{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008922338,0.000083491424,0.99835974,0.00004650833,0.000012946639,0.000010197747,0.000021386802,0.00013498172,0.00043854068],"genre_scores_gemma":[0.12770814,0.0005551413,0.86594427,0.00014524838,0.00010465112,0.0003559122,0.00036770472,0.00053036754,0.0042886175],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990522,0.0005579832,0.00003867376,0.00010784808,0.00019290613,0.00005033361],"domain_scores_gemma":[0.9930875,0.005700105,0.00022350857,0.00041650512,0.00043402586,0.00013833854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002640059,0.00088893116,0.0019507005,0.0012576459,0.0006983648,0.0011385027,0.0020107927,0.0021200317,0.0059040175],"category_scores_gemma":[0.013467719,0.0014761504,0.0014214998,0.0011985822,0.001361245,0.002292411,0.0021139574,0.0027350527,0.0014464856],"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":[0.0000992092,0.00003477529,0.00036735265,0.000115447,0.00005489532,0.00006579559,0.00007160431,0.69672847,0.0014557185,0.2456387,0.002143674,0.05322439],"study_design_scores_gemma":[0.000005724346,0.000006301917,0.00002624004,0.000006850407,0.000003276205,0.000009387617,0.0000017389343,0.9611822,0.00015443645,0.037961002,0.000637942,0.000004910307],"about_ca_topic_score_codex":0.0032461192,"about_ca_topic_score_gemma":0.002884435,"teacher_disagreement_score":0.0059040175,"about_ca_system_score_codex":0.0010502808,"about_ca_system_score_gemma":0.0011751109,"threshold_uncertainty_score":0.019750893},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03739695,0.012264265,0.9313169,0.0036656254,0.0007005526,0.000079603466,0.00006379918,0.0010992357,0.0134130195],"genre_scores_gemma":[0.7206132,0.01025416,0.2616054,0.0008957024,0.001170595,0.0001728285,0.00018791817,0.00073829974,0.004361901],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997547,0.0014101279,0.00014209728,0.00034585697,0.0004301381,0.00012485638],"domain_scores_gemma":[0.97579396,0.019923609,0.0008815986,0.0013838393,0.0016048132,0.00041211888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007742895,0.0013734611,0.0010180421,0.00073948875,0.0011117974,0.002136893,0.00096463313,0.0021234823,0.0013283766],"category_scores_gemma":[0.05319958,0.0010739788,0.00040714926,0.0010094186,0.003864856,0.006069802,0.002529216,0.005307974,0.00067965407],"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":[0.00070774904,0.00012071091,0.0050306986,0.0004025294,0.000088044726,0.0003536114,0.00039353757,0.50895,0.0063475356,0.22593656,0.00722402,0.24444494],"study_design_scores_gemma":[0.00003981365,0.00012484872,0.00090397993,0.00016391142,0.00002844035,0.00008689453,0.00003119025,0.89400154,0.0033219238,0.098682955,0.0025658885,0.00004860476],"about_ca_topic_score_codex":0.0044200798,"about_ca_topic_score_gemma":0.0036689253,"teacher_disagreement_score":0.007742895,"about_ca_system_score_codex":0.0011770295,"about_ca_system_score_gemma":0.0012716613,"threshold_uncertainty_score":0.040948868},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004418518,0.0003868858,0.9968882,0.00034224478,0.00009725681,0.000023147359,0.00007227437,0.00046352547,0.0012846265],"genre_scores_gemma":[0.06240457,0.0017854638,0.9222605,0.00054994505,0.00048455587,0.00047740332,0.00063319743,0.0012029099,0.010201388],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984296,0.00068315136,0.00011337687,0.00023860522,0.0004497024,0.00008548558],"domain_scores_gemma":[0.9979012,0.0012870778,0.00020682966,0.00019695847,0.00028744768,0.00012049112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020915968,0.0021315333,0.001959663,0.0008078784,0.00060861954,0.0021799027,0.0023799865,0.0025114575,0.0059569166],"category_scores_gemma":[0.006962539,0.0010462427,0.00119912,0.00097572454,0.0016891042,0.001983238,0.0027929726,0.0041000266,0.0033992734],"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":[0.000098648205,0.000042297816,0.0005480289,0.00044428732,0.00018435925,0.00024673968,0.00012113762,0.66004944,0.0029243736,0.19920643,0.02881358,0.10732065],"study_design_scores_gemma":[0.0000155567,0.000018361921,0.000046664554,0.000028785767,0.000009614378,0.00007413543,0.0000059660883,0.92529696,0.00069833914,0.061483327,0.012307131,0.000015265352],"about_ca_topic_score_codex":0.0017409886,"about_ca_topic_score_gemma":0.0021543456,"teacher_disagreement_score":0.0059569166,"about_ca_system_score_codex":0.0008394011,"about_ca_system_score_gemma":0.0018305847,"threshold_uncertainty_score":0.01992786},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019020993,0.000102716695,0.99647456,0.00009571784,0.000028873661,0.0000291313,0.000027848255,0.0006016431,0.0007374273],"genre_scores_gemma":[0.1657843,0.00021631613,0.8278399,0.00027295703,0.0000967064,0.00050313864,0.0003665405,0.0007273029,0.004192832],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988292,0.0005480561,0.00006261669,0.00016397417,0.00031659097,0.00007955024],"domain_scores_gemma":[0.998447,0.0007948209,0.00009677186,0.0002745565,0.00030843678,0.000078462166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001977105,0.0013204048,0.0012583697,0.0006510293,0.0005351191,0.0010864706,0.0027477045,0.0018272409,0.0051410594],"category_scores_gemma":[0.011050346,0.000758913,0.0007761809,0.00072499743,0.0011343603,0.002229904,0.0022587767,0.0027029996,0.0023633747],"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":[0.00016832777,0.00007520534,0.0005504106,0.00016847037,0.000071574716,0.000070504444,0.0001232492,0.6987964,0.003074721,0.10887307,0.006001975,0.18202603],"study_design_scores_gemma":[0.0000074904483,0.000014148954,0.00002849268,0.000007366538,0.000002208097,0.000015158721,0.0000032124499,0.9735901,0.0004586695,0.024930373,0.00093756017,0.0000051183356],"about_ca_topic_score_codex":0.0029284898,"about_ca_topic_score_gemma":0.004155946,"teacher_disagreement_score":0.0051410594,"about_ca_system_score_codex":0.0013244357,"about_ca_system_score_gemma":0.0016831461,"threshold_uncertainty_score":0.017198503},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002641952,0.0006058415,0.99303174,0.00041605852,0.00011042752,0.000030301697,0.000034359186,0.0000740502,0.0030553124],"genre_scores_gemma":[0.43130103,0.006179421,0.5288752,0.0014544905,0.001242949,0.0018229553,0.00046008965,0.001293191,0.027370619],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961039,0.0022816572,0.00017067665,0.00037651169,0.0008800344,0.0001872783],"domain_scores_gemma":[0.9734427,0.021337189,0.0011505797,0.0008923959,0.0025008847,0.00067636446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014798874,0.0030363612,0.0029338093,0.00294775,0.00126983,0.0036186995,0.0034786935,0.0027023172,0.0043587363],"category_scores_gemma":[0.03972426,0.0014525019,0.0022123673,0.0026863038,0.005830094,0.0066812024,0.0055075055,0.0070279064,0.0007388175],"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":[0.00007089914,0.000072029245,0.00022541094,0.0002081782,0.0001238573,0.000077466466,0.00012130391,0.15255508,0.0009869644,0.83241874,0.0017445913,0.011395385],"study_design_scores_gemma":[0.00001761315,0.000024463305,0.000089148736,0.00003006571,0.000023201075,0.000023247365,0.000014539258,0.6940515,0.00040879947,0.3043833,0.00091409555,0.000020000234],"about_ca_topic_score_codex":0.0029391802,"about_ca_topic_score_gemma":0.0024983317,"teacher_disagreement_score":0.014798874,"about_ca_system_score_codex":0.0026239108,"about_ca_system_score_gemma":0.0034025607,"threshold_uncertainty_score":0.07826489},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013345292,0.00011319804,0.98332983,0.00017621598,0.000028063725,0.000040267343,0.00014021671,0.00042138345,0.002405591],"genre_scores_gemma":[0.37326273,0.0005528182,0.61590075,0.0002955066,0.00013337155,0.0002245927,0.0012236095,0.00033139967,0.00807518],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99914944,0.00025634433,0.000040536015,0.00021977583,0.00026701062,0.00006692443],"domain_scores_gemma":[0.9975319,0.0013881284,0.00024590897,0.00044912327,0.00029904197,0.00008583186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007991502,0.00096193294,0.00083158724,0.00060145283,0.00041298862,0.0011770054,0.0010262517,0.00067583413,0.0048167924],"category_scores_gemma":[0.006096715,0.0005233166,0.0004938629,0.0009349648,0.001098708,0.002425955,0.0012090869,0.0020313002,0.0012791546],"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":[0.0002919153,0.00014589913,0.0010810161,0.0003882426,0.00007527999,0.00021623942,0.00027124645,0.4906207,0.01704042,0.25651306,0.0116269635,0.22172907],"study_design_scores_gemma":[0.000016530948,0.000042300908,0.00017925062,0.000015817446,0.0000060274333,0.00009210854,0.000049129238,0.89369917,0.004903787,0.09779482,0.0031883847,0.000012643896],"about_ca_topic_score_codex":0.00091843156,"about_ca_topic_score_gemma":0.0018707971,"teacher_disagreement_score":0.0048167924,"about_ca_system_score_codex":0.00047959638,"about_ca_system_score_gemma":0.00055530627,"threshold_uncertainty_score":0.016113818},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066442275,0.00010908155,0.9914568,0.00015154183,0.000027729888,0.00002879278,0.000019395928,0.00037262597,0.0011899039],"genre_scores_gemma":[0.2862096,0.00033404623,0.70739084,0.0002386367,0.00007088602,0.00038523358,0.00016877812,0.0004942725,0.0047076386],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992526,0.0003929855,0.000039233226,0.000085930405,0.0001818073,0.000047437898],"domain_scores_gemma":[0.9978695,0.0012878792,0.0001895166,0.00031665375,0.00024342652,0.000093089555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022323616,0.0007330938,0.0007469787,0.00045855937,0.00041612424,0.0007382189,0.0011817755,0.0012829516,0.003137112],"category_scores_gemma":[0.009335799,0.00045589288,0.0005261139,0.0004355834,0.0014002902,0.0012914853,0.0015568807,0.0022149466,0.0010063784],"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":[0.00012093373,0.000045505334,0.0005217041,0.00009214291,0.00003915793,0.00007904162,0.00011324372,0.847972,0.004920507,0.10113887,0.0022174972,0.04273937],"study_design_scores_gemma":[0.000010275935,0.000015501246,0.000032292002,0.000006571388,0.0000017304577,0.000009498367,0.0000039295687,0.98618,0.0009384227,0.012169059,0.0006279888,0.000004682549],"about_ca_topic_score_codex":0.0015798963,"about_ca_topic_score_gemma":0.0018246286,"teacher_disagreement_score":0.003137112,"about_ca_system_score_codex":0.0008586236,"about_ca_system_score_gemma":0.0012918862,"threshold_uncertainty_score":0.011805952},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029501004,0.0012342324,0.96064085,0.000745387,0.0002259747,0.00013564696,0.00026839715,0.0017017146,0.0055467393],"genre_scores_gemma":[0.4288446,0.00066749693,0.56454235,0.00055386306,0.00018219302,0.0002360052,0.0007231342,0.00073411217,0.0035161856],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973483,0.0012234709,0.00012269674,0.00043595143,0.00074697105,0.00012259895],"domain_scores_gemma":[0.9925799,0.004206953,0.0003856942,0.0011102046,0.0014544693,0.00026276236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006234697,0.0016968788,0.001245813,0.0015063387,0.00083425397,0.0018872117,0.0022684173,0.0019441461,0.003412025],"category_scores_gemma":[0.027475927,0.0006065776,0.0008626238,0.001043731,0.0020502722,0.0051783468,0.0028152287,0.0027956553,0.0008416822],"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":[0.00028668798,0.00024792255,0.0031688814,0.0003097026,0.00014534986,0.00008295223,0.00014674294,0.71884143,0.0027335628,0.117456734,0.007685822,0.14889416],"study_design_scores_gemma":[0.000015840966,0.00006718137,0.00014723436,0.000021131873,0.000006633535,0.00002218015,0.00000918909,0.968116,0.001047235,0.029081274,0.0014577141,0.000008444632],"about_ca_topic_score_codex":0.006603812,"about_ca_topic_score_gemma":0.0095542,"teacher_disagreement_score":0.006603812,"about_ca_system_score_codex":0.001990848,"about_ca_system_score_gemma":0.002619635,"threshold_uncertainty_score":0.032972574},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008043318,0.00026716263,0.9883692,0.00025776573,0.000042901625,0.000042689804,0.00007613932,0.00037907934,0.0025217512],"genre_scores_gemma":[0.45025203,0.000668348,0.5407312,0.0005192313,0.0002820646,0.0004011182,0.0006444294,0.0005522173,0.0059493617],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99414283,0.0021187866,0.00025202843,0.00065497163,0.0022523727,0.00057887984],"domain_scores_gemma":[0.9748971,0.017389348,0.0013668882,0.0037226842,0.0019283189,0.000695664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061573675,0.0019328174,0.001538468,0.0016045567,0.00090782635,0.0027927414,0.0028683436,0.0017045676,0.0060755867],"category_scores_gemma":[0.04268869,0.000678026,0.0012158314,0.0017084262,0.0033195475,0.006090789,0.0041410862,0.004709378,0.001456389],"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":[0.00030476472,0.00011760982,0.0019264084,0.00029380972,0.00009296785,0.00013719214,0.00023972367,0.49368224,0.0046078637,0.4263413,0.0033428904,0.06891324],"study_design_scores_gemma":[0.00001170404,0.000045312125,0.00016065784,0.000024767154,0.000008487588,0.000038257494,0.000018350596,0.9031759,0.001790252,0.093578726,0.0011315022,0.000016130318],"about_ca_topic_score_codex":0.0028378305,"about_ca_topic_score_gemma":0.0028251088,"teacher_disagreement_score":0.0061573675,"about_ca_system_score_codex":0.0031633223,"about_ca_system_score_gemma":0.0018237499,"threshold_uncertainty_score":0.032563686},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065546194,0.0008313542,0.9881577,0.0012870833,0.00023154067,0.00013559581,0.00025133384,0.0005655702,0.001985111],"genre_scores_gemma":[0.20761253,0.0021382584,0.7736665,0.0016781441,0.00185914,0.0018134769,0.0015428377,0.0017750327,0.007914191],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97366196,0.013717999,0.0014025845,0.0031758563,0.006586351,0.0014552725],"domain_scores_gemma":[0.5714717,0.37576574,0.0059754215,0.030392744,0.012511925,0.0038825579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.046722177,0.004561781,0.0061413916,0.0035904793,0.0018007716,0.005862706,0.009751324,0.0063392846,0.012148342],"category_scores_gemma":[0.3129743,0.00333275,0.0031356288,0.0038786524,0.007859194,0.018605834,0.01359313,0.015447097,0.0028432044],"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":[0.0036721379,0.0006638161,0.0067387857,0.0013790886,0.00064373424,0.0007715011,0.001093133,0.26970613,0.01517201,0.5272244,0.01115592,0.1617793],"study_design_scores_gemma":[0.00025847377,0.00022003285,0.00068305084,0.00013956998,0.00013311283,0.00020181318,0.000067530775,0.7621347,0.0039996738,0.2298439,0.0022417766,0.00007635298],"about_ca_topic_score_codex":0.0017348859,"about_ca_topic_score_gemma":0.0022815014,"teacher_disagreement_score":0.046722177,"about_ca_system_score_codex":0.0030576116,"about_ca_system_score_gemma":0.0054940404,"threshold_uncertainty_score":0.24709344},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018502476,0.00090867886,0.958702,0.0004589449,0.00018179054,0.00006459097,0.00047240016,0.0057679494,0.014941203],"genre_scores_gemma":[0.41154376,0.0008821674,0.5665254,0.00030234398,0.0002362023,0.00032052165,0.001535843,0.0007370521,0.017916676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993218,0.00014528788,0.00004171827,0.00009031227,0.0003298977,0.00007105958],"domain_scores_gemma":[0.99836713,0.00044360184,0.00010245584,0.00049519865,0.0005298276,0.000061805724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005044835,0.00054612366,0.000919753,0.00050136226,0.0006307299,0.0010045628,0.0015859961,0.000858285,0.010533478],"category_scores_gemma":[0.004268431,0.00028022967,0.0003221142,0.0012801986,0.0003657312,0.0016761204,0.0014020497,0.000897489,0.0055104187],"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":[0.00054088014,0.00019748943,0.0021891966,0.00053047313,0.00012944241,0.0005483548,0.00029697557,0.23171228,0.02653401,0.1570316,0.081222795,0.49906644],"study_design_scores_gemma":[0.000038479793,0.00006144446,0.00022559841,0.000023089757,0.000011446022,0.0001606971,0.000027846836,0.9250229,0.008327226,0.04409603,0.021988044,0.000017244154],"about_ca_topic_score_codex":0.0019289734,"about_ca_topic_score_gemma":0.0039498974,"teacher_disagreement_score":0.010533478,"about_ca_system_score_codex":0.0003449035,"about_ca_system_score_gemma":0.0010866108,"threshold_uncertainty_score":0.035238028},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0104827415,0.0015509739,0.9782543,0.0022352752,0.00024126552,0.000089036315,0.00018905968,0.00022118707,0.006736066],"genre_scores_gemma":[0.4548116,0.0049252254,0.5113168,0.0018124786,0.0019165364,0.0014831887,0.0012303843,0.0013348814,0.021168884],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99381495,0.0031556,0.00022238634,0.0005141101,0.0018734606,0.00041947278],"domain_scores_gemma":[0.94934255,0.04294986,0.0018067495,0.0023097266,0.0027024266,0.00088876166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008267175,0.0022399377,0.002736044,0.0019178122,0.0013932667,0.003359248,0.0030895274,0.0027890175,0.0066505126],"category_scores_gemma":[0.049355194,0.0012594536,0.0016349208,0.0023484307,0.0036977879,0.0077665234,0.004730847,0.0077688023,0.0010696321],"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":[0.0003043475,0.00015671337,0.0010600265,0.0003197157,0.00009874386,0.00010359791,0.0001439271,0.3368514,0.0014720765,0.6201964,0.00822258,0.031070458],"study_design_scores_gemma":[0.000024760306,0.000033040655,0.0001905877,0.000026904267,0.000014205054,0.000019043917,0.0000113539145,0.84201235,0.0003054271,0.15637688,0.00096991425,0.000015422484],"about_ca_topic_score_codex":0.0049329763,"about_ca_topic_score_gemma":0.0047600744,"teacher_disagreement_score":0.008267175,"about_ca_system_score_codex":0.0034675272,"about_ca_system_score_gemma":0.004020049,"threshold_uncertainty_score":0.043721557},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01633184,0.00004685795,0.9828488,0.0000674923,0.000008241511,0.000030313488,0.0000125848055,0.00014418681,0.0005097549],"genre_scores_gemma":[0.53542787,0.00020342566,0.46261317,0.000073488816,0.000027902945,0.00033557235,0.0000921678,0.00013035467,0.001096063],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854076,0.00067287654,0.000079179765,0.00027356765,0.00035635568,0.00007728436],"domain_scores_gemma":[0.99556184,0.002856527,0.00053947605,0.00047842498,0.00044912804,0.00011454932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028264767,0.0006283787,0.0011570216,0.00072290737,0.00036648367,0.00093855715,0.0007777739,0.00083432795,0.0019176961],"category_scores_gemma":[0.014408688,0.00067268196,0.00059626374,0.00044450624,0.00097044697,0.0017649041,0.0011207585,0.001211105,0.0003956259],"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":[0.00006741609,0.00003350263,0.0008440564,0.000046179823,0.000037549948,0.00002316677,0.000034755754,0.95787364,0.0030761503,0.022361102,0.00016050175,0.0154420305],"study_design_scores_gemma":[0.00001130523,0.000031670672,0.00012257333,0.000007074531,0.000006519098,0.000006597554,0.0000026050056,0.9912102,0.0011413867,0.0071895965,0.00026366455,0.0000068273052],"about_ca_topic_score_codex":0.0017220351,"about_ca_topic_score_gemma":0.0017391674,"teacher_disagreement_score":0.0028264767,"about_ca_system_score_codex":0.00071837445,"about_ca_system_score_gemma":0.001475265,"threshold_uncertainty_score":0.01494807},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024898746,0.000034969762,0.99588543,0.00016002807,0.000020836065,0.00002514913,0.000018257166,0.00010635694,0.0012591336],"genre_scores_gemma":[0.28053784,0.0002463832,0.7090016,0.00028666377,0.00010415834,0.0005434029,0.00016568626,0.0003908041,0.008723408],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99923015,0.00040593257,0.000026894011,0.000112409674,0.00019158128,0.00003304334],"domain_scores_gemma":[0.99743587,0.0017811864,0.00016949486,0.00021160363,0.0002628843,0.00013900433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026073484,0.0014048463,0.0014738567,0.000524222,0.0005206562,0.0015068486,0.0015315244,0.0016470137,0.0044760564],"category_scores_gemma":[0.0080393,0.00078635727,0.0007121467,0.0006276545,0.0015216831,0.0022299604,0.0028336155,0.0026688932,0.0009951484],"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":[0.00016708836,0.0002179374,0.00033679596,0.00023120476,0.000079671256,0.00016952713,0.00012428137,0.5821975,0.0044812416,0.33693781,0.0070316615,0.068025246],"study_design_scores_gemma":[0.00001389452,0.000022413808,0.000016727352,0.000004149611,0.0000030754293,0.000011814019,0.000004374636,0.9690985,0.0002848515,0.0301486,0.0003868418,0.000004786693],"about_ca_topic_score_codex":0.0007767947,"about_ca_topic_score_gemma":0.0010361775,"teacher_disagreement_score":0.0044760564,"about_ca_system_score_codex":0.0006376703,"about_ca_system_score_gemma":0.0015081723,"threshold_uncertainty_score":0.014973938},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012918387,0.000111629335,0.99660873,0.00010159683,0.000060154078,0.00003241419,0.000029907922,0.00027119476,0.0014925047],"genre_scores_gemma":[0.097466335,0.0003926658,0.8923697,0.00024288436,0.00018288069,0.00035316826,0.00022221066,0.00036114233,0.008408979],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99913967,0.00029303873,0.00002715278,0.00013198555,0.0003444312,0.00006361179],"domain_scores_gemma":[0.99935156,0.0001993098,0.000049376173,0.000093971015,0.00025101035,0.000054837437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011091818,0.0010398879,0.0013508938,0.0007559778,0.00049147307,0.0010388443,0.0016256272,0.0013790341,0.006317773],"category_scores_gemma":[0.003141656,0.0005533271,0.0007742126,0.00070480787,0.00086747005,0.0011147519,0.0017616198,0.0017849656,0.0025785938],"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":[0.00019362364,0.00010180757,0.0006079048,0.00027220004,0.000097154356,0.00022072185,0.00011301616,0.63482124,0.010421024,0.14253305,0.01733634,0.19328183],"study_design_scores_gemma":[0.000026327014,0.000031274332,0.000050919665,0.00000898933,0.000007785205,0.00004925208,0.000004959302,0.98527724,0.0011526325,0.0078042545,0.0055764806,0.000009795914],"about_ca_topic_score_codex":0.0024891293,"about_ca_topic_score_gemma":0.0020743862,"teacher_disagreement_score":0.006317773,"about_ca_system_score_codex":0.00054613437,"about_ca_system_score_gemma":0.0018920213,"threshold_uncertainty_score":0.021135032},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00095541833,0.000049446033,0.99838614,0.000034199806,0.000020628771,0.000014582609,0.000014707709,0.00008713984,0.00043777522],"genre_scores_gemma":[0.10542803,0.00021339237,0.8879991,0.00012892613,0.00010077616,0.00026314228,0.00015020215,0.00020481154,0.0055116555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99920124,0.0002571061,0.000034892193,0.0000940155,0.00036652453,0.000046212695],"domain_scores_gemma":[0.99853945,0.0008169142,0.00010877573,0.00014406609,0.00032932113,0.00006136617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013741009,0.00092459965,0.0015434824,0.0005429328,0.000371441,0.0009994117,0.0014394746,0.0014778395,0.0042652236],"category_scores_gemma":[0.0046864776,0.00057136634,0.0006689334,0.00072475534,0.0007149741,0.001112725,0.0012433425,0.0014870443,0.0012846928],"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":[0.00017199229,0.000088709494,0.00024700534,0.0002235352,0.00006910653,0.00013176144,0.000073474475,0.8019512,0.00743198,0.040923204,0.0042990325,0.14438896],"study_design_scores_gemma":[0.0000061332466,0.0000123670225,0.000016545166,0.000002283802,0.0000027982903,0.000011052169,0.0000017626223,0.99715734,0.0002887864,0.0020555574,0.00044179303,0.0000036850593],"about_ca_topic_score_codex":0.004008511,"about_ca_topic_score_gemma":0.0038754183,"teacher_disagreement_score":0.0042652236,"about_ca_system_score_codex":0.0005252976,"about_ca_system_score_gemma":0.0015001585,"threshold_uncertainty_score":0.014268577},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018968105,0.00064310856,0.9919431,0.0005241516,0.0000638109,0.000021130681,0.000041931147,0.00029049552,0.004575389],"genre_scores_gemma":[0.3385999,0.0024304683,0.6379496,0.0021244357,0.00078520173,0.000677712,0.0005303917,0.0015224996,0.015379826],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948384,0.002179488,0.00018147794,0.000647746,0.001823978,0.00032885297],"domain_scores_gemma":[0.98891824,0.0072999517,0.0006785753,0.0012009095,0.0016463046,0.00025596647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065636807,0.0020527244,0.0018002961,0.0012319149,0.000863083,0.0035496794,0.0023218575,0.002192781,0.0058623916],"category_scores_gemma":[0.032859724,0.0009877068,0.00095938065,0.0013426827,0.0030846773,0.005445697,0.0030390352,0.005713287,0.0021770773],"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":[0.00010528625,0.00008275906,0.00059212255,0.00021701567,0.0000647389,0.000111796944,0.00015144197,0.4584001,0.0014635131,0.4422358,0.011192209,0.08538318],"study_design_scores_gemma":[0.0000098789105,0.000020445133,0.00009229667,0.000038119826,0.000009440738,0.00004303601,0.000009273902,0.8173837,0.0008502533,0.17918517,0.0023451564,0.000013241261],"about_ca_topic_score_codex":0.00235345,"about_ca_topic_score_gemma":0.00249501,"teacher_disagreement_score":0.0065636807,"about_ca_system_score_codex":0.002819974,"about_ca_system_score_gemma":0.0022265564,"threshold_uncertainty_score":0.034712493},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002286446,0.0048626056,0.0022374555,0.12684931,0.85950017,0.000019185758,0.00010903504,0.00017961228,0.006014035],"genre_scores_gemma":[0.0030619362,0.004697363,0.0012573211,0.050761405,0.906199,0.000029961568,0.00009956976,0.00029261605,0.03360081],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976572,0.00042271038,0.00029853894,0.0004331868,0.000995294,0.0001930846],"domain_scores_gemma":[0.9872859,0.0029960321,0.0005832198,0.000578685,0.007240099,0.0013161938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026094874,0.0017730648,0.0023353826,0.0020928693,0.0017929119,0.004364721,0.0021101234,0.0053232247,0.020618316],"category_scores_gemma":[0.012250123,0.00066250894,0.0013804559,0.0013476594,0.0012951073,0.0023275365,0.0007557372,0.009138642,0.015939051],"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":[0.000044224827,0.000010921928,0.00005972866,0.000061512736,0.000015621608,0.000064383086,0.0000053572116,0.00007713256,0.00016163677,0.00064307265,0.9912504,0.0076061906],"study_design_scores_gemma":[0.000033148754,0.000045632118,0.0005538097,0.00011771626,0.000050779905,0.00037340357,0.000025082605,0.0016168145,0.0009931112,0.0023740942,0.99376935,0.0000469765],"about_ca_topic_score_codex":0.0019624103,"about_ca_topic_score_gemma":0.00572373,"teacher_disagreement_score":0.020618316,"about_ca_system_score_codex":0.0021687422,"about_ca_system_score_gemma":0.0014870578,"threshold_uncertainty_score":0.06897515},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001287534,0.00008353168,0.99792707,0.000070985174,0.000022246977,0.000009377011,0.0000071321842,0.000047268553,0.0005448327],"genre_scores_gemma":[0.12257124,0.0003942958,0.87198627,0.00015075522,0.000099780715,0.00016093819,0.000103147795,0.00016521213,0.0043683983],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985262,0.00072876946,0.00006689226,0.00018148137,0.00043273924,0.000063940526],"domain_scores_gemma":[0.99718237,0.0016260879,0.00021816944,0.00025512165,0.000583293,0.00013498566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031186368,0.0006645863,0.0015004498,0.0008492963,0.0004700838,0.0012462919,0.0018351505,0.0014892521,0.002518563],"category_scores_gemma":[0.009043531,0.00057524076,0.00095189293,0.0008563261,0.0014036421,0.0014584652,0.001546016,0.0024473509,0.0010520879],"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":[0.00009232678,0.00008792626,0.0007412074,0.00017535004,0.000060272378,0.00015195309,0.00014119726,0.6265963,0.0046353266,0.23475586,0.0030044264,0.1295579],"study_design_scores_gemma":[0.000006077577,0.000019454794,0.000028326165,0.000011070143,0.0000035850492,0.000025265344,0.0000033627455,0.98190844,0.00058025925,0.01654342,0.0008648266,0.000005892663],"about_ca_topic_score_codex":0.0012929215,"about_ca_topic_score_gemma":0.0010355943,"teacher_disagreement_score":0.0031186368,"about_ca_system_score_codex":0.00062094704,"about_ca_system_score_gemma":0.0011422662,"threshold_uncertainty_score":0.016493082},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009968507,0.000024691684,0.9977968,0.00007448255,0.00005808335,0.000027064929,0.000009959309,0.0001334424,0.00087860716],"genre_scores_gemma":[0.24063055,0.00029182938,0.7495772,0.00032276948,0.00031098217,0.00034206963,0.000083178435,0.00028209685,0.008159252],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913317,0.00030012187,0.00004894769,0.00015462776,0.0003067715,0.000056344572],"domain_scores_gemma":[0.99870574,0.0005461709,0.000083545936,0.00037624442,0.0002006961,0.00008751866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015620668,0.0009491131,0.0012898484,0.0005322577,0.0006940217,0.0014523129,0.002012355,0.0014283131,0.0053006555],"category_scores_gemma":[0.005861675,0.00056122645,0.0008980275,0.00080677326,0.0010867334,0.0019254531,0.0022923793,0.003626236,0.0011354046],"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":[0.00010896668,0.00025390976,0.00047719106,0.00016616512,0.00011169169,0.00019852685,0.00012217744,0.6158862,0.011405663,0.25213265,0.004705352,0.114431426],"study_design_scores_gemma":[0.000012765355,0.000017110693,0.000055212666,0.000004408216,0.000009595557,0.000032187178,0.0000052969262,0.95957464,0.00054684083,0.03823355,0.0014995355,0.000008854639],"about_ca_topic_score_codex":0.001585722,"about_ca_topic_score_gemma":0.0021281708,"teacher_disagreement_score":0.0053006555,"about_ca_system_score_codex":0.00062815513,"about_ca_system_score_gemma":0.0011117274,"threshold_uncertainty_score":0.017732382},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029660765,0.0028354342,0.9601597,0.0024305107,0.00015013028,0.00011468875,0.00035779466,0.0002859547,0.0040050396],"genre_scores_gemma":[0.5771063,0.0054996223,0.40461877,0.0013158227,0.0013184347,0.0015170402,0.0016666371,0.000805993,0.0061513656],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98907894,0.005967241,0.0006269505,0.0019538635,0.001932401,0.00044068083],"domain_scores_gemma":[0.88740224,0.097005665,0.0038413866,0.0066063525,0.003923782,0.0012206092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024416834,0.0024426489,0.004396271,0.0038112665,0.001597631,0.0046531768,0.003979999,0.0042834445,0.003753698],"category_scores_gemma":[0.13610783,0.0014082058,0.0017526054,0.0025651008,0.007862831,0.0124205025,0.006897345,0.007941014,0.0009970384],"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":[0.0005738529,0.00011620002,0.0037204667,0.0006531575,0.00026406726,0.00024400043,0.00045787383,0.2991029,0.0026366643,0.6491333,0.0044188756,0.03867857],"study_design_scores_gemma":[0.000036066376,0.000113780654,0.00072186784,0.00013470177,0.000025639461,0.000111860354,0.000058875314,0.51333266,0.00135849,0.4826646,0.0013790885,0.00006243204],"about_ca_topic_score_codex":0.00089841516,"about_ca_topic_score_gemma":0.00050195784,"teacher_disagreement_score":0.024416834,"about_ca_system_score_codex":0.0025356612,"about_ca_system_score_gemma":0.0015467191,"threshold_uncertainty_score":0.12913013},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052294508,0.0012114587,0.9903273,0.00037981913,0.00014750316,0.000024360812,0.00006839428,0.00039389264,0.0022178139],"genre_scores_gemma":[0.38951477,0.002154878,0.57565117,0.00050105836,0.00045177466,0.0003782546,0.00058430317,0.0008054461,0.029958343],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996302,0.00014321442,0.00002027367,0.00006223036,0.000109843066,0.000034201592],"domain_scores_gemma":[0.99882346,0.0007092055,0.000074283744,0.00011984827,0.00020503026,0.00006812006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011587224,0.0009388506,0.0013698518,0.0006326742,0.0004723258,0.0010082432,0.0014043387,0.0020370735,0.0036496993],"category_scores_gemma":[0.005014408,0.0008333681,0.0005937803,0.0009889515,0.0013109703,0.001460694,0.0014312228,0.0027080765,0.00091538654],"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":[0.00009010973,0.00006428396,0.00031483528,0.00018022659,0.000064948006,0.00005497261,0.000060671126,0.74303514,0.0016848214,0.1683527,0.008262707,0.077834606],"study_design_scores_gemma":[0.000004062465,0.000006371121,0.000031039097,0.000006679457,0.0000031836487,0.0000041369485,0.0000015353596,0.96974874,0.0001592838,0.029398486,0.00063332776,0.0000030936596],"about_ca_topic_score_codex":0.0072799125,"about_ca_topic_score_gemma":0.00911138,"teacher_disagreement_score":0.0072799125,"about_ca_system_score_codex":0.0014439017,"about_ca_system_score_gemma":0.0014995064,"threshold_uncertainty_score":0.014475048},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023139513,0.000038941478,0.99667007,0.00005103606,0.00002028497,0.000020789099,0.000006820355,0.00009246462,0.0007856405],"genre_scores_gemma":[0.33255842,0.000179053,0.6621141,0.00013659813,0.000076816665,0.00037332476,0.00008854699,0.000102669204,0.004370486],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935,0.0002469589,0.000029102936,0.00014117129,0.0001764155,0.00005633434],"domain_scores_gemma":[0.999236,0.00040492485,0.000076096185,0.00007470568,0.00016646189,0.00004185959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001602636,0.000962977,0.0009505194,0.0004515346,0.00055905164,0.0008053696,0.0015716508,0.0011045228,0.0024181919],"category_scores_gemma":[0.002792837,0.0004133061,0.000607631,0.0007210576,0.0007681919,0.0010326398,0.0011409677,0.0015393456,0.00056298566],"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":[0.000079287616,0.000049821807,0.00017907795,0.000055111745,0.000032113705,0.000051151375,0.0000792632,0.89472026,0.0020350486,0.03874566,0.0015373728,0.06243594],"study_design_scores_gemma":[0.000017994264,0.000020293699,0.00001353023,0.000002514233,0.00000276016,0.000010135809,0.0000041328235,0.99311596,0.00027625487,0.0060483217,0.00048537468,0.0000027103126],"about_ca_topic_score_codex":0.0020983797,"about_ca_topic_score_gemma":0.002109478,"teacher_disagreement_score":0.0024181919,"about_ca_system_score_codex":0.00073204556,"about_ca_system_score_gemma":0.0015024235,"threshold_uncertainty_score":0.008475661},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034198689,0.000088865345,0.9933816,0.00020824163,0.000069304704,0.00006487462,0.00006377754,0.0008451476,0.0018582204],"genre_scores_gemma":[0.110707425,0.0001637783,0.8812911,0.00036224702,0.00013876265,0.00033312585,0.00037434365,0.00031093752,0.006318321],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99851745,0.0003798989,0.000067012916,0.00031017445,0.0005701838,0.0001553148],"domain_scores_gemma":[0.99895775,0.0003788346,0.000088257795,0.00025118244,0.00026769945,0.000056327804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011469141,0.0007732887,0.0011355133,0.00095512375,0.0007976134,0.0013180802,0.002024625,0.00155948,0.0068824054],"category_scores_gemma":[0.004942439,0.0005819272,0.0006519868,0.0008411017,0.0009653985,0.0016604214,0.002092434,0.0018021795,0.0035035782],"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":[0.00045365564,0.00023559463,0.0007202859,0.00014262667,0.00008694154,0.00017799981,0.00010259939,0.41949114,0.014630012,0.15677907,0.016361138,0.39081886],"study_design_scores_gemma":[0.000085373904,0.000044590444,0.00008173406,0.000008075837,0.000009291093,0.00007562129,0.000010616106,0.9738791,0.0028236264,0.017698843,0.005262182,0.000020941437],"about_ca_topic_score_codex":0.0028344349,"about_ca_topic_score_gemma":0.0038669824,"teacher_disagreement_score":0.0068824054,"about_ca_system_score_codex":0.0007394507,"about_ca_system_score_gemma":0.0027792805,"threshold_uncertainty_score":0.023023903},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048804455,0.00006589899,0.9942228,0.00010588129,0.0000070626947,0.000010748689,0.00006544392,0.00017027021,0.00047145493],"genre_scores_gemma":[0.5370622,0.00043654826,0.4532299,0.00023573764,0.00006650807,0.00025603359,0.00094767904,0.00034536808,0.0074199834],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918324,0.00039137248,0.000029014558,0.00018119598,0.00013394323,0.00008117717],"domain_scores_gemma":[0.9980081,0.0012674164,0.00020426339,0.00026892737,0.00017379672,0.00007756469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001611717,0.0011071791,0.0010249995,0.00046252884,0.00033550584,0.0011881238,0.0019824593,0.0011907576,0.002929813],"category_scores_gemma":[0.0045773066,0.0010680895,0.0010503528,0.0007215841,0.0011108641,0.0023792689,0.0018768447,0.0023871039,0.00073184405],"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":[0.000060630886,0.000027985498,0.00035798247,0.000046236226,0.00003980892,0.00005051172,0.00005388695,0.9340457,0.0013716806,0.04571227,0.0009961441,0.017237239],"study_design_scores_gemma":[0.0000015240176,0.0000031665747,0.000022052487,0.0000011894477,0.0000014077516,0.0000030125404,0.0000012380232,0.9934989,0.00014497913,0.0062230406,0.00009765077,0.0000019264821],"about_ca_topic_score_codex":0.0059137424,"about_ca_topic_score_gemma":0.00728046,"teacher_disagreement_score":0.0059137424,"about_ca_system_score_codex":0.001175289,"about_ca_system_score_gemma":0.0012921368,"threshold_uncertainty_score":0.0117586255},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008261203,0.00032217632,0.9850745,0.00035318843,0.00014334498,0.000040962237,0.000046149697,0.00028714648,0.0054713646],"genre_scores_gemma":[0.59774625,0.0007375529,0.3897213,0.0003296388,0.00019214959,0.0002925093,0.0001537418,0.0001688256,0.010658025],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998978,0.0003292371,0.000041438932,0.000098393844,0.00040699623,0.00014593475],"domain_scores_gemma":[0.99812406,0.00078417495,0.0001364271,0.0005355361,0.00032262632,0.00009715125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010546765,0.00060032145,0.0005820814,0.00047269533,0.0005947253,0.0011746152,0.0012948872,0.00072529836,0.0040390114],"category_scores_gemma":[0.0047808117,0.00020379135,0.00044461046,0.0009291663,0.0013051522,0.0017156826,0.0015184877,0.0018577158,0.0007742163],"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":[0.00017777148,0.00004462528,0.00022125032,0.00010028211,0.000015521222,0.00009404455,0.00012880469,0.2356399,0.006163954,0.69249755,0.0037830772,0.0611331],"study_design_scores_gemma":[0.000016681388,0.000035863577,0.0000416461,0.000014680197,0.0000053125473,0.000030353945,0.000013494681,0.87222224,0.0019746653,0.121787645,0.0038466265,0.000010814015],"about_ca_topic_score_codex":0.0020271305,"about_ca_topic_score_gemma":0.002306842,"teacher_disagreement_score":0.0040390114,"about_ca_system_score_codex":0.0014779232,"about_ca_system_score_gemma":0.0014565206,"threshold_uncertainty_score":0.0135118365},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006203634,0.0003987709,0.9887793,0.0008786402,0.00004942413,0.00003265539,0.00011618998,0.00014164376,0.0033996757],"genre_scores_gemma":[0.5986535,0.0032047792,0.3773949,0.0019935456,0.00094501156,0.00067585026,0.0013979404,0.00075663277,0.014977804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9952762,0.0022304705,0.00016346725,0.00078933284,0.0012442227,0.00029628255],"domain_scores_gemma":[0.97644687,0.017932344,0.0014749214,0.0021367916,0.0014352461,0.0005739049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008385166,0.0025546958,0.0022587993,0.0016810194,0.0007955374,0.003037935,0.002679526,0.002994403,0.006616803],"category_scores_gemma":[0.04474202,0.0011813067,0.0013152336,0.0018228127,0.004541826,0.007118556,0.006306895,0.0067732246,0.0013677177],"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":[0.00010922351,0.00008478313,0.0009063496,0.00017777656,0.00006367999,0.00015770135,0.00012130583,0.41677892,0.0011708003,0.55493975,0.0037750057,0.021714643],"study_design_scores_gemma":[0.000012732121,0.0000468931,0.00015582154,0.000041864474,0.000008643136,0.000037388752,0.000009543552,0.6826382,0.00033422196,0.3158855,0.0008139339,0.000015231454],"about_ca_topic_score_codex":0.0012718975,"about_ca_topic_score_gemma":0.0010661539,"teacher_disagreement_score":0.008385166,"about_ca_system_score_codex":0.002208805,"about_ca_system_score_gemma":0.0020546478,"threshold_uncertainty_score":0.044345558},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03964284,0.0112802405,0.9161366,0.004517388,0.00049108645,0.00010792944,0.0011160634,0.0014444408,0.025263403],"genre_scores_gemma":[0.8035972,0.010110042,0.16312651,0.0029552479,0.0017961481,0.0009603001,0.0021340875,0.0013190156,0.014001409],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960194,0.001205019,0.00019592152,0.0007822248,0.0011244508,0.000673062],"domain_scores_gemma":[0.9689126,0.023345524,0.0013253741,0.002787849,0.0024814128,0.0011472645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004998351,0.0035611063,0.0027170223,0.003102455,0.001498986,0.004623688,0.003416214,0.0027165804,0.00858715],"category_scores_gemma":[0.045502037,0.0014435339,0.0018050314,0.002969266,0.0038476523,0.010146543,0.0072085215,0.01062614,0.0017777085],"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":[0.00041552252,0.00020474386,0.0030923453,0.0007786527,0.00025362297,0.00026698085,0.00040471533,0.41906464,0.0069906,0.46490988,0.0176756,0.08594283],"study_design_scores_gemma":[0.00001689231,0.000057172878,0.00063267985,0.000127207,0.000038783586,0.00010251672,0.0000364868,0.7330203,0.0019274652,0.26048416,0.0035118104,0.000044481123],"about_ca_topic_score_codex":0.0026529965,"about_ca_topic_score_gemma":0.0028057538,"teacher_disagreement_score":0.00858715,"about_ca_system_score_codex":0.0039984053,"about_ca_system_score_gemma":0.0015161458,"threshold_uncertainty_score":0.029010534},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011191522,0.00016613833,0.996478,0.00009803872,0.00007548844,0.000037126123,0.000018100887,0.0008371997,0.0011708571],"genre_scores_gemma":[0.12191189,0.0004922214,0.86748457,0.00040599803,0.0003143827,0.0005152091,0.00019819153,0.0012199891,0.007457551],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768114,0.00089720666,0.0001443833,0.0003774527,0.0007582783,0.00014142119],"domain_scores_gemma":[0.99716187,0.0010750326,0.00030652882,0.00074155966,0.0005831976,0.00013177191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034008021,0.0020520664,0.002043532,0.001099707,0.0005334177,0.0016577699,0.003248314,0.0023939996,0.0046234024],"category_scores_gemma":[0.014467868,0.0010316726,0.0009807439,0.0009955737,0.001589738,0.002464507,0.0028948437,0.003974655,0.0039068065],"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":[0.00019565909,0.00016502975,0.00083905144,0.00031784328,0.00019116237,0.00023501548,0.00017594286,0.63826174,0.011937877,0.083743684,0.013477559,0.25045946],"study_design_scores_gemma":[0.000021752323,0.000031648175,0.0000745441,0.000017309994,0.0000074259106,0.00004660653,0.0000041477592,0.98197997,0.0024331773,0.012150801,0.0032183419,0.000014283599],"about_ca_topic_score_codex":0.0016182,"about_ca_topic_score_gemma":0.0017445334,"teacher_disagreement_score":0.0046234024,"about_ca_system_score_codex":0.0008427134,"about_ca_system_score_gemma":0.0017206167,"threshold_uncertainty_score":0.017985404},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04942261,0.0018553576,0.94023305,0.0020488782,0.00010500145,0.000042865682,0.00017414575,0.0005440397,0.0055739903],"genre_scores_gemma":[0.808029,0.0013694993,0.18406154,0.001443496,0.00026084858,0.00035967812,0.00048762452,0.0006800176,0.0033082818],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99511224,0.0018531425,0.0002858731,0.0010438153,0.0013798047,0.00032513074],"domain_scores_gemma":[0.93254286,0.058099374,0.0023776016,0.004693414,0.0014320195,0.00085469714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011455873,0.0018288855,0.0015790556,0.0022022652,0.0010503398,0.002462153,0.0026333241,0.0024800026,0.0027229814],"category_scores_gemma":[0.08398829,0.0011685676,0.0014962023,0.0013201532,0.006268711,0.008552341,0.005881782,0.007948782,0.0003464324],"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":[0.00014581565,0.00006536584,0.0021260644,0.0002388442,0.00010902367,0.00011878324,0.00026603165,0.59662396,0.0018605543,0.36730897,0.001743474,0.029393082],"study_design_scores_gemma":[0.000005217831,0.000019805664,0.00026879672,0.000039206392,0.000007178782,0.000019247142,0.000010901476,0.7362145,0.00075451535,0.26229152,0.000357279,0.000011819084],"about_ca_topic_score_codex":0.0024708712,"about_ca_topic_score_gemma":0.0024773509,"teacher_disagreement_score":0.011455873,"about_ca_system_score_codex":0.0043607815,"about_ca_system_score_gemma":0.0013472063,"threshold_uncertainty_score":0.0605852},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011789332,0.00039888214,0.9860221,0.0004406906,0.00003782727,0.000025985784,0.00006932181,0.0002954957,0.0009202672],"genre_scores_gemma":[0.61363953,0.001164539,0.37746888,0.0005046729,0.00044508182,0.00029099098,0.0006706398,0.0004728958,0.005342701],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99714917,0.0012936911,0.00012837269,0.0006644583,0.00054342963,0.00022090123],"domain_scores_gemma":[0.9864673,0.009178795,0.0012873849,0.0016823154,0.0009882961,0.00039583363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058087055,0.0015759598,0.0017317423,0.0008351483,0.00069589465,0.0018671998,0.002889279,0.002302277,0.0016516667],"category_scores_gemma":[0.033531256,0.0008223769,0.000998702,0.0012100685,0.0026469587,0.0043063075,0.0039031047,0.0041906885,0.0005477225],"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":[0.00029548275,0.00013417943,0.0021407253,0.00027811798,0.0001357176,0.0001964529,0.00015481678,0.77912146,0.006200067,0.16157354,0.0025647993,0.04720473],"study_design_scores_gemma":[0.000008858925,0.00002184759,0.00010134375,0.0000067558403,0.0000061108253,0.000015827964,0.0000061589876,0.9750728,0.0005937675,0.023901388,0.00025602255,0.000009127185],"about_ca_topic_score_codex":0.0035901945,"about_ca_topic_score_gemma":0.0027118383,"teacher_disagreement_score":0.0058087055,"about_ca_system_score_codex":0.0016631981,"about_ca_system_score_gemma":0.0016905803,"threshold_uncertainty_score":0.030719757},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045284866,0.00015735198,0.99175113,0.00017750525,0.000070349415,0.000027678452,0.00008620641,0.0009390658,0.002262292],"genre_scores_gemma":[0.2591709,0.0003385366,0.7262094,0.00031290622,0.00014269698,0.00024353387,0.0006843308,0.0012130695,0.011684626],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993919,0.00013747824,0.00003593198,0.00013878381,0.00022256517,0.00007327985],"domain_scores_gemma":[0.99833375,0.0007625262,0.00011333009,0.00031378254,0.0003663312,0.00011035148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012597818,0.0014910323,0.0014013154,0.00069539476,0.0005292895,0.0013688306,0.0018348842,0.0015510899,0.0055482592],"category_scores_gemma":[0.005070476,0.0006754549,0.0012154318,0.0007404721,0.0012432146,0.0015952763,0.0014026527,0.0023107445,0.0024098975],"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":[0.000053308126,0.000036264755,0.000501837,0.000066009874,0.00003314402,0.0000606196,0.000051545067,0.939988,0.0011999622,0.025358347,0.0037949022,0.028855998],"study_design_scores_gemma":[0.000003713293,0.0000031252425,0.000016379256,0.0000022171985,9.4743837e-7,0.000003656665,0.0000018100424,0.9960103,0.00011047592,0.003513877,0.000331305,0.0000021323037],"about_ca_topic_score_codex":0.015262984,"about_ca_topic_score_gemma":0.02361878,"teacher_disagreement_score":0.015262984,"about_ca_system_score_codex":0.0015707024,"about_ca_system_score_gemma":0.0026440597,"threshold_uncertainty_score":0.030348301},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008789917,0.02655277,0.9354294,0.0024879125,0.00243838,0.0011815717,0.0032035487,0.0048785293,0.015037997],"genre_scores_gemma":[0.04490902,0.0047778464,0.94167876,0.0005962531,0.0003395788,0.002161136,0.0024796727,0.0017180115,0.0013397877],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.84799904,0.08755508,0.021060636,0.0069585694,0.034819815,0.0016068551],"domain_scores_gemma":[0.74593717,0.16251005,0.006432149,0.052348163,0.03153537,0.0012371374],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06312083,0.0041969237,0.0052491515,0.016978584,0.003126682,0.011783266,0.008567775,0.0066499165,0.012215897],"category_scores_gemma":[0.3444492,0.002109722,0.0047917413,0.020270074,0.003392062,0.0075117364,0.0054726214,0.00835472,0.0043787365],"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":[0.0016703617,0.0009985302,0.00490206,0.011794826,0.005309477,0.0003583316,0.0010480477,0.049261827,0.003988111,0.14491642,0.061806146,0.7139459],"study_design_scores_gemma":[0.0020103098,0.0019354647,0.0070456383,0.014379255,0.00476137,0.0016335476,0.0020430137,0.17886019,0.036904328,0.53781456,0.21173732,0.00087500986],"about_ca_topic_score_codex":0.0049622194,"about_ca_topic_score_gemma":0.0056540025,"teacher_disagreement_score":0.93687916,"about_ca_system_score_codex":0.0030399922,"about_ca_system_score_gemma":0.0044102096,"threshold_uncertainty_score":0.33381885},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01321941,0.0027275032,0.9640458,0.012368031,0.00071927166,0.00007041004,0.00020407717,0.0005038152,0.006141669],"genre_scores_gemma":[0.49123102,0.0045402306,0.47741452,0.004850826,0.003506433,0.0006585491,0.0008368465,0.0019195608,0.015042092],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99592483,0.0020540634,0.0002113502,0.0006854078,0.0009101357,0.00021426346],"domain_scores_gemma":[0.9211064,0.06655272,0.0018794051,0.004776336,0.0041350285,0.00155015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010158255,0.0014270894,0.0021363003,0.0010918832,0.0013118976,0.00353265,0.0036803198,0.0051226914,0.0081795],"category_scores_gemma":[0.111723214,0.0011819893,0.0012264088,0.001028963,0.005151281,0.020750307,0.0038817043,0.010511108,0.0017034846],"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":[0.0005050176,0.0001902679,0.0025337986,0.0009109496,0.0002109312,0.00023445496,0.00047293596,0.1713699,0.0026538132,0.65220684,0.026017694,0.14269345],"study_design_scores_gemma":[0.000035681885,0.000060756814,0.0003633334,0.00011893973,0.000028191804,0.00007715318,0.00006298465,0.6321417,0.0012464796,0.36318207,0.0026396792,0.00004300914],"about_ca_topic_score_codex":0.0020441904,"about_ca_topic_score_gemma":0.0021281596,"teacher_disagreement_score":0.010158255,"about_ca_system_score_codex":0.0017242578,"about_ca_system_score_gemma":0.0019827