{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1336,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":1336,"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"},"query_hash":"347ee4cf1f29","filters":{"topic":"Advanced Neural Network Applications"}},"results":[{"id":"W2163605009","doi":"10.1145/3065386","title":"ImageNet classification with deep convolutional neural networks","year":2017,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":75709,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Softmax function; Convolutional neural network; Computer science; Pooling; Dropout (neural networks); Artificial intelligence; Convolution (computer science); Regularization (linguistics); Pattern recognition (psychology); Deep neural networks; Word error rate; Normalization (sociology); Artificial neural network; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.06443397073163805,"gpt":0.3127342939106008,"spread":0.2483003231789628,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0001476125,0.00009998013,0.0001073857,0.00002703116,0.001562505,0.0001133395,0.05644206,0.0000384942,0.000002328779],"category_scores_gemma":[0.0009398077,0.00007249221,0.00005773023,0.0002024414,0.0007417361,0.0004869688,0.01923155,0.0002167907,0.000007349086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003275544,"about_ca_system_score_gemma":0.00003758948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001492302,"about_ca_topic_score_gemma":0.00007284257,"domain_scores_codex":[0.9991522,0.00009591767,0.000212434,0.0002145143,0.0001660568,0.0001589025],"domain_scores_gemma":[0.9454252,0.0002448405,0.0004660415,0.05362982,0.0001908875,0.00004325289],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002228203,0.000291469,0.03078941,0.00000944363,0.00007324555,3.936111e-7,0.0002350293,0.03797023,0.002492456,0.8703095,0.01058923,0.04721729],"study_design_scores_gemma":[0.0001937397,0.00001533016,0.1995638,0.0000134204,0.00001318278,0.00001113679,0.00001053975,0.7456469,0.0001903619,0.05181773,0.002412132,0.0001117803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009667458,0.001349665,0.7612506,0.2204143,0.0002749988,0.0008586328,0.00001015259,0.0001988367,0.005975419],"genre_scores_gemma":[0.7423923,0.00009058791,0.2571992,0.0001496086,0.00002447446,0.00007146742,0.000006582831,0.000006989382,0.00005879883],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8184918,"threshold_uncertainty_score":0.9997373,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2113137767","doi":"10.1109/tpami.2004.60","title":"An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4600,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"University of Tsukuba","keywords":"Algorithm; Computer science; Maximum flow problem; Minimum cut; Benchmark (surveying); Maximum cut; Minification; Time complexity; Image segmentation; Segmentation; Running time; Cut; Energy minimization; Artificial intelligence; Graph; Mathematics; Theoretical computer science; Mathematical optimization","retraction":null,"screen_n_in":null,"score":{"opus":0.02598367102043963,"gpt":0.331384632381408,"spread":0.3054009613609683,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000718047,0.0001625279,0.0002946059,0.0004002765,0.0001203949,0.00004273589,0.0003440121,0.00005489244,0.00001451707],"category_scores_gemma":[0.000001261301,0.000156485,0.000129675,0.001012335,0.00005257268,0.0003052093,0.000004097155,0.00009289557,0.000001260154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004813838,"about_ca_system_score_gemma":0.00001330332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004388148,"about_ca_topic_score_gemma":0.001977228,"domain_scores_codex":[0.9986926,0.00004102781,0.0004471314,0.0004725949,0.0001774241,0.0001692253],"domain_scores_gemma":[0.9992396,0.00008761034,0.0001307026,0.0003995783,0.00005831368,0.00008424903],"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":[0.00001150688,0.000471405,0.00008104582,0.000003418921,0.00003115961,5.118e-7,0.0003592685,0.6051345,0.002380028,0.0001958017,0.000001112393,0.3913303],"study_design_scores_gemma":[0.0001197324,0.0002133024,0.00009091805,0.000009457716,0.00003765184,0.000001109123,0.00004729724,0.6002309,0.3987944,0.0003392834,0.00001585032,0.0001000981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008043497,0.0001164695,0.9913795,0.0001615057,0.00007466877,0.000154952,0.00002766388,0.00003704495,0.000004675991],"genre_scores_gemma":[0.9437817,0.00008576782,0.05590122,0.0001061255,0.00001173938,0.00007395626,0.00001965414,0.000009324476,0.00001046859],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9357383,"threshold_uncertainty_score":0.6381273,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1787224781","doi":"10.1371/journal.pone.0130140","title":"On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4586,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Technische