descent; Applied mathematics; Artificial intelligence; Numerical analysis; Mathematical analysis; Artificial neural network; Physics; Geometry","score_opus":0.056519009742940295,"score_gpt":0.19631081937671793,"score_spread":0.13979180963377763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208237615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032368727,0.0001697729,0.9653866,0.00013690964,0.0006126386,0.00083819503,0.00004076261,0.00037431522,0.0000720754],"genre_scores_gemma":[0.9682632,0.000043308828,0.031134916,0.00013778427,0.000016146416,0.000012040303,0.00002687619,0.000032319018,0.00033339084],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99625576,0.00036808674,0.00044407175,0.0020040704,0.0003023667,0.0006256484],"domain_scores_gemma":[0.99596095,0.00052120443,0.0005920087,0.0020483648,0.0005323946,0.000345058],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004132972,0.0006306052,0.0007558206,0.0007353335,0.0004286541,0.00033161894,0.0024569682,0.00035739152,0.00009516333],"category_scores_gemma":[0.00017494147,0.00062045647,0.00039918156,0.0029285385,0.00042895254,0.00048628903,0.0030708613,0.00075792195,0.000021169573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025423788,0.00068882294,0.0020447366,0.0001732374,0.005440278,0.0007685298,0.005137863,0.78039765,0.0003069553,0.20363377,0.00008871978,0.0010652159],"study_design_scores_gemma":[0.00040589203,0.00008622175,0.006139267,0.00012387124,0.0012555864,0.000020579735,0.00027283913,0.9819127,0.000048334114,0.009072826,0.0000014099792,0.000660525],"about_ca_topic_score_codex":0.0011919108,"about_ca_topic_score_gemma":0.00030396154,"teacher_disagreement_score":0.9358945,"about_ca_system_score_codex":0.00028392122,"about_ca_system_score_gemma":0.0003353845,"threshold_uncertainty_score":0.99962467},"labels":[],"label_agreement":null},{"id":"W3208592040","doi":"","title":"Towards Noise-adaptive, Problem-adaptive Stochastic Gradient Descent","year":2021,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Noise (video); Stochastic gradient descent; Gradient descent; Computer science; Mathematical optimization; Control theory (sociology); Mathematics; Artificial intelligence; Artificial neural network","score_opus":0.02751191910310913,"score_gpt":0.23170088008440143,"score_spread":0.2041889609812923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208592040","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025954773,0.0028068079,0.94642055,0.012597431,0.001300866,0.002214757,0.00010823419,0.0010166676,0.030939223],"genre_scores_gemma":[0.31464788,0.000520767,0.6754797,0.00022553289,0.00006047063,0.0005404603,0.0003277233,0.0001375322,0.008059921],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9824492,0.009290804,0.0017999437,0.0031935296,0.0017772149,0.0014893428],"domain_scores_gemma":[0.98014194,0.0019839269,0.001685812,0.0050802184,0.010187417,0.00092071516],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0070921043,0.0013559958,0.0013004619,0.0006269049,0.0010456986,0.0020508203,0.0047701653,0.000821688,0.0003513018],"category_scores_gemma":[0.002374003,0.001586239,0.00077642995,0.0020647934,0.0011032302,0.0008989882,0.006379426,0.0018456939,0.00012916973],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032733587,0.0019897586,0.00007785486,0.00018391653,0.0002811288,0.000060924707,0.02244645,0.010296381,0.00050644466,0.9104847,0.0008207708,0.052818954],"study_design_scores_gemma":[0.0014967957,0.0000119013475,0.0027448363,0.010844966,0.0003042916,0.00025307114,0.0006201462,0.92024815,0.024151165,0.034271237,0.0025704375,0.0024829886],"about_ca_topic_score_codex":0.003590677,"about_ca_topic_score_gemma":0.0010356249,"teacher_disagreement_score":0.9099518,"about_ca_system_score_codex":0.0012258892,"about_ca_system_score_gemma":0.002164293,"threshold_uncertainty_score":0.9999191},"labels":[],"label_agreement":null},{"id":"W3209316047","doi":"10.5281/zenodo.20422944","title":"JuliaNLSolvers/Optim.jl: v1.2.1","year":2020,"lang":"en","type":"article","venue":"Open MIND","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.07505916285750394,"score_gpt":0.2992024059540006,"score_spread":0.22414324309649666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209316047","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044078063,0.000016313374,0.94418436,0.0048580016,0.00012293307,0.00033583806,0.0000035874148,0.00003366346,0.050004497],"genre_scores_gemma":[0.07753406,0.000003028278,0.9204251,0.0011869373,0.000045655277,0.000017726954,0.000004673421,0.000010273538,0.0007725471],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989959,0.00002480281,0.0001756103,0.00042675884,0.00018742992,0.0001895247],"domain_scores_gemma":[0.9992687,0.0000362999,0.00007425603,0.0003931477,0.000057802015,0.00016978476],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012394323,0.00010978037,0.00013738072,0.00004017541,0.00007580955,0.0004202089,0.00201594,0.00004487943,0.0009122101],"category_scores_gemma":[0.00008444212,0.00010850565,0.00003653222,0.0004276694,0.000030654384,0.0006427773,0.0008413864,0.0000883358,0.0012974982],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060484505,0.00028817228,0.0005550607,0.000020079919,0.000101300015,0.00018919156,0.014882816,0.0054556946,0.0026997032,0.06867345,0.1256294,0.78144467],"study_design_scores_gemma":[0.0012303976,0.00060123944,0.00019072206,0.00005175484,0.000022853654,0.000029727935,0.00015875793,0.61117697,0.03791522,0.0022558437,0.3455241,0.0008423916],"about_ca_topic_score_codex":0.0000069059224,"about_ca_topic_score_gemma":8.4292736e-7,"teacher_disagreement_score":0.7806023,"about_ca_system_score_codex":0.000021324875,"about_ca_system_score_gemma":0.000068345624,"threshold_uncertainty_score":0.9994801},"labels":[],"label_agreement":null},{"id":"W3211346803","doi":"10.1109/sips52927.2021.00018","title":"Fault-Tolerance of Binarized and Stochastic Computing-based Neural Networks","year":2021,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Stochastic computing; Computer science; Artificial neural network; Fault tolerance; Stochastic neural network; Computation; XNOR gate; MNIST database; Algorithm; Theoretical computer science; Time delay neural network; Logic gate; Artificial intelligence; Distributed computing","score_opus":0.011109639600231811,"score_gpt":0.2355711605956789,"score_spread":0.22446152099544708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211346803","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007959591,0.00016845384,0.99074525,0.00036997185,0.00019203246,0.00012811043,8.691086e-7,0.0002804505,0.00015529359],"genre_scores_gemma":[0.7538122,0.0000011596895,0.24580318,0.00032503146,0.000012751965,0.0000035064463,0.0000024022256,0.0000058678093,0.000033899876],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900794,0.00005119865,0.0002503759,0.00032508295,0.00017482637,0.00019056998],"domain_scores_gemma":[0.99901146,0.0002300798,0.00010504997,0.00037786664,0.00020418296,0.00007133727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012069032,0.00011765851,0.00020451132,0.00007704221,0.00006489131,0.0000660681,0.00030245204,0.000050429502,0.000012425213],"category_scores_gemma":[0.00008474688,0.000113143265,0.000041350148,0.00050702464,0.00007740689,0.0001154929,0.00018795319,0.000088710905,6.041803e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006057146,0.000053324566,0.00014759699,0.0000125437755,0.0000062871163,0.000007579564,0.00008295155,0.97007304,0.00019244832,0.025035426,0.00011842671,0.004264298],"study_design_scores_gemma":[0.0004526207,0.00006318688,0.00039233887,0.000029373145,0.000004591287,0.000016135109,0.0000075157704,0.9971156,0.0011159831,0.00068155664,0.0000047717367,0.00011629199],"about_ca_topic_score_codex":0.000007853884,"about_ca_topic_score_gemma":0.0000016181723,"teacher_disagreement_score":0.7458526,"about_ca_system_score_codex":0.000011232815,"about_ca_system_score_gemma":0.000044805194,"threshold_uncertainty_score":0.46138483},"labels":[],"label_agreement":null},{"id":"W3211638756","doi":"","title":"An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Iterated function; Stochastic gradient descent; Constant (computer programming); Applied mathematics; Mathematical optimization; Asymptotic distribution; Convex function; Regular polygon; Rate of convergence; Convex optimization; Markov chain; Computer science; Artificial intelligence; Statistics; Estimator; Mathematical analysis; Artificial neural network","score_opus":0.04739091611543879,"score_gpt":0.19769854296706418,"score_spread":0.1503076268516254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211638756","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38770717,0.0000106202315,0.6113925,0.000059344282,0.00002122603,0.000078145684,0.0000034236214,0.000033035954,0.0006945181],"genre_scores_gemma":[0.99291956,0.0000274596,0.006852761,0.00013630645,0.0000031323787,4.024703e-7,0.0000031643,0.0000030541175,0.00005413854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989475,0.0002092816,0.00017142309,0.00042056973,0.00009167587,0.00015952745],"domain_scores_gemma":[0.9984895,0.00039906122,0.00012744051,0.0007656689,0.00015430675,0.00006403073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004223526,0.000103059356,0.00023161653,0.00023987968,0.0000650937,0.000051901647,0.0006125867,0.000053044812,0.00002229184],"category_scores_gemma":[0.000106321364,0.00009577333,0.00007329674,0.0028989378,0.00014846852,0.00035554467,0.00015273211,0.00009247686,9.846832e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002126696,0.0002839939,0.17845207,0.000021861695,0.00021997734,0.0003258733,0.00164472,0.07999638,0.00020859632,0.7384459,0.000037272162,0.00034212138],"study_design_scores_gemma":[0.00030135378,0.000062406,0.064476974,0.00001263149,0.0001526756,0.0000050382155,0.0005586792,0.9314675,0.00038834586,0.002438949,0.000009238666,0.00012625205],"about_ca_topic_score_codex":0.00015079044,"about_ca_topic_score_gemma":0.00014561015,"teacher_disagreement_score":0.85147107,"about_ca_system_score_codex":0.00004034443,"about_ca_system_score_gemma":0.0000756023,"threshold_uncertainty_score":0.39055228},"labels":[],"label_agreement":null},{"id":"W3212182603","doi":"","title":"Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks.","year":2021,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Pruning; Artificial neural network; Computer science; Generalization; Compressibility; Limit (mathematics); Compression (physics); Node (physics); Computation; Mathematics; Algorithm; Mathematical optimization; Applied mathematics; Artificial intelligence; Mathematical analysis; Physics","score_opus":0.012085120512579824,"score_gpt":0.22604195174296698,"score_spread":0.21395683123038717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212182603","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09488213,0.000976786,0.8995663,0.0018177582,0.00006867569,0.00019050705,0.000003856576,0.00013631769,0.0023576536],"genre_scores_gemma":[0.7796637,0.00011465576,0.21995972,0.00006724554,0.0000025957302,0.000014011658,0.000015872405,0.000007684781,0.00015450192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964541,0.00212554,0.00043800022,0.0005044258,0.00024867957,0.00022924265],"domain_scores_gemma":[0.99585384,0.0015607836,0.0002242833,0.001273454,0.0009849925,0.000102637285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023243586,0.00013827065,0.00026634333,0.00015524658,0.000094570314,0.00016761968,0.00068549486,0.00008267616,0.000021509892],"category_scores_gemma":[0.0016527211,0.00015061926,0.00006341671,0.0010961267,0.00017284851,0.00029002005,0.0006453624,0.00018326868,8.440202e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038407175,0.0016667751,0.037939828,0.00013490199,0.00004909778,0.000024369758,0.009492728,0.0049085054,0.0053680837,0.83621466,0.0005109567,0.1036517],"study_design_scores_gemma":[0.0006206428,7.06136e-7,0.015295944,0.00023092947,0.000005121452,0.000014268852,0.000032632623,0.9342936,0.043740183,0.0054733655,0.00012259444,0.00016997832],"about_ca_topic_score_codex":0.00024174518,"about_ca_topic_score_gemma":0.00024469336,"teacher_disagreement_score":0.9293851,"about_ca_system_score_codex":0.000043350818,"about_ca_system_score_gemma":0.0000787589,"threshold_uncertainty_score":0.61420757},"labels":[],"label_agreement":null},{"id":"W3214140707","doi":"","title":"On the Role of Optimization in Double Descent: A Least Squares Study","year":2021,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"DeepMind; Engineering and Physical Sciences Research Council; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Overfitting; Gradient descent; Moore–Penrose pseudoinverse; Least-squares function approximation; Covariance matrix; Covariance; Mathematics; Generalization; Mathematical optimization; Applied mathematics; Computer science; Matrix (chemical analysis); Artificial neural network; Algorithm; Inverse; Artificial intelligence; Statistics; Mathematical analysis","score_opus":0.01247180139124885,"score_gpt":0.21845088290943301,"score_spread":0.20597908151818417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214140707","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04210219,0.00015967888,0.93790925,0.002875679,0.000051498577,0.0004624011,0.0000022777278,0.00015028557,0.016286716],"genre_scores_gemma":[0.906777,0.000026471362,0.0926412,0.00005694226,0.0000026900746,0.0000620743,0.000013460868,0.000012576682,0.00040756314],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966065,0.002014836,0.00036951384,0.00042334583,0.00038623158,0.00019955063],"domain_scores_gemma":[0.996081,0.0009977533,0.00021568891,0.001454516,0.0011928722,0.000058157344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022977865,0.00014003151,0.00017157049,0.00017442457,0.00016958122,0.00019654761,0.0010643979,0.00005397854,0.00006649529],"category_scores_gemma":[0.0009196106,0.00012469282,0.000061897284,0.0011740567,0.00008169172,0.00020990308,0.00042551794,0.00016380401,0.000006627119],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010330968,0.0014189903,0.0032640079,0.000008146055,0.000015541127,0.000003426942,0.009389168,0.010670854,0.00059639016,0.96762496,0.000053778895,0.006944422],"study_design_scores_gemma":[0.001383906,0.000004177803,0.0033162658,0.0005810441,0.000013778256,0.000009938698,0.0010991069,0.80116683,0.17602478,0.015835078,0.00025028732,0.00031479355],"about_ca_topic_score_codex":0.00023181151,"about_ca_topic_score_gemma":0.0003235747,"teacher_disagreement_score":0.95178986,"about_ca_system_score_codex":0.000058996673,"about_ca_system_score_gemma":0.00012517907,"threshold_uncertainty_score":0.5084825},"labels":[],"label_agreement":null},{"id":"W3214193129","doi":"10.1088/1742-5468/ac98a8","title":"Particle dual averaging: optimization of mean field neural network with global convergence rate analysis*","year":2022,"lang":"en","type":"article","venue":"Journal of Statistical Mechanics Theory and Experiment","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Artificial neural network; Convergence (economics); Rate of convergence; Mathematical optimization; Nonlinear system; Empirical risk minimization; Computer science; Inner loop; Applied mathematics; Mathematics; Artificial intelligence; Physics; Key (lock)","score_opus":0.010515986847428218,"score_gpt":0.25863466603083723,"score_spread":0.24811867918340902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214193129","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00491876,0.00015096906,0.99445957,0.00016121467,0.00018411658,0.00008539127,0.00000782643,0.000016896045,0.000015280759],"genre_scores_gemma":[0.72648346,0.000009164872,0.27333143,0.00015049173,0.000012517314,0.0000059619606,0.0000012372105,0.0000030118554,0.0000027158494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986211,0.00034931808,0.0003856686,0.00015500566,0.00032960926,0.00015931355],"domain_scores_gemma":[0.9988768,0.00042920184,0.0003094816,0.00015241827,0.00012259386,0.000109503024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010568888,0.000095287134,0.00023630526,0.00005364585,0.00013200076,0.00003700433,0.00022303243,0.000017769162,0.00015162173],"category_scores_gemma":[0.0000913815,0.00007912115,0.00004478219,0.0004902388,0.000031078896,0.00014429836,0.00017542724,0.0001091427,1.08642084e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002273579,0.000060335748,0.00004730955,0.0000024868548,0.00009017604,0.00001956994,0.00037121974,0.36007398,0.000064866406,0.638592,0.00003275212,0.0004179339],"study_design_scores_gemma":[0.0003367034,0.0017266622,0.000020739191,0.000007872843,0.000107162654,0.000059718885,0.00027636858,0.9040448,0.0017226993,0.09159782,0.000007743043,0.00009169732],"about_ca_topic_score_codex":0.0000030666665,"about_ca_topic_score_gemma":2.72648e-7,"teacher_disagreement_score":0.7215647,"about_ca_system_score_codex":0.000047526395,"about_ca_system_score_gemma":0.000041373623,"threshold_uncertainty_score":0.3226467},"labels":[],"label_agreement":null},{"id":"W4200632679","doi":"10.1609/aaai.v36i4.20301","title":"Sample Average Approximation for Stochastic Optimization with Dependent Data: Performance Guarantees and Tractability","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Huawei Technologies (Canada); University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Estimator; Stochastic approximation; Stochastic optimization; Stochastic gradient descent; Bounded function; Iterated function; Mathematics; Applied mathematics; Mathematical optimization; Monotone polygon; Asymptotically optimal algorithm; Consistency (knowledge bases); Computer science; Discrete mathematics; Artificial neural network; Mathematical analysis; Artificial intelligence; Statistics","score_opus":0.07742442528774132,"score_gpt":0.2772157989378486,"score_spread":0.19979137365010727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200632679","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024068458,0.000007929089,0.9738654,0.00064664206,0.00011827106,0.0010266434,0.00004874394,0.00009805857,0.00011986758],"genre_scores_gemma":[0.87759066,0.000006752118,0.12210488,0.00004965268,0.000013908552,0.00020182061,0.000009346708,0.00000979494,0.000013160226],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983625,0.000017413653,0.00037881493,0.00055619754,0.00047503982,0.00021003214],"domain_scores_gemma":[0.9985565,0.00020342028,0.0003712272,0.0004075329,0.00041934702,0.00004198607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073747337,0.00016246548,0.00018259314,0.00011674307,0.0004581527,0.00017439963,0.001579994,0.00003212114,0.000023798642],"category_scores_gemma":[0.0004500675,0.00012794763,0.0000265384,0.00042897314,0.00015110268,0.0007189955,0.0006280406,0.00017505515,5.1952094e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027029403,0.00027200097,0.00016698624,0.000108075226,0.000018125931,7.238988e-8,0.0018651446,0.34141114,0.0010824832,0.6209396,0.000022040464,0.033844013],"study_design_scores_gemma":[0.000050495688,0.00043212852,0.000044454748,0.000043988803,0.000012699427,0.00000754753,0.00027552183,0.95772874,0.01550137,0.025750993,0.000004024157,0.00014800775],"about_ca_topic_score_codex":0.000017299106,"about_ca_topic_score_gemma":0.0000023013572,"teacher_disagreement_score":0.85352224,"about_ca_system_score_codex":0.000060130867,"about_ca_system_score_gemma":0.000082003404,"threshold_uncertainty_score":0.5217553},"labels":[],"label_agreement":null},{"id":"W4205273441","doi":"10.1109/jiot.2021.3138855","title":"Distributed Decoding for Coded Distributed Computing","year":2021,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Decoding methods; Computer science; Coding (social sciences); List decoding; Node (physics); Linear network coding; Sequential decoding; Task (project management); Distributed computing; Algorithm; Theoretical computer science; Computer network; Mathematics; Concatenated error correction code","score_opus":0.02429888583788382,"score_gpt":0.2794336994600285,"score_spread":0.2551348136221447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205273441","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009321744,0.00007249659,0.9883955,0.0005937914,0.001247911,0.00011477793,0.000022399694,0.0001548529,0.00007648754],"genre_scores_gemma":[0.5463327,0.000005471636,0.45335907,0.00015962677,0.00006860041,0.0000025673326,0.0000206161,0.000010351224,0.000041002764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983981,0.000061883125,0.000639539,0.00027244617,0.00031476142,0.0003132355],"domain_scores_gemma":[0.99788177,0.00032642105,0.0005670662,0.00026305043,0.0008316095,0.00013009945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005825337,0.0001553705,0.00029167766,0.00012428188,0.000121735065,0.00033425246,0.000941529,0.0000777986,0.000016465116],"category_scores_gemma":[0.0006799007,0.00015330368,0.00019466177,0.00033064466,0.00004664218,0.0005346181,0.00020051748,0.0002665746,0.0000017328273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042410922,0.0019773024,0.0057985517,0.00068697846,0.0019731743,0.0009225243,0.022150718,0.066398755,0.10751035,0.42948234,0.21518113,0.14749405],"study_design_scores_gemma":[0.000612343,0.00011743667,0.00006496984,0.00028069929,0.000019795467,0.0006631789,0.000051928495,0.8422372,0.14564992,0.009690403,0.00043002274,0.00018209484],"about_ca_topic_score_codex":0.0000058320816,"about_ca_topic_score_gemma":4.987827e-7,"teacher_disagreement_score":0.77583843,"about_ca_system_score_codex":0.00012644073,"about_ca_system_score_gemma":0.00010537478,"threshold_uncertainty_score":0.62515426},"labels":[],"label_agreement":null},{"id":"W4205510022","doi":"10.1109/lcomm.2021.3140100","title":"On Allocation of Systematic Blocks in Coded Distributed Computing","year":2022,"lang":"en","type":"article","venue":"IEEE Communications Letters","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Decoding methods; Computer science; List decoding; Sequential decoding; Computation; Reduction (mathematics); Encoding (memory); Task (project management); Multiplication (music); Algorithm; Separable space; Parallel computing; Block code; Mathematics; Concatenated error correction code; Artificial intelligence","score_opus":0.03326909376298774,"score_gpt":0.27195373687974683,"score_spread":0.23868464311675908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205510022","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017344357,0.00005032398,0.97717613,0.0043910197,0.00012730154,0.00059959537,0.000012219488,0.00017485699,0.00012418818],"genre_scores_gemma":[0.9431976,0.0000035925775,0.055830866,0.0007201457,0.0000025949253,0.00019410673,0.000039543345,0.0000073980927,0.0000041345907],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984402,0.00043283866,0.0005078311,0.00018783455,0.00029016408,0.00014113041],"domain_scores_gemma":[0.9967876,0.0006846825,0.00032140696,0.0021129574,0.00006732878,0.000026019883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060968957,0.00009585219,0.00020541986,0.0003318537,0.00023395517,0.000031773056,0.0026082178,0.000019284402,0.0000041938692],"category_scores_gemma":[0.00012954528,0.00010950662,0.00004546075,0.0010196484,0.0000690737,0.00009786098,0.00051602436,0.00022365066,0.000002269017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011104516,0.00079715287,0.0004122248,0.0006384014,0.000052433166,0.0000038993903,0.0044872565,0.6869911,0.009599941,0.29272798,0.0038248403,0.00045367292],"study_design_scores_gemma":[0.00031312255,0.00006525848,0.00030622978,0.00047665546,0.000009807684,0.000009668838,0.00011639578,0.99616593,0.0011611145,0.0011968674,0.000018364615,0.00016057208],"about_ca_topic_score_codex":0.00003687035,"about_ca_topic_score_gemma":0.0000038958137,"teacher_disagreement_score":0.92585325,"about_ca_system_score_codex":0.00021591228,"about_ca_system_score_gemma":0.000032538013,"threshold_uncertainty_score":0.4846761},"labels":[],"label_agreement":null},{"id":"W4205547947","doi":"10.1561/2400000036","title":"Acceleration Methods","year":2021,"lang":"en","type":"article","venue":"Foundations and Trends® in Optimization","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Agence Nationale de la Recherche","keywords":"Acceleration; Convergence (economics); Momentum (technical analysis); Computer science; Mathematical optimization; Mathematical proof; Quadratic equation; Range (aeronautics); Chebyshev filter; Key (lock); Set (abstract data type); Cover (algebra); Quadratic programming; Mathematics; Applied mathematics; Physics; Mechanical engineering; Engineering","score_opus":0.03732282273889075,"score_gpt":0.3584317859963982,"score_spread":0.32110896325750743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205547947","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009201198,0.00008483176,0.9920828,0.0012113787,0.00019092282,0.0000645433,0.0000014491183,0.00016784685,0.0061042216],"genre_scores_gemma":[0.038863197,0.00007902395,0.96024764,0.00011835378,0.000018910936,0.000041934712,0.0001522939,0.000007939031,0.00047069523],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999067,0.00011574595,0.00024979503,0.00032694577,0.0001091171,0.00013141157],"domain_scores_gemma":[0.99934554,0.00008473843,0.00007496371,0.00028295192,0.0001682136,0.00004361569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002203123,0.00009695134,0.00010890475,0.00041595584,0.00014567877,0.00031641737,0.0001348189,0.000059915365,0.00018812314],"category_scores_gemma":[0.00011860004,0.000107314685,0.000024394563,0.001483738,0.00002578614,0.00082379853,0.000096795884,0.000069769536,0.000002540863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017127477,0.00009961338,0.0003014397,0.0000047562526,0.000009353086,0.0000040049076,0.00044917336,0.34864655,0.00008785326,0.3882791,0.00020655812,0.2619099],"study_design_scores_gemma":[0.0002522528,0.000019324718,0.0014860481,0.0000097522325,0.0000052234004,0.0000176111,0.000020812258,0.99069977,0.0005365083,0.006259089,0.0005693543,0.00012428423],"about_ca_topic_score_codex":0.0000102327185,"about_ca_topic_score_gemma":0.000017251896,"teacher_disagreement_score":0.6420532,"about_ca_system_score_codex":0.000048289716,"about_ca_system_score_gemma":0.000039533898,"threshold_uncertainty_score":0.4376166},"labels":[],"label_agreement":null},{"id":"W4206233727","doi":"10.1007/978-3-030-92121-7","title":"Learning and Intelligent Optimization","year":2021,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Computer science; Artificial intelligence; Human–computer interaction","score_opus":0.011794082589354405,"score_gpt":0.24780645400041365,"score_spread":0.23601237141105924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206233727","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000037603065,0.0006509557,0.99634963,0.0003224104,0.0008111513,0.00028155392,6.313294e-7,0.00031315378,0.0012667321],"genre_scores_gemma":[0.0022330286,0.00020448545,0.99621034,0.00049199513,0.00015011785,0.000013901508,0.000012729,0.00002424237,0.00065917923],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971601,0.000068050234,0.00039233817,0.0012881208,0.00065806403,0.00043336285],"domain_scores_gemma":[0.99828994,0.00040934977,0.00022235331,0.00062236056,0.00031973564,0.0001362825],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006175936,0.00034747095,0.00036585957,0.00078702,0.0002246373,0.0007452327,0.0013558116,0.00023894847,0.00001648688],"category_scores_gemma":[0.00034282706,0.0003517594,0.00005564257,0.0012387375,0.00039647485,0.0004447502,0.0014995395,0.00065813644,0.0000036395686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.4262164e-7,0.00001406135,0.000030487023,0.00002352985,0.0000040998925,0.0000249434,0.0005928549,0.721302,0.000008397805,0.003956309,0.000023803184,0.2740188],"study_design_scores_gemma":[0.000081558836,0.00012196862,0.0000061783394,0.00028996432,0.0000042813776,0.00006700512,2.8868723e-7,0.9791868,0.0006993093,0.01876607,0.00041489908,0.00036168375],"about_ca_topic_score_codex":0.000004045985,"about_ca_topic_score_gemma":0.0000044078074,"teacher_disagreement_score":0.27365708,"about_ca_system_score_codex":0.0003524229,"about_ca_system_score_gemma":0.00075321354,"threshold_uncertainty_score":0.9998934},"labels":[],"label_agreement":null},{"id":"W4224983028","doi":"10.1109/jas.2022.105506","title":"Cooperative and Competitive Multi-Agent Systems: From Optimization to Games","year":2022,"lang":"en","type":"article","venue":"IEEE/CAA Journal of Automatica Sinica","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":199,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Program of Shanghai Academic Research Leader; Project 211; Chinesisch-Deutsche Zentrum für Wissenschaftsförderung; National Natural Science Foundation of China","keywords":"Computer science; Optimization problem; Multi-agent system; Autonomy; Perspective (graphical); Mathematical optimization; Artificial intelligence","score_opus":0.021633974522397972,"score_gpt":0.26784127805189367,"score_spread":0.2462073035294957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224983028","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005660691,0.00028008717,0.9911825,0.0012303329,0.0009130093,0.0004194117,0.000031695537,0.00013651588,0.00014572417],"genre_scores_gemma":[0.41817304,0.000026961123,0.58122975,0.0004156548,0.00005145457,0.000036094058,0.0000027145911,0.000015738715,0.000048589463],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977003,0.00039014601,0.000820336,0.00028809474,0.0005955977,0.0002055221],"domain_scores_gemma":[0.997853,0.0005463886,0.00060734234,0.0003313924,0.00044527935,0.00021660213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062260486,0.00018161396,0.0004261436,0.00031574705,0.0002492744,0.0002483193,0.0007549684,0.000041163537,0.00007190077],"category_scores_gemma":[0.00031926317,0.00016717715,0.00007229201,0.0004920549,0.000068341615,0.00040759178,0.00030414553,0.00024925222,0.0000062182175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035555702,0.0003576992,0.00008331512,0.00001677588,0.00015985411,0.00006808934,0.006177426,0.9695191,0.00049003813,0.018676225,0.0034127235,0.0010032452],"study_design_scores_gemma":[0.00082455325,0.000867769,0.00035697306,0.00015675266,0.00003872688,0.00017995598,0.0008065845,0.9949243,0.0005372123,0.00023628629,0.00083714764,0.0002337105],"about_ca_topic_score_codex":0.000011888119,"about_ca_topic_score_gemma":6.600275e-7,"teacher_disagreement_score":0.41251236,"about_ca_system_score_codex":0.00018552317,"about_ca_system_score_gemma":0.00018233286,"threshold_uncertainty_score":0.6817286},"labels":[],"label_agreement":null},{"id":"W4225620683","doi":"10.1109/cdc45484.2021.9682985","title":"L-DQN: An Asynchronous Limited-Memory Distributed Quasi-Newton Method","year":2021,"lang":"en","type":"article","venue":"2021 60th IEEE Conference on Decision and Control (CDC)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Office of Naval Research; National Science Foundation","keywords":"Asynchronous communication; Computer science; Node (physics); Convergence (economics); Computation; Dimension (graph theory); Distributed memory; Mathematical optimization; Distributed algorithm; Theoretical computer science; Distributed computing; Algorithm; Parallel computing; Shared memory; Mathematics; Computer network","score_opus":0.02599025233896078,"score_gpt":0.2967369035782201,"score_spread":0.2707466512392593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225620683","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030882335,0.00022965524,0.9919231,0.0021108363,0.0007471867,0.0003813223,0.00006734136,0.00031047923,0.0011418806],"genre_scores_gemma":[0.804957,0.00024145524,0.19215368,0.0018622513,0.00014287922,0.00009840962,0.00006376092,0.000033552664,0.00044706004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965314,0.000425234,0.00061368867,0.0012234984,0.00069272483,0.0005134154],"domain_scores_gemma":[0.9962814,0.0008643837,0.00023526252,0.001368504,0.00079928886,0.00045117858],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006787732,0.0004062396,0.0006183872,0.00024934614,0.00028375903,0.00073862064,0.00091059285,0.00024376865,0.00035526068],"category_scores_gemma":[0.0006673443,0.00037517055,0.00013646543,0.00071764237,0.00009730522,0.0005471772,0.00018622425,0.00035751786,0.000080238045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018828645,0.0006857933,0.0000948224,0.000014323786,0.00007096157,0.00024468612,0.00038346247,0.0015866813,0.005102118,0.14693806,0.002413589,0.8422772],"study_design_scores_gemma":[0.0037012084,0.0010317268,0.0011704612,0.00019249048,0.000051330044,0.00012640977,0.00019631977,0.96056354,0.007888865,0.02239654,0.001953136,0.00072799897],"about_ca_topic_score_codex":0.000023468929,"about_ca_topic_score_gemma":0.000028919598,"teacher_disagreement_score":0.9589768,"about_ca_system_score_codex":0.00008995289,"about_ca_system_score_gemma":0.00038265242,"threshold_uncertainty_score":0.99987},"labels":[],"label_agreement":null},{"id":"W4226246573","doi":"10.1109/tsipn.2022.3163931","title":"Staleness Analysis in Asynchronous Optimization","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Signal and Information Processing over Networks","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Asynchronous communication; Computer science; Convergence (economics); Node (physics); Process (computing); Optimization problem; Rate of convergence; Optimization algorithm; Bandwidth (computing); Distributed computing; Work in process; Mathematical optimization; Algorithm; Mathematics; Computer network","score_opus":0.0062926203262685014,"score_gpt":0.2089693430641436,"score_spread":0.2026767227378751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226246573","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00054623844,0.00004346913,0.99852973,0.00006783137,0.0001233031,0.00017501126,0.0000073902474,0.00019133429,0.00031569778],"genre_scores_gemma":[0.97793764,0.000028111806,0.021358345,0.00050249125,0.0000071310087,0.00012475658,0.00001803067,0.000005220473,0.00001828917],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891627,0.000052373638,0.00036319505,0.00018302971,0.00030645236,0.0001787076],"domain_scores_gemma":[0.9995197,0.000044128672,0.00016481026,0.00014618906,0.00007294868,0.00005221355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002572759,0.00012454046,0.00015283232,0.0008033902,0.00044996446,0.00023326572,0.00022861497,0.00004839271,0.00014596757],"category_scores_gemma":[0.0000015340905,0.00013321394,0.000049994058,0.0023221262,0.000029093284,0.002929795,0.000008523834,0.00023563982,8.916627e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017046836,0.000045099147,0.000039673163,0.000007663936,0.000019002788,5.019193e-7,0.00048276692,0.9424758,7.2525677e-7,0.00051609124,0.000013341735,0.056382284],"study_design_scores_gemma":[0.00028994077,0.00008883499,0.000205978,0.000010959305,0.000029687608,0.0000056570316,0.00006311771,0.99892706,0.000057999245,0.00010738159,0.0000615028,0.00015186497],"about_ca_topic_score_codex":0.00001668863,"about_ca_topic_score_gemma":0.000002294612,"teacher_disagreement_score":0.97739136,"about_ca_system_score_codex":0.0001225348,"about_ca_system_score_gemma":0.000059397713,"threshold_uncertainty_score":0.54323065},"labels":[],"label_agreement":null},{"id":"W4226303352","doi":"10.4230/lipics.ccc.2023.1","title":"Constant matters: Fine-grained Complexity of Differentially Private Continual Observation","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Upper and lower bounds; Factorization; Combinatorics; Bounded function; Binary number; Mathematics; Norm (philosophy); Logical matrix; Constant (computer programming); Matrix (chemical analysis); Discrete mathematics; Dimension (graph theory); Algorithm; Computer science; Arithmetic; Physics; Mathematical