867,"threshold_uncertainty_score":0.05372262},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00281172,0.0025330952,0.9902812,0.0006309514,0.0004234188,0.000028208447,0.00006935365,0.0002205072,0.0030016215],"genre_scores_gemma":[0.2095441,0.008262073,0.7348788,0.0007448133,0.002493819,0.0006131019,0.0006736057,0.0013572798,0.041432407],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982734,0.0008129227,0.00009223101,0.0002154866,0.0005163687,0.00008958897],"domain_scores_gemma":[0.9974171,0.0014478648,0.00020172042,0.00027205245,0.00049922854,0.0001619749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003263012,0.0017461685,0.0018394189,0.0013706713,0.00089503644,0.0023644194,0.0016399386,0.0029907238,0.003983271],"category_scores_gemma":[0.015929764,0.00074750494,0.0010112349,0.0028907561,0.0030202903,0.0036390782,0.0023453059,0.004955544,0.0014357482],"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":[0.00010776123,0.000094571944,0.00038719995,0.00029406065,0.00007514485,0.00008530503,0.00013583859,0.16017321,0.0017235994,0.74883467,0.012207596,0.07588104],"study_design_scores_gemma":[0.000013171721,0.000026853528,0.00019059384,0.00003322356,0.000017650167,0.00003627708,0.000015406102,0.73620486,0.0005806736,0.25558123,0.00727763,0.000022491336],"about_ca_topic_score_codex":0.004386762,"about_ca_topic_score_gemma":0.0041969274,"teacher_disagreement_score":0.004386762,"about_ca_system_score_codex":0.001375346,"about_ca_system_score_gemma":0.0026449654,"threshold_uncertainty_score":0.017256677},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019943837,0.00015773586,0.9770861,0.00012317223,0.000068616755,0.0000279982,0.000024412871,0.0011489979,0.0014189846],"genre_scores_gemma":[0.6435845,0.00024321904,0.3502012,0.00021795134,0.00010492262,0.00015216718,0.0001431152,0.0005381445,0.0048147184],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991567,0.00028274718,0.00004792579,0.00014862264,0.00026315957,0.000100985024],"domain_scores_gemma":[0.99876404,0.0004696136,0.00014984244,0.00032842095,0.00018144393,0.00010663508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013375883,0.0009719409,0.0010103307,0.00041332026,0.0006108333,0.0007928722,0.0017716071,0.00067607313,0.0016846764],"category_scores_gemma":[0.0036939234,0.0005004463,0.00038668775,0.00055395195,0.0010191969,0.0015994185,0.0015236384,0.0010052023,0.0006413538],"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":[0.0004641465,0.00013945125,0.0015145343,0.00011791083,0.000086548374,0.00015391529,0.0002509407,0.80813736,0.01241773,0.043470886,0.0029929809,0.13025358],"study_design_scores_gemma":[0.000024758281,0.00004275233,0.00007236785,0.0000035653366,0.0000060234897,0.000012542614,0.000008248781,0.98957235,0.0019503866,0.0072463993,0.0010543806,0.0000061861474],"about_ca_topic_score_codex":0.0038656525,"about_ca_topic_score_gemma":0.006060528,"teacher_disagreement_score":0.0038656525,"about_ca_system_score_codex":0.00066722545,"about_ca_system_score_gemma":0.0018776113,"threshold_uncertainty_score":0.007686317},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14179376,0.0036326672,0.819106,0.009828605,0.00030679407,0.00009694542,0.0006333345,0.0008007561,0.023801075],"genre_scores_gemma":[0.92275727,0.0018698898,0.06582504,0.0016083365,0.00014571086,0.00025156036,0.0006455631,0.0005206743,0.006376026],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986571,0.00053384784,0.000086376946,0.00033318705,0.00024186439,0.0001475089],"domain_scores_gemma":[0.99373466,0.003997203,0.0006165976,0.00071171386,0.0005450876,0.00039485283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041458146,0.00079482014,0.0016631205,0.001495854,0.0013503695,0.0025248937,0.0011597443,0.0029925685,0.007333674],"category_scores_gemma":[0.026462091,0.0011243391,0.0012380589,0.0006387225,0.0034064923,0.0061902995,0.0020521942,0.0026174893,0.001421399],"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":[0.00014344777,0.000056902747,0.003933923,0.0003489756,0.00018608259,0.00022556483,0.00045935498,0.1645408,0.002387046,0.79399866,0.011072191,0.022647006],"study_design_scores_gemma":[0.000026156402,0.000044105538,0.0006470584,0.00008453195,0.000016756308,0.000078396835,0.00008726088,0.21920237,0.00043615027,0.77714694,0.002206188,0.000024183359],"about_ca_topic_score_codex":0.0014957336,"about_ca_topic_score_gemma":0.001541446,"teacher_disagreement_score":0.007333674,"about_ca_system_score_codex":0.0010147517,"about_ca_system_score_gemma":0.0008223394,"threshold_uncertainty_score":0.02453357},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029520923,0.00033632622,0.9596284,0.0005188008,0.00015375554,0.000047641784,0.000057094734,0.0010809685,0.0086560445],"genre_scores_gemma":[0.7330329,0.00041631618,0.25133008,0.0004188813,0.0001935905,0.00027723872,0.00018058046,0.00078720634,0.013363288],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999458,0.00014748325,0.000025057914,0.000094343464,0.00020773217,0.000067383095],"domain_scores_gemma":[0.9982645,0.00087432575,0.00016775467,0.0002729445,0.00028813456,0.00013239593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012429387,0.0010180469,0.0007405194,0.0005494085,0.0007174579,0.0013778133,0.0010778948,0.0010840528,0.0052347356],"category_scores_gemma":[0.008137461,0.0004623014,0.0005236107,0.00036966876,0.0012357897,0.0015119086,0.002309062,0.0016323972,0.0012445605],"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":[0.0003084409,0.0001012649,0.002652313,0.00021177254,0.00009167631,0.0002255578,0.00026175595,0.7177061,0.012206394,0.13771605,0.011383359,0.11713544],"study_design_scores_gemma":[0.00001635546,0.000035520185,0.00012367922,0.000013952246,0.0000056546032,0.000027266651,0.000008307061,0.9811126,0.00087092054,0.015896425,0.001882721,0.00000651232],"about_ca_topic_score_codex":0.0017129797,"about_ca_topic_score_gemma":0.0016672291,"teacher_disagreement_score":0.0052347356,"about_ca_system_score_codex":0.0005597365,"about_ca_system_score_gemma":0.001045595,"threshold_uncertainty_score":0.017511964},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0188351,0.012400749,0.9358034,0.016040633,0.0018980602,0.00006676114,0.00014227579,0.0019173376,0.012895759],"genre_scores_gemma":[0.50512683,0.00843999,0.46124014,0.0052997977,0.0025549093,0.00021605259,0.00037833527,0.0022490923,0.014494847],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99582267,0.002089638,0.00029015914,0.0006570551,0.0008919717,0.00024848586],"domain_scores_gemma":[0.97577286,0.018073011,0.0006119612,0.0027362714,0.002257371,0.00054855266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011908798,0.0016047086,0.0027213283,0.0010881828,0.0010508246,0.0027580224,0.0027766584,0.0048057283,0.00663754],"category_scores_gemma":[0.07838089,0.00084111776,0.0011833193,0.0011005454,0.0025853785,0.011378566,0.0026528651,0.0058195186,0.0019709554],"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":[0.0011994102,0.00039184376,0.004124762,0.0008264009,0.000658955,0.00018447833,0.0003330613,0.15446049,0.0020688504,0.26727167,0.031952113,0.53652793],"study_design_scores_gemma":[0.000083388964,0.00008952629,0.00075833424,0.00028932988,0.00014364692,0.00008124283,0.00009643961,0.84000385,0.0015785679,0.15131561,0.0054854685,0.000074491065],"about_ca_topic_score_codex":0.0067637553,"about_ca_topic_score_gemma":0.006251047,"teacher_disagreement_score":0.011908798,"about_ca_system_score_codex":0.0011905517,"about_ca_system_score_gemma":0.0028740854,"threshold_uncertainty_score":0.06298053},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014793499,0.00032477503,0.98037714,0.0001995151,0.00011785725,0.000069295405,0.00004554526,0.0023829183,0.00168944],"genre_scores_gemma":[0.32961732,0.00015894792,0.66364473,0.0003431174,0.000096452946,0.00027173446,0.00024937245,0.0011042852,0.0045140227],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992182,0.00034893103,0.00007064277,0.00014739485,0.0001589523,0.000055930162],"domain_scores_gemma":[0.9986333,0.0005781172,0.00012251399,0.00020785313,0.00037529098,0.000082974235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002532142,0.0013818567,0.0016240097,0.0006044953,0.00038600582,0.00093712437,0.0013121689,0.0016359563,0.002124379],"category_scores_gemma":[0.0050789574,0.00066084793,0.0008359641,0.00058340415,0.00078772905,0.00084766635,0.0010379609,0.0020570867,0.0010053646],"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":[0.000264662,0.0001234962,0.0014593712,0.00017642132,0.00017997796,0.00019973585,0.000086655404,0.81224084,0.0084390985,0.014859708,0.007930126,0.15403998],"study_design_scores_gemma":[0.000008783839,0.000017478114,0.000056909153,0.0000050500594,0.000004497617,0.000011786235,0.0000017388411,0.9974886,0.0011738964,0.00065325026,0.0005731824,0.0000048641596],"about_ca_topic_score_codex":0.0030737196,"about_ca_topic_score_gemma":0.002928327,"teacher_disagreement_score":0.0030737196,"about_ca_system_score_codex":0.0007361735,"about_ca_system_score_gemma":0.0013764611,"threshold_uncertainty_score":0.013391376},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24053842,0.0006035085,0.7542818,0.000269479,0.000056128345,0.00006545268,0.000052937503,0.0008228609,0.0033093896],"genre_scores_gemma":[0.88559,0.00022137901,0.11157488,0.000066445755,0.00001532704,0.00008520875,0.000046548095,0.0001423808,0.0022578351],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990029,0.00025938783,0.00004201658,0.00012715043,0.00039066272,0.00017791934],"domain_scores_gemma":[0.99500495,0.002827411,0.000519126,0.0010216272,0.00045861187,0.00016835274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011745711,0.0005105357,0.0005081977,0.00058451615,0.0006026999,0.0008435899,0.00094562984,0.00061226217,0.0012136757],"category_scores_gemma":[0.0068198587,0.0004150993,0.00028305664,0.000875864,0.0016561814,0.0016148516,0.0009834644,0.0010968675,0.0003780563],"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":[0.00088132004,0.00014951716,0.0026440069,0.00022386097,0.00004176946,0.00026849794,0.00050522626,0.80129915,0.037260998,0.08552867,0.001187848,0.070009105],"study_design_scores_gemma":[0.000016907648,0.00009776204,0.00026253253,0.000013296301,0.0000068760537,0.000036808324,0.000029794928,0.9678209,0.011992961,0.018678604,0.0010309194,0.000012557822],"about_ca_topic_score_codex":0.0029614796,"about_ca_topic_score_gemma":0.004089507,"teacher_disagreement_score":0.0029614796,"about_ca_system_score_codex":0.0011816995,"about_ca_system_score_gemma":0.0019528312,"threshold_uncertainty_score":0.008573949},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019271014,0.00022628212,0.97132945,0.0002041236,0.00008446897,0.000082594204,0.00010379106,0.0008798445,0.007818501],"genre_scores_gemma":[0.54784673,0.00026242476,0.4401054,0.0002432916,0.000060708677,0.00024244272,0.00022778437,0.00019951089,0.010811674],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994286,0.00011075046,0.00002475708,0.00008509147,0.00023877881,0.00011201439],"domain_scores_gemma":[0.9985695,0.0004306755,0.00009314607,0.00048613382,0.00033737347,0.00008324775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060224993,0.0004761901,0.0004784147,0.0005148587,0.0006090094,0.0009260848,0.0012284495,0.0005392349,0.0052540894],"category_scores_gemma":[0.00319967,0.0002570905,0.00043192846,0.0006711787,0.00096339773,0.0013055346,0.001373813,0.0010038562,0.0008571776],"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":[0.000341881,0.000092436174,0.0010834794,0.0002484774,0.0000521892,0.00015464035,0.0002806733,0.5270504,0.021578798,0.2674585,0.012003425,0.16965514],"study_design_scores_gemma":[0.000017911345,0.00003653468,0.0001175062,0.000012442492,0.00000801054,0.00002763593,0.00001731873,0.96599466,0.004365256,0.025467508,0.0039237957,0.00001143679],"about_ca_topic_score_codex":0.005159386,"about_ca_topic_score_gemma":0.007502485,"teacher_disagreement_score":0.0052540894,"about_ca_system_score_codex":0.0013255986,"about_ca_system_score_gemma":0.0021584488,"threshold_uncertainty_score":0.017576694},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016737225,0.00043539723,0.99443793,0.00032491877,0.00027548528,0.00009624624,0.000094307296,0.0009448915,0.0017170483],"genre_scores_gemma":[0.055356514,0.0005364076,0.92551816,0.0005601414,0.00043531094,0.00088514516,0.00052221026,0.0008162863,0.015369838],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872833,0.00049573893,0.00013858246,0.00024224201,0.0002993615,0.00009577271],"domain_scores_gemma":[0.9970618,0.001606386,0.00014493773,0.0005168213,0.0005632412,0.00010680915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037562896,0.0023288159,0.0022624107,0.0007784687,0.0010860354,0.0014467941,0.0043435,0.003346932,0.012645615],"category_scores_gemma":[0.010111914,0.0017530142,0.0010855823,0.0012793137,0.0013281803,0.0028736524,0.0020185,0.004835395,0.008870814],"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":[0.0010630644,0.0005412856,0.000641337,0.0007410176,0.00038859385,0.0002357856,0.00025081873,0.37090048,0.011547943,0.14058843,0.046831053,0.42627013],"study_design_scores_gemma":[0.0000868011,0.00006241034,0.00013014802,0.000025212834,0.00003572274,0.000054902084,0.000010662273,0.9737241,0.0037049265,0.017322555,0.0048075346,0.00003505754],"about_ca_topic_score_codex":0.0053135785,"about_ca_topic_score_gemma":0.009187593,"teacher_disagreement_score":0.012645615,"about_ca_system_score_codex":0.00091213384,"about_ca_system_score_gemma":0.0026134977,"threshold_uncertainty_score":0.04230374},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012448371,0.00227364,0.962255,0.0017794512,0.00037428917,0.00006976939,0.00008006656,0.00030962503,0.020409822],"genre_scores_gemma":[0.7958474,0.0057503087,0.17450094,0.0010378542,0.0010927992,0.0003020874,0.00030978018,0.00009245893,0.021066276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99910456,0.00019067577,0.00005013455,0.0002704836,0.00024991203,0.00013428643],"domain_scores_gemma":[0.99946433,0.00020750874,0.000044907738,0.00010706275,0.00013476094,0.000041459418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009774803,0.00045956497,0.0006402401,0.000646682,0.000816099,0.0015934849,0.0011800167,0.0011811164,0.0022809631],"category_scores_gemma":[0.0019940578,0.00021621809,0.0008816011,0.0007038353,0.0011246095,0.0023229183,0.001798994,0.0014989311,0.00051370426],"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":[0.00012463846,0.0000832889,0.0023842107,0.00033280882,0.00009937678,0.00041892647,0.00027294704,0.088772595,0.0046937084,0.69919384,0.0079408465,0.19568288],"study_design_scores_gemma":[0.000019667104,0.000075947595,0.00043354582,0.000045176894,0.00002889375,0.00025030616,0.000045640605,0.7548771,0.00230569,0.22712961,0.014762918,0.00002550993],"about_ca_topic_score_codex":0.00094199425,"about_ca_topic_score_gemma":0.00047868083,"teacher_disagreement_score":0.0022809631,"about_ca_system_score_codex":0.00085148605,"about_ca_system_score_gemma":0.0010909479,"threshold_uncertainty_score":0.007630527},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003946965,0.00041036107,0.9937571,0.00020697812,0.00004283264,0.00003170019,0.00003941704,0.00020171815,0.00136282],"genre_scores_gemma":[0.3432059,0.0010252952,0.64494807,0.0005405983,0.00018077527,0.00042829494,0.00065592426,0.00050307,0.008512152],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924624,0.00031906052,0.00003118412,0.00012843721,0.00020587076,0.000069237736],"domain_scores_gemma":[0.99879766,0.0006911412,0.00012224853,0.000089975525,0.00022571703,0.0000731613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013736861,0.0016495977,0.001542335,0.0005421338,0.0004383829,0.0009066197,0.0012920512,0.0014015556,0.0018937546],"category_scores_gemma":[0.0037318214,0.0007623142,0.0012129678,0.00062353926,0.0011846968,0.0011372388,0.001356108,0.0021177267,0.00075285975],"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":[0.000046311554,0.00004036,0.0004834513,0.00015175318,0.00007267822,0.00009201048,0.000042889555,0.9478576,0.001494524,0.023577215,0.003161846,0.022979353],"study_design_scores_gemma":[0.0000031231543,0.000008384971,0.000028280287,0.0000038132941,0.0000020599093,0.000006642351,0.0000019582635,0.9963439,0.0001274637,0.0031100132,0.00036200802,0.0000023357798],"about_ca_topic_score_codex":0.0065977615,"about_ca_topic_score_gemma":0.008562855,"teacher_disagreement_score":0.0065977615,"about_ca_system_score_codex":0.0012075641,"about_ca_system_score_gemma":0.001890871,"threshold_uncertainty_score":0.013118684},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016245106,0.0012370707,0.9770006,0.00057134585,0.0002006639,0.0001597687,0.000080640246,0.0016169247,0.0028879456],"genre_scores_gemma":[0.44017905,0.00086097035,0.54738754,0.0009196844,0.00035557966,0.00091012596,0.0006457423,0.00084378035,0.007897537],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99696213,0.0013485884,0.0001338645,0.0005552298,0.0006749325,0.00032522852],"domain_scores_gemma":[0.9893171,0.006006966,0.00058145437,0.0014691806,0.0020307277,0.0005945213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054536806,0.0017530207,0.0026423074,0.0008288192,0.0009885799,0.0016639599,0.003188666,0.0022000389,0.0047421106],"category_scores_gemma":[0.028185954,0.0010849015,0.0012619057,0.0007009449,0.002426285,0.0028621545,0.0025071586,0.0042329296,0.002270566],"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":[0.0009242722,0.00031183643,0.002640695,0.00040829155,0.00012554329,0.00018181645,0.00022144592,0.75399834,0.0040264274,0.09644638,0.016344333,0.124370664],"study_design_scores_gemma":[0.000038355684,0.00008082489,0.00014619678,0.000020544634,0.000011318115,0.000027706827,0.000008671564,0.9857318,0.0010927492,0.011804764,0.0010266359,0.0000103799075],"about_ca_topic_score_codex":0.0033657504,"about_ca_topic_score_gemma":0.0035554152,"teacher_disagreement_score":0.0054536806,"about_ca_system_score_codex":0.001887856,"about_ca_system_score_gemma":0.003208227,"threshold_uncertainty_score":0.028842151},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004599798,0.00016876716,0.9919892,0.00038861614,0.000101245845,0.000032805612,0.000014122495,0.00089418585,0.0018113654],"genre_scores_gemma":[0.23669319,0.00034884844,0.75167215,0.00056650373,0.00023551266,0.00023467954,0.00014756009,0.00057197444,0.009529571],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987828,0.00035356806,0.000042062533,0.00023210722,0.00044238512,0.00014699688],"domain_scores_gemma":[0.9984781,0.0005867955,0.00012952182,0.00038308473,0.00025725443,0.00016533233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018162237,0.0013215774,0.0011507531,0.00030627928,0.0009356523,0.0011944097,0.002540033,0.0014039422,0.004492874],"category_scores_gemma":[0.004944245,0.0006554533,0.00061132543,0.0006041888,0.0013101983,0.002040142,0.0021494883,0.0022493994,0.0017733291],"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":[0.0009217019,0.00025667445,0.0016716259,0.00027653284,0.00019168669,0.00034880202,0.0005864569,0.55590147,0.01805611,0.06391136,0.01628314,0.3415945],"study_design_scores_gemma":[0.00007610363,0.00008256025,0.00012675201,0.000012651851,0.00002155739,0.00004052409,0.00005233335,0.97193897,0.0032605398,0.018759288,0.005614943,0.000013806705],"about_ca_topic_score_codex":0.0040105637,"about_ca_topic_score_gemma":0.006841982,"teacher_disagreement_score":0.004492874,"about_ca_system_score_codex":0.00074978115,"about_ca_system_score_gemma":0.0029604028,"threshold_uncertainty_score":0.015030205},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015256425,0.000063422776,0.99693394,0.00013786528,0.000021841992,0.000017270877,0.000021710868,0.0001868987,0.0010913475],"genre_scores_gemma":[0.20624392,0.00028119682,0.7820092,0.00036074172,0.00011756017,0.00044401363,0.00018522999,0.00058566337,0.009772485],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99950564,0.00019235734,0.000019799165,0.00008117711,0.00016627117,0.000034805533],"domain_scores_gemma":[0.9989153,0.00074041256,0.00006729219,0.000084089654,0.00014516951,0.00004781233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014503981,0.0009229489,0.0009681083,0.0003809315,0.00039728638,0.0010033676,0.0015032192,0.0014231278,0.0048761046],"category_scores_gemma":[0.0037827292,0.0010811471,0.0005469181,0.0005608174,0.001183353,0.0014148395,0.0020713087,0.0028338283,0.0009597789],"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":[0.000066949025,0.000057181536,0.0001845737,0.00013412126,0.000039661107,0.000027951444,0.00004516065,0.85331416,0.001639038,0.069175646,0.0039352425,0.07138035],"study_design_scores_gemma":[0.0000037442696,0.000005984513,0.0000090412495,0.0000037618006,0.0000015583049,0.000003683279,0.000001097775,0.99273586,0.00020962769,0.0067884047,0.00023590031,0.0000013214257],"about_ca_topic_score_codex":0.001873661,"about_ca_topic_score_gemma":0.003124789,"teacher_disagreement_score":0.0048761046,"about_ca_system_score_codex":0.00080688205,"about_ca_system_score_gemma":0.0014620022,"threshold_uncertainty_score":0.016312182},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2667659,0.0033647479,0.7090677,0.0016941143,0.0005155245,0.00009544678,0.0005342307,0.0031593256,0.014803032],"genre_scores_gemma":[0.88614786,0.0012422474,0.09972044,0.00038598222,0.00018384447,0.00015831238,0.0005341413,0.0034098434,0.008217331],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840814,0.00045310459,0.00011454229,0.00043046635,0.0003397458,0.00025405557],"domain_scores_gemma":[0.96511304,0.027006408,0.0014655374,0.0020949824,0.0028689876,0.001451037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053158044,0.0010168847,0.0014517296,0.0012797865,0.00070342456,0.0025268137,0.0019890082,0.002389651,0.005447706],"category_scores_gemma":[0.05735023,0.0009138711,0.0007234204,0.00083479745,0.0013443391,0.004070258,0.0021306602,0.0034918531,0.0018302875],"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":[0.0027234529,0.00043684238,0.010882358,0.00089194695,0.00032799615,0.00055715966,0.0007517507,0.64394367,0.09149129,0.07377293,0.013526715,0.16069382],"study_design_scores_gemma":[0.000037204692,0.00018040299,0.0021865454,0.000080955666,0.000055636512,0.00015845771,0.0000747325,0.95700824,0.014461255,0.024731798,0.0009815915,0.00004316388],"about_ca_topic_score_codex":0.0009720807,"about_ca_topic_score_gemma":0.0011221643,"teacher_disagreement_score":0.005447706,"about_ca_system_score_codex":0.000811473,"about_ca_system_score_gemma":0.0012174185,"threshold_uncertainty_score":0.028113008},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031757029,0.000102973514,0.99556595,0.00008814288,0.0000214376,0.000029647348,0.000017897546,0.00021744326,0.00078074133],"genre_scores_gemma":[0.16107416,0.0002102097,0.832938,0.00028408488,0.00007121479,0.00033832926,0.00020231407,0.00041371153,0.004467866],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99920803,0.0003389903,0.000035255583,0.00011184899,0.00025020476,0.00005567489],"domain_scores_gemma":[0.9981914,0.0010271274,0.00016006152,0.00019629522,0.00033428188,0.000090902555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023472467,0.0011246904,0.0011370183,0.00092878344,0.0005150403,0.0011259607,0.0012032029,0.0016044887,0.0031776633],"category_scores_gemma":[0.0066345576,0.0006224446,0.0008605046,0.000706848,0.0011029998,0.0012705353,0.0013382062,0.0017597801,0.0011641968],"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":[0.00017049086,0.000117561816,0.00086342945,0.00016032686,0.00007200995,0.00014582134,0.0001680783,0.7917305,0.008617181,0.104940414,0.004020668,0.08899349],"study_design_scores_gemma":[0.0000055603473,0.000028501343,0.000032606316,0.0000060951165,0.0000029776986,0.000013893055,0.0000034529094,0.9945169,0.00057220337,0.0040541156,0.0007593222,0.000004492757],"about_ca_topic_score_codex":0.0036325937,"about_ca_topic_score_gemma":0.0041814735,"teacher_disagreement_score":0.0036325937,"about_ca_system_score_codex":0.0010997499,"about_ca_system_score_gemma":0.001563837,"threshold_uncertainty_score":0.012413561},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16826777,0.00089843315,0.81861037,0.0017170069,0.000044673972,0.000043504013,0.0003345848,0.00041450246,0.009669122],"genre_scores_gemma":[0.94177043,0.0007982405,0.0493428,0.00019391142,0.00007088694,0.00010904824,0.00039973986,0.0002722959,0.0070427894],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99939275,0.00022057613,0.000028687631,0.0001058567,0.00016876792,0.00008331584],"domain_scores_gemma":[0.99745804,0.0014995802,0.00029603572,0.00019338971,0.00037840585,0.00017454219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014045327,0.001149004,0.0008802221,0.0010076531,0.0005470993,0.001445691,0.001097055,0.0011383601,0.0019377475],"category_scores_gemma":[0.008271109,0.00063306506,0.00080164423,0.0005787125,0.0018137065,0.002145841,0.0017747486,0.002219149,0.00036500758],"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":[0.000118797514,0.000031654865,0.0013562861,0.0001546337,0.000054287793,0.0003024043,0.00015219844,0.80414647,0.007761147,0.17046368,0.0017101063,0.013748423],"study_design_scores_gemma":[0.000003961006,0.000032575157,0.00037454965,0.0000113108335,0.000004756345,0.0000440014,0.000020345506,0.9553085,0.001017256,0.04267114,0.0005045519,0.0000069740536],"about_ca_topic_score_codex":0.0026212963,"about_ca_topic_score_gemma":0.0010654309,"teacher_disagreement_score":0.0026212963,"about_ca_system_score_codex":0.0014434109,"about_ca_system_score_gemma":0.0005948747,"threshold_uncertainty_score":0.0104727745},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021142414,0.00063898385,0.956246,0.0014493036,0.0005018499,0.00007174303,0.00037946596,0.004338693,0.015231436],"genre_scores_gemma":[0.64527094,0.001089375,0.24336484,0.001537991,0.00052623544,0.00030569415,0.001539021,0.0016760548,0.104689814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994954,0.000073532334,0.000027920214,0.00015543163,0.00017058816,0.00007716888],"domain_scores_gemma":[0.99816626,0.0007718101,0.00015482503,0.0005870465,0.00022522999,0.000094907824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073282665,0.0010705579,0.0009186123,0.00033675245,0.00036435446,0.0014298578,0.002057171,0.0018088064,0.014437026],"category_scores_gemma":[0.0054470478,0.0008534127,0.0006062932,0.00040430817,0.0010723583,0.004821208,0.0020633228,0.0032220553,0.0046974714],"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":[0.0003556748,0.00020685398,0.0012624903,0.00035943146,0.0001510102,0.00019734324,0.00009012846,0.16998479,0.013618818,0.11170368,0.031570237,0.6704995],"study_design_scores_gemma":[0.000040156363,0.00011397221,0.00037830538,0.000037579313,0.00004631495,0.00014581037,0.000018537425,0.8768574,0.010726465,0.10233305,0.009278419,0.000023985616],"about_ca_topic_score_codex":0.0019594044,"about_ca_topic_score_gemma":0.004396847,"teacher_disagreement_score":0.014437026,"about_ca_system_score_codex":0.0007121141,"about_ca_system_score_gemma":0.0010665949,"threshold_uncertainty_score":0.04829663},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028470694,0.00022803897,0.99392647,0.00010064137,0.0001333841,0.000024863162,0.00004563616,0.00043956458,0.0022543117],"genre_scores_gemma":[0.08964574,0.00041250393,0.8918499,0.00018251638,0.0001921227,0.00023686729,0.00019331403,0.00086129864,0.016425818],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997563,0.000075915974,0.000010649845,0.000027468317,0.00011411835,0.000015525815],"domain_scores_gemma":[0.99954766,0.00020637069,0.00002992543,0.000045475044,0.000119163655,0.000051398147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005715518,0.0009087312,0.0009650196,0.00048772228,0.00039828368,0.0007575553,0.0012403068,0.0012488426,0.0039761527],"category_scores_gemma":[0.0015670969,0.00040918987,0.0008260963,0.0004536192,0.0008204737,0.0007625152,0.0014645262,0.002013443,0.0015630121],"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":[0.0002801785,0.00012874605,0.00036831017,0.00040416679,0.00013160713,0.00012693535,0.00015404681,0.5144657,0.023922233,0.21196638,0.014646397,0.23340523],"study_design_scores_gemma":[0.000010240764,0.000022965329,0.000031822536,0.000007649501,0.000005313714,0.000015849666,0.0000030317458,0.9853873,0.0009798311,0.010197138,0.0033311318,0.000007784204],"about_ca_topic_score_codex":0.002277622,"about_ca_topic_score_gemma":0.0030211764,"teacher_disagreement_score":0.0039761527,"about_ca_system_score_codex":0.00053375185,"about_ca_system_score_gemma":0.000982153,"threshold_uncertainty_score":0.013301611},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025389558,0.00050535414,0.99378467,0.0002239532,0.000054092114,0.000040134604,0.000036934263,0.00008723454,0.0027286196],"genre_scores_gemma":[0.2905334,0.0023353458,0.69448775,0.00042115655,0.00031560604,0.00076476706,0.00037602696,0.00030465826,0.010461224],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991442,0.00043518812,0.00004249331,0.00014694747,0.00016259629,0.00006850428],"domain_scores_gemma":[0.9949426,0.0041113244,0.00026560327,0.00012407612,0.00043553658,0.000120845165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002663217,0.0018078533,0.0016299846,0.0010706706,0.0005930382,0.0016584228,0.0017314911,0.0018697005,0.0060505127],"category_scores_gemma":[0.008458571,0.0009219759,0.0015521263,0.0010500011,0.0011391671,0.0014144428,0.0019902352,0.00300478,0.0008408389],"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":[0.000023955716,0.0000276117,0.00029915175,0.00014852807,0.000045146386,0.000022663304,0.00004808224,0.9519051,0.00029341574,0.02377562,0.00070082286,0.022709925],"study_design_scores_gemma":[0.0000061757773,0.000013097083,0.000027633658,0.000018815246,0.000004657535,0.0000059357044,0.000007641377,0.989507,0.00007644472,0.009610654,0.00071875064,0.000003291763],"about_ca_topic_score_codex":0.0058395783,"about_ca_topic_score_gemma":0.0065187,"teacher_disagreement_score":0.0060505127,"about_ca_system_score_codex":0.0016817863,"about_ca_system_score_gemma":0.002332359,"threshold_uncertainty_score":0.020241022},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11208011,0.00085845724,0.880941,0.001957245,0.00007577458,0.000082005965,0.00022451996,0.0006838796,0.0030970653],"genre_scores_gemma":[0.79328567,0.0009020168,0.20126234,0.00071075384,0.00011251937,0.00027104502,0.00067266834,0.0004082123,0.0023748009],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99635774,0.0015415067,0.00020344698,0.0005765392,0.0010618888,0.00025885433],"domain_scores_gemma":[0.9169861,0.06922019,0.0030603928,0.0074909055,0.0025673837,0.0006750702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008548804,0.0010046933,0.000925941,0.0004120388,0.00060283084,0.0012212377,0.0015265297,0.0016474231,0.00133223],"category_scores_gemma":[0.08505521,0.0009143005,0.0005921673,0.0005557993,0.0026347833,0.0039932528,0.0033859466,0.0034514107,0.0003209561],"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":[0.0006389929,0.00017297207,0.009260948,0.00054137426,0.00016192016,0.00040315784,0.0003497272,0.7641533,0.024876524,0.06880988,0.0026081798,0.12802307],"study_design_scores_gemma":[0.000013193532,0.00006554594,0.0007663107,0.000028111166,0.000011067429,0.000062447696,0.00001269778,0.9809396,0.0059189624,0.011746098,0.0004230713,0.00001282278],"about_ca_topic_score_codex":0.0039217803,"about_ca_topic_score_gemma":0.005316987,"teacher_disagreement_score":0.008548804,"about_ca_system_score_codex":0.0013365378,"about_ca_system_score_gemma":0.0013679243,"threshold_uncertainty_score":0.045210958},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019616015,0.00053932774,0.9753568,0.000815715,0.000041051262,0.000051902418,0.00011467263,0.0002889346,0.0031755844],"genre_scores_gemma":[0.74317306,0.00092565035,0.24769752,0.0008727995,0.00018562048,0.00035376777,0.00050020736,0.000274463,0.006016949],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980411,0.0007848373,0.00008041126,0.0002984457,0.0006085018,0.00018666711],"domain_scores_gemma":[0.99596775,0.0022289136,0.00047956948,0.00047201963,0.0006656385,0.00018618164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00424791,0.0012996737,0.0012195035,0.0007951826,0.00067220256,0.0017467504,0.0025989916,0.0021517088,0.0030736977],"category_scores_gemma":[0.016302967,0.00082099106,0.00064975925,0.000981653,0.0018923456,0.003794279,0.0035429986,0.0044614407,0.00058975973],"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":[0.00032663494,0.00011859502,0.0011877357,0.00021088161,0.000085923915,0.00011138039,0.00018687994,0.6680196,0.004089878,0.23564899,0.004994253,0.08501925],"study_design_scores_gemma":[0.000009420542,0.000029300423,0.00016194407,0.000019669178,0.000008107302,0.000018663117,0.000008293595,0.9377273,0.0007672302,0.060656395,0.00058671273,0.0000069458547],"about_ca_topic_score_codex":0.0025904002,"about_ca_topic_score_gemma":0.0029509529,"teacher_disagreement_score":0.00424791,"about_ca_system_score_codex":0.0019808486,"about_ca_system_score_gemma":0.0016373777,"threshold_uncertainty_score":0.022465348},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005639257,0.00016971283,0.99217105,0.00034626614,0.000033633904,0.00002025688,0.000021839085,0.00025872418,0.0013392231],"genre_scores_gemma":[0.6308635,0.0006431665,0.36094895,0.0006070621,0.00030526074,0.000315937,0.00021452656,0.00053691596,0.0055647385],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874,0.0005487522,0.00006855099,0.00018328198,0.00036454166,0.00009485413],"domain_scores_gemma":[0.9970721,0.0018620482,0.0002573829,0.00037749796,0.00030687999,0.00012416644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031780303,0.0014717375,0.0013080675,0.0008735708,0.0004617348,0.0017043264,0.0015624595,0.0016891806,0.0014363205],"category_scores_gemma":[0.010865147,0.00078390515,0.0007494043,0.0006600193,0.0017538137,0.0024176536,0.0025193393,0.0031983047,0.00039455885],"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":[0.0000463813,0.000033347995,0.000663777,0.0000584411,0.00005538508,0.00008270679,0.00006135975,0.8983735,0.0023239127,0.07038935,0.001771673,0.026140204],"study_design_scores_gemma":[0.0000039901574,0.0000102115,0.000045187357,0.000004706022,0.0000026036703,0.0000117912,0.0000019327774,0.9833619,0.000290232,0.01594452,0.00031924972,0.000003705082],"about_ca_topic_score_codex":0.0018630951,"about_ca_topic_score_gemma":0.0024354209,"teacher_disagreement_score":0.0031780303,"about_ca_system_score_codex":0.0015956797,"about_ca_system_score_gemma":0.0013969404,"threshold_uncertainty_score":0.016807258},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009958617,0.0001273836,0.99814105,0.000098065415,0.00003201417,0.000018111066,0.0000063654143,0.00006781072,0.0005133397],"genre_scores_gemma":[0.27789834,0.00060108735,0.7147542,0.00036852562,0.00028392044,0.00039817925,0.00010012641,0.00024802482,0.005347602],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990727,0.00035680606,0.000034159217,0.0001516472,0.0003236325,0.000061135004],"domain_scores_gemma":[0.9982285,0.001191788,0.00010594686,0.00012863842,0.00025734003,0.00008776848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002234692,0.0011759385,0.0015203159,0.0007811267,0.0004788148,0.0010754311,0.0017922821,0.0017899573,0.0024422284],"category_scores_gemma":[0.006425536,0.00069133326,0.00095784815,0.00082742964,0.0016509655,0.0014676935,0.0015744322,0.0023921395,0.00044804666],"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":[0.000070038615,0.00006846048,0.00035283298,0.00016945458,0.000052453295,0.00008256895,0.000059667043,0.86535496,0.0025155093,0.06078812,0.0021050675,0.06838094],"study_design_scores_gemma":[0.0000059589893,0.000015694755,0.000022544993,0.000005631279,0.0000024539256,0.000009313132,0.0000013085494,0.99481165,0.00025474606,0.0044874917,0.0003793843,0.0000038816506],"about_ca_topic_score_codex":0.0029258847,"about_ca_topic_score_gemma":0.001972513,"teacher_disagreement_score":0.0029258847,"about_ca_system_score_codex":0.000981883,"about_ca_system_score_gemma":0.0014197992,"threshold_uncertainty_score":0.011818349},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01343232,0.00028676362,0.9837527,0.00025316048,0.000052134015,0.000024980467,0.000041008905,0.001320411,0.00083652977],"genre_scores_gemma":[0.4847686,0.00063737534,0.5062945,0.00038856882,0.00020120216,0.00024864147,0.00043612227,0.0015976419,0.005427306],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820113,0.00055571785,0.00013534875,0.00030273764,0.00066367653,0.00014148543],"domain_scores_gemma":[0.9955687,0.0025248742,0.00034591963,0.0008444725,0.00059143454,0.00012459226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029046931,0.0015589277,0.0017447626,0.0007883504,0.00060701394,0.0015540516,0.0017420265,0.0018557266,0.0021764382],"category_scores_gemma":[0.014941652,0.0011689182,0.000983464,0.0008027373,0.0016792198,0.0030874072,0.0022289145,0.0029344468,0.00116799],"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":[0.00025850005,0.0001112723,0.0013795902,0.00021374685,0.000104878636,0.00016359183,0.0001357883,0.84726715,0.010671989,0.026793608,0.0029830511,0.109916836],"study_design_scores_gemma":[0.000009710121,0.000026669251,0.00008630198,0.000007578343,0.0000070437986,0.00002039472,0.0000038808994,0.99026346,0.0020396686,0.007044206,0.0004850227,0.0000059461427],"about_ca_topic_score_codex":0.0034505283,"about_ca_topic_score_gemma":0.004094839,"teacher_disagreement_score":0.0034505283,"about_ca_system_score_codex":0.00097147527,"about_ca_system_score_gemma":0.001929988,"threshold_uncertainty_score":0.015361667},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028245337,0.00023109438,0.9679403,0.00046002632,0.000052512587,0.00007199846,0.00006222539,0.00017720362,0.0027593367],"genre_scores_gemma":[0.8221256,0.00021368547,0.17143446,0.00033203425,0.00006417293,0.00032431333,0.00013729985,0.00013480098,0.0052335775],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980192,0.0011000328,0.00006377692,0.00039659272,0.00023758272,0.00018279304],"domain_scores_gemma":[0.9935615,0.004896297,0.0004968276,0.00055985205,0.00031794628,0.00016762695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026168071,0.001029032,0.0013679952,0.00041449096,0.00047527338,0.0010451698,0.0016742382,0.0013638844,0.002499444],"category_scores_gemma":[0.009320728,0.0005508714,0.00064619654,0.0006038993,0.0016631134,0.0016265714,0.0016338316,0.0019222229,0.00042606404],"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":[0.00016359985,0.00005125276,0.00026596466,0.000066336244,0.0000473467,0.00007254135,0.000038889328,0.94793314,0.0015368462,0.0406042,0.0009429496,0.008276949],"study_design_scores_gemma":[0.000018002203,0.000021729551,0.000034311593,0.0000033539511,0.0000043846726,0.000013292882,0.0000051632246,0.9882923,0.0002676876,0.011089277,0.00024676582,0.0000037148477],"about_ca_topic_score_codex":0.0012026695,"about_ca_topic_score_gemma":0.001008987,"teacher_disagreement_score":0.0026168071,"about_ca_system_score_codex":0.0013840873,"about_ca_system_score_gemma":0.00122099,"threshold_uncertainty_score":0.013839185},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004899532,0.00019244873,0.99138135,0.00049138063,0.00011072552,0.0000330779,0.000017628663,0.00091612426,0.0019577767],"genre_scores_gemma":[0.25183845,0.00036560462,0.73534083,0.00067980436,0.0002758181,0.00024969783,0.00017520082,0.00065039715,0.010424164],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856347,0.00045192882,0.00004970229,0.00029262764,0.0004758766,0.00016627643],"domain_scores_gemma":[0.99822813,0.0007106285,0.000148876,0.00044723417,0.0002811211,0.00018405961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020347985,0.0014125124,0.001230148,0.0003372049,0.0009682628,0.0013142375,0.0026232193,0.0015796272,0.0047189537],"category_scores_gemma":[0.0059254463,0.0007167704,0.0006312281,0.0006719637,0.0014320544,0.0022191384,0.0023525066,0.0025386491,0.0019667223],"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":[0.0010094454,0.00027529238,0.0018025325,0.0002961904,0.00020429003,0.0003795334,0.000630762,0.56786406,0.016426582,0.074413314,0.018924972,0.31777307],"study_design_scores_gemma":[0.00007562286,0.00007867697,0.00013021004,0.000013694307,0.000021792097,0.000041301875,0.00005574538,0.96554106,0.0029091844,0.02574982,0.0053688707,0.000014096911],"about_ca_topic_score_codex":0.0039418703,"about_ca_topic_score_gemma":0.0066285008,"teacher_disagreement_score":0.0047189537,"about_ca_system_score_codex":0.0008137061,"about_ca_system_score_gemma":0.0030853194,"threshold_uncertainty_score":0.015786469},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012427345,0.014122839,0.9188094,0.038975414,0.004976706,0.00020148895,0.00034397497,0.0049424344,0.016385028],"genre_scores_gemma":[0.02063367,0.012410449,0.9357203,0.008787625,0.002500548,0.00078163226,0.0005722755,0.003253388,0.0153402435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9907064,0.0052346317,0.00079628255,0.0007807988,0.002244379,0.000237581],"domain_scores_gemma":[0.9697416,0.017670192,0.0009857827,0.0032516888,0.00747682,0.0008739908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011012247,0.0032321373,0.0015867423,0.0019868673,0.0012025475,0.0043438603,0.00428475,0.0076569784,0.023039658],"category_scores_gemma":[0.10607014,0.0019707023,0.0009111528,0.0021701853,0.00314244,0.011308171,0.0027617025,0.015671708,0.02142708],"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":[0.00021307569,0.00030204092,0.00069360546,0.0013016916,0.000097685435,0.00026763987,0.0003746291,0.04188014,0.003699231,0.22064638,0.36374646,0.3667774],"study_design_scores_gemma":[0.00034483723,0.00020578147,0.00046628495,0.0024631014,0.000057919493,0.00042049238,0.00030145494,0.12407185,0.005607204,0.5165094,0.34933785,0.00021375401],"about_ca_topic_score_codex":0.0022333646,"about_ca_topic_score_gemma":0.004232524,"teacher_disagreement_score":0.023039658,"about_ca_system_score_codex":0.0015960817,"about_ca_system_score_gemma":0.0022718366,"threshold_uncertainty_score":0.07707536},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03139538,0.0007308978,0.94844145,0.0005802448,0.0002498574,0.000120551165,0.00077800296,0.010157532,0.00754612],"genre_scores_gemma":[0.32665792,0.00039798656,0.66253406,0.00043133437,0.0000890281,0.00028222226,0.0016270799,0.0013517147,0.006628705],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99776566,0.0003941575,0.00013787612,0.0003413684,0.0010675864,0.0002932803],"domain_scores_gemma":[0.99751735,0.0007255562,0.000162183,0.00079450087,0.00067377114,0.00012668136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011381453,0.0007468036,0.0009793852,0.00075943244,0.0009568981,0.0021537172,0.0021367385,0.0009029438,0.0100181],"category_scores_gemma":[0.0064640865,0.00040612975,0.0006561983,0.0020518769,0.00086922076,0.0025800993,0.0017697621,0.0014463402,0.0020151907],"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":[0.0014603218,0.00020629694,0.0029779219,0.00051501935,0.00017268477,0.00010483864,0.00018505746,0.31914663,0.015691772,0.1336975,0.044254396,0.4815875],"study_design_scores_gemma":[0.00015367215,0.00011465124,0.00038463043,0.000022140537,0.000028705646,0.00007462839,0.000047220314,0.9022308,0.014206349,0.05978911,0.022915732,0.000032349013],"about_ca_topic_score_codex":0.009018272,"about_ca_topic_score_gemma":0.011744873,"teacher_disagreement_score":0.0100181,"about_ca_system_score_codex":0.0018739696,"about_ca_system_score_gemma":0.003831195,"threshold_uncertainty_score":0.033513904},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34846702,0.0010234026,0.63267845,0.0056747654,0.00022814846,0.0001058433,0.00036570668,0.00094168616,0.010515035],"genre_scores_gemma":[0.9304345,0.00033766762,0.066772945,0.00041658967,0.00008170747,0.00009389336,0.00017817573,0.00022934248,0.0014550618],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824166,0.00093544496,0.000057198908,0.0003207597,0.00030978286,0.00013510404],"domain_scores_gemma":[0.9854168,0.010893898,0.0010484271,0.001385922,0.0008034591,0.0004513929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052681817,0.00064475636,0.0007760079,0.0003547367,0.00055080606,0.0011075685,0.00097264117,0.0011994998,0.0029333404],"category_scores_gemma":[0.04291511,0.0005122601,0.00035293674,0.0003120078,0.001859949,0.0035043894,0.0010170261,0.0025716897,0.0004922314],"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":[0.0010528428,0.00040087922,0.008950504,0.0004984702,0.000101594225,0.0003301084,0.00056389667,0.74893326,0.01913864,0.16335936,0.012258992,0.044411443],"study_design_scores_gemma":[0.00006877107,0.00007977127,0.0011097966,0.000032315143,0.000013190401,0.000037187798,0.000055940774,0.92248887,0.0029654908,0.07234327,0.000786446,0.00001888184],"about_ca_topic_score_codex":0.0031706777,"about_ca_topic_score_gemma":0.0037989826,"teacher_disagreement_score":0.0052681817,"about_ca_system_score_codex":0.0007679434,"about_ca_system_score_gemma":0.0011433351,"threshold_uncertainty_score":0.027861178},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007528479,0.00018619353,0.990319,0.00024394236,0.000037201185,0.000035034544,0.0000211751,0.00041082347,0.0012181705],"genre_scores_gemma":[0.3266668,0.0003134601,0.66722685,0.00035301642,0.000077969664,0.00017351958,0.00016561746,0.00038010307,0.004642684],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992125,0.0003559495,0.000038591093,0.00014203458,0.00018014987,0.00007078898],"domain_scores_gemma":[0.9980379,0.0012117065,0.00014043454,0.00024284706,0.0003039444,0.0000631718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024350432,0.001066796,0.0011971052,0.00040432013,0.00033748455,0.00075457786,0.0014256054,0.0015683823,0.0030345109],"category_scores_gemma":[0.008626001,0.0005793168,0.00043192622,0.00043228414,0.0010634728,0.0012786387,0.0010583436,0.0017499736,0.0009639651],"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":[0.00022302507,0.0000819075,0.0007971236,0.0001498188,0.00006107706,0.00019065962,0.00013744319,0.792861,0.006773399,0.040795177,0.005463923,0.15246542],"study_design_scores_gemma":[0.000009002326,0.000023318813,0.000043637086,0.0000059849126,0.0000029395499,0.00001845564,0.0000051945085,0.99339503,0.0009294191,0.00478014,0.0007822517,0.0000046838068],"about_ca_topic_score_codex":0.0025474448,"about_ca_topic_score_gemma":0.0033994513,"teacher_disagreement_score":0.0030345109,"about_ca_system_score_codex":0.00047114203,"about_ca_system_score_gemma":0.0009549641,"threshold_uncertainty_score":0.0128778815},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006598272,0.00024123499,0.9885029,0.00031495065,0.00012930862,0.000038572536,0.00005386639,0.00021795614,0.003902921],"genre_scores_gemma":[0.51377,0.0008253975,0.46369886,0.00042048248,0.0007667493,0.00060806604,0.0004090648,0.0012060266,0.018295338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813664,0.000737492,0.00008270755,0.00021928374,0.0006580473,0.00016591663],"domain_scores_gemma":[0.99072874,0.006416524,0.00040272408,0.0006638803,0.0014701885,0.00031793723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042818706,0.0015440998,0.0015022325,0.00140596,0.00085761544,0.0016345428,0.0024658146,0.0013436646,0.00797466],"category_scores_gemma":[0.017548613,0.00071008474,0.0012609571,0.001276062,0.0017565957,0.002587605,0.0028306933,0.0031127098,0.00096111634],"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":[0.00025812388,0.00009488061,0.00074527424,0.00025033235,0.000083748935,0.00011388975,0.00012409344,0.7044545,0.0025004568,0.24363282,0.0046429234,0.04309906],"study_design_scores_gemma":[0.000007818179,0.000008108133,0.000041022224,0.000004325847,0.000005901167,0.000004819305,0.0000027795925,0.97668886,0.00019906365,0.022655847,0.00037829002,0.000003089277],"about_ca_topic_score_codex":0.005209118,"about_ca_topic_score_gemma":0.0065219826,"teacher_disagreement_score":0.00797466,"about_ca_system_score_codex":0.0017535408,"about_ca_system_score_gemma":0.0024759162,"threshold_uncertainty_score":0.026677907},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021821046,0.00008540294,0.9961487,0.00006866379,0.00002285038,0.000046953774,0.000041155407,0.0011075359,0.00029667775],"genre_scores_gemma":[0.11101814,0.00014667363,0.88484514,0.00023791139,0.00007353469,0.00042145388,0.00064488105,0.0005918771,0.002020347],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825615,0.000957105,0.00007897563,0.00032888752,0.00027578138,0.000103161714],"domain_scores_gemma":[0.995804,0.0030167557,0.00017687603,0.00041465915,0.00047771013,0.000110087596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038041852,0.001313615,0.0018564678,0.0013339962,0.0008419959,0.0009189178,0.0029575543,0.0020021982,0.0041617597],"category_scores_gemma":[0.010250367,0.001081025,0.001085919,0.0015519785,0.0011821041,0.0021363806,0.0012534305,0.0029924377,0.0018486363],"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":[0.0001760404,0.00013240006,0.0008559514,0.00013634715,0.000084582716,0.00008870154,0.00011655519,0.76493317,0.0027879963,0.027518451,0.0057445834,0.19742522],"study_design_scores_gemma":[0.000008611673,0.00001247165,0.000035660367,0.0000043736536,0.000002888235,0.0000094308,0.0000031502007,0.9936713,0.00038950442,0.0053207576,0.0005372839,0.0000045379247],"about_ca_topic_score_codex":0.00836732,"about_ca_topic_score_gemma":0.012131633,"teacher_disagreement_score":0.00836732,"about_ca_system_score_codex":0.001579491,"about_ca_system_score_gemma":0.002095805,"threshold_uncertainty_score":0.020118713},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00311008,0.0007009285,0.9919751,0.00051139476,0.000055475142,0.000023277333,0.00002584658,0.000059805803,0.0035378998],"genre_scores_gemma":[0.46227834,0.0026533804,0.52137023,0.00093989394,0.0007019045,0.00030239648,0.00019907557,0.00037592638,0.011178897],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976312,0.001039706,0.00008133036,0.00040328485,0.00067030016,0.00017415461],"domain_scores_gemma":[0.9930189,0.0049809124,0.00048580722,0.0007031032,0.00051006244,0.00030114758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005965238,0.0016160375,0.0010112764,0.0010293111,0.0005359085,0.0018536487,0.0022150876,0.0016707472,0.0038072316],"category_scores_gemma":[0.01883811,0.00068264664,0.0013292384,0.0009520498,0.0030811043,0.00507923,0.003715644,0.0060693906,0.0006824752],"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":[0.000055213837,0.00006299721,0.00059310213,0.00020745538,0.00010030576,0.00006185839,0.00015425055,0.17649247,0.0022977118,0.7758441,0.0035995636,0.04053097],"study_design_scores_gemma":[0.000010841509,0.0000584795,0.000244356,0.00003775735,0.000025531386,0.00004604147,0.00001624935,0.67084384,0.0010509354,0.32489067,0.0027585155,0.000016774851],"about_ca_topic_score_codex":0.0008968854,"about_ca_topic_score_