{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":8,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":8,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"8fe21527b3df","filters":{"venue":"Proceedings of International Conference on Neural Networks (ICNN'96)"}},"results":[{"id":"W2100283156","doi":"10.1109/icnn.1996.549082","title":"Modular neural network architectures for classification","year":2002,"lang":"en","type":"article","venue":"Proceedings of International Conference on Neural Networks (ICNN'96)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Modular design; Computer science; Artificial neural network; Divide and conquer algorithms; Modular neural network; Artificial intelligence; Classifier (UML); Machine learning; Task (project management); Time delay neural network; Decomposition; Engineering; Algorithm","authors":[{"name":"G. Auda","is_ca":true},{"name":"Mohamed S. Kamel","is_ca":false},{"name":"Hazem Raafat","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05898314501375335,"gpt":0.2745676832261193,"spread":0.215584538212366,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007831473,0.000856349,0.000593157,0.0007278003,0.0002614222,0.0008126384,0.001145291,0.0008523587,0.00406476],"category_scores_gemma":[0.002167708,0.0002767977,0.0005410425,0.001201218,0.0004056995,0.001485048,0.000817398,0.001202798,0.00159134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006157623,"about_ca_system_score_gemma":0.0004825203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001662222,"about_ca_topic_score_gemma":0.002169478,"domain_scores_codex":[0.9996247,0.00009857415,0.00002225513,0.00008533183,0.0001324857,0.00003654221],"domain_scores_gemma":[0.9995604,0.000154015,0.00004161576,0.00007461904,0.0001487345,0.00002063921],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000123686,0.00006062496,0.0007821051,0.0003383963,0.0001263745,0.0001039531,0.00008605918,0.4067025,0.007802705,0.08170473,0.008655484,0.4935134],"study_design_scores_gemma":[0.000008394471,0.00003815123,0.0002468634,0.00002937022,0.00001977633,0.00004427663,0.000008526795,0.9515074,0.001428686,0.04093204,0.005724257,0.00001222244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006945231,0.002667039,0.984749,0.0003112524,0.0001661636,0.00004997227,0.0001047286,0.000907229,0.004099358],"genre_scores_gemma":[0.3529798,0.005150783,0.6295484,0.0003142398,0.0004919998,0.0003249677,0.0006251903,0.0001472348,0.01041738],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00406476,"threshold_uncertainty_score":0.01359802,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111377264","doi":"10.1109/icnn.1996.548874","title":"An adaptive and fully sparse training approach for multilayer perceptrons","year":2002,"lang":"en","type":"article","venue":"Proceedings of International Conference on Neural Networks (ICNN'96)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Backpropagation; Computer science; Artificial neural network; Artificial intelligence; Feed forward; Perceptron; Process (computing); Sparse approximation; Training (meteorology); Multilayer perceptron; Set (abstract data type); Pattern recognition (psychology); Feedforward neural network; Machine learning; Engineering; Control engineering","authors":[{"name":"Fang Wang","is_ca":true},{"name":"Q.J. Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1040852294187849,"gpt":0.2857363058533977,"spread":0.1816510764346128,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004215649,0.0004991567,0.0004659258,0.000345037,0.0002869085,0.0004193801,0.0009108399,0.0007253423,0.001966983],"category_scores_gemma":[0.001120832,0.0003289303,0.0004817592,0.000418662,0.0003534595,0.0007974162,0.0006723154,0.001070459,0.0005480176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002467668,"about_ca_system_score_gemma":0.0003927018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001336057,"about_ca_topic_score_gemma":0.002139869,"domain_scores_codex":[0.9997575,0.00005929255,0.00001400195,0.00004049699,0.0001036681,0.00002511143],"domain_scores_gemma":[0.9997082,0.0001191363,0.00002716709,0.0000513604,0.00007872959,0.00001530008],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000848116,0.00008256653,0.000433571,0.0001689369,0.00007357366,0.00009683839,0.000101621,0.3514486,0.04114019,0.03464989,0.002832412,0.5688869],"study_design_scores_gemma":[0.000004795455,0.00003134577,0.0001090422,0.000007050301,0.000008548496,0.00003924123,0.000002868871,0.9892445,0.003268494,0.004903363,0.002373199,0.000007521493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002350002,0.0001391092,0.9961627,0.00004805147,0.00002483554,0.0000184216,0.00001549761,0.000216328,0.001025065],"genre_scores_gemma":[0.1996168,0.0005952877,0.792965,0.0001743527,0.000147621,0.0001757956,0.0001534686,0.000125057,0.006046472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001966983,"threshold_uncertainty_score":0.006580234,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140479193","doi":"10.1109/icnn.1996.549011","title":"A