{"meta":{"query_hash":"8fe21527b3df","filters":{"venue":"Proceedings of International Conference on Neural Networks (ICNN'96)"},"cohort_total":8,"direct_labels_cover":0,"predictions_cover":8,"exported":8,"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/8fe21527b3df","api":"https://metacan.xera.ac/api/v1/cohort?venue=Proceedings+of+International+Conference+on+Neural+Networks+%28ICNN%2796%29"},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.058983145013753346,"score_gpt":0.2745676832261193,"score_spread":0.21558453821236595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100283156","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7153641,0.000893429,0.17903484,0.06155861,0.004651715,0.0037833536,0.00007824543,0.0012903366,0.033345338],"genre_scores_gemma":[0.9904781,0.00013909914,0.0061784894,0.0011641859,0.0012340697,0.0002716325,0.000020596035,0.00003407156,0.00047977525],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972473,0.000018189967,0.0006784567,0.00086541753,0.0005728706,0.00061776093],"domain_scores_gemma":[0.9979189,0.00019864223,0.0005659439,0.0003156842,0.00080954784,0.00019129853],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024362003,0.00039039186,0.00036805778,0.00017352875,0.00027844697,0.00041835106,0.0020780014,0.00015808964,0.00007870701],"category_scores_gemma":[0.000065934684,0.00035583222,0.0002429472,0.0005405002,0.00014120253,0.00037569297,0.00025913134,0.00046577986,0.000010794293],"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":[0.00012877474,0.00026902417,0.0023372478,0.000039056005,0.000092437775,0.0000024639648,0.0001732012,0.13809048,0.004973035,0.74761695,0.019335823,0.08694152],"study_design_scores_gemma":[0.0004389496,0.00025240163,0.0022361155,0.000071345356,0.000014667246,0.000021156182,0.000019786141,0.9811339,0.0003946929,0.012606145,0.0024705732,0.00034031188],"about_ca_topic_score_codex":0.000006258172,"about_ca_topic_score_gemma":0.0000033183553,"teacher_disagreement_score":0.8430434,"about_ca_system_score_codex":0.000054381977,"about_ca_system_score_gemma":0.000012529741,"threshold_uncertainty_score":0.9998894},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03712323545250512,"score_gpt":0.26961427705257773,"score_spread":0.2324910416000726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107999479","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9342815,0.0006896866,0.024145192,0.018382857,0.006327165,0.0044647055,0.000046555047,0.0004797663,0.011182536],"genre_scores_gemma":[0.99548864,0.0010297213,0.001511273,0.00048182585,0.0007530771,0.00026627813,0.000023699542,0.000035686822,0.00040979058],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704874,0.000033730128,0.000835528,0.00078748,0.0007234413,0.00057108136],"domain_scores_gemma":[0.9962342,0.0012357581,0.00083535904,0.00033500977,0.0011980513,0.00016164442],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003927161,0.00041221318,0.00041868992,0.00019065608,0.00035058742,0.00039905534,0.0019568026,0.00019557135,0.000027206139],"category_scores_gemma":[0.00031603998,0.0003156226,0.0002930262,0.0005817855,0.00016782382,0.00067804335,0.0002785981,0.0005704369,0.000007960486],"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":[0.000544786,0.00045188412,0.00024601916,0.00008916384,0.00012751567,0.0000037339987,0.00014613572,0.0099243065,0.0064593623,0.087971166,0.020917246,0.8731187],"study_design_scores_gemma":[0.0007723301,0.0010550525,0.00034041045,0.00034522152,0.000025654877,0.000017849332,0.000022898113,0.9811982,0.009977424,0.0050422265,0.0008828292,0.00031988273],"about_ca_topic_score_codex":0.000008289609,"about_ca_topic_score_gemma":0.000003121584,"teacher_disagreement_score":0.9712739,"about_ca_system_score_codex":0.00006594498,"about_ca_system_score_gemma":0.000012288623,"threshold_uncertainty_score":0.9999296},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.10408522941878491,"score_gpt":0.2857363058533977,"score_spread":0.1816510764346128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111377264","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4338864,0.0002624383,0.5180789,0.010524919,0.0009344237,0.002554297,0.00008363901,0.0006235724,0.03305139],"genre_scores_gemma":[0.96155876,0.00011855093,0.03699042,0.0004700955,0.00039648486,0.00018872363,0.00001330219,0.000023240393,0.00024040953],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803287,0.0000116853,0.0004096776,0.000767129,0.0003545003,0.00042411246],"domain_scores_gemma":[0.99865425,0.000097184085,0.0002898234,0.00017699857,0.000576018,0.00020570583],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001934361,0.00029892428,0.00030084,0.0001406662,0.00020767197,0.00035776378,0.0011611383,0.000116510135,0.000046808203],"category_scores_gemma":[0.00002732822,0.00027321358,0.00010975798,0.00023652687,