analysis","score_opus":0.11454045223232952,"score_gpt":0.2070634440599788,"score_spread":0.0925229918276493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226303352","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13857526,0.000009660379,0.8591337,0.00035150605,0.00045473152,0.0005443342,0.00009701151,0.00042184704,0.00041196521],"genre_scores_gemma":[0.9529105,0.000016652903,0.046375945,0.00016138058,0.000018507155,0.0000046210844,0.00014280966,0.000019685567,0.00034990857],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797034,0.00020871506,0.00042243206,0.0009068356,0.00020160699,0.00029004973],"domain_scores_gemma":[0.99753743,0.00013833883,0.0007415494,0.0012160843,0.0002648448,0.0001017643],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025706206,0.0003187731,0.0004830544,0.00035884458,0.00014499856,0.00007836115,0.0020890895,0.00015434047,0.00019504203],"category_scores_gemma":[0.000064388296,0.00039017442,0.00021296657,0.0006629815,0.00033176277,0.00026160828,0.0031324502,0.0004207891,0.00000487031],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042285195,0.00015315888,0.0027232426,0.00009285893,0.00009513968,0.000043927383,0.00027454578,0.037118215,0.00022664989,0.9586248,0.00047872952,0.00012649423],"study_design_scores_gemma":[0.0010453403,0.00018555952,0.0063905288,0.0001476475,0.000100312,0.0000041887647,0.0000657532,0.71636397,0.0008492632,0.27385205,0.00029989055,0.00069549424],"about_ca_topic_score_codex":0.000118950986,"about_ca_topic_score_gemma":0.000020780337,"teacher_disagreement_score":0.8143352,"about_ca_system_score_codex":0.00021575567,"about_ca_system_score_gemma":0.00015952303,"threshold_uncertainty_score":0.99985504},"labels":[],"label_agreement":null},{"id":"W4236771096","doi":"10.2139/ssrn.2710353","title":"Correlation Fix","year":2016,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Bank of Canada","funders":"","keywords":"Correlation; Mathematics; Geometry","score_opus":0.006442820302268904,"score_gpt":0.2186148889978625,"score_spread":0.2121720686955936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236771096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000796684,0.00019567358,0.99553555,0.0020395326,0.00027319754,0.000062146835,2.2198475e-7,0.00018312546,0.00091386173],"genre_scores_gemma":[0.97659004,0.0005805485,0.020131767,0.00010545544,0.00011378234,0.000005846169,3.2341651e-7,0.000010876857,0.002461361],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984008,0.000039669503,0.00017381083,0.00015675556,0.00021234264,0.0010166105],"domain_scores_gemma":[0.99945724,0.00006451345,0.00011885552,0.0002116844,0.00009285579,0.000054878696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007255414,0.00008126529,0.00007201082,0.00012912824,0.00011602298,0.00005572381,0.0005209674,0.000042561125,0.000017922119],"category_scores_gemma":[0.00010681754,0.00005361437,0.000048529,0.00020055867,0.000022247907,0.0005381695,0.00005433258,0.00033874137,0.00007033636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000235139,0.000010458842,0.00028620582,2.2854194e-7,0.000010424186,6.852607e-7,0.000032190972,0.000048901868,0.00014855195,0.9170959,0.00018638746,0.082177736],"study_design_scores_gemma":[0.00038313156,0.00022152382,0.00027314026,0.000020174479,0.0000044153394,0.00045772828,0.00001927669,0.00903613,0.00032369164,0.9883631,0.0007681602,0.00012956648],"about_ca_topic_score_codex":0.000002376388,"about_ca_topic_score_gemma":0.0000074803343,"teacher_disagreement_score":0.97579336,"about_ca_system_score_codex":0.0005263522,"about_ca_system_score_gemma":0.00060346635,"threshold_uncertainty_score":0.21863306},"labels":[],"label_agreement":null},{"id":"W4248310349","doi":"10.1109/cefc.2010.5481803","title":"Enhancing the performance of conjugate gradient solvers on graphic processing units","year":2010,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Conjugate gradient method; Computer science; Conjugate; Parallel computing; Computational science; Computer graphics (images); Algorithm; Mathematics","score_opus":0.013115913260713291,"score_gpt":0.22351897040197283,"score_spread":0.21040305714125954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248310349","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43173572,0.000005654534,0.56447375,0.00022908047,0.00025096635,0.00016694155,2.653548e-7,0.00020878339,0.0029288046],"genre_scores_gemma":[0.9604969,0.0000055152295,0.039178167,0.00021816118,0.000013924555,0.000015857438,4.280773e-7,0.0000061233795,0.00006491928],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990866,0.000016790946,0.00021321628,0.00020366623,0.00029517425,0.00018450807],"domain_scores_gemma":[0.99910855,0.0000816367,0.00012869082,0.00042479587,0.00021141896,0.000044900655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035302693,0.000102355094,0.00009595541,0.00013894823,0.00017460548,0.000057076788,0.0006852543,0.00003801462,0.000008288443],"category_scores_gemma":[0.0000702662,0.000066336375,0.00002498929,0.0007464512,0.000120136014,0.00025818727,0.00009371892,0.00018475235,0.0000035986686],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016273703,0.00011345298,0.0012158125,0.00007541385,0.000019062389,0.0000017201289,0.0038448025,0.002874965,0.07437582,0.8950461,0.00022844916,0.022188118],"study_design_scores_gemma":[0.0001750357,0.00026539675,0.0007923499,0.00007885365,0.0000057206375,0.0000113659935,0.00009038618,0.43114364,0.56597364,0.0011486284,0.00014226434,0.00017275596],"about_ca_topic_score_codex":0.0000045840447,"about_ca_topic_score_gemma":0.000007162554,"teacher_disagreement_score":0.8938975,"about_ca_system_score_codex":0.000008114169,"about_ca_system_score_gemma":0.00007231611,"threshold_uncertainty_score":0.2705119},"labels":[],"label_agreement":null},{"id":"W4254377867","doi":"10.1109/bigdatase53435.2021.00012","title":"An Incentive Mechanism for Resource Allocation in Coded Distributed Computing","year":2021,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital","funders":"National Research Foundation Singapore","keywords":"Server; Computer science; Cloud computing; Enhanced Data Rates for GSM Evolution; Edge computing; Incentive; Distributed computing; Computer network; Resource allocation; Operating system; Microeconomics; Artificial intelligence","score_opus":0.01774023493019792,"score_gpt":0.2707388272312758,"score_spread":0.25299859230107785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254377867","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023455124,0.000004570078,0.99601895,0.0006911241,0.000071001254,0.0002744008,0.000006169245,0.00034326807,0.000245003],"genre_scores_gemma":[0.5240202,5.5475886e-7,0.4755514,0.00028350635,0.000009966528,0.000018078046,0.000086767985,0.0000046536065,0.000024871091],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990683,0.00006148318,0.00020983219,0.00034751242,0.00013256622,0.00018028702],"domain_scores_gemma":[0.99916095,0.00011741035,0.000068053916,0.0003229823,0.0002808244,0.00004978962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021883522,0.00008164477,0.00010650933,0.00007868931,0.00007450155,0.0001042085,0.00035189258,0.00004857754,0.000004509151],"category_scores_gemma":[0.00015442897,0.00008783772,0.000024946738,0.00050707086,0.000012911134,0.00023849144,0.000114210416,0.000051868545,0.0000013293729],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028966472,0.00008090859,0.000060638664,0.0000047506223,0.000003338848,0.0000024764836,0.00039592167,0.0029908384,0.0016457989,0.99228424,0.00015341892,0.0023747713],"study_design_scores_gemma":[0.00029971427,0.000049236787,0.00020653657,0.000017952798,0.0000018138188,0.0000030114309,0.00013865564,0.90744466,0.054887958,0.036790874,0.00005457317,0.000104988496],"about_ca_topic_score_codex":0.000012184757,"about_ca_topic_score_gemma":0.00001739574,"teacher_disagreement_score":0.9554934,"about_ca_system_score_codex":0.000077745804,"about_ca_system_score_gemma":0.000052144806,"threshold_uncertainty_score":0.35819182},"labels":[],"label_agreement":null},{"id":"W4283078428","doi":"10.1145/3550454.3555519","title":"Gaussian Blue Noise","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Gaussian; Noise (video); Computer science; Gaussian noise; Selection (genetic algorithm); Sampling (signal processing); Mathematical optimization; Quality (philosophy); Algorithm; Current (fluid); Mathematics; Artificial intelligence; Physics; Telecommunications","score_opus":0.019458423531143285,"score_gpt":0.24419574382506865,"score_spread":0.22473732029392535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283078428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006248025,0.000021034142,0.99377877,0.0037706352,0.0004987328,0.00020029389,0.000018326811,0.0007074004,0.00038002673],"genre_scores_gemma":[0.83833045,0.000032426546,0.1587707,0.0022493426,0.000013573444,0.0003156806,0.0000058957125,0.000022274973,0.0002596703],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998753,0.00007539262,0.00018568145,0.0003519398,0.0004141933,0.00021978085],"domain_scores_gemma":[0.998561,0.00012013749,0.000059172562,0.0011243246,0.000046528174,0.000088804154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019122974,0.00012954292,0.000104282895,0.0004919777,0.00070174685,0.000060971066,0.0013593074,0.000058034344,0.00015471902],"category_scores_gemma":[0.000019446972,0.00014352449,0.00011140777,0.0014888186,0.000051400642,0.00020725437,0.000040911178,0.00054020906,0.000013435178],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043813077,0.0014008215,0.00013557129,0.000019847244,0.00012548604,0.000048948114,0.0032868804,0.12537125,0.00037877567,0.7966241,0.0038342194,0.06873029],"study_design_scores_gemma":[0.0027635263,0.0032903503,0.0018646017,0.0000570122,0.00014301058,0.0004915737,0.0007702848,0.5250672,0.014714981,0.37895563,0.06937543,0.0025063786],"about_ca_topic_score_codex":0.000014867968,"about_ca_topic_score_gemma":0.000004508218,"teacher_disagreement_score":0.8377057,"about_ca_system_score_codex":0.000058455535,"about_ca_system_score_gemma":0.0000518461,"threshold_uncertainty_score":0.5852759},"labels":[],"label_agreement":null},{"id":"W4285507276","doi":"10.1109/jsait.2022.3190859","title":"Successive Approximation Coding for Distributed Matrix Multiplication","year":2022,"lang":"en","type":"article","venue":"IEEE Journal on Selected Areas in Information Theory","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computation; Computer science; Coding (social sciences); Matrix multiplication; Algorithm; Parallel computing; Multiplication (music); Theoretical computer science; Distributed computing; Mathematics","score_opus":0.010413482430253475,"score_gpt":0.25895779948335734,"score_spread":0.24854431705310387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285507276","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035067734,0.000010415726,0.99443364,0.0003444865,0.0004929923,0.0007030302,0.00005231981,0.0002485474,0.00020780817],"genre_scores_gemma":[0.9583608,0.000008141237,0.04043365,0.00037125914,0.000059085625,0.0004967032,0.00023534927,0.000011370002,0.000023679308],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982218,0.00023983192,0.0006767771,0.00014689019,0.00046085604,0.00025385333],"domain_scores_gemma":[0.9975579,0.00058699347,0.0009880266,0.00023945658,0.0005551892,0.00007244692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013907474,0.00014410123,0.00015527011,0.00079200434,0.0005776695,0.0002615311,0.00067425333,0.00005467069,0.000026643054],"category_scores_gemma":[0.0010739629,0.00014606716,0.000060161175,0.0012942437,0.000020635938,0.0019920485,0.00006350097,0.000386559,0.0000075050384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002863519,0.00014115791,0.000097443095,0.00002558053,0.00002489576,0.0000016146213,0.0027030911,0.23046823,0.00035214485,0.7473645,0.001918262,0.016616708],"study_design_scores_gemma":[0.0015313898,0.00031141532,0.0005114102,0.00004395937,0.000008545783,0.00012040099,0.00035217145,0.92836475,0.004038246,0.06349031,0.00095782237,0.00026958977],"about_ca_topic_score_codex":0.0000011633958,"about_ca_topic_score_gemma":2.0332259e-7,"teacher_disagreement_score":0.954854,"about_ca_system_score_codex":0.00060751307,"about_ca_system_score_gemma":0.00014348379,"threshold_uncertainty_score":0.5956446},"labels":[],"label_agreement":null},{"id":"W4285600461","doi":"10.24963/ijcai.2022/548","title":"Private Stochastic Convex Optimization and Sparse Learning with Heavy-tailed Data Revisited","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"King Abdullah University of Science and Technology","keywords":"Bounded function; Lipschitz continuity; Convex optimization; Mathematics; Mathematical optimization; Regular polygon; Constraint (computer-aided design); Moment (physics); Upper and lower bounds; Curse of dimensionality; Estimator; Monotonic function; Optimization problem; Convex function; Applied mathematics; Mathematical analysis; Statistics; Physics","score_opus":0.07149497516497867,"score_gpt":0.2739307753526263,"score_spread":0.20243580018764762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285600461","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005862041,0.000017338152,0.98669815,0.005037285,0.00032805905,0.0006495667,0.000026544156,0.00022096843,0.0011600605],"genre_scores_gemma":[0.9562334,0.000032091735,0.043262005,0.0002147712,0.000040994804,0.00007720804,0.000020626714,0.000021089603,0.00009780455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973454,0.00004047478,0.00061662734,0.00075700297,0.0009784169,0.00026206503],"domain_scores_gemma":[0.9978574,0.00013307668,0.0007415513,0.00045633042,0.0007242629,0.000087412816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008164566,0.0002536834,0.00028324628,0.0003132776,0.0005308171,0.00034640508,0.0028068065,0.00004836078,0.00016526751],"category_scores_gemma":[0.00071267335,0.00020532518,0.00004754514,0.000704211,0.00024987047,0.00069351314,0.002276238,0.0005069258,0.0000065286167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017069491,0.00015478954,0.0002946992,0.00002659455,0.000049850307,0.000001410896,0.00089434657,0.19621237,0.0006046304,0.79889274,0.00009473519,0.0026031146],"study_design_scores_gemma":[0.00008031698,0.0003419294,0.0000650617,0.00023214784,0.000019211775,0.00004070611,0.00039192147,0.9717849,0.0056125335,0.021090146,0.00009443514,0.00024670045],"about_ca_topic_score_codex":0.000019613899,"about_ca_topic_score_gemma":0.0000022936595,"teacher_disagreement_score":0.9503714,"about_ca_system_score_codex":0.00012128705,"about_ca_system_score_gemma":0.00008575557,"threshold_uncertainty_score":0.8372918},"labels":[],"label_agreement":null},{"id":"W4287685829","doi":"10.48550/arxiv.2008.10526","title":"Stochastic Multi-level Composition Optimization Algorithms with Level-Independent Convergence Rates","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of California, Davis","keywords":"Oracle; Convergence (economics); Generalization; Mathematics; Algorithm; Function (biology); Sample (material); Composition (language); Stochastic optimization; Mathematical optimization; Stochastic approximation; Applied mathematics; Order (exchange); Computer science; Mathematical analysis","score_opus":0.16009295663069031,"score_gpt":0.22319632141435541,"score_spread":0.0631033647836651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287685829","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013555355,0.000024282044,0.9958882,0.00019377844,0.0005258116,0.0009470608,0.00009950042,0.00088512123,0.00008072287],"genre_scores_gemma":[0.6514274,0.000029307253,0.34809092,0.00009595503,0.00003478074,0.000007746949,0.00012540055,0.000032217726,0.0001563087],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971354,0.00015380891,0.0003505294,0.0016558736,0.00028396564,0.00042044526],"domain_scores_gemma":[0.99743766,0.00011196324,0.00052942213,0.0010406622,0.00057945494,0.00030085363],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018126966,0.00054345344,0.0004709667,0.00038009384,0.00027129342,0.00023179945,0.0018718566,0.00032169282,0.000044698292],"category_scores_gemma":[0.000044952187,0.00060527126,0.00014115128,0.000960857,0.00017524953,0.0006226808,0.001470815,0.00061445136,0.000045709006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000410562,0.00012399118,0.000120751305,0.00004565063,0.000089950714,0.0001228178,0.0002518699,0.9676013,0.00003848015,0.031358704,0.00006121528,0.00014421568],"study_design_scores_gemma":[0.0008842803,0.00015121659,0.0005030612,0.0001830071,0.0000953345,0.000016366328,0.000048969905,0.99382925,0.0004903497,0.0031072595,0.0000020778334,0.0006888406],"about_ca_topic_score_codex":0.00009489372,"about_ca_topic_score_gemma":0.000012088888,"teacher_disagreement_score":0.65007186,"about_ca_system_score_codex":0.00036702421,"about_ca_system_score_gemma":0.00032662798,"threshold_uncertainty_score":0.99963987},"labels":[],"label_agreement":null},{"id":"W4288079579","doi":"10.1145/3419111.3421299","title":"Semi-dynamic load balancing","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Load balancing (electrical power); Sizing; Distributed computing; Software deployment; Python (programming language); Execution time; Synchronization (alternating current); Key (lock); Parallel computing; Operating system; Computer network","score_opus":0.01710817377559423,"score_gpt":0.25800771982612863,"score_spread":0.2408995460505344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288079579","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000053277272,0.000096484284,0.9772368,0.002664782,0.00078886194,0.00034014665,0.0000039785677,0.002502964,0.016312672],"genre_scores_gemma":[0.19213511,0.00003142979,0.8059635,0.0010733019,0.000052705855,0.0000653751,0.00001512463,0.000023332215,0.00064012944],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981846,0.00003288813,0.00029870926,0.00079059665,0.0004506929,0.00024246465],"domain_scores_gemma":[0.99851257,0.000060976796,0.00015473666,0.0009775311,0.00016450688,0.0001297069],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016896996,0.0002484408,0.00027412974,0.00010683272,0.000048911676,0.0002618918,0.0018025866,0.00019157224,0.000048120954],"category_scores_gemma":[0.00014005745,0.00024573284,0.000107894746,0.00026572015,0.000025749447,0.0001302765,0.003105916,0.00045384286,0.00009940467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000107200085,0.00017279902,0.00026520345,0.0006322524,0.00023397253,0.0001499182,0.0046440596,0.05999704,0.0016480457,0.83319706,0.061820023,0.03722888],"study_design_scores_gemma":[0.00006764023,0.00002293121,0.00006857836,0.000074737494,0.000006541777,0.000007140804,0.000005399111,0.9382932,0.0005342077,0.06025178,0.000379527,0.00028831296],"about_ca_topic_score_codex":0.000039428145,"about_ca_topic_score_gemma":0.00000439761,"teacher_disagreement_score":0.87829614,"about_ca_system_score_codex":0.00024752153,"about_ca_system_score_gemma":0.00033836137,"threshold_uncertainty_score":0.99999946},"labels":[],"label_agreement":null},{"id":"W4289655150","doi":"10.1109/isit50566.2022.9834389","title":"Successive Approximation for Coded Matrix Multiplication","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Symposium on Information Theory (ISIT)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Computation; Multiplication (music); Matrix multiplication; Parallel computing; Computational science; Matrix (chemical analysis); Supercomputer; Algorithm; Theoretical computer science; Mathematics","score_opus":0.010435386580536908,"score_gpt":0.2684972520790731,"score_spread":0.2580618654985362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289655150","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010544491,0.0000073425435,0.9872631,0.0023165357,0.0020658937,0.0012295103,0.00022085827,0.0005393215,0.0053029764],"genre_scores_gemma":[0.92767406,0.000015462352,0.05921027,0.0035407876,0.00025679526,0.0054659722,0.0018199442,0.00004205042,0.0019746898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976591,0.00014869566,0.0006984644,0.00033631158,0.0009162698,0.00024119679],"domain_scores_gemma":[0.9977254,0.00052501995,0.00069813605,0.0005133987,0.00046239753,0.0000756302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011018204,0.0002138024,0.00016605268,0.0005159269,0.0005854583,0.00032339833,0.0015524263,0.00006622474,0.0001960811],"category_scores_gemma":[0.0002187267,0.0002332048,0.0001364686,0.0004790433,0.000038441878,0.0023831702,0.00027166057,0.000213105,0.0000874314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017954515,0.00010177669,0.00001528256,0.00001522738,0.00004218325,4.243816e-7,0.0016801099,0.10129357,0.0011231753,0.88622326,0.004367638,0.00495783],"study_design_scores_gemma":[0.001150449,0.00026340084,0.00003925464,0.000013794696,0.0000123050795,0.000020605517,0.00030438043,0.92885834,0.010393501,0.046040975,0.012571993,0.00033101666],"about_ca_topic_score_codex":0.0000068678837,"about_ca_topic_score_gemma":3.0636218e-7,"teacher_disagreement_score":0.92805284,"about_ca_system_score_codex":0.0006089481,"about_ca_system_score_gemma":0.00006695859,"threshold_uncertainty_score":0.95098156},"labels":[],"label_agreement":null},{"id":"W4290993997","doi":"10.1109/icc45855.2022.9839180","title":"Heterogeneous Coded Distributed Computing with Nonuniform Input File Popularity","year":2022,"lang":"en","type":"article","venue":"ICC 2022 - IEEE International Conference on Communications","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Shuffling; Computer science; Computational complexity theory; Integer programming; Linear programming; Simple (philosophy); Distributed File System; Integer (computer science); File transfer; Parallel computing; Distributed computing; Mathematical optimization; Algorithm; Mathematics; Operating system; Transfer (computing)","score_opus":0.0713049041609363,"score_gpt":0.31696614361532244,"score_spread":0.24566123945438614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290993997","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017467107,0.000021078207,0.9772501,0.0063008135,0.00049782253,0.0004768021,0.0017943582,0.0006187333,0.011293583],"genre_scores_gemma":[0.9179348,0.000021794933,0.07875556,0.00065487233,0.000025078683,0.00033971755,0.0019980553,0.000019416026,0.00025075488],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978735,0.00022309326,0.00041433756,0.00045068387,0.0007714483,0.00026695908],"domain_scores_gemma":[0.99685013,0.00030986313,0.00034184149,0.001980909,0.00041347145,0.00010377094],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029773003,0.00021511396,0.00019870458,0.00028311473,0.0009632563,0.0002707841,0.00522168,0.00004483065,0.0013602981],"category_scores_gemma":[0.00008485017,0.00022798589,0.00007788629,0.0006308571,0.00014171952,0.0002806602,0.0017728519,0.00060729537,0.000029959865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059975344,0.0009566226,0.0004404381,0.000006195281,0.00016550138,0.00002689459,0.0010053924,0.038555995,0.0003313366,0.9421257,0.009978501,0.006347468],"study_design_scores_gemma":[0.00043685734,0.00030365566,0.0003550205,0.000039676324,0.000009892618,0.00011570457,0.00015332013,0.9827486,0.0003029143,0.007487611,0.0077006617,0.00034603104],"about_ca_topic_score_codex":0.00011300753,"about_ca_topic_score_gemma":0.000073414165,"teacher_disagreement_score":0.94419265,"about_ca_system_score_codex":0.00038175378,"about_ca_system_score_gemma":0.00017649875,"threshold_uncertainty_score":0.9995526},"labels":[],"label_agreement":null},{"id":"W4293025003","doi":"10.1145/3489517.3530417","title":"Sign bit is enough","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 59th ACM/IEEE Design Automation Conference","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Compression (physics); Sign (mathematics); Synchronization (alternating current); Data compression; Convergence (economics); Process (computing); Stochastic gradient descent; Rate of convergence; Compression ratio; Algorithm; Computer engineering; Artificial intelligence; Artificial neural network; Key (lock); Computer network; Mathematics; Engineering","score_opus":0.050709080288593444,"score_gpt":0.25046996521880294,"score_spread":0.1997608849302095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293025003","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034017116,0.000022701255,0.98873895,0.0039636325,0.00041569406,0.00084981456,0.000008366821,0.0007228415,0.0018763129],"genre_scores_gemma":[0.7889418,0.0000053428507,0.20972335,0.0006649115,0.00002048043,0.0002549089,9.1586617e-7,0.000015721645,0.00037255642],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997851,0.00005053554,0.00046474027,0.0004677147,0.0008713733,0.00029464136],"domain_scores_gemma":[0.9979662,0.0001743725,0.0006451257,0.0005208189,0.00062270253,0.00007083506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008262729,0.00020791772,0.00022967462,0.00024624862,0.00045597172,0.00021141938,0.0038525874,0.00005732015,0.0001654059],"category_scores_gemma":[0.00045511452,0.00018251206,0.00009479652,0.0012427011,0.00009455914,0.00073213206,0.00091373606,0.00023604975,0.00001527409],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005112343,0.0003550191,0.0005556047,0.00015968882,0.00008628927,0.0000012738413,0.013777076,0.005218032,0.08488688,0.79610234,0.07854328,0.020263376],"study_design_scores_gemma":[0.00036776115,0.0002945662,0.0004960623,0.000065155975,0.000023627787,0.000037318066,0.00017830156,0.6201645,0.2651253,0.111793876,0.0010785807,0.00037493216],"about_ca_topic_score_codex":0.000009917481,"about_ca_topic_score_gemma":6.0180945e-8,"teacher_disagreement_score":0.7855401,"about_ca_system_score_codex":0.00012766903,"about_ca_system_score_gemma":0.00020346796,"threshold_uncertainty_score":0.7442626},"labels":[],"label_agreement":null},{"id":"W4293388868","doi":"10.48550/arxiv.1305.3803","title":"A fast randomized Kaczmarz algorithm for sparse solutions of consistent\\n linear systems","year":2013,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Overdetermined system; Underdetermined system; Linear system; Compressed sensing; Mathematics; Solver; Convergence (economics); Speedup; System of linear equations; Algorithm; Mathematical optimization; Applied mathematics; Computer science; Mathematical analysis","score_opus":0.09669444067441307,"score_gpt":0.20070538456649836,"score_spread":0.10401094389208529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293388868","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008267602,0.00032398629,0.9870185,0.000073408846,0.00261246,0.0074508535,0.00030403712,0.00042181788,0.0009681316],"genre_scores_gemma":[0.677447,0.000814113,0.3154382,0.000054127457,0.00021843782,0.00016160031,0.00012270497,0.000095078634,0.0056487126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942526,0.00079834735,0.0015247919,0.0021331501,0.00029692522,0.0009941357],"domain_scores_gemma":[0.99064183,0.0017501585,0.002253135,0.002282202,0.0026081807,0.00046450106],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017935231,0.00088314456,0.002356441,0.0010329953,0.00050517754,0.00024347479,0.002687233,0.00074647635,0.000074722404],"category_scores_gemma":[0.00051015493,0.0010096807,0.0014230357,0.0013057219,0.0014351456,0.00063607254,0.002328866,0.00059166586,0.000074549964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010835597,0.00038287567,0.000011936042,0.00032904523,0.0007372093,0.000022354605,0.0003963919,0.4582137,0.0000137769775,0.5370205,0.00048423946,0.0013044439],"study_design_scores_gemma":[0.035056975,0.00019760715,0.0000035581304,0.0006357882,0.00081392465,0.00001831329,0.00024139039,0.9431433,0.00007943412,0.018849464,0.00013486427,0.0008253704],"about_ca_topic_score_codex":0.00072756334,"about_ca_topic_score_gemma":0.000005936651,"teacher_disagreement_score":0.67662024,"about_ca_system_score_codex":0.0004169723,"about_ca_system_score_gemma":0.0006910078,"threshold_uncertainty_score":0.99923533},"labels":[],"label_agreement":null},{"id":"W4312583831","doi":"10.1109/iscc55528.2022.9912470","title":"Learning Auction in Coded Distributed Computing with Heterogeneous User Demands","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Symposium on Computers and Communications (ISCC)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Novelis (Canada)","funders":"","keywords":"Computer science; Resource allocation; Cloud computing; Inference; Distributed computing; Artificial intelligence; Mathematical optimization; Computer network","score_opus":0.01196504871818909,"score_gpt":0.2333107772452348,"score_spread":0.2213457285270457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312583831","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031780433,0.0000965762,0.9647292,0.0020234275,0.00025993588,0.0004201722,0.00001148084,0.00042812448,0.00025068663],"genre_scores_gemma":[0.9494001,0.00008157605,0.049845908,0.00033970794,0.00001811729,0.00014232664,0.00009549722,0.000023158138,0.000053554697],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799967,0.00046696822,0.00038130497,0.00050191616,0.0003498056,0.00030035898],"domain_scores_gemma":[0.9980353,0.00030357702,0.00022827664,0.0012706395,0.00007415632,0.00008805661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004306973,0.00021986767,0.00024858056,0.00037198883,0.0011266404,0.00019772339,0.001560804,0.00004461439,0.0000068383592],"category_scores_gemma":[0.000009541472,0.00023088534,0.000051831918,0.0010454599,0.000109233595,0.00019302785,0.0012686341,0.000584686,0.0000021630385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032215223,0.00030981418,0.001770146,0.00000912348,0.000038594444,0.000012506215,0.001891073,0.9769374,0.00021441445,0.01394814,0.00043868017,0.004397908],"study_design_scores_gemma":[0.0006733347,0.00070606923,0.0004735071,0.000044642155,0.000010336989,0.00012538303,0.00015554036,0.99527985,0.00018928651,0.00022745038,0.0018228258,0.0002917495],"about_ca_topic_score_codex":0.000048050522,"about_ca_topic_score_gemma":0.000016453636,"teacher_disagreement_score":0.9176197,"about_ca_system_score_codex":0.00021281582,"about_ca_system_score_gemma":0.00004643741,"threshold_uncertainty_score":0.94152313},"labels":[],"label_agreement":null},{"id":"W4315480356","doi":"10.21203/rs.3.rs-2285238/v1","title":"Fast Armijo line search for stochastic gradient descent","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Line search; Stochastic gradient descent; Descent direction; Monotone polygon; Convergence (economics); Gradient descent; Mathematical optimization; Mathematics; Regular polygon; Interpolation (computer graphics); Line (geometry); Descent (aeronautics); Convex function; Proximal Gradient Methods; Applied mathematics; Computer science; Artificial intelligence","score_opus":0.1842082631358806,"score_gpt":0.42362163724084234,"score_spread":0.23941337410496175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315480356","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00059536594,0.00027034755,0.9877654,0.0029783598,0.0011032791,0.005309981,0.00022282069,0.0016040525,0.00015043793],"genre_scores_gemma":[0.5730609,0.00042333518,0.40774623,0.00013786355,0.0014639894,0.011033771,0.0009078286,0.00044680416,0.0047792643],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9926574,0.0004539126,0.00069498084,0.0018792647,0.0025752059,0.0017391865],"domain_scores_gemma":[0.9927554,0.0016117092,0.00015765322,0.0024304702,0.0024867842,0.0005579797],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004077164,0.0004917088,0.0005792661,0.0019701156,0.00056163373,0.00083348266,0.0037901122,0.00044792908,0.000021743692],"category_scores_gemma":[0.0012892166,0.0004893343,0.00035009068,0.0017063442,0.00028767457,0.0001857981,0.00650347,0.0019041841,0.00020531085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018198819,0.0012314102,0.00019552605,0.00459796,0.0003147521,0.0001422748,0.0056980737,0.5503105,0.00022346826,0.36159232,0.030302376,0.04520933],"study_design_scores_gemma":[0.0005661263,0.00088913,0.00031135324,0.0015464392,0.000014556106,0.000009887013,0.00019283702,0.94340485,0.0014395019,0.050653424,0.00033064882,0.00064127025],"about_ca_topic_score_codex":0.00015424418,"about_ca_topic_score_gemma":0.000022733986,"teacher_disagreement_score":0.5800191,"about_ca_system_score_codex":0.0008486559,"about_ca_system_score_gemma":0.0009831835,"threshold_uncertainty_score":0.99975586},"labels":[],"label_agreement":null},{"id":"W4316468268","doi":"10.3390/math11020480","title":"Neural Teleportation","year":2023,"lang":"en","type":"article","venue":"MDPI (MDPI AG)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Teleportation; Artificial neural network; Computer science; Representation (politics); Simple (philosophy); Maxima and minima; Function (biology); Process (computing); Superdense coding; Topology (electrical circuits); Statistical physics; Theoretical computer science; Physics; Quantum entanglement; Mathematics; Artificial intelligence; Quantum mechanics; Quantum; Quantum channel; Biology; Mathematical analysis","score_opus":0.02136916870484977,"score_gpt":0.260053241226518,"score_spread":0.23868407252166823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316468268","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026569106,0.000022202557,0.96406263,0.0014750324,0.000824752,0.00025650012,0.000002591783,0.002969203,0.003817993],"genre_scores_gemma":[0.9322508,0.000009456221,0.06517335,0.00050457957,0.00010339501,0.00008770953,0.000034162433,0.000022614526,0.0018139222],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988411,0.000029052679,0.0002251845,0.0003280348,0.00030470412,0.00027191793],"domain_scores_gemma":[0.99920887,0.0000795344,0.0000915133,0.00045326745,0.00009033617,0.00007647918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020922403,0.000115159404,0.00010930473,0.0002444999,0.00011291359,0.00012538276,0.0005357938,0.000051987772,0.000030954943],"category_scores_gemma":[0.00012553281,0.000112431444,0.00005158101,0.0010276715,0.00003094257,0.00037533304,0.00014439202,0.000087784625,0.0003089297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001373383,0.00018272016,0.005612291,0.00006856081,0.000058824946,0.00033045028,0.0054448866,0.031773005,0.0034622818,0.6258516,0.14504123,0.18216045],"study_design_scores_gemma":[0.00028745597,0.00012676156,0.015983649,0.000020273665,0.0000074944364,0.000029216815,0.000045751047,0.9495951,0.0036811915,0.025474634,0.004390222,0.00035824513],"about_ca_topic_score_codex":0.00001699885,"about_ca_topic_score_gemma":0.0000031307866,"teacher_disagreement_score":0.9178221,"about_ca_system_score_codex":0.000030800624,"about_ca_system_score_gemma":0.000030441492,"threshold_uncertainty_score":0.45848215},"labels":[],"label_agreement":null},{"id":"W4318977537","doi":"10.1007/978-3-031-10602-6_4","title":"Background on Optimization","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.05160478755999781,"score_gpt":0.2582168002821748,"score_spread":0.206612012722177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318977537","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.693748e-9,0.000004389864,0.5226008,0.00019078309,0.00033420275,0.00015386943,0.0000024504868,0.0013203402,0.47539312],"genre_scores_gemma":[0.0000070182277,0.000055442455,0.28424266,0.00040962506,0.0000660547,0.000015742113,0.000035086166,0.000055371966,0.715113],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985398,0.000007407872,0.00027552395,0.000567471,0.00042696754,0.0001828005],"domain_scores_gemma":[0.99868125,0.00012939841,0.00015563982,0.0008241951,0.00013189082,0.00007760406],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012181279,0.0002779261,0.00021759179,0.00042370785,0.000074316325,0.00016533828,0.0007988064,0.00025784425,0.00042108612],"category_scores_gemma":[0.000021869206,0.00026709933,0.00009523193,0.00010490983,0.000036647398,0.00016869881,0.0002582006,0.0001927464,0.0012775614],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.966725e-7,0.0000049661176,4.30683e-8,0.000004699325,0.000012657632,0.000006988059,0.000012882535,0.027137505,1.59235e-7,0.95784396,0.013127317,0.0018478464],"study_design_scores_gemma":[0.00020295038,0.00029876595,0.0000013958796,0.00022790756,0.000018305134,0.000011328301,0.0000025540276,0.6978442,0.00004471897,0.27847278,0.022073088,0.00080201234],"about_ca_topic_score_codex":0.000002022175,"about_ca_topic_score_gemma":7.8054853e-7,"teacher_disagreement_score":0.6793712,"about_ca_system_score_codex":0.000092345465,"about_ca_system_score_gemma":0.000051600127,"threshold_uncertainty_score":0.9999781},"labels":[],"label_agreement":null},{"id":"W4320712010","doi":"10.48550/arxiv.2302.02607","title":"Target-based Surrogates for Stochastic Optimization","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Stochastic gradient descent; Mathematical optimization; Computer