modular architecture for hybrid VLSI neural networks and its application in a smart photosensor","year":2002,"lang":"en","type":"article","venue":"Proceedings of International Conference on Neural Networks (ICNN'96)","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Very-large-scale integration; Computer science; Scalability; Modular design; Block (permutation group theory); Neuromorphic engineering; CMOS; Robustness (evolution); Computer architecture; Artificial neural network; Computer hardware; Embedded system; Electronic engineering; Engineering; Artificial intelligence","authors":[{"name":"H. Djahanshahi","is_ca":true},{"name":"Majid Ahmadi","is_ca":true},{"name":"G.A. Jullien","is_ca":true},{"name":"William C. Miller","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02436856128460841,"gpt":0.2384320765011076,"spread":0.2140635152164992,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008063792,0.000173618,0.0001081888,0.0001470576,0.0001122915,0.000228547,0.0004167312,0.0002488918,0.001273131],"category_scores_gemma":[0.0001494366,0.0001186852,0.0001819641,0.0001600297,0.0002077206,0.0003814275,0.0002380376,0.0002154045,0.0003628641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002319941,"about_ca_system_score_gemma":0.0001176604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002270066,"about_ca_topic_score_gemma":0.0004824688,"domain_scores_codex":[0.9999563,0.00000668892,0.000002316917,0.00001122635,0.00001624767,0.000007406488],"domain_scores_gemma":[0.9999522,0.00001107492,0.000007867038,0.000009406773,0.00001443469,0.000005078606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001406557,0.00005065625,0.0006811345,0.0002148886,0.00006252368,0.0003397391,0.0001077343,0.1027547,0.6063114,0.07801611,0.002539802,0.2087807],"study_design_scores_gemma":[0.00005228336,0.0005536188,0.001408391,0.0000282689,0.00006438965,0.0008616801,0.00003259544,0.7303141,0.2042658,0.02328188,0.03909694,0.0000401861],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1224061,0.0009866118,0.86483,0.0002247558,0.00007848275,0.00004641991,0.00006821991,0.001752231,0.009607219],"genre_scores_gemma":[0.5999163,0.0004098483,0.3945984,0.0001058526,0.0000263183,0.00008942596,0.00007498416,0.00004405179,0.004734864],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001273131,"threshold_uncertainty_score":0.00425905,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165213417","doi":"10.1109/icnn.1996.549169","title":"A connectionist model for learning robotic grasps using reinforcement learning","year":2002,"lang":"en","type":"article","venue":"Proceedings of International Conference on Neural Networks (ICNN'96)","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Connectionism; Reinforcement learning; Computer science; Artificial intelligence; Machine learning; Artificial neural network","authors":[{"name":"Medhat Moussa","is_ca":true},{"name":"Mohamed S. Kamel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08300094715980585,"gpt":0.2693531162245573,"spread":0.1863521690647514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003961078,0.0006221952,0.0005714135,0.0002739974,0.0003138872,0.000650641,0.001350714,0.001111672,0.003221559],"category_scores_gemma":[0.001053184,0.0004227732,0.0004812153,0.000287594,0.0007424247,0.001030281,0.0005005904,0.001220299,0.0005860759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008998347,"about_ca_system_score_gemma":0.0008021249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006494574,"about_ca_topic_score_gemma":0.006764729,"domain_scores_codex":[0.9998287,0.00003235892,0.0000107964,0.00004773171,0.00005634305,0.00002391466],"domain_scores_gemma":[0.9997494,0.0001084615,0.00003521405,0.00003040624,0.00005304637,0.0000235314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004256325,0.00004590279,0.0002711737,0.00004416972,0.00003682811,0.00007042171,0.00003130612,0.9624177,0.002183947,0.01401382,0.0006381386,0.02020407],"study_design_scores_gemma":[0.00001011363,0.00002486217,0.00005556503,0.000003249168,0.000006469807,0.00001333215,0.000001261086,0.9930814,0.0002732778,0.006127247,0.0003984662,0.000004751771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02818758,0.0003668687,0.963428,0.0005129011,0.00008883295,0.00006493483,0.0001184596,0.0007638292,0.006468682],"genre_scores_gemma":[0.8790122,0.0005277242,0.1091638,0.0001740406,0.0000798133,0.0004470283,0.0001914099,0.00007167448,0.01033235],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006494574,"threshold_uncertainty_score":0.01291358,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107999479","doi":"10.1109/icnn.1996.549206","title":"The