gemma":0.00092679705,"teacher_disagreement_score":0.005965238,"about_ca_system_score_codex":0.0017381402,"about_ca_system_score_gemma":0.001460634,"threshold_uncertainty_score":0.031547546},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005550675,0.0028048353,0.97172946,0.0009241711,0.00039351787,0.000050876504,0.00008592614,0.00021455504,0.01824589],"genre_scores_gemma":[0.30768943,0.008777295,0.5827145,0.00090528035,0.0015151477,0.0008417721,0.00067212805,0.0015974446,0.09528704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980732,0.00090527034,0.000076128345,0.00026458502,0.0005246105,0.0001562319],"domain_scores_gemma":[0.99370307,0.004480813,0.00029145114,0.000333815,0.00089524995,0.00029569576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041513285,0.002422076,0.0021318165,0.0017615518,0.0009485255,0.0024209,0.0026019476,0.0031661522,0.00664907],"category_scores_gemma":[0.020264637,0.0011999997,0.0016585388,0.002122345,0.0046228915,0.0046218666,0.005113363,0.00649016,0.0024358055],"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":[0.0002636377,0.00009401357,0.0002826552,0.00056307344,0.00008455467,0.000090396796,0.00026838458,0.13532367,0.0020858818,0.794345,0.010528761,0.056069966],"study_design_scores_gemma":[0.00003849199,0.000055534765,0.00016090127,0.00007322799,0.000020964148,0.00007348761,0.000034722492,0.63265765,0.0008239567,0.36151457,0.0045094974,0.00003706985],"about_ca_topic_score_codex":0.0045092874,"about_ca_topic_score_gemma":0.0027028774,"teacher_disagreement_score":0.00664907,"about_ca_system_score_codex":0.0021035802,"about_ca_system_score_gemma":0.0026753347,"threshold_uncertainty_score":0.02224338},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047299587,0.00009217409,0.99345607,0.00010392857,0.000029788018,0.0000377301,0.000029988285,0.0007406273,0.0007797279],"genre_scores_gemma":[0.27002862,0.00012103662,0.72469956,0.0002472076,0.00006657525,0.00040129805,0.00034359298,0.0005731836,0.003519038],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99891376,0.0005274017,0.000060668695,0.00015199065,0.00026830236,0.00007800616],"domain_scores_gemma":[0.9984145,0.0008140773,0.000098360666,0.00023685973,0.00034984775,0.00008637277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002072395,0.0010734822,0.001057075,0.00056151353,0.00049417745,0.0009025258,0.0024358556,0.0016166761,0.0047361716],"category_scores_gemma":[0.009317224,0.0006495419,0.00069463474,0.00057905924,0.0010118193,0.001890726,0.002092714,0.002184496,0.0016858581],"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":[0.00022248355,0.00008452226,0.0006074001,0.00012643758,0.000064400745,0.0000668078,0.00011167126,0.7475437,0.003099806,0.052721847,0.0044065025,0.19094434],"study_design_scores_gemma":[0.0000067399546,0.000013641648,0.000027588309,0.000004750048,0.0000015964825,0.000010635388,0.0000023300302,0.9888626,0.00046291278,0.010153322,0.00045008404,0.0000038166727],"about_ca_topic_score_codex":0.0034960003,"about_ca_topic_score_gemma":0.00434184,"teacher_disagreement_score":0.0047361716,"about_ca_system_score_codex":0.0013722759,"about_ca_system_score_gemma":0.0017301415,"threshold_uncertainty_score":0.015844107},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011537777,0.0004111574,0.98420745,0.00040867444,0.00010024042,0.000054901033,0.000030279183,0.00045957376,0.0027898361],"genre_scores_gemma":[0.2645652,0.000893996,0.7248475,0.0007326021,0.00019852647,0.00036115016,0.0002771251,0.0005731041,0.007550743],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959484,0.0017771119,0.00027866603,0.00072330434,0.001075302,0.00019732509],"domain_scores_gemma":[0.98657274,0.008540024,0.0007179389,0.0025602207,0.0013920182,0.00021713343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061088568,0.001059426,0.0017786752,0.0009845458,0.00080383074,0.0015733766,0.0016848183,0.0016357446,0.0030681884],"category_scores_gemma":[0.030259764,0.0007011981,0.0010207371,0.0011118149,0.0021594462,0.0026383912,0.0015180389,0.0022495128,0.0017359697],"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":[0.0003618814,0.00013516743,0.0040423796,0.00032812436,0.00027574235,0.0001673226,0.00018493424,0.589403,0.0064245225,0.2282913,0.009302209,0.16108344],"study_design_scores_gemma":[0.000053387572,0.000121006226,0.00041095552,0.00002512153,0.000022749824,0.0000956999,0.000018192395,0.9519672,0.0032855566,0.040213965,0.003766149,0.000020044945],"about_ca_topic_score_codex":0.003621527,"about_ca_topic_score_gemma":0.0050778375,"teacher_disagreement_score":0.0061088568,"about_ca_system_score_codex":0.0008697577,"about_ca_system_score_gemma":0.0019550778,"threshold_uncertainty_score":0.03230709},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011733351,0.0031632062,0.9712432,0.0026788316,0.00028556114,0.00012714356,0.00023731217,0.00064273627,0.009888599],"genre_scores_gemma":[0.5875375,0.006520189,0.36144036,0.0051622097,0.0018812021,0.0014737195,0.0016257981,0.0032113562,0.031147702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9879396,0.0043287748,0.00060490926,0.0021134058,0.0037384832,0.0012747747],"domain_scores_gemma":[0.9178297,0.059364017,0.005036654,0.0076838927,0.0075814547,0.002504308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026893979,0.005478594,0.0056837588,0.0042580147,0.0034404134,0.0051183137,0.0065266755,0.00547856,0.011553679],"category_scores_gemma":[0.13092871,0.0025816113,0.0052866023,0.002817784,0.007728141,0.01225153,0.010861069,0.014483699,0.002261876],"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":[0.0004304193,0.00018993799,0.0030741417,0.00084877014,0.00034342488,0.00034816237,0.0005948542,0.3736889,0.0036380487,0.57889277,0.009510169,0.028440472],"study_design_scores_gemma":[0.000028876073,0.000112118345,0.0006552244,0.00016497738,0.000077472294,0.00007474286,0.00004978207,0.79136795,0.0011724426,0.20337677,0.0028716559,0.00004804743],"about_ca_topic_score_codex":0.008286189,"about_ca_topic_score_gemma":0.006163376,"teacher_disagreement_score":0.026893979,"about_ca_system_score_codex":0.0078051244,"about_ca_system_score_gemma":0.005633266,"threshold_uncertainty_score":0.14223063},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0100608375,0.0009790946,0.983136,0.000571826,0.00012542927,0.0000335284,0.000038417515,0.0000775053,0.0049772942],"genre_scores_gemma":[0.7494116,0.0035873665,0.2194509,0.0005287598,0.00053136237,0.00039432745,0.00020774682,0.0002624626,0.02562552],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99945706,0.00019350398,0.000028654042,0.000078958205,0.00019713206,0.000044696557],"domain_scores_gemma":[0.9988612,0.00047590182,0.00013408445,0.00008748671,0.00035624843,0.00008510077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014246608,0.0010070964,0.0006587822,0.0007787848,0.00048721998,0.00085483544,0.00082575553,0.0008251007,0.0026161652],"category_scores_gemma":[0.004844168,0.00041006808,0.00079254934,0.00042514552,0.0011455449,0.0012422452,0.0015746603,0.001604019,0.00043848404],"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":[0.00003846409,0.00003174149,0.00063730084,0.00019616098,0.000058969476,0.00019526582,0.00019268839,0.27630505,0.0050222715,0.6888796,0.0025744615,0.025867978],"study_design_scores_gemma":[0.0000067335745,0.000032162316,0.0001593641,0.000028314496,0.000009779883,0.000044126584,0.00001240688,0.90728503,0.0006206624,0.08860662,0.0031822722,0.000012507528],"about_ca_topic_score_codex":0.0026225382,"about_ca_topic_score_gemma":0.0014403509,"teacher_disagreement_score":0.0026225382,"about_ca_system_score_codex":0.00083980674,"about_ca_system_score_gemma":0.00123411,"threshold_uncertainty_score":0.008751929},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1611451,0.00084427366,0.8264393,0.0014554932,0.000041531446,0.00004344073,0.000303984,0.0003810313,0.009345694],"genre_scores_gemma":[0.945911,0.0007854903,0.045710582,0.0001670837,0.000060744864,0.00010387352,0.00034750142,0.0002355945,0.006678215],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99939704,0.00021577236,0.0000291118,0.00010032452,0.00017177183,0.00008596479],"domain_scores_gemma":[0.99758756,0.0014300584,0.0002758928,0.00017235086,0.00037934355,0.00015479785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013726949,0.0011035721,0.0008304802,0.0009671463,0.0004968184,0.0014058562,0.0010166527,0.0010110452,0.0018188511],"category_scores_gemma":[0.0076250196,0.00057567353,0.00078540767,0.0005324216,0.0017228723,0.0020311119,0.0016216866,0.001999219,0.00035297527],"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":[0.0001169836,0.00002889368,0.0011515802,0.0001496159,0.00005146579,0.00029541398,0.00014312846,0.81837153,0.008623314,0.15576743,0.0014653349,0.013835327],"study_design_scores_gemma":[0.0000035051548,0.000033740864,0.000360548,0.000010208218,0.000004415012,0.000043104046,0.000019274143,0.96270156,0.001068594,0.03529018,0.0004580362,0.000006817775],"about_ca_topic_score_codex":0.0026401607,"about_ca_topic_score_gemma":0.0009994664,"teacher_disagreement_score":0.0026401607,"about_ca_system_score_codex":0.0013396249,"about_ca_system_score_gemma":0.0005679157,"threshold_uncertainty_score":0.009719729},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010573863,0.00029764415,0.99524575,0.0003854063,0.000042418964,0.00001348516,0.000056073986,0.000043133627,0.002858691],"genre_scores_gemma":[0.31163734,0.0030893867,0.66043586,0.00067915,0.000889449,0.00053071143,0.0006308196,0.00045224236,0.02165507],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985464,0.0006602893,0.000061377825,0.00023558455,0.00040060355,0.000095754716],"domain_scores_gemma":[0.99851376,0.0008851741,0.00012879685,0.00014474103,0.00022565159,0.00010186571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026619986,0.0010330206,0.0009976665,0.00094958296,0.0006705722,0.0019158963,0.0019083623,0.0013966297,0.0045950958],"category_scores_gemma":[0.005291363,0.0005198591,0.0011514166,0.0008475298,0.002376935,0.0025605517,0.002254747,0.0034346175,0.00087023305],"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":[0.000004369489,0.000008520684,0.0000726647,0.00003189826,0.000015825974,0.000016627255,0.00004082236,0.04412684,0.00036745204,0.9496528,0.0007175266,0.004944686],"study_design_scores_gemma":[0.000007663724,0.00001546688,0.000072931194,0.000021494656,0.000007304496,0.000022710352,0.000015246966,0.46579945,0.0001747809,0.52865994,0.005192194,0.000010831904],"about_ca_topic_score_codex":0.003122434,"about_ca_topic_score_gemma":0.003338301,"teacher_disagreement_score":0.0045950958,"about_ca_system_score_codex":0.0016387157,"about_ca_system_score_gemma":0.0021583254,"threshold_uncertainty_score":0.015372157},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011251109,0.00026185036,0.98600125,0.00022308971,0.00005120802,0.000023946417,0.00003998588,0.0013847959,0.0007626902],"genre_scores_gemma":[0.4391492,0.00057163596,0.552631,0.0004005374,0.00017070658,0.0002527612,0.00041025082,0.0015384356,0.004875516],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984908,0.00047849384,0.00012076922,0.0002650966,0.000517833,0.00012693179],"domain_scores_gemma":[0.99633396,0.002082965,0.00027628941,0.00069377496,0.00050914474,0.00010384219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027065047,0.001671234,0.0016726777,0.00071171543,0.00059820333,0.0014480995,0.0018120885,0.0018323568,0.002327647],"category_scores_gemma":[0.014269058,0.0011404167,0.0009802133,0.000759878,0.0015337924,0.0030618152,0.0022407188,0.0029226274,0.0012282266],"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":[0.00026103266,0.000101817204,0.0011530692,0.00019918765,0.000104987936,0.00014852568,0.00013101671,0.84271425,0.010674475,0.023130193,0.003033279,0.118348144],"study_design_scores_gemma":[0.000010046008,0.000028820601,0.00008235052,0.000007781157,0.000007084919,0.000020744077,0.000003937373,0.991017,0.002402301,0.0058999825,0.00051338825,0.0000065099816],"about_ca_topic_score_codex":0.0035142174,"about_ca_topic_score_gemma":0.0046485662,"teacher_disagreement_score":0.0035142174,"about_ca_system_score_codex":0.0009196741,"about_ca_system_score_gemma":0.0019039314,"threshold_uncertainty_score":0.014313519},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037965998,0.00034074555,0.9589761,0.00022832536,0.00002536133,0.000046200665,0.000031472933,0.0003707815,0.002015039],"genre_scores_gemma":[0.7549716,0.0003597178,0.23950972,0.00018697184,0.000042744945,0.00021488089,0.00019911231,0.00033147208,0.0041837073],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990693,0.00046816695,0.000044183707,0.0001364005,0.00019226292,0.00008976889],"domain_scores_gemma":[0.99584466,0.0027745254,0.00033365854,0.00041272095,0.0005141593,0.00012029866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035641987,0.001005062,0.0009879468,0.0007636375,0.00060504314,0.0008523124,0.0010390651,0.0012140117,0.0016301125],"category_scores_gemma":[0.014588671,0.0006169163,0.00060708745,0.00042976055,0.0015394519,0.0020121634,0.0017324035,0.0017797922,0.0002858369],"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":[0.000107876505,0.000032646993,0.0011840416,0.00010109946,0.00006542766,0.00010024767,0.00009596254,0.93741196,0.0029870812,0.032429516,0.0009560287,0.024528082],"study_design_scores_gemma":[0.0000022122529,0.00000861596,0.00006485752,0.00000388501,0.0000014025907,0.000008502184,0.0000031308941,0.99460405,0.00021317578,0.004985891,0.00010223683,0.0000020456212],"about_ca_topic_score_codex":0.0036455053,"about_ca_topic_score_gemma":0.0053941472,"teacher_disagreement_score":0.0036455053,"about_ca_system_score_codex":0.0015265645,"about_ca_system_score_gemma":0.0012733211,"threshold_uncertainty_score":0.018849492},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040828935,0.0011918334,0.9890476,0.0005800566,0.0001411721,0.00008970398,0.000058519818,0.00032719766,0.004481118],"genre_scores_gemma":[0.32711303,0.0038535628,0.6539188,0.0014539163,0.0012619906,0.0010043434,0.00052511756,0.0013816982,0.009487546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9897413,0.004399617,0.0005112367,0.0015228323,0.0030780048,0.0007469109],"domain_scores_gemma":[0.949759,0.036795337,0.0030585395,0.0044424944,0.00450909,0.0014354785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014178851,0.005382857,0.0035606287,0.0033784776,0.0019220446,0.0048962343,0.005649495,0.0052572177,0.006634397],"category_scores_gemma":[0.08220223,0.001619985,0.0022471554,0.0030057845,0.006434483,0.010455979,0.0074461913,0.008197201,0.0021768762],"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":[0.00030603606,0.00028161262,0.0010841031,0.0005600266,0.00023614908,0.00021147523,0.00021410683,0.42909214,0.0054291934,0.5033691,0.0069945077,0.052221537],"study_design_scores_gemma":[0.00003051967,0.000069866415,0.0001800524,0.00006469831,0.000027769242,0.000057483427,0.0000140092425,0.8781828,0.0020335205,0.11775351,0.0015529692,0.00003261365],"about_ca_topic_score_codex":0.0018758846,"about_ca_topic_score_gemma":0.0024078693,"teacher_disagreement_score":0.014178851,"about_ca_system_score_codex":0.004021506,"about_ca_system_score_gemma":0.003604394,"threshold_uncertainty_score":0.07498586},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19284375,0.00024479488,0.8027002,0.0002178854,0.00005519787,0.000043570097,0.00004874764,0.00032615682,0.003519735],"genre_scores_gemma":[0.94381195,0.00008402485,0.054199707,0.000054203825,0.000010331611,0.000046581616,0.000038766844,0.00007086265,0.0016836035],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995433,0.00013885766,0.000020256795,0.00006841763,0.00009917201,0.00013003557],"domain_scores_gemma":[0.9987054,0.00078339427,0.00013501929,0.00015833015,0.00012444305,0.00009347743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008495034,0.00051284075,0.00055517507,0.00036068444,0.00037527437,0.0007614212,0.001077011,0.0005329087,0.0012400346],"category_scores_gemma":[0.0037608016,0.00027221534,0.00023254576,0.0005246466,0.0011155519,0.0010635741,0.0010291262,0.000655512,0.00017397673],"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":[0.00016920062,0.000035131154,0.0002458954,0.00003772712,0.000008853455,0.00003520588,0.00003831875,0.96285415,0.0031289924,0.017567355,0.00037620525,0.015503003],"study_design_scores_gemma":[0.000005270561,0.000029522413,0.00006478225,0.000002869068,0.000002549214,0.000010378217,0.000012377595,0.9920581,0.001335496,0.0062863356,0.00018921075,0.000003212732],"about_ca_topic_score_codex":0.0016379912,"about_ca_topic_score_gemma":0.0013086767,"teacher_disagreement_score":0.0016379912,"about_ca_system_score_codex":0.0009253942,"about_ca_system_score_gemma":0.00087209576,"threshold_uncertainty_score":0.006714225},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007742739,0.000120875346,0.99104184,0.00015749205,0.000023500408,0.000021829295,0.000027437316,0.00020725859,0.00065713836],"genre_scores_gemma":[0.3839664,0.00038480439,0.60902274,0.00026827693,0.00011480563,0.0003027854,0.00028798153,0.00041282183,0.005239359],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990362,0.00047230718,0.000037026042,0.00012871403,0.00025227026,0.000073485506],"domain_scores_gemma":[0.99708253,0.0019676774,0.0002392435,0.0002858985,0.0003114651,0.00011322596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002860466,0.0011238154,0.0013607551,0.00071166153,0.00053424074,0.0010200085,0.0017000831,0.0017400979,0.0013462822],"category_scores_gemma":[0.008595305,0.0006691317,0.0010384792,0.0007212906,0.0016869475,0.0013549016,0.0015824859,0.0019471054,0.00043992282],"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":[0.000071186005,0.000032875716,0.0004420864,0.000072251605,0.000034375702,0.000043662494,0.000059973627,0.9523081,0.0014697912,0.031026037,0.00053811836,0.013901531],"study_design_scores_gemma":[0.0000029495104,0.000005163019,0.000013692235,0.0000021622834,8.490476e-7,0.0000027598878,0.0000014646406,0.9965197,0.00012063522,0.0032085977,0.00012019368,0.0000018619936],"about_ca_topic_score_codex":0.007843129,"about_ca_topic_score_gemma":0.0065158284,"teacher_disagreement_score":0.007843129,"about_ca_system_score_codex":0.0014376903,"about_ca_system_score_gemma":0.0021008032,"threshold_uncertainty_score":0.015594959},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006654985,0.00039853022,0.98778915,0.00054859766,0.00005199626,0.000043490265,0.000019880119,0.00029789552,0.0041955034],"genre_scores_gemma":[0.4392625,0.0010356292,0.54222906,0.0013077665,0.0002655392,0.00064090564,0.00016318289,0.0008667104,0.014228697],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991155,0.00045781524,0.00003459739,0.00014161532,0.00017582007,0.0000747065],"domain_scores_gemma":[0.99732864,0.0019302645,0.00017617775,0.00025557503,0.00020519372,0.00010411084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024992647,0.0013738864,0.001884554,0.0006673711,0.0007665835,0.0009895707,0.0015306992,0.0020982358,0.0040912703],"category_scores_gemma":[0.007948387,0.00077266595,0.00087802234,0.0005816815,0.002320199,0.0022147833,0.0027270725,0.0033174073,0.0012255698],"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":[0.00012786781,0.00010864271,0.0008111655,0.00023480057,0.000089387344,0.0001560286,0.0001877568,0.7288991,0.003212453,0.19687939,0.0057051205,0.063588254],"study_design_scores_gemma":[0.000018667237,0.00005647629,0.00004822797,0.000022746415,0.0000061500396,0.000026063752,0.000012282748,0.9492818,0.00040551592,0.049148735,0.0009651023,0.000008151084],"about_ca_topic_score_codex":0.0014868602,"about_ca_topic_score_gemma":0.0019481416,"teacher_disagreement_score":0.0040912703,"about_ca_system_score_codex":0.0007437567,"about_ca_system_score_gemma":0.0013389762,"threshold_uncertainty_score":0.013686657},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021270037,0.014315196,0.923121,0.01680991,0.0007006527,0.00012700031,0.00022630735,0.0009908502,0.022438988],"genre_scores_gemma":[0.6478566,0.021207878,0.31234473,0.0055848905,0.0028415236,0.001085491,0.00056975574,0.0012982263,0.007210969],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98628634,0.0055092527,0.0007119094,0.0017210228,0.004985775,0.0007856605],"domain_scores_gemma":[0.89876366,0.080527455,0.0020640858,0.011634609,0.0062005427,0.0008095852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016731637,0.0026827431,0.002258016,0.0019294177,0.0017858029,0.005955824,0.004768834,0.0050123837,0.008181457],"category_scores_gemma":[0.1152038,0.0015069403,0.0010728575,0.0024551912,0.00748148,0.018589579,0.0065654684,0.014651913,0.00208144],"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":[0.00048789225,0.0002780552,0.0012249735,0.000958345,0.00008010151,0.00020691605,0.00045974416,0.14732976,0.003696635,0.7085417,0.0143482005,0.122387685],"study_design_scores_gemma":[0.00009407841,0.00018786395,0.00045562582,0.00056920544,0.000031304808,0.00031858293,0.0002000469,0.6081081,0.0056302994,0.3761659,0.008166655,0.0000723892],"about_ca_topic_score_codex":0.0018501811,"about_ca_topic_score_gemma":0.0017155396,"teacher_disagreement_score":0.016731637,"about_ca_system_score_codex":0.00321896,"about_ca_system_score_gemma":0.0032043883,"threshold_uncertainty_score":0.08848637},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038269233,0.00029761106,0.9559311,0.00058639684,0.00007894862,0.000058913418,0.0001101517,0.00015677825,0.0045108907],"genre_scores_gemma":[0.89931214,0.0003816261,0.0922515,0.00024871898,0.00010067072,0.00026951288,0.00015445329,0.000059357506,0.0072220652],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987704,0.00039921672,0.000063982894,0.0003486165,0.0001823035,0.0002355116],"domain_scores_gemma":[0.9968765,0.0019079811,0.00040943862,0.00022891523,0.00024015772,0.00033699232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022705293,0.00083735684,0.0015249243,0.00043408395,0.0007443417,0.0022744017,0.0023253032,0.0015644409,0.0037424024],"category_scores_gemma":[0.0052188877,0.00075969845,0.0008172846,0.00059199176,0.0020271249,0.0028501577,0.0028718123,0.0023478153,0.00035290004],"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":[0.00013484871,0.000054578508,0.00074219436,0.000084928455,0.00006948549,0.00014026568,0.000104014165,0.8572333,0.00085298804,0.1259857,0.0010477244,0.013549958],"study_design_scores_gemma":[0.00001496005,0.000018515317,0.00004037223,0.000005301748,0.000006062026,0.0000085560205,0.000012671681,0.95447916,0.00012517837,0.044951413,0.00033294945,0.0000049315613],"about_ca_topic_score_codex":0.0034806433,"about_ca_topic_score_gemma":0.0031205453,"teacher_disagreement_score":0.0037424024,"about_ca_system_score_codex":0.0017911419,"about_ca_system_score_gemma":0.001905936,"threshold_uncertainty_score":0.01299566},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20051521,0.00020676914,0.7782522,0.0005891068,0.000084411695,0.000096019845,0.00011092206,0.00019902381,0.019946294],"genre_scores_gemma":[0.9677793,0.0001256106,0.025826765,0.00007450612,0.000013256278,0.00006994717,0.000033088952,0.0000251249,0.0060524363],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997726,0.00008663456,0.0000104685305,0.00004176393,0.000045080338,0.00004345301],"domain_scores_gemma":[0.9994978,0.00021073857,0.00007600521,0.000041924337,0.00008386263,0.00008964207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005623952,0.0006045711,0.0005368085,0.00024568106,0.0003519073,0.0010694038,0.0007679504,0.0007237424,0.0028074153],"category_scores_gemma":[0.0026746271,0.00022832504,0.0004369069,0.00015492697,0.0010077563,0.0011863597,0.00077901076,0.0008718291,0.0002739227],"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":[0.00015123285,0.000090799746,0.0009256867,0.00009334048,0.000038852628,0.00031115572,0.00024860486,0.32685137,0.010287919,0.6437746,0.0015424838,0.015683873],"study_design_scores_gemma":[0.00001397281,0.00004492611,0.00011369281,0.0000069392754,0.0000047674616,0.00003461765,0.000026608117,0.9430988,0.00069988886,0.055243026,0.00070308027,0.000009748121],"about_ca_topic_score_codex":0.002825892,"about_ca_topic_score_gemma":0.0017667928,"teacher_disagreement_score":0.002825892,"about_ca_system_score_codex":0.0012184996,"about_ca_system_score_gemma":0.00077632663,"threshold_uncertainty_score":0.009391725},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006154044,0.00039131325,0.98974425,0.0003806731,0.000043646465,0.00003978227,0.000015809059,0.00032454127,0.0029058836],"genre_scores_gemma":[0.4170362,0.00092722685,0.56835407,0.0011164689,0.00021243477,0.00057288405,0.00015435353,0.00078123115,0.010845176],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991731,0.00041436768,0.000033444874,0.00013853883,0.00016483932,0.00007567622],"domain_scores_gemma":[0.99761754,0.0016640638,0.00016168423,0.00024839895,0.00020915734,0.00009902862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002471987,0.0013019057,0.0020533204,0.00064186985,0.0007054039,0.0009383641,0.0016379264,0.002090576,0.0037703272],"category_scores_gemma":[0.0069496995,0.0007704822,0.0009347555,0.0006045498,0.0020476163,0.0022437347,0.0025779991,0.0030729393,0.0011524315],"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":[0.00012094122,0.00011278038,0.0008519823,0.00021472915,0.0000898106,0.00016074315,0.0001902709,0.7750995,0.0031295067,0.14077498,0.004915725,0.074339114],"study_design_scores_gemma":[0.000015544152,0.000055135468,0.000044972883,0.000019129211,0.0000060021343,0.000030742456,0.0000116019555,0.9674944,0.0003765194,0.031115254,0.0008230974,0.00000749947],"about_ca_topic_score_codex":0.0014729861,"about_ca_topic_score_gemma":0.002066458,"teacher_disagreement_score":0.0037703272,"about_ca_system_score_codex":0.0006792238,"about_ca_system_score_gemma":0.0013420673,"threshold_uncertainty_score":0.013073266},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007309853,0.0020946348,0.97053456,0.0044482127,0.0002742003,0.000056491685,0.00015898337,0.00085057464,0.014272403],"genre_scores_gemma":[0.41524506,0.0041715424,0.55825144,0.0021584644,0.00062521925,0.00048479103,0.00068580225,0.0011406724,0.017237008],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956701,0.0021876544,0.00017970322,0.00044861005,0.0013247421,0.00018917356],"domain_scores_gemma":[0.9824599,0.013610009,0.00033148547,0.0021062987,0.0012454961,0.00024677278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008036,0.00091270846,0.0015453736,0.000774933,0.0009248679,0.0022029162,0.002986463,0.0019117384,0.0050891913],"category_scores_gemma":[0.056390274,0.00090357853,0.0006350057,0.00087333156,0.0028183104,0.004820098,0.0028539125,0.0044063525,0.0022455638],"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":[0.00025751747,0.00007128329,0.001224604,0.00038025112,0.00007632338,0.00011494313,0.00025166644,0.20554742,0.00070733007,0.6694352,0.019038018,0.10289549],"study_design_scores_gemma":[0.000023697636,0.00002366534,0.00017667976,0.00008041195,0.0000051329757,0.00006678564,0.000028761122,0.7947703,0.00041273324,0.19733761,0.0070587546,0.000015474618],"about_ca_topic_score_codex":0.008521223,"about_ca_topic_score_gemma":0.008344332,"teacher_disagreement_score":0.008521223,"about_ca_system_score_codex":0.0017117588,"about_ca_system_score_gemma":0.0031472072,"threshold_uncertainty_score":0.042498946},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028914353,0.0003578925,0.94058305,0.00037155126,0.00026668722,0.000111942994,0.00015998144,0.0015842121,0.027650265],"genre_scores_gemma":[0.49240842,0.00023768238,0.48586035,0.0003036695,0.000083896586,0.0001892504,0.00028970296,0.0002062145,0.020420797],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99948126,0.00007483698,0.000019718862,0.000066464454,0.000260103,0.0000976982],"domain_scores_gemma":[0.9991893,0.00023313296,0.00005636112,0.00021304836,0.0002344945,0.00007357848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035284538,0.00050277286,0.00040374915,0.0005156143,0.0004976998,0.0008664502,0.001039121,0.00082983787,0.009433312],"category_scores_gemma":[0.0019506373,0.00019282833,0.0003834542,0.0007058686,0.0006843383,0.0013402808,0.0014042123,0.0009863878,0.0018515784],"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":[0.00045202463,0.0001696141,0.0007946337,0.0003689741,0.000049084498,0.00029526686,0.00039965648,0.38152754,0.056711275,0.26045826,0.021445839,0.2773278],"study_design_scores_gemma":[0.000028602853,0.00006045237,0.00013267693,0.000014747363,0.0000057937464,0.00007245109,0.0000258442,0.96346116,0.007096657,0.021847693,0.0072374507,0.00001652925],"about_ca_topic_score_codex":0.003418231,"about_ca_topic_score_gemma":0.0057483823,"teacher_disagreement_score":0.009433312,"about_ca_system_score_codex":0.0009224491,"about_ca_system_score_gemma":0.0013125144,"threshold_uncertainty_score":0.0315575},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048692923,0.00092282164,0.9398533,0.0016862196,0.000093815885,0.000052532174,0.000104658684,0.00039276754,0.008201012],"genre_scores_gemma":[0.8704663,0.0015344784,0.11507168,0.0012969518,0.00040345482,0.00036468927,0.00037071606,0.00038232264,0.010109422],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982773,0.00077479176,0.000079197525,0.00033959452,0.00036998533,0.00015903146],"domain_scores_gemma":[0.98980206,0.0061789835,0.0009585062,0.0016706588,0.0009851652,0.0004046933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075998395,0.0013908214,0.0010660808,0.0008918666,0.00058396184,0.0013312084,0.0022722029,0.001883862,0.0027117676],"category_scores_gemma":[0.035369985,0.0007264858,0.0013364041,0.0004957762,0.0028673946,0.0055640857,0.004509371,0.004391959,0.00043023855],"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":[0.0001375122,0.00006594446,0.0024423015,0.00023542327,0.000122262,0.00030757385,0.00026434017,0.52359116,0.0032833542,0.44607577,0.002185014,0.02128946],"study_design_scores_gemma":[0.000008639508,0.00004176541,0.00033184717,0.000028414657,0.000011446254,0.00006755155,0.000018327712,0.87801635,0.0004768461,0.12044589,0.000541192,0.000011678525],"about_ca_topic_score_codex":0.0022486944,"about_ca_topic_score_gemma":0.0013539387,"teacher_disagreement_score":0.0075998395,"about_ca_system_score_codex":0.0019012656,"about_ca_system_score_gemma":0.000819693,"threshold_uncertainty_score":0.040192306},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019546043,0.014820895,0.92605835,0.015555246,0.00070049654,0.00012236355,0.00021929257,0.00096181047,0.022015544],"genre_scores_gemma":[0.64776504,0.022368006,0.3117165,0.005531863,0.0028417883,0.0010396461,0.00055443717,0.001239621,0.006943154],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98722804,0.004985816,0.00068344845,0.0016879502,0.0046802848,0.0007345384],"domain_scores_gemma":[0.90367526,0.07658472,0.001983909,0.010873641,0.006113595,0.00076888525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015748953,0.0028266434,0.0022478087,0.0019407878,0.0017239944,0.005618819,0.0047185775,0.0047824043,0.008091575],"category_scores_gemma":[0.111086674,0.0014883187,0.0010508808,0.0024332602,0.007399196,0.017629717,0.006287971,0.014122487,0.0020528613],"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":[0.00047873787,0.0002814427,0.001227983,0.0010626426,0.00008487259,0.00021303135,0.00044951646,0.15260595,0.0038534622,0.700158,0.014447358,0.12513706],"study_design_scores_gemma":[0.00008989352,0.00020093539,0.0004758384,0.00060829235,0.000033450804,0.00033708272,0.0001994706,0.62798315,0.005707804,0.35609078,0.008199372,0.00007381194],"about_ca_topic_score_codex":0.0018011677,"about_ca_topic_score_gemma":0.0017415306,"teacher_disagreement_score":0.015748953,"about_ca_system_score_codex":0.003017136,"about_ca_system_score_gemma":0.0031967955,"threshold_uncertainty_score":0.083289385},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025048058,0.00013738436,0.99577457,0.00012876301,0.000057322617,0.000036252837,0.000034452874,0.0006490553,0.0006774701],"genre_scores_gemma":[0.14675944,0.0004542077,0.8455749,0.0004102046,0.00013143789,0.00043054883,0.00046795732,0.00070622994,0.00506515],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992803,0.00025554065,0.000038248367,0.00009412925,0.0002802887,0.000051597126],"domain_scores_gemma":[0.9988808,0.0005073717,0.00008885669,0.00017843282,0.0002688739,0.00007573587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017211501,0.0015062331,0.0012313483,0.0008386984,0.00041303842,0.00086506514,0.0017570232,0.0013935103,0.002826607],"category_scores_gemma":[0.004753794,0.00076349056,0.000868022,0.0008904622,0.0011514166,0.0011678471,0.001940107,0.0025810148,0.0014032024],"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":[0.00012538757,0.00009879163,0.0011499875,0.00021053488,0.00012085979,0.0001126377,0.00009761405,0.7458714,0.0061733117,0.036866546,0.01024008,0.19893274],"study_design_scores_gemma":[0.000015868149,0.000022287499,0.00005284089,0.000007956158,0.000003615668,0.000017748722,0.0000029456291,0.9929274,0.0009230524,0.0041269804,0.001894219,0.000005142665],"about_ca_topic_score_codex":0.0030281933,"about_ca_topic_score_gemma":0.0047209654,"teacher_disagreement_score":0.0030281933,"about_ca_system_score_codex":0.0009019872,"about_ca_system_score_gemma":0.0022570502,"threshold_uncertainty_score":0.009455919},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073987454,0.00091440364,0.90485495,0.004495981,0.00030317093,0.00022687143,0.00037536712,0.0030337179,0.011808083],"genre_scores_gemma":[0.53082705,0.0005539666,0.45173275,0.0015278852,0.00013839401,0.00032483027,0.0006926425,0.0006393845,0.013563088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99925417,0.00017387158,0.000039245708,0.00018853378,0.00016668446,0.00017759738],"domain_scores_gemma":[0.9976674,0.0014368236,0.00016862669,0.000325881,0.00021232213,0.00018896536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014597256,0.0008877326,0.0011531964,0.0007395599,0.0013276234,0.0016655901,0.0017054984,0.0026588216,0.008057935],"category_scores_gemma":[0.00871332,0.00073186075,0.0010652128,0.00061392784,0.0019996597,0.0041542985,0.0025714086,0.0025111374,0.0019931877],"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":[0.00095481594,0.00040253383,0.004066353,0.0006099724,0.00016601734,0.00071535876,0.0007933792,0.3266312,0.012557698,0.4190567,0.03194681,0.20209914],"study_design_scores_gemma":[0.00008057283,0.0001468339,0.00023627418,0.00005530596,0.000026891734,0.00021056988,0.00011486546,0.8397905,0.004143529,0.14771898,0.0074356445,0.000039992217],"about_ca_topic_score_codex":0.003208218,"about_ca_topic_score_gemma":0.001771969,"teacher_disagreement_score":0.008057935,"about_ca_system_score_codex":0.0011175537,"about_ca_system_score_gemma":0.0016320266,"threshold_uncertainty_score":0.026956439},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0154587515,0.00025789486,0.9779965,0.00042930286,0.000108388,0.00005432572,0.00015761008,0.0012573701,0.00427976],"genre_scores_gemma":[0.79968464,0.0005796158,0.18019292,0.00053932704,0.00018444288,0.0005045738,0.00051118975,0.00049643527,0.01730686],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995011,0.000103452636,0.000026023035,0.000142694,0.00014766608,0.00007917418],"domain_scores_gemma":[0.99930346,0.0002629,0.00006817607,0.00013978074,0.00016454745,0.00006119621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011267377,0.0007947304,0.00081958645,0.0004178705,0.00054862985,0.0009023383,0.0024491665,0.00089117425,0.005463556],"category_scores_gemma":[0.0027295335,0.0004254291,0.0005560976,0.00067859323,0.0008487801,0.0018632918,0.0015474587,0.0016810514,0.0010393348],"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":[0.00019118495,0.00007281755,0.00059633754,0.00008759615,0.000031365154,0.00007940233,0.000059207192,0.90276074,0.002287544,0.039936494,0.0060768193,0.047820557],"study_design_scores_gemma":[0.0000078587245,0.000013247638,0.000024180043,0.000002041878,0.0000031906927,0.00000778363,0.00000335549,0.9928731,0.0003556744,0.0061756037,0.00053192704,0.0000020906703],"about_ca_topic_score_codex":0.004577665,"about_ca_topic_score_gemma":0.0070260363,"teacher_disagreement_score":0.005463556,"about_ca_system_score_codex":0.0010649688,"about_ca_system_score_gemma":0.0017467653,"threshold_uncertainty_score":0.018277466},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011964402,0.0004978036,0.98304313,0.00043823707,0.00008250081,0.00002769898,0.000035275618,0.00018406322,0.0037268058],"genre_scores_gemma":[0.88315797,0.0011765311,0.10335028,0.0003151855,0.00019641755,0.00023947311,0.000104958024,0.0003384647,0.011120694],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99907327,0.00031154038,0.000040421597,0.00014343101,0.00032804022,0.00010342334],"domain_scores_gemma":[0.9962161,0.002559213,0.00026263218,0.000233349,0.0006004944,0.00012834728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002402997,0.0008390305,0.00060421653,0.0006228001,0.0004447832,0.0011301053,0.00092395715,0.0007123703,0.00253376],"category_scores_gemma":[0.010345753,0.00036407445,0.00040432383,0.00057297485,0.0013465116,0.0018934456,0.0011606307,0.0014365352,0.00044880903],"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":[0.00010035668,0.00001865132,0.00044387596,0.000081505255,0.000026179156,0.000061970226,0.000072698866,0.7653062,0.0017447704,0.21803972,0.0013046799,0.012799431],"study_design_scores_gemma":[0.000006253335,0.000010091596,0.000043924738,0.000003935505,0.000003013528,0.0000054193406,0.0000043321284,0.97238624,0.00030543417,0.02675428,0.00047388434,0.000003214928],"about_ca_topic_score_codex":0.0029882682,"about_ca_topic_score_gemma":0.0016296338,"teacher_disagreement_score":0.0029882682,"about_ca_system_score_codex":0.0016565244,"about_ca_system_score_gemma":0.0013859808,"threshold_uncertainty_score":0.012708366},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.396151,0.0040415702,0.56815434,0.002396646,0.00040880623,0.0006208058,0.0009940119,0.010753308,0.01647951],"genre_scores_gemma":[0.92242116,0.0003069896,0.0739132,0.00028534708,0.000045083667,0.00023017668,0.00043222695,0.0003140653,0.002051746],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798286,0.00043961479,0.00009881089,0.0004007329,0.00047880967,0.0005990826],"domain_scores_gemma":[0.99417675,0.002633237,0.00038326273,0.0010127815,0.0012469287,0.0005470217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003641071,0.0011593109,0.0016841624,0.00064243533,0.0010744537,0.0016462009,0.0020518582,0.001398352,0.0047646146],"category_scores_gemma":[0.013814295,0.0003755272,0.0004413728,0.00077404623,0.0010609253,0.0018119558,0.0016246065,0.0020875095,0.0009990894],"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":[0.0014608506,0.0003620683,0.003716573,0.00026263445,0.00008681852,0.00009769595,0.00014748694,0.90437627,0.005983672,0.009614831,0.009137195,0.06475388],"study_design_scores_gemma":[0.0000329085,0.00008438495,0.00037437686,0.000009448454,0.0000061059036,0.000025325022,0.000022721195,0.9955285,0.0016564471,0.0018973021,0.00035297908,0.000009365381],"about_ca_topic_score_codex":0.013757667,"about_ca_topic_score_gemma":0.011376657,"teacher_disagreement_score":0.013757667,"about_ca_system_score_codex":0.0025828395,"about_ca_system_score_gemma":0.004836113,"threshold_uncertainty_score":0.027355194},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050107655,0.00025077374,0.9929288,0.00016676019,0.000033234715,0.00002070717,0.000027424096,0.00015350645,0.0014080784],"genre_scores_gemma":[0.49628234,0.0008207809,0.4920969,0.00043827944,0.00017911095,0.00037907902,0.00047599358,0.0004947618,0.008832836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990895,0.00035237838,0.000033175937,0.00017526938,0.00027046067,0.00007914572],"domain_scores_gemma":[0.99868685,0.00079674163,0.0001178506,0.00010369438,0.00022962269,0.0000651844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001395178,0.0012796043,0.001321775,0.00046840374,0.00042023498,0.00092239154,0.0012033919,0.0010957828,0.0018706546],"category_scores_gemma":[0.0036841019,0.00060367055,0.0012194489,0.00050252373,0.001184038,0.0010505185,0.0014308426,0.0018704355,0.0005148474],"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":[0.00003484732,0.000030856587,0.0003410725,0.000095739284,0.000045882796,0.00007489479,0.000038601393,0.95418274,0.001585473,0.024457248,0.0015293895,0.017583283],"study_design_scores_gemma":[0.0000019402923,0.000006425724,0.00002327624,0.000002528252,0.0000015506507,0.0000046724876,0.0000015718977,0.9961641,0.00014673568,0.0034063736,0.00023890828,0.0000020127954],"about_ca_topic_score_codex":0.005269673,"about_ca_topic_score_gemma":0.0055112885,"teacher_disagreement_score":0.005269673,"about_ca_system_score_codex":0.0011007095,"about_ca_system_score_gemma":0.0014751885,"threshold_uncertainty_score":0.01047802},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17237258,0.0020143788,0.80586624,0.0041265143,0.00019833296,0.00015894123,0.0006277579,0.001148766,0.013486506],"genre_scores_gemma":[0.9683782,0.0015378355,0.022744702,0.0006886,0.00065796974,0.00033791302,0.00044524492,0.0005081713,0.004701286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936433,0.0018675646,0.00039350108,0.0018361139,0.0010561103,0.0012034307],"domain_scores_gemma":[0.8846212,0.08765104,0.009662263,0.008194526,0.0046557207,0.0052153114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012357231,0.0025691385,0.00612124,0.0037787238,0.0026711875,0.005905473,0.005601698,0.0035683247,0.00793564],"category_scores_gemma":[0.079541735,0.0023628497,0.004787073,0.0027048911,0.009923915,0.01828285,0.006283417,0.009973447,0.00051989395],"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":[0.00015678987,0.00017183433,0.0033493307,0.00031920502,0.00028190113,0.00063176954,0.00055463566,0.07180015,0.0016217311,0.91297454,0.0023158311,0.005822274],"study_design_scores_gemma":[0.000030092338,0.000049059527,0.0006708134,0.000042511452,0.00008950595,0.00020035185,0.00008192562,0.38715428,0.0005784601,0.6106921,0.0003556417,0.000055241337],"about_ca_topic_score_codex":0.0031036348,"about_ca_topic_score_gemma":0.0026462234,"teacher_disagreement_score":0.012357231,"about_ca_system_score_codex":0.003465791,"about_ca_system_score_gemma":0.0033811263,"threshold_uncertainty_score":0.06535208},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00306977,0.00019620192,0.9948068,0.00021664388,0.00008314386,0.000027038694,0.000024326297,0.00043488492,0.0011412114],"genre_scores_gemma":[0.10646421,0.00034857113,0.8853713,0.00029287452,0.00022882297,0.00021440997,0.00019843792,0.0004924359,0.006388917],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925596,0.00028536626,0.000026007698,0.000089753295,0.00028209007,0.000060894014],"domain_scores_gemma":[0.9989471,0.00043375994,0.00007270939,0.00018259884,0.00027200038,0.00009184834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013690373,0.0009958508,0.0014005422,0.0004736597,0.00036452195,0.0010325959,0.0016870825,0.0014711147,0.002698869],"category_scores_gemma":[0.004097247,0.0005579053,0.0007031829,0.0006627161,0.0009260971,0.0010430247,0.0016900388,0.002517393,0.0012492947],"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":[0.00022477088,0.0001402969,0.001098269,0.00021379202,0.00012210777,0.0002728588,0.00015007972,0.6447713,0.008943638,0.12685847,0.01721653,0.19998798],"study_design_scores_gemma":[0.000018294528,0.000026844604,0.0000484282,0.00000601469,0.000003889632,0.000026786376,0.000002831865,0.99158925,0.0005458033,0.0053424616,0.002382364,0.000006988677],"about_ca_topic_score_codex":0.003314829,"about_ca_topic_score_gemma":0.0036045823,"teacher_disagreement_score":0.003314829,"about_ca_system_score_codex":0.0005441961,"about_ca_system_score_gemma":0.0013665935,"threshold_uncertainty_score":0.009028614},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015422299,0.002615289,0.9706143,0.0013475418,0.00017523032,0.00008704802,0.000103489176,0.00049284403,0.009142016],"genre_scores_gemma":[0.58005184,0.0061893347,0.39359584,0.0015922235,0.00074183056,0.00090446364,0.000558943,0.0020738118,0.014291777],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99589396,0.0023090402,0.00017687681,0.0005068696,0.000778091,0.0003351392],"domain_scores_gemma":[0.9517057,0.0409589,0.0015426058,0.0023645,0.0026977,0.00073063205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013993669,0.0020292867,0.0017882898,0.002040979,0.0010167961,0.0026572188,0.001903821,0.0018700075,0.0063536554],"category_scores_gemma":[0.08193297,0.0007869434,0.0014050798,0.0011807133,0.0038030231,0.005344062,0.0043160585,0.006235855,0.0015291971],"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":[0.0005591377,0.00012656001,0.003173841,0.00063903787,0.00015421763,0.0001800132,0.00045274675,0.50071824,0.003348097,0.40936667,0.005316202,0.07596518],"study_design_scores_gemma":[0.000026735424,0.00009842859,0.00041484783,0.00016216542,0.000025710076,0.000055632467,0.00004126317,0.908459,0.0019943237,0.08715637,0.0015391529,0.00002628927],"about_ca_topic_score_codex":0.002244779,"about_ca_topic_score_gemma":0.0018337998,"teacher_disagreement_score":0.013993669,"about_ca_system_score_codex":0.0017901405,"about_ca_system_score_gemma":0.002122564,"threshold_uncertainty_score":0.07400644},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005423009,0.00023459177,0.9894923,0.0002654476,0.00009121124,0.00008398367,0.00012351501,0.0027213034,0.0015646509],"genre_scores_gemma":[0.24742143,0.00019994205,0.74408424,0.00047735308,0.000095926385,0.00053315033,0.0009007421,0.0011304178,0.0051567703],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805176,0.00086689193,0.00013063209,0.00032305,0.0004680623,0.00015962482],"domain_scores_gemma":[0.99645585,0.0020750894,0.00021428471,0.00062092295,0.0005219123,0.00011181699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030966762,0.0015303959,0.0019642904,0.0008120543,0.0005259131,0.0012187962,0.0016419323,0.0020930415,0.007032037],"category_scores_gemma":[0.012233408,0.0008382494,0.0009058607,0.0008668607,0.00090928335,0.0013562688,0.0014826109,0.0031937398,0.0022374336],"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":[0.0002390386,0.000105871324,0.0005597429,0.0001393299,0.000067550274,0.00010734326,0.0000625173,0.82369846,0.0024002257,0.02433358,0.0088468455,0.13943946],"study_design_scores_gemma":[0.00001129794,0.000013992387,0.000036519203,0.0000054439324,0.000002475505,0.00000881018,0.000002741002,0.99445844,0.00039720917,0.0043131695,0.0007465582,0.0000034448785],"about_ca_topic_score_codex":0.0060990364,"about_ca_topic_score_gemma":0.0079155285,"teacher_disagreement_score":0.007032037,"about_ca_system_score_codex":0.0011273834,"about_ca_system_score_gemma":0.0026151412,"threshold_uncertainty_score":0.023524523},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020403039,0.0010891237,0.9752467,0.0008535575,0.00010490153,0.000037205245,0.000024555451,0.0006114608,0.0016294664],"genre_scores_gemma":[0.54745346,0.0015507657,0.4455309,0.00084371096,0.00023338114,0.00024065239,0.00019429566,0.00067318423,0.003279637],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99744487,0.0013335649,0.00018352114,0.00036307916,0.0005530829,0.00012205829],"domain_scores_gemma":[0.991197,0.0060729315,0.0005017111,0.0011861292,0.00085966673,0.00018267447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069201156,0.0012940334,0.0011821481,0.00064636284,0.00058885256,0.0011420224,0.0014126786,0.0016195023,0.0013828909],"category_scores_gemma":[0.02508292,0.0007236548,0.00078657834,0.00068886275,0.0022692883,0.0028385809,0.0025079695,0.003852788,0.0004873198],"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":[0.00026400888,0.00007745416,0.0023242254,0.00024196431,0.00014755449,0.00013706805,0.00029277278,0.73781025,0.0045400555,0.07096955,0.0041706115,0.17902453],"study_design_scores_gemma":[0.000010779364,0.000046143672,0.00014800094,0.000023033659,0.0000074055456,0.0000287305,0.000009808697,0.9809826,0.0012094107,0.016620826,0.00090672716,0.0000064072055],"about_ca_topic_score_codex":0.0026235238,"about_ca_topic_score_gemma":0.0023131918,"teacher_disagreement_score":0.0069201156,"about_ca_system_score_codex":0.000856728,"about_ca_system_score_gemma":0.0015208386,"threshold_uncertainty_score":0.03659749},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025942312,0.00019410107,0.99613464,0.00013993461,0.000031256222,0.000021731063,0.000017509909,0.00027738806,0.0005892293],"genre_scores_gemma":[0.33004063,0.00059922604,0.6635331,0.0003824903,0.00015427441,0.00043286273,0.00025071987,0.0005098011,0.0040967497],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986058,0.0006615659,0.00006943589,0.00026809098,0.00031399436,0.00008108508],"domain_scores_gemma":[0.99595475,0.0025451458,0.00026405588,0.0005559997,0.00050132425,0.00017879528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038034208,0.0014093133,0.0019908936,0.00087156455,0.00063922344,0.0015819526,0.0022188977,0.002048092,0.002718745],"category_scores_gemma":[0.010836476,0.0006722663,0.00095751975,0.0010133316,0.0019821245,0.0019142649,0.0031670656,0.0031804678,0.0010218575],"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":[0.00011232735,0.00006862826,0.0005510669,0.0001308589,0.000066968576,0.0000662447,0.00010336747,0.88887334,0.0011051671,0.04755024,0.0019885101,0.059383307],"study_design_scores_gemma":[0.000011151497,0.000021436588,0.000029632325,0.000010134244,0.0000037804168,0.000008051502,0.000007820733,0.9747167,0.0002750527,0.024389198,0.0005228007,0.000004323923],"about_ca_topic_score_codex":0.0026002403,"about_ca_topic_score_gemma":0.002731251,"teacher_disagreement_score":0.0038034208,"about_ca_system_score_codex":0.0012253141,"about_ca_system_score_gemma":0.001583523,"threshold_uncertainty_score":0.02011466},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047524204,0.00012768844,0.9918995,0.00014788193,0.00010474556,0.000074319585,0.00005166287,0.0016811235,0.001160581],"genre_scores_gemma":[0.24288148,0.00023044489,0.7496128,0.00037884232,0.00015213026,0.0005501381,0.00040139607,0.0009127519,0.0048800376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908996,0.0003409002,0.000077081546,0.0001649901,0.00024544075,0.000081679456],"domain_scores_gemma":[0.99805045,0.00092464034,0.00018684892,0.000266545,0.00042136843,0.0001501876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018792829,0.0011622632,0.0010682472,0.0006355664,0.00055653375,0.0010733764,0.001995985,0.0012043483,0.004829589],"category_scores_gemma":[0.0074123614,0.0006952016,0.00069512974,0.0005674011,0.0011117201,0.0011371559,0.0015487131,0.0023431925,0.0021484033],"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":[0.00039022957,0.00016569595,0.001233438,0.00018003474,0.00008696808,0.000094424664,0.00014456929,0.689387,0.005721435,0.037552785,0.012943709,0.25209975],"study_design_scores_gemma":[0.00003301849,0.000035685705,0.00005322898,0.000007630987,0.00000383052,0.000013461384,0.000005867477,0