0.00014561247,0.000941691,0.00016187984,0.00033152412,0.000002419085],"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":[0.00021715683,0.0005693162,0.0010159382,0.000032091804,0.000098548495,0.0000023655875,0.0023118136,0.018982315,0.0064294306,0.8202345,0.0042340704,0.14587247],"study_design_scores_gemma":[0.0004901672,0.0004902548,0.0007152246,0.000040349878,0.000012556924,0.000024968069,0.0003962382,0.9955651,0.00020341542,0.0014147559,0.00036346147,0.00028346202],"about_ca_topic_score_codex":0.000007547203,"about_ca_topic_score_gemma":0.0000023903374,"teacher_disagreement_score":0.9765828,"about_ca_system_score_codex":0.000032932123,"about_ca_system_score_gemma":0.000012412927,"threshold_uncertainty_score":0.999972},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0593627372812839,"score_gpt":0.286303340884466,"score_spread":0.22694060360318213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112636696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78983253,0.00089958054,0.043860808,0.04795896,0.001302564,0.0017572404,0.000061919134,0.0009695853,0.113356836],"genre_scores_gemma":[0.9929296,0.0005868173,0.004823733,0.0007238947,0.00017464784,0.0000779822,0.00003983597,0.00001660137,0.0006269146],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975176,0.000027681195,0.0006940802,0.0006654417,0.00073452876,0.0003606845],"domain_scores_gemma":[0.9977783,0.0001668078,0.00056769344,0.0004508383,0.0008690162,0.00016737015],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027621264,0.0003057749,0.00037393952,0.0003897393,0.00024407048,0.00045095288,0.002745125,0.00012564559,0.00044828333],"category_scores_gemma":[0.000050681658,0.0002820029,0.00025201341,0.0015139095,0.00013344684,0.0009557671,0.00063238345,0.00045670127,0.000030251205],"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":[0.00018944535,0.0012827554,0.023882922,0.000030697105,0.00101427,0.000007760009,0.0008081467,0.027945919,0.0054190545,0.8095561,0.038253788,0.091609105],"study_design_scores_gemma":[0.00035054112,0.00014442544,0.0031829225,0.00006765757,0.000058550457,0.000010463003,0.00005512402,0.9922376,0.00071602,0.0015690348,0.0013294165,0.00027819298],"about_ca_topic_score_codex":0.000022774084,"about_ca_topic_score_gemma":0.000010858156,"teacher_disagreement_score":0.96429175,"about_ca_system_score_codex":0.000074289,"about_ca_system_score_gemma":0.000009224629,"threshold_uncertainty_score":0.9999632},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.024368561284608414,"score_gpt":0.2384320765011076,"score_spread":0.2140635152164992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140479193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98849833,0.0004144874,0.008247839,0.0005435751,0.00039367573,0.0007721785,0.00001541688,0.0001835735,0.0009309108],"genre_scores_gemma":[0.99855644,0.0002638586,0.00030271176,0.00022107922,0.00038637788,0.00013079343,0.000019613828,0.000048080863,0.00007106529],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839836,0.000008093665,0.0004735268,0.0004686528,0.00022764681,0.00042373102],"domain_scores_gemma":[0.99926156,0.00012156297,0.00017261348,0.00008558665,0.00024597117,0.00011270556],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012456776,0.00033393066,0.00033840103,0.00019034196,0.00007948583,0.000076600605,0.00035270385,0.00010940094,0.00001824703],"category_scores_gemma":[0.00006620305,0.00033697064,0.000093399925,0.00020621305,0.00005016009,0.0003086255,0.00007763746,0.00055358885,0.0000012855759],"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":[0.00024675782,0.00007579323,0.00082197855,0.00013334653,0.00004296306,0.000006730282,0.00013449838,0.92025167,0.03537028,0.0034712767,0.00018474646,0.03925996],"study_design_scores_gemma":[0.00076660595,0.0001448355,0.00033824757,0.00013134824,0.00001130721,0.000048748596,0.000029584788,0.98953164,0.007827707,0.0006420364,0.00022862238,0.0002993314],"about_ca_topic_score_codex":0.0000027086344,"about_ca_topic_score_gemma":0.000004875969,"teacher_disagreement_score":0.069279954,"about_ca_system_score_codex":0.000049673632,"about_ca_system_score_gemma":0.0000024753317,"threshold_uncertainty_score":0.9999082},"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,"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; 