effects of reduced precision bit lengths on feedforward neural networks for speech recognition","year":2002,"lang":"en","type":"article","venue":"Proceedings of International Conference on Neural Networks (ICNN'96)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Technical University of Nova Scotia","funders":"","keywords":"Artificial neural network; Computer science; Feedforward neural network; Feed forward; Fixed-point arithmetic; Speech recognition; Fixed point; Floating point; Set (abstract data type); Arithmetic; A priori and a posteriori; Time delay neural network; Precision and recall; Independence (probability theory); Point (geometry); Algorithm; Artificial intelligence; Pattern recognition (psychology); Mathematics; Statistics","authors":[{"name":"Selçuk Şen","is_ca":true},{"name":"William Robertson","is_ca":true},{"name":"William Phillips","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03712323545250512,"gpt":0.2696142770525777,"spread":0.2324910416000726,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003080109,0.00119993,0.0004407264,0.0007964024,0.000589286,0.0009970963,0.001544831,0.0008894141,0.002368944],"category_scores_gemma":[0.03530487,0.0004996336,0.0003561818,0.0009328125,0.000869529,0.003763601,0.00069412,0.001351216,0.0004267722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001334244,"about_ca_system_score_gemma":0.0007073075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002679154,"about_ca_topic_score_gemma":0.003585786,"domain_scores_codex":[0.9974947,0.0008332324,0.0003080139,0.0002648307,0.0009607629,0.0001384593],"domain_scores_gemma":[0.9586891,0.03386775,0.002490961,0.002496569,0.002324733,0.0001308956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003480494,0.0002478027,0.003140431,0.0006384074,0.0001060208,0.0006544234,0.000351175,0.3209788,0.08345748,0.02022174,0.001388037,0.5653351],"study_design_scores_gemma":[0.0001309503,0.002535196,0.002401754,0.0002085933,0.0001683349,0.000785662,0.0001227787,0.8009154,0.172578,0.01593982,0.004122086,0.00009147244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3865935,0.0047821,0.5989261,0.001004691,0.000301445,0.0002310368,0.000139449,0.003382691,0.004638974],"genre_scores_gemma":[0.6949366,0.001162318,0.3009793,0.0002055105,0.0001322493,0.0001539099,0.0001159587,0.0001777523,0.002136342],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003080109,"threshold_uncertainty_score":0.01628941,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160149488","doi":"10.1109/icnn.1996.549071","title":"Neurosolver solves blocks world problems","year":2002,"lang":"en","type":"article","venue":"Proceedings of International Conference on Neural Networks (ICNN'96)","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Construct (python library); Problem solver; Task (project management); Solver; Process (computing); Artificial intelligence; Neuromorphic engineering; Control (management); Space (punctuation); State (computer science); Theoretical computer science; Programming language; Software engineering; Artificial neural network; Engineering","authors":[{"name":"Andrzej Bieszczad","is_ca":true},{"name":"B. Pagurek","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04199792720959844,"gpt":0.2497103811118165,"spread":0.207712453902218,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003352741,0.0006855234,0.0006225517,0.0003021914,0.000521387,0.0007580221,0.0009186591,0.0009349349,0.007771059],"category_scores_gemma":[0.001300335,0.0002481019,0.0004682709,0.0002286143,0.0007427909,0.001138334,0.001396017,0.0008427476,0.000850682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005186588,"about_ca_system_score_gemma":0.0007233253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001897481,"about_ca_topic_score_gemma":0.003784431,"domain_scores_codex":[0.999837,0.000040486,0.000007951118,0.00003759607,0.00004939922,0.00002750472],"domain_scores_gemma":[0.999707,0.0001598316,0.00002521539,0.00003988644,0.00003174256,0.00003628102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002422052,0.0002012562,0.001212539,0.0003060507,0.00009156926,0.0003815659,0.0003439759,0.5510232,0.01055244,0.2056576,0.01803254,0.211955],"study_design_scores_gemma":[0.00006834292,0.000114591,0.0001462282,0.00001615424,0.00001395393,0.00007755715,0.00008491628,0.9151341,0.004868911,0.06054084,0.0189224,0.00001194388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1833774,0.0006744047,0.7548479,0.00151935,0.0002473555,0.0003188945,0.0002867642,0.002482827,0.05624506],"genre_scores_gemma":[0.5195239,0.0004784902,0.4403237,0.0003093394,0.00007980786,0.0004500627,0.00046849,0.0004730911,0.03789319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007771059,"threshold_uncertainty_score":0.02599674,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112636696","doi":"10.1109/icnn.1996.549056","title":"Limited