science; Stochastic optimization; Optimization problem; Convergence (economics); Mathematics; Artificial intelligence","score_opus":0.1002730716856377,"score_gpt":0.20584296165682317,"score_spread":0.10556988997118547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320712010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026513322,0.000015057283,0.9952488,0.00019835518,0.0009548976,0.0010826091,0.00006690186,0.002069277,0.00009898367],"genre_scores_gemma":[0.60555184,0.0000096291205,0.3933153,0.000072573486,0.000059397677,0.000026950634,0.00021752097,0.00005780447,0.00068898546],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787265,0.00007517134,0.00026987598,0.0012440092,0.00012236726,0.00041593774],"domain_scores_gemma":[0.997484,0.00045581316,0.0003432513,0.0011126243,0.00044862367,0.0001556514],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031735093,0.00036184565,0.0003528569,0.00061624765,0.00020070076,0.00016755708,0.0017311968,0.00031911125,0.000019467076],"category_scores_gemma":[0.00026943904,0.00045143111,0.0002422298,0.0008757169,0.000095658535,0.00027418646,0.00087951584,0.00027068643,0.000031768115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015995303,0.000046622,0.00005351257,0.00006033624,0.0000332558,0.000009992976,0.000041560506,0.91205335,0.000002422253,0.08724634,0.00040909875,0.000027483818],"study_design_scores_gemma":[0.000457381,0.00007695628,0.000022478955,0.000101155296,0.000047599973,6.0530135e-7,0.000012969581,0.948696,0.0001378909,0.050014883,0.000014131499,0.00041791316],"about_ca_topic_score_codex":0.00003127962,"about_ca_topic_score_gemma":0.0000053102613,"teacher_disagreement_score":0.6052867,"about_ca_system_score_codex":0.00024003234,"about_ca_system_score_gemma":0.00029819395,"threshold_uncertainty_score":0.99979377},"labels":[],"label_agreement":null},{"id":"W4321012054","doi":"10.48550/arxiv.2302.06763","title":"Breaking the Lower Bound with (Little) Structure: Acceleration in Non-Convex Stochastic Optimization with Heavy-Tailed Noise","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; National Science Foundation","keywords":"Bounded function; Mathematics; Upper and lower bounds; Combinatorics; Omega; Convex function; Rate of convergence; Regular polygon; Discrete mathematics; Physics; Mathematical analysis; Quantum mechanics; Computer science; Geometry","score_opus":0.03945059861527851,"score_gpt":0.18823529030614633,"score_spread":0.14878469169086783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321012054","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045206536,0.0000080573855,0.95241874,0.0002055484,0.00036649205,0.0011855632,0.000012334938,0.00048060864,0.00011614638],"genre_scores_gemma":[0.9800276,0.000011400317,0.019493995,0.0000895648,0.00005118187,0.0000137780935,0.00005577605,0.000053000724,0.0002036859],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767107,0.00011886038,0.00029458775,0.0012394894,0.00024911988,0.00042688387],"domain_scores_gemma":[0.99763066,0.00018272214,0.00042846837,0.00130864,0.0003416967,0.000107813285],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024858405,0.0004515112,0.0003808903,0.0005545056,0.0002701071,0.00043881073,0.0015335269,0.0002642989,0.000024441844],"category_scores_gemma":[0.00004416189,0.00036396875,0.00007191033,0.0017773492,0.00020060745,0.00066702935,0.0008115019,0.00065358885,0.000009097585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011838736,0.000055155204,0.00063435384,0.000029003553,0.00005025861,0.00008575007,0.00045438495,0.9864419,0.000006095565,0.012026441,0.000032808075,0.00006545444],"study_design_scores_gemma":[0.0007172506,0.00018023836,0.0013273478,0.00028944857,0.000062762345,0.000011811003,0.00007000505,0.9912014,0.00005868112,0.0056106104,0.0000019479446,0.0004685072],"about_ca_topic_score_codex":0.00021777324,"about_ca_topic_score_gemma":0.0003439998,"teacher_disagreement_score":0.93482107,"about_ca_system_score_codex":0.00038270914,"about_ca_system_score_gemma":0.0003324922,"threshold_uncertainty_score":0.9998812},"labels":[],"label_agreement":null},{"id":"W4321488391","doi":"10.1109/tit.2023.3247860","title":"Transition Waste Optimization for Coded Elastic Computing","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Australian Research Council; Ministry of Science and Technology, Taiwan","keywords":"Computer science; Cloud computing; Joins; Redundancy (engineering); Theoretical computer science; Notice; Distributed computing; Database; Programming language","score_opus":0.012898203094649624,"score_gpt":0.2385268382463974,"score_spread":0.22562863515174778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321488391","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002216778,0.000001732356,0.9956102,0.00029480166,0.0008762191,0.00072382763,0.000044095796,0.0018586307,0.00036884125],"genre_scores_gemma":[0.7456622,0.000015540398,0.25293818,0.0008018977,0.000045631095,0.0002907605,0.00011152858,0.000025104977,0.00010911324],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987162,0.00007229446,0.00046927214,0.0001927474,0.00027860614,0.00027091746],"domain_scores_gemma":[0.99872476,0.00047668166,0.00016370926,0.00031881794,0.00024110792,0.0000749036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006304508,0.00016989974,0.00014564469,0.00075088395,0.00043042935,0.00017577416,0.00034138115,0.000101432066,0.000031553405],"category_scores_gemma":[0.000035319197,0.00017962336,0.00011232706,0.0010345887,0.000043504908,0.0018519674,0.0000025844433,0.00012339278,0.000114424874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037190628,0.000023105658,3.7011926e-8,0.000031677704,0.000015347718,1.6345547e-7,0.00197498,0.9297168,0.000030684012,0.040968865,0.00022476306,0.026976375],"study_design_scores_gemma":[0.0006076801,0.00014324041,0.0000013491369,0.00004557194,0.000016373984,0.0000057700636,0.0003024584,0.98464423,0.0072041485,0.006773504,0.00006789859,0.00018775271],"about_ca_topic_score_codex":0.0000011795273,"about_ca_topic_score_gemma":2.3786897e-7,"teacher_disagreement_score":0.74544054,"about_ca_system_score_codex":0.00008177465,"about_ca_system_score_gemma":0.000048765814,"threshold_uncertainty_score":0.7324828},"labels":[],"label_agreement":null},{"id":"W4366813870","doi":"10.1016/j.neunet.2023.04.028","title":"Stability analysis of stochastic gradient descent for homogeneous neural networks and linear classifiers","year":2023,"lang":"en","type":"article","venue":"Neural Networks","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Stability (learning theory); Generalization; Stochastic gradient descent; Artificial neural network; Mathematics; Activation function; Invariant (physics); Regular polygon; Computer science; Euclidean geometry; Gradient descent; Invariant measure; Applied mathematics; Artificial intelligence; Machine learning; Mathematical analysis","score_opus":0.03546809893951639,"score_gpt":0.2656003313902598,"score_spread":0.2301322324507434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366813870","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08255788,0.00018808295,0.91534084,0.00018149045,0.0005749686,0.00067124085,0.000015139697,0.00046507025,0.0000052951705],"genre_scores_gemma":[0.99105966,0.000027327364,0.008490523,0.00013208219,0.00009067552,0.0001063775,0.00005787778,0.000023189572,0.000012279395],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977575,0.000101091784,0.0005458687,0.0006983266,0.00028812562,0.0006091039],"domain_scores_gemma":[0.9980779,0.00057177135,0.00024663005,0.00068205275,0.0002074526,0.00021415812],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043639782,0.00026734782,0.0005051449,0.00040164628,0.00018980428,0.00008125247,0.0005960834,0.00014684862,0.0000050004164],"category_scores_gemma":[0.00013453276,0.00025232925,0.00026036595,0.0028698295,0.00017952186,0.00016687294,0.00031381592,0.00021163371,3.170298e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003378065,0.000037048885,0.0017295453,0.000011883134,0.00013065273,0.0000040038735,0.00012088976,0.9880201,0.000010255778,0.0016448642,0.0002158147,0.008041144],"study_design_scores_gemma":[0.00026557542,0.000248309,0.0031956914,0.0000100477555,0.00022790849,0.0000053709227,0.000020596579,0.9955066,0.000020836354,0.00027321881,0.0000056949143,0.00022016698],"about_ca_topic_score_codex":0.000016720585,"about_ca_topic_score_gemma":0.000023173894,"teacher_disagreement_score":0.9085018,"about_ca_system_score_codex":0.000058532714,"about_ca_system_score_gemma":0.00001701095,"threshold_uncertainty_score":0.9999929},"labels":[],"label_agreement":null},{"id":"W4372263166","doi":"10.1109/icassp49357.2023.10097231","title":"M22: Rate-Distortion Inspired Gradient Compression","year":2023,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Science and Technology Council","keywords":"Computer science; Constraint (computer-aided design); Distortion (music); Bottleneck; Rate distortion; Measure (data warehouse); Benchmark (surveying); Algorithm; Theoretical computer science; Mathematical optimization; Artificial intelligence; Mathematics; Data mining; Bandwidth (computing); Telecommunications; Statistics","score_opus":0.025497484525650732,"score_gpt":0.25883211931269173,"score_spread":0.233334634787041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4372263166","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007856091,0.000009369115,0.9833231,0.0007013228,0.00050883234,0.00023022034,8.369899e-7,0.0032193428,0.0041509066],"genre_scores_gemma":[0.9270885,0.000014502035,0.070667356,0.000322532,0.00003324533,0.00008797572,0.000023522975,0.000013778226,0.0017486081],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900866,0.00004694283,0.00020011551,0.00031076535,0.00021456809,0.00021895231],"domain_scores_gemma":[0.99929,0.00005705659,0.000066351466,0.00042949818,0.00007380266,0.00008328084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024005474,0.0001020309,0.00009999914,0.00025042472,0.0001281653,0.000076396194,0.00048275216,0.00004472317,0.000029385143],"category_scores_gemma":[0.000060289694,0.00008808881,0.000040945022,0.00094144704,0.000027784745,0.0002999201,0.00023204135,0.000057307243,0.00024765954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013908159,0.00018180476,0.001207448,0.00003069085,0.000020874024,0.000032929493,0.0014764277,0.007714702,0.0074962946,0.8248565,0.10890482,0.048063565],"study_design_scores_gemma":[0.0003831822,0.00013621524,0.011034906,0.00004132845,0.00000400978,0.0000067616265,0.000026579712,0.938948,0.020691236,0.023556264,0.0048565473,0.00031501366],"about_ca_topic_score_codex":0.000017079401,"about_ca_topic_score_gemma":0.0000020432972,"teacher_disagreement_score":0.9312332,"about_ca_system_score_codex":0.000052358057,"about_ca_system_score_gemma":0.000021465425,"threshold_uncertainty_score":0.35921574},"labels":[],"label_agreement":null},{"id":"W4377130721","doi":"10.48550/arxiv.2305.10634","title":"Modified Gauss-Newton Algorithms under Noise","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Institutes of Health; National Science Foundation","keywords":"Stylized fact; Gauss; Noise (video); Stochastic gradient descent; Convergence (economics); Algorithm; Applied mathematics; Quadratic equation; Gradient descent; Computer science; Newton's method; Mathematics; Mathematical optimization; Artificial intelligence; Nonlinear system; Artificial neural network; Physics","score_opus":0.14333372036839412,"score_gpt":0.2145114235177642,"score_spread":0.07117770314937008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377130721","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005081934,0.00002177372,0.9890264,0.00045699553,0.0013738434,0.00046870144,0.000020470761,0.002333045,0.0012167802],"genre_scores_gemma":[0.960049,0.00016376484,0.031181712,0.00017670925,0.00012322344,0.000007141147,0.00005216169,0.00006374318,0.008182598],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749714,0.000101109785,0.0002696407,0.0014875113,0.00018028817,0.00046431192],"domain_scores_gemma":[0.99732536,0.0001509678,0.00028171044,0.0017868716,0.00023412416,0.00022096607],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002508038,0.0004036286,0.00036871113,0.00060469925,0.00016522096,0.00018160853,0.002567643,0.0004091215,0.000018189541],"category_scores_gemma":[0.00005175982,0.00048642387,0.00022940902,0.0010936384,0.00012395976,0.0003472181,0.0029892358,0.00056776206,0.00019642006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056621193,0.000045403052,0.00006468685,0.000023136232,0.00004756515,0.0001073871,0.00011004173,0.6251862,0.000009174647,0.3731759,0.0010600818,0.00016480476],"study_design_scores_gemma":[0.00025838535,0.000035500172,0.00034889643,0.00006829958,0.000035548153,0.0000030757021,0.000034714478,0.7879586,0.00012370256,0.21063611,0.000067485074,0.0004296717],"about_ca_topic_score_codex":0.0004096724,"about_ca_topic_score_gemma":0.000024415938,"teacher_disagreement_score":0.95784473,"about_ca_system_score_codex":0.00032634728,"about_ca_system_score_gemma":0.00023924,"threshold_uncertainty_score":0.9997587},"labels":[],"label_agreement":null},{"id":"W4378765260","doi":"10.48550/arxiv.2305.17498","title":"A Model-Based Method for Minimizing CVaR and Beyond","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Flatiron Health","keywords":"CVAR; Subgradient method; Quantile; Mathematical optimization; Expected shortfall; Computer science; Measure (data warehouse); Risk measure; Convergence (economics); Mathematics; Risk management; Econometrics; Economics; Data mining","score_opus":0.13706898090744468,"score_gpt":0.23955181912164344,"score_spread":0.10248283821419876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378765260","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007020337,0.000018069639,0.996911,0.00023113722,0.00026161142,0.00062840636,0.00003582973,0.00087217864,0.00033973937],"genre_scores_gemma":[0.20598815,0.000019146093,0.79313844,0.00017709217,0.00002007572,0.000011010301,0.000018294044,0.000029307741,0.00059848774],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982516,0.00006775717,0.00018230749,0.0011267863,0.00007574519,0.00029576762],"domain_scores_gemma":[0.9982168,0.00041219417,0.0002038015,0.000842168,0.00018836252,0.00013664446],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039874695,0.00026581303,0.00030538943,0.0004626545,0.00015036612,0.00011911764,0.0010719281,0.00024647257,0.0000017560558],"category_scores_gemma":[0.00010491042,0.0003275299,0.0001519378,0.0004513635,0.000066702196,0.00018307153,0.0011684875,0.00023250139,0.000004138386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011340549,0.000019512618,0.00003210292,0.000065974404,0.000025346819,0.000013437049,0.00012433616,0.6921465,0.000015583486,0.30683312,0.00033091815,0.00038188187],"study_design_scores_gemma":[0.0003046925,0.00003804875,0.000009819426,0.00004574558,0.000046172885,8.497526e-7,0.00001614723,0.7777709,0.00017183425,0.22130999,0.000029987063,0.000255854],"about_ca_topic_score_codex":0.000026646527,"about_ca_topic_score_gemma":0.000006410196,"teacher_disagreement_score":0.20528612,"about_ca_system_score_codex":0.00010947586,"about_ca_system_score_gemma":0.00019225014,"threshold_uncertainty_score":0.9999177},"labels":[],"label_agreement":null},{"id":"W4380993202","doi":"10.48550/arxiv.2306.08289","title":"$\\textbf{A}^2\\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche; Compute Canada","keywords":"Asynchronous communication; Gossip; Asynchrony (computer programming); Computer science; Synchronization (alternating current); Distributed computing; Momentum (technical analysis); Network topology; Process (computing); Scaling; Adaptation (eye); Topology (electrical circuits); Channel (broadcasting); Computer network; Mathematics; Engineering; Physics; Electrical engineering","score_opus":0.10353557416400389,"score_gpt":0.21761545282920916,"score_spread":0.11407987866520528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380993202","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03084917,0.00015208656,0.9646,0.00015462108,0.00033358106,0.00063354365,0.000002873272,0.0021022973,0.0011717821],"genre_scores_gemma":[0.9461773,0.0008208621,0.05239174,0.000055727574,0.000022876824,0.000011479156,0.00007084374,0.000049639937,0.00039952926],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970432,0.00048386582,0.00048417994,0.0012382866,0.0001693303,0.0005811497],"domain_scores_gemma":[0.9969831,0.00042065172,0.00053370494,0.0016707993,0.00022966546,0.00016206513],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006513535,0.0004182226,0.00047656847,0.0007453152,0.0003205198,0.0003239329,0.0030037446,0.00040886033,0.000042470416],"category_scores_gemma":[0.00032143868,0.00055084785,0.00017783586,0.0014740826,0.00012322013,0.00059768965,0.0034469534,0.0012318423,0.00010908392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012585616,0.00007477411,0.0066709425,0.00004680474,0.0000386557,0.000089250956,0.0009889171,0.8721679,0.000011545456,0.11755326,0.00006546672,0.0022799387],"study_design_scores_gemma":[0.0005510642,0.000041846302,0.0028023992,0.00025945264,0.00002502025,0.000003937012,0.000121037425,0.945261,0.000056486428,0.050317716,0.000057102963,0.0005029435],"about_ca_topic_score_codex":0.0004653808,"about_ca_topic_score_gemma":0.0003446821,"teacher_disagreement_score":0.91532815,"about_ca_system_score_codex":0.000636228,"about_ca_system_score_gemma":0.00018323188,"threshold_uncertainty_score":0.9996943},"labels":[],"label_agreement":null},{"id":"W4381713175","doi":"10.48550/arxiv.2306.11922","title":"No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Samsung; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial neural network; Initialization; Maxima and minima; Stochastic optimization; Artificial intelligence; Stochastic neural network; Simple (philosophy); Deep neural networks; Mathematical optimization; Machine learning; Algorithm; Mathematics; Recurrent neural network","score_opus":0.06147547643506778,"score_gpt":0.19473069894888692,"score_spread":0.13325522251381913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381713175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025631364,0.000050410763,0.99481845,0.00006949279,0.000931615,0.00047209163,0.0000138782,0.0006464969,0.00043441818],"genre_scores_gemma":[0.98437214,0.0002122885,0.0146533055,0.00007861902,0.00008910434,0.000003692333,0.000055527526,0.000032297947,0.0005030499],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825656,0.00014694854,0.0003125307,0.0008025265,0.00014928727,0.00033214048],"domain_scores_gemma":[0.9973049,0.00030704943,0.0004832448,0.001432685,0.0003809874,0.000091126734],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034607365,0.00028252063,0.00030822714,0.00037185065,0.0001336641,0.00011267335,0.0023420437,0.0002714413,0.000029908453],"category_scores_gemma":[0.00015956092,0.00026753248,0.00020074227,0.0014769078,0.00014750905,0.0003045544,0.0024789174,0.00049560587,0.000013214548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073915357,0.000026781123,0.000627899,0.00003214609,0.000038015183,0.000021896742,0.000079370235,0.96412885,7.2225816e-7,0.034446754,0.0004466061,0.00014354766],"study_design_scores_gemma":[0.00015488591,0.00005024624,0.0003524245,0.00004706581,0.000040855026,0.0000018370672,0.000026353937,0.98899657,0.000010738832,0.010042416,0.000029027486,0.00024756364],"about_ca_topic_score_codex":0.00012014722,"about_ca_topic_score_gemma":0.000007789814,"teacher_disagreement_score":0.98180896,"about_ca_system_score_codex":0.00011591897,"about_ca_system_score_gemma":0.00007623207,"threshold_uncertainty_score":0.9999777},"labels":[],"label_agreement":null},{"id":"W4382203111","doi":"10.1609/aaai.v37i8.26186","title":"Fast Convergence in Learning Two-Layer Neural Networks with Separable Data","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Science Foundation","keywords":"Overfitting; Generalization; Convergence (economics); Separable space; Applied mathematics; Stability (learning theory); Mathematics; Artificial neural network; Gradient descent; Stochastic gradient descent; Exponential function; Exponential stability; Computer science; Mathematical optimization; Algorithm; Artificial intelligence; Mathematical analysis; Nonlinear system; Machine learning","score_opus":0.11363951927513236,"score_gpt":0.32079958893637917,"score_spread":0.2071600696612468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382203111","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08028902,0.000020079375,0.9104862,0.0022681223,0.00055034616,0.00083031337,0.000005200458,0.000716585,0.0048341053],"genre_scores_gemma":[0.99267256,0.000034103916,0.0068880464,0.00008712513,0.000033884025,0.000039149196,0.0000033271217,0.000017238437,0.00022453602],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99776906,0.000027790074,0.0004911568,0.00072328607,0.00050719135,0.00048150547],"domain_scores_gemma":[0.99847764,0.00014452703,0.00033112135,0.0005716543,0.00039432672,0.00008076166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076101726,0.00023119053,0.00025866364,0.0002565682,0.0001781479,0.00024136266,0.0035173784,0.00006904681,0.000033848333],"category_scores_gemma":[0.00037237722,0.00017501347,0.000039243067,0.0024488422,0.00023471485,0.00076600764,0.0010900652,0.0004573332,0.00004256096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009707829,0.000116772244,0.006169556,0.000034534227,0.000017979117,0.0000048623124,0.001545812,0.29201,0.0043244422,0.667458,0.0003618806,0.027859058],"study_design_scores_gemma":[0.000036374237,0.00014491353,0.00023683679,0.00016237255,0.000005416391,0.000005527491,0.00033099088,0.9607296,0.025806088,0.012325634,0.000014677048,0.00020159925],"about_ca_topic_score_codex":0.000068245456,"about_ca_topic_score_gemma":0.0000240238,"teacher_disagreement_score":0.91238356,"about_ca_system_score_codex":0.000036408917,"about_ca_system_score_gemma":0.00006983738,"threshold_uncertainty_score":0.7136842},"labels":[],"label_agreement":null},{"id":"W4383065888","doi":"10.1007/s11590-023-02033-5","title":"Detecting negative eigenvalues of exact and approximate Hessian matrices in optimization","year":2023,"lang":"en","type":"article","venue":"Optimization Letters","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Hessian matrix; Eigenvalues and eigenvectors; Block matrix; Mathematics; Curvature; Diagonal; Hessian equation; Quasi-Newton method; Mathematical optimization; Applied mathematics; Matrix (chemical analysis); Function (biology); Diagonal matrix; Algorithm; Computer science; Newton's method; Mathematical analysis; Geometry","score_opus":0.0137678340011307,"score_gpt":0.24152640173663803,"score_spread":0.22775856773550734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383065888","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066219196,0.000026548072,0.991278,0.000926509,0.00010474235,0.0003645846,0.0000027530853,0.00047243934,0.00020251317],"genre_scores_gemma":[0.16190837,0.00012678142,0.8376372,0.000204787,0.000016701331,0.000053334817,0.000016796761,0.000023330833,0.000012707735],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998549,0.00010724882,0.00041862222,0.00040473093,0.00025979092,0.0002606156],"domain_scores_gemma":[0.9990853,0.00020188499,0.0002915409,0.00028155764,0.000084234176,0.00005545621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004063559,0.00016845675,0.00021452307,0.00083912537,0.00010586474,0.00011842963,0.00033266254,0.00006932346,0.000012763198],"category_scores_gemma":[0.00021422279,0.00017775338,0.00003329957,0.0021518697,0.00007707149,0.00081762817,0.00016135235,0.0000913958,0.0000019728022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004702864,0.000013831774,0.0007164314,0.000028839364,0.0000071591758,0.0000033283127,0.0011213664,0.9955072,0.00024977795,0.0012847843,0.00005152463,0.0010110796],"study_design_scores_gemma":[0.00030553245,0.00003162112,0.00040734606,0.000069183276,0.0000054817383,0.000004123646,0.00011686089,0.99684644,0.001770395,0.0002705602,0.0000022795277,0.00017017405],"about_ca_topic_score_codex":0.000029641216,"about_ca_topic_score_gemma":0.0000012945248,"teacher_disagreement_score":0.15528645,"about_ca_system_score_codex":0.0000516812,"about_ca_system_score_gemma":0.00002306338,"threshold_uncertainty_score":0.7248573},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W4384575270","doi":"10.23952/asvao.5.2023.2.07","title":"Federated learning on Riemannian manifolds","year":2023,"lang":"en","type":"article","venue":"Applied Set-Valued Analysis and Optimization","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of California, Davis; Rice University; National Science Foundation","keywords":"Convergence (economics); Rate of convergence; Smart phone; Computer science; Riemannian geometry; Mathematics; Machine learning; Mathematical optimization; Pure mathematics; Economics; Telecommunications","score_opus":0.014354195525833155,"score_gpt":0.24663669805810476,"score_spread":0.23228250253227162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384575270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021569654,0.0000075826592,0.992574,0.00022587828,0.00004379777,0.00021243117,0.0000019754373,0.0011642724,0.0036131227],"genre_scores_gemma":[0.861644,0.00007457336,0.13720457,0.000227956,0.000029462106,0.000065192544,0.00030304058,0.000023984401,0.00042718026],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838185,0.00006939295,0.00031371834,0.00059831276,0.00035461521,0.00028209543],"domain_scores_gemma":[0.9992576,0.00008232453,0.00016903052,0.00028022812,0.00010536607,0.00010545511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041280466,0.00020471973,0.00028740993,0.00095843873,0.00046965716,0.0003890498,0.0002429579,0.0001084825,0.00003758228],"category_scores_gemma":[0.00005178366,0.00019893576,0.00008319887,0.0046732,0.000033388373,0.00018310851,0.00013354556,0.00013556716,0.00004009302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063820216,0.000017675928,0.0002238735,0.00000447661,0.00014628786,0.0000021396622,0.00026546992,0.94854015,0.00004899374,0.047856513,0.00017836323,0.0027096902],"study_design_scores_gemma":[0.0002372585,0.000056003126,0.0009525513,0.000006589392,0.00012770167,8.5475216e-7,0.000079006364,0.99724865,0.00035723363,0.0006700146,0.00004385196,0.00022029811],"about_ca_topic_score_codex":0.000018452756,"about_ca_topic_score_gemma":0.0000050724325,"teacher_disagreement_score":0.85948706,"about_ca_system_score_codex":0.000036928715,"about_ca_system_score_gemma":0.000018269431,"threshold_uncertainty_score":0.8112365},"labels":[],"label_agreement":null},{"id":"W4384807922","doi":"10.48550/arxiv.2307.09022","title":"Harnessing the mathematics of matrix decomposition to solve planted and maximum clique problem","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Organization for Women in Science for the Developing World; University of Waterloo; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Adjacency matrix; Mathematics; Clique; Matrix (chemical analysis); Mathematical optimization; Uniqueness; Clique problem; Maximum cut; Graph; Combinatorics; Discrete mathematics; Line graph","score_opus":0.06260207752066671,"score_gpt":0.23164305843127203,"score_spread":0.16904098091060532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384807922","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037755445,0.000012766662,0.9605449,0.000291446,0.00015408247,0.0006355532,0.00001345765,0.00039707517,0.00019526924],"genre_scores_gemma":[0.7262073,0.000054084045,0.27346027,0.000043771877,0.000016814885,0.000005286941,0.000011412584,0.000022896846,0.00017816601],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883443,0.00004920714,0.00025733327,0.00055927545,0.00009772186,0.00020204564],"domain_scores_gemma":[0.9984962,0.00021490143,0.00031990316,0.0007155722,0.00017033643,0.00008314079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032139616,0.00020427248,0.0002626868,0.00032514136,0.00012834797,0.00011356926,0.0010300364,0.00013592104,0.0000023340754],"category_scores_gemma":[0.00003837114,0.00019004615,0.000078588004,0.0005922567,0.00008511018,0.00015728561,0.0016875673,0.00024832156,0.000009472983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000242377,0.000104394756,0.0003302222,0.00042416583,0.00009374869,0.000074643336,0.0026644098,0.27892166,0.00036324954,0.7162528,0.0003805918,0.0003658828],"study_design_scores_gemma":[0.00015661486,0.000059351827,0.00031552743,0.0005003957,0.00005099465,0.000014772714,0.00012560489,0.7299448,0.000900764,0.26767173,0.000010868964,0.00024854974],"about_ca_topic_score_codex":0.000054606193,"about_ca_topic_score_gemma":0.000010452865,"teacher_disagreement_score":0.6884519,"about_ca_system_score_codex":0.00008015303,"about_ca_system_score_gemma":0.00007894035,"threshold_uncertainty_score":0.77498573},"labels":[],"label_agreement":null},{"id":"W4384817809","doi":"10.1007/s11222-023-10274-8","title":"Generalized linear models for massive data via doubly-sketching","year":2023,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generalized linear model; Computer science; Computation; Sequence (biology); Mathematical optimization; Linear model; Generalized linear mixed model; Least-squares function approximation; Algorithm; Poisson distribution; Data mining; Mathematics; Machine learning; Statistics; Estimator","score_opus":0.06817895037337768,"score_gpt":0.32345754913113184,"score_spread":0.25527859875775416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384817809","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046336686,0.000031019306,0.9981181,0.00020254983,0.00028046744,0.00025441806,0.00016219725,0.0004307822,0.000057085395],"genre_scores_gemma":[0.08111451,0.000016671605,0.91838926,0.00012082773,0.00008085483,0.000008120736,0.00021632791,0.000015144893,0.00003830054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988692,0.00002541312,0.00024087065,0.0004372728,0.00016041273,0.0002668401],"domain_scores_gemma":[0.99884665,0.0003781713,0.00011516356,0.00046948227,0.00011973189,0.0000707871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038591484,0.000118232376,0.00015364749,0.0001108316,0.00026449322,0.00015800823,0.0006465206,0.000034525438,8.7048284e-7],"category_scores_gemma":[0.00010822289,0.00011940243,0.000015235848,0.00027318156,0.000028557444,0.00019879716,0.0008775236,0.00006871303,0.000002697282],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004315863,0.000011654379,0.000012601563,0.00004731324,0.000022137176,0.000008309166,0.00063717575,0.106068954,0.00008579069,0.8273006,0.0046774936,0.061123647],"study_design_scores_gemma":[0.00023789464,0.000031071217,0.000017623308,0.00001663149,0.0000065819427,0.0000033417575,0.000011144306,0.83400714,0.00004181097,0.16540602,0.00009885131,0.000121867735],"about_ca_topic_score_codex":0.00002068245,"about_ca_topic_score_gemma":0.0000011948887,"teacher_disagreement_score":0.7279382,"about_ca_system_score_codex":0.000012471787,"about_ca_system_score_gemma":0.00003417406,"threshold_uncertainty_score":0.48690897},"labels":[],"label_agreement":null},{"id":"W4384945953","doi":"10.1109/iwcmc58020.2023.10183345","title":"Transmission Order Optimization of Coded Distributed Computing in Heterogeneous Wireless Multiple-Access Network","year":2023,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Latency (audio); Computer network; Distributed computing; Wireless; Transmission (telecommunications); Sorting; Operating system; Algorithm; Telecommunications","score_opus":0.023499891646876294,"score_gpt":0.2748933274247469,"score_spread":0.25139343577787066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384945953","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005976133,0.000013236127,0.99241436,0.00017020124,0.000111877554,0.00037034048,0.0000041819603,0.00084258826,0.00009708086],"genre_scores_gemma":[0.6763913,0.00001732274,0.32338884,0.000055396657,0.000013704486,0.000014089783,0.00009369984,0.000014025768,0.0000116283045],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985048,0.00008100033,0.00047026048,0.0003600478,0.0002541136,0.00032974218],"domain_scores_gemma":[0.9990748,0.0002386463,0.00014999528,0.00031825728,0.00015009705,0.000068203975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029391766,0.0001468714,0.00023471213,0.00022237735,0.00008035988,0.00007803311,0.0007400273,0.000085851374,0.000015665739],"category_scores_gemma":[0.000057128193,0.0001414044,0.000043050226,0.0030198302,0.00003584425,0.00027612725,0.00027005406,0.00008138748,0.0000019346126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008380804,0.000037965354,0.0015419233,0.00001746006,0.000005525647,0.0000056277713,0.00012204914,0.9907029,0.00006191462,0.0017823355,0.00022992303,0.005483959],"study_design_scores_gemma":[0.00042578919,0.000036730384,0.0006341681,0.00008208262,0.0000023990024,0.0000037755426,0.0000072859966,0.99553394,0.0027566445,0.00034175868,0.000025054267,0.00015038648],"about_ca_topic_score_codex":0.000037152902,"about_ca_topic_score_gemma":0.0000071452737,"teacher_disagreement_score":0.67041516,"about_ca_system_score_codex":0.00003778331,"about_ca_system_score_gemma":0.000038875758,"threshold_uncertainty_score":0.5766304},"labels":[],"label_agreement":null},{"id":"W4386553863","doi":"10.3934/math.20231321","title":"Sequential stochastic blackbox optimization with zeroth-order gradient estimators","year":2023,"lang":"en","type":"article","venue":"AIMS Mathematics","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Polytechnique Montréal; Group for Research in Decision Analysis","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Maxima and minima; Lipschitz continuity; Mathematical optimization; Sequence (biology); Rate of convergence; Convergence (economics); Stochastic optimization; Algorithm; Mathematics; Convex function; Estimator; Computer science; Regular polygon; Key (lock)","score_opus":0.019507950188851413,"score_gpt":0.24999332810834338,"score_spread":0.23048537791949197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386553863","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017094897,0.000008182451,0.9943425,0.00035207154,0.00025078398,0.00062286586,0.0000040340265,0.0020769655,0.0006330973],"genre_scores_gemma":[0.052557904,0.0000061669125,0.9467278,0.00010073002,0.000037093185,0.00015013745,0.000026731768,0.00005881392,0.00033461186],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806273,0.000031093838,0.0004111558,0.00045217064,0.0005889743,0.00045384897],"domain_scores_gemma":[0.99837655,0.0001809928,0.0002363577,0.00080181594,0.0002577023,0.00014659486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030945233,0.00027959075,0.00027679844,0.0003895418,0.00018808557,0.00021606749,0.0007377027,0.000089160465,0.00003781858],"category_scores_gemma":[0.00020019512,0.00023812709,0.00005638623,0.0019209374,0.000112798094,0.00042357435,0.00024694792,0.00013099532,0.00017204012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003015463,0.000097117634,0.000012044405,0.000052191866,0.000034163175,0.000015377416,0.0018746238,0.83203614,0.000021468797,0.16447978,0.0010134046,0.00036068543],"study_design_scores_gemma":[0.0003120311,0.0001414066,0.000011357732,0.000103416605,0.000027219192,0.000055335073,0.000092249255,0.98266196,0.00025748354,0.01601986,0.000020945778,0.00029673922],"about_ca_topic_score_codex":0.0000043611212,"about_ca_topic_score_gemma":0.0000011508876,"teacher_disagreement_score":0.15062582,"about_ca_system_score_codex":0.000075475684,"about_ca_system_score_gemma":0.00009587026,"threshold_uncertainty_score":0.9710541},"labels":[],"label_agreement":null},{"id":"W4386811880","doi":"10.1007/978-3-031-43421-1_18","title":"Fast Convergence of Random Reshuffling Under Over-Parameterization and the Polyak-Łojasiewicz Condition","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; University of British Columbia","funders":"","keywords":"Parameterized complexity; Convergence (economics); Permutation (music); Computer science; Stochastic gradient descent; Algorithm; Mathematics; Applied mathematics; Artificial intelligence; Artificial neural