.9906735,0.0012999113,0.006350439,0.0015175808,0.0000057829043],"about_ca_topic_score_codex":0.003785526,"about_ca_topic_score_gemma":0.0049239397,"teacher_disagreement_score":0.004829589,"about_ca_system_score_codex":0.0010615531,"about_ca_system_score_gemma":0.0022453964,"threshold_uncertainty_score":0.016156554},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00229031,0.00014172558,0.9934794,0.0002584738,0.000035913275,0.000051140993,0.000040980784,0.00085716386,0.0028448282],"genre_scores_gemma":[0.18311648,0.00023706723,0.80833346,0.00053714204,0.00010301714,0.0004715108,0.00028594947,0.00082859327,0.0060867653],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878246,0.0005003317,0.00005640489,0.000247779,0.0002813067,0.00013163898],"domain_scores_gemma":[0.9976609,0.0016382494,0.000105315296,0.0002684449,0.00022120016,0.00010583623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025990943,0.0018538719,0.0013974101,0.00063837075,0.0006921811,0.0014239236,0.0018953028,0.0023235737,0.006234768],"category_scores_gemma":[0.007676285,0.00084267004,0.0009899824,0.0006296395,0.00159826,0.0018460812,0.0028431397,0.0046154656,0.0020524354],"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":[0.00016213294,0.00010267498,0.00053849275,0.00017124815,0.00004750766,0.00010006092,0.0001726474,0.7360602,0.0029723085,0.14605087,0.009387528,0.10423434],"study_design_scores_gemma":[0.00001765041,0.000019660378,0.000025673215,0.00001337942,0.0000030921813,0.00002062773,0.000006918015,0.9660683,0.0006536526,0.03194444,0.0012207426,0.000005807137],"about_ca_topic_score_codex":0.0022834134,"about_ca_topic_score_gemma":0.0043034335,"teacher_disagreement_score":0.006234768,"about_ca_system_score_codex":0.0018781689,"about_ca_system_score_gemma":0.0020477974,"threshold_uncertainty_score":0.020857394},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0138764465,0.0002525649,0.9826841,0.00089609437,0.000069748545,0.00003730829,0.000036191832,0.00042394616,0.0017236288],"genre_scores_gemma":[0.6901966,0.0004012354,0.30273008,0.00057072693,0.00025083884,0.00019030074,0.00014696861,0.00015148993,0.005361816],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833256,0.00062758074,0.00006718216,0.0002969827,0.0005525893,0.000123103],"domain_scores_gemma":[0.9973247,0.0013413494,0.0001967621,0.0006788465,0.0003236229,0.00013471335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019128232,0.0006849581,0.00092737924,0.00046569956,0.0005805284,0.0008962486,0.0013349709,0.0013384823,0.002951486],"category_scores_gemma":[0.008366959,0.0002440331,0.00035336582,0.0007456679,0.001346102,0.003475518,0.0022839634,0.0024599126,0.0004751078],"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":[0.00055066997,0.00022481552,0.00096044265,0.00024104571,0.00006558523,0.00019387696,0.0002807889,0.526961,0.017766323,0.28612873,0.0054543996,0.1611723],"study_design_scores_gemma":[0.000043512784,0.00010825174,0.00010453915,0.000017357748,0.0000072109247,0.000048768783,0.000026126092,0.93739593,0.0050323643,0.05421198,0.0029905688,0.0000133531175],"about_ca_topic_score_codex":0.0008102182,"about_ca_topic_score_gemma":0.0008866616,"teacher_disagreement_score":0.002951486,"about_ca_system_score_codex":0.0007034681,"about_ca_system_score_gemma":0.00136768,"threshold_uncertainty_score":0.010116041},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017409363,0.0005263142,0.9950891,0.00022707864,0.00009075893,0.000027681099,0.000022453552,0.000042559444,0.0022331818],"genre_scores_gemma":[0.28089568,0.0038849986,0.6830576,0.00066942285,0.0013947116,0.0008065276,0.00048130672,0.0011040339,0.027705729],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99726355,0.0013945994,0.00012688318,0.00023764023,0.00080181746,0.00017554672],"domain_scores_gemma":[0.9920351,0.0051516453,0.0004591999,0.000399808,0.0015669053,0.0003872944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008879001,0.0028264578,0.0027783753,0.0029376643,0.0008404596,0.0030010499,0.0027899211,0.002733356,0.0052595045],"category_scores_gemma":[0.019278016,0.0014261684,0.0029562227,0.0018752267,0.0030958343,0.004769214,0.0049456246,0.0047333017,0.00081276655],"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":[0.00006773246,0.000070002716,0.00028551248,0.00025013747,0.000121740064,0.00008100996,0.00010155306,0.24057458,0.0013957749,0.7370613,0.00281642,0.017174179],"study_design_scores_gemma":[0.000005647581,0.000020579673,0.00006623532,0.000016610076,0.000013991568,0.000013294295,0.000008334176,0.93380433,0.00017029264,0.06500157,0.00086824235,0.000010932712],"about_ca_topic_score_codex":0.0034909905,"about_ca_topic_score_gemma":0.0041570333,"teacher_disagreement_score":0.008879001,"about_ca_system_score_codex":0.0020793779,"about_ca_system_score_gemma":0.0031937456,"threshold_uncertainty_score":0.046957254},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029238788,0.00011552563,0.9953655,0.00013439143,0.00005846018,0.000025756415,0.000017809261,0.00026092466,0.0010978384],"genre_scores_gemma":[0.22894323,0.00027618438,0.76369804,0.00025361922,0.00009920729,0.00024301905,0.00010479427,0.00027430255,0.006107626],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995029,0.00017253231,0.000018622404,0.00007646064,0.00019261491,0.000036812733],"domain_scores_gemma":[0.99911565,0.00042749124,0.00007769996,0.0000860385,0.00023267645,0.00006038504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011325144,0.00063018996,0.0008191141,0.0003235182,0.00040476923,0.0006193249,0.0015129441,0.0010124501,0.002425169],"category_scores_gemma":[0.0027384078,0.00036852833,0.00042461776,0.00033754666,0.00074102165,0.0009220431,0.0010366159,0.0011795784,0.0006709708],"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":[0.00012701152,0.000057655507,0.00054385397,0.00012651432,0.000051780782,0.00009111336,0.00007018833,0.8902762,0.0042966874,0.0306517,0.003304061,0.07040325],"study_design_scores_gemma":[0.000010612659,0.000009720778,0.000022734608,0.000002125688,0.000001412636,0.0000067148344,0.0000016158431,0.9970572,0.00025589415,0.0019692942,0.00066040177,0.0000022383156],"about_ca_topic_score_codex":0.0043497975,"about_ca_topic_score_gemma":0.0049924827,"teacher_disagreement_score":0.0043497975,"about_ca_system_score_codex":0.0007131281,"about_ca_system_score_gemma":0.0015095903,"threshold_uncertainty_score":0.008648932},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032355627,0.009419271,0.97340965,0.0016633217,0.00053389533,0.00003555404,0.00004712868,0.0001939659,0.011461623],"genre_scores_gemma":[0.395391,0.03972097,0.5413672,0.0013977535,0.0050331578,0.0004439163,0.00024555702,0.0006220599,0.015778452],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976579,0.0007684869,0.00013678668,0.00039354627,0.0009309605,0.00011225314],"domain_scores_gemma":[0.9959764,0.0024349324,0.00027230123,0.00048314236,0.000714301,0.000119069584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031894846,0.0011522598,0.0011207899,0.00085269584,0.0005584134,0.0019229503,0.0014307452,0.0011220835,0.002598748],"category_scores_gemma":[0.00819615,0.0005826553,0.0009400357,0.0012758638,0.0014943905,0.0026568577,0.0019520016,0.003306171,0.00087725505],"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":[0.000109308574,0.00007624377,0.0006900692,0.0006574433,0.000084607644,0.00012962468,0.00018147875,0.22452195,0.00368006,0.6457522,0.0069553554,0.11716163],"study_design_scores_gemma":[0.000041936364,0.000053953507,0.00024325651,0.00007272157,0.000028693512,0.00007435323,0.000023430892,0.73314244,0.0013176579,0.2355741,0.02940598,0.000021478932],"about_ca_topic_score_codex":0.0013389157,"about_ca_topic_score_gemma":0.0009482273,"teacher_disagreement_score":0.0031894846,"about_ca_system_score_codex":0.0011848283,"about_ca_system_score_gemma":0.0014361502,"threshold_uncertainty_score":0.016867816},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033730557,0.00057517615,0.9935354,0.0004745027,0.00007207245,0.000023656214,0.00006403779,0.00024863586,0.0016333907],"genre_scores_gemma":[0.25721094,0.0019613001,0.73062795,0.0007790696,0.00059025345,0.00030270658,0.0007049169,0.00076952914,0.007053308],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983734,0.0009227452,0.00006841077,0.00018127164,0.00034614664,0.00010800301],"domain_scores_gemma":[0.9931973,0.0049935826,0.0002924647,0.00056614063,0.00075699063,0.00019345823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033547366,0.0014009138,0.0016336443,0.00083501317,0.00049965625,0.0017281043,0.0018746814,0.0019300028,0.0031006564],"category_scores_gemma":[0.022473725,0.0008857293,0.00080215774,0.001201045,0.001926057,0.003215023,0.0024624832,0.0035678246,0.0010979354],"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":[0.0002443535,0.0001296459,0.0015008058,0.0003490282,0.00014272191,0.0001914515,0.0002471075,0.5521987,0.0025473319,0.31380475,0.02331962,0.1053245],"study_design_scores_gemma":[0.000020399926,0.000042700238,0.00009464793,0.00001892121,0.00001000401,0.000022720658,0.0000147246565,0.92665344,0.00044072038,0.07098819,0.0016861527,0.000007420076],"about_ca_topic_score_codex":0.0053240177,"about_ca_topic_score_gemma":0.006277763,"teacher_disagreement_score":0.0053240177,"about_ca_system_score_codex":0.00080394646,"about_ca_system_score_gemma":0.0016603864,"threshold_uncertainty_score":0.0177418},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013312222,0.00025611877,0.99702674,0.00015259343,0.00005585744,0.000046477602,0.000034878303,0.0005007456,0.00059538643],"genre_scores_gemma":[0.15988673,0.00096140156,0.83144367,0.0008298928,0.00030209275,0.00058799237,0.00055479544,0.0007748823,0.0046586148],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99824667,0.00072827365,0.00007524826,0.00029197376,0.0005126,0.00014530051],"domain_scores_gemma":[0.99699914,0.0017867059,0.0002009726,0.00034661,0.0005104077,0.00015620209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027864312,0.0018216089,0.0024167602,0.00073515065,0.0005673414,0.0015856504,0.0028078132,0.0020530685,0.0037225466],"category_scores_gemma":[0.012682485,0.0011447427,0.00096589205,0.00085917115,0.0017096569,0.0031327757,0.0024875943,0.003520426,0.0018029904],"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":[0.00029476476,0.00017040326,0.0013197778,0.0004791271,0.00018576349,0.00016757079,0.000070996044,0.71915877,0.005219581,0.08457777,0.014507776,0.17384776],"study_design_scores_gemma":[0.000024047806,0.00003201001,0.00006893391,0.000012950247,0.000008232282,0.00003112967,0.0000036913375,0.9877144,0.0007068454,0.010153808,0.0012306455,0.000013364848],"about_ca_topic_score_codex":0.0025596872,"about_ca_topic_score_gemma":0.003170655,"teacher_disagreement_score":0.0037225466,"about_ca_system_score_codex":0.0009223849,"about_ca_system_score_gemma":0.0028435034,"threshold_uncertainty_score":0.014736235},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008689672,0.00016408727,0.99005973,0.00017354822,0.000020658721,0.00002014311,0.00004213668,0.00020945973,0.00062057056],"genre_scores_gemma":[0.50609374,0.0005427082,0.48586026,0.00025701112,0.00011119921,0.00034894445,0.00045771158,0.00040214712,0.005926285],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999087,0.00044065548,0.00004120223,0.00015561857,0.00020836879,0.00006715385],"domain_scores_gemma":[0.99679226,0.0022222262,0.00035291704,0.00024797034,0.00026990907,0.00011473925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021417558,0.0012784604,0.001436354,0.0006180937,0.00045685473,0.0011025675,0.0014452526,0.0014527722,0.0013441663],"category_scores_gemma":[0.006860246,0.0007721124,0.0009726222,0.00081675244,0.001408378,0.001149283,0.0011923874,0.0018198211,0.000368391],"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":[0.000017129989,0.0000116347965,0.00018987236,0.00003587897,0.000019044333,0.000019534444,0.000016497253,0.98483557,0.00046451614,0.009746389,0.00023312109,0.0044107805],"study_design_scores_gemma":[0.0000011522334,0.000002528034,0.000011158391,0.0000012841178,6.316898e-7,0.0000015795099,7.660399e-7,0.998019,0.000052963547,0.0018302466,0.000077626224,0.0000010656904],"about_ca_topic_score_codex":0.009414146,"about_ca_topic_score_gemma":0.009551516,"teacher_disagreement_score":0.009414146,"about_ca_system_score_codex":0.0017138949,"about_ca_system_score_gemma":0.0022086862,"threshold_uncertainty_score":0.01871866},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039179735,0.00060456496,0.9441201,0.0012742763,0.00033794245,0.00007206225,0.00018352877,0.0046421182,0.00958557],"genre_scores_gemma":[0.6877358,0.00055080565,0.299794,0.00039732977,0.00028556527,0.0003772686,0.00057421025,0.00074905244,0.00953602],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993394,0.00016346679,0.0000307378,0.000103961516,0.00025859947,0.00010375323],"domain_scores_gemma":[0.9978375,0.0009638665,0.00012208607,0.00052113953,0.00040181793,0.00015369704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009924779,0.00071584474,0.0007899665,0.00057379954,0.0008225066,0.0009147287,0.0013987642,0.0008485868,0.0060294312],"category_scores_gemma":[0.006493226,0.00030569645,0.0004112441,0.0009791469,0.0007644723,0.0018605243,0.0022728064,0.0017373834,0.0017356665],"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":[0.00052510755,0.00031625014,0.002205912,0.00026337194,0.00009327133,0.0002127833,0.00042858068,0.56084067,0.016384436,0.10128539,0.028297478,0.2891468],"study_design_scores_gemma":[0.000024239653,0.00003788515,0.00012459722,0.000008661669,0.0000061929677,0.000021401682,0.000023948138,0.9685799,0.0024736463,0.025845751,0.002845909,0.000007811968],"about_ca_topic_score_codex":0.00315066,"about_ca_topic_score_gemma":0.00678359,"teacher_disagreement_score":0.0060294312,"about_ca_system_score_codex":0.0007366043,"about_ca_system_score_gemma":0.0014230629,"threshold_uncertainty_score":0.02017045},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017466543,0.001085909,0.9762256,0.0019007672,0.00008065101,0.000044317487,0.00028355065,0.00038064172,0.002531991],"genre_scores_gemma":[0.43014875,0.0024237896,0.53942966,0.0026200495,0.00074047496,0.0008422444,0.0024329398,0.0015722447,0.019789914],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970867,0.001981154,0.00008324012,0.0003884138,0.00029217708,0.00016831589],"domain_scores_gemma":[0.99098176,0.0069321147,0.0004909251,0.000702039,0.00061219494,0.00028092018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009220363,0.0025178983,0.0022983896,0.0012128917,0.000704166,0.0019597914,0.0030436188,0.0037036636,0.0036548944],"category_scores_gemma":[0.021539485,0.0012781365,0.0013129858,0.0012932128,0.0032486813,0.002937258,0.0036704524,0.0044437577,0.0009865189],"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":[0.00025107036,0.000098085686,0.0014934596,0.00027973152,0.00019220258,0.00024553284,0.00016960944,0.7792098,0.0016899357,0.18047392,0.0068711783,0.029025463],"study_design_scores_gemma":[0.000016953303,0.000018488428,0.00009914927,0.000024102304,0.0000092219925,0.000011938654,0.000009494227,0.9583347,0.00014800696,0.040687095,0.0006278247,0.000013124732],"about_ca_topic_score_codex":0.0088503705,"about_ca_topic_score_gemma":0.0087015275,"teacher_disagreement_score":0.009220363,"about_ca_system_score_codex":0.0019279472,"about_ca_system_score_gemma":0.0026781184,"threshold_uncertainty_score":0.0487625},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024683278,0.000333675,0.9701474,0.0002909111,0.000034691635,0.00003885382,0.000050629144,0.00014998332,0.004270637],"genre_scores_gemma":[0.65414923,0.0010805475,0.33217037,0.00033233187,0.00012831225,0.0002781217,0.00031770734,0.0004934959,0.011049911],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983444,0.0006796631,0.00008160348,0.00023359564,0.00050838303,0.0001522598],"domain_scores_gemma":[0.993049,0.004338576,0.00062866585,0.00066358247,0.0009810244,0.00033910532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004619303,0.0013385657,0.0013664315,0.001666618,0.0006715943,0.0016476725,0.0014842976,0.0013810568,0.0024999767],"category_scores_gemma":[0.018293006,0.00066427223,0.0011802837,0.0009973453,0.0031110279,0.0030766053,0.0025782702,0.0029811107,0.0005217549],"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":[0.000091098984,0.000039811108,0.0007869812,0.00014988678,0.000058723374,0.00013612304,0.00014582464,0.42347702,0.004073838,0.5489294,0.001420041,0.020691212],"study_design_scores_gemma":[0.000006155786,0.000033089287,0.0001495434,0.000015372501,0.000007310749,0.000023760515,0.000011153431,0.91364473,0.0011636727,0.08430521,0.00062881,0.000011173169],"about_ca_topic_score_codex":0.0019573253,"about_ca_topic_score_gemma":0.0013046402,"teacher_disagreement_score":0.004619303,"about_ca_system_score_codex":0.0017897314,"about_ca_system_score_gemma":0.0013884632,"threshold_uncertainty_score":0.0244295},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004373829,0.00016915522,0.9941526,0.00017976847,0.000032839365,0.000037540307,0.000022319495,0.0002257629,0.0008062225],"genre_scores_gemma":[0.35649085,0.00045621346,0.638489,0.00044455202,0.00018603064,0.00047840245,0.00023946988,0.00026488362,0.002950634],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99671364,0.0016810063,0.00013658503,0.00049245113,0.0007788881,0.00019744057],"domain_scores_gemma":[0.9884544,0.008991815,0.00051951525,0.0010728714,0.0006861363,0.0002753271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052199177,0.0013143439,0.0014672623,0.0009282646,0.0006856341,0.0012607402,0.0019828386,0.0013525597,0.00240636],"category_scores_gemma":[0.026578968,0.00077917526,0.00088552176,0.00096188666,0.0019529411,0.0021536937,0.002055841,0.0031776903,0.00063430076],"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":[0.0003096724,0.00021793492,0.0015246368,0.00025082388,0.0000876899,0.00011826317,0.00011892978,0.7350499,0.0038469622,0.16158012,0.0034181916,0.09347683],"study_design_scores_gemma":[0.000023365126,0.000027950877,0.00008119153,0.00000984074,0.000005145581,0.000015055391,0.0000038054047,0.97248095,0.00087843585,0.026085086,0.00038347792,0.000005704374],"about_ca_topic_score_codex":0.0024492329,"about_ca_topic_score_gemma":0.0034334245,"teacher_disagreement_score":0.0052199177,"about_ca_system_score_codex":0.0016802441,"about_ca_system_score_gemma":0.001896468,"threshold_uncertainty_score":0.027605891},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040288996,0.00022855023,0.9932653,0.00023618824,0.00005467375,0.0000234168,0.000027006166,0.00007809174,0.0020579381],"genre_scores_gemma":[0.43608284,0.0008825553,0.5404431,0.00035847782,0.00020851092,0.0004754445,0.00016871002,0.0005693654,0.020811012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987286,0.0006997424,0.000047069,0.00017842061,0.00026265954,0.00008353327],"domain_scores_gemma":[0.9945129,0.0042388574,0.00035541918,0.0002646339,0.00036897545,0.00025925026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048133056,0.0017275384,0.0027412314,0.0011764561,0.00064211455,0.002293592,0.0025059138,0.0027356748,0.0048732874],"category_scores_gemma":[0.013458636,0.0013223705,0.0012335118,0.0011339346,0.002352455,0.004129683,0.003911632,0.0032667331,0.00060522946],"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":[0.00011968746,0.000073356525,0.00014936613,0.00017461504,0.00006484985,0.000073607116,0.000046035104,0.68615675,0.001356831,0.3000727,0.0015398419,0.010172334],"study_design_scores_gemma":[0.000007137368,0.000011455713,0.00001672934,0.000009935616,0.000004792707,0.000006294435,0.000002082257,0.97573346,0.00019403311,0.02373352,0.00027545542,0.000005026724],"about_ca_topic_score_codex":0.0021600514,"about_ca_topic_score_gemma":0.0016741483,"teacher_disagreement_score":0.0048732874,"about_ca_system_score_codex":0.0013341728,"about_ca_system_score_gemma":0.0019680911,"threshold_uncertainty_score":0.025455475},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016716508,0.00011122858,0.99704295,0.00017361708,0.000027546816,0.000021434504,0.0000428378,0.0003142543,0.0005944925],"genre_scores_gemma":[0.24596547,0.0007942143,0.743158,0.0007646433,0.00033566286,0.00056969724,0.0007738659,0.0006374295,0.0070010307],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979965,0.001042839,0.00010825774,0.00033633586,0.00039451948,0.000121571145],"domain_scores_gemma":[0.9970293,0.0018700967,0.00023043419,0.00045643598,0.0003157605,0.00009785153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033731242,0.0015653,0.0017277359,0.0009471912,0.00047481197,0.001677649,0.002151024,0.0015421346,0.005383845],"category_scores_gemma":[0.016781216,0.001088697,0.0012845559,0.0012507483,0.0014355116,0.0031900865,0.0023378935,0.004113864,0.0021651953],"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":[0.00019032255,0.0001001853,0.000616848,0.00022676431,0.00015786437,0.00009184835,0.000104906016,0.65600896,0.0034966073,0.19103241,0.008451246,0.13952194],"study_design_scores_gemma":[0.000012510063,0.0000145784825,0.00005276767,0.000010488707,0.0000065375016,0.000011825284,0.0000037807195,0.96054626,0.00045931124,0.03811477,0.0007593507,0.0000078278945],"about_ca_topic_score_codex":0.0017100956,"about_ca_topic_score_gemma":0.0019773948,"teacher_disagreement_score":0.005383845,"about_ca_system_score_codex":0.0009272807,"about_ca_system_score_gemma":0.0014729376,"threshold_uncertainty_score":0.018010795},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04558682,0.00054988597,0.9256965,0.0011236051,0.00022824883,0.000037977894,0.00006678199,0.00028144036,0.026428673],"genre_scores_gemma":[0.87026864,0.00082554284,0.106121294,0.000547876,0.00015850225,0.00013540166,0.00009808599,0.00025803185,0.021586608],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994561,0.00016608053,0.000026108242,0.00014328606,0.00015405327,0.000054340202],"domain_scores_gemma":[0.9988024,0.0005452841,0.00016683553,0.00026681682,0.00014375978,0.00007493657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008609667,0.000367934,0.00044780923,0.00047131698,0.0006177868,0.0015791316,0.0011710554,0.0011399318,0.007821038],"category_scores_gemma":[0.0047685984,0.0002311983,0.00044736,0.00038236153,0.0018107789,0.004344531,0.0019332046,0.0015354223,0.00080391776],"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":[0.000046998714,0.000029309993,0.00022583685,0.000051134208,0.000020391211,0.00011477581,0.00010411351,0.042278875,0.004119191,0.91966397,0.0013277492,0.032017745],"study_design_scores_gemma":[0.000014660651,0.00008431972,0.00022665146,0.000025486732,0.000012564746,0.00022663192,0.000040880182,0.3193506,0.005048549,0.6661811,0.00876681,0.000021721697],"about_ca_topic_score_codex":0.0004541414,"about_ca_topic_score_gemma":0.00034134695,"teacher_disagreement_score":0.007821038,"about_ca_system_score_codex":0.0007552537,"about_ca_system_score_gemma":0.00042550432,"threshold_uncertainty_score":0.026164055},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081385456,0.0013577951,0.9036758,0.000784694,0.00038869478,0.00034022448,0.0003274562,0.0056263935,0.0061135315],"genre_scores_gemma":[0.80246407,0.00024020838,0.18841727,0.00059796334,0.00010469276,0.00043927843,0.0005520761,0.0004288964,0.0067555555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883693,0.00038637576,0.00006427129,0.00029839328,0.00016889717,0.00024515358],"domain_scores_gemma":[0.99719787,0.0011773898,0.00022568197,0.0006700365,0.00037690328,0.00035212436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018123741,0.0014520447,0.0017648813,0.0002809118,0.00077728526,0.00092988356,0.0030746274,0.0014986093,0.008271837],"category_scores_gemma":[0.0051341476,0.00051481376,0.0006275151,0.00041954374,0.0011912567,0.0017015233,0.0019668571,0.0020347065,0.0015406968],"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":[0.0017985742,0.0002966827,0.0016216519,0.000287634,0.000093347386,0.00016632529,0.0001483084,0.83916616,0.004983453,0.019197458,0.010987374,0.121253036],"study_design_scores_gemma":[0.00012619265,0.00015971258,0.00028685085,0.000013744976,0.000014131445,0.00004429196,0.000021773245,0.98664176,0.0016955486,0.0091459835,0.0018330322,0.000016941956],"about_ca_topic_score_codex":0.0044485065,"about_ca_topic_score_gemma":0.0052425656,"teacher_disagreement_score":0.008271837,"about_ca_system_score_codex":0.0010458834,"about_ca_system_score_gemma":0.0022491545,"threshold_uncertainty_score":0.027672052},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02329721,0.00032785657,0.9618472,0.0006132143,0.00016940806,0.00026691842,0.00013767026,0.00031831878,0.013022219],"genre_scores_gemma":[0.86979055,0.00030142226,0.115075834,0.00031323367,0.00016183539,0.00031639705,0.00012802477,0.00015017527,0.013762457],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964748,0.001170086,0.00013657653,0.00055566913,0.00088984286,0.0007729578],"domain_scores_gemma":[0.99663526,0.0017425308,0.00026245142,0.0005331366,0.0004366811,0.0003899313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031970371,0.0014953008,0.0023317614,0.000739097,0.0010963128,0.0034631472,0.0038585623,0.001769287,0.0074279895],"category_scores_gemma":[0.007404868,0.00067596557,0.0010617868,0.0013259636,0.00177379,0.0030455613,0.0030381181,0.0019243831,0.0011001424],"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":[0.00079703494,0.00042479168,0.0007446674,0.00029659737,0.000174683,0.000749537,0.00019961756,0.7511784,0.004885186,0.1657569,0.0075496566,0.06724299],"study_design_scores_gemma":[0.000060834354,0.000070211885,0.00013321322,0.000015438383,0.000019316449,0.00013301011,0.000037552087,0.9410842,0.0006433676,0.056158572,0.0016234086,0.000020869376],"about_ca_topic_score_codex":0.002208146,"about_ca_topic_score_gemma":0.002576119,"teacher_disagreement_score":0.0074279895,"about_ca_system_score_codex":0.0014841612,"about_ca_system_score_gemma":0.002017292,"threshold_uncertainty_score":0.024849117},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006799068,0.00013159236,0.9916768,0.00017080012,0.000035656834,0.000011804207,0.000014474697,0.000103305465,0.0010565423],"genre_scores_gemma":[0.5798909,0.000461673,0.412381,0.00030437554,0.00022227854,0.0002394438,0.00014128305,0.0003579839,0.0060011055],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946684,0.0002231768,0.000020182648,0.00009092717,0.00015176318,0.000047149322],"domain_scores_gemma":[0.99865735,0.0007788814,0.0001427802,0.00011710924,0.00022386774,0.00008012911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019621432,0.000825966,0.001090013,0.0005394619,0.00037938348,0.0010288659,0.0012544141,0.0012032378,0.0012669693],"category_scores_gemma":[0.0058443807,0.0005403179,0.0005748483,0.0005083539,0.0012703339,0.0015475161,0.0018069906,0.0014601988,0.00026825024],"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":[0.000048996964,0.00002895205,0.0003925932,0.00006376948,0.000049779897,0.00004459191,0.000037820995,0.8865,0.0020319673,0.084978275,0.0012397072,0.02458356],"study_design_scores_gemma":[0.0000018022847,0.0000044776907,0.0000130043,0.0000011887805,0.0000011441126,0.0000025831732,6.579824e-7,0.9930428,0.00013779842,0.00668677,0.00010628615,0.0000015258698],"about_ca_topic_score_codex":0.0018122457,"about_ca_topic_score_gemma":0.0012407635,"teacher_disagreement_score":0.0019621432,"about_ca_system_score_codex":0.0008676288,"about_ca_system_score_gemma":0.0010815875,"threshold_uncertainty_score":0.01037693},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31968722,0.0061876723,0.62530637,0.026318057,0.0009797137,0.00018714006,0.0005960074,0.0043158643,0.016421966],"genre_scores_gemma":[0.7969509,0.0024733075,0.19303213,0.002751652,0.0005707763,0.00013853953,0.00035268333,0.0012337912,0.0024962528],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973974,0.001253629,0.0001835854,0.00051598303,0.00040397132,0.00024533804],"domain_scores_gemma":[0.98245066,0.011139288,0.0011227723,0.0036917056,0.0010954171,0.00050017535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008216715,0.0007362559,0.0013399975,0.00040236497,0.00056546886,0.0015152213,0.0007964836,0.0025064454,0.0029843056],"category_scores_gemma":[0.05620421,0.000435901,0.00071484636,0.00050503155,0.0018216382,0.0046768147,0.0015206026,0.0019505268,0.0015002498],"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":[0.0013032269,0.0004065502,0.018236378,0.0012718757,0.0004179242,0.0004011724,0.0009853464,0.28074756,0.03442247,0.0749833,0.02808327,0.558741],"study_design_scores_gemma":[0.0002467552,0.0007502419,0.009504808,0.0006129811,0.00017775499,0.00046153672,0.0005866729,0.77204025,0.026131103,0.1756454,0.013741228,0.000101177386],"about_ca_topic_score_codex":0.0015994628,"about_ca_topic_score_gemma":0.0023847441,"teacher_disagreement_score":0.008216715,"about_ca_system_score_codex":0.0004544753,"about_ca_system_score_gemma":0.0012321884,"threshold_uncertainty_score":0.043454647},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003546384,0.004042644,0.9790467,0.0003688201,0.0005911976,0.00001944397,0.000048719947,0.0003485178,0.011987581],"genre_scores_gemma":[0.28548262,0.007202909,0.6116278,0.0004505877,0.0010858403,0.00028727992,0.00033547418,0.00095831044,0.0925692],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985516,0.000044055443,0.0000062617164,0.000024014742,0.0000567141,0.000013682339],"domain_scores_gemma":[0.99974114,0.00014831824,0.000013449449,0.00002547634,0.000061466686,0.000010153871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044409494,0.0007477996,0.00072673056,0.00029499255,0.00027115902,0.0006791697,0.001086897,0.0011148613,0.005932289],"category_scores_gemma":[0.0021732862,0.0003637005,0.00031229947,0.00072467414,0.00050607655,0.0011314588,0.0008294442,0.0020448316,0.0014268346],"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":[0.00008170403,0.00006189805,0.00017649162,0.00026508127,0.000059430797,0.00007413576,0.000039656934,0.5508263,0.005692964,0.10782359,0.025062773,0.30983597],"study_design_scores_gemma":[0.0000043535083,0.000008608224,0.00005895785,0.000014740643,0.000004695187,0.000015066968,0.0000022552342,0.9796952,0.00052664196,0.016355416,0.0033092108,0.000004906989],"about_ca_topic_score_codex":0.0020597568,"about_ca_topic_score_gemma":0.0027220713,"teacher_disagreement_score":0.005932289,"about_ca_system_score_codex":0.00057814294,"about_ca_system_score_gemma":0.0004137671,"threshold_uncertainty_score":0.019845545},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011576214,0.000703587,0.996097,0.00045424976,0.00010322455,0.00002468079,0.000019148747,0.00012582408,0.0013147476],"genre_scores_gemma":[0.1231734,0.0038710104,0.8608327,0.00084531197,0.0010192039,0.0005454324,0.00022565613,0.0005762625,0.008911054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979304,0.0009913865,0.000099481724,0.00021967795,0.0006742729,0.0000847755],"domain_scores_gemma":[0.9945741,0.003329057,0.00030086967,0.0007197006,0.0009058812,0.00017032193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048368685,0.0018627341,0.0017076414,0.0014676074,0.0006172801,0.0020645896,0.0020922648,0.002345027,0.0027590336],"category_scores_gemma":[0.016597271,0.00078756985,0.0010448113,0.0018179752,0.0028894066,0.0036994785,0.0030837392,0.006005548,0.001306633],"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":[0.00008738515,0.00010934891,0.00091188477,0.0003176654,0.00009685448,0.00010594013,0.00015925596,0.3054787,0.002209332,0.5421824,0.0068880315,0.14145322],"study_design_scores_gemma":[0.0000145219765,0.000035601843,0.00007300636,0.00002959335,0.0000070719675,0.00003276685,0.000007179938,0.9303614,0.00052850315,0.065337695,0.0035593358,0.000013324209],"about_ca_topic_score_codex":0.0017418134,"about_ca_topic_score_gemma":0.0017220523,"teacher_disagreement_score":0.0048368685,"about_ca_system_score_codex":0.0012442333,"about_ca_system_score_gemma":0.0017072838,"threshold_uncertainty_score":0.025580108},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.096258804,0.00032875102,0.8983929,0.00041959804,0.00017757887,0.00014746732,0.00012192009,0.0014247957,0.0027282878],"genre_scores_gemma":[0.87853086,0.00009493494,0.117743544,0.00017329586,0.000059412847,0.00023715668,0.00013789971,0.00011505986,0.0029079474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989341,0.0003792985,0.000044975004,0.00029646727,0.00016950179,0.00017567168],"domain_scores_gemma":[0.9962723,0.0019873579,0.00028932642,0.00068144617,0.0004316241,0.00033799207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022655074,0.0008432697,0.0010895935,0.00024270653,0.0005679227,0.00093805796,0.0021048186,0.001098392,0.0041234377],"category_scores_gemma":[0.0065263254,0.00041464192,0.0004394297,0.0003745904,0.0010747992,0.0014567933,0.0010906128,0.0019961104,0.00063703395],"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":[0.00066697807,0.00020001165,0.0007986341,0.00010106908,0.00003887007,0.00005967405,0.000067382854,0.9468088,0.0046727858,0.016682507,0.002183545,0.027719645],"study_design_scores_gemma":[0.000035158926,0.00005540958,0.000108328306,0.0000027332187,0.0000037575671,0.0000076254287,0.0000057744987,0.9939288,0.0010380571,0.0045367423,0.00027281253,0.0000048068996],"about_ca_topic_score_codex":0.003101629,"about_ca_topic_score_gemma":0.0032854322,"teacher_disagreement_score":0.0041234377,"about_ca_system_score_codex":0.0012528284,"about_ca_system_score_gemma":0.0017360598,"threshold_uncertainty_score":0.013794303},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027383778,0.0002870962,0.9686612,0.0007588999,0.000043017288,0.000034286102,0.00003318835,0.00021023846,0.0025883706],"genre_scores_gemma":[0.7966905,0.00065200607,0.19077954,0.00040259206,0.0001834331,0.0003296878,0.00019892324,0.00029890437,0.010464441],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991498,0.00040367714,0.000025456902,0.00011602702,0.00022367055,0.0000812764],"domain_scores_gemma":[0.9962012,0.002642379,0.00044273023,0.00020845106,0.00030456198,0.00020067354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026461668,0.0010824982,0.00093893235,0.0006428267,0.00061629777,0.0012880756,0.0014220909,0.0014857514,0.0018925869],"category_scores_gemma":[0.012693077,0.00063163496,0.0005792348,0.0005332761,0.0022503617,0.0020861707,0.0020493458,0.00180545,0.00036556268],"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":[0.00005506126,0.000032459728,0.0005746814,0.000053740438,0.00003237752,0.00007258832,0.00006465258,0.8793884,0.0011714558,0.10916408,0.0011777643,0.008212801],"study_design_scores_gemma":[0.0000036104645,0.0000062045515,0.00003703824,0.000002767814,9.653396e-7,0.0000038044636,0.0000020217267,0.9886573,0.00007414069,0.011085906,0.00012402455,0.0000021645676],"about_ca_topic_score_codex":0.0042868443,"about_ca_topic_score_gemma":0.0035488263,"teacher_disagreement_score":0.0042868443,"about_ca_system_score_codex":0.0013800117,"about_ca_system_score_gemma":0.0011358346,"threshold_uncertainty_score":0.013994396},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20114356,0.002162733,0.78782296,0.0021538073,0.00010069471,0.00008358161,0.00032932387,0.0006356168,0.0055676377],"genre_scores_gemma":[0.94638616,0.0014078919,0.0475188,0.00039268006,0.00009567019,0.00017124713,0.00039490667,0.00016094638,0.0034717273],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941444,0.00018285614,0.000048643546,0.000112581474,0.00016695097,0.000074615615],"domain_scores_gemma":[0.99039245,0.0069201216,0.0008914325,0.00078033627,0.00068838237,0.00032726783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025274244,0.0008965048,0.0010146792,0.0014003835,0.00073000405,0.0010781797,0.0013289681,0.0015002684,0.001985645],"category_scores_gemma":[0.02136985,0.00055282685,0.00074998336,0.00064548646,0.0031580506,0.0029088366,0.0021004095,0.0027377687,0.00020994515],"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":[0.00009486899,0.000031153206,0.0029686186,0.00019434988,0.000047466652,0.00031543573,0.00022770371,0.8733603,0.0033056485,0.104674965,0.0011535942,0.013625901],"study_design_scores_gemma":[0.0000043617533,0.0000124919925,0.0003269129,0.00001581885,0.000003026968,0.000020267553,0.0000087924,0.97212493,0.00041426579,0.026918096,0.00014526615,0.0000057384054],"about_ca_topic_score_codex":0.0043162573,"about_ca_topic_score_gemma":0.0034969721,"teacher_disagreement_score":0.0043162573,"about_ca_system_score_codex":0.0016327439,"about_ca_system_score_gemma":0.00095373933,"threshold_uncertainty_score":0.01336652},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015403288,0.00019460249,0.9961986,0.0002315652,0.00005404328,0.000032011525,0.000030888466,0.0003343946,0.0013835094],"genre_scores_gemma":[0.12542564,0.00070448493,0.86254215,0.00040217052,0.0003243025,0.00043070377,0.0003300828,0.00053079193,0.009309673],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984478,0.00039238072,0.000066255176,0.00017521763,0.00081603724,0.000102223814],"domain_scores_gemma":[0.9956944,0.00233652,0.00035335182,0.00077360123,0.00065071473,0.00019136308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016797163,0.0013367923,0.0011463428,0.0009085511,0.00053791486,0.001442245,0.0021255396,0.0015322012,0.0038616187],"category_scores_gemma":[0.008864637,0.0006586598,0.0009065031,0.0010469486,0.0014567744,0.0025350486,0.002906467,0.0039695785,0.0017743517],"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":[0.00026665023,0.00019214506,0.0008197485,0.00045297627,0.00009368029,0.00015827896,0.00032059802,0.5672393,0.011669218,0.15975544,0.012291678,0.24674039],"study_design_scores_gemma":[0.000022218472,0.000027256827,0.000042695545,0.0000115320145,0.0000044923977,0.00003294081,0.000009587072,0.98249936,0.0017036574,0.012790807,0.0028459383,0.000009561333],"about_ca_topic_score_codex":0.0029182602,"about_ca_topic_score_gemma":0.005285692,"teacher_disagreement_score":0.0038616187,"about_ca_system_score_codex":0.0011505958,"about_ca_system_score_gemma":0.0024582844,"threshold_uncertainty_score":0.012918353},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14643668,0.002662103,0.82737607,0.0051474874,0.00020604297,0.00014615359,0.00025828375,0.0010087478,0.016758373],"genre_scores_gemma":[0.94944227,0.0005534137,0.04729109,0.00053536944,0.000101491794,0.00011834424,0.0001387403,0.00025935483,0.0015598322],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935628,0.0034099692,0.00025414955,0.0011696455,0.001076774,0.00052659755],"domain_scores_gemma":[0.95784277,0.032199524,0.0027672634,0.0047889734,0.0014705686,0.00093087606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014995936,0.0011911659,0.0023736942,0.0012076659,0.0012137931,0.0047244774,0.0017264689,0.0026655584,0.0031329335],"category_scores_gemma":[0.1018435,0.00076927675,0.00090156874,0.0009444395,0.0032719232,0.009420582,0.0033343674,0.0050250487,0.0005655211],"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":[0.0004572823,0.00023868734,0.0055368724,0.00023801585,0.00018974794,0.00015159958,0.00033857665,0.5708395,0.0022095453,0.3543149,0.0027266438,0.062758535],"study_design_scores_gemma":[0.000027652404,0.00017840891,0.0011922991,0.000048789407,0.00002230438,0.000039265724,0.00005705539,0.78576154,0.00084468565,0.2108904,0.0009128501,0.000024744939],"about_ca_topic_score_codex":0.0029585923,"about_ca_topic_score_gemma":0.00213221,"teacher_disagreement_score":0.014995936,"about_ca_system_score_codex":0.002425235,"about_ca_system_score_gemma":0.002137601,"threshold_uncertainty_score":0.07930702},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07867648,0.0011544952,0.9131377,0.0010134454,0.000073299074,0.00004948325,0.000066673034,0.0002580637,0.005570401],"genre_scores_gemma":[0.8889048,0.0013163163,0.10597075,0.00030475354,0.00020627894,0.00020882896,0.00024819214,0.00023288712,0.0026070743],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983321,0.0005456288,0.00012877994,0.00029452168,0.00053775054,0.00016117953],"domain_scores_gemma":[0.98366064,0.011605213,0.0015508578,0.0013545146,0.0014140503,0.0004146115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046404717,0.0007698107,0.0009291158,0.001585193,0.0007214517,0.0016117332,0.0009515414,0.0015425157,0.0013495114],"category_scores_gemma":[0.02544168,0.0005356822,0.0010766274,0.00063938147,0.0029533696,0.0025712128,0.0022519233,0.0024876026,0.00023780006],"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":[0.000053966094,0.00003667569,0.0021862555,0.0001259766,0.00007561923,0.00011291844,0.00020012284,0.6155334,0.0031368106,0.35866085,0.0009343737,0.018943015],"study_design_scores_gemma":[0.0000043556283,0.00002051402,0.0003271373,0.000015862955,0.000006182938,0.000024714138,0.0000073949564,0.9344043,0.0003994244,0.06446875,0.0003131577,0.000008151833],"about_ca_topic_score_codex":0.0018403762,"about_ca_topic_score_gemma":0.0011801949,"teacher_disagreement_score":0.0046404717,"about_ca_system_score_codex":0.0017496204,"about_ca_system_score_gemma":0.0008611911,"threshold_uncertainty_score":0.024541497},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001138496,0.0006901874,0.99607855,0.00043279803,0.0001094766,0.000030729614,0.000021482047,0.0001291599,0.0013691377],"genre_scores_gemma":[0.12794603,0.0040294365,0.85527766,0.0009229755,0.00094295834,0.0006124223,0.00026006013,0.00065975636,0.009348622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976342,0.001088316,0.000118876,0.00025551778,0.00080339663,0.00009974323],"domain_scores_gemma":[0.9933559,0.0040676906,0.0003761832,0.0008147656,0.0011761073,0.00020934812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054555116,0.002110211,0.0019032257,0.0015359839,0.00067439035,0.0023146516,0.0022231755,0.0025470317,0.0032352742],"category_scores_gemma":[0.020253329,0.00086282357,0.0011558507,0.0017496428,0.002764033,0.0038603588,0.0033639292,0.006530232,0.0014207215],"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":[0.00009697506,0.00012421267,0.0011695513,0.00036923075,0.00010201635,0.00013802838,0.00018834654,0.35253936,0.0024684332,0.50164986,0.0072590597,0.13389495],"study_design_scores_gemma":[0.000013828361,0.000036621757,0.00007067759,0.00003223526,0.000006788209,0.00003440637,0.000007593963,0.94192636,0.00043060989,0.054394133,0.0030337048,0.000012987484],"about_ca_topic_score_codex":0.0019427432,"about_ca_topic_score_gemma":0.0020701657,"teacher_disagreement_score":0.0054555116,"about_ca_system_score_codex":0.0012622481,"about_ca_system_score_gemma":0.002005366,"threshold_uncertainty_score":0.028851807},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00090232684,0.000052271895,0.9984792,0.00005964209,0.00002384154,0.000016520318,0.000014778864,0.00024315587,0.0002082742],"genre_scores_gemma":[0.113946,0.00023956448,0.88288933,0.0002382228,0.0002211556,0.0003443421,0.00026958677,0.00039764732,0.0014542493],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99639386,0.0017099986,0.00017599213,0.0006185053,0.0009429285,0.00015868784],"domain_scores_gemma":[0.9894918,0.007020532,0.0008227081,0.0012158293,0.001225981,0.00022317898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055194204,0.0016724182,0.0022776339,0.0014232532,0.0007283113,0.0016500353,0.0027908285,0.0016240808,0.0023084371],"category_scores_gemma":[0.02872387,0.0011086836,0.0011783369,0.001376269,0.0018835848,0.0025701516,0.0026513694,0.0034775832,0.0011433542],"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":[0.000103127015,0.00014882161,0.0014187262,0.00018198756,0.00020006095,0.00015262303,0.000105673025,0.7113774,0.0038763671,0.1227767,0.0044229855,0.1552356],"study_design_scores_gemma":[0.000011377983,0.00001721255,0.000070542985,0.000005771065,0.0000046077334,0.00001428941,0.0000023833995,0.9825256,0.00038023852,0.016405411,0.00055398344,0.000008684621],"about_ca_topic_score_codex":0.004439688,"about_ca_topic_score_gemma":0.0045696306,"teacher_disagreement_score":0.0055194204,"about_ca_system_score_codex":0.001035512,"about_ca_system_score_gemma":0.0031558299,"threshold_uncertainty_score":0.029189825},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015163686,0.00017836492,0.98099935,0.00015159001,0.00007492608,0.00005253585,0.00003211939,0.0022101414,0.0011372672],"genre_scores_gemma":[0.600266,0.00022640244,0.39264053,0.00030856475,0.00015439531,0.00035782903,0.00036380804,0.00046275684,0.0052196956],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930155,0.00016032116,0.000043090142,0.00018175674,0.00021766798,0.000095625466],"domain_scores_gemma":[0.99916685,0.0002910636,0.00008847619,0.00022212598,0.00014327532,0.000088140834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011224995,0.0009177732,0.0011358643,0.00035554013,0.00058847334,0.0005875189,0.0018152257,0.000765622,0.0024227004],"category_scores_gemma":[0.0024405618,0.0004259979,0.00045617434,0.00058393733,0.00069783954,0.0013345045,0.002022063,0.0013286498,0.00081707316],"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":[0.0007896101,0.00032087765,0.0020733816,0.00022182394,0.000098434146,0.00023555153,0.00028297133,0.5344444,0.01943559,0.012286129,0.010970029,0.41884118],"study_design_scores_gemma":[0.00005733607,0.0000759518,0.00016867397,0.000004554687,0.000007845612,0.00003037879,0.000015526404,0.99411327,0.0023911046,0.0018850169,0.0012435092,0.000006783695],"about_ca_topic_score_codex":0.0039568334,"about_ca_topic_score_gemma":0.0051116385,"teacher_disagreement_score":0.0039568334,"about_ca_system_score_codex":0.00046097508,"about_ca_system_score_gemma":0.0022081672,"threshold_uncertainty_score":0.008104682},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013388342,0.00019476922,0.99717194,0.00011727545,0.000046290872,0.000039259736,0.000029622795,0.00066472695,0.0003973436],"genre_scores_gemma":[0.14231826,0.0005680799,0.851475,0.0006731177,0.00021354611,0.00044926582,0.0004206515,0.0007470563,0.0031351147],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983948,0.0006402294,0.00007614816,0.00027772988,0.00047968706,0.00013145847],"domain_scores_gemma":[0.9975569,0.0013218599,0.00018996546,0.00032217312,0.0004549305,0.0001541336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027661447,0.0015715931,0.0022219117,0.0007618073,0.00046161137,0.0014613597,0.0028047492,0.0022542623,0.0031640488],"category_scores_gemma":[0.010965952,0.0010876023,0.0008624257,0.00075565255,0.001329505,0.0028437166,0.0025315941,0.0032134678,0.0015055198],"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":[0.00032996087,0.00019593546,0.0016449044,0.0004388384,0.00021367053,0.00016052049,0.000068319845,0.6626197,0.007300809,0.061334644,0.014320182,0.25137243],"study_design_scores_gemma":[0.000023136685,0.00003184157,0.00007579133,0.0000094695215,0.0000072635607,0.00003099413,0.0000026605778,0.9907432,0.0009035403,0.007054666,0.0011049904,0.000012434626],"about_ca_topic_score_codex":0.0021748936,"about_ca_topic_score_gemma":0.002506233,"teacher_disagreement_score":0.0031640488,"about_ca_system_score_codex":0.00082518405,"about_ca_system_score_gemma":0.0023271502,"threshold_uncertainty_score":0.014628947},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017355746,0.0005399767,0.97891974,0.0005290939,0.00011976874,0.000059376845,0.0001302942,0.0009144469,0.0014315486],"genre_scores_gemma":[0.6711597,0.00074364484,0.31807706,0.0007298661,0.0003832827,0.00040635685,0.0009811565,0.0003380486,0.0071808035],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986792,0.0004941866,0.000084249725,0.00030117054,0.0002941847,0.0001469389],"domain_scores_gemma":[0.9972447,0.0015073863,0.00021258749,0.00026113994,0.00060067885,0.0001735562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026359542,0.0013507754,0.001967929,0.0005781118,0.00077583967,0.0011725539,0.0021653487,0.0015682158,0.002262148],"category_scores_gemma":[0.008251673,0.0009497034,0.000909214,0.0009243719,0.001143357,0.0012545891,0.0014086035,0.0023646995,0.0010101036],"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":[0.00011798262,0.00006768707,0.0008537696,0.00007852227,0.000058480597,0.00006159993,0.00004955593,0.95708776,0.00088418473,0.008753443,0.0029385989,0.029048368],"study_design_scores_gemma":[0.000006546652,0.000007363604,0.000046462337,0.0000017694421,0.0000020529803,0.000002638916,0.0000015313653,0.99750465,0.00006798978,0.0022014945,0.00015543347,0.0000020916339],"about_ca_topic_score_codex":0.012184085,"about_ca_topic_score_gemma":0.011671621,"teacher_disagreement_score":0.012184085,"about_ca_system_score_codex":0.0012242525,"about_ca_system_score_gemma":0.0018326098,"threshold_uncertainty_score":0.024226308},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015786434,0.00020843679,0.98224497,0.0002276453,0.000040701478,0.000044392593,0.000035702476,0.0003350285,0.0010765803],"genre_scores_gemma":[0.60642576,0.0004290037,0.38932413,0.0002813263,0.00009193294,0.00020303756,0.00020097972,0.0001688886,0.0028749711],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99949,0.00012952344,0.000042970387,0.00007059261,0.00022164988,0.000045238936],"domain_scores_gemma":[0.9980348,0.0011710791,0.0001567548,0.00027415046,0.00027769833,0.00008549196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016817221,0.0006918095,0.00095116766,0.00049835915,0.00042288547,0.0010704803,0.00074880896,0.00084819074,0.0012566077],"category_scores_gemma":[0.006766446,0.00039673096,0.0003376199,0.0005767148,0.0013616509,0.0013900991,0.0016481432,0.0012674526,0.00029286172],"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":[0.00019962825,0.00006598623,0.001427117,0.00014443374,0.000034434543,0.00014660852,0.0001569426,0.82094115,0.009338035,0.036438752,0.0018244577,0.12928244],"study_design_scores_gemma":[0.0000071512,0.000025085255,0.00005307389,0.000005464436,0.0000021175406,0.000017598451,0.0000048975135,0.99425924,0.0014460598,0.0038237793,0.00035213825,0.0000033223325],"about_ca_topic_score_codex":0.0021195486,"about_ca_topic_score_gemma":0.002638829,"teacher_disagreement_score":0.0021195486,"about_ca_system_score_codex":0.0007706904,"about_ca_system_score_gemma":0.0015883597,"threshold_uncertainty_score":0.008893847},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023727715,0.00040155294,0.96827996,0.00079241703,0.00013759248,0.00005070412,0.00015243671,0.00055239705,0.005905148],"genre_scores_gemma":[0.8089463,0.0003152645,0.1804537,0.00048864295,0.00009005103,0.00013694212,0.00033798118,0.00014505604,0.009086006],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993944,0.00019995177,0.000023001832,0.0001396931,0.00014514555,0.00009784653],"domain_scores_gemma":[0.99882704,0.00057920127,0.00009346439,0.00018540911,0.00023685164,0.00007807038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009793334,0.00061152474,0.000896325,0.0002754377,0.00038974817,0.0010829706,0.0011682331,0.0011731829,0.0032502336],"category_scores_gemma":[0.004917146,0.00034298905,0.00030053212,0.0004482763,0.0011926003,0.001378656,0.0012933121,0.00127477,0.00060657645],"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":[0.00020750947,0.000053842