Universität Berlin; Bundesministerium für Wirtschaft und Technologie; Bundesministerium für Bildung und Forschung; Banting and Best Diabetes Centre, University of Toronto; National Research Foundation of Korea; Deutsche Forschungsgemeinschaft; National Research Foundation","keywords":"MNIST database; Computer science; Artificial intelligence; Pixel; Pascal (unit); Machine learning; Pattern recognition (psychology); Classifier (UML); Contextual image classification; Artificial neural network; Data mining; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.1253811001846517,"gpt":0.3043329874426111,"spread":0.1789518872579594,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001782965,0.0001657282,0.0001895267,0.00009547122,0.0002414553,0.00006193775,0.0006619091,0.00007534662,0.000003996498],"category_scores_gemma":[0.0006517553,0.0001593511,0.00004659176,0.0005622804,0.00004338668,0.000539917,0.0001094145,0.0001732321,0.0002527171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001153731,"about_ca_system_score_gemma":0.00008628951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001516187,"about_ca_topic_score_gemma":0.000008030193,"domain_scores_codex":[0.9983234,0.00003490459,0.0003018071,0.0005272318,0.0005072383,0.000305408],"domain_scores_gemma":[0.9976201,0.0007837893,0.0001572349,0.000821734,0.0003840903,0.0002330631],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003529651,0.01217808,0.0002777913,0.00009105544,0.0002707384,0.00001037304,0.00167149,0.02198921,0.1991431,0.3222113,0.3557976,0.08600631],"study_design_scores_gemma":[0.001609378,0.0005325575,0.00009214485,0.0001813869,0.00005003086,0.000002815355,0.00002609668,0.8637451,0.04100037,0.05662578,0.03559074,0.0005435817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02037155,0.00005585631,0.9725996,0.004671699,0.00009602005,0.00115665,0.00004755574,0.0002463744,0.000754646],"genre_scores_gemma":[0.3860932,0.00009203103,0.6076689,0.001123545,0.0002430824,0.001573772,0.0001208462,0.00004584252,0.003038761],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8417559,"threshold_uncertainty_score":0.6498149,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2737258237","doi":"10.1109/cvpr.2017.544","title":"Scene Parsing through ADE20K Dataset","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3165,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Samsung; National Science Foundation","keywords":"Parsing; Computer science; Object (grammar); Segmentation; Artificial intelligence; Benchmark (surveying); Market segmentation; Cascade; Computer vision; Key (lock); Image segmentation; Pattern recognition (psychology); Information retrieval; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.07541479895096069,"gpt":0.3560834127799415,"spread":0.2806686138289808,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004719224,0.00006802432,0.00006647001,0.000008804498,0.0006137848,0.0002449209,0.001606555,0.00002010954,0.00001922815],"category_scores_gemma":[0.0000211778,0.00005924013,0.0000161947,0.00005592743,0.00006145675,0.001320521,0.0005585607,0.00006657337,0.0002387507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001113057,"about_ca_system_score_gemma":0.00001154428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002721291,"about_ca_topic_score_gemma":0.00001668098,"domain_scores_codex":[0.9993297,0.000008716119,0.0000915238,0.0002836009,0.0001023709,0.0001841149],"domain_scores_gemma":[0.9979234,0.0000338535,0.00007940637,0.001899757,0.00001670558,0.00004682179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002301842,0.00005346227,0.0004262541,0.000003991182,0.000007681687,0.00001367595,0.00007911865,0.0002427726,0.00135959