network","score_opus":0.01717722583237915,"score_gpt":0.2518321152477164,"score_spread":0.23465488941533727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386811880","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013136538,0.0002027605,0.9966243,0.0006159873,0.0011589582,0.00069221563,0.000009196666,0.0002238087,0.00034141372],"genre_scores_gemma":[0.54932123,0.0004875474,0.4476366,0.0017335559,0.00024130152,0.000058265763,0.00002803606,0.00007947858,0.00041395155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971768,0.00007505813,0.0006308027,0.00093897345,0.0008265059,0.00035181837],"domain_scores_gemma":[0.99673814,0.0014926757,0.00052399177,0.0008947831,0.00026946474,0.00008095171],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001211708,0.00035462563,0.0005287242,0.0007112667,0.00023358829,0.00028582418,0.0015871513,0.0002130927,0.000011075316],"category_scores_gemma":[0.0002956047,0.00027542654,0.00009775631,0.0008548772,0.0017348904,0.00044008307,0.0008752075,0.000376362,0.000005154505],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008067068,0.00002004919,0.000045754943,0.000090852045,0.00003483312,0.000011652124,0.0019116601,0.17651972,0.00042920504,0.7612475,0.000023372417,0.05958472],"study_design_scores_gemma":[0.00085779454,0.0000741503,0.000103693965,0.00033915314,0.000013560865,0.000019880394,5.2892824e-7,0.726687,0.0014308306,0.27019867,0.000013390385,0.00026133918],"about_ca_topic_score_codex":0.00003303121,"about_ca_topic_score_gemma":0.000016286283,"teacher_disagreement_score":0.55016726,"about_ca_system_score_codex":0.00009742312,"about_ca_system_score_gemma":0.00021313352,"threshold_uncertainty_score":0.9999698},"labels":[],"label_agreement":null},{"id":"W4386988712","doi":"10.1007/s11081-023-09836-6","title":"A fast non-monotone line search for stochastic gradient descent","year":2023,"lang":"en","type":"article","venue":"Optimization and Engineering","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Stochastic gradient descent; Monotone polygon; Line search; Descent direction; Convergence (economics); Mathematical optimization; Descent (aeronautics); Mathematics; Line (geometry); Interpolation (computer graphics); Gradient descent; Computer science; Regular polygon; Applied mathematics; Algorithm; Artificial intelligence; Path (computing)","score_opus":0.017242471805317332,"score_gpt":0.2414483519281693,"score_spread":0.22420588012285197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386988712","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009789275,0.000018477043,0.9972527,0.00027335278,0.00022180165,0.00045595,0.000004353349,0.0007677964,0.000026646376],"genre_scores_gemma":[0.29940045,0.00005538368,0.70003945,0.000045560275,0.00005669493,0.00021114066,0.000043313306,0.000034084536,0.00011393641],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991031,0.00000584892,0.00018060033,0.00028314823,0.00014372097,0.00028353345],"domain_scores_gemma":[0.9994718,0.00008053849,0.000029829163,0.00020365596,0.00009790824,0.00011627854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018904083,0.00013229808,0.00012785649,0.00033749794,0.00010191059,0.00011035587,0.00019970936,0.000048988026,0.000003307273],"category_scores_gemma":[0.00005841871,0.00014007858,0.000032532604,0.00070313574,0.000012210519,0.00019454892,0.00011778481,0.00006321605,0.0000047004546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022678882,0.000012167555,0.0000055145774,0.000027510736,0.0000072176886,8.7892533e-7,0.00030214823,0.99070734,0.00017693614,0.0074064913,0.0000731142,0.0012784307],"study_design_scores_gemma":[0.00030241444,0.00007245153,0.000076668504,0.000039949453,0.000004652187,0.0000052661926,0.000016207694,0.99863446,0.00062421424,0.000039197006,0.000034862176,0.00014967112],"about_ca_topic_score_codex":0.0000023827492,"about_ca_topic_score_gemma":1.9404334e-7,"teacher_disagreement_score":0.29842153,"about_ca_system_score_codex":0.000038928873,"about_ca_system_score_gemma":0.000018483111,"threshold_uncertainty_score":0.5712239},"labels":[],"label_agreement":null},{"id":"W4387385575","doi":"10.1109/tcomm.2023.3322174","title":"A Family of Binary Locally Repairable Codes for Coded Distributed Computing","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Communications","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Computer science; Block code; Decoding methods; Linear code; Matrix multiplication; Computational complexity theory; Concatenated error correction code; Coding (social sciences); Theoretical computer science; Multiplication (music); List decoding; Binary number; Algorithm; Mathematics; Arithmetic","score_opus":0.05301074733122166,"score_gpt":0.30565334862846394,"score_spread":0.25264260129724225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387385575","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00076445885,0.00004001266,0.99532634,0.0012088827,0.00017529371,0.00060856977,0.00022823698,0.0014119854,0.00023621498],"genre_scores_gemma":[0.6849274,0.000100944664,0.314533,0.00007628245,0.000004097689,0.00018931694,0.000061096805,0.000015455349,0.00009242749],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873334,0.0001086813,0.0004525015,0.00027063297,0.00019705035,0.00023780462],"domain_scores_gemma":[0.9962667,0.0011379593,0.00016555775,0.0020157287,0.00034704228,0.00006700188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000420861,0.00013884756,0.00021583434,0.00035159886,0.0005512452,0.000047922866,0.0016641757,0.0000770982,0.0000028717689],"category_scores_gemma":[0.000040908842,0.00015326933,0.00014250934,0.0016608738,0.00016875372,0.00019677487,0.000026981817,0.0001713832,0.000015070443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007843129,0.001715869,0.000033246466,0.0001397056,0.00027359673,0.0000022966237,0.00214251,0.822473,0.018440107,0.1159784,0.009311378,0.02941147],"study_design_scores_gemma":[0.00036948727,0.00019610547,0.00015488866,0.0000861102,0.000022226495,0.0000026747985,0.000101902944,0.98982745,0.006084588,0.002449765,0.0005505819,0.00015420587],"about_ca_topic_score_codex":0.000042399446,"about_ca_topic_score_gemma":0.000014177764,"teacher_disagreement_score":0.6841629,"about_ca_system_score_codex":0.00006355524,"about_ca_system_score_gemma":0.00010318665,"threshold_uncertainty_score":0.6250141},"labels":[],"label_agreement":null},{"id":"W4387544216","doi":"10.1109/icdcs57875.2023.00072","title":"Distributed Online Min-Max Load Balancing with Risk-Averse Assistance","year":2023,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Workload; Computer science; Regret; Distributed computing; Idle; Load balancing (electrical power); Distributed algorithm; Pointwise; Process (computing); Range (aeronautics); Real-time computing; Machine learning; Operating system","score_opus":0.011125117895567482,"score_gpt":0.23262006939615826,"score_spread":0.2214949515005908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387544216","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008928022,0.000009915955,0.9869928,0.0004981423,0.00013152385,0.0001693955,0.00005870119,0.0022549934,0.0009565584],"genre_scores_gemma":[0.37868932,0.000023182132,0.61939764,0.00021089631,0.000038741775,0.000031958487,0.0000935904,0.000020141351,0.0014945216],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864185,0.000031248997,0.0001933088,0.0004070694,0.00041587435,0.0003106586],"domain_scores_gemma":[0.9988805,0.0001334036,0.00012162968,0.0005729622,0.00019101535,0.00010046509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022666532,0.00014592991,0.00014968227,0.00011017704,0.00012305567,0.000096030315,0.00056300306,0.000045647095,0.00003076228],"category_scores_gemma":[0.00018174874,0.00011645244,0.000035706755,0.0015099475,0.00004583783,0.0002753328,0.00017391086,0.00011574255,0.00008480337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022644771,0.0012868817,0.103529796,0.00020209815,0.0004367753,0.0009190828,0.0045403824,0.13521169,0.0017972942,0.39436382,0.29179183,0.06569389],"study_design_scores_gemma":[0.0006179797,0.00016214713,0.023347786,0.00007263424,0.000014783797,0.000016790756,0.00013431904,0.9687051,0.0014251702,0.0022598505,0.0028523572,0.00039104288],"about_ca_topic_score_codex":0.000061553474,"about_ca_topic_score_gemma":0.00008780795,"teacher_disagreement_score":0.8334935,"about_ca_system_score_codex":0.000120542274,"about_ca_system_score_gemma":0.00009594788,"threshold_uncertainty_score":0.47487924},"labels":[],"label_agreement":null},{"id":"W4387838993","doi":"10.48550/arxiv.2310.12771","title":"Stochastic Average Gradient : A Simple Empirical Investigation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Université de Montréal; Compute Canada","keywords":"Rate of convergence; Convergence (economics); Mathematical optimization; Computer science; Simple (philosophy); Artificial neural network; Convex function; Gradient method; Function (biology); Stochastic approximation; Mathematics; Algorithm; Applied mathematics; Regular polygon; Artificial intelligence; Key (lock)","score_opus":0.1405757196807451,"score_gpt":0.2286035112568162,"score_spread":0.0880277915760711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387838993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046774752,0.000010948459,0.94942063,0.000314979,0.000714164,0.00057395565,0.00002191976,0.0019818465,0.0001867813],"genre_scores_gemma":[0.9891025,0.00001744458,0.009691651,0.00019666411,0.00006737438,0.000009191525,0.00008061089,0.000040683946,0.0007939099],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973774,0.0001635193,0.00032509412,0.0014660645,0.0001984887,0.00046941324],"domain_scores_gemma":[0.99741775,0.0002546951,0.00032520108,0.0014637563,0.00022859639,0.00030998222],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032655825,0.00039918657,0.00037005835,0.0006591471,0.00020475428,0.00017952916,0.0019034036,0.00033479117,0.000018825158],"category_scores_gemma":[0.00021437147,0.00048123393,0.0002124877,0.0013262805,0.0001630416,0.00033797152,0.0025649944,0.0005969949,0.00017475255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007312159,0.00004563365,0.0009913594,0.000039110968,0.0000476426,0.00012576274,0.0005688835,0.860387,0.000007510837,0.13546549,0.0022168816,0.00009735926],"study_design_scores_gemma":[0.00019172445,0.000053914286,0.0009882395,0.00006232333,0.000030186822,0.000004036901,0.0000180697,0.71332335,0.00004007539,0.2848944,0.00003552969,0.0003581648],"about_ca_topic_score_codex":0.00010988355,"about_ca_topic_score_gemma":0.000024341587,"teacher_disagreement_score":0.94232774,"about_ca_system_score_codex":0.00041239997,"about_ca_system_score_gemma":0.00027917678,"threshold_uncertainty_score":0.9997639},"labels":[],"label_agreement":null},{"id":"W4387869731","doi":"10.1109/icc45041.2023.10279174","title":"Coded Reactive Stragglers Mitigation in Distributed Computing Systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Redundancy (engineering); Computer science; Computation; Distributed computing; Task (project management); Real-time computing; Parallel computing; Algorithm; Operating system; Engineering","score_opus":0.019317517896542732,"score_gpt":0.2606849335030329,"score_spread":0.24136741560649017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387869731","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020001583,0.0000042626366,0.9766589,0.00032716474,0.00023941809,0.00028700652,0.0000054502966,0.0013727029,0.001103552],"genre_scores_gemma":[0.9731968,0.0000014016015,0.02661396,0.000033656343,0.000013502045,0.000018954252,0.000054159456,0.0000060406264,0.00006152119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999025,0.00005236373,0.00023589483,0.00026742968,0.00020359909,0.000215749],"domain_scores_gemma":[0.9993852,0.00017003759,0.00008234517,0.00023395693,0.000081283564,0.000047197507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029820148,0.00008639301,0.00011673151,0.00024448775,0.000054431453,0.000111154135,0.0003231843,0.00004806814,0.0000019787951],"category_scores_gemma":[0.0000968709,0.000086346176,0.000021277141,0.0014587763,0.00002237401,0.00027074167,0.000109067965,0.00007835179,0.00002863498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005361651,0.000071400835,0.0036967776,0.00003490551,0.000021521788,0.00004093785,0.0021544427,0.26663324,0.0015024523,0.716252,0.005781226,0.0038057256],"study_design_scores_gemma":[0.00016823436,0.000021474636,0.005285676,0.000042530406,9.3325644e-7,0.000004031686,0.00020556067,0.99097383,0.0011758518,0.0019917428,0.000027333419,0.00010281534],"about_ca_topic_score_codex":0.00009140566,"about_ca_topic_score_gemma":0.000005189888,"teacher_disagreement_score":0.9531952,"about_ca_system_score_codex":0.00011635714,"about_ca_system_score_gemma":0.000029784496,"threshold_uncertainty_score":0.35210946},"labels":[],"label_agreement":null},{"id":"W4388685739","doi":"10.48550/arxiv.2311.07540","title":"Finding planted cliques using gradient descent","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; National Science Foundation","keywords":"Combinatorics; Clique; Markov chain Monte Carlo; Mathematics; Omega; Markov chain; Vertex (graph theory); Time complexity; Vertex cover; Discrete mathematics; Gradient descent; Graph; Monte Carlo method; Computer science; Statistics","score_opus":0.22347729603507488,"score_gpt":0.23093153819082726,"score_spread":0.007454242155752383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388685739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06895766,0.000021985794,0.9273639,0.000056700403,0.001080493,0.00042554687,0.000020278912,0.0018327992,0.0002406683],"genre_scores_gemma":[0.94956,0.00013440072,0.04967761,0.000058774836,0.0000593199,0.0000021729093,0.000031930213,0.000040746967,0.00043504543],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769354,0.00012724297,0.00029604175,0.0012509715,0.00014690126,0.0004853251],"domain_scores_gemma":[0.99797887,0.00013436354,0.00035760005,0.0011591476,0.00018296836,0.00018707721],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030710665,0.0003706364,0.00035844764,0.00074116106,0.0002214999,0.00018381349,0.0018703646,0.00029590869,0.000009757729],"category_scores_gemma":[0.00007926897,0.00045026198,0.0002051752,0.0009553424,0.00009482726,0.0002990178,0.0026812372,0.0005023371,0.000044932258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018442168,0.00009655715,0.0027116118,0.000099542856,0.00011423456,0.00054349424,0.00047789916,0.64449793,0.00006587161,0.35061637,0.00056115695,0.00019685575],"study_design_scores_gemma":[0.0001900874,0.000041399344,0.0004092323,0.00033145177,0.000048010028,0.000010484666,0.000035218083,0.94743896,0.0004634355,0.05052639,0.000041198327,0.00046413016],"about_ca_topic_score_codex":0.00020083142,"about_ca_topic_score_gemma":0.00001673148,"teacher_disagreement_score":0.88060236,"about_ca_system_score_codex":0.0005739997,"about_ca_system_score_gemma":0.000184524,"threshold_uncertainty_score":0.9997949},"labels":[],"label_agreement":null},{"id":"W4388706357","doi":"10.1088/1742-5468/ad01b2","title":"Two-layer neural network on infinite-dimensional data: global optimization guarantee in the mean-field regime <sup>*</sup>","year":2023,"lang":"en","type":"article","venue":"Journal of Statistical Mechanics Theory and Experiment","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"","keywords":"Artificial neural network; Computer science; Convergence (economics); Applied mathematics; Optimization problem; Mathematical optimization; Global optimization; Mean field theory; Mathematics; Algorithm; Artificial intelligence","score_opus":0.03427880606703779,"score_gpt":0.3151299462813089,"score_spread":0.28085114021427116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388706357","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002294686,0.00014217883,0.9959894,0.0008691882,0.00033436023,0.00019075438,0.000018185163,0.000045880315,0.0001154135],"genre_scores_gemma":[0.73359793,0.00008380952,0.26384383,0.0022262845,0.00019149474,0.000014698477,0.000021337284,0.00001364507,0.000006942285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978263,0.00047568555,0.00053279585,0.0002918932,0.00057707133,0.00029629443],"domain_scores_gemma":[0.99734116,0.0018154889,0.0002046085,0.00045566953,0.000097813136,0.00008528511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026157044,0.00017324026,0.00024318168,0.00011511194,0.00014005856,0.0001379537,0.0008474614,0.000066310065,0.00002604317],"category_scores_gemma":[0.000560692,0.00012038852,0.00003703094,0.0005188302,0.000035828267,0.00033754835,0.00034019546,0.00026889236,0.0000051588286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017410312,0.00006121109,0.0000018293246,0.0000024466383,0.000014266875,0.0000670394,0.00044508695,0.31197798,0.000011386146,0.6842934,0.0015016294,0.0014496116],"study_design_scores_gemma":[0.00042803452,0.00056557165,0.0000052202736,0.0000490921,0.000011675601,0.000090453315,0.00024191769,0.7115139,0.00008882725,0.28687865,0.00003069956,0.00009598369],"about_ca_topic_score_codex":0.000003352235,"about_ca_topic_score_gemma":4.1882194e-7,"teacher_disagreement_score":0.73214555,"about_ca_system_score_codex":0.00005072103,"about_ca_system_score_gemma":0.00005140748,"threshold_uncertainty_score":0.49093014},"labels":[],"label_agreement":null},{"id":"W4389943643","doi":"10.1007/s00453-023-01195-z","title":"Stochastic Variance Reduction for DR-Submodular Maximization","year":2023,"lang":"en","type":"article","venue":"Algorithmica","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Monotone polygon; Mathematics; Combinatorics; Approximation algorithm; Submodular set function; Reduction (mathematics); Discrete mathematics; Algorithm; Applied mathematics; Geometry","score_opus":0.02096022274690139,"score_gpt":0.26192232649568314,"score_spread":0.24096210374878174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389943643","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007881205,0.000016994969,0.9950866,0.0015215048,0.0009492931,0.00061818754,0.000008807954,0.0016165613,0.00010323359],"genre_scores_gemma":[0.055693023,0.000009778308,0.94197893,0.00011956907,0.00030612678,0.0005827385,0.00009751761,0.000042573673,0.0011697225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873024,0.000027132071,0.00023634979,0.00046085264,0.00023411514,0.00031129847],"domain_scores_gemma":[0.99904764,0.000091709146,0.000107027685,0.00049396453,0.00018754628,0.00007212753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028357128,0.00013677905,0.00013830475,0.00026225985,0.00018071542,0.00010191056,0.000518703,0.000079031524,0.0000067471137],"category_scores_gemma":[0.00018682919,0.00014902168,0.00006048606,0.0011483202,0.000036542213,0.00039391784,0.000113729206,0.000068205205,0.000067135894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002055018,0.00012707901,0.0000038358235,0.0000535315,0.00006682641,0.000007168196,0.001044231,0.14207113,0.0022641085,0.6683641,0.025095176,0.16088226],"study_design_scores_gemma":[0.0002456323,0.00007646608,0.000040202634,0.00001669979,0.000008466205,0.000017549433,0.000012489184,0.9385297,0.0022051907,0.057961106,0.00071672513,0.00016982545],"about_ca_topic_score_codex":0.0000045342786,"about_ca_topic_score_gemma":8.972862e-8,"teacher_disagreement_score":0.79645854,"about_ca_system_score_codex":0.00006250987,"about_ca_system_score_gemma":0.000048102895,"threshold_uncertainty_score":0.6076928},"labels":[],"label_agreement":null},{"id":"W4389986737","doi":"10.1137/1.9781611977806.ch28","title":"Chapter 28: Subgradient Methods","year":2023,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Subgradient method; Computer science; Machine learning","score_opus":0.11198712313478015,"score_gpt":0.2978296290613603,"score_spread":0.18584250592658014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389986737","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000015892123,0.000029504328,0.767551,0.00011504522,0.00041746127,0.0016132316,0.000045447086,0.0006699233,0.22955678],"genre_scores_gemma":[0.000023925157,0.000034048353,0.82405174,0.0001483852,0.00033200474,0.00033230323,0.000025004902,0.00012609942,0.17492652],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978765,0.0000045887386,0.00065885385,0.00070220896,0.00036036593,0.00039744575],"domain_scores_gemma":[0.99803346,0.0005420882,0.0004985719,0.00065122644,0.00010500097,0.00016965093],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00089073746,0.0005238846,0.00069368014,0.000117591335,0.00028196943,0.00019406644,0.0006581479,0.0008079996,0.000012151494],"category_scores_gemma":[0.000039140476,0.0004848743,0.0005601998,0.00003996053,0.00021630432,0.00004120638,0.00051252084,0.00048611802,0.000015239723],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003585969,0.000009397396,1.0325169e-8,0.000090557565,0.00015308773,4.387531e-7,0.0011797099,0.000003719767,0.00005617593,0.9526296,0.002806386,0.04306731],"study_design_scores_gemma":[0.00068487733,0.00010825933,2.1321688e-8,0.00018766745,0.00015483293,0.0000062495146,0.00006018203,0.0061181244,0.0010558815,0.9477555,0.04326235,0.0006060564],"about_ca_topic_score_codex":9.850077e-7,"about_ca_topic_score_gemma":3.46411e-7,"teacher_disagreement_score":0.0565007,"about_ca_system_score_codex":0.00006256791,"about_ca_system_score_gemma":0.000074005686,"threshold_uncertainty_score":0.99976027},"labels":[],"label_agreement":null},{"id":"W4390357323","doi":"10.1109/tcomm.2023.3347772","title":"Coded Reactive Stragglers Mitigation in Distributed Computing Systems","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Communications","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Redundancy (engineering); Computer science; Erasure; Erasure code; Exploit; Computation; Distributed computing; Real-time computing; Decoding methods; Algorithm; Computer security; Operating system","score_opus":0.040177227710613383,"score_gpt":0.29294832556789424,"score_spread":0.25277109785728086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390357323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021120189,0.00002058979,0.9932513,0.0017236662,0.00034114005,0.0005305542,0.000067268054,0.0013214069,0.0006320224],"genre_scores_gemma":[0.97211283,0.00007082982,0.027419075,0.000047419413,0.000006725159,0.00018906676,0.00007337468,0.000015727323,0.000064955864],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853724,0.00023159274,0.00041336005,0.00030599308,0.00024820297,0.0002635944],"domain_scores_gemma":[0.9972974,0.0007034684,0.00013734358,0.0016301759,0.00015419158,0.00007741873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037116776,0.00015064843,0.00017500894,0.0005794682,0.00041514824,0.00013564051,0.0013355024,0.00009168633,0.0000030058586],"category_scores_gemma":[0.000026788694,0.00017462611,0.00006502365,0.0024809164,0.00010748557,0.00038981056,0.0000174046,0.00035997,0.000066172746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010667256,0.00050054345,0.000076428674,0.000022553937,0.000061199724,0.000005386858,0.0031040641,0.913403,0.0013023311,0.06997517,0.0007773103,0.010761386],"study_design_scores_gemma":[0.00030319137,0.000044533594,0.0006328541,0.000103539285,0.000008082906,0.0000069113826,0.00033869763,0.9951619,0.0017417591,0.0013196998,0.00015851416,0.00018032627],"about_ca_topic_score_codex":0.00013465308,"about_ca_topic_score_gemma":0.000065422726,"teacher_disagreement_score":0.9700008,"about_ca_system_score_codex":0.00025403788,"about_ca_system_score_gemma":0.00007269794,"threshold_uncertainty_score":0.7121046},"labels":[],"label_agreement":null},{"id":"W4391019797","doi":"10.1109/mnet.2024.3355922","title":"(Com)<sup>2</sup>Net: A Novel Communication and Computation Integrated Network Architecture","year":2024,"lang":"en","type":"article","venue":"IEEE Network","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Calgary","funders":"National Key Research and Development Program of China; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Cloud computing; Software deployment; Computation; The Internet; Distributed computing; Domain (mathematical analysis); Artificial intelligence; World Wide Web; Algorithm; Software engineering; Operating system","score_opus":0.01848259349535607,"score_gpt":0.2557321649710994,"score_spread":0.23724957147574333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391019797","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079079974,0.0020430847,0.9925401,0.0011363236,0.0010307459,0.0003974049,0.0000040946647,0.00136451,0.00069290225],"genre_scores_gemma":[0.36066347,0.0001479745,0.6366579,0.00084129715,0.0012449654,0.00009831322,0.00007409323,0.000056332727,0.00021566897],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984543,0.00013083295,0.00033791727,0.00047961876,0.00022058071,0.00037680002],"domain_scores_gemma":[0.9987166,0.00047459154,0.00008823444,0.0005386925,0.00007661248,0.00010525566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037909468,0.00023552102,0.00021668084,0.00013258931,0.00024195528,0.00049779954,0.0006097934,0.00013616311,0.000004004135],"category_scores_gemma":[0.000021520324,0.00021906076,0.000057375073,0.0013267315,0.0001067653,0.00029330805,0.00019400044,0.00040228065,0.000011916731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009687267,0.000020954276,0.000049585342,0.000019158142,0.00003548085,0.0000034300285,0.00077171845,0.92005944,0.000016304484,0.026999503,0.028599212,0.023415541],"study_design_scores_gemma":[0.0001578841,0.000069022215,0.000103760765,0.00032742528,0.000015847472,0.00004853794,0.000010194446,0.94273657,0.000018159064,0.047115214,0.009176633,0.00022075674],"about_ca_topic_score_codex":0.000015251779,"about_ca_topic_score_gemma":0.000005283731,"teacher_disagreement_score":0.35987267,"about_ca_system_score_codex":0.000048482776,"about_ca_system_score_gemma":0.00005427208,"threshold_uncertainty_score":0.8933039},"labels":[],"label_agreement":null},{"id":"W4394896940","doi":"10.1109/tpds.2024.3390109","title":"Sampling-Based Multi-Job Placement for Heterogeneous Deep Learning Clusters","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Parallel and Distributed Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of Toronto; Memorial University of Newfoundland","funders":"British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Computer science; Workload; Job scheduler; Scheduling (production processes); Distributed computing; Artificial intelligence; Machine learning; Latency (audio); Mathematical optimization; Computer network","score_opus":0.03431295490472693,"score_gpt":0.2792646518185682,"score_spread":0.24495169691384125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394896940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022691852,0.00047004982,0.99631923,0.00014780858,0.0009976004,0.0007905937,0.00013375476,0.00090401364,0.000010041174],"genre_scores_gemma":[0.95293236,0.000020892669,0.046186738,0.000044870805,0.000022219429,0.00059197046,0.000043309996,0.000020757203,0.00013690037],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986138,0.0000638906,0.00033110357,0.00049693655,0.00020051571,0.00029380288],"domain_scores_gemma":[0.99919313,0.00028543928,0.000058784222,0.00024800823,0.000080815815,0.0001338411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020611947,0.00021519828,0.00020754352,0.00018963742,0.00031060554,0.00038904836,0.00022297105,0.00010415736,0.000004092601],"category_scores_gemma":[0.000008892752,0.00020114704,0.00011736493,0.0002745624,0.000038434253,0.00014516935,0.000002870902,0.0001574462,0.000009362842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030065332,0.000059296854,0.000003939506,0.00012059155,0.00004998829,0.0000046921764,0.00013382395,0.9969512,0.000054434528,0.000571817,0.00006590482,0.0019542219],"study_design_scores_gemma":[0.00063935213,0.00027936525,0.0000040726827,0.00012531623,0.000029429762,0.000029489542,0.000058336638,0.99730724,0.0001786484,0.000037723432,0.0010897503,0.00022126206],"about_ca_topic_score_codex":0.000023150316,"about_ca_topic_score_gemma":0.000007894461,"teacher_disagreement_score":0.95270544,"about_ca_system_score_codex":0.00011369458,"about_ca_system_score_gemma":0.00004185782,"threshold_uncertainty_score":0.8202538},"labels":[],"label_agreement":null},{"id":"W4396220729","doi":"10.1007/s10107-024-02078-z","title":"Sample complexity analysis for adaptive optimization algorithms with stochastic oracles","year":2024,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Algorithm; Sample complexity; Stochastic optimization; Numerical analysis; Mathematical optimization; Sample (material); Computer science; Artificial intelligence","score_opus":0.05945494826338559,"score_gpt":0.29939278713259126,"score_spread":0.23993783886920567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396220729","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019983523,0.00005951477,0.9971539,0.00026617208,0.000052435098,0.0009942376,0.0000163243,0.0013577628,0.00007967464],"genre_scores_gemma":[0.08652066,4.5534412e-7,0.9129134,0.000024686902,0.000031339965,0.0004270174,0.000033830715,0.000025388765,0.000023227945],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835825,0.000033234657,0.0003420176,0.000542572,0.00036207182,0.00036187095],"domain_scores_gemma":[0.9982788,0.00093383854,0.00008368064,0.00039083246,0.00019266695,0.00012019681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040161403,0.00021393017,0.00033244718,0.00036793374,0.00017181272,0.000583917,0.0004261794,0.000064689135,0.00003363196],"category_scores_gemma":[0.00025275763,0.00016666659,0.00015241682,0.001793147,0.00014697127,0.00038899606,0.00011398692,0.00010927276,0.000007793608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009245903,0.00010660039,0.0000039993683,0.00010036986,0.00030411885,0.0000035332628,0.00062344765,0.20162135,9.914636e-7,0.7683552,0.000018961146,0.028852211],"study_design_scores_gemma":[0.00010907033,0.00022438398,0.000002911733,0.000088762354,0.00022558773,0.000009409894,0.000060439255,0.8969505,0.000026466852,0.10206347,0.000038942133,0.00020006497],"about_ca_topic_score_codex":0.000009676128,"about_ca_topic_score_gemma":0.0000025556808,"teacher_disagreement_score":0.6953291,"about_ca_system_score_codex":0.00007753536,"about_ca_system_score_gemma":0.000049740436,"threshold_uncertainty_score":0.6796466},"labels":[],"label_agreement":null},{"id":"W4399911298","doi":"10.48550/arxiv.2406.13888","title":"Open Problem: Anytime Convergence Rate of Gradient Descent","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Azrieli Foundation","keywords":"Convergence (economics); Rate of convergence; Gradient descent; Descent (aeronautics); Mathematical optimization; Computer science; Applied mathematics; Mathematics; Economics; Artificial intelligence; Physics; Telecommunications; Meteorology","score_opus":0.08431971796349359,"score_gpt":0.20820740434471635,"score_spread":0.12388768638122276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399911298","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017261332,0.0000962408,0.9755957,0.0002089942,0.00082921097,0.0012164952,0.000028846214,0.0004770739,0.0042861025],"genre_scores_gemma":[0.9649047,0.00015797469,0.03325689,0.00006994054,0.000018219382,0.0000075494877,0.000013340499,0.000025811767,0.0015455787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769336,0.00014201282,0.00036844207,0.0013518998,0.00010213413,0.00034215112],"domain_scores_gemma":[0.9975996,0.00007515017,0.0003922391,0.0014433996,0.00030967442,0.00017994545],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00049170974,0.0003442049,0.0004374548,0.00040576005,0.00008180348,0.00022168693,0.004762532,0.00020680037,0.000057086767],"category_scores_gemma":[0.000035994162,0.00038172223,0.00018299815,0.0010392535,0.00016474274,0.000316426,0.011842521,0.00045968607,0.0000872713],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017873472,0.000118867916,0.00022682828,0.00022470756,0.000097542514,0.00012420712,0.00032238176,0.12389249,0.000061581966,0.87320155,0.0014781588,0.00023383416],"study_design_scores_gemma":[0.00022120857,0.00009587777,0.0000970093,0.0003962589,0.00007088852,0.000004543403,0.000017777187,0.62593,0.0017400293,0.37085488,0.00018759954,0.00038392007],"about_ca_topic_score_codex":0.00030672847,"about_ca_topic_score_gemma":0.000012424728,"teacher_disagreement_score":0.94764334,"about_ca_system_score_codex":0.0002622906,"about_ca_system_score_gemma":0.00039857088,"threshold_uncertainty_score":0.99986345},"labels":[],"label_agreement":null},{"id":"W4401024942","doi":"10.24963/ijcai.2024/630","title":"SIFAR: A Simple Faster Accelerated Variance-Reduced Gradient Method","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Renmin University of China; National Natural Science Foundation of China; University of Oxford; Royal Society; Institute for Catastrophic Loss Reduction","keywords":"Minimax; Generalization; Mathematical optimization; Mathematics; Saddle point; Stochastic gradient descent; Applied mathematics; Generalization error; Dimension (graph theory); Computer science; Upper and lower bounds; Combinatorics; Artificial intelligence; Artificial neural network; Mathematical analysis","score_opus":0.05201765390773348,"score_gpt":0.33036379421198414,"score_spread":0.27834614030425064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401024942","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022125899,0.00015877694,0.97605634,0.0018725407,0.002489207,0.0010657605,0.000028068176,0.003541411,0.014566665],"genre_scores_gemma":[0.051197883,0.00001988516,0.9443495,0.0008182649,0.00017440435,0.0005094049,0.00006812829,0.00007395487,0.0027885507],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961484,0.00018683725,0.0007401823,0.0017623707,0.0005636169,0.0005985639],"domain_scores_gemma":[0.99707216,0.00017607493,0.00025160145,0.0019284624,0.0003395077,0.00023219718],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00061561156,0.0006119416,0.00060167426,0.00061620446,0.00010501418,0.0011678664,0.0024385136,0.00043193618,0.00025150622],"category_scores_gemma":[0.000101826554,0.0005427065,0.00027979782,0.0009689823,0.00004655167,0.00020154729,0.006179683,0.00096704304,0.00021759898],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012740851,0.000226674,0.000007885937,0.00036637104,0.00038098075,0.00009357805,0.0025853664,0.021448515,0.0014791819,0.884669,0.040730163,0.047999557],"study_design_scores_gemma":[0.00014482444,0.00006627061,0.000021154414,0.0001299938,0.000047849455,0.00003186673,0.000015095913,0.702102,0.0068149376,0.28850496,0.001517253,0.00060381996],"about_ca_topic_score_codex":0.00013749926,"about_ca_topic_score_gemma":0.000006336562,"teacher_disagreement_score":0.68065345,"about_ca_system_score_codex":0.00024054047,"about_ca_system_score_gemma":0.00037024103,"threshold_uncertainty_score":0.999869},"labels":[],"label_agreement":null},{"id":"W4401410605","doi":"10.1016/j.autcon.2024.105676","title":"Updating simulation model parameters using stochastic gradient descent","year":2024,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Natural Resources","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Descent (aeronautics); Stochastic gradient descent; Computer science; Gradient descent; Mathematical optimization; Applied mathematics; Mathematics; Engineering; Artificial intelligence; Aerospace engineering; Artificial neural network","score_opus":0.03705394001229035,"score_gpt":0.29681311961372253,"score_spread":0.2597591796014322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401410605","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.067209736,0.000030020612,0.9304084,0.00010023015,0.000786422,0.00032777304,0.000001766068,0.0010563564,0.000079279765],"genre_scores_gemma":[0.58368737,0.000001025314,0.4162471,0.000018299108,0.000011951408,0.000019176408,0.000004888119,0.000008101674,0.0000020978716],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986353,0.00005606448,0.00043826824,0.00039273783,0.00027563077,0.00020200758],"domain_scores_gemma":[0.9993549,0.0001496865,0.0001178074,0.00024664064,0.000084386505,0.000046578047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028689473,0.00014086222,0.000120348945,0.00063004036,0.00010205071,0.00027435596,0.00017995486,0.00007691612,0.000005283814],"category_scores_gemma":[0.0001149321,0.00015524885,0.000045630393,0.000879009,0.000051461,0.0011296114,0.00005987172,0.00012574931,0.000008808231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011408081,0.000008808008,0.000039278722,0.00001725927,0.0000047566714,0.0000011057837,0.00040195388,0.855727,0.00020102295,0.1192622,0.000005143643,0.02433028],"study_design_scores_gemma":[0.00010870335,0.00001553935,0.00008351649,0.00016727518,0.000008415948,0.000035172277,0.00004308098,0.9691654,0.00031603183,0.029906807,0.000001706378,0.00014835657],"about_ca_topic_score_codex":0.000018246543,"about_ca_topic_score_gemma":0.0000015925839,"teacher_disagreement_score":0.51647764,"about_ca_system_score_codex":0.0003964414,"about_ca_system_score_gemma":0.00009730857,"threshold_uncertainty_score":0.63308644},"labels":[],"label_agreement":null},{"id":"W4402157250","doi":"10.1109/icufn61752.2024.10625058","title":"Group-Wise