163,0.00077927933,0.000096689066,0.00003523994,0.00012575346,0.00008182357,0.8748587,0.002133836,0.0844631,0.005287751,0.031876493],"study_design_scores_gemma":[0.000013713005,0.000016233598,0.000055012635,0.0000037982004,0.000002299622,0.000009007052,0.000006446769,0.9859035,0.00029241675,0.013143215,0.000551373,0.0000029930552],"about_ca_topic_score_codex":0.0047525894,"about_ca_topic_score_gemma":0.004737149,"teacher_disagreement_score":0.0047525894,"about_ca_system_score_codex":0.0014893167,"about_ca_system_score_gemma":0.0016340619,"threshold_uncertainty_score":0.010873139},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026357993,0.00030012513,0.9943995,0.00035661785,0.00025710824,0.000032568252,0.000027643799,0.00030376628,0.0016869791],"genre_scores_gemma":[0.20442459,0.00086363376,0.77157706,0.0006329553,0.00062900956,0.00048605996,0.0003018343,0.00085494405,0.020229936],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978283,0.0010655759,0.00014225452,0.00031050865,0.00051647186,0.0001368599],"domain_scores_gemma":[0.9936028,0.0038561977,0.00029985007,0.00070704514,0.0012775977,0.00025641496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044571245,0.001404714,0.0025312954,0.00097262545,0.0009689097,0.0020967028,0.0026819115,0.004016095,0.005822189],"category_scores_gemma":[0.017755749,0.0013572075,0.0012067581,0.00152592,0.0018431523,0.0031861963,0.0025207994,0.004929794,0.0031267044],"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":[0.00018849967,0.00018403353,0.0003536572,0.0002129706,0.00012343684,0.00008196337,0.00004965113,0.76314753,0.002028821,0.13658394,0.009800442,0.08724492],"study_design_scores_gemma":[0.000013671456,0.000015370879,0.00002262577,0.0000067841265,0.0000050854824,0.000009709346,0.0000012905115,0.99033266,0.00023776469,0.008746474,0.00060205173,0.0000065567906],"about_ca_topic_score_codex":0.0038253048,"about_ca_topic_score_gemma":0.0031194657,"teacher_disagreement_score":0.005822189,"about_ca_system_score_codex":0.0011855362,"about_ca_system_score_gemma":0.0028605529,"threshold_uncertainty_score":0.023571849},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011951149,0.00017773312,0.9859855,0.00020479951,0.000038227936,0.000040022784,0.000030134068,0.00016104881,0.001411497],"genre_scores_gemma":[0.5350877,0.00050079526,0.4567768,0.00027973796,0.00010567358,0.00036828715,0.00021171039,0.00028329977,0.006385949],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908483,0.00037250985,0.000050691582,0.000165545,0.00025615646,0.000070175694],"domain_scores_gemma":[0.9971269,0.0017177961,0.0001996216,0.00040502427,0.00040352988,0.00014719146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002378926,0.0009623702,0.0011205422,0.0007638984,0.00041024014,0.0010066201,0.0014690924,0.0010493146,0.0027134407],"category_scores_gemma":[0.008951422,0.0004204245,0.00079688564,0.00066039275,0.001848932,0.0016329723,0.0021024814,0.002004822,0.00065312954],"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":[0.00023555578,0.00013060898,0.0021294365,0.00020148481,0.00010760089,0.0001702457,0.00012838264,0.7003689,0.0065939664,0.20657226,0.0025818737,0.080779724],"study_design_scores_gemma":[0.000008987123,0.000039556428,0.00007425614,0.0000064820338,0.0000033467738,0.0000124509115,0.0000046503387,0.98249096,0.00065084593,0.016364178,0.00033832277,0.00000595188],"about_ca_topic_score_codex":0.0020326898,"about_ca_topic_score_gemma":0.0019193772,"teacher_disagreement_score":0.0027134407,"about_ca_system_score_codex":0.0008159621,"about_ca_system_score_gemma":0.0013597537,"threshold_uncertainty_score":0.01258111},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003479856,0.00013160717,0.9952743,0.00013113796,0.00003027037,0.000027647278,0.00001671848,0.00021691463,0.0006914332],"genre_scores_gemma":[0.18871303,0.00033767777,0.8064581,0.00051587005,0.00013275945,0.00032436813,0.0002117924,0.00032688284,0.0029794418],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850684,0.00058310095,0.00007639478,0.0002961032,0.00043293266,0.00010454794],"domain_scores_gemma":[0.995609,0.0027327917,0.00039636117,0.0004245454,0.0006287079,0.00020858437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032311606,0.0018113599,0.0011411487,0.0008396507,0.00041640276,0.0011629675,0.00216132,0.0021873135,0.0014032645],"category_scores_gemma":[0.014271264,0.00076931313,0.000977633,0.00070171984,0.0018177701,0.0014194254,0.002725685,0.0026940373,0.0008524379],"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":[0.0001467451,0.00011187663,0.000851272,0.00022136261,0.000078812234,0.00008382833,0.00010428018,0.9059244,0.006672885,0.04307381,0.0024689618,0.040261697],"study_design_scores_gemma":[0.0000107519345,0.000024682478,0.000043050375,0.0000074528766,0.000002943873,0.000009991577,0.0000027686344,0.993718,0.0005575751,0.0051648873,0.0004541013,0.0000036622628],"about_ca_topic_score_codex":0.0036783656,"about_ca_topic_score_gemma":0.0032717148,"teacher_disagreement_score":0.0036783656,"about_ca_system_score_codex":0.0012704906,"about_ca_system_score_gemma":0.002273399,"threshold_uncertainty_score":0.017088234},"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":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00061797263,0.0004133271,0.06420783,0.00048249844,0.0004484698,0.00017434394,0.02505024,0.86412275,0.044482578],"genre_scores_gemma":[0.016705923,0.00054011267,0.06781213,0.0011660766,0.00017723053,0.00062117283,0.058677595,0.78848356,0.0658162],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986149,0.00015889421,0.00009189998,0.0002855438,0.0005767252,0.00027201526],"domain_scores_gemma":[0.99774796,0.00058348355,0.00008920447,0.00074870983,0.00060856744,0.00022197497],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022195978,0.0038449082,0.0019987614,0.0019726625,0.000719401,0.004737747,0.00814004,0.0033111933,0.50726116],"category_scores_gemma":[0.011622614,0.003977745,0.002695389,0.0017016302,0.0009154275,0.0034810218,0.004546973,0.005136223,0.54631627],"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":[0.00020841729,0.00006625613,0.00039570945,0.0004954021,0.00008136868,0.0000588632,0.00006595158,0.0021694105,0.0008707747,0.0049407817,0.95597106,0.03467597],"study_design_scores_gemma":[0.0007746999,0.00008456153,0.0008703028,0.00044623247,0.00008434551,0.00021265053,0.00007382653,0.041678544,0.016136412,0.02261764,0.9168273,0.00019348538],"about_ca_topic_score_codex":0.006745565,"about_ca_topic_score_gemma":0.007964639,"teacher_disagreement_score":0.50726116,"about_ca_system_score_codex":0.0020769148,"about_ca_system_score_gemma":0.0019379836,"threshold_uncertainty_score":0.7028321},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2637206,0.001698096,0.7263146,0.00051059056,0.00014427665,0.000052257477,0.00010358848,0.0012131614,0.006242894],"genre_scores_gemma":[0.9191012,0.00042418664,0.07735768,0.0001382442,0.00001850666,0.000047844947,0.00008414237,0.000058835583,0.0027693359],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995321,0.00009698722,0.000029838218,0.000088620356,0.00018928172,0.00006321415],"domain_scores_gemma":[0.9990903,0.00034673463,0.00015010725,0.00014038206,0.00023406465,0.000038416518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064337096,0.00041458104,0.00054511736,0.0004894079,0.00030546452,0.00071266637,0.0012034423,0.0005821313,0.0011470775],"category_scores_gemma":[0.0020282133,0.00023889358,0.0002978735,0.0006651395,0.00054718606,0.0012433123,0.0006857442,0.0007574485,0.00018506104],"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":[0.000341802,0.00006849659,0.00056406425,0.00008797099,0.000051833187,0.000045036206,0.000048043865,0.9067388,0.011863899,0.017549198,0.00064673333,0.06199413],"study_design_scores_gemma":[0.0000061977416,0.000049759496,0.00014866935,0.0000044551384,0.000006248943,0.000014319313,0.000005007041,0.9929097,0.0037984657,0.002767891,0.00028359125,0.0000055940845],"about_ca_topic_score_codex":0.0036800648,"about_ca_topic_score_gemma":0.003949999,"teacher_disagreement_score":0.0036800648,"about_ca_system_score_codex":0.001223967,"about_ca_system_score_gemma":0.0009430337,"threshold_uncertainty_score":0.008880556},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02733874,0.00082866603,0.96839094,0.0009549838,0.000068327405,0.00004324902,0.000061949584,0.000253711,0.0020594245],"genre_scores_gemma":[0.813396,0.0015700364,0.17791916,0.00094081333,0.00027745447,0.00036633946,0.0004640733,0.0005698808,0.004496295],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769956,0.00091313507,0.00011452575,0.00044975817,0.0006479192,0.00017504042],"domain_scores_gemma":[0.95206213,0.037938606,0.002949393,0.0025355676,0.003524125,0.000990143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0101731485,0.0010859098,0.0017534816,0.0015032284,0.0007131667,0.00162008,0.0023972988,0.0018961827,0.0021887335],"category_scores_gemma":[0.07797807,0.00072852755,0.0009925398,0.0008916657,0.0046219653,0.0037787133,0.0032667753,0.003405843,0.00043319707],"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":[0.00029018102,0.000118867545,0.009208984,0.0004683052,0.00017437723,0.0003905211,0.00035806236,0.5617547,0.00556754,0.3877644,0.0032127283,0.030691339],"study_design_scores_gemma":[0.000011775174,0.000043532575,0.00047391615,0.000042863718,0.000010649515,0.00004769665,0.000017757191,0.9383215,0.0008552912,0.059765596,0.0003954242,0.000014035231],"about_ca_topic_score_codex":0.0024714237,"about_ca_topic_score_gemma":0.001661167,"teacher_disagreement_score":0.0101731485,"about_ca_system_score_codex":0.0021421849,"about_ca_system_score_gemma":0.0020135543,"threshold_uncertainty_score":0.053801358},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27048987,0.0038058385,0.70138013,0.005813014,0.00032491898,0.000082543826,0.0008554594,0.0010021183,0.016246067],"genre_scores_gemma":[0.962423,0.0015399838,0.020264156,0.0005736942,0.0002855306,0.00011313927,0.0006338055,0.00036961777,0.013797087],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993649,0.00029475693,0.000032299402,0.00011210054,0.00011750188,0.00007846056],"domain_scores_gemma":[0.9863236,0.010027543,0.0010743721,0.0009865628,0.00069951173,0.0008885215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026487291,0.00079605833,0.0011546996,0.0011718314,0.00058134313,0.0017246314,0.0014416265,0.0017574581,0.003919196],"category_scores_gemma":[0.029864352,0.0007002051,0.00057727465,0.00071395864,0.0031605358,0.0036201954,0.0023632455,0.0027273253,0.00047064805],"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":[0.0001759861,0.00004440702,0.0033446,0.0002378017,0.00007941474,0.0004650841,0.00028737096,0.42540088,0.0023019852,0.5452129,0.0057101455,0.0167394],"study_design_scores_gemma":[0.000009795142,0.000017504079,0.0006345503,0.000028867826,0.000006350303,0.00004678356,0.000017382741,0.80091584,0.00035451172,0.19740829,0.00054496893,0.000015206733],"about_ca_topic_score_codex":0.003190822,"about_ca_topic_score_gemma":0.0035705534,"teacher_disagreement_score":0.003919196,"about_ca_system_score_codex":0.00173452,"about_ca_system_score_gemma":0.0008603098,"threshold_uncertainty_score":0.014007986},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04749593,0.0023448416,0.9399139,0.0021882232,0.000100829755,0.00003858789,0.000046052326,0.00037627935,0.0074953153],"genre_scores_gemma":[0.8047216,0.0025485698,0.18027546,0.0009101837,0.00032672676,0.00015065105,0.00014761931,0.0011111306,0.00980797],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975414,0.0012185685,0.00011025717,0.0003744058,0.00060187554,0.00015351873],"domain_scores_gemma":[0.9752431,0.019509885,0.0012473505,0.0018425628,0.0016200256,0.00053708925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070174816,0.0015779149,0.0014060537,0.0010967641,0.0005480985,0.001766833,0.0014402268,0.0022148676,0.0029331802],"category_scores_gemma":[0.05074471,0.00081174914,0.0013157274,0.0007636633,0.004028908,0.004704736,0.003057334,0.0039906404,0.00072780106],"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":[0.00027272204,0.0001596265,0.003991127,0.0005592543,0.00019053445,0.0006060658,0.0006657375,0.45935827,0.010097332,0.4463419,0.0039875493,0.07376992],"study_design_scores_gemma":[0.000013220017,0.00013579371,0.0007237653,0.000081537444,0.000014220063,0.00011513644,0.00004790981,0.90955883,0.0019591711,0.085842185,0.0014781036,0.000030137599],"about_ca_topic_score_codex":0.0016502324,"about_ca_topic_score_gemma":0.00079662475,"teacher_disagreement_score":0.0070174816,"about_ca_system_score_codex":0.0007778918,"about_ca_system_score_gemma":0.00078100053,"threshold_uncertainty_score":0.037112415},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011541965,0.00014457868,0.98665226,0.00020787923,0.000047297213,0.000015662668,0.000015277741,0.000102113954,0.0012729368],"genre_scores_gemma":[0.67382276,0.00030681814,0.32029384,0.00027719318,0.00016659626,0.00018039205,0.000109741864,0.00021945557,0.004623212],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999522,0.00019441223,0.00001984289,0.00008562728,0.00013133792,0.000046831497],"domain_scores_gemma":[0.9988638,0.0006126305,0.00012435447,0.00009367022,0.0002289245,0.00007657297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018971883,0.0006989131,0.0011202701,0.00049164594,0.00039460268,0.00087064446,0.001179233,0.0010754839,0.0012284325],"category_scores_gemma":[0.004350161,0.00045166007,0.0005609617,0.0004579131,0.0011688465,0.0013499594,0.0015989176,0.001206323,0.00018769395],"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":[0.000060175375,0.000031613905,0.00043751037,0.00006174697,0.000049342347,0.00004464866,0.000031140786,0.9094111,0.0026349318,0.062125135,0.0011272833,0.023985343],"study_design_scores_gemma":[0.000001470396,0.0000046045925,0.000013043603,7.908316e-7,9.989566e-7,0.0000022236075,4.868995e-7,0.9967359,0.000115569346,0.0030546293,0.00006907874,0.0000012311905],"about_ca_topic_score_codex":0.002210887,"about_ca_topic_score_gemma":0.0012651224,"teacher_disagreement_score":0.002210887,"about_ca_system_score_codex":0.0008823058,"about_ca_system_score_gemma":0.0010931576,"threshold_uncertainty_score":0.010033369},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060837315,0.00017957426,0.99272823,0.000191086,0.000011678106,0.000030578394,0.000030725783,0.00013556785,0.00060883316],"genre_scores_gemma":[0.46310395,0.00086810085,0.531521,0.00034324525,0.00012139873,0.0007602269,0.00061733526,0.00032920192,0.0023354993],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969253,0.0014985921,0.00015135443,0.00045663153,0.0007946577,0.00017337852],"domain_scores_gemma":[0.9741018,0.021184834,0.0011976211,0.0017754196,0.001365754,0.0003746512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009381009,0.0017005516,0.002023089,0.00119421,0.00091363344,0.0017664294,0.0024996889,0.0022686883,0.0014620299],"category_scores_gemma":[0.04587028,0.0009688626,0.0015816204,0.0014712246,0.002290162,0.0030165107,0.0030041416,0.004228982,0.0004160877],"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":[0.0001096333,0.00009893612,0.001306084,0.00015195248,0.00010238887,0.00007054548,0.0001203043,0.8794118,0.0012987191,0.09261483,0.0007436489,0.023971094],"study_design_scores_gemma":[0.0000061334317,0.000015787533,0.00006857595,0.00000747102,0.0000038477983,0.000009287315,0.000004853675,0.9852748,0.00025454233,0.014210311,0.00014114725,0.0000031991133],"about_ca_topic_score_codex":0.0050354875,"about_ca_topic_score_gemma":0.0039770342,"teacher_disagreement_score":0.009381009,"about_ca_system_score_codex":0.002143906,"about_ca_system_score_gemma":0.0030343926,"threshold_uncertainty_score":0.049612105},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031573938,0.00022122027,0.9932401,0.00017427914,0.00006156971,0.000033398497,0.000027180457,0.00015596692,0.0029287715],"genre_scores_gemma":[0.47401208,0.0010690517,0.51230973,0.0004464374,0.00018067202,0.00040779266,0.00020807888,0.00023514719,0.011131027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990771,0.00032395107,0.000043018677,0.00015517038,0.00028877228,0.00011194937],"domain_scores_gemma":[0.99844486,0.0008876325,0.00010091086,0.00022046256,0.00028625608,0.000059884715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010581263,0.00084265316,0.0007004401,0.0004719763,0.00048382717,0.0010462815,0.0009665553,0.0010128635,0.0027982993],"category_scores_gemma":[0.004848724,0.0002799853,0.00034707587,0.0009883337,0.0013513596,0.0013455247,0.0013322352,0.0017637468,0.000747987],"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":[0.00013339467,0.000052967207,0.00025908469,0.00018654524,0.000028324817,0.0001214577,0.00013453349,0.53506804,0.006692468,0.36817068,0.0053343195,0.08381819],"study_design_scores_gemma":[0.000015788493,0.00002657139,0.000033471355,0.000015607053,0.00000556974,0.00003010106,0.000012062289,0.9222854,0.0015595165,0.07302684,0.0029789964,0.000010133103],"about_ca_topic_score_codex":0.002241911,"about_ca_topic_score_gemma":0.0024213907,"teacher_disagreement_score":0.0027982993,"about_ca_system_score_codex":0.0015468936,"about_ca_system_score_gemma":0.0017637351,"threshold_uncertainty_score":0.011223495},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056551263,0.0002766418,0.93880874,0.00028370414,0.00003814758,0.00007073778,0.000031042287,0.00017305464,0.00376671],"genre_scores_gemma":[0.76469046,0.00037081886,0.23057856,0.00012945596,0.000039481838,0.00021264805,0.00005766567,0.0000925616,0.0038283428],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991352,0.00038025464,0.00002913908,0.00009082162,0.00023162935,0.0001328832],"domain_scores_gemma":[0.99739754,0.0017970043,0.00017820219,0.00026867518,0.00026459782,0.00009395756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011947852,0.00051115145,0.00057527394,0.00029004636,0.00040713372,0.0006172101,0.00068342226,0.00048676785,0.001355019],"category_scores_gemma":[0.006096481,0.0002855803,0.00017729303,0.0005999371,0.0012908231,0.0010378764,0.0010046809,0.00073524064,0.00027670397],"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":[0.00025151207,0.00004823573,0.00028470418,0.00011930319,0.000013528813,0.000080846155,0.00010624159,0.86063015,0.008411009,0.09321477,0.0010510217,0.035788592],"study_design_scores_gemma":[0.000019267853,0.0000345848,0.000041425363,0.000008332012,0.0000032273629,0.000012026163,0.000010423114,0.9765951,0.0019546377,0.02074474,0.00057164003,0.000004669825],"about_ca_topic_score_codex":0.0019899397,"about_ca_topic_score_gemma":0.0026687612,"teacher_disagreement_score":0.0019899397,"about_ca_system_score_codex":0.0010073786,"about_ca_system_score_gemma":0.0019109988,"threshold_uncertainty_score":0.007309079},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011060371,0.002786179,0.961844,0.00056913495,0.0008330851,0.00012984725,0.00035988877,0.002261202,0.030110657],"genre_scores_gemma":[0.0693767,0.007823968,0.81446534,0.001117216,0.0014242351,0.0009101023,0.002258268,0.004166923,0.0984573],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984976,0.00030103655,0.00009551237,0.0003095185,0.0006786118,0.000117784104],"domain_scores_gemma":[0.9984964,0.0005426631,0.0000903149,0.00040527762,0.0003673919,0.00009789389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014376856,0.0019878375,0.0013062068,0.0012581222,0.0008000901,0.0023946464,0.0026377763,0.0015508515,0.06547971],"category_scores_gemma":[0.0060625253,0.00078860397,0.0014345236,0.0012317273,0.0010439359,0.0025045518,0.0035617526,0.0028343406,0.03225572],"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":[0.00015769896,0.000101812184,0.0006962787,0.00071314716,0.0000952869,0.00012377497,0.00018528552,0.056402847,0.003898896,0.39762485,0.065107174,0.47489294],"study_design_scores_gemma":[0.00009168928,0.000120518336,0.00048333747,0.00032082765,0.000055163586,0.00034702843,0.00008808242,0.2874309,0.0036072761,0.27615863,0.4312228,0.000073779454],"about_ca_topic_score_codex":0.001375957,"about_ca_topic_score_gemma":0.0014280458,"teacher_disagreement_score":0.06547971,"about_ca_system_score_codex":0.0009415932,"about_ca_system_score_gemma":0.0013459661,"threshold_uncertainty_score":0.21905148},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004112594,0.046721593,0.61099327,0.003626753,0.001619406,0.000051843235,0.0003913611,0.001207451,0.33127576],"genre_scores_gemma":[0.11382997,0.036286432,0.2111019,0.0013824129,0.002454462,0.00025578213,0.0009822175,0.0012949089,0.63241196],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99980885,0.000041350846,0.000007425983,0.00003934944,0.0000912738,0.000011837402],"domain_scores_gemma":[0.99980515,0.000106769854,0.000010051448,0.000040407675,0.00002685058,0.000010827912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029417273,0.0009360813,0.0012294053,0.00059628015,0.0003220715,0.0013546442,0.00053354434,0.0006572351,0.020714985],"category_scores_gemma":[0.00096443685,0.00038033948,0.0004896713,0.0011544867,0.00093513326,0.0015764807,0.0009372539,0.0016078929,0.008575689],"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":[0.000027334065,0.000050675488,0.00017236189,0.0003535832,0.00005465236,0.00003660158,0.00008233041,0.031525794,0.0013587427,0.38133198,0.1284501,0.45655578],"study_design_scores_gemma":[0.000011259851,0.000033658307,0.00044706362,0.0001290997,0.000023493612,0.00011445183,0.000028141965,0.06983423,0.0012552651,0.68209493,0.2460104,0.000017996676],"about_ca_topic_score_codex":0.00058769924,"about_ca_topic_score_gemma":0.0009103791,"teacher_disagreement_score":0.020714985,"about_ca_system_score_codex":0.0005190223,"about_ca_system_score_gemma":0.0003553302,"threshold_uncertainty_score":0.069298565},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0117465565,0.018733451,0.93793666,0.0028145448,0.00036633393,0.00014533474,0.00014831912,0.0001243626,0.027984312],"genre_scores_gemma":[0.7174687,0.0373132,0.22643706,0.0013899613,0.0014276209,0.00082459755,0.00030884068,0.00011766229,0.014712317],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877375,0.0006297348,0.00005957639,0.00017947535,0.00026936556,0.000088156754],"domain_scores_gemma":[0.9988432,0.0007967558,0.00010793468,0.00006359831,0.00011721417,0.00007140424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012531428,0.0013186906,0.0012355902,0.00076795474,0.00057346467,0.0023332958,0.0012417589,0.0014176711,0.0017247235],"category_scores_gemma":[0.0032635306,0.00048213,0.00082705676,0.0011960007,0.0022544102,0.0024154854,0.0016984708,0.0022017958,0.0003214994],"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":[0.000028257511,0.000049684277,0.0004940143,0.00032188644,0.00006849365,0.00015089578,0.00022958295,0.23822452,0.00053487817,0.7311069,0.003825733,0.024965119],"study_design_scores_gemma":[0.000017825432,0.000039933413,0.00022243256,0.00007822984,0.000023346014,0.000064490116,0.000088047644,0.48594865,0.00020694267,0.5011946,0.012093666,0.000021918631],"about_ca_topic_score_codex":0.0032656284,"about_ca_topic_score_gemma":0.0019009426,"teacher_disagreement_score":0.0032656284,"about_ca_system_score_codex":0.0014552971,"about_ca_system_score_gemma":0.0012676385,"threshold_uncertainty_score":0.010558903},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016969729,0.00007172568,0.9972191,0.00009961504,0.000030608233,0.000020670926,0.00001389796,0.00016477934,0.0006826349],"genre_scores_gemma":[0.17392953,0.00023837379,0.8206935,0.00021815307,0.00009755311,0.00034292843,0.00010651112,0.0002222954,0.0041511045],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938416,0.00024514267,0.000024042603,0.00008956267,0.00021123148,0.000045763773],"domain_scores_gemma":[0.99901533,0.00054408103,0.000083929895,0.00009907474,0.00019658038,0.000060908158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013371859,0.0005357328,0.0009263795,0.0003168955,0.0004454553,0.0006616978,0.0019507451,0.0010114821,0.0027399345],"category_scores_gemma":[0.0030855648,0.00042120833,0.00042158997,0.00034972705,0.0007275656,0.0008528835,0.001322458,0.0012985658,0.00075482525],"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":[0.00018336625,0.00006967136,0.0006315987,0.00020330677,0.000042944608,0.00010729239,0.000100945406,0.85844654,0.0037299911,0.036765385,0.0036364596,0.096082486],"study_design_scores_gemma":[0.000017401286,0.0000092348555,0.000021266731,0.0000031925615,0.0000014693957,0.0000065867503,0.0000021179526,0.99667054,0.00018363191,0.0024430235,0.0006391627,0.0000023956509],"about_ca_topic_score_codex":0.0037534481,"about_ca_topic_score_gemma":0.00363456,"teacher_disagreement_score":0.0037534481,"about_ca_system_score_codex":0.00058930734,"about_ca_system_score_gemma":0.0016572216,"threshold_uncertainty_score":0.009166002},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04189848,0.00077798887,0.95067286,0.0005533014,0.00006691147,0.00004723464,0.000075138436,0.00030179054,0.005606279],"genre_scores_gemma":[0.9217581,0.00096855895,0.06705802,0.00033075627,0.00011866889,0.0002307345,0.00013688662,0.00037167594,0.009026572],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986064,0.00048277262,0.00007666575,0.00022498572,0.00042251623,0.00018668434],"domain_scores_gemma":[0.99016553,0.006696102,0.00096775184,0.0006757021,0.0011826719,0.00031214798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036395488,0.00095052534,0.0008444183,0.0011271681,0.00063664856,0.0012276272,0.0013133454,0.00095369894,0.0029573124],"category_scores_gemma":[0.016910797,0.0004654659,0.00081399194,0.000665834,0.0021373173,0.00226202,0.0016897484,0.002043007,0.0005323513],"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":[0.00012941552,0.00003242242,0.001209268,0.00010991714,0.000048376944,0.00012353274,0.00016061464,0.7872075,0.0033757724,0.19771148,0.001118108,0.0087736165],"study_design_scores_gemma":[0.000003704062,0.000009209405,0.00008921709,0.000005124662,0.0000033126582,0.000006162393,0.000005336627,0.9785751,0.00029716123,0.020781577,0.00022015354,0.000003963735],"about_ca_topic_score_codex":0.0029457859,"about_ca_topic_score_gemma":0.0016552655,"teacher_disagreement_score":0.0036395488,"about_ca_system_score_codex":0.0015696334,"about_ca_system_score_gemma":0.0011887426,"threshold_uncertainty_score":0.019248009},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.178594,0.0020390681,0.7657534,0.017153498,0.00038687926,0.0003703979,0.0013915114,0.0019287972,0.032382462],"genre_scores_gemma":[0.9073167,0.000756474,0.081100754,0.0013832134,0.0004749154,0.00051880797,0.00054824114,0.00044014788,0.007460657],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98940814,0.0030329274,0.0005090443,0.002715633,0.0030577353,0.0012764833],"domain_scores_gemma":[0.9198673,0.059196778,0.0026001134,0.014903362,0.0021998754,0.0012327221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009066242,0.0009802203,0.002418629,0.0011332624,0.002960552,0.00629805,0.004853017,0.0030127787,0.008716191],"category_scores_gemma":[0.05995245,0.0013245058,0.0025216185,0.0014365804,0.009621781,0.022752618,0.007870382,0.010476054,0.0011106123],"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":[0.00053111406,0.00008992181,0.0015104123,0.0002297169,0.00008300608,0.00019370743,0.00049106014,0.037626624,0.001994449,0.93874705,0.0035932504,0.014909674],"study_design_scores_gemma":[0.00005827543,0.000025854584,0.00023494767,0.000020639214,0.000023724324,0.000048586997,0.00003329992,0.11940797,0.0010962257,0.87774295,0.0012821635,0.000025355359],"about_ca_topic_score_codex":0.0029711542,"about_ca_topic_score_gemma":0.0018497064,"teacher_disagreement_score":0.009066242,"about_ca_system_score_codex":0.006145308,"about_ca_system_score_gemma":0.0033608354,"threshold_uncertainty_score":0.047947407},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012392064,0.0013195219,0.69500357,0.0052921935,0.002776057,0.00036144885,0.0020714598,0.0042930567,0.27649072],"genre_scores_gemma":[0.4386505,0.002138725,0.16654322,0.0075914683,0.0019441562,0.0010895806,0.0039043184,0.005593457,0.3725446],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99716127,0.0005121459,0.000102250335,0.0009256725,0.0007372493,0.00056146004],"domain_scores_gemma":[0.9958819,0.00093031325,0.00021959822,0.0018358348,0.00074972486,0.00038265478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021739823,0.0019020955,0.0018441369,0.002455079,0.0026340368,0.0040983954,0.002313871,0.0033674894,0.098030284],"category_scores_gemma":[0.013691243,0.00083966635,0.0014387798,0.0017811948,0.0024223423,0.0043183584,0.005822264,0.0057214457,0.03499895],"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":[0.00016661704,0.00006613942,0.0003425391,0.00010708309,0.00005418479,0.00014992709,0.000058387934,0.007502259,0.00270193,0.88948494,0.05143389,0.047932036],"study_design_scores_gemma":[0.00008782192,0.00011622061,0.00050315796,0.00012768438,0.000076477736,0.00060075574,0.00011798677,0.051564556,0.007277229,0.8464896,0.092957444,0.00008105177],"about_ca_topic_score_codex":0.0012298819,"about_ca_topic_score_gemma":0.0011959135,"teacher_disagreement_score":0.098030284,"about_ca_system_score_codex":0.0019861602,"about_ca_system_score_gemma":0.0026556891,"threshold_uncertainty_score":0.32794398},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028302541,0.0004891509,0.9640639,0.00045314408,0.00012296156,0.000056030345,0.00002970583,0.002064894,0.0044177976],"genre_scores_gemma":[0.2673643,0.00067529944,0.72740257,0.00015657042,0.00008514665,0.00012791525,0.00010853666,0.0004993743,0.003580238],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991904,0.00030792961,0.00003699194,0.000052989468,0.00032505926,0.0000865694],"domain_scores_gemma":[0.99764204,0.0014551737,0.00013141571,0.0002630756,0.00043906207,0.000069215836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010694049,0.0009260817,0.0007901633,0.0005515484,0.000505799,0.0011698105,0.0010726572,0.0009907509,0.0039480464],"category_scores_gemma":[0.0083217975,0.00040820942,0.00042033516,0.001041768,0.0007152362,0.0014702394,0.0012068511,0.0016394929,0.0015543478],"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":[0.00083965715,0.00017553587,0.0022120785,0.0006147722,0.00012224182,0.00061835436,0.00039256367,0.50948656,0.08011503,0.07096844,0.011104176,0.3233506],"study_design_scores_gemma":[0.000026944603,0.000049197526,0.00016366647,0.000014093929,0.0000084484855,0.00005814891,0.000013246891,0.9757616,0.016202047,0.004389051,0.0033039928,0.000009654355],"about_ca_topic_score_codex":0.0023828482,"about_ca_topic_score_gemma":0.0026559895,"teacher_disagreement_score":0.0039480464,"about_ca_system_score_codex":0.00039270983,"about_ca_system_score_gemma":0.0013318007,"threshold_uncertainty_score":0.013207495},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016145363,0.000118680975,0.9788256,0.0003178234,0.00007957992,0.00012191104,0.000034521145,0.00016449369,0.0041920673],"genre_scores_gemma":[0.8423606,0.00021468048,0.15087105,0.0001960348,0.00006849302,0.0002986084,0.00004920638,0.000043011416,0.0058982857],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977406,0.0010143698,0.0000985526,0.0002645011,0.0005399493,0.0003418896],"domain_scores_gemma":[0.9969266,0.0016812966,0.00029805614,0.00034544533,0.00043270492,0.0003159379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030515797,0.00075728644,0.00081094616,0.0005895419,0.00077489973,0.0015413014,0.0023016601,0.0011610504,0.0027514452],"category_scores_gemma":[0.009382001,0.00039578945,0.0004227911,0.00083356985,0.0014515249,0.0020545998,0.00182872,0.0016398139,0.0002984173],"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":[0.00021950711,0.00015793716,0.00043368922,0.00013915474,0.00003404336,0.00018673671,0.00014531867,0.48026252,0.005249855,0.47093698,0.002479682,0.039754562],"study_design_scores_gemma":[0.00004988952,0.000047065692,0.00007588375,0.000010654568,0.000006564752,0.000039099286,0.000013430925,0.9352209,0.0007684626,0.06196181,0.0017920962,0.0000141390165],"about_ca_topic_score_codex":0.0017291484,"about_ca_topic_score_gemma":0.0019256776,"teacher_disagreement_score":0.0030515797,"about_ca_system_score_codex":0.0018502198,"about_ca_system_score_gemma":0.0026985456,"threshold_uncertainty_score":0.016138494},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011820883,0.000121666155,0.9808801,0.0002218269,0.00006273071,0.00003410037,0.000077905774,0.00065185176,0.006128956],"genre_scores_gemma":[0.43583742,0.00061586825,0.5355868,0.00085176737,0.00017297706,0.0002471396,0.0006075736,0.0010799665,0.025000526],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991171,0.00018039122,0.000031488835,0.00016116344,0.00042613354,0.000083759085],"domain_scores_gemma":[0.99863845,0.0004713087,0.00013577257,0.00031881663,0.00032856196,0.000107140084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014541633,0.0010053272,0.0008794725,0.0010501682,0.0006179921,0.001849682,0.0014201076,0.0013936841,0.005348487],"category_scores_gemma":[0.005604979,0.00055822555,0.00067996955,0.0009416708,0.0017919375,0.002075495,0.0028265843,0.0015727497,0.0021633366],"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":[0.00043658607,0.00012713583,0.001673512,0.00024522207,0.000076267715,0.00027952032,0.0002929546,0.4103171,0.056793526,0.43432677,0.008703579,0.08672771],"study_design_scores_gemma":[0.000024852945,0.00006128175,0.000358934,0.00003524667,0.000018539376,0.00019776994,0.000035756682,0.91008854,0.015944766,0.06446501,0.008737474,0.000031767067],"about_ca_topic_score_codex":0.0014358911,"about_ca_topic_score_gemma":0.001442006,"teacher_disagreement_score":0.005348487,"about_ca_system_score_codex":0.0011256502,"about_ca_system_score_gemma":0.00077550666,"threshold_uncertainty_score":0.01789242},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053252056,0.00024107718,0.9914967,0.0001589686,0.000067211346,0.000025042362,0.000029028628,0.00020991302,0.0024468533],"genre_scores_gemma":[0.49316028,0.0008259409,0.4985943,0.00022879429,0.00016878641,0.00025205477,0.00016108116,0.000095182106,0.006513484],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991726,0.00023284132,0.00003336451,0.00007473414,0.0004204162,0.00006592535],"domain_scores_gemma":[0.9984806,0.0008450763,0.000097747376,0.00024730802,0.0002847147,0.00004451806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095322693,0.00054899784,0.00043501912,0.00046501067,0.00042876948,0.0007431499,0.00070985843,0.0005519455,0.0021981157],"category_scores_gemma":[0.0044243666,0.00020920818,0.0002994293,0.0010383412,0.0009681858,0.0009490566,0.00093562953,0.0013899045,0.0006167719],"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":[0.00021271406,0.0000397165,0.00028797108,0.00014309528,0.000031162603,0.00011219387,0.00018420229,0.43485475,0.014130216,0.41406193,0.0045520207,0.13138996],"study_design_scores_gemma":[0.000012268865,0.00002647208,0.000026803444,0.000012019042,0.0000036973315,0.000024644261,0.000005799427,0.9624441,0.0024730337,0.032677673,0.0022873199,0.000006175148],"about_ca_topic_score_codex":0.0022873909,"about_ca_topic_score_gemma":0.0029991956,"teacher_disagreement_score":0.0022873909,"about_ca_system_score_codex":0.0008333248,"about_ca_system_score_gemma":0.0012735928,"threshold_uncertainty_score":0.0073534846},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014377367,0.0007823136,0.98116595,0.0016576574,0.000059520185,0.000045660134,0.00014617291,0.00011862079,0.0016467491],"genre_scores_gemma":[0.79605335,0.00262082,0.19328606,0.0013085236,0.0007814333,0.00030841012,0.0005618141,0.00021975498,0.004859741],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995182,0.0022864232,0.000188839,0.0007822166,0.001118777,0.00044173622],"domain_scores_gemma":[0.9771738,0.017635334,0.0014364735,0.002120473,0.0011343854,0.00049963174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006936723,0.0015770715,0.0027402423,0.0008831569,0.00076947216,0.0021488173,0.0027101277,0.0026413111,0.0019629437],"category_scores_gemma":[0.02866687,0.0010836641,0.0010338061,0.0019215014,0.004398534,0.005711586,0.0038179941,0.0054152915,0.0003854985],"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":[0.00021171464,0.00011170194,0.0014061087,0.0003311583,0.00011501266,0.00032774953,0.00014227614,0.68214875,0.0017903299,0.28121465,0.0033884763,0.028812084],"study_design_scores_gemma":[0.000022229313,0.000037588085,0.00016678154,0.00002046035,0.00000842492,0.000062241525,0.000016826854,0.90918994,0.00046863695,0.08944354,0.00055037206,0.0000129066175],"about_ca_topic_score_codex":0.0025221882,"about_ca_topic_score_gemma":0.0017340604,"teacher_disagreement_score":0.006936723,"about_ca_system_score_codex":0.0024592655,"about_ca_system_score_gemma":0.0020837667,"threshold_uncertainty_score":0.036685348},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043061627,0.00015918707,0.9942238,0.00014572819,0.000019569807,0.000040680225,0.000017367842,0.00029131563,0.0007961184],"genre_scores_gemma":[0.20079875,0.00029057014,0.7929041,0.00031966312,0.00010236719,0.00046152654,0.00021775278,0.000469138,0.004436101],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975254,0.0009936423,0.00011827121,0.00048173266,0.00063295057,0.0002479571],"domain_scores_gemma":[0.9918268,0.0057511725,0.000661847,0.000651637,0.0007435203,0.00036504437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059188576,0.001932601,0.0024602308,0.0009934613,0.0007810061,0.0018527578,0.0026022594,0.002539718,0.0038800251],"category_scores_gemma":[0.019112064,0.0012455834,0.0017077381,0.001031908,0.0022878805,0.0035546788,0.004340898,0.0050162,0.0014495972],"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":[0.00026210368,0.00014474698,0.0011412812,0.00024333925,0.000099680496,0.000076375305,0.00011956299,0.8686018,0.0022206616,0.07868553,0.0014630998,0.046941824],"study_design_scores_gemma":[0.000009681774,0.000017918714,0.00003125744,0.0000056109257,0.0000041270664,0.000006493734,0.00000349146,0.99057734,0.00035772158,0.008791177,0.00019174346,0.0000034463496],"about_ca_topic_score_codex":0.0025056216,"about_ca_topic_score_gemma":0.002117345,"teacher_disagreement_score":0.0059188576,"about_ca_system_score_codex":0.0017600465,"about_ca_system_score_gemma":0.002146551,"threshold_uncertainty_score":0.031302273},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06493963,0.00032756221,0.906758,0.0006213984,0.00025501227,0.00021061288,0.000432585,0.017540533,0.008914608],"genre_scores_gemma":[0.7353299,0.0001967687,0.25078428,0.00053176214,0.00019091382,0.0005590022,0.0013920593,0.0027193923,0.008295787],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815613,0.0003223605,0.00012540353,0.0005516003,0.0005286467,0.00031582173],"domain_scores_gemma":[0.9971812,0.00062946475,0.00017642153,0.0011072401,0.0006259597,0.00027970527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017387237,0.0012611161,0.0010667827,0.00066152716,0.0011276638,0.0017712285,0.0033455165,0.0008276863,0.007382415],"category_scores_gemma":[0.006300951,0.0006283458,0.0006474692,0.000759723,0.0009996493,0.002523807,0.0032206224,0.0016007181,0.003611532],"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":[0.0016244443,0.00061337725,0.0054945652,0.00032985484,0.00016269875,0.00020273935,0.00079372677,0.5114304,0.072736286,0.026157906,0.034663476,0.34579048],"study_design_scores_gemma":[0.00007653624,0.00008691464,0.0007094544,0.000010894069,0.000015223132,0.000043030952,0.000066244625,0.96831304,0.011874817,0.011269004,0.0075116707,0.00002329116],"about_ca_topic_score_codex":0.0037115351,"about_ca_topic_score_gemma":0.004049156,"teacher_disagreement_score":0.007382415,"about_ca_system_score_codex":0.0010838913,"about_ca_system_score_gemma":0.0025036454,"threshold_uncertainty_score":0.024696648},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022630324,0.00023358653,0.9938304,0.0001267117,0.00008354814,0.00002524809,0.000021325885,0.00016165862,0.0032544667],"genre_scores_gemma":[0.28828216,0.0010448211,0.6954861,0.00021166941,0.00015243316,0.00029660075,0.00015488103,0.00017104589,0.0142002525],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993918,0.0001774141,0.000022397096,0.000055645953,0.00030153035,0.000051151277],"domain_scores_gemma":[0.9990246,0.000554448,0.00005780267,0.00011175884,0.00022123588,0.000030091105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008859158,0.00075178227,0.0005973075,0.00047974772,0.00037596293,0.0008218169,0.00086585723,0.00073256204,0.004558913],"category_scores_gemma":[0.0037061065,0.00026688597,0.00042846877,0.0009386846,0.00092422304,0.0008390261,0.0008416277,0.0015464033,0.0012943527],"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":[0.0001211238,0.000035313875,0.00027423454,0.0001799017,0.00004119914,0.000101269914,0.00012940347,0.61635506,0.005509832,0.28618142,0.0042911842,0.08678003],"study_design_scores_gemma":[0.0000061575092,0.000009867938,0.000012457813,0.0000065541344,0.0000018662241,0.000012206411,0.000003335714,0.9856603,0.00064728153,0.0117144855,0.0019227654,0.0000027263004],"about_ca_topic_score_codex":0.003798914,"about_ca_topic_score_gemma":0.005045788,"teacher_disagreement_score":0.004558913,"about_ca_system_score_codex":0.0008385173,"about_ca_system_score_gemma":0.0014008192,"threshold_uncertainty_score":0.0152511},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2016402,0.00018744927,0.7928207,0.00020837245,0.000038189264,0.000050468036,0.000056211138,0.00017115306,0.0048272465],"genre_scores_gemma":[0.960092,0.00008041606,0.038485445,0.000029554172,0.00001692939,0.0000361119,0.000030992538,0.000014665161,0.0012138758],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951994,0.00014849474,0.0000147267565,0.000088124405,0.000121032586,0.00010763187],"domain_scores_gemma":[0.99847275,0.0009319675,0.00016278031,0.00016049371,0.00019685246,0.000075035605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005649641,0.0004404717,0.0004510199,0.00026274234,0.0004322825,0.00078685535,0.00087868096,0.00041214048,0.0009344541],"category_scores_gemma":[0.002477834,0.00016132568,0.00020722747,0.0006956507,0.00064487895,0.0011434479,0.00061534956,0.0005069692,0.00010921741],"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":[0.00012493155,0.000047489444,0.0008147721,0.00005758973,0.000012237192,0.00023601184,0.000040963612,0.95178074,0.007104709,0.020995302,0.00043950285,0.018345658],"study_design_scores_gemma":[0.0000053076624,0.000025750853,0.00009397835,0.0000016845797,0.0000028008387,0.000023339246,0.000020112608,0.99506795,0.0013745903,0.0031399173,0.00024144005,0.0000030765361],"about_ca_topic_score_codex":0.0019649738,"about_ca_topic_score_gemma":0.0027385564,"teacher_disagreement_score":0.0019649738,"about_ca_system_score_codex":0.00088147714,"about_ca_system_score_gemma":0.00066412287,"threshold_uncertainty_score":0.0063955784},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10513012,0.00096417445,0.84136075,0.0045322687,0.0019738928,0.00023667487,0.00045231188,0.0053873397,0.039962437],"genre_scores_gemma":[0.87910354,0.00037971523,0.098672405,0.0018541786,0.00036508014,0.00015483046,0.0005143744,0.00055053324,0.018405357],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990497,0.00015626027,0.00006408024,0.00021562436,0.0003629408,0.00015146825],"domain_scores_gemma":[0.99795616,0.00043940832,0.00015561776,0.0008659976,0.0004663845,0.00011647409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007899164,0.0006927767,0.0007396787,0.00033978638,0.0008166058,0.0015812387,0.00079702836,0.0010997369,0.010068639],"category_scores_gemma":[0.006340688,0.0002929399,0.00027449627,0.0004836616,0.0012270479,0.0027104768,0.0015749744,0.0020619004,0.003795117],"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":[0.0021153812,0.0002754832,0.0037365162,0.00033380298,0.000098470045,0.0005203619,0.00039364025,0.06526573,0.1271008,0.12445108,0.025780033,0.6499288],"study_design_scores_gemma":[0.00021558139,0.00087858696,0.0031115997,0.00021627339,0.00010979142,0.0013162694,0.0003125283,0.55734235,0.24392048,0.12469965,0.06774889,0.00012800492],"about_ca_topic_score_codex":0.00072730775,"about_ca_topic_score_gemma":0.0011139117,"teacher_disagreement_score":0.010068639,"about_ca_system_score_codex":0.00040753154,"about_ca_system_score_gemma":0.0012798925,"threshold_uncertainty_score":0.033682883},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020392875,0.00005918958,0.9965024,0.00012779098,0.000021820466,0.00003927047,0.000035193196,0.00041161344,0.00076342566],"genre_scores_gemma":[0.06642883,0.00011787704,0.9298646,0.00017001883,0.000058709047,0.00024640188,0.00026798347,0.00022929406,0.0026161857],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990689,0.0002826159,0.000047015583,0.00016342459,0.00034846526,0.0000895902],"domain_scores_gemma":[0.99883085,0.0006332509,0.00011345835,0.00016864971,0.00020759804,0.000046291178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014355362,0.0010684275,0.0008779412,0.0009518561,0.0007581497,0.0009868381,0.0015063344,0.0013641457,0.0059143985],"category_scores_gemma":[0.0054159337,0.0005838889,0.00077402155,0.0008650066,0.00092118216,0.0013385332,0.0018742487,0.0019953144,0.0021359122],"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":[0.00030205832,0.00016524814,0.000754685,0.00017873108,0.00008547938,0.00019204637,0.00015670556,0.49959603,0.011862216,0.11669197,0.011604666,0.35841012],"study_design_scores_gemma":[0.000046337947,0.00003079366,0.000078718636,0.000008344343,0.0000057211246,0.00004635952,0.000012718897,0.9806575,0.0019079221,0.014436439,0.0027552806,0.000013836153],"about_ca_topic_score_codex":0.004608737,"about_ca_topic_score_gemma":0.008162164,"teacher_disagreement_score":0.0059143985,"about_ca_system_score_codex":0.00075929315,"about_ca_system_score_gemma":0.002889393,"threshold_uncertainty_score":0.019785583},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06714177,0.00018348434,0.92767113,0.00042185764,0.0000632016,0.0001461625,0.000089691646,0.0002635063,0.0040192334],"genre_scores_gemma":[0.9284459,0.000097447184,0.06743079,0.00011844711,0.000027687869,0.00012720058,0.000055944907,0.000039885897,0.0036567254],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974662,0.001049138,0.00011502791,0.0004005873,0.00046690294,0.00050217705],"domain_scores_gemma":[0.99611807,0.0023270394,0.00036539894,0.0003441351,0.0005283049,0.00031702995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038516603,0.0008383939,0.001647325,0.00052318064,0.0007282031,0.0018622874,0.0021644877,0.0012435676,0.0025507812],"category_scores_gemma":[0.0069468175,0.00051360606,0.0005266324,0.0010548895,0.0013776931,0.002388176,0.0016707329,0.0018223685,0.0002661983],"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":[0.00027973694,0.0001459878,0.00057022757,0.000071445225,0.000034191573,0.0001681016,0.00008674934,0.9144349,0.0015586213,0.056308296,0.0012481955,0.025093546],"study_design_scores_gemma":[0.0000203933,0.000019333029,0.00003993736,0.000001922009,0.0000028511267,0.000014704482,0.000008643742,0.98815304,0.00021961905,0.011342082,0.00017263844,0.000004845025],"about_ca_topic_score_codex":0.004497282,"about_ca_topic_score_gemma":0.003254452,"teacher_disagreement_score":0.004497282,"about_ca_system_score_codex":0.0021239887,"about_ca_system_score_gemma":0.0026793529,"threshold_uncertainty_score":0.020369828},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0078441575,0.00022986632,0.98935974,0.00011909509,0.000058209163,0.000042084124,0.000047933685,0.0007961928,0.0015028034],"genre_scores_gemma":[0.27709863,0.00019302762,0.71633,0.00020496896,0.000093893446,0.00026458228,0.00039122088,0.00055705686,0.0048666853],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985555,0.00067074713,0.000054146454,0.00017173344,0.00045961674,0.00008828352],"domain_scores_gemma":[0.9981981,0.0010091879,0.0001271178,0.00021823055,0.00037043117,0.00007695797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017211877,0.0009968418,0.0014321117,0.0007572897,0.00038912226,0.00096079306,0.0014004195,0.0012216369,0.004874749],"category_scores_gemma":[0.005308601,0.00048460928,0.0005348529,0.0010832069,0.0007576867,0.00088646566,0.0009789729,0.0017140656,0.001554117],"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":[0.0003083162,0.00014190332,0.0005967656,0.00018758034,0.00007723218,0.00008517646,0.0000451255,0.83131593,0.005769562,0.031481296,0.005158967,0.1248321],"study_design_scores_gemma":[0.000011748774,0.00001278514,0.00003079613,0.0000027178746,0.0000011137331,0.0000046615837,9.255732e-7,0.99727076,0.00035241854,0.0019016251,0.00040851062,0.0000019180334],"about_ca_topic_score_codex":0.0033454832,"about_ca_topic_score_gemma":0.003341692,"teacher_disagreement_score":0.004874749,"about_ca_system_score_codex":0.0009387214,"about_ca_system_score_gemma":0.001449121,"threshold_uncertainty_score":0.016307592},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032980345,0.00038709078,0.94718236,0.0008316001,0.00016176037,0.000034066474,0.000048435035,0.00026967944,0.01810471],"genre_scores_gemma":[0.8440732,0.0006626257,0.13503894,0.0005197632,0.000114659015,0.00015410823,0.00008621437,0.00023417266,0.019116279],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953187,0.00015408154,0.000022676453,0.00011415772,0.00013167145,0.00004564987],"domain_scores_gemma":[0.9989759,0.0004992221,0.00013223416,0.00021517582,0.00011648441,0.00006108398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008970756,0.00038005642,0.00048428052,0.00040611348,0.00053906225,0.0013767049,0.0011834804,0.0011110456,0.007131196],"category_scores_gemma":[0.004603472,0.00024738142,0.00041779224,0.00034733853,0.0015595515,0.003654339,0.0018579741,0.0015149205,0.0007006183],"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":[0.00006654174,0.00004481859,0.00027224334,0.000066419256,0.000028780345,0.00013196781,0.000110074325,0.113492996,0.0046793213,0.8289125,0.0017977848,0.05039646],"study_design_scores_gemma":[0.000015271826,0.00008343484,0.00016360443,0.00002093711,0.000010991797,0.00015080918,0.000027772634,0.5746108,0.0040354514,0.4145837,0.0062788283,0.0000184013],"about_ca_topic_score_codex":0.0005239634,"about_ca_topic_score_gemma":0.00040488,"teacher_disagreement_score":0.007131196,"about_ca_system_score_codex":0.0007348915,"about_ca_system_score_gemma":0.00048223865,"threshold_uncertainty_score":0.023856223},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006544717,0.03804349,0.21311788,0.0031239272,0.0023590706,0.000077953715,0.0006174588,0.0010052618,0.7410005],"genre_scores_gemma":[0.01711462,0.048221335,0.09230639,0.002283027,0.0037042345,0.00027226904,0.0010488196,0.0015669519,0.8334823],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995844,0.00007058311,0.000017199953,0.00007967769,0.00022071018,0.000027472604],"domain_scores_gemma":[0.9996717,0.00016560512,0.000012684513,0.000047182246,0.000081880855,0.000021076186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047556413,0.0016712801,0.0012