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","score_opus":0.043550514904178717,"score_gpt":0.2629600539197134,"score_spread":0.21940953901553467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156451528","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7633016,0.0008898566,0.11232572,0.026763026,0.008286655,0.0023425317,0.000118122436,0.0008357653,0.085136734],"genre_scores_gemma":[0.9962392,0.0006525419,0.00076680013,0.00073909893,0.0005017197,0.00008645669,0.000014753081,0.000025269617,0.00097415445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997303,0.000022645354,0.0007678531,0.00076833414,0.0006506115,0.00048751803],"domain_scores_gemma":[0.99761,0.0002921427,0.000643431,0.00031661786,0.0009207776,0.00021704337],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021061965,0.0003873389,0.00042370596,0.000244632,0.00019857309,0.00022357397,0.0018042588,0.0001677336,0.00057292776],"category_scores_gemma":[0.00008118604,0.00035751692,0.00023527916,0.0007880761,0.00022080877,0.00066935166,0.00025969316,0.0005479093,0.00003370614],"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":[0.00026683134,0.00079630816,0.0058632805,0.000039956132,0.00017916925,0.000007727443,0.0002245464,0.09483911,0.0027768516,0.7877184,0.06417882,0.04310901],"study_design_scores_gemma":[0.0005069181,0.00035433075,0.0010477018,0.0001497385,0.000018457291,0.00001341641,0.000036945054,0.99311996,0.0014710127,0.001925209,0.001026871,0.00032943155],"about_ca_topic_score_codex":0.000020720236,"about_ca_topic_score_gemma":0.0000042444703,"teacher_disagreement_score":0.89828086,"about_ca_system_score_codex":0.000055469565,"about_ca_system_score_gemma":0.000019967549,"threshold_uncertainty_score":0.9998877},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04199792720959844,"score_gpt":0.24971038111181648,"score_spread":0.20771245390221804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160149488","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27645886,0.001382964,0.0814916,0.10663903,0.0063281977,0.0032168205,0.00009367187,0.0021965685,0.5221923],"genre_scores_gemma":[0.98856217,0.000270605,0.0046237796,0.0007666684,0.00035639966,0.00010261983,0.000008131122,0.000019234072,0.005290377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977112,0.000008257874,0.0005377745,0.000691267,0.0006338934,0.0004176293],"domain_scores_gemma":[0.9983973,0.00008209954,0.00037639777,0.00022404388,0.0007582916,0.0001618774],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001534224,0.00029782546,0.00025672707,0.00026194545,0.00019447142,0.00034666373,0.001817372,0.00008739052,0.00043040942],"category_scores_gemma":[0.00003608282,0.0002790727,0.000144391,0.00064651057,0.00014676705,0.0009646604,0.00036779468,0.00045462383,0.000031034106],"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":[0.000030237261,0.00069354934,0.0054735336,0.000028435203,0.000082807615,0.0000066523357,0.00034331848,0.008145582,0.0038952357,0.9134296,0.04461654,0.023254469],"study_design_scores_gemma":[0.00033965477,0.00015405151,0.0012562319,0.000094681614,0.000007941296,0.000027626073,0.000021733447,0.98451215,0.00056963676,0.007475814,0.005246484,0.0002939744],"about_ca_topic_score_codex":0.000013012786,"about_ca_topic_score_gemma":0.0000045314664,"teacher_disagreement_score":0.9763666,"about_ca_system_score_codex":0.000050349976,"about_ca_system_score_gemma":0.000015915572,"threshold_uncertainty_score":0.99996614},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Connectionism; Reinforcement learning; Computer science; Artificial intelligence; Machine learning; Artificial neural network","score_opus":0.08300094715980585,"score_gpt":0.26935311622455727,"score_spread":0.1863521690647514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165213417","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2327514,0.00016274393,0.73510474,0.00074113806,0.0013183833,0.00078038935,0.0000010726923,0.00082721474,0.028312897],"genre_scores_gemma":[0.99619067,0.000114321236,0.0015669097,0.00010597487,0.00028707672,0.000040338582,0.000020099842,0.00006171083,0.0016129289],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983735,0.000009197889,0.0005387423,0.00032875588,0.00036685477,0.00038296822],"domain_scores_gemma":[0.9989871,0.00007459214,0.00027485288,0.00005977234,0.0005066861,0.00009702085],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018832259,0.000292486,0.00030048675,0.00023772678,0.00027420674,0.0002467397,0.0002824775,0.00012919793,0.00020554644],"category_scores_gemma":[0.00015459768,0.00031965997,0.00014399769,0.00019545299,0.00005504305,0.0004356488,0.000054244694,0.0006508992,0.000008573524],"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":[0.00004666913,0.000018840266,0.0017640683,0.00005408932,0.00006173167,5.963277e-7,0.00028020536,0.9823762,0.0018347233,0.012104699,0.00023419828,0.001223966],"study_design_scores_gemma":[0.0006405785,0.0001456017,0.000059504615,0.00017016247,0.000026663909,0.000012360292,0.00026740754,0.9977263,0.00022642409,0.00019635414,0.00021860634,0.00031003],"about_ca_topic_score_codex":0.000011533901,"about_ca_topic_score_gemma":0.00000219088,"teacher_disagreement_score":0.76343924,"about_ca_system_score_codex":0.0001455041,"about_ca_system_score_gemma":0.000007982713,"threshold_uncertainty_score":0.99992555},"labels":[],"label_agreement":null}]}