Coding for Coded Distributed Computing Systems with Group Heterogeneity and Communication Delay","year":2024,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Communication in small groups; Group (periodic table); Coding (social sciences); Distributed computing; Theoretical computer science; Computer network; Mathematics; Statistics","score_opus":0.02195455033627822,"score_gpt":0.26378779195049157,"score_spread":0.24183324161421335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402157250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005491823,0.00052845397,0.9917114,0.00021798126,0.00013399123,0.00066697225,0.000019576026,0.0011548062,0.00007498938],"genre_scores_gemma":[0.70524883,0.000014319906,0.29454634,0.00004072309,0.000012787583,0.00005697351,0.00006217536,0.000010949144,0.000006916787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896705,0.000060522285,0.0002467694,0.00036905808,0.00015349212,0.00020311624],"domain_scores_gemma":[0.9989282,0.00039257217,0.00007296586,0.00043149275,0.000100453035,0.00007430596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043745156,0.00014206911,0.00016274884,0.00009904816,0.00022678993,0.00059305807,0.00040797278,0.000052672196,5.4667066e-7],"category_scores_gemma":[0.000026463827,0.000115382805,0.000030247566,0.00033949938,0.000061192426,0.00037771094,0.00022172491,0.0000832376,0.0000010006282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001130249,0.000038718827,0.00040511639,0.00017357602,0.00005301279,0.000003928271,0.00032950006,0.0024331925,0.00026034706,0.99289036,0.00061059184,0.0027903665],"study_design_scores_gemma":[0.00024081083,0.00013242914,0.00013800422,0.00020087628,0.000014696538,0.0000625461,0.00003349682,0.9974369,0.00029515196,0.0010108673,0.00027277722,0.00016147553],"about_ca_topic_score_codex":0.00004285791,"about_ca_topic_score_gemma":0.000019191135,"teacher_disagreement_score":0.9950037,"about_ca_system_score_codex":0.00007471927,"about_ca_system_score_gemma":0.000014302897,"threshold_uncertainty_score":0.57188725},"labels":[],"label_agreement":null},{"id":"W4402387425","doi":"10.48550/arxiv.2408.06243","title":"Complexity of trust-region methods in the presence of unbounded Hessian approximations","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hessian matrix; Trust region; Approximations of π; Mathematics; Mathematical optimization; Applied mathematics; Computer science; Mathematical economics; Computer security","score_opus":0.1927757549530781,"score_gpt":0.2768991883653062,"score_spread":0.08412343341222808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402387425","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010335646,0.00004659806,0.98525,0.00025289785,0.00020914304,0.00054537924,0.000010015084,0.00013139485,0.0032189393],"genre_scores_gemma":[0.7969063,0.000019942596,0.20295002,0.000014517588,0.000007561528,0.0000037206933,0.000005242158,0.0000070063893,0.00008567058],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832845,0.00045542183,0.00033464795,0.00058681215,0.00012302258,0.00017164978],"domain_scores_gemma":[0.9978437,0.00032225833,0.0003663965,0.0012532482,0.00017451533,0.000039899824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000657784,0.00018747966,0.00032216098,0.000490979,0.000053669064,0.00005553761,0.002296963,0.00016191664,0.0000053156523],"category_scores_gemma":[0.00012966325,0.00017050188,0.0001552412,0.0014980914,0.00046279622,0.00016464149,0.001555662,0.00044115967,0.0000017278289],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005674914,0.00008790982,0.00017759157,0.00017461013,0.000023813584,0.000014728581,0.001522252,0.061757218,0.000019250276,0.9358377,0.00005389866,0.0003253908],"study_design_scores_gemma":[0.00007187402,0.000021259091,0.00028651557,0.00012337322,0.000022912845,0.0000025724664,0.000114432936,0.5268786,0.0003368652,0.4720441,0.000007630775,0.00008983415],"about_ca_topic_score_codex":0.00020503474,"about_ca_topic_score_gemma":0.000021406058,"teacher_disagreement_score":0.78657067,"about_ca_system_score_codex":0.00009250107,"about_ca_system_score_gemma":0.00017307713,"threshold_uncertainty_score":0.6952865},"labels":[],"label_agreement":null},{"id":"W4402897057","doi":"10.1109/iwqos61813.2024.10682956","title":"Blade: Pushing the Performance Envelope of Asynchronous Federated Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Asynchronous communication; Envelope (radar); Computer science; Asynchronous learning; Blade (archaeology); Telecommunications; Engineering; Synchronous learning; Mathematics education; Mechanical engineering","score_opus":0.011846142436443613,"score_gpt":0.23208734436568423,"score_spread":0.22024120192924063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402897057","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008421226,0.00016189174,0.9819389,0.00070722075,0.00020371497,0.00011517434,1.5232453e-7,0.0007768217,0.0076749194],"genre_scores_gemma":[0.93866754,0.000034363966,0.060631834,0.00007590795,0.000018606363,0.000012495174,0.0000010097995,0.000007862502,0.0005504056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992489,0.00003434583,0.00018103907,0.00020036731,0.00018675467,0.00014857593],"domain_scores_gemma":[0.99954355,0.00014030487,0.000039588784,0.0001863564,0.000065766326,0.000024434974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031104087,0.00008299666,0.00008036294,0.00009010029,0.00015938368,0.0002862607,0.00046174836,0.000032538104,0.000051567535],"category_scores_gemma":[0.000053710875,0.0000540121,0.000029456078,0.00055576494,0.000043064047,0.00038649517,0.00016351118,0.00016935194,0.000030980533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051883817,0.000057866437,0.0012891018,0.00019825017,0.0001040741,0.000016684166,0.007151629,0.07507193,0.004725639,0.62089455,0.0037718022,0.28671327],"study_design_scores_gemma":[0.000033914173,0.00006852446,0.00033191644,0.000058466827,0.000003007202,0.000018450872,0.000034823755,0.98070276,0.01702349,0.00032908388,0.0013134022,0.00008216135],"about_ca_topic_score_codex":0.000012942027,"about_ca_topic_score_gemma":0.0000010753487,"teacher_disagreement_score":0.9302463,"about_ca_system_score_codex":0.00002974791,"about_ca_system_score_gemma":0.00007322031,"threshold_uncertainty_score":0.27604187},"labels":[],"label_agreement":null},{"id":"W4403585525","doi":"10.1093/imaiai/iaae028","title":"Hitting the High-dimensional notes: an ODE for SGD learning dynamics on GLMs and multi-index models","year":2024,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Israel Science Foundation; Canadian Institute for Advanced Research","keywords":"Ode; Index (typography); Dynamics (music); Econometrics; Artificial intelligence; Statistical physics; Computer science; Mathematics; Physics; Applied mathematics","score_opus":0.023443340076124308,"score_gpt":0.2753627054817372,"score_spread":0.2519193654056129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403585525","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02430227,0.00004489804,0.9731233,0.0021143842,0.00021503078,0.00012587827,0.0000027719977,0.000038194783,0.00003323584],"genre_scores_gemma":[0.94417584,0.0000223542,0.055236667,0.0005256226,0.000020660636,0.0000041960534,0.0000014282316,0.0000031568563,0.000010060857],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992843,0.000033457443,0.00031225703,0.0000621962,0.00021198689,0.0000957725],"domain_scores_gemma":[0.9990926,0.00031805923,0.00022924723,0.000111188325,0.00020629633,0.000042622458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005365976,0.000079564896,0.00008382168,0.00012244993,0.00022333341,0.00046028927,0.00029264743,0.00003546322,0.0000011136848],"category_scores_gemma":[0.00030979534,0.0000436908,0.000035113473,0.00013223718,0.00004605,0.0023268561,0.00009709486,0.00021686174,6.440462e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027338003,0.000019709576,0.00022394945,0.000036474932,0.000025090509,6.1962567e-7,0.005048189,0.40954608,0.000036403246,0.3292534,0.000078011835,0.25570473],"study_design_scores_gemma":[0.00019885488,0.00014363974,0.0003671776,0.00014179641,0.000005909438,0.00005145239,0.00010744004,0.9851687,0.00010200033,0.013589063,0.00006676791,0.000057182773],"about_ca_topic_score_codex":0.000009701519,"about_ca_topic_score_gemma":0.0000021598123,"teacher_disagreement_score":0.9198736,"about_ca_system_score_codex":0.000035802306,"about_ca_system_score_gemma":0.000074572294,"threshold_uncertainty_score":0.443858},"labels":[],"label_agreement":null},{"id":"W4403730249","doi":"10.23952/jnva.8.2024.6.04","title":"A distributed primal-dual hybrid gradient algorithm for fair resource allocation","year":2024,"lang":"en","type":"article","venue":"Journal of Nonlinear and Variational Analysis","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Science Fund for Distinguished Young Scholars of Gansu Province; National Natural Science Foundation of China; Ant Group","keywords":"Dual (grammatical number); Computer science; Resource allocation; Algorithm; Resource (disambiguation); Mathematical optimization; Distributed computing; Mathematics; Computer network","score_opus":0.011473895302202775,"score_gpt":0.25870138239275176,"score_spread":0.24722748709054898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403730249","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004373892,0.00025096347,0.9966489,0.0022527867,0.000117059826,0.000094731,0.00012863004,0.000052756,0.000016755554],"genre_scores_gemma":[0.061881285,0.000035812973,0.9373426,0.00011797032,0.00032052398,0.000009848043,0.00021747175,0.0000082564275,0.000066238885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880046,0.000038950213,0.00046567785,0.00021115915,0.00036228512,0.00012144454],"domain_scores_gemma":[0.9988203,0.00028432682,0.00022239354,0.0001228158,0.000458195,0.00009198587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006311523,0.00010458528,0.00022358228,0.00056648644,0.000093761264,0.00022561275,0.00020607113,0.0000356742,0.000009341189],"category_scores_gemma":[0.00011908801,0.00008562253,0.00024096122,0.0009789491,0.000021985574,0.0003576931,0.00004998546,0.00010143499,8.899438e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117862386,0.0013763416,0.0006465407,0.00017091905,0.011070646,0.00012871175,0.002130035,0.14889751,0.0004014917,0.5484238,0.012056341,0.27457976],"study_design_scores_gemma":[0.00019372177,0.00016259165,0.00066055974,0.000020407677,0.00047654624,0.0000764397,0.000012090642,0.9886404,0.0001300114,0.005567255,0.0039665434,0.0000934319],"about_ca_topic_score_codex":0.000004048265,"about_ca_topic_score_gemma":6.37935e-7,"teacher_disagreement_score":0.8397429,"about_ca_system_score_codex":0.000073755305,"about_ca_system_score_gemma":0.00011739762,"threshold_uncertainty_score":0.34915856},"labels":[],"label_agreement":null},{"id":"W4403730451","doi":"10.23952/jnva.8.2024.6.05","title":"Fully polynomial-time randomized approximation schemes for global optimization of high-dimensional minimax concave penalized generalized linear models","year":2024,"lang":"en","type":"article","venue":"Journal of Nonlinear and Variational Analysis","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Division of Civil, Mechanical and Manufacturing Innovation; National Science Foundation","keywords":"Minimax; Mathematics; Applied mathematics; Polynomial; Mathematical optimization; Minimax approximation algorithm; Polynomial and rational function modeling; Mathematical analysis","score_opus":0.013091670798794674,"score_gpt":0.26520768852605925,"score_spread":0.25211601772726455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403730451","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002453387,0.00045546822,0.99529636,0.0011404867,0.00015947821,0.00031601574,0.00010190567,0.000046579837,0.000030307332],"genre_scores_gemma":[0.06887913,0.000056367793,0.93051606,0.00008818411,0.00018876597,0.000016711021,0.00017179153,0.000009967808,0.00007304154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768484,0.00016861624,0.0011417756,0.00028092775,0.00057983445,0.00014400273],"domain_scores_gemma":[0.9971214,0.0006460012,0.0007478052,0.00015450752,0.0012308323,0.000099446035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013858401,0.00018513063,0.0008533546,0.0006174601,0.00008312912,0.00013868343,0.0002671064,0.000107527674,0.000053776323],"category_scores_gemma":[0.00035117855,0.00014672824,0.00058445375,0.0011061605,0.00007355901,0.00069329445,0.000067683846,0.000083583844,7.3896507e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022237662,0.00010696293,0.0000071877294,0.000040928502,0.0021542488,0.0000021692433,0.00015258254,0.87177235,0.00017126581,0.12258892,0.00017822758,0.00060140557],"study_design_scores_gemma":[0.011277049,0.00009644699,0.000011228571,0.000043258282,0.0013086828,0.000024371542,0.0000031247905,0.96845186,0.00024106442,0.018377123,0.000029818764,0.00013597767],"about_ca_topic_score_codex":0.000018871644,"about_ca_topic_score_gemma":5.311562e-7,"teacher_disagreement_score":0.1042118,"about_ca_system_score_codex":0.00007833271,"about_ca_system_score_gemma":0.00030911082,"threshold_uncertainty_score":0.5983404},"labels":[],"label_agreement":null},{"id":"W4403829686","doi":"10.1007/s10957-024-02556-6","title":"The “Black-Box” Optimization Problem: Zero-Order Accelerated Stochastic Method via Kernel Approximation","year":2024,"lang":"en","type":"article","venue":"Journal of Optimization Theory and Applications","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Analytical Center for the Government of the Russian Federation","keywords":"Mathematics; Theory of computation; Zero order; Applied mathematics; Zero (linguistics); Mathematical optimization; Kernel (algebra); Order (exchange); Stochastic optimization; First order; Algorithm; Combinatorics","score_opus":0.01322407823589315,"score_gpt":0.28370880503282225,"score_spread":0.2704847267969291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403829686","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004367134,0.00066664454,0.9964396,0.0011867044,0.00016835707,0.0008065433,0.000003568477,0.00025973967,0.00046448543],"genre_scores_gemma":[0.016335227,0.00036058124,0.98249024,0.00014128796,0.00013132242,0.00020310332,0.000021165257,0.00003614874,0.00028094073],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979568,0.00031897618,0.00079832744,0.00034173788,0.00036017795,0.00022398648],"domain_scores_gemma":[0.9971091,0.0009612867,0.0005240541,0.00038484504,0.0008933399,0.00012738287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021589247,0.00022008804,0.00022042179,0.00035292833,0.0005224109,0.00081813347,0.0006436349,0.00011759299,0.000027791557],"category_scores_gemma":[0.00020640431,0.00016253999,0.00008395752,0.0015467766,0.00015330367,0.0011583207,0.00011313052,0.00028088363,0.0000058987944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013841353,0.00003483412,4.860841e-7,0.000016875993,0.00003758088,5.444079e-7,0.0002441902,0.6325471,0.000060266135,0.35294825,0.00015509782,0.013940948],"study_design_scores_gemma":[0.00020198694,0.000068684734,0.0000019088448,0.00005759192,0.00006094905,0.00011698514,0.000058088444,0.8795253,0.00025391483,0.1190879,0.00041032635,0.0001563695],"about_ca_topic_score_codex":9.13577e-7,"about_ca_topic_score_gemma":1.359651e-7,"teacher_disagreement_score":0.24697821,"about_ca_system_score_codex":0.000078194236,"about_ca_system_score_gemma":0.0001570273,"threshold_uncertainty_score":0.788928},"labels":[],"label_agreement":null},{"id":"W4404986356","doi":"10.48550/arxiv.2411.15370","title":"Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Computer science; Real-time computing","score_opus":0.05825574032702813,"score_gpt":0.25314721150064595,"score_spread":0.19489147117361783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404986356","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067243486,0.0003258076,0.9914965,0.00048631275,0.0018574992,0.00076250173,0.000015249977,0.0019898312,0.0023938704],"genre_scores_gemma":[0.4132138,0.0004315872,0.58145624,0.00037119366,0.00028337736,0.000014064465,0.00006440743,0.000093530485,0.0040718284],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995776,0.00044353877,0.00048580908,0.0023009886,0.00019023471,0.00080341054],"domain_scores_gemma":[0.99615407,0.00027426516,0.00040866426,0.0024693005,0.0002691783,0.00042450888],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008317129,0.0007038918,0.00070063357,0.0010693368,0.00021588537,0.0003844278,0.0031704172,0.0005461003,0.00007659311],"category_scores_gemma":[0.00022901222,0.00069533166,0.00035713165,0.0024922346,0.00021619594,0.000316073,0.0054785744,0.0011889696,0.00006349257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040804516,0.00006523359,0.00024396244,0.00008084209,0.00017895729,0.0002614467,0.00032019545,0.58183163,0.000002952841,0.41320992,0.0024296232,0.0013344465],"study_design_scores_gemma":[0.00021630774,0.000095474614,0.000040938434,0.00014774,0.00010322625,0.000027835824,0.00003757992,0.8244115,0.000106311425,0.17303728,0.0011335339,0.0006422723],"about_ca_topic_score_codex":0.0004361648,"about_ca_topic_score_gemma":0.00004209099,"teacher_disagreement_score":0.41254136,"about_ca_system_score_codex":0.0007737631,"about_ca_system_score_gemma":0.0006440474,"threshold_uncertainty_score":0.9995498},"labels":[],"label_agreement":null},{"id":"W4406011402","doi":"10.1007/978-3-031-75623-8","title":"Learning and Intelligent Optimization","year":2025,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Sobolev Institute of Mathematics, Siberian Branch, Russian Academy of Sciences; University of Ioannina; SBA Research; Università degli Studi di Ferrara; Syddansk Universitet; Consejo Superior de Investigaciones Científicas; Università di Bologna; Università Politecnica delle Marche; Universität Bielefeld; University of Haifa; Università degli Studi di Cagliari; Centre National de la Recherche Scientifique; Universite Angers; Sapienza Università di Roma; Università degli Studi di Trento; Khalifa University of Science, Technology and Research; Università degli Studi di Milano-Bicocca; Beijing University of Technology; University of Toronto; University of Crete; Università degli Studi di Camerino; KU Leuven; Technische Universiteit Eindhoven; Indian Council of Agricultural Research; University of Warwick; Université de Lorraine; Universitat de Lleida; Universidade de Aveiro; Indian Institute of Information Technology, Allahabad; Singapore Management University; Wilfrid Laurier University; University of Patras; Institut national de recherche en informatique et en automatique (INRIA); Université de Lille; University of Pittsburgh; Università degli Studi di Udine; Università della Calabria; University of Washington; Università degli Studi di Napoli Federico II","keywords":"Computer science; Artificial intelligence","score_opus":0.010010768580344631,"score_gpt":0.2506112010465052,"score_spread":0.24060043246616056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406011402","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000013616769,0.00038307568,0.9946017,0.00039619222,0.00085332216,0.00038451544,8.2969945e-7,0.0003879247,0.0029910258],"genre_scores_gemma":[0.0016447478,0.00015996187,0.9959114,0.000600475,0.00010167904,0.000017824343,0.000008084021,0.00001559255,0.0015402143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973925,0.000055307675,0.00039363824,0.0011939089,0.0005504983,0.00041416445],"domain_scores_gemma":[0.9983348,0.0005052333,0.00020597335,0.0005944539,0.0002541455,0.00010536938],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006366177,0.0003462277,0.00034745963,0.0012280205,0.00023708101,0.00057550037,0.0016387079,0.0002420442,0.000007942833],"category_scores_gemma":[0.00034512798,0.000343686,0.000050062663,0.0013486568,0.00039954626,0.00040409595,0.0015036226,0.00063533155,0.0000030001129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010723986,0.000010759821,0.00002659097,0.00002960866,0.0000036711144,0.000006980921,0.0003696265,0.6631205,0.0000026005105,0.007443923,0.00004363238,0.32894102],"study_design_scores_gemma":[0.00008348789,0.00011879573,0.0000052998857,0.0003548827,0.0000047546905,0.000018129078,1.4212908e-7,0.9587831,0.00035746355,0.03943627,0.00052769773,0.00030998842],"about_ca_topic_score_codex":0.0000051562224,"about_ca_topic_score_gemma":0.0000035802595,"teacher_disagreement_score":0.328631,"about_ca_system_score_codex":0.00038059376,"about_ca_system_score_gemma":0.00079350296,"threshold_uncertainty_score":0.99990153},"labels":[],"label_agreement":null},{"id":"W4407638124","doi":"10.1109/tdsc.2025.3542761","title":"New Secure Sparse Inner Product With Applications to Machine Learning","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Dependable and Secure Computing","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"National Natural Science Foundation of China","keywords":"Computer science; Product (mathematics); Artificial intelligence; Computer security","score_opus":0.010138908995805496,"score_gpt":0.23928451255183247,"score_spread":0.22914560355602698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407638124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007461968,0.00013416949,0.99597895,0.0011558871,0.00016968082,0.000634609,0.0000032660912,0.0005996743,0.0005775713],"genre_scores_gemma":[0.6610091,0.000010090772,0.3377136,0.00032211703,0.000031707703,0.00004194534,0.0000023725852,0.000014803218,0.00085430825],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862236,0.000045547866,0.00023578737,0.0006098118,0.0001991449,0.00028736886],"domain_scores_gemma":[0.9991577,0.00010887606,0.00006954413,0.0003947814,0.00012192737,0.00014714489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016701876,0.00021378256,0.00020158719,0.00038014565,0.0005373347,0.00019619284,0.00038189723,0.000059874834,0.000012660953],"category_scores_gemma":[0.000007687108,0.00019402828,0.000038224887,0.001292329,0.000023254499,0.00020450904,0.000014967251,0.0003874116,0.000010485268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004617112,0.00016542598,0.00023959274,0.00007522837,0.000102273,0.000010143335,0.001598844,0.67319846,0.00041795758,0.02976481,0.0007649043,0.2936162],"study_design_scores_gemma":[0.0010139238,0.00045448725,0.00010712582,0.00034966788,0.00007678738,0.00011006369,0.000095964286,0.9553249,0.024908425,0.001911631,0.0149458945,0.0007011506],"about_ca_topic_score_codex":0.000101908925,"about_ca_topic_score_gemma":0.000079953374,"teacher_disagreement_score":0.6602629,"about_ca_system_score_codex":0.000045666184,"about_ca_system_score_gemma":0.000117275995,"threshold_uncertainty_score":0.7912244},"labels":[],"label_agreement":null},{"id":"W4407689519","doi":"10.1007/s10208-024-09673-8","title":"Restarts Subject to Approximate Sharpness: A Parameter-Free and Optimal Scheme For First-Order Methods","year":2025,"lang":"en","type":"article","venue":"Foundations of Computational Mathematics","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mathematics; Scheme (mathematics); Subject (documents); Order (exchange); Applied mathematics; Numerical analysis; Mathematical optimization; Calculus (dental); Mathematical analysis; Computer science","score_opus":0.03329306612632124,"score_gpt":0.3558228624035679,"score_spread":0.32252979627724665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407689519","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019101457,0.0000266275,0.9945019,0.0019550344,0.00014710762,0.0009617329,0.000025723644,0.0001796713,0.00029207536],"genre_scores_gemma":[0.006418218,0.0000019161796,0.9929704,0.00014280157,0.000011898034,0.00033046925,0.000028631293,0.00001287181,0.000082798775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987002,0.000038031856,0.0005272899,0.00032489505,0.00022963189,0.00017992617],"domain_scores_gemma":[0.99601114,0.0024750934,0.00019599895,0.0005331274,0.00072209636,0.00006256172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005660764,0.00016122512,0.0002699542,0.00044816575,0.00021038677,0.00017650801,0.00067721534,0.00005518494,0.000007750254],"category_scores_gemma":[0.0023438123,0.0001677377,0.000059722945,0.00086217356,0.00008727503,0.0002883646,0.00037277784,0.000056721452,0.0000019696804],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008036979,0.00014909834,0.000019869629,0.00024395123,0.000049932863,1.5917445e-7,0.0008116388,0.0678088,0.00003300878,0.9273365,0.0013955745,0.0021434363],"study_design_scores_gemma":[0.00022700662,0.00005856652,0.00005536716,0.00007837107,0.000012921722,0.000003124161,0.000027192651,0.57922876,0.00019244502,0.4197801,0.00024534584,0.0000907811],"about_ca_topic_score_codex":0.000002508543,"about_ca_topic_score_gemma":0.0000017350451,"teacher_disagreement_score":0.51141995,"about_ca_system_score_codex":0.00004184854,"about_ca_system_score_gemma":0.00014311915,"threshold_uncertainty_score":0.6840145},"labels":[],"label_agreement":null},{"id":"W4407780854","doi":"10.4018/979-8-3693-7352-1.ch002","title":"Overview of Optimization Algorithms in Deep Learning","year":2025,"lang":"en","type":"book-chapter","venue":"Advances in computational intelligence and robotics book series","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Computer science; Optimization algorithm; Artificial intelligence; Algorithm; Machine learning; Mathematical optimization; Mathematics","score_opus":0.027061038123428405,"score_gpt":0.2971209770189782,"score_spread":0.2700599388955498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407780854","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.3972535e-8,0.029116618,0.9499727,0.00016195708,0.00017843739,0.0002478104,0.0000025626775,0.00006088932,0.020258978],"genre_scores_gemma":[0.00023211779,0.07351324,0.9160449,0.00011951382,0.000017384436,0.000016535227,0.000046272497,0.000017994018,0.0099920295],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983806,0.000030076142,0.0006985618,0.00044170048,0.00028513672,0.0001639227],"domain_scores_gemma":[0.9987879,0.00041794256,0.0003292616,0.0001809187,0.00024956377,0.00003444284],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016835381,0.00025954586,0.00041004972,0.000561362,0.00006066414,0.00004696455,0.00039033988,0.00015945455,0.000019689518],"category_scores_gemma":[0.00007657305,0.0002846559,0.000051116906,0.0002279499,0.00020225145,0.0011149641,0.0002462314,0.00029908225,0.0000014212533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003296518,0.000008388722,0.0000166451,0.000076719545,0.0000046113823,0.0000035455903,0.00009960869,0.51683694,2.4154847e-8,0.46456558,0.0000017394585,0.018382931],"study_design_scores_gemma":[0.000046155645,0.000085905056,0.0000066615153,0.0007640372,0.0000057188777,0.000007611675,0.00001720946,0.7160246,0.000012559136,0.28164762,0.0011900631,0.00019186565],"about_ca_topic_score_codex":0.0000038693693,"about_ca_topic_score_gemma":0.000015362586,"teacher_disagreement_score":0.19918768,"about_ca_system_score_codex":0.00007534994,"about_ca_system_score_gemma":0.00009926503,"threshold_uncertainty_score":0.99996054},"labels":[],"label_agreement":null},{"id":"W4408017304","doi":"10.1109/jiot.2025.3546672","title":"Adaptive Central Acceleration With Variance Control for Robust Federated Optimization in Ubiquitous Intelligence","year":2025,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Acceleration; Variance (accounting); Robustness (evolution); Adaptive control; Control (management); Mathematical optimization; Distributed computing; Artificial intelligence; Mathematics","score_opus":0.020097225084076464,"score_gpt":0.2514308858322141,"score_spread":0.23133366074813766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408017304","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047721344,0.000040495106,0.9975103,0.0005696938,0.0006371133,0.0004664941,0.0000014003512,0.000073091,0.00022421079],"genre_scores_gemma":[0.5624783,0.000007809614,0.4371569,0.00022838522,0.00002318911,0.000021972499,0.000001046287,0.0000065377963,0.000075878095],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864167,0.00007032783,0.0005435272,0.00026417006,0.00021683196,0.00026345326],"domain_scores_gemma":[0.99862474,0.00016742019,0.00041856966,0.00014070663,0.0005927887,0.00005576353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041709087,0.00015407326,0.00024030198,0.00034207333,0.00007578028,0.00031915915,0.0006371783,0.000083609666,0.000008423085],"category_scores_gemma":[0.00015179592,0.00013631738,0.000054643067,0.0004297375,0.00005002622,0.0010699513,0.000036393958,0.000246815,3.269152e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028373318,0.00009206152,0.00012701773,0.000015010602,0.00005118391,0.0000066870793,0.0009916673,0.97437525,0.00022409126,0.018440796,0.0004073685,0.0049851416],"study_design_scores_gemma":[0.0007054133,0.00039446217,0.000047317357,0.00039257575,0.000013324944,0.000044528624,0.000041791613,0.97886807,0.016075741,0.0032895298,0.0000057713214,0.000121469275],"about_ca_topic_score_codex":0.00003690072,"about_ca_topic_score_gemma":0.000006493656,"teacher_disagreement_score":0.56200105,"about_ca_system_score_codex":0.00019705911,"about_ca_system_score_gemma":0.0001844425,"threshold_uncertainty_score":0.55588615},"labels":[],"label_agreement":null},{"id":"W4410327709","doi":"10.23952/jnva.9.2025.4.07","title":"Convergence analysis of a proximal stochastic gradient algorithm with adaptive sampling for non-convex and non-smooth composite optimization problems","year":2025,"lang":"en","type":"article","venue":"Journal of Nonlinear and Variational Analysis","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Research and Innovation Foundation; National Natural Science Foundation of China","keywords":"Convergence (economics); Proximal Gradient Methods; Mathematical optimization; Regular polygon; Sampling (signal processing); Mathematics; Algorithm; Composite number; Computer science; Convex optimization","score_opus":0.012934794747495718,"score_gpt":0.2567101088984031,"score_spread":0.24377531415090742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410327709","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040438436,0.00007581242,0.9952949,0.00018227461,0.000045653564,0.0002853275,0.000052173677,0.000011631,0.000008333956],"genre_scores_gemma":[0.2637655,0.000019925596,0.73609066,0.00004072778,0.000020919259,0.000014148274,0.000031348052,0.0000045398338,0.000012193454],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850005,0.000035523215,0.000671308,0.00029364222,0.00035243863,0.00014705578],"domain_scores_gemma":[0.9973795,0.00033635093,0.0007745965,0.00015785945,0.001263381,0.00008833403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051117333,0.00016395586,0.00063444633,0.0017085792,0.00013274429,0.00008518418,0.00023859066,0.000059513382,0.0000049366167],"category_scores_gemma":[0.000055355253,0.00013189593,0.00021243488,0.0031536033,0.00007294372,0.00032918507,0.000070198395,0.00010008027,3.7047958e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008953745,0.00016785368,0.0025671422,0.000025487583,0.004993699,7.3793274e-7,0.0004181942,0.9877463,0.000057452788,0.0029786576,0.000003676765,0.00095125276],"study_design_scores_gemma":[0.0006425,0.00039041517,0.01562793,0.0000640287,0.004765343,0.00000453432,0.000044101664,0.9777058,0.000053785923,0.00057471596,0.0000020608354,0.0001248271],"about_ca_topic_score_codex":0.000027397518,"about_ca_topic_score_gemma":0.000009983235,"teacher_disagreement_score":0.25972167,"about_ca_system_score_codex":0.000047651007,"about_ca_system_score_gemma":0.00015274184,"threshold_uncertainty_score":0.537856},"labels":[],"label_agreement":null},{"id":"W4411309355","doi":"10.1145/3744639","title":"Nested Dissection Meets IPMs: Planar Min-Cost Flow in Nearly-Linear Time","year":2025,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Planar; Flow (mathematics); Computer science; Mathematics; Algorithm; Mathematical optimization; Combinatorics; Geometry; Computer graphics (images)","score_opus":0.011028140869351813,"score_gpt":0.2602603873843488,"score_spread":0.249232246514997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411309355","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03142957,0.00012331578,0.94939876,0.016792692,0.0013535612,0.00027899054,0.0000016316278,0.00007070404,0.00055076205],"genre_scores_gemma":[0.26041952,0.00003302156,0.7364272,0.0012848766,0.00022630667,0.000012812507,0.0000015067895,0.000019830022,0.0015749282],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910814,0.00008014029,0.00034230232,0.000112111105,0.00022758562,0.00012971631],"domain_scores_gemma":[0.998745,0.00014509763,0.0002248584,0.00072189444,0.00012564984,0.000037502035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041213926,0.00008359359,0.0001511918,0.00025374905,0.0000669664,0.00006837371,0.0021023303,0.000052662752,0.000007833707],"category_scores_gemma":[0.0010214616,0.000057705063,0.000083052495,0.00071566354,0.000024367846,0.000302817,0.0002969453,0.0002009932,0.0000073331344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008400519,0.002141864,0.03976709,0.00019113702,0.00068310165,0.0004710309,0.011371726,0.2606066,0.061577123,0.037828475,0.4570701,0.12745169],"study_design_scores_gemma":[0.0017060045,0.00031724834,0.037445735,0.00083331874,0.000057014204,0.0004574128,0.000061886865,0.88432765,0.023204198,0.046727005,0.004517911,0.00034461103],"about_ca_topic_score_codex":0.0000074742575,"about_ca_topic_score_gemma":0.0000049194127,"teacher_disagreement_score":0.62372106,"about_ca_system_score_codex":0.00009917287,"about_ca_system_score_gemma":0.000086857326,"threshold_uncertainty_score":0.39066878},"labels":[],"label_agreement":null},{"id":"W4413451426","doi":"10.1016/j.spa.2025.104763","title":"Essential barrier height and a probabilistic approach in characterizing potential landscape","year":2025,"lang":"en","type":"article","venue":"Stochastic Processes and their Applications","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China; U.S. Department of Energy; Jilin University; National Science Foundation","keywords":"Mathematics; Probabilistic logic; Statistical physics; Statistics","score_opus":0.00537538895859835,"score_gpt":0.21800831644243102,"score_spread":0.21263292748383267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413451426","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013900027,0.00056303135,0.9960294,0.0004153105,0.000034194378,0.00084039115,0.000010185192,0.00017673308,0.0005407909],"genre_scores_gemma":[0.98081106,0.00001688267,0.01780129,0.000107803244,0.000030150974,0.0011687207,0.00001590257,0.000008903762,0.000039278308],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989232,0.000017079888,0.00024353014,0.0005101735,0.00008695904,0.00021906586],"domain_scores_gemma":[0.9993353,0.00010503018,0.00007673414,0.00029514867,0.00011520953,0.00007259511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012763662,0.0001734687,0.00019347368,0.00024410972,0.00019901143,0.0001838794,0.00033688135,0.00006757121,0.0000024444519],"category_scores_gemma":[0.00006013615,0.00014851747,0.000019094045,0.00078009383,0.000114425675,0.00022402336,0.00024205357,0.00011624858,7.935314e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002066288,0.00031658617,0.00008778001,0.00063140725,0.000040905,7.9496107e-7,0.0015351049,0.00065874535,0.001440608,0.98234946,0.000034999972,0.01288297],"study_design_scores_gemma":[0.00091486535,0.000072771654,0.00076421956,0.00020499216,0.000040450886,0.00005812372,0.00041083543,0.6752264,0.00040678907,0.32125893,0.00011117412,0.00053042744],"about_ca_topic_score_codex":0.00000528402,"about_ca_topic_score_gemma":0.0000026209443,"teacher_disagreement_score":0.9794211,"about_ca_system_score_codex":0.000015228938,"about_ca_system_score_gemma":0.00012931427,"threshold_uncertainty_score":0.60563666},"labels":[],"label_agreement":null},{"id":"W4414197066","doi":"10.1109/lcn65610.2025.11146375","title":"Performance