023384,0.0014244146,0.0006967557,0.0020319547,0.0010647147,0.0012959131,0.06581637],"category_scores_gemma":[0.0012287954,0.00070599234,0.00076914526,0.002624813,0.0011158414,0.0021579415,0.0011086203,0.00293284,0.042591322],"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":[0.000011966958,0.00006320259,0.00006626456,0.0004956268,0.000018715053,0.000042921954,0.000099091696,0.008933525,0.0008977809,0.4531751,0.27637956,0.2598163],"study_design_scores_gemma":[0.000005282689,0.000016750322,0.00015785816,0.00028040516,0.000007956672,0.000093022165,0.000020086569,0.006880494,0.00042633901,0.2638578,0.72823614,0.000017916105],"about_ca_topic_score_codex":0.0015959204,"about_ca_topic_score_gemma":0.0028491537,"teacher_disagreement_score":0.06581637,"about_ca_system_score_codex":0.0010626632,"about_ca_system_score_gemma":0.0010279401,"threshold_uncertainty_score":0.22017771},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002220012,0.00009499366,0.99577206,0.00019638537,0.000023439727,0.000018214429,0.00002627845,0.00013107236,0.0015176346],"genre_scores_gemma":[0.4300338,0.0005701862,0.55900806,0.00045699146,0.00015841905,0.00043421867,0.00037968974,0.00065745076,0.00830121],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985159,0.0007237329,0.000064489985,0.00022082587,0.00038738447,0.00008765386],"domain_scores_gemma":[0.99619675,0.0024654502,0.0003327061,0.00044305096,0.00042086284,0.00014118598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032699334,0.0014267593,0.0014055911,0.00070135045,0.00053385005,0.001622478,0.0014211012,0.0020248794,0.003989941],"category_scores_gemma":[0.01176392,0.00068661006,0.0010895053,0.0007871887,0.0019833585,0.0023174502,0.002418995,0.003281526,0.001092626],"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":[0.00005146562,0.000047451293,0.00036170913,0.00010231559,0.000033579854,0.00005187862,0.000046878755,0.8528855,0.0013295201,0.124869265,0.0018226816,0.018397769],"study_design_scores_gemma":[0.0000043783402,0.00002016806,0.000024444187,0.000009320144,0.0000024443243,0.000011569411,0.0000032481535,0.9694141,0.00043370939,0.02942786,0.0006446238,0.0000040722675],"about_ca_topic_score_codex":0.001253714,"about_ca_topic_score_gemma":0.0013401462,"teacher_disagreement_score":0.003989941,"about_ca_system_score_codex":0.0013597504,"about_ca_system_score_gemma":0.001675944,"threshold_uncertainty_score":0.017293334},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013433256,0.00065397914,0.9802343,0.00096733513,0.00014327595,0.000044041055,0.00004925567,0.00033169432,0.004142869],"genre_scores_gemma":[0.61822635,0.0016999462,0.36471048,0.0018351665,0.00062475924,0.00037482893,0.00030412897,0.0006185344,0.01160579],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985098,0.00051199045,0.000043449476,0.00027180044,0.0004570366,0.00020582462],"domain_scores_gemma":[0.9937224,0.004495421,0.00033389629,0.00068770035,0.00048898585,0.00027151042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031781555,0.0020444754,0.0018988224,0.00074784376,0.0006909338,0.0016646025,0.0018332195,0.0018360496,0.0029362387],"category_scores_gemma":[0.01608845,0.0006392764,0.0011595505,0.0008436012,0.0026422446,0.003075801,0.0035060933,0.0045549287,0.0010119524],"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":[0.00023022149,0.00013324032,0.0010019351,0.00024103522,0.00006682718,0.00019240422,0.00021171487,0.7858617,0.0047225608,0.15481499,0.0051205866,0.04740284],"study_design_scores_gemma":[0.000008740593,0.00003201564,0.0000597982,0.00001077797,0.0000039653564,0.000012626405,0.0000051462157,0.9782606,0.00044067524,0.02071328,0.00044667843,0.0000056834324],"about_ca_topic_score_codex":0.003472751,"about_ca_topic_score_gemma":0.002321546,"teacher_disagreement_score":0.003472751,"about_ca_system_score_codex":0.0011542558,"about_ca_system_score_gemma":0.0015810723,"threshold_uncertainty_score":0.016807854},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05823603,0.00030315694,0.9345336,0.00031230267,0.00009214418,0.0000982316,0.000108609354,0.00056491117,0.005751029],"genre_scores_gemma":[0.7965564,0.00024181636,0.19593336,0.00021333383,0.000043628454,0.0002350193,0.00030089053,0.00041454576,0.006061045],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918693,0.00022590172,0.0000333788,0.00012346455,0.00019674825,0.00023357103],"domain_scores_gemma":[0.9981635,0.0011323532,0.0001654695,0.00016310932,0.00022035399,0.00015517669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013744372,0.0010088682,0.00089755916,0.00072864594,0.0005479781,0.0011592921,0.0016879644,0.00084166694,0.002893634],"category_scores_gemma":[0.004877139,0.00044022276,0.0005850959,0.0008428503,0.0012105671,0.0012008253,0.0013411524,0.0013380973,0.00031790798],"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":[0.00015961601,0.000044626177,0.00024408221,0.000055731412,0.000016263466,0.00003199659,0.00004267138,0.96408105,0.0012140196,0.015894545,0.0012485685,0.016966853],"study_design_scores_gemma":[0.000006395646,0.00001777755,0.00004270904,0.0000039913307,0.0000030232857,0.0000056206804,0.000010771795,0.9944728,0.0003659275,0.0047914134,0.00027669113,0.0000029291932],"about_ca_topic_score_codex":0.0051509365,"about_ca_topic_score_gemma":0.0039132936,"teacher_disagreement_score":0.0051509365,"about_ca_system_score_codex":0.0019620266,"about_ca_system_score_gemma":0.0021978114,"threshold_uncertainty_score":0.0142354965},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025402023,0.00077393337,0.9667422,0.0008881275,0.00008295791,0.0000612871,0.00009000943,0.00014617205,0.0058132308],"genre_scores_gemma":[0.8783811,0.0014461585,0.09208282,0.00038507555,0.00036293303,0.00043142174,0.00040824263,0.00052184187,0.025980435],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987112,0.0006235447,0.00005386614,0.00023762869,0.00027464883,0.00009913832],"domain_scores_gemma":[0.9915052,0.0057257796,0.0006694127,0.00026558756,0.0015564482,0.00027750304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004970344,0.0011474584,0.0015228123,0.0016375295,0.000997696,0.0019741068,0.001652067,0.0016289001,0.0033648964],"category_scores_gemma":[0.02055382,0.0007947629,0.0010060889,0.0007639672,0.0027443669,0.0025619844,0.0023289267,0.0019067669,0.00056096946],"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":[0.00018885497,0.00006264971,0.0010389719,0.00021357053,0.00013694492,0.00011590684,0.00023706342,0.54836595,0.003646446,0.42517042,0.003215506,0.017607747],"study_design_scores_gemma":[0.0000027118997,0.000008908664,0.0000922198,0.000006393952,0.0000051415127,0.000006379742,0.0000068027252,0.9695295,0.00017267665,0.030012028,0.00015228681,0.000004985474],"about_ca_topic_score_codex":0.008012774,"about_ca_topic_score_gemma":0.0043528117,"teacher_disagreement_score":0.008012774,"about_ca_system_score_codex":0.0026077305,"about_ca_system_score_gemma":0.0018012903,"threshold_uncertainty_score":0.026286006},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011379621,0.0006270334,0.98438674,0.00029387875,0.00008976183,0.00007435693,0.00006437947,0.00089397177,0.0021903398],"genre_scores_gemma":[0.45306,0.0008858227,0.5372098,0.000696901,0.0002446426,0.00026862917,0.00034874142,0.0003461321,0.00693926],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99903417,0.00029227292,0.000060106526,0.00014869301,0.00040487683,0.000059767222],"domain_scores_gemma":[0.99870896,0.0004990368,0.00011619913,0.00038120325,0.00023999192,0.00005457452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00184651,0.0010898405,0.0010055965,0.0006261658,0.0003539557,0.0010269715,0.0018646322,0.0012696517,0.00171524],"category_scores_gemma":[0.0066354093,0.00026827736,0.0004305497,0.0007180195,0.00094715867,0.0017999011,0.0016411501,0.001791848,0.00062395027],"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":[0.0005386885,0.00022106571,0.0011524458,0.000199038,0.00009036864,0.00019179267,0.00014540726,0.4037678,0.013198291,0.080840245,0.007445512,0.49220943],"study_design_scores_gemma":[0.000021659205,0.000121424106,0.00013259485,0.000019839055,0.000008194528,0.00014020175,0.000010875229,0.97541815,0.00852616,0.012968955,0.0026159512,0.000015918158],"about_ca_topic_score_codex":0.0012354902,"about_ca_topic_score_gemma":0.0014086403,"teacher_disagreement_score":0.0018646322,"about_ca_system_score_codex":0.00088485586,"about_ca_system_score_gemma":0.0008804497,"threshold_uncertainty_score":0.009765387},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066729803,0.00017019904,0.9909548,0.00017289116,0.00004818762,0.000026009404,0.000040969648,0.00038527028,0.001528581],"genre_scores_gemma":[0.24172145,0.00048496213,0.7490708,0.0002663064,0.00014640337,0.00024501237,0.0003516822,0.00045769295,0.007255712],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99887866,0.00039300538,0.00006398678,0.0001899648,0.0004207449,0.000053765743],"domain_scores_gemma":[0.9972958,0.0014624686,0.00025162072,0.00042682327,0.0004712403,0.000092030125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016127265,0.0010169147,0.001000688,0.0005451025,0.00037871426,0.00093792647,0.0014041167,0.001308822,0.0023200875],"category_scores_gemma":[0.008127637,0.00048884866,0.00058016635,0.0008275652,0.0009858011,0.0012886248,0.0013379259,0.0014584785,0.000988263],"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":[0.00016576318,0.000052564836,0.0006690368,0.00016261518,0.00008605998,0.00008351655,0.00012266822,0.7867121,0.005391224,0.09131034,0.003993434,0.11125075],"study_design_scores_gemma":[0.000010743701,0.000020773132,0.00010913374,0.0000066313096,0.0000043208365,0.000019565332,0.00000403104,0.9804505,0.000971307,0.016780287,0.0016167753,0.0000060201673],"about_ca_topic_score_codex":0.002579103,"about_ca_topic_score_gemma":0.0030529103,"teacher_disagreement_score":0.002579103,"about_ca_system_score_codex":0.00070829777,"about_ca_system_score_gemma":0.001599979,"threshold_uncertainty_score":0.008529007},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009761497,0.00009291117,0.9977816,0.00013539242,0.000021592492,0.000013124003,0.000026393278,0.000184405,0.00076845457],"genre_scores_gemma":[0.17151651,0.0005320895,0.8159516,0.00053215236,0.00020882238,0.00033850706,0.00047900685,0.0009824716,0.0094588045],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989341,0.00036986035,0.00004372951,0.00023073377,0.00033921326,0.00008229012],"domain_scores_gemma":[0.99851424,0.00071421615,0.00015192872,0.00019258905,0.00033339555,0.00009364886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021966207,0.0014413553,0.0015100719,0.0008418028,0.00058696204,0.0015226383,0.0021055008,0.0017067881,0.004489452],"category_scores_gemma":[0.005695658,0.0008953468,0.0013396026,0.00077505014,0.0011144759,0.0018053767,0.0027357931,0.0031252005,0.0015404123],"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":[0.000038303097,0.000053814878,0.00035366515,0.00015233108,0.000059652004,0.00006369416,0.00005453061,0.8483648,0.0035140638,0.08897631,0.005367621,0.053001266],"study_design_scores_gemma":[0.0000031202578,0.000014802888,0.000023775243,0.000007972425,0.0000039418705,0.000014199676,0.0000023465457,0.9858985,0.0004153759,0.01251435,0.0010966258,0.000005109778],"about_ca_topic_score_codex":0.003555986,"about_ca_topic_score_gemma":0.0033317776,"teacher_disagreement_score":0.004489452,"about_ca_system_score_codex":0.0011159356,"about_ca_system_score_gemma":0.002441227,"threshold_uncertainty_score":0.015018702},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026214078,0.00023398852,0.9644907,0.0006155016,0.00013194443,0.00005716848,0.00009563625,0.004480409,0.0036804383],"genre_scores_gemma":[0.65178907,0.0002407048,0.33905873,0.0003977459,0.0001843043,0.00025107755,0.00032980775,0.00073153456,0.0070169913],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994061,0.00017369482,0.000020963753,0.00014786104,0.00018774995,0.00006367264],"domain_scores_gemma":[0.9988752,0.0004701828,0.00010144327,0.00027619675,0.00016292997,0.0001140985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010890445,0.0007153473,0.0006501262,0.00031340183,0.0005209722,0.00067826547,0.001662647,0.0007708362,0.0036809545],"category_scores_gemma":[0.0043571885,0.00030764216,0.00028360717,0.00036817524,0.0006724144,0.0014005137,0.0013161158,0.0015721725,0.0012551892],"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":[0.0005343401,0.00023979934,0.0013395421,0.0001491758,0.00006494201,0.00015049068,0.00014169754,0.69471586,0.019340457,0.040965565,0.020029003,0.2223292],"study_design_scores_gemma":[0.000034081182,0.000027228645,0.00009833383,0.000003184616,0.0000041759067,0.000013343061,0.00000633014,0.9900157,0.0020514163,0.006580789,0.0011609857,0.0000044278995],"about_ca_topic_score_codex":0.0036216131,"about_ca_topic_score_gemma":0.007406028,"teacher_disagreement_score":0.0036809545,"about_ca_system_score_codex":0.00079423946,"about_ca_system_score_gemma":0.0014092461,"threshold_uncertainty_score":0.012313962},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21684173,0.00087977725,0.76176924,0.0027808992,0.00013762583,0.000059773123,0.00031632528,0.00059659086,0.01661809],"genre_scores_gemma":[0.9363615,0.00044071735,0.057584956,0.0003361987,0.000044552362,0.000105184605,0.00019518963,0.00033988053,0.0045918855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938476,0.0002263135,0.000023839917,0.00016926238,0.00012368229,0.00007215521],"domain_scores_gemma":[0.9976488,0.001314306,0.00029092113,0.00037981934,0.00019455094,0.00017157817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013994684,0.00042446036,0.00056071155,0.0005783246,0.000854291,0.0017581936,0.00081757514,0.0011053771,0.0047169407],"category_scores_gemma":[0.012200113,0.0005168735,0.00056939584,0.0003232019,0.0026792204,0.0037403493,0.0016681356,0.0018948157,0.0006286441],"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":[0.00018044833,0.000042844258,0.0024564834,0.000081626305,0.000033386623,0.0002352847,0.00036918125,0.32968536,0.002786874,0.63163817,0.003667489,0.028822768],"study_design_scores_gemma":[0.00002111419,0.000055090404,0.00092233595,0.000030745556,0.0000075730127,0.000071100396,0.00007430912,0.51335615,0.000931867,0.48179674,0.0027126924,0.000020267169],"about_ca_topic_score_codex":0.0020157536,"about_ca_topic_score_gemma":0.001792121,"teacher_disagreement_score":0.0047169407,"about_ca_system_score_codex":0.0011875887,"about_ca_system_score_gemma":0.0007961122,"threshold_uncertainty_score":0.015779734},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04574298,0.00043150043,0.951525,0.00034026962,0.000028976587,0.000038629205,0.000039928014,0.00041880427,0.0014338433],"genre_scores_gemma":[0.7271969,0.00036625375,0.2675828,0.00026131028,0.00003400374,0.00020039998,0.00020208619,0.00021220642,0.0039440463],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902105,0.0004004205,0.000062515704,0.0001881658,0.00021701335,0.00011086536],"domain_scores_gemma":[0.99483997,0.0037423302,0.0002886072,0.00041477164,0.00058734603,0.00012691278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004486981,0.0011341799,0.00090171007,0.00063427084,0.00035259422,0.00077117485,0.0013520077,0.0011226417,0.0012321022],"category_scores_gemma":[0.01876759,0.0006961265,0.0005860508,0.00057952997,0.0020368872,0.0028502361,0.0023493997,0.0021878518,0.00026146887],"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":[0.000114867194,0.00003115271,0.00083581416,0.00010185895,0.000040124858,0.000056069373,0.000106881715,0.9285754,0.0017346838,0.037004698,0.00052479707,0.030873682],"study_design_scores_gemma":[0.0000044797143,0.000016151143,0.00005032993,0.000004938935,0.0000019309484,0.000006610853,0.000004094716,0.9893022,0.0004197492,0.010088807,0.000098574776,0.0000021563646],"about_ca_topic_score_codex":0.006481566,"about_ca_topic_score_gemma":0.0046946853,"teacher_disagreement_score":0.006481566,"about_ca_system_score_codex":0.0020413927,"about_ca_system_score_gemma":0.0013719203,"threshold_uncertainty_score":0.023729682},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046905473,0.0001643339,0.9514221,0.00017989537,0.00003123616,0.000017714377,0.000028721644,0.00032812802,0.00092244573],"genre_scores_gemma":[0.7241208,0.00024136389,0.27245393,0.00011632424,0.000059881848,0.00007555753,0.00011724217,0.00031622755,0.002498619],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99850166,0.00067588635,0.00006576771,0.00019377179,0.0004907167,0.000072061615],"domain_scores_gemma":[0.9912847,0.006878543,0.00053192914,0.00051295816,0.0005953961,0.00019659224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023502435,0.0008362696,0.0009823901,0.00087242445,0.00040119505,0.001236832,0.00078451785,0.0013443942,0.0012877426],"category_scores_gemma":[0.021332212,0.00086228765,0.00028995593,0.00057750085,0.0015648297,0.0019565243,0.0012664673,0.0012590338,0.00036626312],"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":[0.0005615334,0.00021981902,0.0036084505,0.00027199843,0.00008832939,0.00016653989,0.000240751,0.73612684,0.021833107,0.08836546,0.0029777272,0.14553946],"study_design_scores_gemma":[0.000008692036,0.000022875409,0.00035239581,0.000005009691,0.0000022411004,0.000026624251,0.000011161456,0.9795251,0.0013733966,0.018509155,0.00015565843,0.000007718253],"about_ca_topic_score_codex":0.0011968736,"about_ca_topic_score_gemma":0.0013580946,"teacher_disagreement_score":0.0023502435,"about_ca_system_score_codex":0.0003951553,"about_ca_system_score_gemma":0.00068427273,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007921759,0.00016679343,0.99077785,0.00012412222,0.000021885175,0.00001909099,0.00003835602,0.00038136748,0.0005486635],"genre_scores_gemma":[0.59259295,0.0005065731,0.4006461,0.00032459272,0.00007795312,0.00020376005,0.0005800699,0.00028573626,0.004782306],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99890685,0.0004941555,0.000061214116,0.00024743934,0.00020734099,0.00008300441],"domain_scores_gemma":[0.99815863,0.0008278332,0.00017185816,0.0002900686,0.00045504086,0.00009659069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015993027,0.0013991472,0.0016408851,0.0006685357,0.00040402715,0.001141247,0.001162679,0.0013013337,0.0018941478],"category_scores_gemma":[0.006059676,0.000520887,0.0011030472,0.0007261016,0.0011637066,0.0014594899,0.0019448828,0.0016328637,0.00071974075],"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":[0.00008702214,0.0000420317,0.00085478224,0.000105260646,0.00008735615,0.00012109247,0.00007273864,0.89740795,0.0020576317,0.020072635,0.0023192551,0.076772265],"study_design_scores_gemma":[0.0000033337374,0.000017955004,0.000075448996,0.000004149837,0.0000027634228,0.000016326843,0.0000061106775,0.9933137,0.00034851348,0.00587072,0.00033666505,0.0000042796237],"about_ca_topic_score_codex":0.0037848244,"about_ca_topic_score_gemma":0.002369964,"teacher_disagreement_score":0.0037848244,"about_ca_system_score_codex":0.0007997833,"about_ca_system_score_gemma":0.0009897782,"threshold_uncertainty_score":0.008458018},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030998236,0.00007791495,0.99553597,0.00011537342,0.000019643348,0.000012000684,0.000014674745,0.0000394798,0.001085174],"genre_scores_gemma":[0.26142704,0.00068317045,0.7332766,0.00023461622,0.00012961534,0.00018461239,0.00021691794,0.00016252181,0.0036847924],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993019,0.0003293046,0.000024438967,0.0001038931,0.00017128064,0.00006914868],"domain_scores_gemma":[0.99830675,0.0010551648,0.0002081366,0.00015929465,0.0001866132,0.000084044514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014078235,0.0010564367,0.0009163285,0.00086151937,0.00046639438,0.0008911687,0.00087829924,0.0012435972,0.001819465],"category_scores_gemma":[0.0042282934,0.00043592052,0.0010474444,0.0011018299,0.0013919253,0.001970479,0.0017908631,0.0023132833,0.00034772666],"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":[0.000026113621,0.00003495902,0.00030515494,0.00011889179,0.000034321583,0.00011389581,0.000086028675,0.7919419,0.0034486821,0.18563756,0.0014238288,0.016828641],"study_design_scores_gemma":[0.0000042533015,0.000020839789,0.00003995064,0.000006714363,0.000002952116,0.000026485937,0.000015425114,0.94346946,0.00042897952,0.05514356,0.00083541,0.0000060349876],"about_ca_topic_score_codex":0.0023313619,"about_ca_topic_score_gemma":0.0025936523,"teacher_disagreement_score":0.0023313619,"about_ca_system_score_codex":0.0007942307,"about_ca_system_score_gemma":0.0010191882,"threshold_uncertainty_score":0.0074453354},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023389685,0.0002618536,0.99638224,0.00022136566,0.000030128575,0.000021806081,0.00014235756,0.00027891455,0.00032235216],"genre_scores_gemma":[0.3341241,0.002219769,0.64782166,0.00067936745,0.0006284476,0.0007999402,0.0022296163,0.00066192646,0.010835134],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99717283,0.0015469313,0.0001404984,0.00041234924,0.00055251375,0.00017484977],"domain_scores_gemma":[0.9742157,0.020240186,0.0009495079,0.0030774593,0.00096933986,0.00054774625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046088807,0.002331656,0.003207283,0.0013108549,0.00085565646,0.00241102,0.004136032,0.0028397432,0.005848203],"category_scores_gemma":[0.033243977,0.0021427923,0.0016905707,0.0021548786,0.0031019787,0.005540083,0.0047743046,0.0063618277,0.0020067368],"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":[0.00014258156,0.00007912689,0.0005368368,0.0002223435,0.0001026114,0.0001541076,0.0001273291,0.78874815,0.0008703912,0.16200961,0.004478551,0.042528387],"study_design_scores_gemma":[0.000009181474,0.00000886034,0.00003349056,0.000009817758,0.000005126964,0.000011111978,0.000005731336,0.93014455,0.0001021174,0.06926962,0.00039090763,0.000009452737],"about_ca_topic_score_codex":0.0065126033,"about_ca_topic_score_gemma":0.008721128,"teacher_disagreement_score":0.0065126033,"about_ca_system_score_codex":0.001346813,"about_ca_system_score_gemma":0.002180054,"threshold_uncertainty_score":0.024374425},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07009641,0.00015648852,0.9271224,0.00015426321,0.000036483292,0.000038919985,0.00002614061,0.0001979595,0.0021709348],"genre_scores_gemma":[0.8822942,0.00014823816,0.11450182,0.0000696112,0.000018083765,0.000083482635,0.000062630636,0.000054859524,0.0027670509],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967563,0.000083220686,0.000012309704,0.000053861007,0.000101557685,0.000073533665],"domain_scores_gemma":[0.9993156,0.0003674066,0.000081562444,0.000044065906,0.0001405449,0.00005077457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054894027,0.000546397,0.00051879627,0.00034459424,0.00041609583,0.0005676851,0.0008055292,0.00038841384,0.00086713204],"category_scores_gemma":[0.001723485,0.00022635775,0.00023039927,0.0005659989,0.0006488752,0.0006664292,0.0006361867,0.0005939017,0.000092761766],"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":[0.000057830082,0.000027692638,0.00024022949,0.000024979852,0.000008182205,0.000026586757,0.000025299678,0.9755037,0.0019469903,0.0075459257,0.0003905612,0.014202105],"study_design_scores_gemma":[0.0000035686355,0.00000786996,0.000018039018,5.892723e-7,9.5123187e-7,0.0000014642605,0.0000024812532,0.9988945,0.00025412068,0.00076593686,0.000049496743,0.0000010143342],"about_ca_topic_score_codex":0.009572663,"about_ca_topic_score_gemma":0.008744954,"teacher_disagreement_score":0.009572663,"about_ca_system_score_codex":0.0010724257,"about_ca_system_score_gemma":0.0019104787,"threshold_uncertainty_score":0.01903385},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071906974,0.00015838153,0.9914432,0.00009703206,0.000032561886,0.00002353505,0.000015964088,0.00013607196,0.00090261153],"genre_scores_gemma":[0.57318324,0.00047350992,0.4192981,0.00016711079,0.00011067914,0.00026311664,0.00018082967,0.0002204937,0.0061029317],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994972,0.00021694021,0.00002401899,0.00009992835,0.00011718693,0.000044572735],"domain_scores_gemma":[0.99860364,0.00095809123,0.00013793098,0.00008446989,0.00015567224,0.000060166116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001532318,0.0011205021,0.0017492931,0.00046446445,0.00038409943,0.0010623969,0.0009654058,0.001306162,0.002153622],"category_scores_gemma":[0.0040094955,0.00057468814,0.00077017717,0.00054238393,0.0010991765,0.0011805868,0.0012439964,0.0012171007,0.00045649536],"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":[0.000076215365,0.00003187731,0.00028487493,0.00007921034,0.000039455637,0.000039225502,0.00002034439,0.9666832,0.0013329467,0.011363597,0.0005409703,0.01950805],"study_design_scores_gemma":[0.0000032223813,0.0000068379086,0.000014823717,0.0000020728196,0.000001418173,0.0000021609114,8.767317e-7,0.9986626,0.00018901302,0.0010303055,0.0000852419,0.0000013531643],"about_ca_topic_score_codex":0.0030692562,"about_ca_topic_score_gemma":0.0024036763,"teacher_disagreement_score":0.0030692562,"about_ca_system_score_codex":0.00070034096,"about_ca_system_score_gemma":0.0014352293,"threshold_uncertainty_score":0.008103788},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028628273,0.0012350522,0.9495226,0.0008163259,0.0002769329,0.00008607205,0.00013576477,0.000766947,0.018532109],"genre_scores_gemma":[0.69379604,0.0022532667,0.24322416,0.00085697323,0.00059550354,0.00062582653,0.00061858795,0.0021359895,0.055893667],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971359,0.0011963318,0.00013551515,0.00045618037,0.0006268961,0.00044916596],"domain_scores_gemma":[0.9823398,0.013290516,0.00092528795,0.0017620797,0.0010519335,0.00063041534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005297177,0.0025500015,0.0029599383,0.0022054927,0.0014143122,0.0027676155,0.0030273108,0.0024756254,0.011332962],"category_scores_gemma":[0.031346075,0.0013633845,0.0020498333,0.0021716582,0.005015867,0.0077191982,0.0065851007,0.0046757646,0.0017556788],"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":[0.00039754435,0.00006782069,0.0004723805,0.00026627275,0.00012256029,0.00015037037,0.00017588145,0.14972638,0.003912935,0.80609465,0.0053039747,0.03330915],"study_design_scores_gemma":[0.000030431967,0.000034259887,0.00014294639,0.00003048623,0.000018607921,0.000057848505,0.000023605495,0.658725,0.0011894173,0.3385186,0.0011909433,0.00003789216],"about_ca_topic_score_codex":0.004022203,"about_ca_topic_score_gemma":0.0024734195,"teacher_disagreement_score":0.011332962,"about_ca_system_score_codex":0.002513495,"about_ca_system_score_gemma":0.0015827992,"threshold_uncertainty_score":0.037912548},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011739804,0.00013675768,0.99663526,0.00006945786,0.00009985111,0.00006245073,0.000036755948,0.000658,0.0011274845],"genre_scores_gemma":[0.055215374,0.00023028924,0.93668604,0.00016795205,0.00015398205,0.00044823834,0.0002650585,0.00057546404,0.0062576523],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988745,0.00039599944,0.00005383376,0.00012403882,0.0004839866,0.00006760049],"domain_scores_gemma":[0.9983321,0.00080264633,0.000066725974,0.0001554024,0.0005266748,0.00011650374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001852464,0.0016410775,0.00210767,0.0011439697,0.0006599061,0.001238503,0.0021438287,0.002486402,0.010686087],"category_scores_gemma":[0.004934362,0.0010404092,0.0010633786,0.0011467066,0.00075339194,0.0014745776,0.0020720698,0.002627061,0.004732334],"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":[0.00052799075,0.00035191223,0.0004436445,0.0005789629,0.00022352973,0.0002472338,0.000111669666,0.46726987,0.016360488,0.066582926,0.020537453,0.42676437],"study_design_scores_gemma":[0.000029298419,0.000042475756,0.00003798812,0.000008320573,0.000005583351,0.000025420048,0.0000025457566,0.9945427,0.00060773944,0.003082739,0.0016076962,0.000007496894],"about_ca_topic_score_codex":0.0030325297,"about_ca_topic_score_gemma":0.0037799734,"teacher_disagreement_score":0.010686087,"about_ca_system_score_codex":0.00071936054,"about_ca_system_score_gemma":0.0018987057,"threshold_uncertainty_score":0.03574854},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012524551,0.00135804,0.980988,0.0003056711,0.000098649296,0.00010402911,0.0002145844,0.0004898101,0.0039165695],"genre_scores_gemma":[0.40948522,0.0022117207,0.57372797,0.00042871237,0.00012982458,0.0006286274,0.00065186934,0.00021181107,0.012524218],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990878,0.00022346628,0.000045232595,0.00014431411,0.0004101884,0.00008899282],"domain_scores_gemma":[0.9975236,0.00081402523,0.00033215695,0.00044395658,0.0007737714,0.000112483205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080970925,0.0006419644,0.00051701587,0.0010393185,0.00063132227,0.00077378296,0.00092731963,0.0008101418,0.002169508],"category_scores_gemma":[0.004992838,0.00020475684,0.00036307503,0.0012050408,0.0009250627,0.0010520788,0.000899224,0.0015805033,0.0010999348],"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":[0.00045763902,0.00010770077,0.00084387016,0.00050129567,0.00005731958,0.00030194368,0.00031741595,0.26102695,0.033459906,0.33903432,0.012142634,0.35174897],"study_design_scores_gemma":[0.000076642056,0.00020563848,0.00035577663,0.00012594895,0.00002599322,0.0006437486,0.000070750284,0.8513069,0.018673716,0.09677621,0.03166029,0.00007845328],"about_ca_topic_score_codex":0.0021186129,"about_ca_topic_score_gemma":0.001726704,"teacher_disagreement_score":0.002169508,"about_ca_system_score_codex":0.00086948014,"about_ca_system_score_gemma":0.0016347279,"threshold_uncertainty_score":0.0072577596},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04092845,0.00037302024,0.952802,0.0006676414,0.00010228527,0.00011473731,0.00009551518,0.0014201615,0.00349614],"genre_scores_gemma":[0.8742796,0.00016568218,0.11979826,0.0003663358,0.00016624993,0.00025467513,0.00018949906,0.00023378842,0.004545952],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989386,0.00028313175,0.000047704136,0.00030943498,0.00018905192,0.00023198762],"domain_scores_gemma":[0.997678,0.0012726076,0.0002335595,0.0003348487,0.0002495704,0.00023151927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001599947,0.0014635099,0.0020759522,0.0004459868,0.0009026896,0.0012274319,0.0025608197,0.0012530128,0.004357079],"category_scores_gemma":[0.0048761,0.00059057726,0.00055048225,0.0006930785,0.0011044156,0.0019134934,0.0023297598,0.0017286415,0.0010569048],"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":[0.00053296465,0.00021752651,0.00080584,0.00011508836,0.00005790749,0.00009751079,0.00011776255,0.9214247,0.003223717,0.0084899645,0.003946301,0.060970817],"study_design_scores_gemma":[0.000038480623,0.000034527806,0.000089113746,0.0000037635505,0.000004930604,0.000020122821,0.000013436186,0.9918943,0.00057725003,0.0069521563,0.0003668831,0.000004935365],"about_ca_topic_score_codex":0.0026751426,"about_ca_topic_score_gemma":0.003555723,"teacher_disagreement_score":0.004357079,"about_ca_system_score_codex":0.0009880733,"about_ca_system_score_gemma":0.001735673,"threshold_uncertainty_score":0.014575839},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101267785,0.008482016,0.8413441,0.005100732,0.00035579232,0.00025069766,0.00062190264,0.0012052851,0.041371666],"genre_scores_gemma":[0.82236254,0.004718932,0.16088523,0.00084854587,0.0004806017,0.00042774004,0.0010088127,0.0007315397,0.008536073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981154,0.00083291007,0.00009793533,0.0002851942,0.0005558287,0.0001127461],"domain_scores_gemma":[0.9811014,0.014124349,0.0009102373,0.0017545877,0.0017793671,0.00033007428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060206736,0.0011084846,0.001532458,0.0018979124,0.0008863351,0.0019048824,0.0017276084,0.00175244,0.0062400317],"category_scores_gemma":[0.050721113,0.00048868626,0.0009889978,0.0016603305,0.002516847,0.004696056,0.0018529702,0.0026852258,0.0007842477],"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":[0.00017794587,0.0002601193,0.015866686,0.00075907016,0.00021912297,0.0004980875,0.00029559055,0.33121532,0.0011873747,0.54367095,0.021259563,0.08459013],"study_design_scores_gemma":[0.000023177668,0.000078562785,0.0027166272,0.00015624658,0.000030502375,0.00029998668,0.000062298415,0.8336538,0.00062198326,0.15613204,0.0061947657,0.000030005605],"about_ca_topic_score_codex":0.003706994,"about_ca_topic_score_gemma":0.0031636907,"teacher_disagreement_score":0.0062400317,"about_ca_system_score_codex":0.0010911522,"about_ca_system_score_gemma":0.0014557276,"threshold_uncertainty_score":0.0318408},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05836824,0.00040841463,0.93834025,0.0001594705,0.000063795225,0.000049510087,0.000025702942,0.00061866984,0.0019659235],"genre_scores_gemma":[0.8867231,0.00015427542,0.11033041,0.000104320694,0.000024776424,0.00006364013,0.000033216296,0.00006024465,0.002506063],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935704,0.00018455459,0.000021693017,0.00011862473,0.00022217419,0.000095867734],"domain_scores_gemma":[0.99867946,0.00061636046,0.00016776775,0.00017470644,0.00029693494,0.0000648264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005887271,0.0007100445,0.00042553435,0.00037901982,0.00055211125,0.00057042006,0.0011736233,0.0005021926,0.0009695856],"category_scores_gemma":[0.0020851574,0.00022533275,0.00029086656,0.00047979728,0.00072314264,0.0009699488,0.00080075784,0.00076539145,0.00020354532],"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":[0.00035033218,0.00008244852,0.0007127463,0.00016877953,0.000048153935,0.00018420162,0.00020603572,0.85333544,0.037418425,0.022558039,0.0015645212,0.083370976],"study_design_scores_gemma":[0.000014403821,0.00006152511,0.00008821038,0.0000064137976,0.000008529067,0.00003554788,0.00001719093,0.9889474,0.0065617627,0.0035345966,0.0007123975,0.000012009058],"about_ca_topic_score_codex":0.0036978072,"about_ca_topic_score_gemma":0.0044435803,"teacher_disagreement_score":0.0036978072,"about_ca_system_score_codex":0.0007896947,"about_ca_system_score_gemma":0.001216538,"threshold_uncertainty_score":0.0073525906},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02951024,0.00018775728,0.9655347,0.0006963012,0.0000464797,0.00007390756,0.00017286903,0.000682704,0.0030950557],"genre_scores_gemma":[0.50899476,0.00026463083,0.4812533,0.00045720005,0.00009236782,0.0003208154,0.00086761866,0.00055467593,0.0071946154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992926,0.00027342734,0.000018338435,0.0002048304,0.000121700024,0.00008899052],"domain_scores_gemma":[0.99633753,0.0026951479,0.00028400365,0.00027242515,0.00022515011,0.00018577889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011707982,0.0010665541,0.001188866,0.00083694165,0.00069209374,0.0010240176,0.0016298798,0.0013367509,0.0032170254],"category_scores_gemma":[0.007730778,0.0008396823,0.00081653846,0.00074824895,0.0016293685,0.0018814658,0.0015909821,0.0019504897,0.00066808733],"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":[0.00013290983,0.000105558385,0.0011435538,0.00012648285,0.00009670854,0.00010843038,0.00007507816,0.87754196,0.0020672486,0.0853799,0.0059675653,0.027254546],"study_design_scores_gemma":[0.000012517955,0.0000074892614,0.000070163835,0.0000046528767,0.0000028730406,0.000005852512,0.0000055537917,0.9681245,0.00019827827,0.03125424,0.00031043534,0.000003527452],"about_ca_topic_score_codex":0.006747699,"about_ca_topic_score_gemma":0.010460766,"teacher_disagreement_score":0.006747699,"about_ca_system_score_codex":0.0017812001,"about_ca_system_score_gemma":0.001928587,"threshold_uncertainty_score":0.013416827},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027650047,0.0003713097,0.96964353,0.0006107849,0.000025943518,0.000018898663,0.00004837559,0.00017834248,0.0014527447],"genre_scores_gemma":[0.82621014,0.0005413291,0.16833457,0.0003343935,0.00009502421,0.00014860423,0.00026024156,0.0002373765,0.0038383221],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99928087,0.00028732675,0.00003913187,0.00016884595,0.0001451786,0.00007870868],"domain_scores_gemma":[0.9954301,0.0032347299,0.0004025022,0.00032543222,0.00042952917,0.00017770607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037959628,0.0011360797,0.0014574323,0.00058820355,0.00042813763,0.0010986468,0.001700891,0.0020269742,0.0014918951],"category_scores_gemma":[0.010298118,0.0006088072,0.00084532966,0.0005354408,0.0019676941,0.003474656,0.0021214818,0.0023081857,0.00027137419],"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":[0.00009448246,0.00003470784,0.0005481871,0.00011296385,0.00004283819,0.00006305255,0.00006938057,0.9086724,0.0019887327,0.07354397,0.001092005,0.013737314],"study_design_scores_gemma":[0.0000020148495,0.0000065264567,0.000045217817,0.0000035345088,0.0000016701666,0.000006028271,0.0000021886947,0.98941857,0.00019290441,0.010262391,0.00005608514,0.0000029654752],"about_ca_topic_score_codex":0.002582094,"about_ca_topic_score_gemma":0.0015546541,"teacher_disagreement_score":0.0037959628,"about_ca_system_score_codex":0.001453955,"about_ca_system_score_gemma":0.0009828901,"threshold_uncertainty_score":0.020075202},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016915053,0.00033827493,0.9949839,0.00035555087,0.000051199208,0.000028180291,0.000056059074,0.00014478211,0.0023505043],"genre_scores_gemma":[0.21854264,0.0015421207,0.7564923,0.0011458899,0.0006964266,0.0007554144,0.00072885444,0.0011581203,0.01893822],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996995,0.0015752679,0.00009748007,0.00044435778,0.0006932154,0.00019470383],"domain_scores_gemma":[0.99439925,0.0041499934,0.00023649668,0.0005424352,0.0004978282,0.00017395153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004075321,0.0018932971,0.0021700829,0.0013127751,0.0007761553,0.0018654596,0.0027205376,0.0021816895,0.0063578715],"category_scores_gemma":[0.016203046,0.0012668686,0.0017336971,0.0019066327,0.0020200296,0.0028290893,0.0039824024,0.0053026443,0.001652539],"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":[0.000119244534,0.00022206795,0.00044605133,0.00039208762,0.00014229573,0.000113606,0.00014115754,0.39929128,0.0022324293,0.47990045,0.016168358,0.100831],"study_design_scores_gemma":[0.000013742758,0.000023294695,0.000067027235,0.000020882087,0.0000134530355,0.000027967235,0.000009902728,0.8116735,0.00035750415,0.18620233,0.0015795018,0.000010820587],"about_ca_topic_score_codex":0.0024502887,"about_ca_topic_score_gemma":0.0037773042,"teacher_disagreement_score":0.0063578715,"about_ca_system_score_codex":0.0016321423,"about_ca_system_score_gemma":0.0020623656,"threshold_uncertainty_score":0.021552622},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008307183,0.029895525,0.8306999,0.0013743007,0.00212352,0.000111601155,0.0005741605,0.0016422701,0.132748],"genre_scores_gemma":[0.027992198,0.062491633,0.57733095,0.002175673,0.00257966,0.00045319519,0.0023351184,0.004988346,0.31965327],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999374,0.000104496816,0.000029584173,0.000121022305,0.00033437068,0.000036518482],"domain_scores_gemma":[0.99965847,0.00015563544,0.000013829459,0.000057242192,0.000094593226,0.000020187035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006241975,0.0016958968,0.0010906871,0.0008784767,0.0004652814,0.0017665488,0.0010405197,0.0010158182,0.044958886],"category_scores_gemma":[0.0021709485,0.00054676825,0.0009742132,0.0014152075,0.00078622316,0.0020979403,0.0011296791,0.0031159637,0.032916673],"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":[0.000047330028,0.00007656975,0.00012177303,0.00096611516,0.00006190739,0.00008183083,0.000134072,0.023633992,0.0036612027,0.2548273,0.24831563,0.46807232],"study_design_scores_gemma":[0.000019340765,0.00003654212,0.00022806157,0.00038188807,0.00003157888,0.00029241433,0.00003388698,0.042261217,0.0040770657,0.20258379,0.7500225,0.000031822517],"about_ca_topic_score_codex":0.0012591411,"about_ca_topic_score_gemma":0.0017300682,"teacher_disagreement_score":0.044958886,"about_ca_system_score_codex":0.00072219194,"about_ca_system_score_gemma":0.0009313985,"threshold_uncertainty_score":0.15040249},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08773148,0.0009557977,0.9073011,0.00026174847,0.000102525344,0.000060186758,0.000044637094,0.0007200751,0.0028223821],"genre_scores_gemma":[0.9346015,0.00021937228,0.06282161,0.00011456196,0.000029424918,0.000048840066,0.000030799925,0.00004348306,0.002090474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992538,0.00021464328,0.000027918204,0.00013947579,0.00023617203,0.00012795514],"domain_scores_gemma":[0.99834406,0.0007352286,0.00022420961,0.0002456086,0.00037725177,0.000073643874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066463795,0.0007144364,0.0004512805,0.00043078,0.0006582139,0.00066704454,0.0011561771,0.0005173491,0.0009351919],"category_scores_gemma":[0.0022247583,0.00023076488,0.0002877654,0.00057324633,0.0007935291,0.0012425038,0.00084735575,0.0007664709,0.0002067339],"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":[0.00046355874,0.00009579788,0.00096443354,0.00024645988,0.00005822983,0.00023385927,0.00027718503,0.83282745,0.04366408,0.029525962,0.002012227,0.08963075],"study_design_scores_gemma":[0.000018602323,0.00011396694,0.00014286154,0.000011660724,0.00001513303,0.000066289314,0.000036106827,0.9805958,0.011484394,0.0061585014,0.0013379093,0.000018769224],"about_ca_topic_score_codex":0.0030418336,"about_ca_topic_score_gemma":0.0038003975,"teacher_disagreement_score":0.0030418336,"about_ca_system_score_codex":0.0008580536,"about_ca_system_score_gemma":0.0013076146,"threshold_uncertainty_score":0.0062256455},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04493507,0.0011548765,0.7830666,0.0032726259,0.001412288,0.00024235455,0.00094190973,0.010033144,0.15494114],"genre_scores_gemma":[0.4549551,0.0013345418,0.44659743,0.0018468244,0.0004924501,0.00040200655,0.00298494,0.0005830064,0.090803586],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997818,0.000044094664,0.000012725327,0.000048538368,0.0000772382,0.000035603192],"domain_scores_gemma":[0.99971455,0.000056857694,0.000029982994,0.00006771867,0.000085383545,0.00004548333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003677257,0.00032763928,0.00019125069,0.00033754986,0.00069966353,0.0019187059,0.0011003216,0.0006495936,0.006295567],"category_scores_gemma":[0.00046943675,0.00018094922,0.00026144218,0.0004644275,0.00044823313,0.00189399,0.0010793174,0.0007765534,0.0022216411],"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":[0.00062642724,0.00021619059,0.0015762624,0.00025370799,0.00006545325,0.000610792,0.0002563598,0.06839597,0.038779806,0.39929584,0.13373029,0.3561929],"study_design_scores_gemma":[0.00008429642,0.0002527204,0.0007812322,0.00005886416,0.00006823968,0.00048346902,0.00009399373,0.53267413,0.017856032,0.074715026,0.37287012,0.00006185423],"about_ca_topic_score_codex":0.0026034948,"about_ca_topic_score_gemma":0.005964404,"teacher_disagreement_score":0.006295567,"about_ca_system_score_codex":0.000791865,"about_ca_system_score_gemma":0.0008580944,"threshold_uncertainty_score":0.021060765},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19635752,0.0004137531,0.7963958,0.00043885427,0.00019901888,0.0002936527,0.00012224361,0.0024520094,0.0033271073],"genre_scores_gemma":[0.86663693,0.000079311656,0.13114166,0.00013707628,0.000043995307,0.00016397201,0.00015990346,0.00014075961,0.0014963854],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991574,0.00019342384,0.000057724024,0.00021224134,0.0001651264,0.00021410089],"domain_scores_gemma":[0.9981864,0.0005796683,0.00016706304,0.00041798316,0.0002940482,0.00035481656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014847578,0.0007360349,0.00091516634,0.00041917732,0.0012842531,0.000815767,0.002219338,0.0006503629,0.0031067657],"category_scores_gemma":[0.0039981944,0.00043894723,0.00046879234,0.0006298189,0.0007069235,0.001103744,0.0012896255,0.001010168,0.0005457485],"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":[0.001104648,0.0005788264,0.004274349,0.00017261153,0.00007093543,0.00021191873,0.00024534078,0.8051181,0.019124199,0.009148265,0.0072176848,0.15273319],"study_design_scores_gemma":[0.000027186095,0.00006113839,0.0002336361,0.0000025507513,0.000004821788,0.000014582857,0.000032215423,0.99470323,0.0022064948,0.0022892924,0.00041899635,0.0000058095784],"about_ca_topic_score_codex":0.004169896,"about_ca_topic_score_gemma":0.0073868823,"teacher_disagreement_score":0.004169896,"about_ca_system_score_codex":0.0012436492,"about_ca_system_score_gemma":0.0023449846,"threshold_uncertainty_score":0.010393202},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010063586,0.0008593524,0.9852446,0.0011238595,0.00008668993,0.00006672628,0.00010834319,0.00019062139,0.0022562332],"genre_scores_gemma":[0.6064378,0.0030342988,0.37333,0.0011971182,0.0012771457,0.0014433227,0.0011464234,0.0009277832,0.011206119],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915172,0.004098729,0.00038309503,0.0008924134,0.002583162,0.00052541716],"domain_scores_gemma":[0.8751484,0.11268695,0.0031183637,0.0038197937,0.0038309265,0.0013955631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0142687755,0.0026734956,0.0032366046,0.0028318914,0.0010184995,0.0041443203,0.0041504414,0.003362385,0.005964658],"category_scores_gemma":[0.0935134,0.0016491055,0.0021850013,0.0026501669,0.0043607503,0.009517741,0.0050436,0.008550966,0.0006785082],"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":[0.00039990156,0.00023694515,0.002077112,0.0004658273,0.00021112307,0.00013757352,0.00017493572,0.5233129,0.0014981665,0.43379724,0.0036643913,0.034023996],"study_design_scores_gemma":[0.000017711973,0.00003387019,0.00021112419,0.000020421323,0.000015435271,0.000019134211,0.000010144732,0.8861894,0.00024969465,0.1129735,0.00024676585,0.000012709355],"about_ca_topic_score_codex":0.002983883,"about_ca_topic_score_gemma":0.0026475566,"teacher_disagreement_score":0.0142687755,"about_ca_system_score_codex":0.0038132619,"about_ca_system_score_gemma":0.0033635644,"threshold_uncertainty_score":0.07546139},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038355503,0.00934392,0.88106114,0.022748452,0.0025940263,0.00018635596,0.0010050462,0.0033121498,0.041393366],"genre_scores_gemma":[0.6341216,0.0077681076,0.2940076,0.007481746,0.0051115844,0.0012805685,0.0014855597,0.0067886584,0.04195458],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9942772,0.0022488174,0.00021962293,0.0014829391,0.0010678063,0.0007036189],"domain_scores_gemma":[0.94353646,0.044297203,0.0016791944,0.0054267333,0.003344937,0.0017154011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011418813,0.0025527002,0.0029188334,0.0012677455,0.0016874277,0.0032151497,0.005324631,0.0040389732,0.013068645],"category_scores_gemma":[0.09868684,0.0011280156,0.0020218713,0.001268147,0.004971556,0.010839288,0.004136118,0.015146518,0.0046397555],"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":[0.0014523708,0.00031064043,0.0021906963,0.0008807104,0.00020907428,0.00022826814,0.00044892955,0.09397067,0.0041539418,0.7678391,0.042856097,0.08545947],"study_design_scores_gemma":[0.00014833813,0.00018207316,0.0005397063,0.00021287291,0.00005437232,0.00014071845,0.000076567725,0.42719868,0.0030245446,0.55944484,0.008907287,0.000070085276],"about_ca_topic_score_codex":0.0021959655,"about_ca_topic_score_gemma":0.0012133614,"teacher_disagreement_score":0.013068645,"about_ca_system_score_codex":0.0021175465,"about_ca_system_score_gemma":0.0027407606,"threshold_uncertainty_score":0.06038922},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030055356,0.00027767674,0.99286413,0.00014431585,0.00010079069,0.000043318458,0.00004224793,0.00079605466,0.0027259192],"genre_scores_gemma":[0.13909699,0.00047577283,0.8503984,0.00047031196,0.00019867427,0.00031956562,0.0003955815,0.0008181753,0.007826474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993736,0.00019060382,0.000024175613,0.000083499974,0.0002590623,0.00006903971],"domain_scores_gemma":[0.99924767,0.0003252413,0.00005215596,0.00012172403,0.0001943991,0.00005883243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012004,0.0012363255,0.001534389,0.0006704367,0.00045305895,0.0008813819,0.0019985132,0.0012235297,0.006062528],"category_scores_gemma":[0.003088849,0.0005353767,0.0009065221,0.0005492349,0.0007437323,0.0013222138,0.0013906693,0.0019947393,0.0025754317],"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":[0.00027721364,0.00017407072,0.00076592574,0.00040642807,0.0001638923,0.00020798779,0.00014176487,0.6620491,0.009882415,0.08955857,0.017043281,0.21932939],"study_design_scores_gemma":[0.00003179731,0.000032021126,0.000042960095,0.0000092729715,0.0000070572637,0.00002739785,0.0000057874686,0.9893294,0.00063716003,0.0069328896,0.0029360573,0.000008309685],"about_ca_topic_score_codex":0.0030696997,"about_ca_topic_score_gemma":0.00419851,"teacher_disagreement_score":0.006062528,"about_ca_system_score_codex":0.00056909124,"about_ca_system_score_gemma":0.0018171421,"threshold_uncertainty_score":0.020281196},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048692017,0.00003131,0.99379337,0.00005333996,0.00001677381,0.000024111892,0.000016782404,0.0005636797,0.0006314392],"genre_scores_gemma":[0.41848806,0.0001065764,0.5787512,0.00011521612,0.00003190819,0.00021994406,0.00020852483,0.00039728626,0.0016813073],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896646,0.00036053974,0.000066388806,0.00017687194,0.00035434065,0.00007538773],"domain_scores_gemma":[0.99756765,0.0011435187,0.00025244727,0.00030681648,0.0006658207,0.00006377712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00194358,0.0012518925,0.0011975471,0.0010976472,0.0006367869,0.0011179104,0.0014124163,0.001027288,0.0015204086],"category_scores_gemma":[0.008201815,0.0008916788,0.00078897376,0.0005404833,0.00072848244,0.0013017029,0.0011178853,0.0015863035,0.00061894464],"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":[0.000025369873,0.000033070002,0.00070475636,0.000031310767,0.000029673742,0.000024356075,0.000044891127,0.9631088,0.0018395944,0.0030388099,0.000489561,0.030629842],"study_design_scores_gemma":[0.000002074322,0.0000057491343,0.000037081114,0.000001969131,0.0000018078208,0.0000034702,0.0000017096429,0.998809,0.00044035606,0.0004405436,0.0002536469,0.0000026726273],"about_ca_topic_score_codex":0.014796275,"about_ca_topic_score_gemma":0.011743981,"teacher_disagreement_score":0.014796275,"about_ca_system_score_codex":0.0012940759,"about_ca_system_score_gemma":0.0019511544,"threshold_uncertainty_score":0.029420316},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029777156,0.00013671372,0.96843016,0.00015199391,0.000017306882,0.000030848674,0.000024600246,0.00012976029,0.0013014262],"genre_scores_gemma":[0.7618698,0.00021622845,0.23522708,0.00008152773,0.000024565827,0.0001379669,0.000068587,0.000054423246,0.0023198635],