precision incremental communication: error analysis","year":2002,"lang":"en","type":"article","venue":"Proceedings of International Conference on Neural Networks (ICNN'96)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Backpropagation; Computer science; Convergence (economics); Error analysis; Perceptron; Nonlinear system; Propagation of uncertainty; Node (physics); Algorithm; Artificial neural network; Perturbation (astronomy); Artificial intelligence; Mathematics; Engineering","authors":[{"name":"Ali A. Ghorbani","is_ca":true},{"name":"Virendrakumar C. Bhavsar","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0593627372812839,"gpt":0.286303340884466,"spread":0.2269406036031821,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002259606,0.0006354116,0.0005427754,0.0007567551,0.0003541312,0.001025105,0.001356377,0.0010107,0.002424301],"category_scores_gemma":[0.02062745,0.0002951602,0.0003868334,0.0006207749,0.0009696914,0.00170105,0.001370942,0.001351215,0.0004153027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006984933,"about_ca_system_score_gemma":0.0006673784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001932202,"about_ca_topic_score_gemma":0.001027819,"domain_scores_codex":[0.9980479,0.0003072691,0.00008227414,0.0001559964,0.001290177,0.0001163197],"domain_scores_gemma":[0.9889184,0.007440435,0.000751677,0.001230483,0.001565,0.00009410029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002503449,0.00004631627,0.0006192723,0.000241108,0.00004337988,0.000190651,0.0001778621,0.8718857,0.01164429,0.03787266,0.0009021425,0.0761264],"study_design_scores_gemma":[0.000004078385,0.00004062723,0.0001409717,0.00001315921,0.000006788463,0.00004105618,0.000005867299,0.9892151,0.005087552,0.005118233,0.0003185332,0.000008106414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02687482,0.0005684076,0.967913,0.0001800181,0.0000571153,0.00004418869,0.00002902086,0.0003611589,0.003972242],"genre_scores_gemma":[0.8511956,0.0006967595,0.1428404,0.0001128471,0.00007304453,0.0001704986,0.0000777497,0.0001752245,0.004657766],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002424301,"threshold_uncertainty_score":0.01195014,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156451528","doi":"10.1109/icnn.1996.548897","title":"On MISE convergence rates of radial basis functions networks","year":2002,"lang":"en","type":"article","venue":"Proceedings of International Conference on Neural Networks (ICNN'96)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Alexander von Humboldt-Stiftung","keywords":"Convergence (economics); Radial basis function; Rate of convergence; Radial basis function network; Basis (linear algebra); Mathematics; Applied mathematics; Mean squared error; Computer science; Mathematical optimization; Algorithm; Artificial neural network; Artificial intelligence; Statistics; Telecommunications; Geometry","authors":[{"name":"A. Krzyiak","is_ca":true},{"name":"H. Niemann","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04355051490417872,"gpt":0.2629600539197134,"spread":0.2194095390155347,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02581356,0.002574718,0.002167742,0.003370222,0.001033693,0.002626329,0.002829388,0.002915198,0.003601277],"category_scores_gemma":[0.1401963,0.001020327,0.001504756,0.001970112,0.003986126,0.007531467,0.004059874,0.005100341,0.001486838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002425388,"about_ca_system_score_gemma":0.001138553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002535888,"about_ca_topic_score_gemma":0.001321882,"domain_scores_codex":[0.9927021,0.003488812,0.0004227826,0.0009060173,0.001871052,0.0006091092],"domain_scores_gemma":[0.8870595,0.08849984,0.005104511,0.004250105,0.01381553,0.001270352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005388397,0.0001105779,0.00566286,0.0005961084,0.0002355046,0.0003758937,0.0006004421,0.5484269,0.006162202,0.3733996,0.003214012,0.06067694],"study_design_scores_gemma":[0.00001324938,0.00008691548,0.0006719117,0.0001165954,0.00003067458,0.0001177503,0.00006104652,0.9256096,0.003454007,0.06836079,0.001431961,0.00004544442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03754129,0.0086248,0.9422122,0.001217336,0.0002471372,0.00008240494,0.0001411708,0.0003220931,0.009611511],"genre_scores_gemma":[0.7400079,0.01209397,0.2322613,0.0009032997,0.0008044966,0.0006075341,0.0005727585,0.0009140434,0.01183472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02581356,"threshold_uncertainty_score":0.1365168,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}