Analysis of Communication Scheduling Schemes for Distributed Deep Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Scheduling (production processes); Deep learning; Popularity; Fair-share scheduling; Dynamic priority scheduling; Two-level scheduling; Round-robin scheduling; Telecommunications network","score_opus":0.013197497379292693,"score_gpt":0.2737004708763754,"score_spread":0.2605029734970827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414197066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011527322,0.00007426654,0.9871197,0.00017456278,0.000019440564,0.00013379751,0.0000011662295,0.00021591588,0.0007338492],"genre_scores_gemma":[0.5687855,0.000016846088,0.4310728,0.000019147923,7.343135e-7,0.000022818343,0.000028144452,0.0000012525843,0.000052775744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943477,0.0000224379,0.00021766042,0.00014544318,0.0000828487,0.0000968594],"domain_scores_gemma":[0.9990309,0.00020239198,0.00010771872,0.00039739895,0.000246075,0.000015550715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002478464,0.000058382342,0.00014752768,0.00035981834,0.00012291562,0.000035849785,0.00052970863,0.000033527813,0.0000056503477],"category_scores_gemma":[0.00020525431,0.00005704217,0.000069332484,0.0018269763,0.000030129519,0.00018982883,0.00015385287,0.00005360636,3.4954323e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007963656,0.00005304339,0.022057988,0.000035581692,0.00038280545,2.3238574e-8,0.00021927954,0.365846,0.00027804516,0.5710841,0.000034602424,0.04000059],"study_design_scores_gemma":[0.00010360104,0.000020778194,0.002752613,0.00001963198,0.0000853227,5.2135373e-8,0.000029847399,0.9910371,0.0051535163,0.0005712607,0.00017408516,0.000052233383],"about_ca_topic_score_codex":0.000005321029,"about_ca_topic_score_gemma":0.0000021015305,"teacher_disagreement_score":0.62519103,"about_ca_system_score_codex":0.000026821885,"about_ca_system_score_gemma":0.000020338523,"threshold_uncertainty_score":0.23261121},"labels":[],"label_agreement":null},{"id":"W4414989062","doi":"10.48550/arxiv.2506.20335","title":"CLARSTA: A random subspace trust-region algorithm for convex-constrained derivative-free optimization","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Subspace topology; Linear subspace; Convergence (economics); Measure (data warehouse); Random subspace method; Constraint (computer-aided design); Projection (relational algebra); Random projection","score_opus":0.03735733149559817,"score_gpt":0.274019454456596,"score_spread":0.2366621229609978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414989062","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043221214,0.00015411638,0.9904017,0.002791394,0.0012385553,0.0029395365,0.00008425363,0.0012137892,0.0007444675],"genre_scores_gemma":[0.008767803,0.00012761593,0.9875419,0.0007483579,0.00014726982,0.0012298333,0.00016744366,0.000048743088,0.0012210397],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968698,0.00016916488,0.000727691,0.0013350231,0.0003702905,0.0005280447],"domain_scores_gemma":[0.996501,0.00052400125,0.0006399783,0.0016410752,0.00054090685,0.00015303874],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046933434,0.00059437566,0.0007728142,0.0004469909,0.0002744465,0.00023337903,0.0023092593,0.0005953668,0.00003102977],"category_scores_gemma":[0.0008038934,0.00063537474,0.0003282109,0.00069749623,0.00021481163,0.00039547693,0.0019837392,0.00052070065,0.0000061390397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005341802,0.0010880011,0.014827127,0.0012038256,0.0015312813,0.000090692534,0.0056050564,0.70124817,0.00012989885,0.124493234,0.050631426,0.09861714],"study_design_scores_gemma":[0.0034817008,0.00010238511,0.00037038693,0.00027633776,0.0000899176,0.00001199263,0.000026107695,0.9815802,0.0014738492,0.0114460075,0.00050326606,0.0006378523],"about_ca_topic_score_codex":0.000033147866,"about_ca_topic_score_gemma":0.000003109605,"teacher_disagreement_score":0.28033206,"about_ca_system_score_codex":0.00024698782,"about_ca_system_score_gemma":0.0003982444,"threshold_uncertainty_score":0.99960977},"labels":[],"label_agreement":null},{"id":"W4415480599","doi":"10.1145/3704413.3764446","title":"Adaptive Sparsification for Communication-Efficient Distributed Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ericsson (Canada); Ontario Tech University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Regret; Stochastic approximation; Convergence (economics); Optimization problem; Computational complexity theory; Distributed learning; Stochastic optimization; Function (biology)","score_opus":0.027380303733686082,"score_gpt":0.28281344854844,"score_spread":0.2554331448147539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415480599","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007387188,0.00055036036,0.9855053,0.0038092197,0.00042998357,0.001917843,0.00003186857,0.00064086844,0.007040682],"genre_scores_gemma":[0.66886127,0.00006659668,0.32818335,0.00017425267,0.000013963059,0.0003667,0.00011828284,0.000012862513,0.0022027378],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975808,0.00021667905,0.0007284461,0.0007430083,0.00028200232,0.00044906608],"domain_scores_gemma":[0.99614483,0.00093897857,0.0003916029,0.0012800844,0.0011439953,0.000100493424],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008283981,0.00029243506,0.00031060184,0.000380279,0.0009369509,0.00037159698,0.00155857,0.00018140383,0.000043792126],"category_scores_gemma":[0.00082577125,0.00032228325,0.00015718903,0.0017333776,0.00022376365,0.0002295045,0.00055995025,0.000295136,0.000022453587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032430937,0.00022453802,0.00006976796,0.00002460494,0.00005101853,1.08487285e-7,0.0005138275,0.16448931,0.00002843186,0.8128401,0.0029726836,0.018753156],"study_design_scores_gemma":[0.0005676522,0.00017286485,0.00045872937,0.00019923125,0.00005461496,9.481973e-7,0.00041760167,0.9812312,0.0016156752,0.011863467,0.0031359761,0.0002820227],"about_ca_topic_score_codex":0.000034767163,"about_ca_topic_score_gemma":0.0000033111553,"teacher_disagreement_score":0.8167419,"about_ca_system_score_codex":0.0003320034,"about_ca_system_score_gemma":0.0003024401,"threshold_uncertainty_score":0.99992293},"labels":[],"label_agreement":null},{"id":"W4415974379","doi":"10.1016/j.procs.2025.09.338","title":"KurtHGR: A Neural Maximal Correlation for Tabular Datasets","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Fondation du Risque; CNP Assurances","keywords":"Nonlinear system; Universality (dynamical systems); Curse of dimensionality; Bivariate analysis; Correlation; A priori and a posteriori; Feature selection; Pattern recognition (psychology); Covariance matrix; Feature (linguistics)","score_opus":0.01086153656386521,"score_gpt":0.26296386590555776,"score_spread":0.2521023293416925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415974379","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00053872506,0.00005256554,0.9954326,0.0010747974,0.0015134063,0.00068757357,0.0000126397335,0.00053757493,0.00015009462],"genre_scores_gemma":[0.16607052,0.0000021506805,0.83241606,0.0012659426,0.000066808294,0.00012391212,0.000020087513,0.0000059208032,0.000028594517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980315,0.000015687538,0.0002880736,0.00081579346,0.0004065969,0.00044236914],"domain_scores_gemma":[0.9986048,0.0001475827,0.00011460104,0.0006740357,0.00034675858,0.00011226599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005888518,0.0001694638,0.00015601006,0.0004793414,0.00039524745,0.00049360737,0.0022021248,0.000048687587,0.0000017519777],"category_scores_gemma":[0.00017401407,0.00016560269,0.000047733658,0.0019652369,0.00023955459,0.0014510503,0.0007736036,0.000101137506,0.000007140882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017980605,0.00014150418,0.0012426246,0.00007805163,0.000011731969,0.0000044896983,0.0006254262,0.01991015,0.000473085,0.8061973,0.01096212,0.16033556],"study_design_scores_gemma":[0.00027071591,0.000100305304,0.00072651386,0.000029314915,0.000005319631,0.0000095958285,0.0000024828355,0.9829842,0.0015085883,0.013105096,0.0010894372,0.00016846914],"about_ca_topic_score_codex":0.000003903219,"about_ca_topic_score_gemma":0.0000011912153,"teacher_disagreement_score":0.963074,"about_ca_system_score_codex":0.000080342004,"about_ca_system_score_gemma":0.00032295496,"threshold_uncertainty_score":0.6753081},"labels":[],"label_agreement":null},{"id":"W4416159177","doi":"10.48550/arxiv.2511.07272","title":"Revisiting the Neural Tangent Kernel: the role of large width and depth","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Generalization; Artificial neural network; Limit (mathematics); Kernel (algebra); Limiting; Tangent; Property (philosophy)","score_opus":0.027693998299192713,"score_gpt":0.27876949542319884,"score_spread":0.2510754971240061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416159177","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17648035,0.012260351,0.7928387,0.009706245,0.0013004697,0.002777296,0.0000661627,0.0003960056,0.004174418],"genre_scores_gemma":[0.9895087,0.00078617595,0.008015329,0.0009636683,0.000271441,0.00013772518,0.000006903933,0.000025972011,0.00028409032],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99626476,0.0004717909,0.0009789312,0.0010943625,0.000569529,0.00062062684],"domain_scores_gemma":[0.99599165,0.0007569376,0.0009422889,0.0018518588,0.00034247086,0.00011480174],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015931801,0.00052569475,0.00057330827,0.00015793362,0.0006497407,0.00026354226,0.0028486343,0.00022945671,0.00003470944],"category_scores_gemma":[0.00051518914,0.00034470935,0.00026180033,0.00074967043,0.00042845082,0.00020508927,0.0051926863,0.00093181425,0.000008187541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005084603,0.00020002408,0.606403,0.00055183086,0.00044959373,0.00001185159,0.011741811,0.008277514,0.00046712282,0.169392,0.00030005633,0.20215434],"study_design_scores_gemma":[0.00043186947,0.000108172826,0.17402525,0.0011766823,0.00026976818,0.000035570214,0.0006108837,0.8037668,0.0044287355,0.01064259,0.0038314804,0.0006721815],"about_ca_topic_score_codex":0.000098874596,"about_ca_topic_score_gemma":0.000007403687,"teacher_disagreement_score":0.81302834,"about_ca_system_score_codex":0.00007620766,"about_ca_system_score_gemma":0.00017842973,"threshold_uncertainty_score":0.9999005},"labels":[],"label_agreement":null},{"id":"W4416246782","doi":"10.48550/arxiv.2510.19382","title":"A Derandomization Framework for Structure Discovery: Applications in Neural Networks and Beyond","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Commission; Canadian Institute for Advanced Research","keywords":"Gradient descent; Artificial neural network; Feature (linguistics); Lemma (botany); Stochastic gradient descent; Property (philosophy); Key (lock); Function approximation; Function (biology)","score_opus":0.01795878457888987,"score_gpt":0.27951561371222877,"score_spread":0.2615568291333389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416246782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016664453,0.001212241,0.9738915,0.0012307266,0.0009610951,0.0056324275,0.00014369933,0.00021595512,0.000047924834],"genre_scores_gemma":[0.7972434,0.00033826634,0.19929716,0.0007729044,0.00024771952,0.0017191713,0.00023249807,0.00003752485,0.0001113428],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99611574,0.00017794187,0.0010476904,0.0017572885,0.00027244637,0.00062891253],"domain_scores_gemma":[0.9962896,0.0014914689,0.0006522304,0.001145356,0.00026620805,0.00015512962],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035694632,0.0006867591,0.00086775655,0.0005175426,0.00043806064,0.0006652915,0.0012845547,0.0009018146,0.000010194606],"category_scores_gemma":[0.00048060034,0.0007171704,0.00020226312,0.0013115772,0.00022540565,0.0006729366,0.001391927,0.0010857631,4.6869798e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002078444,0.00016572283,0.098641515,0.00035183784,0.00011447474,0.0000013256002,0.0013205549,0.58756167,0.00001061027,0.30021277,0.00009405716,0.011317592],"study_design_scores_gemma":[0.0014344293,0.0000615707,0.013627521,0.00032569352,0.000103937935,0.000003522746,0.00004762639,0.8762755,0.000097199714,0.107370004,0.00008389433,0.00056914426],"about_ca_topic_score_codex":0.000027667496,"about_ca_topic_score_gemma":0.00002676946,"teacher_disagreement_score":0.780579,"about_ca_system_score_codex":0.00017424507,"about_ca_system_score_gemma":0.00018951714,"threshold_uncertainty_score":0.99952793},"labels":[],"label_agreement":null},{"id":"W4416531016","doi":"10.48550/arxiv.2504.06568","title":"Relaxed Weak Accelerated Proximal Gradient Method: a Unified Framework for Nesterov's Accelerations","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Extrapolation; Regular polygon; Sequence (biology); Convergence (economics); Constant (computer programming); Convex function; Momentum (technical analysis); Proximal Gradient Methods","score_opus":0.11006401193336178,"score_gpt":0.3597235002587034,"score_spread":0.24965948832534163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416531016","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005350217,0.00011336106,0.98303044,0.0031281065,0.0019916552,0.0034679868,0.00007003923,0.0018133915,0.0010348334],"genre_scores_gemma":[0.049628574,0.00004154192,0.9441321,0.0009209973,0.00021120672,0.0029456557,0.00016624162,0.00005555716,0.0018981532],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99587727,0.00026852102,0.0009954274,0.0017382939,0.0004075638,0.0007129281],"domain_scores_gemma":[0.99558717,0.00090337644,0.00063445145,0.001958593,0.00069656974,0.0002198213],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007151146,0.00068142783,0.00076181156,0.00064787257,0.00044658652,0.0006095907,0.0027946348,0.0008391515,0.00002812302],"category_scores_gemma":[0.00091356,0.0007031485,0.00034550077,0.0011918655,0.000088786466,0.00044110033,0.0021083567,0.0011584173,0.000018277899],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000699223,0.00045481927,0.004803648,0.00037867887,0.00031788985,0.000007686,0.0018090508,0.010804711,0.000391244,0.97345585,0.003715804,0.0037906715],"study_design_scores_gemma":[0.001983749,0.00064697734,0.017936103,0.0021156091,0.00043224005,0.000028060167,0.00014091685,0.6620825,0.03800993,0.2646819,0.0088274395,0.0031145965],"about_ca_topic_score_codex":0.000042569987,"about_ca_topic_score_gemma":0.000007904197,"teacher_disagreement_score":0.708774,"about_ca_system_score_codex":0.00028266813,"about_ca_system_score_gemma":0.00058707525,"threshold_uncertainty_score":0.99954194},"labels":[],"label_agreement":null},{"id":"W4416772379","doi":"10.1142/s2010326325500261","title":"Dyson equation for correlated linearizations and test error of random features regression","year":2025,"lang":"en","type":"article","venue":"Random Matrices Theory and Application","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Class (philosophy); Scaling; Stability (learning theory); Ridge; Test (biology); Regression","score_opus":0.007147016461262469,"score_gpt":0.27092611505286,"score_spread":0.26377909859159754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416772379","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025221456,0.0009147087,0.99470246,0.00031177545,0.00005231687,0.0011205372,0.000008717337,0.00013679262,0.00023052275],"genre_scores_gemma":[0.94332755,0.0002307062,0.05567672,0.00006456598,0.000017831342,0.0003400495,0.000045045912,0.000006738211,0.00029078074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992542,0.00007712552,0.00025139272,0.00025186723,0.000082069506,0.00008331244],"domain_scores_gemma":[0.99699557,0.0024115446,0.00021539646,0.00021066332,0.00013984932,0.000026976752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071215903,0.00009879704,0.0001733083,0.0001835474,0.00018311667,0.000056687477,0.00016173361,0.00008531882,0.0000011577171],"category_scores_gemma":[0.0006584095,0.00008058367,0.000029615125,0.00045086673,0.000062472835,0.00018617549,0.00005584512,0.00005084404,3.4698155e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055050856,0.0000690723,0.00020666435,0.00010809854,0.000016669723,4.7258556e-8,0.00035175332,0.0006342989,0.003941508,0.9518053,0.00017852157,0.042137586],"study_design_scores_gemma":[0.0076429043,0.00011672327,0.0009858431,0.00017714924,0.00011513406,0.00000424361,0.000070118775,0.6874778,0.016451247,0.2863859,0.00038788986,0.00018503726],"about_ca_topic_score_codex":0.000003974023,"about_ca_topic_score_gemma":4.3765448e-7,"teacher_disagreement_score":0.94080544,"about_ca_system_score_codex":0.000010056393,"about_ca_system_score_gemma":0.000020503921,"threshold_uncertainty_score":0.32861066},"labels":[],"label_agreement":null},{"id":"W4416960645","doi":"10.1109/tpami.2025.3639635","title":"FedFask: Fast Sketching Distributed PCA for Large-Scale Federated Data","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Priority Academic Program Development of Jiangsu Higher Education Institutions; National Natural Science Foundation of China","keywords":"Principal component analysis; Overhead (engineering); Dimension (graph theory); Computational complexity theory; Representation (politics); Rank (graph theory); Stiefel manifold; Ambiguity; Column (typography); Computation","score_opus":0.025768541254703337,"score_gpt":0.2961420152608359,"score_spread":0.27037347400613254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416960645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018740585,0.00005454967,0.99733806,0.00081914157,0.00022779769,0.00030493605,0.0007659119,0.00025951138,0.000042674892],"genre_scores_gemma":[0.97031355,0.00008474604,0.028668758,0.00046627328,0.000009391368,0.000063098414,0.00019325233,0.000009925236,0.00019100065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982362,0.0000613166,0.00043415697,0.0007872934,0.0001911921,0.00028984697],"domain_scores_gemma":[0.99849707,0.00023160607,0.000108854154,0.0009222844,0.00014779545,0.00009238848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035714783,0.00022887666,0.00033302902,0.00057050487,0.0004976928,0.00034457876,0.0009341345,0.00007668837,0.000035775498],"category_scores_gemma":[0.000019048437,0.00021210937,0.00015386546,0.0016774337,0.000036424615,0.00033146795,0.000029541428,0.00019849351,0.0000038755534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042725842,0.0006837296,0.0009647199,0.00007151267,0.0014382437,0.000004769125,0.0005210775,0.0748609,0.0002564303,0.0017266945,0.00036533235,0.91906387],"study_design_scores_gemma":[0.0001332065,0.000058637266,0.00019233879,0.000034292392,0.0003463375,0.0000021242797,0.000057598085,0.96850574,0.029711947,0.00059370813,0.00016225582,0.00020180782],"about_ca_topic_score_codex":0.0002633315,"about_ca_topic_score_gemma":0.0010883738,"teacher_disagreement_score":0.97012615,"about_ca_system_score_codex":0.00004192634,"about_ca_system_score_gemma":0.000035946334,"threshold_uncertainty_score":0.8649569},"labels":[],"label_agreement":null},{"id":"W4416978430","doi":"10.1038/s41467-025-66983-3","title":"Sufficient is better than optimal for training neural networks","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Universities Space Research Association","keywords":"Overfitting; Leverage (statistics); Spurious relationship; Artificial neural network; Deep neural networks; Convolutional neural network; Feedforward neural network; Training (meteorology)","score_opus":0.031036499331539312,"score_gpt":0.3159515656064312,"score_spread":0.2849150662748919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416978430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036475548,0.0013802551,0.96860415,0.026967954,0.00038495025,0.0004242884,0.000008632097,0.00036879073,0.0014962147],"genre_scores_gemma":[0.5867033,0.000022479173,0.40947673,0.003504011,0.000019172421,0.00014530783,0.000024057266,0.0000063506636,0.00009858925],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991058,0.000054765547,0.00022452923,0.0002639481,0.00011591817,0.00023501192],"domain_scores_gemma":[0.9971921,0.00046940806,0.000083823106,0.0019942024,0.00021646247,0.000044028548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023384205,0.00012244775,0.00013143409,0.00018489931,0.0004105929,0.00014411872,0.002819721,0.0001928442,0.0000029250248],"category_scores_gemma":[0.00013181183,0.00012243756,0.000096107105,0.00070507004,0.00008880431,0.000175164,0.0006604489,0.0005278496,0.0000010170952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055304545,0.00012319331,0.00044680794,0.0000065998343,0.000043146156,2.6373425e-7,0.0019386702,0.0108263595,0.00003094446,0.93152255,0.026453909,0.028602025],"study_design_scores_gemma":[0.00015904209,0.000028397268,0.000722799,0.000020681822,0.00001259919,0.0000020950615,0.000050986113,0.98515576,0.00011440083,0.001994429,0.011622031,0.000116757845],"about_ca_topic_score_codex":0.0000025777597,"about_ca_topic_score_gemma":0.000008552351,"teacher_disagreement_score":0.9743294,"about_ca_system_score_codex":0.000046474797,"about_ca_system_score_gemma":0.000053522035,"threshold_uncertainty_score":0.523979},"labels":[],"label_agreement":null},{"id":"W4417035030","doi":"10.48550/arxiv.2512.03947","title":"Data-Dependent Complexity of First-Order Methods for Binary Classification","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sublinear function; Hyperplane; Iterated function; Data point; Upper and lower bounds; MNIST database; Binary number; Optimization problem; Support vector machine; Time complexity","score_opus":0.33705160535650114,"score_gpt":0.4320574363079129,"score_spread":0.09500583095141174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417035030","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010151407,0.00051015714,0.98605937,0.0036988042,0.0027119068,0.0036630414,0.0010750062,0.00044973218,0.00081687054],"genre_scores_gemma":[0.05286915,0.0004210624,0.94376546,0.00024395282,0.00013878543,0.00070110225,0.0009747194,0.00004750753,0.0008382858],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99289924,0.0006790414,0.0021422952,0.002970282,0.00060456706,0.0007045594],"domain_scores_gemma":[0.9882269,0.0017474744,0.001958511,0.006179516,0.0016741512,0.00021343255],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003559695,0.0008070693,0.0012845272,0.0007245566,0.0005059387,0.00017703866,0.007756327,0.00069684803,0.00011995273],"category_scores_gemma":[0.0021126086,0.00089880207,0.00032598607,0.0013692353,0.0007961604,0.0006735146,0.009289342,0.00078463426,0.000017445529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008581983,0.0071950075,0.10357019,0.011440987,0.0029683183,0.000009965725,0.0056837723,0.03668921,0.0057687485,0.6407706,0.017157089,0.16788791],"study_design_scores_gemma":[0.00064960937,0.00022557896,0.022106716,0.0005947474,0.00028072367,0.0000045545357,0.00006888489,0.94592893,0.0033405153,0.020168172,0.0058893887,0.0007422023],"about_ca_topic_score_codex":0.00013881578,"about_ca_topic_score_gemma":0.000024389929,"teacher_disagreement_score":0.9092397,"about_ca_system_score_codex":0.00031958675,"about_ca_system_score_gemma":0.0007431575,"threshold_uncertainty_score":0.99934626},"labels":[],"label_agreement":null},{"id":"W4417035278","doi":"10.48550/arxiv.2512.04006","title":"Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Centre International de Mathématiques et Informatique de Toulouse; Natural Sciences and Engineering Research Council of Canada","keywords":"Initialization; Artificial neural network; Softmax function; Hadamard transform; Convex function; Convex optimization; Spurious relationship; Function (biology); Regular polygon","score_opus":0.05876001954424071,"score_gpt":0.3319350698524984,"score_spread":0.27317505030825767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417035278","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008670515,0.00044128258,0.97673607,0.0030743417,0.004939299,0.003795857,0.00029972146,0.0007281644,0.0013147509],"genre_scores_gemma":[0.8421898,0.0010389802,0.13995953,0.0038030467,0.0011401154,0.0033171854,0.0009635863,0.00018904233,0.007398737],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99379945,0.00031823004,0.0017706862,0.0020810976,0.000847245,0.0011833165],"domain_scores_gemma":[0.9931518,0.0017534835,0.0013850306,0.0020913417,0.0013959368,0.00022243183],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016429753,0.0009819355,0.0009125023,0.00046224947,0.0017108191,0.0017904362,0.003993063,0.00080236926,0.0000972435],"category_scores_gemma":[0.0018899309,0.0009136777,0.0006512692,0.0012676625,0.0005474375,0.0010076587,0.0025695607,0.0010581202,0.000035974594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002463151,0.00081661,0.159624,0.0013544502,0.0007048001,0.000013771393,0.0036792217,0.17333741,0.00010474609,0.6349862,0.0036314689,0.021500979],"study_design_scores_gemma":[0.00094864704,0.00016786187,0.013954649,0.00074496504,0.00025310257,0.000013875857,0.00008250931,0.94301385,0.002212022,0.032379616,0.0051755197,0.0010533627],"about_ca_topic_score_codex":0.00013784751,"about_ca_topic_score_gemma":0.000029780394,"teacher_disagreement_score":0.83677655,"about_ca_system_score_codex":0.00087140204,"about_ca_system_score_gemma":0.0010568468,"threshold_uncertainty_score":0.99958885},"labels":[],"label_agreement":null},{"id":"W4417170031","doi":"10.1109/sita67914.2025.11273464","title":"LoTAS: A Novel Activation Function for Deep Neural Networks","year":2025,"lang":"","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Activation function; Residual; Smoothness; Artificial neural network; Normalization (sociology); Deep neural networks; Balanced flow; Stability (learning theory)","score_opus":0.01880123241813505,"score_gpt":0.2578916871350734,"score_spread":0.23909045471693832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417170031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004602548,0.000122029945,0.99053645,0.0019719545,0.003132842,0.001733666,0.0000030432955,0.0006256467,0.0018283598],"genre_scores_gemma":[0.6976128,0.000010304513,0.2961863,0.0033343968,0.00022838055,0.00040811722,0.00002883393,0.000025723248,0.002165108],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777997,0.000039508806,0.00059899746,0.0008198736,0.0002475976,0.0005140356],"domain_scores_gemma":[0.99798936,0.00042111357,0.00025028113,0.0006670382,0.00057803636,0.00009418233],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035694137,0.00032295336,0.00027543376,0.0004327068,0.00040684428,0.00046309136,0.00065947644,0.0002550597,0.000055106426],"category_scores_gemma":[0.0002717905,0.00033736345,0.00017097677,0.0016092323,0.00007937549,0.00091545423,0.00027745502,0.00020414242,0.000003106815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013038312,0.0002228598,0.00004666639,0.000046040375,0.000071402734,1.1545094e-7,0.000109137654,0.27719197,0.00021561907,0.5172083,0.0028635878,0.20189396],"study_design_scores_gemma":[0.0009261447,0.00037359842,0.00039365914,0.00007271128,0.000062979154,0.0000018159317,0.0000326783,0.98892766,0.00084502785,0.0073893014,0.00068601634,0.00028839245],"about_ca_topic_score_codex":0.000022530272,"about_ca_topic_score_gemma":0.000006200603,"teacher_disagreement_score":0.7117357,"about_ca_system_score_codex":0.00018373475,"about_ca_system_score_gemma":0.00009106872,"threshold_uncertainty_score":0.99990785},"labels":[],"label_agreement":null},{"id":"W4417298805","doi":"10.48550/arxiv.2505.14371","title":"Layer-wise Quantization for Quantized Optimistic Dual Averaging","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Army Research Office; Centers for Disease Control and Prevention; National Supercomputing Centre Singapore; Norges Forskningsråd; Institute for Catastrophic Loss Reduction; Hasler Stiftung; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Centro Svizzero di Calcolo Scientifico; National Science Foundation","keywords":"Quantization (signal processing); Speedup; Monotone polygon; Convergence (economics); Representation (politics); Artificial neural network; Dual (grammatical number)","score_opus":0.08142263447052059,"score_gpt":0.32273352140403305,"score_spread":0.24131088693351246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417298805","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008299994,0.00013463713,0.98520154,0.0009920027,0.0018440713,0.0013896973,0.00004640968,0.0013520606,0.0007395682],"genre_scores_gemma":[0.50552285,0.00008476053,0.4915281,0.0005878231,0.00018033416,0.0005792858,0.00018199752,0.000043615375,0.0012912473],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99725413,0.000098508855,0.0006753455,0.0011635389,0.0003421148,0.00046637852],"domain_scores_gemma":[0.99750924,0.00044273524,0.0004419913,0.001135279,0.00035445418,0.00011627092],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049076165,0.00044452408,0.00052981277,0.00047006077,0.0002425292,0.0002697186,0.0013530774,0.00033551856,0.00001600781],"category_scores_gemma":[0.00068715465,0.00048923516,0.00023867415,0.0003960318,0.00006362292,0.0002514715,0.0014102275,0.0003986267,0.000020017944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001680733,0.0007353848,0.036697034,0.0021285417,0.0006111372,0.000043959233,0.0031519642,0.33313233,0.0014939699,0.59797,0.015070346,0.008797274],"study_design_scores_gemma":[0.0008637294,0.000080951984,0.0023628378,0.0005652094,0.000104271276,0.0000067573274,0.000015399632,0.97350174,0.0056770034,0.01482881,0.0012134161,0.0007798762],"about_ca_topic_score_codex":0.000034268967,"about_ca_topic_score_gemma":0.0000032535643,"teacher_disagreement_score":0.6403694,"about_ca_system_score_codex":0.00015927861,"about_ca_system_score_gemma":0.00031875668,"threshold_uncertainty_score":0.9997559},"labels":[],"label_agreement":null},{"id":"W4417473694","doi":"10.13140/rg.2.2.32728.97288","title":"An Inexact Modified Quasi-Newton Method for Nonsmooth Regularized Optimization","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Quadratic equation; Convergence (economics); Regularization (linguistics); Measure (data warehouse); Quadratic programming; Quadratic model; Flexibility (engineering); Function (biology); Term (time)","score_opus":0.03143370361791698,"score_gpt":0.3260212385068838,"score_spread":0.29458753488896683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417473694","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016337684,0.000028602068,0.9938875,0.0018739545,0.00031525266,0.0008054964,0.000004478102,0.00085349364,0.0005974817],"genre_scores_gemma":[0.080945045,0.0000093265435,0.91725266,0.00082955405,0.00004001313,0.00022528731,0.000033506025,0.000021254162,0.0006433464],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833685,0.00014296906,0.00038246394,0.0006390883,0.0001846085,0.00031403254],"domain_scores_gemma":[0.9983986,0.00027025276,0.00016361661,0.0008398084,0.00023281573,0.00009488414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006067196,0.00021176535,0.0002725721,0.00035469502,0.0002267856,0.00013759173,0.0009444645,0.0001474187,0.0000108410595],"category_scores_gemma":[0.00030509566,0.00021149292,0.00009588381,0.00086895894,0.000039859286,0.00063228415,0.00013693488,0.00011144994,0.000003982419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012704908,0.0006329473,0.0036006502,0.00007698181,0.00010530109,0.000002090063,0.00057839695,0.41308543,0.007516717,0.55441844,0.002660976,0.017195014],"study_design_scores_gemma":[0.0006227857,0.00016965541,0.0010664654,0.000032481174,0.00002421739,0.000001829853,0.000010788031,0.98017055,0.009688645,0.0076054106,0.00039410236,0.00021309947],"about_ca_topic_score_codex":0.000034383367,"about_ca_topic_score_gemma":0.0000022753104,"teacher_disagreement_score":0.5670851,"about_ca_system_score_codex":0.000086703454,"about_ca_system_score_gemma":0.00011359886,"threshold_uncertainty_score":0.86244315},"labels":[],"label_agreement":null},{"id":"W6911081839","doi":"10.5267/j.ac.2025.1.003","title":"The convergence of AI and portfolio optimization: A bibliometric exploration of research trends","year":2025,"lang":"en","type":"article","venue":"Accounting","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Portfolio; Transformative learning; Context (archaeology); Field (mathematics); Bibliometrics; Convergence (economics); Domain (mathematical analysis); Application portfolio management; Technological convergence; Key (lock)","score_opus":0.04978812077141731,"score_gpt":0.36963154019082506,"score_spread":0.31984341941940775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6911081839","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015761213,0.00038734762,0.99496233,0.00073366374,0.00013130125,0.00009700956,4.948018e-7,0.000053287986,0.0020584462],"genre_scores_gemma":[0.9256153,0.0002668463,0.0738336,0.00004612874,0.0000118272,0.000025027894,0.0000012788425,0.000003932365,0.00019605315],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896926,0.00004977106,0.00030598685,0.00017593536,0.00035742577,0.00014159619],"domain_scores_gemma":[0.99827814,0.0004139014,0.00015087136,0.00032230446,0.0008190687,0.000015736972],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.0013019525,0.000054316333,0.00009609165,0.010928798,0.0001793606,0.00011917729,0.00047110228,0.000036351517,0.000007146897],"category_scores_gemma":[0.0006754731,0.000044291475,0.000019072573,0.0550902,0.0001341968,0.0008588152,0.00027380875,0.000090467394,3.1451924e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001371935,0.00006810976,0.01888217,0.00009825329,0.000036959707,0.0000010640466,0.00073444523,0.021073176,0.0003676974,0.7811401,0.005331031,0.17225327],"study_design_scores_gemma":[0.0001635177,0.00005621257,0.003988086,0.0000900502,0.000005825198,0.0000015436545,0.00012323898,0.98029697,0.005208015,0.009700126,0.0002950726,0.000071369366],"about_ca_topic_score_codex":0.000036016605,"about_ca_topic_score_gemma":0.0000015665557,"teacher_disagreement_score":0.95922375,"about_ca_system_score_codex":0.000014193556,"about_ca_system_score_gemma":0.00007137802,"threshold_uncertainty_score":0.97516525},"labels":[],"label_agreement":null},{"id":"W6912192316","doi":"10.5281/zenodo.16623955","title":"MLP Model Results and Hidden Node Weight Analysis","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Python (programming language); Pattern recognition (psychology); Correlation; Artificial neural network; Statistical analysis; Connection (principal bundle)","score_opus":0.024573880405203308,"score_gpt":0.251922511842871,"score_spread":0.2273486314376677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6912192316","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000013963112,0.000056303044,0.46283796,0.0005662958,0.00007128269,0.00030608452,0.5264732,0.0008441973,0.008843234],"genre_scores_gemma":[0.00014287414,0.00041534862,0.021524705,0.00026809797,0.000058598573,1.487553e-7,0.9763745,0.00024348787,0.0009722128],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971643,0.0002839102,0.0004932366,0.0010646838,0.00058695895,0.0004069126],"domain_scores_gemma":[0.996982,0.00006641773,0.0002809825,0.001763969,0.0006975659,0.00020905714],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007500937,0.00029897792,0.0003765084,0.0014668052,0.0014273443,0.0015786347,0.0034611532,0.00020913046,0.00051546993],"category_scores_gemma":[0.0009596165,0.00031914536,0.000108104425,0.0023732716,0.00015300332,0.00034826048,0.004615363,0.00044538226,0.00027211357],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018765017,0.000063567684,7.1607076e-8,0.000054895376,0.00018563205,0.000009078736,0.00013174159,0.0008863435,0.000005667326,0.0045973286,0.9878843,0.006162604],"study_design_scores_gemma":[0.000305863,0.00007127098,0.0000064803057,0.000045340854,0.00016560305,0.00001744528,0.0000072209045,0.10367071,0.000018401082,0.0005152777,0.89489675,0.00027965795],"about_ca_topic_score_codex":0.00003171424,"about_ca_topic_score_gemma":7.6451175e-7,"teacher_disagreement_score":0.44990128,"about_ca_system_score_codex":0.00016532316,"about_ca_system_score_gemma":0.000014258959,"threshold_uncertainty_score":0.9999261},"labels":[],"label_agreement":null},{"id":"W6923523305","doi":"10.1371/journal.pone.0273569.s001","title":"Model