,0.7082939,0.1443693,0.145148],"study_design_scores_gemma":[0.0004562996,0.00002795392,0.004985555,0.00001724074,0.000005164831,0.00003225947,0.000006965989,0.04974729,0.01257299,0.08471918,0.8470652,0.000363948],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005259024,0.00003515004,0.9805884,0.005943672,0.000147328,0.00009800596,0.00002578617,0.0001428433,0.01249286],"genre_scores_gemma":[0.3412997,0.00004389539,0.6558799,0.002028639,0.0001457249,0.00001867088,0.00006189282,0.000007893746,0.0005136877],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7026958,"threshold_uncertainty_score":0.4720798,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320002812","doi":"10.1109/jproc.2023.3238524","title":"Object Detection in 20 Years: A Survey","year":2023,"lang":"en","type":"article","venue":"Proceedings of the IEEE","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2868,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Object (grammar); Artificial intelligence; Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.02860654961029068,"gpt":0.267200256518802,"spread":0.2385937069085113,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003006307,0.00005072582,0.00006949318,0.00007915361,0.0000372054,0.00002346322,0.0006745094,0.00002549299,4.019032e-7],"category_scores_gemma":[0.00008072522,0.00004202495,0.00002729094,0.001918603,0.00002437733,0.0002202499,0.0001518723,0.0000963623,0.000025345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002437892,"about_ca_system_score_gemma":0.000009696472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003358515,"about_ca_topic_score_gemma":0.00007761928,"domain_scores_codex":[0.9994166,0.00000594237,0.0001208362,0.0001734601,0.0001403904,0.0001427971],"domain_scores_gemma":[0.9996538,0.00006905979,0.00007788633,0.0001217475,0.00005943408,0.0000181447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00004615534,0.0001304878,0.07335331,0.00007890945,0.00002914653,0.000001952106,0.002445762,0.003392775,0.7873461,0.006591725,0.01505903,0.1115247],"study_design_scores_gemma":[0.0002142381,0.0000334949,0.7136896,0.00003541231,0.000002514858,0.000006141149,0.00002350011,0.03504612,0.2306113,0.01929605,0.000888237,0.000153393],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969153,0.000008832938,0.001930324,0.0002859034,0.0001968682,0.0001852707,0.000001398632,0.0001419884,0.0003341188],"genre_scores_gemma":[0.9988086,0.00001084599,0.0008746472,0.00003800079,0.00003014004,0.00003204009,1.565184e-7,0.000005826008,0.0001997448],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6403363,"threshold_uncertainty_score":0.1713728,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2988916019","doi":"10.1007/s11263-019-01247-4","title":"Deep Learning for Generic Object Detection: A Survey","year":2019,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2776,"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":"Oulun Yliopisto; National Natural Science Foundation of China","keywords":"Computer science; Object detection; Artificial intelligence; Deep learning; Field (mathematics); Representation (politics); Object (grammar); Context (archaeology); Feature (linguistics); Feature learning; Machine learning; Learning object; Cognitive neuroscience of visual object recognition; Pattern recognition (psychology); Geography; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01823367031555728,"gpt":0.3036416907018827,"spread":0.2854080203863254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004354201,0.0001045532,0.0001598701,0.0001977089,0.00006408443,0.0001647249,0.001112222,0.00004007921,0.000009185543],"category_scores_gemma":[0.00003798741,0.00009284267,0.0001340712,0.0002298764,0.00001266192,0.0006500165,0.0002091607,0.0001928804,0.00003502739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008426865,"about_ca_system_score_gemma":0.0000326393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002470294,"about_ca_topic_score_gemma":0.000004661978,"domain_scores_codex":[0.9987321,0.00009280875,0.0003946256,0.0002074763,0.0004329332,0.000140014],"domain_scores_gemma":[0.9979895,0.0004715857,0.0004348883,0.0001790939,0.0008593625,0.00006555356],"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":[0.0001223561,0.00007528369,0.001673338,0.000004458307,0.00