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995789,0.00014504834,0.000015453152,0.000051775427,0.00014678694,0.00006203696],"domain_scores_gemma":[0.9984503,0.0010211528,0.00016043485,0.00015377367,0.00016767104,0.000046640427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073843624,0.0005015021,0.00043692708,0.00039707925,0.00039470126,0.00054756016,0.0005794712,0.0004562148,0.00091524224],"category_scores_gemma":[0.0031603286,0.00020075058,0.0002310141,0.00063476095,0.0009485671,0.0007886329,0.0008882542,0.0006860554,0.0001644051],"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":[0.00008462867,0.00002391851,0.00029561558,0.000060413007,0.000011305483,0.000059690054,0.00011900651,0.9022829,0.008286139,0.054597065,0.00071436947,0.033465046],"study_design_scores_gemma":[0.000007022738,0.00002117337,0.00003520013,0.000006046997,0.000002488133,0.000014769318,0.00001926047,0.9846585,0.0020561437,0.012744321,0.00042969137,0.0000053795156],"about_ca_topic_score_codex":0.0027548962,"about_ca_topic_score_gemma":0.0028238748,"teacher_disagreement_score":0.0027548962,"about_ca_system_score_codex":0.001023389,"about_ca_system_score_gemma":0.0014299436,"threshold_uncertainty_score":0.007425189},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032273237,0.0005307575,0.9623251,0.00086165516,0.000041083986,0.00009071495,0.00008882379,0.00027692935,0.0035117797],"genre_scores_gemma":[0.71830994,0.0006918658,0.2744629,0.00028961126,0.00014769926,0.00041108218,0.00031117385,0.00045461743,0.0049210745],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962102,0.0018014663,0.00020821969,0.0004751347,0.0009576462,0.0003473764],"domain_scores_gemma":[0.94168794,0.051018704,0.0022818758,0.0020993568,0.0021328724,0.0007792558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007138262,0.0011986232,0.0017369665,0.0008687198,0.0007003837,0.0023713107,0.0021141968,0.0019210697,0.002488876],"category_scores_gemma":[0.03992485,0.0009017689,0.0014687049,0.00060029747,0.002942204,0.0032625115,0.0034781497,0.0034462055,0.0004277982],"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":[0.0002055212,0.00003244108,0.0011109522,0.00016107562,0.00004898732,0.00013972021,0.00016140792,0.94259644,0.0011840098,0.04175721,0.00074789516,0.011854406],"study_design_scores_gemma":[0.000006379036,0.000010366064,0.000049255144,0.000007194023,0.0000037048048,0.000008591925,0.000006142539,0.9901709,0.0002465281,0.009376916,0.00011047016,0.0000035866751],"about_ca_topic_score_codex":0.0057407725,"about_ca_topic_score_gemma":0.003384124,"teacher_disagreement_score":0.007138262,"about_ca_system_score_codex":0.0018503853,"about_ca_system_score_gemma":0.002154079,"threshold_uncertainty_score":0.037751198},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07246953,0.0016383809,0.9149279,0.0007265492,0.00024487727,0.000133117,0.00016650387,0.00674055,0.0029525005],"genre_scores_gemma":[0.8089059,0.000468527,0.18678103,0.00056628167,0.00015845476,0.00015975558,0.0004355279,0.00018432982,0.0023401107],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844235,0.0004716714,0.00010563386,0.00041653664,0.00038136911,0.00018237314],"domain_scores_gemma":[0.9969683,0.0013740871,0.0001719383,0.0006941138,0.0006054959,0.00018596566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037471664,0.0010688254,0.0011907989,0.00065516663,0.00053310103,0.0012601808,0.0026081942,0.001228628,0.0013290712],"category_scores_gemma":[0.008585348,0.0003640557,0.00039456753,0.0006829128,0.0007734674,0.0028303028,0.0016694114,0.0020071322,0.0005236269],"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":[0.001033858,0.00050798984,0.0035895007,0.00025470724,0.00012229285,0.00011626733,0.00015484395,0.4720315,0.010971573,0.009998057,0.008102885,0.49311656],"study_design_scores_gemma":[0.00005250727,0.00016441596,0.00029103056,0.000010983211,0.000014431858,0.00004033173,0.000019003348,0.99019885,0.0029946128,0.0049842745,0.0012181138,0.000011430375],"about_ca_topic_score_codex":0.0033281078,"about_ca_topic_score_gemma":0.0032083949,"teacher_disagreement_score":0.0037471664,"about_ca_system_score_codex":0.0008299664,"about_ca_system_score_gemma":0.0015650226,"threshold_uncertainty_score":0.019817114},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09577498,0.00069736876,0.8898723,0.0026477352,0.00015581651,0.000054866945,0.0001988773,0.00024916793,0.010348794],"genre_scores_gemma":[0.9155753,0.0006830004,0.06716822,0.0006016569,0.00014064582,0.00017226403,0.00018632755,0.00016847506,0.015304111],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995759,0.00016257814,0.000027815246,0.00008182064,0.00010913377,0.000042754316],"domain_scores_gemma":[0.99789774,0.0010941542,0.00030333883,0.00014857049,0.0003111106,0.00024508874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018672327,0.0005489073,0.0008927959,0.0008816666,0.000608231,0.0016436231,0.0010853042,0.001916252,0.0038353847],"category_scores_gemma":[0.009682279,0.0004096366,0.00087800977,0.00045960766,0.0027864194,0.0023585823,0.0022556505,0.0017894334,0.00040572247],"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":[0.000040430255,0.00003486672,0.0015095513,0.00008613424,0.000039449384,0.00021716404,0.00018971846,0.46812966,0.0035874022,0.51692456,0.0022183487,0.0070227175],"study_design_scores_gemma":[0.0000038170633,0.0000073196843,0.00010242964,0.000006623886,0.0000023613418,0.000018215696,0.000008323965,0.962591,0.00009815144,0.036890276,0.00026541713,0.000006130558],"about_ca_topic_score_codex":0.0048890417,"about_ca_topic_score_gemma":0.0025864942,"teacher_disagreement_score":0.0048890417,"about_ca_system_score_codex":0.00156274,"about_ca_system_score_gemma":0.00085877086,"threshold_uncertainty_score":0.012830615},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004458636,0.000084423926,0.99381375,0.00011678235,0.00006663304,0.000036552585,0.000017219007,0.00015893504,0.0012471076],"genre_scores_gemma":[0.4333465,0.00017349757,0.55844086,0.00022603871,0.00014336414,0.00030964616,0.00009590049,0.00016842604,0.007095744],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992742,0.00028375973,0.000024556972,0.000106611835,0.00022491365,0.00008605355],"domain_scores_gemma":[0.99908483,0.000499148,0.00004300252,0.00008130716,0.00021251697,0.00007918725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022715242,0.0007059446,0.0014757694,0.0005178519,0.000692038,0.0014236389,0.0017994075,0.0014726655,0.004694086],"category_scores_gemma":[0.0031730146,0.0005146455,0.000477298,0.00066638057,0.0010306077,0.0011378174,0.001698289,0.0016517383,0.00062313734],"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":[0.00028727457,0.00016814444,0.00020519605,0.00006588972,0.000048872243,0.000047771136,0.000045630597,0.8854079,0.0024706821,0.03952527,0.0030775813,0.06864976],"study_design_scores_gemma":[0.0000129265345,0.000010376515,0.000009850659,0.0000013198891,0.0000019136444,0.000004240693,0.0000014148748,0.9966288,0.00012206745,0.0030424225,0.0001627376,0.0000018379976],"about_ca_topic_score_codex":0.003250218,"about_ca_topic_score_gemma":0.0036973257,"teacher_disagreement_score":0.004694086,"about_ca_system_score_codex":0.0011007217,"about_ca_system_score_gemma":0.002538497,"threshold_uncertainty_score":0.01570326},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067089996,0.0003568916,0.9907816,0.00040909686,0.000052615185,0.000043710425,0.00007228899,0.00027264698,0.0013020998],"genre_scores_gemma":[0.49389482,0.0005970689,0.49422276,0.00050470594,0.00023344814,0.00065349287,0.00060723815,0.0006211371,0.008665317],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814916,0.00097482186,0.00007103673,0.00027660467,0.00032097998,0.00020741958],"domain_scores_gemma":[0.9909368,0.0071442793,0.00048188833,0.0005872917,0.00051494915,0.00033482086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004792057,0.0020705538,0.0027196156,0.00077491085,0.0008806658,0.0018613907,0.0031433557,0.0030880782,0.0051499126],"category_scores_gemma":[0.017147794,0.00128466,0.0011798284,0.0010825312,0.00237594,0.0032534546,0.0039100423,0.0051888316,0.00097468577],"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":[0.00021519783,0.00009514022,0.00028496873,0.00013076192,0.000043523854,0.000048998743,0.00008133863,0.90264773,0.0006885063,0.07152338,0.0028440852,0.021396386],"study_design_scores_gemma":[0.0000110419105,0.000009271991,0.000011837319,0.000003819062,0.0000023600405,0.0000027164597,0.00000298252,0.9907979,0.00005625971,0.0090006525,0.000098716555,0.000002459609],"about_ca_topic_score_codex":0.007857491,"about_ca_topic_score_gemma":0.012837682,"teacher_disagreement_score":0.007857491,"about_ca_system_score_codex":0.0024625596,"about_ca_system_score_gemma":0.0036496872,"threshold_uncertainty_score":0.02534306},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009845194,0.00018109361,0.9872613,0.00041191845,0.000090476846,0.00002070774,0.000022928372,0.00009182832,0.002074568],"genre_scores_gemma":[0.4850312,0.0007731048,0.49287763,0.00050374767,0.00031687666,0.0002512071,0.00021500287,0.00049239973,0.019538848],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930036,0.00036676053,0.000021403443,0.00010735474,0.00015406922,0.000050009985],"domain_scores_gemma":[0.99754757,0.0015525668,0.00017087691,0.00020269236,0.0003700101,0.00015618045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026294584,0.00071419403,0.0014187408,0.00045834915,0.00038802892,0.0012752212,0.0016649211,0.002353093,0.0030523515],"category_scores_gemma":[0.0077632354,0.0006000235,0.0006346962,0.0005031737,0.002188766,0.0024985955,0.0022201196,0.0023494062,0.00049916666],"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":[0.00018664089,0.000096999,0.00043761168,0.00025282367,0.0000549634,0.0001099434,0.00008939597,0.65315866,0.0034453012,0.31851476,0.0033808576,0.020272022],"study_design_scores_gemma":[0.0000051861557,0.0000056847043,0.000020899393,0.0000035165492,0.000002299386,0.000006124327,0.0000022163586,0.98939157,0.00017653829,0.010144841,0.00023767266,0.0000034809473],"about_ca_topic_score_codex":0.0025740026,"about_ca_topic_score_gemma":0.0019162474,"teacher_disagreement_score":0.0030523515,"about_ca_system_score_codex":0.0007373305,"about_ca_system_score_gemma":0.0019684096,"threshold_uncertainty_score":0.013906062},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027470453,0.00039976905,0.9650703,0.0003595419,0.000112240436,0.00007833755,0.00007561872,0.0030412942,0.003392477],"genre_scores_gemma":[0.72604257,0.00032075838,0.26592398,0.0003325493,0.00007442935,0.00024208685,0.00023514578,0.00039548567,0.0064329444],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952006,0.00011889293,0.00003144493,0.0001119012,0.0001506094,0.00006703001],"domain_scores_gemma":[0.99877197,0.0005573725,0.0001235487,0.00024405574,0.00021943336,0.000083524705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012662465,0.0011422917,0.00085641094,0.0003643135,0.00036097888,0.00085566135,0.0018047463,0.00095080875,0.0028432154],"category_scores_gemma":[0.0057236026,0.0005181632,0.00040332464,0.00032574066,0.0009963585,0.0022862703,0.0013365186,0.0024130922,0.001013347],"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":[0.00036877312,0.00023749164,0.0017302774,0.00015747394,0.000087234155,0.00010938099,0.00010773111,0.70474285,0.009188993,0.030439675,0.006478163,0.2463519],"study_design_scores_gemma":[0.000012494497,0.000037469177,0.000078994766,0.000006009717,0.00000531899,0.0000144377345,0.0000040806813,0.9916957,0.0030062716,0.004465789,0.00066844077,0.0000049367018],"about_ca_topic_score_codex":0.004237676,"about_ca_topic_score_gemma":0.0053248988,"teacher_disagreement_score":0.004237676,"about_ca_system_score_codex":0.0011052882,"about_ca_system_score_gemma":0.0014558772,"threshold_uncertainty_score":0.009511471},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004289663,0.042273317,0.639558,0.0036159293,0.0015055981,0.00004844585,0.00034575062,0.00110374,0.30725947],"genre_scores_gemma":[0.13073613,0.034404267,0.22494842,0.0014002583,0.0024622595,0.0002490791,0.000915546,0.0012329087,0.6036511],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99980754,0.000042228698,0.0000075779208,0.00003949918,0.00009131059,0.000011874121],"domain_scores_gemma":[0.9997987,0.000110897716,0.00001070008,0.000041463954,0.000027115504,0.000011029592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003048925,0.0009128085,0.001198315,0.0005827028,0.0003164366,0.0013484258,0.00052051875,0.00065382704,0.018857507],"category_scores_gemma":[0.0009985979,0.00037757834,0.0004953763,0.0011052266,0.0009757329,0.0015395111,0.0009436799,0.0016182577,0.007442093],"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":[0.00002740707,0.000050434704,0.00017475132,0.0003382221,0.00005741583,0.000035823574,0.00008317133,0.033896923,0.0013954284,0.41793856,0.11390233,0.4320996],"study_design_scores_gemma":[0.000010964984,0.000033011846,0.00042436487,0.00011877144,0.000023249957,0.00010292583,0.000027117307,0.07551809,0.0012419265,0.7152566,0.20722587,0.000017073484],"about_ca_topic_score_codex":0.0005995907,"about_ca_topic_score_gemma":0.0008968222,"teacher_disagreement_score":0.018857507,"about_ca_system_score_codex":0.00052640936,"about_ca_system_score_gemma":0.00035122977,"threshold_uncertainty_score":0.06308466},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009390961,0.0003662884,0.9836944,0.00065223844,0.000089098656,0.000104647515,0.00015693414,0.0012811444,0.004264342],"genre_scores_gemma":[0.5273408,0.0008538045,0.4603399,0.0008234943,0.00041606033,0.000609398,0.0006460966,0.00070222706,0.008268206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99322987,0.0021460655,0.0004091647,0.0009677916,0.0025663057,0.00068079587],"domain_scores_gemma":[0.9888192,0.0048500677,0.00079536356,0.0041197212,0.0010588442,0.00035678627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043177884,0.0012070823,0.0018146029,0.0011857192,0.0014436742,0.003596361,0.0023180179,0.0019035237,0.005754351],"category_scores_gemma":[0.018153993,0.0007793843,0.0016138002,0.002262977,0.0032209053,0.008698073,0.006176515,0.004766347,0.002677962],"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":[0.00040441685,0.00017359018,0.000798712,0.00028282215,0.000072316245,0.0002572962,0.00038521312,0.06797391,0.007840191,0.7880203,0.009254201,0.124537006],"study_design_scores_gemma":[0.00005016938,0.00013122841,0.00012135486,0.000052412153,0.000029407003,0.00027412068,0.000055921522,0.44721845,0.009199502,0.5345895,0.008231298,0.000046682624],"about_ca_topic_score_codex":0.00058699475,"about_ca_topic_score_gemma":0.00056960055,"teacher_disagreement_score":0.005754351,"about_ca_system_score_codex":0.0018402236,"about_ca_system_score_gemma":0.0029113933,"threshold_uncertainty_score":0.022834957},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049198004,0.00021815476,0.9927913,0.00012289955,0.000042477408,0.000048452974,0.000017799524,0.00027611348,0.0015630441],"genre_scores_gemma":[0.32504848,0.0004173092,0.6673307,0.00032610944,0.00008946542,0.000354682,0.000109543114,0.0004900995,0.0058336537],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99868387,0.00055199536,0.00009775776,0.00014223698,0.00041715446,0.0001070173],"domain_scores_gemma":[0.99510926,0.002822018,0.00047772797,0.00089911284,0.0005152207,0.00017669093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035737439,0.001212988,0.0011853222,0.0009322975,0.00078712724,0.0014962443,0.0019926168,0.002181839,0.0030510793],"category_scores_gemma":[0.013379499,0.0005404936,0.0013091062,0.0005491412,0.0021946619,0.0014803656,0.0028450736,0.0031297542,0.00089230185],"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":[0.00044701743,0.00011937437,0.0006313733,0.00025707632,0.000068894886,0.00021884206,0.00039516098,0.6612674,0.01695854,0.23275273,0.0033103607,0.08357329],"study_design_scores_gemma":[0.000016761556,0.000051724935,0.00004231901,0.000030519197,0.000008600335,0.000025940117,0.000008783771,0.98427886,0.0026906577,0.011667739,0.0011641901,0.000013903731],"about_ca_topic_score_codex":0.0019057973,"about_ca_topic_score_gemma":0.0018642135,"teacher_disagreement_score":0.0035737439,"about_ca_system_score_codex":0.0013174696,"about_ca_system_score_gemma":0.0012034711,"threshold_uncertainty_score":0.018899977},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006301013,0.05540363,0.90398663,0.0012130727,0.0006092579,0.00007527978,0.0005202492,0.0014889251,0.036072835],"genre_scores_gemma":[0.031114133,0.10869724,0.7984902,0.0011748797,0.0014157644,0.00047452823,0.002373106,0.001509716,0.054750342],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993216,0.000099770725,0.00006444577,0.000109920955,0.00036797478,0.000036271907],"domain_scores_gemma":[0.99948347,0.0002610397,0.0000286519,0.00005419698,0.00015294754,0.000019675927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008685461,0.0018482439,0.0011864123,0.0011874608,0.0003763348,0.0020834624,0.001541344,0.001736321,0.011927693],"category_scores_gemma":[0.0016602364,0.00080748706,0.0011866541,0.0028841195,0.0007132364,0.0021133309,0.0012827335,0.003553468,0.009069305],"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":[0.00004402256,0.00007758985,0.00029305264,0.0013607129,0.00010143063,0.0000997575,0.000067469824,0.11264703,0.0021973478,0.16856791,0.06550134,0.6490423],"study_design_scores_gemma":[0.000025792588,0.000075688346,0.00040418797,0.0005689203,0.00004182699,0.0003670468,0.00003004803,0.29948497,0.0032223691,0.25431776,0.44139203,0.00006934996],"about_ca_topic_score_codex":0.0021962987,"about_ca_topic_score_gemma":0.0020594874,"teacher_disagreement_score":0.011927693,"about_ca_system_score_codex":0.0010407368,"about_ca_system_score_gemma":0.0011734504,"threshold_uncertainty_score":0.03990209},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01017395,0.00018503904,0.98806727,0.00013673518,0.00004162122,0.000018110073,0.000012368737,0.0002965509,0.0010684066],"genre_scores_gemma":[0.87514657,0.00020339168,0.122000694,0.00018373558,0.000061202714,0.000102705235,0.00005720749,0.00011574098,0.002128659],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99938357,0.00021118081,0.000028578252,0.00012738838,0.00015649058,0.000092744485],"domain_scores_gemma":[0.9989281,0.00057851645,0.00013910943,0.00010162759,0.00019694093,0.000055672248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016664887,0.0009815155,0.0010995043,0.0003544137,0.0005065406,0.0008613006,0.0010794532,0.00080097426,0.0010621389],"category_scores_gemma":[0.003955798,0.0003960627,0.0005244636,0.0004544489,0.0009964268,0.001011379,0.0014475425,0.001432937,0.00021780883],"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":[0.00007190042,0.00004599297,0.00037958586,0.00004369019,0.000028734627,0.000036251713,0.000039138435,0.9569364,0.001449208,0.009187627,0.00077718205,0.031004159],"study_design_scores_gemma":[0.00000405073,0.000014026189,0.000028651079,0.000002165034,0.0000018664061,0.0000044201493,0.0000025866511,0.9976997,0.00019193381,0.0019240773,0.00012425693,0.0000022110814],"about_ca_topic_score_codex":0.00407553,"about_ca_topic_score_gemma":0.003622527,"teacher_disagreement_score":0.00407553,"about_ca_system_score_codex":0.00069662853,"about_ca_system_score_gemma":0.0012419908,"threshold_uncertainty_score":0.008813322},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065462464,0.00015160706,0.9923368,0.000095991796,0.000022708778,0.000036534446,0.0000069033526,0.00006090157,0.00074229465],"genre_scores_gemma":[0.4966845,0.00064278225,0.49863467,0.0001464279,0.000116669595,0.00039563933,0.00009948198,0.00014749994,0.0031323074],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99882025,0.00059957843,0.000041598512,0.00012742153,0.00032723884,0.00008394416],"domain_scores_gemma":[0.99628806,0.0027106162,0.00019029735,0.00012931293,0.00053131825,0.00015043498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004979573,0.0010774384,0.0013300038,0.0007583166,0.00049029157,0.0008296465,0.0014528795,0.0014360388,0.0015768823],"category_scores_gemma":[0.009552323,0.00055389595,0.00096222956,0.0005575425,0.0015678625,0.0010575232,0.0017108921,0.0017636654,0.00029511072],"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":[0.00011703495,0.00005085199,0.0007145785,0.0001377643,0.00006281,0.00008833327,0.000068821515,0.9516546,0.0018683788,0.026520928,0.00052203005,0.018193806],"study_design_scores_gemma":[0.0000044683893,0.000017142946,0.000034179477,0.0000027787971,0.0000023472053,0.000006590658,0.0000023606924,0.9984267,0.0001483851,0.0012685981,0.00008397841,0.0000024746994],"about_ca_topic_score_codex":0.003534356,"about_ca_topic_score_gemma":0.002061975,"teacher_disagreement_score":0.004979573,"about_ca_system_score_codex":0.00078319764,"about_ca_system_score_gemma":0.0019187368,"threshold_uncertainty_score":0.026334763},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020024773,0.000113639304,0.97384214,0.00029123056,0.00002677884,0.00009583737,0.0001888166,0.0008524111,0.004564449],"genre_scores_gemma":[0.16921502,0.00017347337,0.82376325,0.00016285392,0.000040508523,0.00022359614,0.0006565536,0.00031561012,0.0054490874],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994295,0.00010291171,0.00002479685,0.00016137026,0.00019047421,0.000090919435],"domain_scores_gemma":[0.99903154,0.00056092953,0.00009394523,0.00017704227,0.00008385501,0.000052732783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007445357,0.0012288919,0.0009081128,0.0005463093,0.00052390475,0.0010071271,0.0012858834,0.0009021913,0.007970851],"category_scores_gemma":[0.0039599994,0.00064089336,0.0008340489,0.00087434566,0.0008335814,0.0029159593,0.00204367,0.0017065566,0.0013376169],"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":[0.00043112907,0.00015062679,0.0008801426,0.0004272403,0.000054998633,0.00016637173,0.00029717095,0.55249983,0.0112248855,0.127169,0.010702487,0.29599613],"study_design_scores_gemma":[0.000049705905,0.0000862343,0.00012169037,0.000016384438,0.000010328038,0.00006706756,0.000036043028,0.9168012,0.003003065,0.075710334,0.004086116,0.000011760798],"about_ca_topic_score_codex":0.0032197544,"about_ca_topic_score_gemma":0.00446638,"teacher_disagreement_score":0.007970851,"about_ca_system_score_codex":0.0010052009,"about_ca_system_score_gemma":0.0014589264,"threshold_uncertainty_score":0.026665092},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012466753,0.00057991105,0.9832827,0.0003766292,0.00006088106,0.000023925597,0.00005838003,0.00008590594,0.0030649116],"genre_scores_gemma":[0.6995019,0.002280075,0.28393278,0.0004523053,0.00053783733,0.000301167,0.00019710766,0.0004376166,0.012359292],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991738,0.00037418233,0.000046818357,0.00012123392,0.0002157966,0.00006812681],"domain_scores_gemma":[0.99457186,0.0039224816,0.0005174299,0.00030329527,0.0003765345,0.00030834982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031258469,0.001191831,0.0014301913,0.003136471,0.0010089595,0.0019909467,0.0025926188,0.002269163,0.002789393],"category_scores_gemma":[0.01137929,0.0011280924,0.0013920326,0.001745173,0.0034444192,0.005195895,0.0027744279,0.0031073196,0.00030875902],"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":[0.000014768355,0.000024832148,0.0002445258,0.000072198054,0.000026906346,0.00005624362,0.000051680756,0.17983274,0.0013771537,0.8123349,0.00054223166,0.0054218615],"study_design_scores_gemma":[0.000004515527,0.000011269881,0.00014714523,0.000015758003,0.000009775366,0.000040163904,0.000012028012,0.7513668,0.00026126843,0.2474639,0.00065130345,0.000016159178],"about_ca_topic_score_codex":0.0016527812,"about_ca_topic_score_gemma":0.0018170659,"teacher_disagreement_score":0.003136471,"about_ca_system_score_codex":0.001384629,"about_ca_system_score_gemma":0.0010361696,"threshold_uncertainty_score":0.016531229},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.790415,0.0013785717,0.19470039,0.0013098466,0.0002762107,0.00017099993,0.0002522883,0.002043696,0.009452966],"genre_scores_gemma":[0.98807424,0.000098635486,0.010914842,0.00006956346,0.000020202637,0.000045195673,0.000091745875,0.00004380995,0.000641688],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820006,0.00046317416,0.000073890784,0.00033665897,0.00038712792,0.00053912384],"domain_scores_gemma":[0.992975,0.003822524,0.0005691344,0.0007726945,0.0012953879,0.00056537794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038281644,0.00081576814,0.00079370715,0.0006996925,0.0009963532,0.0008440917,0.0015235019,0.0007100533,0.0023499976],"category_scores_gemma":[0.011167612,0.0002947165,0.00029119372,0.0007837666,0.0008698956,0.0013774761,0.0011433603,0.0010316077,0.00033516315],"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":[0.0009588074,0.00029761362,0.0030434853,0.00010372258,0.00004039437,0.00003736535,0.00007671333,0.92873895,0.0039448985,0.0059590884,0.0029953946,0.05380354],"study_design_scores_gemma":[0.000016125221,0.00009662574,0.00026761225,0.0000029491719,0.000005026499,0.0000075902717,0.000029517678,0.9969375,0.0012254191,0.0012760785,0.00013190256,0.000003663254],"about_ca_topic_score_codex":0.0066390433,"about_ca_topic_score_gemma":0.0065431446,"teacher_disagreement_score":0.0066390433,"about_ca_system_score_codex":0.002800509,"about_ca_system_score_gemma":0.003249864,"threshold_uncertainty_score":0.020319223},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011976296,0.00008451353,0.9979634,0.00005623885,0.00001613735,0.000022778462,0.000015131589,0.00025785877,0.00038629348],"genre_scores_gemma":[0.14006485,0.00020115094,0.85594565,0.00020925626,0.00007772407,0.0003336738,0.00025660385,0.00041905246,0.0024920625],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985946,0.0005771071,0.000065680426,0.00021992187,0.00044341586,0.00009920997],"domain_scores_gemma":[0.9975399,0.0013649003,0.00021525373,0.00031334293,0.00042642842,0.00014025475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025993811,0.001117088,0.0018774718,0.0008212701,0.0005538012,0.0012890225,0.0024480403,0.0017642841,0.002854188],"category_scores_gemma":[0.00798359,0.0007955661,0.0011669536,0.0009869918,0.0014732855,0.0017873752,0.0025967034,0.0026329358,0.0012860433],"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":[0.0001840918,0.00006869679,0.00036660323,0.00012208115,0.000083542414,0.00007409315,0.000073748495,0.85790217,0.002289964,0.033966545,0.00414881,0.10071964],"study_design_scores_gemma":[0.0000091298325,0.000015319938,0.000013712275,0.0000037645912,0.0000022586546,0.000009707125,0.0000019080603,0.996068,0.0003231812,0.0031015896,0.00044664124,0.0000047513026],"about_ca_topic_score_codex":0.0044137808,"about_ca_topic_score_gemma":0.0033590437,"teacher_disagreement_score":0.0044137808,"about_ca_system_score_codex":0.0010228524,"about_ca_system_score_gemma":0.0019682879,"threshold_uncertainty_score":0.013747036},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012004496,0.00015295226,0.9860444,0.00016231467,0.000032734766,0.000028321207,0.00002620048,0.0003066167,0.0012419281],"genre_scores_gemma":[0.75572836,0.00025011285,0.23965046,0.0002747597,0.00011703362,0.000227104,0.00020166016,0.00015172048,0.0033988138],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928313,0.00023917477,0.00003479612,0.00015503891,0.00019762381,0.00009027132],"domain_scores_gemma":[0.9979716,0.001307082,0.00014492866,0.00025653487,0.00023305968,0.00008682739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012730785,0.0008844761,0.00110417,0.000334793,0.00041669287,0.00079334236,0.0013384969,0.0009565267,0.0020082358],"category_scores_gemma":[0.004946014,0.00042746862,0.00040402883,0.0004802228,0.0012829968,0.0014037244,0.0017015145,0.0020232901,0.00054808444],"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":[0.00015263424,0.00006091647,0.00033528608,0.00007606379,0.000023515782,0.00007076793,0.00006239045,0.92449796,0.0026980205,0.0136885075,0.0015435896,0.05679034],"study_design_scores_gemma":[0.000008669829,0.000018717335,0.000022277809,0.000003090041,0.0000014784047,0.000011782392,0.000007292504,0.99405473,0.0005709804,0.005050997,0.00024782552,0.0000021294427],"about_ca_topic_score_codex":0.001589822,"about_ca_topic_score_gemma":0.0020779793,"teacher_disagreement_score":0.0020082358,"about_ca_system_score_codex":0.00062423944,"about_ca_system_score_gemma":0.0011736333,"threshold_uncertainty_score":0.006732762},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04105397,0.001495723,0.9358587,0.00083225354,0.00017154503,0.00038772466,0.0042212973,0.013118922,0.0028598611],"genre_scores_gemma":[0.25800693,0.00063210976,0.7239059,0.0006828918,0.00015578361,0.001043304,0.011632224,0.0011517646,0.0027890576],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739397,0.0012058002,0.00017056409,0.0005254765,0.00052988995,0.00017423577],"domain_scores_gemma":[0.99525696,0.002437426,0.000406283,0.001156103,0.00056504534,0.00017816636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006487673,0.0017927114,0.0020940315,0.0033572454,0.0010774374,0.002197688,0.0039114296,0.0021624896,0.0036330428],"category_scores_gemma":[0.025066804,0.0007128627,0.0016279124,0.0035485243,0.0011423315,0.0035861623,0.0037266146,0.0025928938,0.0018422725],"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":[0.0009652261,0.00047494104,0.007838255,0.0007360859,0.0005072888,0.0003143607,0.00022668326,0.45804062,0.0031196936,0.036770597,0.04039429,0.45061198],"study_design_scores_gemma":[0.000042557553,0.000058054444,0.00045557896,0.000026906268,0.000013823728,0.0000467714,0.000021594056,0.9812843,0.00096519734,0.01525007,0.0018122,0.000022909064],"about_ca_topic_score_codex":0.0047295857,"about_ca_topic_score_gemma":0.006266923,"teacher_disagreement_score":0.006487673,"about_ca_system_score_codex":0.0014062371,"about_ca_system_score_gemma":0.0032297047,"threshold_uncertainty_score":0.03431046},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07645239,0.00074907375,0.9191987,0.0008627733,0.0000577957,0.000025057552,0.00005980095,0.00045170213,0.0021426831],"genre_scores_gemma":[0.8620707,0.0007785325,0.1339199,0.00033558466,0.000074306045,0.00006454406,0.00010089088,0.00051451573,0.0021410105],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998933,0.000394933,0.00008020092,0.00024640074,0.00025363074,0.000091822614],"domain_scores_gemma":[0.9914609,0.0049058287,0.0010078641,0.0016908742,0.00063149014,0.00030309576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034253888,0.0012277277,0.000889043,0.00055412325,0.00041898256,0.0018310822,0.0023942168,0.0015550569,0.0010558949],"category_scores_gemma":[0.02376239,0.00072441384,0.00071716646,0.00047402465,0.003502192,0.010237662,0.0031187094,0.004029926,0.0003125121],"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":[0.00016461813,0.00006696885,0.0031680132,0.00026450853,0.0000820936,0.00035466382,0.0006001421,0.6979638,0.0143358745,0.23104683,0.0011984444,0.05075406],"study_design_scores_gemma":[0.000005893058,0.00003358316,0.00027137672,0.00003155234,0.0000086601785,0.00006109655,0.000027757798,0.9327474,0.0016138491,0.06466325,0.0005159438,0.000019553756],"about_ca_topic_score_codex":0.002310659,"about_ca_topic_score_gemma":0.001714387,"teacher_disagreement_score":0.0034253888,"about_ca_system_score_codex":0.0013647901,"about_ca_system_score_gemma":0.0011104192,"threshold_uncertainty_score":0.018115401},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006242787,0.0018326377,0.9836098,0.0031041296,0.00013821415,0.00007187085,0.00015592446,0.00036501884,0.0044795997],"genre_scores_gemma":[0.56316453,0.006315569,0.4020659,0.003803819,0.0017772281,0.0014971065,0.0010628666,0.0013497589,0.01896314],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941596,0.0031685852,0.00021750997,0.0012795761,0.00091216626,0.00026265977],"domain_scores_gemma":[0.9531688,0.037823997,0.0020466237,0.0046105217,0.0016857221,0.00066430075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012499442,0.0026642226,0.0029271536,0.0016694258,0.001607638,0.0027900296,0.003925241,0.0037221983,0.0051928745],"category_scores_gemma":[0.054873962,0.0013625044,0.0024175777,0.0016134392,0.008201091,0.007881501,0.0070392755,0.010825835,0.0012832278],"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":[0.00016824044,0.00006414325,0.0010758407,0.00022483044,0.00012366282,0.00020062218,0.00016729486,0.25238043,0.0011421076,0.71343493,0.005682782,0.025335211],"study_design_scores_gemma":[0.000031894873,0.000042532924,0.0001377812,0.000043279466,0.000014633192,0.000040277348,0.000015428574,0.4711699,0.0004770388,0.5256992,0.0023030224,0.000025012998],"about_ca_topic_score_codex":0.0031230694,"about_ca_topic_score_gemma":0.0021919091,"teacher_disagreement_score":0.012499442,"about_ca_system_score_codex":0.0034943658,"about_ca_system_score_gemma":0.0024992977,"threshold_uncertainty_score":0.066104114},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011582286,0.00020489692,0.9971558,0.0001043769,0.000051624902,0.00002610722,0.000017287526,0.00013493677,0.0011467634],"genre_scores_gemma":[0.12633099,0.0010390711,0.8619898,0.0002253066,0.00024948586,0.00037249777,0.00017260792,0.00037330206,0.009246935],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99886876,0.00045951983,0.000057434198,0.00012992775,0.0004009907,0.0000832824],"domain_scores_gemma":[0.9989587,0.0003950072,0.000094659445,0.00016119966,0.0002741207,0.00011626888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025606407,0.0014513218,0.0017456533,0.0011200487,0.00057738245,0.001239764,0.002258497,0.0016420003,0.0035524417],"category_scores_gemma":[0.0061380314,0.0005980517,0.0011544692,0.0010195076,0.001449874,0.0017341824,0.0028485346,0.0029118184,0.001436653],"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":[0.00013913351,0.000069932976,0.00047863717,0.00039079838,0.000089635294,0.00019797766,0.00021163111,0.5413891,0.0061471746,0.3118732,0.0056025456,0.13341023],"study_design_scores_gemma":[0.000016658156,0.00006256655,0.00005950015,0.00002329084,0.000010023382,0.00005569499,0.000010675615,0.9610943,0.0009109372,0.031704206,0.006036123,0.00001602942],"about_ca_topic_score_codex":0.0019158862,"about_ca_topic_score_gemma":0.0016347605,"teacher_disagreement_score":0.0035524417,"about_ca_system_score_codex":0.0007347322,"about_ca_system_score_gemma":0.0018651995,"threshold_uncertainty_score":0.013542175},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0100605935,0.00024205135,0.9861579,0.00048988994,0.00006517514,0.000039121926,0.00009573165,0.00010664158,0.002742966],"genre_scores_gemma":[0.7290785,0.0014638372,0.23918933,0.0013760634,0.0005233104,0.000672399,0.0008008959,0.00054613856,0.026349535],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99583226,0.0019023451,0.00023118618,0.00064303324,0.0011209364,0.00027037863],"domain_scores_gemma":[0.98618025,0.009684351,0.0012287081,0.0007343044,0.0018055459,0.00036677253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007850083,0.0010677497,0.0013816153,0.0017239914,0.0006451689,0.0019068433,0.0018371624,0.0021188215,0.0042443452],"category_scores_gemma":[0.034403965,0.0006551613,0.001067798,0.00088301685,0.0043554865,0.004312869,0.0033028666,0.0028402603,0.00081931823],"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":[0.000051672207,0.00002580462,0.0012149456,0.00008954428,0.00004370929,0.00014523054,0.00014623412,0.10233764,0.0017037784,0.8786203,0.0012869721,0.014334138],"study_design_scores_gemma":[0.000014661778,0.00003916958,0.00052615,0.00003614629,0.000013295463,0.000075780365,0.00003076861,0.7278435,0.0009996019,0.26921272,0.0011593567,0.00004879431],"about_ca_topic_score_codex":0.0030319225,"about_ca_topic_score_gemma":0.0019967365,"teacher_disagreement_score":0.007850083,"about_ca_system_score_codex":0.0016793725,"about_ca_system_score_gemma":0.0015628454,"threshold_uncertainty_score":0.041515708},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003176098,0.00012738179,0.9944035,0.000112902126,0.000041702857,0.00003825957,0.00010129404,0.001685406,0.00031343615],"genre_scores_gemma":[0.14943518,0.00036148258,0.8447478,0.00027921968,0.00013177548,0.00031974041,0.001272335,0.00043780316,0.0030147],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830097,0.00037195446,0.00011079411,0.00052683847,0.0005203095,0.00016914173],"domain_scores_gemma":[0.9960515,0.0013536088,0.00024831315,0.0014439629,0.0006727685,0.00022994512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019766684,0.001947591,0.0020093971,0.0011255506,0.0011137065,0.0017284901,0.0030517932,0.0017328968,0.004628277],"category_scores_gemma":[0.009648759,0.00091956864,0.0019845888,0.0018402193,0.0015747914,0.0037768069,0.003951836,0.0036761225,0.0022802078],"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":[0.000344859,0.00017278563,0.002071972,0.00031867606,0.00022395507,0.00020378879,0.00025275917,0.44259468,0.010832602,0.036400255,0.013492728,0.49309093],"study_design_scores_gemma":[0.000017437373,0.000032430773,0.00016617347,0.00000899293,0.000009072144,0.000053557796,0.000020277288,0.97856015,0.002562484,0.017110342,0.0014439675,0.000015186869],"about_ca_topic_score_codex":0.005230675,"about_ca_topic_score_gemma":0.0056168525,"teacher_disagreement_score":0.005230675,"about_ca_system_score_codex":0.0010343426,"about_ca_system_score_gemma":0.0021463844,"threshold_uncertainty_score":0.015483081},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020295573,0.0005979357,0.9724352,0.0013616515,0.000087539396,0.000033865897,0.000070210524,0.0009754876,0.004142524],"genre_scores_gemma":[0.5414159,0.00076257886,0.4507665,0.0014729915,0.00018873891,0.0002457245,0.00032026213,0.000923305,0.003904005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859375,0.0005650042,0.00009698455,0.00033730152,0.0003083371,0.00009859868],"domain_scores_gemma":[0.99619424,0.0024236692,0.0002131067,0.0007910606,0.0002873846,0.00009054098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036473991,0.0009732002,0.001074577,0.00085756445,0.00065925956,0.0014273443,0.0010387567,0.0014407007,0.0029187028],"category_scores_gemma":[0.017169287,0.0006548099,0.0009023348,0.0006333704,0.0023896554,0.0041466807,0.0015250462,0.0032653986,0.00070043403],"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":[0.00022530532,0.00013165326,0.0027128882,0.00033798537,0.00015257705,0.00008677029,0.00028085758,0.49774423,0.00570029,0.36302695,0.0059995046,0.12360098],"study_design_scores_gemma":[0.000020979212,0.00007712277,0.00024524037,0.000057091893,0.000018736366,0.00004204552,0.000028292605,0.81400895,0.0031073703,0.17904225,0.0033369712,0.000015054],"about_ca_topic_score_codex":0.0015366158,"about_ca_topic_score_gemma":0.0023017225,"teacher_disagreement_score":0.0036473991,"about_ca_system_score_codex":0.0010618333,"about_ca_system_score_gemma":0.0014854239,"threshold_uncertainty_score":0.019289553},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010321839,0.00054729887,0.9846296,0.0008885355,0.00006544537,0.00008941663,0.00006127034,0.00032101924,0.0030755647],"genre_scores_gemma":[0.2921457,0.0008693295,0.69584817,0.00056652783,0.00021580239,0.0007977005,0.00048170137,0.0006721676,0.008402953],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966775,0.0012524291,0.00021178565,0.00040048826,0.0012402732,0.000217413],"domain_scores_gemma":[0.9687395,0.025596112,0.0012833166,0.0016652257,0.0021205342,0.00059523736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008139417,0.0015000971,0.001313747,0.0010997772,0.0011515772,0.0030457291,0.0022711158,0.0025513188,0.004406114],"category_scores_gemma":[0.041140173,0.0008680278,0.0013741356,0.0007013418,0.0030841406,0.0036293801,0.0040566954,0.0067563686,0.0011663068],"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":[0.00031459023,0.00015205388,0.0021679015,0.00050669647,0.00006611546,0.0001535093,0.00039113383,0.6732202,0.004969698,0.25012198,0.0031997142,0.06473639],"study_design_scores_gemma":[0.000006849861,0.000019377969,0.000069517846,0.00001830672,0.000002915745,0.000016299393,0.000011123936,0.971835,0.0006939273,0.026856577,0.00046422932,0.0000058934274],"about_ca_topic_score_codex":0.0028201095,"about_ca_topic_score_gemma":0.0033759545,"teacher_disagreement_score":0.008139417,"about_ca_system_score_codex":0.0023810442,"about_ca_system_score_gemma":0.0033918703,"threshold_uncertainty_score":0.04304588},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022506345,0.00023210603,0.97125083,0.0005455593,0.00004485348,0.000032930722,0.00007194521,0.00035783325,0.004957648],"genre_scores_gemma":[0.835196,0.00046567517,0.15281667,0.0004496403,0.00008938341,0.00021772317,0.00024163553,0.0005240667,0.009999137],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994444,0.00021639155,0.000027733957,0.00012262486,0.00013009265,0.000058704278],"domain_scores_gemma":[0.9983864,0.0008788627,0.0002004011,0.00023919885,0.00018836431,0.00010669809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018186616,0.0010068326,0.000680858,0.0007069582,0.00060871465,0.0013070126,0.0010840353,0.0012531489,0.0035894525],"category_scores_gemma":[0.009259899,0.00063003803,0.0006422906,0.00042297394,0.0025333962,0.0023698458,0.002635203,0.0030107053,0.00075219723],"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":[0.00010107609,0.000047411013,0.0009859414,0.000108501496,0.000041554038,0.0001446777,0.00017729292,0.54971844,0.006248989,0.41420126,0.0036320065,0.02459277],"study_design_scores_gemma":[0.000004411219,0.0000151025115,0.00010142215,0.00001411088,0.000002262463,0.0000174223,0.000007852091,0.9385941,0.0011125291,0.059681233,0.00044230503,0.000007313594],"about_ca_topic_score_codex":0.0028519037,"about_ca_topic_score_gemma":0.0030994376,"teacher_disagreement_score":0.0035894525,"about_ca_system_score_codex":0.001587575,"about_ca_system_score_gemma":0.0011927066,"threshold_uncertainty_score":0.012007892},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0112475045,0.00063130585,0.98223406,0.0002658139,0.000095822215,0.000043701864,0.00013714045,0.0024097492,0.002934973],"genre_scores_gemma":[0.48718116,0.0011699903,0.49441704,0.00068271614,0.00014929516,0.00037658302,0.0006902956,0.0011698285,0.014163112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997484,0.000070356444,0.000016837128,0.000036524776,0.000101048776,0.000026831392],"domain_scores_gemma":[0.999739,0.00009242361,0.000029277704,0.00003195101,0.00007150864,0.0000357587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072135235,0.00075330475,0.00044565767,0.0004173918,0.00028425033,0.0006008478,0.0013360546,0.0007054009,0.0030140895],"category_scores_gemma":[0.0013631041,0.00027660956,0.0005014997,0.0004198658,0.0005211016,0.0013054382,0.0011794256,0.001457519,0.0013742672],"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":[0.00051256164,0.00016402942,0.0011001035,0.0003502748,0.000100033016,0.00019615646,0.00015005912,0.37358257,0.057205778,0.09646891,0.015398598,0.45477086],"study_design_scores_gemma":[0.000024279345,0.000110353496,0.000120112694,0.000020468551,0.000013540426,0.00008563585,0.0000109008515,0.9596023,0.010742515,0.020035358,0.009215871,0.000018786439],"about_ca_topic_score_codex":0.0009766886,"about_ca_topic_score_gemma":0.0019322213,"teacher_disagreement_score":0.0030140895,"about_ca_system_score_codex":0.0004344996,"about_ca_system_score_gemma":0.00081277743,"threshold_uncertainty_score":0.010083139},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011146804,0.00019571329,0.98597693,0.00021550996,0.00005426936,0.000032658256,0.00007352026,0.0005705716,0.0017339097],"genre_scores_gemma":[0.6337983,0.00022683715,0.36122724,0.0003337328,0.00010078253,0.00016211852,0.00031761147,0.0003216293,0.0035117513],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917704,0.00026209923,0.00005506424,0.000153231,0.00026650637,0.00008617058],"domain_scores_gemma":[0.9990363,0.0003923231,0.000078826495,0.00021786436,0.00020832448,0.000066414344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013662102,0.0007094537,0.00074002205,0.00034700028,0.00042692904,0.0009867704,0.0016661873,0.00070064,0.003395213],"category_scores_gemma":[0.0051693395,0.00036968547,0.00045195146,0.00045557463,0.00089124136,0.0016176616,0.0021055038,0.002156209,0.0005533216],"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":[0.0002718662,0.00008568146,0.0011772976,0.000115290844,0.00005770359,0.00009281452,0.00015848065,0.6614628,0.012799279,0.14772639,0.005667046,0.1703854],"study_design_scores_gemma":[0.0000072949974,0.000019751702,0.000042776282,0.0000044611206,0.0000030233334,0.000013982325,0.0000062177396,0.9771852,0.0015575781,0.020537049,0.00061790034,0.0000049096625],"about_ca_topic_score_codex":0.0022414161,"about_ca_topic_score_gemma":0.0035727895,"teacher_disagreement_score":0.003395213,"about_ca_system_score_codex":0.0009813785,"about_ca_system_score_gemma":0.0011428234,"threshold_uncertainty_score":0.011358082},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010620544,0.00014633105,0.9973622,0.00008866932,0.00005551113,0.00001845916,0.000027511524,0.00013619146,0.0011031493],"genre_scores_gemma":[0.060615186,0.00038407603,0.9316358,0.00019985587,0.000113899325,0.00020617383,0.00019237869,0.00032702534,0.0063256137],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991906,0.00028482807,0.0000228325,0.00008679776,0.00037926855,0.000035576813],"domain_scores_gemma":[0.9994754,0.00021466489,0.00006236425,0.00006957076,0.00013421809,0.000043866683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012032217,0.0009918361,0.0010402338,0.0005209533,0.00037605473,0.0007317066,0.001402336,0.0012198798,0.0029652668],"category_scores_gemma":[0.0023575984,0.00050225365,0.0007396033,0.00050311466,0.0009887754,0.00080145564,0.0015012166,0.001844985,0.0010529135],"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":[0.00007138632,0.000057238118,0.0003094107,0.0002618555,0.00006974304,0.00012683315,0.000094751886,0.83815145,0.0071784514,0.07839701,0.006506013,0.06877581],"study_design_scores_gemma":[0.0000052430073,0.000014940811,0.000034837554,0.0000071539685,0.0000028821848,0.000015101337,0.0000021363844,0.99166733,0.0004302301,0.0049688895,0.0028464952,0.000004736726],"about_ca_topic_score_codex":0.0027278895,"about_ca_topic_score_gemma":0.0037775429,"teacher_disagreement_score":0.0029652668,"about_ca_system_score_codex":0.00067831494,"about_ca_system_score_gemma":0.0015191032,"threshold_uncertainty_score":0.009919822},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5476661,0.25003245,0.032282908,0.032296292,0.00072750484,0.0004042247,0.016697546,0.00054323766,0.11934974],"genre_scores_gemma":[0.8282777,0.13666409,0.022159781,0.0009063947,0.0012026493,0.00035632285,0.007502951,0.0001632635,0.0027668758],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98463976,0.0036402096,0.0024003445,0.0014529392,0.007401225,0.00046537968],"domain_scores_gemma":[0.86737835,0.09221116,0.015954455,0.0052254857,0.017847503,0.0013830486],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.016600858,0.0006299588,0.0012487211,0.12335852,0.0019583139,0.010651139,0.0010111468,0.0010825982,0.0025799556],"category_scores_gemma":[0.08929041,0.00040960475,0.00068371964,0.22773169,0.0028658556,0.012408197,0.0037311988,0.0011007362,0.00062684325],"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":[0.00024344416,0.000104578234,0.17467923,0.010351528,0.0006823677,0.00073169055,0.016256232,0.0041370746,0.0023727876,0.12810405,0.022603199,0.6397339],"study_design_scores_gemma":[0.000053129934,0.00033436727,0.4007612,0.015248418,0.0008651134,0.0025770743,0.036478534,0.019214973,0.004465336,0.09991191,0.41979814,0.0002918303],"about_ca_topic_score_codex":0.003548285,"about_ca_topic_score_gemma":0.0048951446,"teacher_disagreement_score":0.98339915,"about_ca_system_score_codex":0.0037873336,"about_ca_system_score_gemma":0.0052512162,"threshold_uncertainty_score":0.08779478},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013589824,0.00013404536,0.001068533,0.00015371073,0.0001304618,0.000043155575,0.9881738,0.006026958,0.0029104096],"genre_scores_gemma":[0.002433652,0.000056110977,0.0019929158,0.00006176912,0.000013247211,0.00014267542,0.9925817,0.0004115961,0.0023062457],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839777,0.00022400964,0.00016041861,0.0004948603,0.00053316343,0.00018976998],"domain_scores_gemma":[0.9976666,0.00069010013,0.00011574269,0.00069135433,0.0007218716,0.00011430232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017411653,0.004620338,0.0013059599,0.0022397789,0.0008539277,0.002303425,0.0026937681,0.0021089641,0.057900265],"category_scores_gemma":[0.0069363452,0.0006505973,0.0020847705,0.0022799799,0.00046201306,0.0017205636,0.0014467969,0.0024932695,0.09584073],"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":[0.0000865833,0.000060465463,0.00066287594,0.00034275837,0.000041619256,0.00003054624,0.000010473108,0.0024088218,0.0002180972,0.00034287365,0.989036,0.006758885],"study_design_scores_gemma":[0.0005951561,0.00015801801,0.010224487,0.0003680271,0.00013167516,0.00024789126,0.00014719658,0.024931392,0.0060869865,0.006362266,0.9506194,0.00012737467],"about_ca_topic_score_codex":0.016756868,"about_ca_topic_score_gemma":0.034762174,"teacher_disagreement_score":0.057900265,"about_ca_system_score_codex":0.0018036737,"about_ca_system_score_gemma":0.0016592038,"threshold_uncertainty_score":0.19369566},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21519418,0.005279313,0.35374492,0.014703493,0.0045318697,0.00038446955,0.3326752,0.031573784,0.041912775],"genre_scores_gemma":[0.59701455,0.0008690838,0.115080394,0.0016031752,0.00050520676,0.00052910135,0.23111545,0.010304433,0.042978637],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857676,0.00069623283,0.00006629756,0.00034558526,0.00017463932,0.00014053303],"domain_scores_gemma":[0.9943335,0.0031113143,0.00024191871,0.0010292208,0.001062029,0.0002220227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004917496,0.0012238619,0.001346527,0.0010951374,0.0008337636,0.001895782,0.0026061013,0.0024175374,0.06725907],"category_scores_gemma":[0.026495954,0.000676515,0.0020645661,0.0016465598,0.00038817953,0.0024650535,0.0011118132,0.0033539585,0.020429308],"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":[0.0012000658,0.00028552653,0.015803326,0.00044926332,0.0006496289,0.00018963568,0.00012340135,0.26589456,0.00065570563,0.013859024,0.63511163,0.06577812],"study_design_scores_gemma":[0.00037864747,0.0001775567,0.013985842,0.00026534707,0.00021620677,0.00020362742,0.0002652891,0.86139107,0.0012032038,0.04063117,0.08113659,0.00014548682],"about_ca_topic_score_codex":0.058040716,"about_ca_topic_score_gemma":0.097282335,"teacher_disagreement_score":0.06725907,"about_ca_system_score_codex":0.0011027603,"about_ca_system_score_gemma":0.002472635,"threshold_uncertainty_score":0.22500402},"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":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