fit by rank parameter and MME-weighted edges (2012 quarter 3 to 2015 quarter 2).","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Rank (graph theory); Window (computing); Statistical analysis; Maximum likelihood","score_opus":0.03877211966217909,"score_gpt":0.25975954624280706,"score_spread":0.22098742658062798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6923523305","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004899566,0.0006976391,0.92295784,0.0061569666,0.0002565185,0.0013524255,0.06556563,0.0011510554,0.0013719753],"genre_scores_gemma":[0.5482993,0.0000063429575,0.3790173,0.019635329,0.00023206533,0.008952544,0.036771342,0.00017997474,0.0069057913],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985964,0.00005770812,0.00020549582,0.00049001747,0.00033366252,0.0003167588],"domain_scores_gemma":[0.9990026,0.0001262412,0.00007583039,0.000532098,0.00009179248,0.00017148824],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007707849,0.00017966743,0.00016633063,0.00015532896,0.00018860375,0.00016566266,0.00070020935,0.000052126787,0.016212782],"category_scores_gemma":[0.00008850624,0.00018055769,0.000047033504,0.00031960863,0.0000064426563,0.000424075,0.0005072981,0.00015974157,0.0002760163],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004594205,0.00003461541,0.0000054787765,0.000009720235,0.000006649924,0.0000024117628,0.00057891,0.00076324976,0.000024497127,0.0002008142,0.99712604,0.0012430439],"study_design_scores_gemma":[0.0003795833,0.00029242184,0.00006524701,0.00007658239,0.0000059446165,0.000021305608,0.000034827714,0.88829833,0.00045103775,0.0018128825,0.10810553,0.00045628578],"about_ca_topic_score_codex":0.0000027447684,"about_ca_topic_score_gemma":7.380648e-7,"teacher_disagreement_score":0.8890205,"about_ca_system_score_codex":0.000051242787,"about_ca_system_score_gemma":0.000034813616,"threshold_uncertainty_score":0.98468655},"labels":[],"label_agreement":null},{"id":"W6930388102","doi":"10.5281/zenodo.12193255","title":"NLPModelsJuMP.jl","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Nonlinear system; Mathematical model; Jump; Process (computing); Nonlinear programming","score_opus":0.03476828824167595,"score_gpt":0.2501411934190127,"score_spread":0.21537290517733676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930388102","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.556117e-7,0.00025694037,0.46851474,0.00027917998,0.00022612835,0.00028126617,0.00008267726,0.0059341276,0.5244248],"genre_scores_gemma":[0.0010034154,0.00035662798,0.06096387,0.0004110488,0.0006575602,2.8647284e-7,0.0015689416,0.02580738,0.9092309],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979099,0.00015165062,0.00024740567,0.00080889324,0.0004986675,0.00038345982],"domain_scores_gemma":[0.9983449,0.0000113367305,0.000142124,0.0010902889,0.00023869143,0.00017268102],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003737307,0.00026010163,0.00021524867,0.00083783496,0.00047962714,0.0015514912,0.0029074561,0.00018342404,0.014805325],"category_scores_gemma":[0.00020418361,0.00027411603,0.0000823937,0.00088902673,0.00012267203,0.00018460937,0.0026730462,0.00036781243,0.038763948],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015797601,0.000032831293,1.156648e-8,0.00007428373,0.00003402114,0.00001471767,0.0002240911,0.000015907019,0.000024249824,0.11167634,0.8634876,0.02441438],"study_design_scores_gemma":[0.000117540396,0.00009472959,5.322055e-7,0.00015696281,0.000013652072,0.00008707268,0.000012857678,0.0064260303,0.00003719588,0.0037461643,0.9890275,0.00027975783],"about_ca_topic_score_codex":0.0000147750125,"about_ca_topic_score_gemma":1.4287878e-7,"teacher_disagreement_score":0.40755087,"about_ca_system_score_codex":0.00013850373,"about_ca_system_score_gemma":0.0000053253025,"threshold_uncertainty_score":0.9999711},"labels":[],"label_agreement":null},{"id":"W6958264125","doi":"10.6084/m9.figshare.28334759.v1","title":"A Lightweight Note on Success in Mergers and Acquisitions","year":2025,"lang":"en","type":"article","venue":"Figshare","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mergers and acquisitions; Shareholder; Value (mathematics); Shareholder value; Quarter (Canadian coin)","score_opus":0.014225558871695257,"score_gpt":0.27463711472528185,"score_spread":0.2604115558535866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958264125","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001314093,0.0013483536,0.7324036,0.015464321,0.00090867304,0.0030322897,0.044722177,0.0036678524,0.19713865],"genre_scores_gemma":[0.89979064,0.000019025527,0.0814434,0.006408949,0.00007628913,0.0013806943,0.009084317,0.00003212,0.0017645578],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994524,0.000016766342,0.00010312114,0.00022303146,0.000086016385,0.000118642],"domain_scores_gemma":[0.9995444,0.000121194316,0.000027632812,0.00023376067,0.000041367428,0.000031688567],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00002597082,0.000072403884,0.00007467452,0.0002518801,0.00005438917,0.000076627264,0.00031354403,0.000044696135,0.0022370492],"category_scores_gemma":[0.00021528611,0.00007060831,0.000017252587,0.0005550582,0.0000042440215,0.0001718724,0.00014654934,0.00006844779,0.00007176677],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001106086,0.00017499282,0.00031698484,0.00015749861,0.000017815964,0.000050960858,0.0008584261,0.0019319628,0.00008472393,0.1983344,0.7794518,0.018609416],"study_design_scores_gemma":[0.0017850783,0.00031050612,0.028668175,0.0110958135,0.000013270691,0.000011194751,0.000026456111,0.7925878,0.022069873,0.03166503,0.11051614,0.001250653],"about_ca_topic_score_codex":0.0000032183605,"about_ca_topic_score_gemma":0.000003860402,"teacher_disagreement_score":0.89847654,"about_ca_system_score_codex":0.00003309121,"about_ca_system_score_gemma":0.00003352614,"threshold_uncertainty_score":0.99867505},"labels":[],"label_agreement":null},{"id":"W6979256277","doi":"","title":"SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institut de Valorisation des Données; Canada First Research Excellence Fund","keywords":"Maxima and minima; Artificial neural network; Monotonic function; Stochastic gradient descent; Gradient descent; Energy (signal processing); Entropy (arrow of time); Function (biology)","score_opus":0.028487612075489603,"score_gpt":0.25530707651169304,"score_spread":0.22681946443620343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979256277","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017376151,0.0002979577,0.96615946,0.0027302587,0.0006984038,0.00017939179,0.0000011955024,0.0007348017,0.011822357],"genre_scores_gemma":[0.96498585,0.00004533167,0.027273111,0.0064396127,0.00012820447,0.000085636944,0.000008079634,0.000020975935,0.001013207],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855703,0.000092180024,0.00030041303,0.0004901059,0.00020918326,0.00035109266],"domain_scores_gemma":[0.9987873,0.00019165633,0.00011340133,0.0007656837,0.00006996362,0.00007200351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001313301,0.00020408866,0.00021654795,0.00015650397,0.00019626063,0.00008990384,0.0011604726,0.000089397785,0.000040073894],"category_scores_gemma":[0.00013455434,0.00019680135,0.00008112829,0.0010068514,0.00005618087,0.00022560885,0.00029252563,0.00012902208,0.000019454399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015546713,0.00007145278,0.0029137346,0.000013157141,0.00004753299,0.000015738711,0.00050082646,0.03515611,0.00006111553,0.9159325,0.00517043,0.04010189],"study_design_scores_gemma":[0.0006106382,0.00022141868,0.0124306725,0.00024950426,0.000023853345,0.000015678574,0.000031059557,0.9310589,0.00033392533,0.04948448,0.005116626,0.00042324196],"about_ca_topic_score_codex":0.000019458086,"about_ca_topic_score_gemma":0.0000068080853,"teacher_disagreement_score":0.94760966,"about_ca_system_score_codex":0.000058814505,"about_ca_system_score_gemma":0.000091502625,"threshold_uncertainty_score":0.8025326},"labels":[],"label_agreement":null},{"id":"W6979262665","doi":"","title":"Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation Dynamics","year":2024,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Air Canada","funders":"","keywords":"Computation; Asynchronous communication; Constant (computer programming); Model of computation; Stochastic optimization; Stochastic modelling; Stochastic process; Computational complexity theory","score_opus":0.030013650413624287,"score_gpt":0.17233545579017745,"score_spread":0.14232180537655317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979262665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028551382,0.000029070012,0.9933901,0.00014103724,0.00009432816,0.00027100893,0.0000061688143,0.00076375407,0.0024494333],"genre_scores_gemma":[0.8731327,0.000005120289,0.12629882,0.0000499388,0.000013234091,0.0000020108537,0.000049417624,0.00001756615,0.0004311995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998934,0.000057150177,0.00015893852,0.000525958,0.00009671556,0.00022729461],"domain_scores_gemma":[0.9993898,0.00014416224,0.00006016877,0.00025432723,0.00007976866,0.00007174232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010874545,0.00017408686,0.0001596942,0.00048507578,0.00008364034,0.00014615452,0.00041617575,0.00006799053,0.00002591582],"category_scores_gemma":[0.000010324546,0.00018230417,0.00004013679,0.001359806,0.0000894543,0.0008474868,0.0001087629,0.00015244949,0.000041423264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010146748,0.00002252906,0.000033871034,0.000010612826,0.000009971938,0.0000623648,0.00010541355,0.6069556,8.007134e-7,0.392655,0.00003957664,0.00009410436],"study_design_scores_gemma":[0.00028103418,0.00009818791,0.00011067146,0.00010065436,0.000013389905,0.000017431496,0.000035895904,0.9543981,0.0000035336964,0.044725,0.0000036813205,0.00021243765],"about_ca_topic_score_codex":0.00002591183,"about_ca_topic_score_gemma":0.000017558057,"teacher_disagreement_score":0.8702776,"about_ca_system_score_codex":0.00024495102,"about_ca_system_score_gemma":0.00009767748,"threshold_uncertainty_score":0.7434148},"labels":[],"label_agreement":null},{"id":"W6979330535","doi":"","title":"Hybrid least squares for learning functions from highly noisy data","year":2025,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Air Force Office of Scientific Research; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Leverage (statistics); Noise (video); Linear subspace; Noisy data; Stochastic approximation; Function approximation; Function (biology); Computational complexity theory; Sampling (signal processing)","score_opus":0.07134795580049684,"score_gpt":0.19998069208996666,"score_spread":0.1286327362894698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979330535","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008601932,0.000027797754,0.9882651,0.00023443451,0.00037643375,0.00022079596,0.000059089787,0.0006014921,0.0016129159],"genre_scores_gemma":[0.9683213,0.000011810169,0.027547413,0.00011334357,0.00003290516,0.0000019879774,0.00013131964,0.000008184407,0.0038317183],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885064,0.000045453573,0.00012406448,0.0007197893,0.000050398074,0.00020964656],"domain_scores_gemma":[0.9984053,0.00028075484,0.00008201651,0.0010353334,0.0001322845,0.00006432717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012623079,0.00012714631,0.00013365358,0.0002364614,0.0003061052,0.00009662235,0.0015410644,0.000046155117,0.000018026823],"category_scores_gemma":[0.00015605663,0.0001513448,0.000056097906,0.00058451,0.000059582937,0.00068525434,0.0007097378,0.00012526062,0.00003111729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004634267,0.00011774565,0.0035461413,0.000017357073,0.00010879701,0.000025230103,0.00008433751,0.13760816,0.00014418499,0.8385446,0.015389503,0.0043676062],"study_design_scores_gemma":[0.00043430814,0.000055840675,0.0004396294,0.000029080575,0.00004550708,8.2294054e-7,0.000058398084,0.9623287,0.0002957984,0.02718101,0.008962771,0.00016814578],"about_ca_topic_score_codex":0.00011149303,"about_ca_topic_score_gemma":0.000015810743,"teacher_disagreement_score":0.9607177,"about_ca_system_score_codex":0.000070801514,"about_ca_system_score_gemma":0.0000853803,"threshold_uncertainty_score":0.6171661},"labels":[],"label_agreement":null},{"id":"W6979348375","doi":"","title":"Approximation Rates in Besov Norms and Sample-Complexity of Kolmogorov-Arnold Networks with Residual Connections","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Core Research for Evolutional Science and Technology; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Residual; Bounded function; Complement (music); Bounding overwatch; Superposition principle; Norm (philosophy); Perceptron; Class (philosophy); Domain (mathematical analysis)","score_opus":0.035726082723056996,"score_gpt":0.2649069276680074,"score_spread":0.2291808449449504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979348375","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3238899,0.000043896212,0.6749324,0.0005294756,0.000050548526,0.00022112587,0.0000022846566,0.000113584516,0.00021674522],"genre_scores_gemma":[0.8897723,0.0000148125,0.11000712,0.00010574986,0.000011867027,0.000044191704,0.0000070734914,0.0000055850387,0.000031308915],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99907595,0.00004786744,0.00027450506,0.00031067873,0.00011249812,0.00017847469],"domain_scores_gemma":[0.9991427,0.0003157321,0.000115468174,0.00029487957,0.00009722567,0.00003399237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021744036,0.00011909893,0.00018442588,0.00024709324,0.0000960621,0.000041892497,0.00027058358,0.000063471685,0.0000051749857],"category_scores_gemma":[0.00017948486,0.0001047362,0.000016670847,0.00087992323,0.0001826809,0.00029977196,0.000141306,0.00012537643,7.040954e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028167042,0.0001255612,0.6398206,0.000041486182,0.000028145467,0.0000013322656,0.00044186125,0.00804789,0.00019731569,0.34967753,0.00016991157,0.0014202341],"study_design_scores_gemma":[0.00085587153,0.00019872475,0.645601,0.00017540737,0.000017068094,0.0000068030076,0.00010052479,0.31392765,0.0067966417,0.032035712,0.000037915393,0.00024668314],"about_ca_topic_score_codex":0.00019507951,"about_ca_topic_score_gemma":0.00011057968,"teacher_disagreement_score":0.5658824,"about_ca_system_score_codex":0.000035719688,"about_ca_system_score_gemma":0.000041662057,"threshold_uncertainty_score":0.42710185},"labels":[],"label_agreement":null},{"id":"W7008845853","doi":"","title":"Deep networks training and generalization: insights from linearization","year":2023,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Institute for Catastrophic Loss Reduction","keywords":"Linearization; Reprojection error; Counterweight","score_opus":0.012613219557736893,"score_gpt":0.18531507385695145,"score_spread":0.17270185429921456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7008845853","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033338442,0.017172512,0.94179165,0.000263922,0.0033094613,0.0005286809,0.000019930603,0.0006650071,0.0029103968],"genre_scores_gemma":[0.8313843,0.005177314,0.106123276,0.0005124991,0.0015023501,0.00015816368,0.006239609,0.00020752318,0.048694946],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99701136,0.00019951888,0.0005969801,0.0010564623,0.0006831423,0.0004525036],"domain_scores_gemma":[0.9977543,0.00025590506,0.0005719143,0.00048971456,0.00054734864,0.00038083308],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00012949905,0.00054246216,0.00048016396,0.00049858383,0.0063849078,0.00032665327,0.0006227533,0.0007090761,0.000020348789],"category_scores_gemma":[0.00013537862,0.00067865994,0.00016970368,0.0010930053,0.00026236984,0.0008688352,0.0003427992,0.00041517313,0.000027907892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000113277834,0.00011106777,0.002329921,0.000075712975,0.00033870045,0.00090190145,0.1556586,0.5331857,0.0012551927,0.2906577,0.00023972562,0.015132469],"study_design_scores_gemma":[0.00061292364,0.00009218702,0.012233358,0.00037027732,0.00021878692,0.00015382686,0.008672676,0.97111756,0.00087447587,0.0028160033,0.002176347,0.00066156854],"about_ca_topic_score_codex":0.01728208,"about_ca_topic_score_gemma":0.0054043364,"teacher_disagreement_score":0.8356684,"about_ca_system_score_codex":0.0020382153,"about_ca_system_score_gemma":0.0009685268,"threshold_uncertainty_score":0.99956644},"labels":[],"label_agreement":null},{"id":"W7020289426","doi":"","title":"La dynamique de transport des réseaux de neurones : un principe de moindre action pour l'apprentissage en profondeur","year":2023,"lang":"en","type":"article","venue":"theses.fr (ABES)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Context (archaeology); Transport policy; Mass transport; Agrégation","score_opus":0.027247349871644743,"score_gpt":0.2865686535047482,"score_spread":0.25932130363310346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7020289426","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3223183,0.000014110534,0.67283916,0.00031408752,0.000080139835,0.00029735838,0.0000056190033,0.0014176244,0.0027136414],"genre_scores_gemma":[0.8813546,0.00010101491,0.118033186,0.00007406137,0.00004916632,0.00015675841,0.0000099043655,0.000046438807,0.0001749134],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797016,0.00033993568,0.0002784314,0.0004665466,0.000299226,0.00064570195],"domain_scores_gemma":[0.99875134,0.00031900694,0.00011120463,0.0005488103,0.00007789144,0.00019176914],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009933118,0.00024758393,0.00021024075,0.0002678431,0.00018059193,0.00010243826,0.00095900986,0.00018266955,0.000036470592],"category_scores_gemma":[0.00021740994,0.00025213778,0.00010351748,0.00077890494,0.000099448065,0.00043416666,0.00017325184,0.0003132384,0.00004598913],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093297276,0.0009039219,0.07758809,0.0006163811,0.00020841816,0.0009833873,0.055214763,0.0325802,0.062042646,0.64620167,0.00039021875,0.12317699],"study_design_scores_gemma":[0.0008194152,0.0002266996,0.18535282,0.00025916455,0.00007614078,0.00061532255,0.0016224388,0.60608685,0.09308235,0.1099412,0.0010754454,0.00084213284],"about_ca_topic_score_codex":0.00018780894,"about_ca_topic_score_gemma":0.000053173284,"teacher_disagreement_score":0.57350665,"about_ca_system_score_codex":0.00024770945,"about_ca_system_score_gemma":0.00026009852,"threshold_uncertainty_score":0.9999931},"labels":[],"label_agreement":null},{"id":"W7023359142","doi":"","title":"Outflow of Weddell Sea waters into the Scotia Sea through the western sector of the South Scotia Ridge","year":2017,"lang":"en","type":"other","venue":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ridge; Outflow; Nova scotia; Weddell Sea Bottom Water; Submarine pipeline","score_opus":0.11402372075141008,"score_gpt":0.3214890865410757,"score_spread":0.20746536578966562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023359142","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003943056,0.0016556648,0.15106411,0.006811,0.0027844151,0.0054944255,0.0030828735,0.0006051196,0.8281081],"genre_scores_gemma":[0.5612312,0.0003172439,0.0066218865,0.0013546337,0.0015138806,0.0004299035,0.00029733544,0.00090241013,0.42733148],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9826156,0.00042014342,0.00072018773,0.0010374069,0.014357029,0.0008496423],"domain_scores_gemma":[0.9853523,0.0011973183,0.0010267907,0.0029304018,0.009319473,0.000173728],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0054709376,0.00058400637,0.00062214205,0.0003062119,0.00059766666,0.0012202114,0.008291404,0.00036043723,0.00009795406],"category_scores_gemma":[0.00916685,0.00033351124,0.00040254663,0.0010818113,0.002501864,0.00090517174,0.0023046888,0.0010141133,0.00019325495],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032834967,0.00020259981,0.00091729884,0.0002054479,0.00034876753,0.0000053375193,0.0051794057,0.0004258102,0.00002409433,0.025129018,0.9663417,0.0011877042],"study_design_scores_gemma":[0.0012861065,0.00037215534,0.0009962507,0.0018849619,0.00007602998,0.000027437927,0.00037275336,0.008475609,0.0011026835,0.025952127,0.95837337,0.0010805342],"about_ca_topic_score_codex":0.0023988038,"about_ca_topic_score_gemma":0.0011798909,"teacher_disagreement_score":0.5608369,"about_ca_system_score_codex":0.0015563612,"about_ca_system_score_gemma":0.0072618276,"threshold_uncertainty_score":0.99991167},"labels":[],"label_agreement":null},{"id":"W7024444477","doi":"","title":"Saint-Pourcain-sur-Besbre – Accès sud, Le Pal, RD 296","year":2024,"lang":"fr","type":"other","venue":"Industrias Culturais (Universidade de Coimbra)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medical prescription; Quarter (Canadian coin); Population","score_opus":0.038573828443967,"score_gpt":0.24570009063456164,"score_spread":0.20712626219059463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024444477","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042368178,0.0035790643,0.36040705,0.07490306,0.0048349383,0.0023127636,0.00043667547,0.0028368132,0.55026597],"genre_scores_gemma":[0.008639862,0.00019622919,0.030436782,0.0011073411,0.0012553778,0.00007047597,0.0002015367,0.0005246837,0.9575677],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938379,0.0004754628,0.0008022654,0.002208674,0.0010543946,0.001621325],"domain_scores_gemma":[0.9956247,0.000392951,0.00079342467,0.0017136731,0.0006283379,0.0008468648],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.00060511805,0.0013774163,0.0011752321,0.0012865224,0.00047849878,0.001629004,0.0037320533,0.002782647,0.006499475],"category_scores_gemma":[0.00071852835,0.0014987093,0.0007056687,0.0032479125,0.0006893307,0.0012733778,0.0015280865,0.002537246,0.0040590214],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025529922,0.00021085812,0.000035528526,0.00015840135,0.000492734,0.000867592,0.0031689657,0.00070295844,0.0003712853,0.3185572,0.6529117,0.022497192],"study_design_scores_gemma":[0.0016852582,0.00032742362,0.0006989792,0.0020471727,0.00038615437,0.00049301574,0.0017271285,0.021476269,0.0007793141,0.0025679609,0.9658236,0.0019877162],"about_ca_topic_score_codex":0.0037384743,"about_ca_topic_score_gemma":0.00032906272,"teacher_disagreement_score":0.40730175,"about_ca_system_score_codex":0.0019438175,"about_ca_system_score_gemma":0.0015362921,"threshold_uncertainty_score":0.99989766},"labels":[],"label_agreement":null},{"id":"W7024763545","doi":"","title":"Studies in Canadian Literature/ Études en Littérature canadienne, vol. 27, n. 1, 2002, \"Past Matters: History and Canadian Fiction\"/ Choses du passé: l'histoire et le roman historique au Canada\"","year":2015,"lang":"fr","type":"other","venue":"Institutional Research Information System (University of Udine)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Period (music); Government (linguistics); Subject (documents)","score_opus":0.03771595059587391,"score_gpt":0.23495079659770002,"score_spread":0.19723484600182611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024763545","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00091124396,0.016693117,0.013001643,0.0581724,0.011284537,0.003475275,0.0037366885,0.00024947352,0.8924756],"genre_scores_gemma":[0.8401299,0.0012776175,0.008464976,0.0014220934,0.0009772741,0.00006359506,0.0016022807,0.000116390096,0.14594589],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964686,0.00045643863,0.0005468881,0.00049220293,0.0010414924,0.000994377],"domain_scores_gemma":[0.99358445,0.00019349005,0.00038523556,0.00048629526,0.0039383653,0.001412175],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021084067,0.00041063438,0.000578276,0.003888918,0.0010109029,0.00012851096,0.0010348761,0.0005233094,0.00016149024],"category_scores_gemma":[0.0009506109,0.0005132391,0.000068794536,0.0014971455,0.001011389,0.002432106,0.0002549748,0.0008204203,0.000029406909],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000015674537,0.000014256585,0.0003397412,0.0007483122,0.000084134015,0.0002163678,0.017087819,0.0013576089,4.8143477e-7,0.47383866,0.50607294,0.00022403976],"study_design_scores_gemma":[0.000527707,0.000070775255,0.0024152277,0.0026702462,0.000013757985,0.0001630663,0.007713861,0.006539191,3.7073818e-7,0.000025259491,0.97946084,0.00039967583],"about_ca_topic_score_codex":0.9993462,"about_ca_topic_score_gemma":0.9999416,"teacher_disagreement_score":0.8392186,"about_ca_system_score_codex":0.08654234,"about_ca_system_score_gemma":0.07141974,"threshold_uncertainty_score":0.9997319},"labels":[],"label_agreement":null},{"id":"W7024796571","doi":"","title":"Simmons Reports First Quarter Net Income of $22 Million","year":2017,"lang":"en","type":"other","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Net income","score_opus":0.010714431326778674,"score_gpt":0.24184370842735825,"score_spread":0.23112927710057957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024796571","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.843076e-7,0.00007605395,0.57437253,0.000090116504,0.0004362778,0.0002019627,0.0000034729255,0.00042924294,0.42438987],"genre_scores_gemma":[0.004661025,0.00007845621,0.34036165,0.000082035236,0.00014075647,0.000059208083,0.000024203071,0.00019046337,0.6544022],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99874556,0.00001725202,0.00030595207,0.00045154704,0.0002992164,0.00018046184],"domain_scores_gemma":[0.9971226,0.000036135145,0.0007709695,0.001940792,0.000063036736,0.00006650689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014019471,0.00021354933,0.0003310091,0.0004020066,0.00005694589,0.000070653296,0.00091965933,0.00022990686,0.0006636702],"category_scores_gemma":[0.000064805965,0.00018687417,0.00009033724,0.00013139687,0.00008177977,0.00011425627,0.00027379056,0.00009380781,0.000022306343],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.5779526e-7,0.000029338518,0.00019777626,0.00004151262,0.00002268333,0.000029869596,0.000045423963,0.000018623665,0.0000022863499,0.009599006,0.9894046,0.0006083136],"study_design_scores_gemma":[0.00032350942,0.00032877858,0.00052915834,0.0014241007,0.000041712337,0.00015232351,0.000006817681,0.016850654,0.00055591174,0.007900744,0.97080064,0.0010856712],"about_ca_topic_score_codex":0.0003655451,"about_ca_topic_score_gemma":0.000100435616,"teacher_disagreement_score":0.23401088,"about_ca_system_score_codex":0.000023902812,"about_ca_system_score_gemma":0.000046323777,"threshold_uncertainty_score":0.7620507},"labels":[],"label_agreement":null},{"id":"W7025304037","doi":"","title":"Women as Owners and Collectors in de Ricci’s &lt;i&gt;Census of Medieval and Renaissance Manuscripts in the United States and Canada&lt;/i&gt;","year":2024,"lang":"en","type":"book-chapter","venue":"UWA Profiles and Research Repository (University of Western Australia)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"The Renaissance; Middle Ages; Clothing; Craft","score_opus":0.047091515726244586,"score_gpt":0.2677636247299558,"score_spread":0.2206721090037112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025304037","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99448675,0.00092928635,0.0001695642,0.00079845544,0.00007508795,0.0006935252,0.00006221107,0.00002713317,0.002757978],"genre_scores_gemma":[0.8874468,0.002955487,0.0013283367,0.000022423936,0.000025237936,0.0000071740333,0.0000256644,0.000026850657,0.10816199],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9982625,0.00014388203,0.00022092804,0.00046314378,0.0005692825,0.00034025527],"domain_scores_gemma":[0.99900806,0.0002612339,0.00014092989,0.00026328687,0.00016218769,0.00016431676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007126642,0.00019052862,0.0003215585,0.00065043534,0.00017135694,0.00009285077,0.00044370614,0.00017788103,0.0000032172372],"category_scores_gemma":[0.00002721616,0.00017176941,0.000020530593,0.00025612276,0.0008460988,0.00013888448,0.00043212,0.00039707604,1.5726982e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023238773,0.0005972087,0.08476663,0.016184201,0.0016307469,0.017488964,0.18947943,0.0006190267,0.02564763,0.58933294,0.06663886,0.0052905297],"study_design_scores_gemma":[0.014679765,0.012656843,0.50524276,0.025650864,0.0006507284,0.0038568487,0.049477343,0.060494713,0.013671276,0.117436744,0.18872444,0.0074576563],"about_ca_topic_score_codex":0.06147551,"about_ca_topic_score_gemma":0.017965304,"teacher_disagreement_score":0.47189617,"about_ca_system_score_codex":0.0002245098,"about_ca_system_score_gemma":0.0002514144,"threshold_uncertainty_score":0.9999543},"labels":[],"label_agreement":null},{"id":"W7031633709","doi":"","title":"A quick note","year":2018,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Curiosity; Publication; Task (project management); Work (physics); Editorial board; Field (mathematics); Order (exchange)","score_opus":0.0803168008890549,"score_gpt":0.32001436474442935,"score_spread":0.23969756385537444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7031633709","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34087646,0.000012854917,0.6565368,0.0002920241,0.0003873679,0.00020096957,0.000003964288,0.00081431697,0.0008752273],"genre_scores_gemma":[0.97796905,0.000010952044,0.0171537,0.00082363776,0.00016242031,0.0000018433718,0.0000053196914,0.000033445813,0.0038395997],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978768,0.00015807227,0.00023945683,0.000748256,0.00044532298,0.00053209084],"domain_scores_gemma":[0.9979908,0.00008605194,0.00018452406,0.0011044886,0.00034766475,0.00028647095],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031353635,0.0002855977,0.00024673648,0.00064980786,0.00033647966,0.0004120687,0.002317724,0.00018205082,0.000028132663],"category_scores_gemma":[0.000068851754,0.00032622492,0.00010940957,0.0011500722,0.00022365831,0.0025909115,0.00092052907,0.0003194713,0.00065249583],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010206863,0.0002945775,0.94702995,0.00004704981,0.00009441224,0.00042913688,0.0026550808,0.000053723794,0.0019926468,0.039837025,0.000026039377,0.0074382774],"study_design_scores_gemma":[0.0031134451,0.0016243827,0.9246373,0.0004334977,0.000110612236,0.00027879572,0.0001236289,0.00028859227,0.04016603,0.008260235,0.018636199,0.0023272831],"about_ca_topic_score_codex":0.0000025928468,"about_ca_topic_score_gemma":0.00015516678,"teacher_disagreement_score":0.63938314,"about_ca_system_score_codex":0.00020785019,"about_ca_system_score_gemma":0.00012214443,"threshold_uncertainty_score":0.999919},"labels":[],"label_agreement":null},{"id":"W7039154034","doi":"","title":"Limitations of information : theoretic generalization bounds for gradient descent methods in stochastic convex optimization","year":2023,"lang":"en","type":"article","venue":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Vetenskapsrådet; University of Toronto","keywords":"Minimax; Generalization; Stochastic gradient descent; Gradient descent; Mutual information; Regular polygon; Convex optimization; Convex function","score_opus":0.06181125478238244,"score_gpt":0.3177407573990477,"score_spread":0.2559295026166653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039154034","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008226661,0.000043477074,0.9932926,0.0026352517,0.00044832204,0.0014811311,0.00017654178,0.0008310298,0.0002689641],"genre_scores_gemma":[0.09498134,0.00009160149,0.901021,0.00009870068,0.000013017475,0.0008552489,0.002890169,0.00001780401,0.000031142157],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976309,0.000074812575,0.0011411638,0.0004386757,0.0003544534,0.00036000845],"domain_scores_gemma":[0.9964871,0.0002149543,0.0008371681,0.0010626544,0.0013166453,0.00008149043],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011550423,0.0002333663,0.0003514286,0.003299701,0.00015590111,0.00009511631,0.0011533846,0.00022040604,0.000009469899],"category_scores_gemma":[0.004840326,0.00024969905,0.00008015257,0.0048912894,0.0003585583,0.0019508785,0.00041466305,0.00015343253,0.000005510652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011167719,0.000103655715,0.00009538179,0.000070884074,0.000017568396,1.8993005e-7,0.00020475079,0.3286742,0.00017418005,0.65508914,0.00094277156,0.01461612],"study_design_scores_gemma":[0.0007012177,0.00012425937,0.00025407807,0.00009836949,0.000027094562,0.0000026400394,0.000079228215,0.98313177,0.0039627845,0.008880677,0.002512901,0.00022496478],"about_ca_topic_score_codex":0.000028310267,"about_ca_topic_score_gemma":0.0000078366065,"teacher_disagreement_score":0.65445757,"about_ca_system_score_codex":0.00015152812,"about_ca_system_score_gemma":0.00024269531,"threshold_uncertainty_score":0.9999955},"labels":[],"label_agreement":null},{"id":"W7043660303","doi":"","title":"Stochastic variance reduced gradient for policy evaluation with fewer gradient evaluations","year":2020,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Convergence (economics); Gradient method; Computation; Variance (accounting); Function (biology); Gradient descent; Bellman equation","score_opus":0.033323809386387127,"score_gpt":0.3014796231985526,"score_spread":0.26815581381216547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7043660303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13218294,0.0014951568,0.68851846,0.0042731613,0.0184924,0.06342984,0.005599986,0.011373784,0.07463428],"genre_scores_gemma":[0.86517996,0.00003566711,0.12250435,0.0005844402,0.00019749164,0.006641769,0.0027875556,0.0003480001,0.0017207579],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9917793,0.00053317426,0.0013856752,0.0025571543,0.002590999,0.001153686],"domain_scores_gemma":[0.99239814,0.0005328021,0.001429497,0.0018169838,0.003148396,0.00067419297],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0018765619,0.0012034603,0.0010209715,0.0012745333,0.0016466088,0.00038221918,0.0022072308,0.0006312145,0.000055345412],"category_scores_gemma":[0.0041540638,0.0012315931,0.00043333066,0.0027391792,0.00010711386,0.0013792705,0.0002322667,0.0010286475,0.00010928728],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002487904,0.00033016008,6.7523325e-7,0.0002113084,0.0003183471,0.000008374286,0.00012485284,0.010781407,0.003685088,0.88950336,0.000044648063,0.09474296],"study_design_scores_gemma":[0.0069912598,0.0035424812,0.00059664977,0.0020401387,0.0020593358,0.00013929486,0.0002719876,0.34759596,0.036297932,0.5878988,0.0074985903,0.005067578],"about_ca_topic_score_codex":0.00009349276,"about_ca_topic_score_gemma":0.00015090288,"teacher_disagreement_score":0.732997,"about_ca_system_score_codex":0.0025757132,"about_ca_system_score_gemma":0.0009608583,"threshold_uncertainty_score":0.9996531},"labels":[],"label_agreement":null},{"id":"W7071379344","doi":"","title":"Statistical Divergences for Learning and Inference: Limit Laws and Non-Asymptotic Bounds","year":2022,"lang":"en","type":"dissertation","venue":"ResearchWorks at the University of Washington (University of Washington)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Institute for Catastrophic Loss Reduction","keywords":"Limit (mathematics); Stability (learning theory); Work (physics); Term (time); Calculus (dental); Noise (video)","score_opus":0.01371592093911118,"score_gpt":0.2602309455448983,"score_spread":0.24651502460578711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071379344","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3553118,0.0009686418,0.63554686,0.0014245202,0.00040087133,0.0017318877,0.00020654526,0.00026441092,0.0041444683],"genre_scores_gemma":[0.898481,0.004848964,0.06451483,0.000020114028,0.000030819127,0.0000014768265,0.0006018147,0.000056052497,0.03144492],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739826,0.00030286363,0.00022119097,0.00073673966,0.00088083406,0.0004600928],"domain_scores_gemma":[0.99662614,0.0017985691,0.00050469174,0.00043990178,0.00041479306,0.00021588341],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0011597266,0.00028895345,0.00054650096,0.00050835265,0.0022948533,0.00011782443,0.0019641265,0.0002783073,0.00039550778],"category_scores_gemma":[0.00044529288,0.00033328478,0.00015445726,0.0005822804,0.00079918286,0.00061866967,0.0019851408,0.00084461557,0.0000032117584],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0066305976,0.0014540768,0.026406832,0.0075631035,0.002899808,0.00033332754,0.30818823,0.011919725,0.002500291,0.37859944,0.04341591,0.21008869],"study_design_scores_gemma":[0.010231103,0.007643214,0.057075087,0.0036422797,0.0016964978,0.000045673176,0.27695706,0.5544335,0.0009894993,0.027621895,0.055305414,0.004358745],"about_ca_topic_score_codex":0.0013591155,"about_ca_topic_score_gemma":0.0010577056,"teacher_disagreement_score":0.571032,"about_ca_system_score_codex":0.0002449129,"about_ca_system_score_gemma":0.00029227207,"threshold_uncertainty_score":0.9999119},"labels":[],"label_agreement":null},{"id":"W7091283671","doi":"10.1016/j.automatica.2025.112655","title":"EF21-RR: Fast <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" display=\"inline\" id=\"d1e437\" altimg=\"si9.svg\"> <mml:mrow> <mml:mi mathvariant=\"script\">O</mml:mi> <mml:mrow> <mml:mo>(</mml:mo> <mml:mn>1</mml:mn> <mml:mo>/</mml:mo> <mml:mi>T</mml:mi> <mml:mo>)</mml:mo> </mml:mrow> </mml:mrow> </mml:math> rate for non-convex federated optimization with error feedback","year":2025,"lang":"lv","type":"article","venue":"Automatica","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Control theory (sociology); Control (management); Minification; Output feedback; Scheme (mathematics); Feedback control","score_opus":0.015211168880792474,"score_gpt":0.2411077985792404,"score_spread":0.22589662969844793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7091283671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33317757,0.0019988134,0.40506917,0.0049598077,0.01064608,0.0008680785,0.002017035,0.003648372,0.23761511],"genre_scores_gemma":[0.9181167,0.0008660156,0.06508738,0.0040925774,0.0019312131,0.0045889374,0.0028476734,0.0016098932,0.0008596458],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98042595,0.0010184484,0.0046118996,0.0045630625,0.0044352864,0.0049453597],"domain_scores_gemma":[0.9846815,0.0032857547,0.0046673124,0.0042306967,0.0009944785,0.0021402969],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"category_scores_codex":[0.0040925546,0.0024320388,0.001151535,0.0016180422,0.0041437205,0.0054154256,0.005529299,0.004279655,0.03536022],"category_scores_gemma":[0.003564307,0.0040913746,0.002644844,0.0040557873,0.0030950215,0.0039681317,0.0039977776,0.0029507983,0.0026820821],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018516273,0.00095048285,0.000011323578,0.002525262,0.0028048507,0.0009825527,0.003409246,0.017062847,0.0019987966,0.7947399,0.1705771,0.0030860351],"study_design_scores_gemma":[0.0033187706,0.0026295844,0.00006317469,0.0028317713,0.0022247813,0.0014152853,0.0017158389,0.62089735,0.3592024,0.001167282,0.0018905842,0.0026431966],"about_ca_topic_score_codex":0.0016152887,"about_ca_topic_score_gemma":0.00075175945,"teacher_disagreement_score":0.7935726,"about_ca_system_score_codex":0.00010628915,"about_ca_system_score_gemma":0.004026017,"threshold_uncertainty_score":0.9998513},"labels":[],"label_agreement":null},{"id":"W7095207190","doi":"","title":"Pierre-Antoine ManzagolUniversity of Montreal","year":2008,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Frequentist inference; Stochastic gradient descent; Gradient descent; Convergence (economics); Computation; Generalization; Bayesian probability; Natural (archaeology)","score_opus":0.015622760994898555,"score_gpt":0.20521467141353777,"score_spread":0.1895919104186392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095207190","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005956013,0.000014579468,0.9452997,0.000097219694,0.000046992667,0.000063883344,6.65489e-7,0.0002557067,0.048265234],"genre_scores_gemma":[0.6754762,0.00001532852,0.32264715,0.000047294838,0.000005395724,8.695415e-7,7.352922e-7,0.0000021728667,0.001804861],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999517,0.0000101797905,0.00009877495,0.00013806667,0.00014226501,0.000093665505],"domain_scores_gemma":[0.9995236,0.000025061172,0.000048122245,0.00028896565,0.000073139614,0.000041151252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004297273,0.000052441217,0.00008715402,0.000094697236,0.00004980998,0.0000042267566,0.00041462656,0.000023744173,0.00004613112],"category_scores_gemma":[0.0000139080275,0.000049180424,0.000032882657,0.00024005151,0.000050246283,0.00020038153,0.00014145959,0.000028560773,0.000008453289],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002557459,0.00048501266,0.01727317,0.000021143538,0.00005975889,0.00012751375,0.0030066133,0.0017734596,0.0009714747,0.91008687,0.03866351,0.027505875],"study_design_scores_gemma":[0.0016130137,0.00061282126,0.18503502,0.000029816067,0.000018221395,0.000300939,0.00007410218,0.7570295,0.037847526,0.015460859,0.001307748,0.00067048793],"about_ca_topic_score_codex":0.00016551436,"about_ca_topic_score_gemma":0.000005129914,"teacher_disagreement_score":0.894626,"about_ca_system_score_codex":0.000013673751,"about_ca_system_score_gemma":0.000022990333,"threshold_uncertainty_score":0.20055194},"labels":[],"label_agreement":null},{"id":"W7097981640","doi":"","title":"Author manuscript, published in &amp;quot;International Conference on Machine Learning (ICML 2009), Montreal: Canada (2009)&amp;quot; Multiple Indefinite Kernel Learning with Mixed Norm Regularization","year":2009,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Proximal gradient methods for learning; Regularization (linguistics); Multiple kernel learning; Norm (philosophy); Kernel (algebra); Online machine learning; Gradient descent; Convex function; Term (time)","score_opus":0.028874238375710213,"score_gpt":0.234812308996348,"score_spread":0.2059380706206378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097981640","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0075148223,0.00003394159,0.97235656,0.0049059503,0.00048298098,0.00051278743,0.00001695555,0.0008261677,0.013349821],"genre_scores_gemma":[0.8451784,0.00001669179,0.1276817,0.00081471965,0.000056668116,0.00005409187,0.0005317582,0.000042315998,0.025623618],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99627787,0.00021765799,0.0007051545,0.0010050787,0.0011371849,0.0006570606],"domain_scores_gemma":[0.99789613,0.00017249101,0.00045994174,0.00066390616,0.00055502605,0.00025249153],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061808556,0.00045983132,0.0004080078,0.0007345821,0.00027011207,0.0007606072,0.0011802202,0.0001840313,0.00020849107],"category_scores_gemma":[0.0008308849,0.00042105914,0.000057935395,0.0011607123,0.00005563153,0.0010655232,0.0001838929,0.0008157482,0.000018307273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007338496,0.0013350797,0.11113054,0.000054477227,0.00021152722,0.00019181713,0.005115932,0.5047711,0.0015750898,0.27221346,0.043832418,0.0588347],"study_design_scores_gemma":[0.0017901213,0.00033138355,0.029556181,0.00014942394,0.000012181847,0.00004293051,0.000103535756,0.9559629,0.00032910763,0.0029944782,0.007987409,0.0007403515],"about_ca_topic_score_codex":0.10421303,"about_ca_topic_score_gemma":0.32090878,"teacher_disagreement_score":0.8446749,"about_ca_system_score_codex":0.0004564532,"about_ca_system_score_gemma":0.00043629098,"threshold_uncertainty_score":0.9998241},"labels":[],"label_agreement":null},{"id":"W7099274952","doi":"","title":"Version: 1.3","year":2010,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Identification (biology); Work (physics); Product (mathematics); Context (archaeology)","score_opus":0.005258255056463563,"score_gpt":0.2153391388412323,"score_spread":0.21008088378476872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099274952","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007375753,8.5064056e-7,0.9349976,0.0006898857,0.0003761037,0.000032341366,7.5547426e-8,0.0005469318,0.06261861],"genre_scores_gemma":[0.2686438,2.9185574e-7,0.7303155,0.0002839128,0.00001652208,0.0000031626873,2.628622e-7,0.0000016063063,0.0007349128],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997126,0.0000025428592,0.000042089767,0.00009958895,0.00007853824,0.000064647305],"domain_scores_gemma":[0.9996329,0.000018634704,0.000010956413,0.0002712571,0.00003174993,0.00003452433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005189445,0.0000289434,0.000024524392,0.000039188642,0.00003180769,0.0000361904,0.00036353729,0.000021149279,0.00022770265],"category_scores_gemma":[0.000026452835,0.000024439934,0.000012290237,0.00013021758,0.000013173231,0.00015872113,0.000087434244,0.00005345175,0.00016273711],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.3458033e-7,0.0000070486362,0.000082896586,2.4827187e-7,5.270297e-7,7.027698e-7,0.0000225026,0.0000039638535,0.0011572056,0.9871883,0.0077677253,0.0037687875],"study_design_scores_gemma":[0.0005651963,0.00016520289,0.003029095,0.0000063317657,0.0000036799531,0.000100041056,0.000016459739,0.5794138,0.1223792,0.15935664,0.13440663,0.0005577534],"about_ca_topic_score_codex":0.000002344499,"about_ca_topic_score_gemma":8.673153e-7,"teacher_disagreement_score":0.8278316,"about_ca_system_score_codex":0.0000024473898,"about_ca_system_score_gemma":0.000009923794,"threshold_uncertainty_score":0.24931844},"labels":[],"label_agreement":null},{"id":"W7102418797","doi":"10.18280/mmep.120912","title":"Advanced Hybrid Conjugate Gradient Algorithms with Proven Convergence and Superior Efficiency","year":2025,"lang":"","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Conjugate gradient method; Convergence (economics); Gradient method; Gradient descent; Representation (politics); Stability (learning theory)","score_opus":0.01083254025612516,"score_gpt":0.2046783634995552,"score_spread":0.19384582324343005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7102418797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022155412,0.0021069283,0.973598,0.00028855872,0.00022205399,0.0010706281,0.000005936661,0.0004148746,0.00013761205],"genre_scores_gemma":[0.57721823,0.00037313483,0.42196715,0.000024863908,0.000011519152,0.00015377621,0.0000015380425,0.00003185731,0.00021795055],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745744,0.00002339294,0.0006532507,0.000892837,0.0003227406,0.0006503057],"domain_scores_gemma":[0.9987827,0.00021437653,0.00010576862,0.00048368992,0.00015451554,0.00025896702],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004313344,0.0004923901,0.000578968,0.00025637524,0.0002305451,0.0003696366,0.00037990787,0.00010319482,0.00000557537],"category_scores_gemma":[0.00007206405,0.00042992036,0.00005110142,0.000499028,0.0002377537,0.0003195361,0.0002671178,0.0003249475,0.0000033650942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010851546,0.00011175454,0.000008669616,0.001608824,0.00004912717,0.0000081407625,0.0013167133,0.837124,0.00015128449,0.15597387,0.000003608974,0.0036331832],"study_design_scores_gemma":[0.00055599486,0.00035262984,0.0000033772874,0.002383879,0.00006241465,0.000072040064,0.000025027375,0.97784597,0.0010732445,0.01708564,0.00006755549,0.00047224012],"about_ca_topic_score_codex":0.000007856984,"about_ca_topic_score_gemma":1.2301282e-7,"teacher_disagreement_score":0.55506283,"about_ca_system_score_codex":0.000054178454,"about_ca_system_score_gemma":0.00006869007,"threshold_uncertainty_score":0.9998153},"labels":[],"label_agreement":null},{"id":"W7103104646","doi":"","title":"Automatic selection of hyper-parameters via the use of softened profile likelihood","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Curse of dimensionality; Extension (predicate logic); Heuristic; Selection (genetic algorithm); Maximum likelihood; Feature selection","score_opus":0.04246349758805146,"score_gpt":0.25723469035103874,"score_spread":0.21477119276298728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103104646","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40082493,0.0000926296,0.5970343,0.00054532144,0.00043402982,0.0008252098,0.0000050354083,0.00018024594,0.00005832402],"genre_scores_gemma":[0.8477706,0.000030195315,0.15147819,0.00035603537,0.000015211205,0.00009995814,0.0000027810515,0.000019864074,0.00022720364],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99711543,0.00027721256,0.0010887013,0.0006065379,0.00045402392,0.0004581119],"domain_scores_gemma":[0.99691576,0.000723517,0.0007647817,0.0009589478,0.0005572427,0.00007973606],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048315318,0.00032931392,0.0005183431,0.000454753,0.00022463177,0.00009348738,0.0010909812,0.00018977447,0.00007984126],"category_scores_gemma":[0.00075135,0.0002749613,0.00022227979,0.0026962904,0.00038876853,0.000607775,0.00042279882,0.00026951416,0.000019575547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001903286,0.0027151457,0.43034273,0.0017151703,0.0012884352,0.0000044584754,0.005757291,0.018506775,0.055060517,0.020588718,0.0057432475,0.45808718],"study_design_scores_gemma":[0.00037106665,0.00038526804,0.054975852,0.00040357985,0.00015857196,0.0000075829607,0.000027135633,0.8340618,0.10798512,0.001303868,0.00009054637,0.00022960693],"about_ca_topic_score_codex":0.0001279563,"about_ca_topic_score_gemma":0.000005518964,"teacher_disagreement_score":0.81555504,"about_ca_system_score_codex":0.000112578964,"about_ca_system_score_gemma":0.0003184768,"threshold_uncertainty_score":0.99997026},"labels":[],"label_agreement":null},{"id":"W7104183320","doi":"","title":"Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Scaling; Limit (mathematics); Gradient descent; Exponent; Stochastic gradient descent; Population; Scaling limit; Dynamics (music); Stochastic process","score_opus":0.04192090285095918,"score_gpt":0.26246087838759374,"score_spread":0.22053997553663457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104183320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.114774935,0.0010031491,0.87540066,0.002296035,0.0038142025,0.0022523443,0.000012356549,0.0003214202,0.0001249236],"genre_scores_gemma":[0.9639706,0.00003178303,0.032937825,0.0018330022,0.00021956884,0.00043903556,0.000025730063,0.00006313427,0.000479291],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99469846,0.00022407102,0.0013786199,0.0017162261,0.00054221094,0.0014404111],"domain_scores_gemma":[0.99652773,0.0010921507,0.00045051234,0.0011639666,0.00046335536,0.00030230344],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001016311,0.00075311976,0.0008032369,0.0008840856,0.00045560286,0.00025870654,0.0015386104,0.00042858478,0.000051408486],"category_scores_gemma":[0.00062826363,0.0007832529,0.00031126614,0.002125641,0.00040384143,0.00046384716,0.00090623106,0.00060618314,0.000031721003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038431748,0.0021888397,0.01570986,0.000120346005,0.00020900417,0.000026704556,0.000677469,0.6188847,0.0006245117,0.33674362,0.0026602633,0.021770393],"study_design_scores_gemma":[0.0021891817,0.00067219004,0.018337483,0.0010644636,0.000114963535,0.000011604445,0.000026256717,0.95798296,0.0015820094,0.017082667,0.00014963893,0.0007865865],"about_ca_topic_score_codex":0.000053453386,"about_ca_topic_score_gemma":0.000027127333,"teacher_disagreement_score":0.8491957,"about_ca_system_score_codex":0.0007269841,"about_ca_system_score_gemma":0.0003054992,"threshold_uncertainty_score":0.9994618},"labels":[],"label_agreement":null},{"id":"W7117132980","doi":"10.1134/s0001434625605210","title":"Accelerated Algorithm for Splitting a Vector into Two Vectors with Small Uniform Norm","year":2025,"lang":"en","type":"article","venue":"Mathematical Notes","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Norm (philosophy); Uniform norm; Efficient algorithm; Approximation algorithm; Matrix norm; Vector field","score_opus":0.028630622175947903,"score_gpt":0.28587952980811987,"score_spread":0.25724890763217195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117132980","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020167725,0.000013109167,0.99484015,0.00077629625,0.000079989004,0.000674584,0.000002361821,0.00061486295,0.0009818742],"genre_scores_gemma":[0.050995357,5.9120487e-7,0.9484394,0.00020389212,0.00002608306,0.00020564203,0.0000051035486,0.000016605389,0.00010728498],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998784,0.000018640221,0.0003327846,0.0003718173,0.0001755162,0.0003172518],"domain_scores_gemma":[0.99809456,0.0010701581,0.000092442046,0.00043939738,0.00022026776,0.00008320522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027928848,0.00020174778,0.0002741029,0.0001757252,0.00016391028,0.00022903651,0.0006139284,0.00006440069,0.000013490361],"category_scores_gemma":[0.0005299908,0.00015415552,0.00006117807,0.00071464654,0.000073690026,0.00018464454,0.00018673783,0.00010619128,0.000012321305],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000113732885,0.00021815188,0.00006232825,0.00021827039,0.00006731074,0.0000047708772,0.0009700464,0.00022953912,0.0003585757,0.8917338,0.00007305771,0.10605276],"study_design_scores_gemma":[0.00051536923,0.00016843155,0.00004846861,0.00022534262,0.00002371211,0.0000068589175,0.000025271582,0.7895809,0.017603174,0.19151248,0.000073853786,0.00021615527],"about_ca_topic_score_codex":0.000017860739,"about_ca_topic_score_gemma":0.000005550235,"teacher_disagreement_score":0.78935134,"about_ca_system_score_codex":0.00008248108,"about_ca_system_score_gemma":0.000087880915,"threshold_uncertainty_score":0.628628},"labels":[],"label_agreement":null},{"id":"W7117174638","doi":"","title":"Optimizer Dynamics at the Edge of Stability with Differential Privacy","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Simon Fraser University","keywords":"Stability (learning theory); Clipping (morphology); Noise (video); Gradient descent; Artificial neural network; Enhanced Data Rates for GSM Evolution; Differential privacy; Gaussian noise; Dynamics (music)","score_opus":0.025238357965588102,"score_gpt":0.25186733290303925,"score_spread":0.22662897493745116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117174638","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41799098,0.00011048577,0.5780328,0.0016828511,0.0004872526,0.0007202321,0.000019511843,0.00011545637,0.0008404695],"genre_scores_gemma":[0.98045903,0.000053789317,0.017749881,0.0002151839,0.00003707461,0.00007596952,0.000012754458,0.000025724834,0.0013706111],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967885,0.00025674226,0.0008444024,0.0009885252,0.00054574263,0.0005760812],"domain_scores_gemma":[0.99630266,0.00048132087,0.00049234123,0.002143247,0.00045733232,0.00012310536],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004486593,0.00045453984,0.0005571097,0.00019414669,0.0004581864,0.0001254348,0.002134085,0.0001898304,0.00034042017],"category_scores_gemma":[0.00027696908,0.0003189983,0.00020170663,0.0014142797,0.0010706084,0.0003405245,0.0021798615,0.00039356214,0.000018258357],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006637824,0.0016596697,0.85935134,0.00038191568,0.00060610374,0.000008953552,0.004114205,0.008627319,0.0008541359,0.112228915,0.0013051445,0.010198521],"study_design_scores_gemma":[0.0017495342,0.0005094766,0.21435028,0.00038721066,0.00027921217,0.000009944163,0.00013034194,0.75391775,0.026268099,0.0015853363,0.000175296,0.00063750194],"about_ca_topic_score_codex":0.00005676139,"about_ca_topic_score_gemma":0.00003835098,"teacher_disagreement_score":0.74529046,"about_ca_system_score_codex":0.00045031626,"about_ca_system_score_gemma":0.00033635518,"threshold_uncertainty_score":0.9999262},"labels":[],"label_agreement":null},{"id":"W7117277200","doi":"","title":"Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures","year":2025,"lang":"","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Simplicity; Initialization; Gradient descent; Invariant (physics); Convolutional neural network; Artificial neural network; Class (philosophy)","score_opus":0.06538742909950591,"score_gpt":0.2209794611678297,"score_spread":0.15559203206832378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117277200","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27592048,0.000060425984,0.7192112,0.0004919865,0.0011590942,0.0008710705,0.00007140469,0.00062215776,0.0015921992],"genre_scores_gemma":[0.9860343,0.000041217416,0.008967153,0.0016336326,0.00013811796,0.000005936722,0.000017365797,0.000043775242,0.0031185043],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99481547,0.00040378762,0.000643423,0.0021710345,0.0002482687,0.0017179888],"domain_scores_gemma":[0.99555856,0.000907135,0.00039306883,0.0021111588,0.00043543545,0.0005946476],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0006275201,0.0007827952,0.00072772894,0.00062919996,0.0013159965,0.0005149873,0.003421471,0.0003935816,0.000051545263],"category_scores_gemma":[0.00047663623,0.000958203,0.00042442975,0.006825443,0.0004982836,0.00045906394,0.002924599,0.0007884431,0.0000690752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012787207,0.00016064015,0.00828932,0.000041195344,0.000099890436,0.0001186985,0.0007696786,0.7442746,0.000005864622,0.24005088,0.00094549404,0.0051158466],"study_design_scores_gemma":[0.00080307975,0.00031952743,0.0053462577,0.00022431911,0.000088188426,0.000013560248,0.00022989234,0.9645636,0.00009559235,0.027123166,0.00039226015,0.0008005205],"about_ca_topic_score_codex":0.0002918893,"about_ca_topic_score_gemma":0.00070298556,"teacher_disagreement_score":0.71024406,"about_ca_system_score_codex":0.00078598794,"about_ca_system_score_gemma":0.00029876034,"threshold_uncertainty_score":0.99998415},"labels":[],"label_agreement":null},{"id":"W7117360046","doi":"10.5281/zenodo.18059997","title":"Backpropagation and Training Models in Neural Networks and Deep Learning","year":2025,"lang":"en","type":"book-chapter","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Backpropagation; Deep learning; Artificial neural network; Training (meteorology); Training set","score_opus":0.03728011047778847,"score_gpt":0.22623703059169978,"score_spread":0.1889569201139113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117360046","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001905645,0.00042036426,0.7804944,0.00018760459,0.00005082224,0.00036195072,0.0000060057428,0.0006809259,0.21777889],"genre_scores_gemma":[0.78362703,0.0066166217,0.08484423,0.001183796,0.00058149995,0.0000011805085,0.0036071774,0.0067458726,0.11279256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985017,0.000117794094,0.00029290142,0.0005889997,0.00023692012,0.00026165432],"domain_scores_gemma":[0.99913555,0.0000539884,0.00014898326,0.0002975504,0.00025791588,0.00010598863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004950758,0.00020519442,0.0002162791,0.0005097423,0.00078330125,0.00080941874,0.00065854384,0.00015297129,0.00021071649],"category_scores_gemma":[0.00019034366,0.00023918535,0.000027369975,0.00020827724,0.00012795442,0.00042867637,0.0014549635,0.0005342397,0.000025191248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010621624,0.000008868786,5.1883507e-7,0.00004444204,0.000015226303,0.000010632059,0.0012355711,0.015828883,0.0000070184096,0.38084677,0.0009673992,0.60102403],"study_design_scores_gemma":[0.00024614303,0.00012535574,0.000018550256,0.00013172755,0.000008788304,0.000064321895,0.00003988563,0.9427258,0.0000018346581,0.010035078,0.046376903,0.00022562491],"about_ca_topic_score_codex":0.0000035137848,"about_ca_topic_score_gemma":3.4080654e-7,"teacher_disagreement_score":0.9268969,"about_ca_system_score_codex":0.00009411753,"about_ca_system_score_gemma":0.0000037387324,"threshold_uncertainty_score":0.9753695},"labels":[],"label_agreement":null},{"id":"W7117374469","doi":"10.5281/zenodo.18059996","title":"Backpropagation and Training Models in Neural Networks and Deep Learning","year":2025,"lang":"en","type":"book-chapter","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Backpropagation; Deep learning; Artificial neural network; Training (meteorology); Training set","score_opus":0.03728011047778847,"score_gpt":0.22623703059169978,"score_spread":0.1889569201139113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117374469","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001905645,0.00042036426,0.7804944,0.00018760459,0.00005082224,0.00036195072,0.0000060057428,0.0006809259,0.21777889],"genre_scores_gemma":[0.78362703,0.0066166217,0.08484423,0.001183796,0.00058149995,0.0000011805085,0.0036071774,0.0067458726,0.11279256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985017,0.000117794094,0.00029290142,0.0005889997,0.00023692012,0.00026165432],"domain_scores_gemma":[0.99913555,0.0000539884,0.00014898326,0.0002975504,0.00025791588,0.00010598863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004950758,0.00020519442,0.0002162791,0.0005097423,0.00078330125,0.00080941874,0.00065854384,0.00015297129,0.00021071649],"category_scores_gemma":[0.00019034366,0.00023918535,0.000027369975,0.00020827724,0.00012795442,0.00042867637,0.0014549635,0.0005342397,0.000025191248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010621624,0.000008868786,5.1883507e-7,0.00004444204,0.000015226303,0.000010632059,0.0012355711,0.015828883,0.0000070184096,0.38084677,0.0009673992,0.60102403],"study_design_scores_gemma":[0.00024614303,0.00012535574,0.000018550256,0.00013172755,0.000008788304,0.000064321895,0.00003988563,0.9427258,0.0000018346581,0.010035078,0.046376903,0.00022562491],"about_ca_topic_score_codex":0.0000035137848,"about_ca_topic_score_gemma":3.4080654e-7,"teacher_disagreement_score":0.9268969,"about_ca_system_score_codex":0.00009411753,"about_ca_system_score_gemma":0.0000037387324,"threshold_uncertainty_score":0.9753695},"labels":[],"label_agreement":null},{"id":"W7124323873","doi":"10.65109/ondy7628","title":"Lyapunov Exponents for Diversity in Differentiable Games","year":2022,"lang":"","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hessian matrix; Differentiable function; Bifurcation; Dynamical systems theory; Field (mathematics); Construct (python library); Eigenvalues and eigenvectors; Lyapunov exponent","score_opus":0.046830671560962676,"score_gpt":0.25361588387726647,"score_spread":0.20678521231630378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124323873","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018096479,0.0001163826,0.9773627,0.00047234583,0.0010486994,0.0013448476,0.00004082967,0.00024201375,0.001275701],"genre_scores_gemma":[0.9136905,0.000016496228,0.0801203,0.0003777333,0.000023611545,0.00036694395,0.00001627345,0.000017613369,0.0053705354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99732965,0.00013964919,0.0004528898,0.0008284554,0.0006362014,0.00061312434],"domain_scores_gemma":[0.9987579,0.00018665771,0.00018924978,0.00064282544,0.00010098589,0.00012240578],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005489434,0.00025582057,0.0003261606,0.0005157453,0.0011423967,0.00013956075,0.0017995376,0.00006004744,0.0014284209],"category_scores_gemma":[0.000072221505,0.0003004259,0.00015092453,0.0009808777,0.000061968414,0.00042796574,0.007383913,0.00022831088,0.000007682115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051078893,0.0062208343,0.09242464,0.0002852235,0.00022382842,0.000053474363,0.025977831,0.051512707,0.00044970436,0.7095975,0.065093994,0.04764945],"study_design_scores_gemma":[0.0018308423,0.00064222194,0.0051866546,0.00002578637,0.000023302853,0.000007565265,0.0004784777,0.96376187,0.0008337724,0.025330273,0.001348397,0.00053082017],"about_ca_topic_score_codex":0.00019822648,"about_ca_topic_score_gemma":0.000013758185,"teacher_disagreement_score":0.9122492,"about_ca_system_score_codex":0.00038044574,"about_ca_system_score_gemma":0.00008900194,"threshold_uncertainty_score":0.9999448},"labels":[],"label_agreement":null},{"id":"W7126437193","doi":"10.21428/594757db.be36222c","title":"Adaptive Learning Rates for Gradient Boosting Machines","year":2024,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Boosting (machine learning); Gradient boosting; Hyperparameter; Rate of convergence; Convergence (economics); Online machine learning; Adaptive learning; Context (archaeology)","score_opus":0.025906614144536946,"score_gpt":0.30059139829777926,"score_spread":0.2746847841532423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126437193","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000181514,0.00028404695,0.9924557,0.00053879427,0.00037887527,0.00026407395,0.0000010830344,0.001805461,0.004090426],"genre_scores_gemma":[0.31132123,0.000006060018,0.6868466,0.000104117455,0.00006169209,0.000103483566,0.0000036371055,0.000015064424,0.0015381328],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991898,0.000020363965,0.00015030909,0.00032856636,0.0001129102,0.00019807692],"domain_scores_gemma":[0.9993346,0.00037530935,0.00002850455,0.00013905577,0.00007600019,0.000046579215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002278807,0.00010699566,0.00008979218,0.00015194343,0.00013171873,0.00025558745,0.0002899557,0.00002888856,0.000014451432],"category_scores_gemma":[0.00015174934,0.00008762072,0.000059890423,0.00032702982,0.000020397283,0.000315345,0.00011297206,0.00008911324,0.000016429192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002326548,0.0000098803175,0.00008093614,0.000017378754,0.00001677929,0.0000036315814,0.00060316554,0.0033940906,0.00012434783,0.93351424,0.0017948087,0.0604384],"study_design_scores_gemma":[0.000052983418,0.00014186482,0.000019044719,0.000051818384,0.000004426084,0.000009995048,0.000028293618,0.96728426,0.00147073,0.029383022,0.0014366815,0.000116857846],"about_ca_topic_score_codex":0.000012372899,"about_ca_topic_score_gemma":0.0000013683459,"teacher_disagreement_score":0.9638902,"about_ca_system_score_codex":0.00003360086,"about_ca_system_score_gemma":0.000028758517,"threshold_uncertainty_score":0.35730693},"labels":[],"label_agreement":null},{"id":"W7132867797","doi":"","title":"Network Resource Allocation and Topology Design for Distributed Machine Learning","year":2024,"lang":"","type":"dissertation","venue":"TSpace","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Distributed learning; Distributed algorithm; Overhead (engineering); Network topology; Resource allocation; Load balancing (electrical power); Bandwidth (computing); Computation; Telecommunications network","score_opus":0.030632112598365995,"score_gpt":0.3154574142471624,"score_spread":0.2848253016487964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132867797","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002917868,0.0048582274,0.98841757,0.002551915,0.0010491073,0.0018492771,0.000012940954,0.0006745442,0.00029464005],"genre_scores_gemma":[0.14918561,0.00080820924,0.81246185,0.00046536903,0.0009183312,0.0014490543,0.005882328,0.0003034124,0.028525813],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99686277,0.0003286978,0.0005952754,0.0012263446,0.00031559088,0.0006713477],"domain_scores_gemma":[0.99741066,0.0010728929,0.00050393236,0.00049345015,0.0003416435,0.00017745318],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010486093,0.000560023,0.00055616547,0.00028467466,0.00061382295,0.0004630363,0.00060948724,0.0005428862,0.000034125376],"category_scores_gemma":[0.00069993944,0.0006157877,0.00011579302,0.00093020336,0.00012737921,0.00016069447,0.0002102708,0.0006531974,0.000015498297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007202682,0.00013902893,0.000107885586,0.0012347162,0.00036307244,0.000023364479,0.041448735,0.56057745,0.00048884505,0.34124863,0.02607664,0.02757138],"study_design_scores_gemma":[0.00036439695,0.0007851466,0.000048315967,0.00043589386,0.00020938582,0.000027247566,0.00091121753,0.97030985,0.00056277803,0.014925665,0.0108396765,0.0005804495],"about_ca_topic_score_codex":0.000085152366,"about_ca_topic_score_gemma":0.000018726832,"teacher_disagreement_score":0.40973237,"about_ca_system_score_codex":0.00014844314,"about_ca_system_score_gemma":0.00019337828,"threshold_uncertainty_score":0.9996293},"labels":[],"label_agreement":null},{"id":"W7132869902","doi":"","title":"Distributed Optimization Algorithms with Improved Efficiency, Reliability, and Privacy Preservation","year":2025,"lang":"","type":"dissertation","venue":"TSpace","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"RIKEN; Vector Institute; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Differential privacy; Randomness; Computation; Distributed learning; Distributed algorithm; Secure multi-party computation; Popularity; Cryptography; Information privacy","score_opus":0.015538587575795001,"score_gpt":0.2945686986921361,"score_spread":0.2790301111163411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132869902","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056694,0.00030085127,0.98690426,0.0013764687,0.00069374224,0.0033893555,0.000047375517,0.0007562501,0.000862311],"genre_scores_gemma":[0.07481387,0.0005069661,0.9129529,0.00013620184,0.00010358841,0.00070847565,0.003336431,0.00011370147,0.007327878],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99491626,0.0002489621,0.0010165421,0.0021372268,0.0009248281,0.00075618725],"domain_scores_gemma":[0.99440956,0.00045925583,0.001104517,0.0017481152,0.0020015296,0.0002770055],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007443531,0.000934656,0.0008130578,0.0006299899,0.00068047876,0.0009090666,0.0014718667,0.0006661079,0.000050750456],"category_scores_gemma":[0.001300971,0.00090826175,0.00011761479,0.0029435782,0.00022258042,0.0012718027,0.0006033157,0.00064550474,0.0000028323873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005922393,0.00093584013,0.0005506238,0.0016114814,0.00020611838,0.000011597002,0.019618308,0.9475497,0.00033858305,0.0144096445,0.00056327175,0.01361261],"study_design_scores_gemma":[0.0011744294,0.0008150208,0.00071301503,0.0008131775,0.00019854025,0.000010092619,0.00061775406,0.99178106,0.002143953,0.00065991434,0.00018479169,0.0008882721],"about_ca_topic_score_codex":0.00039181448,"about_ca_topic_score_gemma":0.000023398896,"teacher_disagreement_score":0.07395136,"about_ca_system_score_codex":0.00035026376,"about_ca_system_score_gemma":0.00093124295,"threshold_uncertainty_score":0.9993368},"labels":[],"label_agreement":null},{"id":"W7133004520","doi":"","title":"Optimization and Loss Landscape Geometry of Deep Learning","year":2022,"lang":"","type":"dissertation","venue":"TSpace","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Deep learning; Artificial neural network; Deep neural networks; Set (abstract data type); Class (philosophy); Convolutional neural network; Optimization problem; Focus (optics)","score_opus":0.009943714337835304,"score_gpt":0.28987365066890214,"score_spread":0.27992993633106683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133004520","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014019843,0.0024175432,0.9789621,0.00010581836,0.00070703274,0.00056473276,0.000003640945,0.00024682892,0.0029724515],"genre_scores_gemma":[0.66496104,0.0026989,0.32317585,0.00006374392,0.000097352124,0.00017393474,0.0008643922,0.00014904441,0.007815732],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970057,0.0002312652,0.00066221587,0.00089129055,0.00080502586,0.00040449965],"domain_scores_gemma":[0.9974148,0.00031767544,0.0011317289,0.0005570436,0.00042733442,0.00015141859],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005633869,0.00044939356,0.00060178025,0.000987641,0.00046189025,0.00017524719,0.0007628435,0.0002929157,0.002049582],"category_scores_gemma":[0.00044689045,0.0005452678,0.00012095641,0.0018891707,0.00010640316,0.00033239633,0.00043097715,0.0006749215,0.000004161759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065751185,0.00012804884,0.0024031834,0.00039525848,0.00008789843,0.000012050204,0.030229818,0.9474655,0.00009725323,0.008734781,0.0000606015,0.010319863],"study_design_scores_gemma":[0.00045575836,0.00051606685,0.00064585876,0.00013240926,0.00009402702,0.000028979708,0.0068797586,0.98965037,0.0007135714,0.00017476815,0.00018103766,0.00052742433],"about_ca_topic_score_codex":0.00007363804,"about_ca_topic_score_gemma":0.0000047387293,"teacher_disagreement_score":0.6557863,"about_ca_system_score_codex":0.000080607264,"about_ca_system_score_gemma":0.00012424418,"threshold_uncertainty_score":0.9996999},"labels":[],"label_agreement":null}]}