009228486,0.00035836737,0.8041025,0.00028727902,0.00028941184,0.00017152006,0.04346272,0.11817947,0.032225966],"genre_scores_gemma":[0.034164675,0.0010354106,0.63823396,0.0008893403,0.00026747212,0.0022978478,0.07315066,0.15167738,0.09828329],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99959713,0.00008198093,0.00003724855,0.000072276605,0.00016708073,0.000044272278],"domain_scores_gemma":[0.99889755,0.000648568,0.000057920566,0.00016543649,0.00018922632,0.000041342046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010660666,0.0018084396,0.0013290542,0.0013825841,0.000513051,0.0012895697,0.0023631114,0.001681161,0.21420756],"category_scores_gemma":[0.0036749945,0.0013839772,0.0016359704,0.0011200609,0.0003848088,0.00152013,0.0015458063,0.002704131,0.09136658],"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":[0.00012616474,0.00016618619,0.0007677914,0.001510703,0.00019010871,0.00031560156,0.00012971311,0.06632577,0.004048671,0.08645736,0.68959016,0.15037173],"study_design_scores_gemma":[0.00023660937,0.000031317453,0.00046805295,0.00019933133,0.00005459554,0.00023162435,0.000030131147,0.36225158,0.0061953273,0.06490807,0.56530625,0.00008704256],"about_ca_topic_score_codex":0.0055123316,"about_ca_topic_score_gemma":0.008946757,"teacher_disagreement_score":0.21420756,"about_ca_system_score_codex":0.0006702592,"about_ca_system_score_gemma":0.0012128183,"threshold_uncertainty_score":0.71659565},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012222775,0.3536314,0.004629607,0.24838816,0.05502977,0.00007330368,0.001189835,0.00028381872,0.32455134],"genre_scores_gemma":[0.2237172,0.38750717,0.006581078,0.07063694,0.08472928,0.0001796335,0.0021982423,0.00062106655,0.22382936],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964451,0.00079420675,0.00029936185,0.00028847557,0.0018878805,0.00028495974],"domain_scores_gemma":[0.98275673,0.012394339,0.001726764,0.00036696548,0.0022577741,0.00049742043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003263315,0.0005155536,0.0004524489,0.0024169877,0.0015747441,0.005230166,0.0005873375,0.0019374313,0.015639905],"category_scores_gemma":[0.016299099,0.00024549328,0.00055451086,0.004366634,0.0013131622,0.005971764,0.001844272,0.0030517583,0.006193398],"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":[0.00011521143,0.000035125842,0.0022125954,0.00082226744,0.000030264348,0.00040460553,0.0006775483,0.00042901566,0.0005372506,0.08585999,0.72900754,0.17986864],"study_design_scores_gemma":[0.000007832145,0.0001341239,0.0096983835,0.0014668548,0.00002130178,0.00038758994,0.00067240273,0.00027522378,0.00058745325,0.014795117,0.9719116,0.000042022504],"about_ca_topic_score_codex":0.0038134323,"about_ca_topic_score_gemma":0.0066314028,"teacher_disagreement_score":0.015639905,"about_ca_system_score_codex":0.0026634587,"about_ca_system_score_gemma":0.0018795138,"threshold_uncertainty_score":0.05232066},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015340354,0.0005453877,0.9776865,0.0012937506,0.00008470067,0.000028874676,0.0000756716,0.0003981972,0.0045465943],"genre_scores_gemma":[0.6552983,0.00138357,0.33132127,0.001278107,0.00029616186,0.0005357104,0.0004290697,0.0013661424,0.00809166],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986198,0.0007363391,0.000065256274,0.00020338217,0.0002877079,0.00008754894],"domain_scores_gemma":[0.9964483,0.0023165175,0.0002341748,0.00047405297,0.0003883449,0.00013866568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038388858,0.0011454424,0.0014369806,0.0010867412,0.00084756047,0.002029144,0.0021593866,0.0021546902,0.003059326],"category_scores_gemma":[0.013789617,0.000933128,0.0008922576,0.0008196106,0.0036204383,0.003107934,0.0024331445,0.0030244484,0.0008176149],"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":[0.000050873274,0.00003314952,0.00076815,0.000112621616,0.000048607224,0.00006849705,0.00011460851,0.7977727,0.0016183909,0.18255933,0.0017222186,0.015130898],"study_design_scores_gemma":[0.000006043593,0.000019486013,0.00007102716,0.000014937296,0.000003057555,0.000011651253,0.000007190036,0.9325792,0.00039229245,0.066429965,0.00045738035,0.000007702395],"about_ca_topic_score_codex":0.003224059,"about_ca_topic_score_gemma":0.0033503645,"teacher_disagreement_score":0.0038388858,"about_ca_system_score_codex":0.00198048,"about_ca_system_score_gemma":0.001584001,"threshold_uncertainty_score":0.020302176},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059140213,0.0016349627,0.9206842,0.003312584,0.00022495782,0.00008205024,0.00032324984,0.0007468747,0.013850959],"genre_scores_gemma":[0.80311173,0.001422153,0.18074226,0.0011462936,0.0005391695,0.00055041537,0.0005686347,0.0012735472,0.010645813],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99559444,0.0013361452,0.0002276049,0.0009842289,0.0010731304,0.00078441546],"domain_scores_gemma":[0.9740381,0.020481942,0.001197777,0.002311556,0.00094346463,0.0010272112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005427131,0.0021675196,0.0022151638,0.0011210409,0.0016158405,0.0037411847,0.0030169152,0.001998364,0.0055683665],"category_scores_gemma":[0.03605811,0.0012938189,0.0018391773,0.0012621178,0.0041494602,0.008224849,0.005278822,0.0077155246,0.00085296156],"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":[0.00038052964,0.00013410498,0.0012771597,0.00030651945,0.000075047734,0.0001187794,0.00027799048,0.46895525,0.0030729978,0.5007909,0.005223112,0.01938759],"study_design_scores_gemma":[0.00002043617,0.000017721892,0.00014702258,0.000016247515,0.000011632191,0.0000145023905,0.000016180005,0.8262195,0.00066589785,0.17221369,0.0006475281,0.00000966591],"about_ca_topic_score_codex":0.0046140617,"about_ca_topic_score_gemma":0.0049279206,"teacher_disagreement_score":0.0055683665,"about_ca_system_score_codex":0.0045575215,"about_ca_system_score_gemma":0.00334993,"threshold_uncertainty_score":0.033067286},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030358022,0.00009201339,0.99649554,0.000065697706,0.0000067172055,0.000012595939,0.000015055408,0.0001087874,0.00016778063],"genre_scores_gemma":[0.2547208,0.00042663305,0.7417008,0.00018228835,0.000079937345,0.00038606836,0.0003002987,0.00019513127,0.0020080318],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820995,0.0010681917,0.000059547645,0.00029025372,0.0003082794,0.000063770196],"domain_scores_gemma":[0.99479854,0.0041410346,0.00032180542,0.0003779264,0.00028250983,0.00007818723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043913545,0.0011464565,0.0012163346,0.0011182214,0.00042995397,0.0010350045,0.0015014168,0.0014836454,0.001309834],"category_scores_gemma":[0.010297817,0.0008755203,0.0008650648,0.0013609119,0.002108597,0.0012514222,0.001741263,0.0019685943,0.00050285266],"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":[0.00011436344,0.00005309399,0.0006902881,0.00015242753,0.00010560813,0.00006163888,0.000075949254,0.8963788,0.0036075362,0.04938684,0.0007040254,0.048669394],"study_design_scores_gemma":[0.000008482625,0.000015029569,0.00006482303,0.0000045665947,0.0000032545847,0.000008014004,0.000003507683,0.9847141,0.00052598974,0.014426771,0.00022053822,0.000005000284],"about_ca_topic_score_codex":0.0026684324,"about_ca_topic_score_gemma":0.002477635,"teacher_disagreement_score":0.0043913545,"about_ca_system_score_codex":0.0011275413,"about_ca_system_score_gemma":0.0013455477,"threshold_uncertainty_score":0.023223996},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16351834,0.0013334159,0.8244963,0.0020374167,0.000106601205,0.00005579932,0.00030595416,0.00040435776,0.0077417367],"genre_scores_gemma":[0.8804588,0.0011451636,0.11078388,0.00042309114,0.00020672071,0.00022998922,0.00057838246,0.00027054522,0.005903452],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99863416,0.0005528343,0.000077863195,0.00023204458,0.0003641203,0.00013894931],"domain_scores_gemma":[0.9852529,0.011060198,0.0009947029,0.0010572139,0.0009605831,0.0006743493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037631697,0.0012444941,0.001078341,0.0012328682,0.0006700663,0.001815325,0.0015160404,0.0018589151,0.0020195195],"category_scores_gemma":[0.023537504,0.00074384076,0.0010349809,0.00056083314,0.0034397903,0.005248818,0.0035907847,0.003886979,0.00038895686],"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":[0.00031092507,0.000066310626,0.0028405518,0.00023220119,0.00007712919,0.000121564335,0.00022816235,0.43075252,0.0043378803,0.5445651,0.0016150061,0.014852686],"study_design_scores_gemma":[0.000007718573,0.000036619756,0.0002524482,0.000019333653,0.0000064983833,0.000024148338,0.00001542272,0.86012673,0.0007308162,0.13843659,0.00033117548,0.000012521972],"about_ca_topic_score_codex":0.0017190409,"about_ca_topic_score_gemma":0.001808343,"teacher_disagreement_score":0.0037631697,"about_ca_system_score_codex":0.002090772,"about_ca_system_score_gemma":0.0010101709,"threshold_uncertainty_score":0.019901752},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020495037,0.0023852284,0.94974345,0.0013287137,0.000082180726,0.00003533491,0.00013954211,0.00065077335,0.025139732],"genre_scores_gemma":[0.78437114,0.0076100226,0.1680512,0.00076723384,0.00038379207,0.00021557852,0.00033261313,0.0005216914,0.03774671],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968016,0.00010027258,0.000019580091,0.000064573745,0.00010233623,0.000033065568],"domain_scores_gemma":[0.9991642,0.00050567294,0.000076818535,0.00011671778,0.000108834545,0.000027747423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000781362,0.00060339697,0.00051325763,0.00055262214,0.00033115453,0.0010472704,0.0008734526,0.0006711604,0.0050744126],"category_scores_gemma":[0.0038734036,0.00047612295,0.0006009567,0.00051663164,0.0010266145,0.00196967,0.0013859662,0.0012867538,0.00083889184],"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":[0.00006906377,0.000043055315,0.0013901045,0.0003560342,0.000059609018,0.00020258322,0.00045534194,0.48098105,0.008964834,0.34448862,0.0034939656,0.15949574],"study_design_scores_gemma":[0.00000841252,0.00004718585,0.00055728713,0.00006977182,0.000015885262,0.00009692023,0.000060860188,0.844162,0.0033838586,0.145411,0.0061660744,0.000020739086],"about_ca_topic_score_codex":0.004684997,"about_ca_topic_score_gemma":0.0043832688,"teacher_disagreement_score":0.0050744126,"about_ca_system_score_codex":0.0011172881,"about_ca_system_score_gemma":0.0007125136,"threshold_uncertainty_score":0.016975582},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062345922,0.0012352559,0.9180458,0.00093058695,0.00023400164,0.000053814114,0.00012201639,0.00048652967,0.01654604],"genre_scores_gemma":[0.71358377,0.0030603197,0.23837462,0.00043273586,0.00012588035,0.0002657218,0.0002113091,0.00048107194,0.043464515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997553,0.000035695535,0.0000146350085,0.000079164856,0.000081960985,0.000033163018],"domain_scores_gemma":[0.99963963,0.00011457087,0.000041710853,0.000074379765,0.00009111,0.000038496844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006095248,0.000698991,0.0006925582,0.00041829934,0.0007560984,0.0019185718,0.0011398499,0.0014351316,0.0053718677],"category_scores_gemma":[0.0015106149,0.00046899234,0.0009314221,0.00033255163,0.0015656524,0.002451136,0.0014587654,0.001646052,0.0010392135],"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":[0.00014042236,0.000056715417,0.00176954,0.0004222185,0.00009807717,0.00040034438,0.0007228165,0.27993444,0.13304846,0.512653,0.0018845316,0.06886936],"study_design_scores_gemma":[0.00003535609,0.00020411401,0.0016137273,0.00011704237,0.000055165554,0.00046997983,0.00027519665,0.7568278,0.042651735,0.1704257,0.027233625,0.00009058421],"about_ca_topic_score_codex":0.0034884398,"about_ca_topic_score_gemma":0.0028357194,"teacher_disagreement_score":0.0053718677,"about_ca_system_score_codex":0.0013804106,"about_ca_system_score_gemma":0.0010312564,"threshold_uncertainty_score":0.017970681},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9728335,0.00038727667,0.000982793,0.00038298566,0.000058569203,0.000032934247,0.0035311328,0.000077163524,0.021713644],"genre_scores_gemma":[0.9799217,0.00032588505,0.00076715625,0.000059380232,0.0000062773815,0.000008396333,0.0012229772,0.000024447041,0.017663755],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9999485,0.0000054381153,0.000002950703,0.000011945094,0.000011960528,0.000019207118],"domain_scores_gemma":[0.9998729,0.000016991959,0.000021560403,0.0000073081087,0.000037539525,0.00004365022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010595821,0.00020694689,0.00010720451,0.0003488062,0.0004536793,0.0008105622,0.00013291006,0.0001574268,0.004236296],"category_scores_gemma":[0.00037089223,0.00010116253,0.000117477,0.0004983126,0.00027613025,0.00015626251,0.0005115377,0.00020479666,0.00043126338],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077838846,0.00008104815,0.82500863,0.00020029179,0.000094716765,0.0022233324,0.0014230893,0.022368679,0.0075826873,0.00580215,0.014787244,0.11964967],"study_design_scores_gemma":[0.000037110058,0.00004392042,0.96475095,0.00013583839,0.000018503808,0.00012956932,0.0014832016,0.014747482,0.0011018356,0.0008974667,0.01664058,0.00001345294],"about_ca_topic_score_codex":0.59377337,"about_ca_topic_score_gemma":0.7715142,"teacher_disagreement_score":0.59377337,"about_ca_system_score_codex":0.0015170281,"about_ca_system_score_gemma":0.0029455326,"threshold_uncertainty_score":0.817238},"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":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45799625,0.006615327,0.06784329,0.018332114,0.0016734959,0.0005900798,0.014178882,0.003556562,0.4292139],"genre_scores_gemma":[0.6285898,0.001780756,0.049184844,0.0004841924,0.000097565884,0.00015950947,0.002936687,0.00043786506,0.3163288],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99957496,0.00007962878,0.000010036893,0.000097302014,0.00014173273,0.00009644055],"domain_scores_gemma":[0.99927706,0.00015231922,0.00010681691,0.000053994565,0.00022864471,0.00018123684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045406283,0.0004735159,0.0002924705,0.00058292475,0.0014065211,0.0020340434,0.000603447,0.0009869561,0.026275473],"category_scores_gemma":[0.0013891383,0.00027255266,0.0002598396,0.000967249,0.0007131528,0.00041792326,0.00138302,0.0009589051,0.0057628686],"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":[0.0015389298,0.00035622474,0.08952885,0.0011136468,0.000108832486,0.0030901814,0.005959197,0.033144068,0.022540417,0.08049171,0.12509933,0.63702863],"study_design_scores_gemma":[0.00010146202,0.00036988637,0.119095124,0.0004370447,0.00002472683,0.0013193795,0.0056594396,0.03835046,0.012268531,0.0114219375,0.81083053,0.00012142069],"about_ca_topic_score_codex":0.14949705,"about_ca_topic_score_gemma":0.24321839,"teacher_disagreement_score":0.14949705,"about_ca_system_score_codex":0.0027311253,"about_ca_system_score_gemma":0.007625539,"threshold_uncertainty_score":0.29725373},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015867742,0.42967853,0.001322694,0.042776633,0.0044276738,0.00018722337,0.021511685,0.00034158578,0.48388627],"genre_scores_gemma":[0.20393685,0.4754148,0.0044006766,0.007332391,0.001916944,0.00018082996,0.011006866,0.00055576814,0.29525486],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971879,0.00021185247,0.00012871149,0.00023910387,0.0017077948,0.000524649],"domain_scores_gemma":[0.99244326,0.0017338375,0.0003954054,0.00032005794,0.004461933,0.00064560137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023080506,0.001026347,0.00087811024,0.024481015,0.014824912,0.009452826,0.0016758698,0.0014608469,0.04910396],"category_scores_gemma":[0.010023564,0.00049641175,0.000563067,0.06312418,0.0063711004,0.0024980225,0.002169127,0.00144891,0.004063982],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041066418,0.000026400727,0.004595084,0.0023036273,0.00004292009,0.00021671636,0.013088116,0.00031821112,0.00028657375,0.10945579,0.72800136,0.1416241],"study_design_scores_gemma":[0.000004476976,0.000004653694,0.01158348,0.0012904493,0.000028932931,0.000092565686,0.0058884416,0.000060945404,0.00021896834,0.0027163508,0.9780804,0.0000302322],"about_ca_topic_score_codex":0.98808527,"about_ca_topic_score_gemma":0.9951421,"teacher_disagreement_score":0.10334475,"about_ca_system_score_codex":0.10334475,"about_ca_system_score_gemma":0.20035695,"threshold_uncertainty_score":0.74982214},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034000846,0.0008092982,0.0011905747,0.0066733276,0.0023508826,0.00007393004,0.014309199,0.0016221908,0.9695705],"genre_scores_gemma":[0.008113454,0.00089299254,0.0005785623,0.00051687023,0.00048077316,0.00003267275,0.0067456583,0.000392298,0.9822466],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999328,0.00007331053,0.000018770117,0.00006674064,0.0003953711,0.000117788455],"domain_scores_gemma":[0.9990502,0.00014135496,0.00008489224,0.000099440185,0.00037582987,0.00024822177],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000927761,0.0009051916,0.00044198098,0.0022200688,0.0009952821,0.0024863568,0.001026368,0.0010839357,0.45549613],"category_scores_gemma":[0.003681313,0.00021271205,0.0004842267,0.0016602072,0.00040313456,0.0014109381,0.0012095522,0.0014603983,0.24489143],"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":[0.000054640124,0.000042218995,0.00032910288,0.000027919903,0.0000036858544,0.000030832805,0.000009131717,0.00018510394,0.00010408463,0.005693803,0.9589698,0.034549624],"study_design_scores_gemma":[0.000025350695,0.000035222612,0.001151868,0.00005860627,0.000004510223,0.000043659275,0.00005072637,0.0011087882,0.0005059155,0.0031513278,0.9938565,0.0000075483345],"about_ca_topic_score_codex":0.0064032236,"about_ca_topic_score_gemma":0.01143949,"teacher_disagreement_score":0.45549613,"about_ca_system_score_codex":0.0010744255,"about_ca_system_score_gemma":0.0019847031,"threshold_uncertainty_score":0.77666867},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19140382,0.15996261,0.0017949977,0.028270105,0.00195431,0.00016112205,0.07475428,0.000263859,0.5414349],"genre_scores_gemma":[0.34523258,0.043814808,0.0016164279,0.0028709818,0.0005804143,0.00021663259,0.014225509,0.00032723742,0.5911155],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.99926883,0.00016836538,0.000044016084,0.00013063369,0.00024490058,0.00014320744],"domain_scores_gemma":[0.9990766,0.0003432644,0.00020101204,0.00004932306,0.00020372549,0.00012592708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092208403,0.00024846615,0.00033991598,0.0033134618,0.002059599,0.0031481977,0.00078622915,0.0004609107,0.014124698],"category_scores_gemma":[0.003175205,0.00042441406,0.00014539683,0.013571268,0.0011892426,0.0020612157,0.0008959818,0.00077026454,0.0031202561],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082462095,0.00003440352,0.028292803,0.00045568202,0.000021492577,0.0001740707,0.04362733,0.00017039532,0.00019631656,0.057302188,0.7289092,0.14073354],"study_design_scores_gemma":[0.0000029579971,0.000005945272,0.06354516,0.00022695397,0.0000074543395,0.000114239396,0.015390127,0.000052667598,0.00016033945,0.002024573,0.91845965,0.0000099428025],"about_ca_topic_score_codex":0.11415813,"about_ca_topic_score_gemma":0.40181038,"teacher_disagreement_score":0.88584185,"about_ca_system_score_codex":0.0028568152,"about_ca_system_score_gemma":0.0022626775,"threshold_uncertainty_score":0.2269873},"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":"editorial","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00061265304,0.0043233195,0.0035715858,0.24367724,0.48062322,0.00064669515,0.0054454105,0.0054609496,0.2556389],"genre_scores_gemma":[0.0016611768,0.0022930745,0.0021968328,0.07914102,0.043872513,0.0002103543,0.0022296624,0.0022172832,0.86617804],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975782,0.00027303142,0.00013993653,0.00029326096,0.0014186341,0.00029691256],"domain_scores_gemma":[0.974409,0.0022834495,0.00064830465,0.0010489908,0.017400527,0.004209755],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027245341,0.00095599325,0.00092000497,0.0019619304,0.004219433,0.007816521,0.0016870045,0.0042438577,0.49309367],"category_scores_gemma":[0.03178063,0.00066135416,0.000837269,0.0018146356,0.001060942,0.005902921,0.0029290926,0.0058157453,0.44338012],"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":[0.000002374681,0.0000028201327,0.000020977554,0.000012740784,2.7935212e-7,0.000012119013,0.000009894108,0.0000024319713,0.000025868125,0.00020685552,0.9947942,0.0049094646],"study_design_scores_gemma":[0.0000021979415,0.0000044454246,0.00009336566,0.000037424754,5.3351334e-7,0.00004125637,0.000053912932,0.000007412346,0.00003196411,0.00022310896,0.99949956,0.000004822694],"about_ca_topic_score_codex":0.013328364,"about_ca_topic_score_gemma":0.032167703,"teacher_disagreement_score":0.49309367,"about_ca_system_score_codex":0.0029229815,"about_ca_system_score_gemma":0.0075967545,"threshold_uncertainty_score":0.72304034},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006454091,0.009499057,0.9570366,0.0083393445,0.0003715137,0.00010528305,0.00023371213,0.0003433135,0.017617034],"genre_scores_gemma":[0.60508406,0.016122913,0.36060786,0.0052549927,0.0024528091,0.0011306715,0.00056077336,0.0012544442,0.0075314366],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95983815,0.019834105,0.0021519968,0.0033863103,0.0136239,0.0011654584],"domain_scores_gemma":[0.75399315,0.20903312,0.0058974144,0.017265534,0.012373819,0.0014369269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05462456,0.0029901837,0.0041581113,0.0032832045,0.0022092904,0.007251472,0.007455405,0.0047107977,0.00540819],"category_scores_gemma":[0.21856895,0.0017346267,0.0029064254,0.003080671,0.011774807,0.021582726,0.009168388,0.017717004,0.0015969077],"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":[0.00017927642,0.000066072666,0.00056870404,0.0005643258,0.00014536508,0.00009097026,0.0003139152,0.09090061,0.00052772986,0.86178064,0.0036448345,0.041217636],"study_design_scores_gemma":[0.00002533405,0.000099922705,0.00022773958,0.00034114285,0.000037173068,0.00010395185,0.00006936265,0.30126047,0.0010801858,0.69273293,0.0039711124,0.000050643193],"about_ca_topic_score_codex":0.0028215945,"about_ca_topic_score_gemma":0.0019095106,"teacher_disagreement_score":0.05462456,"about_ca_system_score_codex":0.005450668,"about_ca_system_score_gemma":0.0037890107,"threshold_uncertainty_score":0.2888857},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002674319,0.00014911531,0.9942445,0.00018388803,0.000078069424,0.00004868957,0.000041502433,0.0008769905,0.0017029374],"genre_scores_gemma":[0.1453021,0.00021283954,0.84578705,0.00036174443,0.00013131335,0.00040297915,0.0003939446,0.00088132126,0.0065266504],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819213,0.000730937,0.00010312893,0.0003036854,0.0005221754,0.00014788184],"domain_scores_gemma":[0.99707246,0.0016270635,0.00017288695,0.00047913857,0.00054366986,0.00010473611],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026837704,0.0013385377,0.0017193141,0.0008685916,0.000590653,0.0015172802,0.0013403625,0.0018408325,0.00709319],"category_scores_gemma":[0.011042262,0.00091527094,0.0011465707,0.00085098605,0.0009527926,0.0016764698,0.001761339,0.0030777566,0.0026232982],"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":[0.00020370088,0.00014497287,0.0006431467,0.00018320173,0.00009539067,0.00012615861,0.00009207947,0.73432827,0.005562909,0.061424382,0.012688433,0.18450731],"study_design_scores_gemma":[0.0000104702285,0.000015850352,0.000052495732,0.0000086381,0.000003755916,0.0000130000135,0.0000026702126,0.99176073,0.00069348316,0.00624474,0.001188964,0.0000052296627],"about_ca_topic_score_codex":0.0047079413,"about_ca_topic_score_gemma":0.0056964275,"teacher_disagreement_score":0.00709319,"about_ca_system_score_codex":0.0011943943,"about_ca_system_score_gemma":0.0024462137,"threshold_uncertainty_score":0.023729086},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006426394,0.006513982,0.9765302,0.002999222,0.00025886047,0.000037578062,0.00012274343,0.0001845731,0.0069265305],"genre_scores_gemma":[0.45002776,0.027011318,0.48438677,0.0025039224,0.0036825675,0.0010609806,0.0013343159,0.0013290897,0.028663341],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99317837,0.003422833,0.0003916715,0.0009334758,0.0017920351,0.00028163794],"domain_scores_gemma":[0.8800831,0.10501203,0.0024451588,0.0048179375,0.0063767987,0.0012650649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015816439,0.0017330486,0.0024070723,0.003761286,0.0011187142,0.0046882243,0.0025287936,0.0029510101,0.0050661354],"category_scores_gemma":[0.11548364,0.0013193305,0.0018016986,0.004122261,0.0064855283,0.011572999,0.00543376,0.010823598,0.0013446338],"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":[0.00008660978,0.00012526702,0.0014565422,0.00036185942,0.00014856842,0.00010531262,0.00025795776,0.078584574,0.0006229179,0.8393021,0.006628034,0.072320245],"study_design_scores_gemma":[0.000011107145,0.0000257325,0.00047369092,0.00009063612,0.00002065729,0.000069570044,0.000025991396,0.29284498,0.00032684393,0.70405704,0.0020298092,0.000023886667],"about_ca_topic_score_codex":0.0032628789,"about_ca_topic_score_gemma":0.0026981463,"teacher_disagreement_score":0.015816439,"about_ca_system_score_codex":0.004139899,"about_ca_system_score_gemma":0.002232968,"threshold_uncertainty_score":0.0836463},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029514993,0.00033156396,0.6001756,0.0018376495,0.0010305739,0.00022612464,0.039205246,0.22842099,0.1258207],"genre_scores_gemma":[0.07114521,0.00065957266,0.42851105,0.0012087007,0.0004983575,0.0008487629,0.09064667,0.11586295,0.2906187],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905986,0.00013411508,0.00006933509,0.00018406528,0.0004225062,0.0001300586],"domain_scores_gemma":[0.99792635,0.0006443673,0.00008821191,0.00051675463,0.0006964472,0.00012778235],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001748564,0.0016167777,0.0009665802,0.0013364798,0.0005826448,0.0028836534,0.002343838,0.0018902492,0.35122356],"category_scores_gemma":[0.007123843,0.00068343885,0.00085388817,0.0014143122,0.0005182894,0.0025197554,0.0019368449,0.001814868,0.26057014],"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":[0.00032012723,0.00008521171,0.0003253379,0.00034185467,0.000029603863,0.000093413044,0.000062216655,0.0076934216,0.0034311821,0.030993568,0.82735085,0.12927319],"study_design_scores_gemma":[0.00038628408,0.0000765516,0.0008881712,0.00015033096,0.00002164193,0.00027913053,0.000051107843,0.15420614,0.034889754,0.040980846,0.76798403,0.00008604252],"about_ca_topic_score_codex":0.004554507,"about_ca_topic_score_gemma":0.0053594513,"teacher_disagreement_score":0.35122356,"about_ca_system_score_codex":0.0015534593,"about_ca_system_score_gemma":0.0014883314,"threshold_uncertainty_score":0.92540085},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0495634,0.06477995,0.11934837,0.13053861,0.011769567,0.0005044129,0.023671167,0.010899223,0.5889253],"genre_scores_gemma":[0.14833476,0.02139194,0.046392072,0.0033017988,0.002574889,0.00034244955,0.008311202,0.0012871339,0.7680638],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99816173,0.00028455022,0.00004594002,0.00063338643,0.0005721782,0.00030213615],"domain_scores_gemma":[0.99580586,0.0012795399,0.00013486696,0.00042556826,0.0016846535,0.0006695371],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013109565,0.0016927393,0.0017211884,0.0016910479,0.0029968768,0.003946762,0.0014393191,0.0012413225,0.1790546],"category_scores_gemma":[0.0061784564,0.0005547154,0.00073851657,0.0021431625,0.0014998764,0.0017186089,0.0017007444,0.0021178257,0.07696739],"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":[0.0005107415,0.00018468342,0.005948986,0.00054997427,0.00008970244,0.0008251747,0.00046745985,0.0061535574,0.002810973,0.07145476,0.5293137,0.3816904],"study_design_scores_gemma":[0.00006716756,0.000046015815,0.0059747617,0.00020644147,0.000033172502,0.00030368584,0.00024520323,0.011153402,0.0033329455,0.012130451,0.966409,0.00009780224],"about_ca_topic_score_codex":0.31767812,"about_ca_topic_score_gemma":0.3316363,"teacher_disagreement_score":0.8209454,"about_ca_system_score_codex":0.00679459,"about_ca_system_score_gemma":0.010114811,"threshold_uncertainty_score":0.6316581},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010444081,0.028072547,0.48006782,0.050429814,0.11745207,0.0006427819,0.021027941,0.009041464,0.2828215],"genre_scores_gemma":[0.03854281,0.00935475,0.12732747,0.002286637,0.0059276186,0.0002212727,0.010504846,0.0032186809,0.80261594],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987814,0.00027243423,0.000069504684,0.00037463242,0.00037822194,0.00012375647],"domain_scores_gemma":[0.9961843,0.00087681384,0.00013323782,0.0007223433,0.0017860461,0.0002972882],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002580753,0.0011299106,0.002282661,0.0013875815,0.0012730429,0.0047605694,0.002037691,0.0016910221,0.3128064],"category_scores_gemma":[0.010447955,0.0006635509,0.0007518267,0.002920113,0.0011897077,0.0029703618,0.0016945604,0.0014667503,0.1206461],"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":[0.00017850735,0.000051425763,0.0005890412,0.00039224364,0.00007181532,0.00012054983,0.0000930388,0.0029504434,0.0010359663,0.013324537,0.7573964,0.22379611],"study_design_scores_gemma":[0.000063747226,0.00007379999,0.001413781,0.0002463056,0.000038210033,0.00029178165,0.00013045724,0.025534347,0.0037807256,0.02158802,0.94677615,0.0000627372],"about_ca_topic_score_codex":0.007993396,"about_ca_topic_score_gemma":0.02117678,"teacher_disagreement_score":0.3128064,"about_ca_system_score_codex":0.0018209767,"about_ca_system_score_gemma":0.0023752917,"threshold_uncertainty_score":0.98019826},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009839234,0.0010131826,0.008218735,0.003269703,0.002438869,0.0010956244,0.15159227,0.04431669,0.787071],"genre_scores_gemma":[0.0059180367,0.001269028,0.0054562865,0.00084731187,0.000336095,0.0004525517,0.07866244,0.016443186,0.89061505],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986033,0.00008792653,0.00009295904,0.00018572713,0.00080655183,0.00022355928],"domain_scores_gemma":[0.9936417,0.0004999124,0.00009559731,0.0008499565,0.00452475,0.0003881555],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013470569,0.0012667828,0.0011532733,0.003031891,0.0017416178,0.0072221914,0.0027342674,0.0015585715,0.794925],"category_scores_gemma":[0.008963575,0.0007669426,0.00095137965,0.0038299358,0.0007185463,0.0025990496,0.0019163631,0.001993922,0.7900999],"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":[0.0000353382,0.000011207084,0.00012910382,0.000088325745,0.0000033518165,0.000018643743,0.000026662514,0.00009764507,0.00015906383,0.0011249114,0.97586435,0.022441339],"study_design_scores_gemma":[0.000022281412,0.000008547103,0.00051743176,0.00010656054,0.0000036740025,0.000042317548,0.000031882944,0.00018144598,0.00045193805,0.0005111729,0.9981059,0.000016923861],"about_ca_topic_score_codex":0.19043383,"about_ca_topic_score_gemma":0.13279518,"teacher_disagreement_score":0.20507503,"about_ca_system_score_codex":0.0063134674,"about_ca_system_score_gemma":0.006123321,"threshold_uncertainty_score":0.37865078},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040571196,0.00035558542,0.9931901,0.00009943225,0.000038076036,0.00003163884,0.000020983593,0.0002972935,0.0019098156],"genre_scores_gemma":[0.2054624,0.00076852,0.78814036,0.00023201031,0.00011050351,0.0003099285,0.0001676973,0.00028559702,0.004522897],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989579,0.00038128375,0.000057401376,0.00010152823,0.00043936996,0.00006245942],"domain_scores_gemma":[0.99818546,0.000938356,0.00016236067,0.00027031082,0.00037973185,0.000063833126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023957063,0.0013739793,0.0014419772,0.0010547006,0.00043587747,0.0014273151,0.0014678877,0.0014877504,0.0027068122],"category_scores_gemma":[0.006372335,0.0006227244,0.0008043089,0.0011986895,0.0012753864,0.0016776322,0.0017160125,0.0014641115,0.0013665108],"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":[0.00022330444,0.000109975794,0.0008321336,0.00027642612,0.00015348807,0.000077125966,0.00009824716,0.7443352,0.0053508724,0.07758654,0.0034234172,0.16753334],"study_design_scores_gemma":[0.000031155825,0.00004417666,0.000079697544,0.000014206749,0.000008906404,0.000035707246,0.0000055555006,0.9856608,0.0015800475,0.010763362,0.0017654926,0.000010956202],"about_ca_topic_score_codex":0.0014733074,"about_ca_topic_score_gemma":0.001741259,"teacher_disagreement_score":0.0027068122,"about_ca_system_score_codex":0.00061666616,"about_ca_system_score_gemma":0.0011654189,"threshold_uncertainty_score":0.012669861},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033262237,0.000051644594,0.99558026,0.00014246658,0.000014834092,0.000044360306,0.000024052953,0.00039506023,0.00042106071],"genre_scores_gemma":[0.16731231,0.00012689379,0.82960755,0.00031904064,0.00006898221,0.00046040118,0.00028301778,0.00064402237,0.0011778275],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940235,0.0034181385,0.00035101114,0.0007906305,0.0011748642,0.00024184074],"domain_scores_gemma":[0.9807536,0.013005114,0.0014273464,0.0026045898,0.0016947896,0.0005145751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009987648,0.0017716215,0.0019944904,0.0033228197,0.0013437637,0.0034020192,0.0028827307,0.0027130574,0.0038544624],"category_scores_gemma":[0.053117618,0.0014385065,0.0014939572,0.002378927,0.00228421,0.004822146,0.005244257,0.004822833,0.00180394],"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":[0.0003623566,0.0003726486,0.004723189,0.0003312032,0.00030515608,0.0002927863,0.00058447267,0.46348906,0.009225136,0.08100771,0.0075988085,0.43170738],"study_design_scores_gemma":[0.000046435583,0.000027147986,0.0002829009,0.000031747204,0.000014181772,0.000048061447,0.000039164523,0.9408963,0.0017462613,0.055907745,0.00092368544,0.00003634687],"about_ca_topic_score_codex":0.0013658791,"about_ca_topic_score_gemma":0.0019972601,"teacher_disagreement_score":0.009987648,"about_ca_system_score_codex":0.0010408509,"about_ca_system_score_gemma":0.0024202205,"threshold_uncertainty_score":0.052820385},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04417145,0.0023322448,0.9436895,0.0013056197,0.00011305949,0.00006447418,0.00015825464,0.0003032718,0.007861989],"genre_scores_gemma":[0.8170654,0.0039838,0.16713943,0.0007625803,0.00039434334,0.000775136,0.00041061416,0.0004895993,0.008978984],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986608,0.0006524443,0.00007893202,0.00017954457,0.00030968722,0.000118669],"domain_scores_gemma":[0.9851217,0.011331956,0.0010036698,0.0006080394,0.0012933646,0.0006412522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061206636,0.001392284,0.0013131584,0.0019940208,0.0009869698,0.00229193,0.0022140066,0.0017106658,0.002432125],"category_scores_gemma":[0.029726079,0.00067848334,0.0011494884,0.001038211,0.0038118947,0.0048490255,0.0029045634,0.0028983748,0.00038934802],"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":[0.000048090835,0.000046972244,0.0009767815,0.0002515688,0.0000726709,0.00013730057,0.00022193226,0.1826153,0.0014090007,0.804739,0.0015082848,0.007973071],"study_design_scores_gemma":[0.000008591148,0.0000157457,0.00013981355,0.00003102093,0.000007682253,0.000025652218,0.00001611192,0.8060734,0.00022717776,0.1929831,0.00046087042,0.0000108355225],"about_ca_topic_score_codex":0.0028962672,"about_ca_topic_score_gemma":0.002232247,"teacher_disagreement_score":0.0061206636,"about_ca_system_score_codex":0.0022255206,"about_ca_system_score_gemma":0.001305902,"threshold_uncertainty_score":0.032369554},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005834742,0.000049536477,0.9933717,0.000051785024,0.00005383378,0.000032215317,0.00001513191,0.00020015128,0.00039083848],"genre_scores_gemma":[0.08130561,0.00006509608,0.91539156,0.00007159981,0.00006172525,0.0001696916,0.00013077585,0.000119606426,0.0026843236],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991541,0.0001901051,0.000051229174,0.00014029801,0.0003914036,0.00007290389],"domain_scores_gemma":[0.99917185,0.00020211308,0.00006658,0.00013426386,0.0003516534,0.000073618256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011111086,0.00084796123,0.0009632577,0.00068704726,0.00044615797,0.0007708421,0.0011685615,0.00089734147,0.0041851485],"category_scores_gemma":[0.0021826874,0.0005139009,0.0005792378,0.00067592046,0.00074616086,0.0009406113,0.001528155,0.0013993131,0.0011540904],"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":[0.0007755523,0.00017289538,0.0008715529,0.00019261366,0.00013659317,0.00016738428,0.00017940062,0.38155657,0.0612804,0.06070568,0.0065486897,0.4874126],"study_design_scores_gemma":[0.00006390496,0.00008006402,0.000114270675,0.0000058276673,0.000011147312,0.000048290698,0.000010704472,0.9821783,0.0065324237,0.008738631,0.0022034002,0.000012971768],"about_ca_topic_score_codex":0.0014984402,"about_ca_topic_score_gemma":0.0014539418,"teacher_disagreement_score":0.0041851485,"about_ca_system_score_codex":0.0004919502,"about_ca_system_score_gemma":0.0011325054,"threshold_uncertainty_score":0.014000714},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30513147,0.0005829897,0.68326193,0.002146236,0.00006630495,0.00006210393,0.00023737903,0.00075142103,0.007760212],"genre_scores_gemma":[0.9744839,0.0001902942,0.023401164,0.00018688642,0.000023945242,0.000046440495,0.00007735253,0.00007891022,0.0015110526],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987538,0.00047197784,0.000067076806,0.00026372136,0.00028422903,0.0001592461],"domain_scores_gemma":[0.9930252,0.004372966,0.0008183321,0.0010935654,0.00045649402,0.00023352285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031178673,0.000572399,0.00068256335,0.0003775839,0.00048777083,0.0012272403,0.0010946128,0.001158537,0.0018430863],"category_scores_gemma":[0.018839166,0.00046239307,0.0005469267,0.00035924278,0.002434807,0.0032125346,0.002075816,0.0028489842,0.00024948834],"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":[0.00045084947,0.00009323323,0.005459479,0.00013276121,0.00008131381,0.00026232502,0.0002609156,0.80242425,0.009661417,0.14912564,0.0025549342,0.029492939],"study_design_scores_gemma":[0.000012671218,0.000060258753,0.0005855858,0.000013609461,0.0000073769015,0.000049910836,0.00002677546,0.95195895,0.0026418397,0.044258364,0.00037482585,0.000009877996],"about_ca_topic_score_codex":0.0015427896,"about_ca_topic_score_gemma":0.0013270349,"teacher_disagreement_score":0.0031178673,"about_ca_system_score_codex":0.001207972,"about_ca_system_score_gemma":0.0011041431,"threshold_uncertainty_score":0.016489089},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16982529,0.0006848308,0.8159569,0.0026293728,0.000086999404,0.00007261194,0.0001929371,0.0005435125,0.01000748],"genre_scores_gemma":[0.9447551,0.0005385742,0.04990233,0.00034588392,0.00006311431,0.00011815869,0.00015270163,0.00019618013,0.003928056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954104,0.00015089249,0.000029446564,0.00012577239,0.000091962225,0.000060840677],"domain_scores_gemma":[0.9968809,0.0017555545,0.0004653176,0.00040331992,0.00030283848,0.00019203928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018827523,0.0005945097,0.0008992566,0.0008687852,0.0008077002,0.0012597524,0.001086751,0.0014406568,0.003753277],"category_scores_gemma":[0.012429841,0.0007095443,0.0008842356,0.00047838458,0.0023158828,0.0031952383,0.0016700323,0.0020967117,0.00053115515],"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":[0.000101296864,0.00005661862,0.0060576717,0.00018398887,0.00011277442,0.0004344126,0.0005665219,0.39314216,0.0077737616,0.558405,0.005052657,0.028113019],"study_design_scores_gemma":[0.000014982222,0.000047202473,0.0011932488,0.00002697798,0.000011121479,0.00008879251,0.00003855652,0.73318243,0.0008774236,0.26345825,0.0010412352,0.000019793872],"about_ca_topic_score_codex":0.0019204709,"about_ca_topic_score_gemma":0.0019751254,"teacher_disagreement_score":0.003753277,"about_ca_system_score_codex":0.0012191718,"about_ca_system_score_gemma":0.0007296566,"threshold_uncertainty_score":0.012555957},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022896437,0.06726927,0.82130235,0.0030835953,0.0028828194,0.000048818205,0.0004603146,0.0012491116,0.10141403],"genre_scores_gemma":[0.063220985,0.07823686,0.45685312,0.0014908831,0.0036813368,0.00029526552,0.0013429752,0.0020216934,0.39285684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99966896,0.00007193295,0.000018622586,0.000059675414,0.0001615885,0.000019277748],"domain_scores_gemma":[0.99966776,0.00021694641,0.000014245173,0.000038786668,0.00005231506,0.000009892236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055461575,0.0013423061,0.00095882325,0.00087334187,0.00034628762,0.0016893414,0.0010070753,0.0018217952,0.010363265],"category_scores_gemma":[0.0017420382,0.000743003,0.00052405207,0.0025510278,0.0011323484,0.0028129113,0.00077573356,0.0026331965,0.0052277404],"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":[0.000028514842,0.000048445094,0.00012968537,0.0005770991,0.000034535682,0.000060698203,0.00010007517,0.033106312,0.0016381405,0.49614763,0.10653878,0.36159015],"study_design_scores_gemma":[0.000010708962,0.000026578444,0.00025955416,0.00022316085,0.000024601632,0.00013118687,0.00001995343,0.117341444,0.0029586377,0.5925583,0.2864138,0.000032023116],"about_ca_topic_score_codex":0.0025279664,"about_ca_topic_score_gemma":0.0034970155,"teacher_disagreement_score":0.010363265,"about_ca_system_score_codex":0.0011743702,"about_ca_system_score_gemma":0.0006671145,"threshold_uncertainty_score":0.034668505},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022896437,0.06726927,0.82130235,0.0030835953,0.0028828194,0.000048818205,0.0004603146,0.0012491116,0.10141403],"genre_scores_gemma":[0.063220985,0.07823686,0.45685312,0.0014908831,0.0036813368,0.00029526552,0.0013429752,0.0020216934,0.39285684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99966896,0.00007193295,0.000018622586,0.000059675414,0.0001615885,0.000019277748],"domain_scores_gemma":[0.99966776,0.00021694641,0.000014245173,0.000038786668,0.00005231506,0.000009892236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055461575,0.0013423061,0.00095882325,0.00087334187,0.00034628762,0.0016893414,0.0010070753,0.0018217952,0.010363265],"category_scores_gemma":[0.0017420382,0.000743003,0.00052405207,0.0025510278,0.0011323484,0.0028129113,0.00077573356,0.0026331965,0.0052277404],"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":[0.000028514842,0.000048445094,0.00012968537,0.0005770991,0.000034535682,0.000060698203,0.00010007517,0.033106312,0.0016381405,0.49614763,0.10653878,0.36159015],"study_design_scores_gemma":[0.000010708962,0.000026578444,0.00025955416,0.00022316085,0.000024601632,0.00013118687,0.00001995343,0.117341444,0.0029586377,0.5925583,0.2864138,0.000032023116],"about_ca_topic_score_codex":0.0025279664,"about_ca_topic_score_gemma":0.0034970155,"teacher_disagreement_score":0.010363265,"about_ca_system_score_codex":0.0011743702,"about_ca_system_score_gemma":0.0006671145,"threshold_uncertainty_score":0.034668505},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13148218,0.0016139804,0.83297384,0.0027575293,0.00020304143,0.000120741606,0.00017217989,0.0003639678,0.030312581],"genre_scores_gemma":[0.94432795,0.00092761713,0.04350272,0.00025459722,0.00016269827,0.00028260902,0.00010458987,0.00016434709,0.010272934],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996389,0.00015862405,0.000020055199,0.0000515025,0.000079687736,0.0000512511],"domain_scores_gemma":[0.9966365,0.0021234653,0.00046088392,0.00015246842,0.00031403932,0.00031270317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012839651,0.00081579655,0.0006999629,0.0013296126,0.0007831716,0.0013835666,0.000770935,0.0009461422,0.0053556017],"category_scores_gemma":[0.010186115,0.00033444562,0.0005829908,0.00043435796,0.0017058288,0.0016739882,0.001600866,0.0019498504,0.00060660567],"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":[0.00004744478,0.000033051307,0.0011340685,0.000105120205,0.00003488078,0.00017187287,0.00029215307,0.2399801,0.0026851848,0.7386686,0.0034397463,0.013407807],"study_design_scores_gemma":[0.000016378057,0.000024134206,0.0002511495,0.000031136162,0.00000533175,0.000039697225,0.000042473104,0.70514864,0.00028925177,0.29286218,0.0012736076,0.00001613343],"about_ca_topic_score_codex":0.0009744365,"about_ca_topic_score_gemma":0.0009021337,"teacher_disagreement_score":0.0053556017,"about_ca_system_score_codex":0.0013063225,"about_ca_system_score_gemma":0.0006815049,"threshold_uncertainty_score":0.017916262},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060195234,0.00071364536,0.9902569,0.0002800831,0.00015689676,0.000077575954,0.000038726455,0.0005491956,0.0019074896],"genre_scores_gemma":[0.374496,0.0015376786,0.6158322,0.00060364936,0.00041852662,0.0006675426,0.0003580874,0.00061853573,0.0054677706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966827,0.0017792822,0.00014749439,0.00036632922,0.00082097965,0.00020326815],"domain_scores_gemma":[0.9944857,0.002839853,0.00042468117,0.000808533,0.0012398125,0.00020150251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008160103,0.0013628483,0.0019747175,0.0011425387,0.0006910599,0.0017835821,0.0022404897,0.0018531731,0.002580493],"category_scores_gemma":[0.030446896,0.0007191971,0.0009994131,0.0012818524,0.0012654129,0.002277867,0.0016726094,0.003046628,0.0021084142],"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":[0.00024667874,0.000121823505,0.0021239177,0.00029142384,0.00012907563,0.00012053842,0.00017128042,0.6686759,0.0042905444,0.1358318,0.009392732,0.17860433],"study_design_scores_gemma":[0.000024570802,0.000035354664,0.0001350612,0.000028642387,0.000012312724,0.000042856773,0.000007856858,0.96211076,0.0011195067,0.033317894,0.0031520769,0.000013270927],"about_ca_topic_score_codex":0.0012109153,"about_ca_topic_score_gemma":0.00093683513,"teacher_disagreement_score":0.008160103,"about_ca_system_score_codex":0.0010737502,"about_ca_system_score_gemma":0.0014046557,"threshold_uncertainty_score":0.043155253},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011534998,0.000392325,0.9814353,0.00045297065,0.00010514451,0.00010650228,0.00009287664,0.0005696497,0.0053103287],"genre_scores_gemma":[0.7046481,0.0009033542,0.28686303,0.00017529765,0.00011954158,0.00060991297,0.00030952823,0.0002586553,0.0061125257],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992242,0.00029820367,0.000039570703,0.00017142713,0.00017794603,0.00008867252],"domain_scores_gemma":[0.99859136,0.0005953539,0.00012089305,0.00023055827,0.00035917465,0.000102557846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011585536,0.00064017787,0.0007448799,0.0006691362,0.0007493165,0.0013420096,0.0017809186,0.00072729343,0.0043194923],"category_scores_gemma":[0.0053885453,0.00046052292,0.0004252156,0.0006989963,0.00063366693,0.0019349462,0.0012999938,0.0010573635,0.0009888008],"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":[0.00010453709,0.000051540042,0.00048406195,0.0001350494,0.00002002107,0.000078963385,0.00005862148,0.8814828,0.0037466707,0.03614346,0.0039801737,0.07371418],"study_design_scores_gemma":[0.0000120334325,0.000023359831,0.000087583045,0.000009424869,0.0000055718947,0.000031300973,0.000018448192,0.9808688,0.0007092732,0.016074581,0.0021530483,0.0000064945784],"about_ca_topic_score_codex":0.0017161856,"about_ca_topic_score_gemma":0.002169543,"teacher_disagreement_score":0.0043194923,"about_ca_system_score_codex":0.0013220834,"about_ca_system_score_gemma":0.0011214019,"threshold_uncertainty_score":0.014450133},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012681577,0.00062674895,0.9819594,0.0006255123,0.00008453062,0.00004006393,0.00004300258,0.0003012884,0.0036378817],"genre_scores_gemma":[0.5461362,0.0013293833,0.44338316,0.0003946676,0.00026788044,0.00023332126,0.00016966164,0.00025981423,0.007825897],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99762744,0.00085198594,0.000119324424,0.0004030934,0.000795454,0.00020270725],"domain_scores_gemma":[0.9936133,0.003278914,0.00059882726,0.0016168258,0.000749809,0.00014233733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029353467,0.0009835848,0.0013711283,0.000703204,0.00060038955,0.002158503,0.002204043,0.0013326934,0.001574161],"category_scores_gemma":[0.013903119,0.00062853505,0.0008381703,0.0015108616,0.0017409364,0.0027801886,0.0027111075,0.003156169,0.0006608136],"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":[0.00021867132,0.00008091912,0.00055304536,0.00019479901,0.00006454493,0.00007368206,0.00020017782,0.7802011,0.0037431095,0.14223073,0.0030658797,0.0693734],"study_design_scores_gemma":[0.000031063486,0.000040301013,0.00007718982,0.000015303427,0.00000868716,0.000035353016,0.00001904277,0.95561016,0.0014673906,0.041140873,0.0015462689,0.000008355291],"about_ca_topic_score_codex":0.0013952513,"about_ca_topic_score_gemma":0.0011798172,"teacher_disagreement_score":0.0029353467,"about_ca_system_score_codex":0.0017527597,"about_ca_system_score_gemma":0.0020058297,"threshold_uncertainty_score":0.015523791},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1701197,0.0033836975,0.7918957,0.004688934,0.00007830131,0.00006990986,0.00045816298,0.0005066918,0.028798955],"genre_scores_gemma":[0.92258525,0.00201121,0.066205144,0.0004084737,0.00014533206,0.00018007714,0.00042717872,0.0002777275,0.007759646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992836,0.000306439,0.00002674184,0.00012560793,0.00018273198,0.000074977455],"domain_scores_gemma":[0.99844664,0.00087782927,0.00017819478,0.0001292956,0.0002266907,0.00014130393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016812714,0.00059147744,0.000672061,0.00093391596,0.00049504446,0.0020289326,0.0007760932,0.0010438666,0.0026921225],"category_scores_gemma":[0.0059621935,0.00045266247,0.0005748692,0.00038938588,0.0019533054,0.0026038848,0.0016095288,0.0018021659,0.00044954335],"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":[0.000061089966,0.000031440002,0.0012400768,0.000096593896,0.000027539265,0.000093403345,0.00013638093,0.26009032,0.0022765899,0.71563643,0.0029604323,0.017349714],"study_design_scores_gemma":[0.000009169728,0.000038285332,0.00072427443,0.000027198279,0.000005344449,0.00005766569,0.000032567477,0.57722044,0.0005261067,0.41907942,0.0022650496,0.000014601375],"about_ca_topic_score_codex":0.0011797386,"about_ca_topic_score_gemma":0.00057310425,"teacher_disagreement_score":0.0026921225,"about_ca_system_score_codex":0.0016520253,"about_ca_system_score_gemma":0.000533776,"threshold_uncertainty_score":0.011986375},"labels":[],"label_agreement":null}]}