007454799,0.00001265526,0.0001054955,0.2240762,0.004460838,0.001294059,0.0003798312,0.7677209],"study_design_scores_gemma":[0.000762417,0.0006193373,0.02847524,0.00003484274,0.000003499825,0.0002986819,0.000002305006,0.949137,0.001425526,0.001839847,0.01726849,0.0001328462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05862093,0.00009246796,0.9381599,0.0003566932,0.002565067,0.0001285756,5.341892e-7,0.00003411101,0.00004169315],"genre_scores_gemma":[0.8670601,0.00003530955,0.1319532,0.000235637,0.0006325651,0.000003715869,0.000003519433,0.00001005576,0.00006596272],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8084391,"threshold_uncertainty_score":0.3786014,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1902934009","doi":"10.48550/arxiv.1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","year":2015,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1835,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research; Polytechnique Montréal","funders":"","keywords":"MNIST database; Computer science; Dropout (neural networks); Artificial neural network; Deep neural networks; Binary number; Invariant (physics); Computation; Range (aeronautics); Artificial intelligence; Permutation (music); Computer engineering; Simple (philosophy); Deep learning; Algorithm; Machine learning; Arithmetic; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01877200430149616,"gpt":0.2391499425125286,"spread":0.2203779382110324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0005305067,0.001007949,0.000869527,0.000771887,0.0008309062,0.0006567327,0.003192352,0.0006865101,0.000008354886],"category_scores_gemma":[0.00008526102,0.0009465104,0.0002708682,0.001688924,0.0002268296,0.001017501,0.002907159,0.002318467,0.00001227289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009348929,"about_ca_system_score_gemma":0.0005726715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004768254,"about_ca_topic_score_gemma":0.001127438,"domain_scores_codex":[0.9947062,0.0002842458,0.0008985478,0.00183169,0.0007381646,0.001541131],"domain_scores_gemma":[0.9943988,0.0002202373,0.0008441103,0.003295927,0.0004289713,0.0008119253],"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":[0.00007127074,0.0001872994,0.001136006,0.00006386609,0.00008295566,0.0003071472,0.0008695356,0.9576534,0.0003892313,0.02513707,0.0003276495,0.01377458],"study_design_scores_gemma":[0.0005279299,0.0002022483,0.003975621,0.000172048,0.00005673878,0.0005570336,0.00006874785,0.9789689,0.0004252766,0.01367945,0.00025475,0.001111217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08002909,0.002064321,0.9065148,0.005207263,0.0003361989,0.002332262,0.00002500362,0.003146594,0.0003444384],"genre_scores_gemma":[0.6785156,0.0001298153,0.3169068,0.0006330397,0.000453625,0.002880757,0.0001046684,0.0001462206,0.0002293917],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5984865,"threshold_uncertainty_score":0.9999833,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2507296351","doi":"10.1007/s11263-018-1140-0","title":"Semantic Understanding of Scenes Through the ADE20K Dataset","year":2018,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1667,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Samsung; National Science Foundation","keywords":"Computer science; Normalization (sociology); Parsing; Segmentation; Artificial intelligence; Variety (cybernetics); Object (grammar); Pixel; Context (archaeology); Pattern recognition (psychology); Computer vision; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.05449105503919781,"gpt":0.3589244139169077,"spread":0.3044333588777099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002319145,0.00008713682,0.0001282172,0.0000981168,0.00009660288,0.0001087268,0.001963418,0.00002498383,0.0000116632],"category_scores_gemma":[0.00001603799,0.00005751299,0.00007196005,0.0002213941,0.0001432902,0.0008448106,0.0004454056,0.0001298079,0.00001378005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006318501,"about_ca_system_score_gemma":0.00003829635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003824347,"about_ca_topic_score_gemma":0.000002533511,"domain_scores_codex":[0.9986808,0.00005689774,0.0004378464,0.0001410018,0.0005731184,0.0001103024],"domain_scores_gemma":[0.9984736,0.000257677,0.0005117462,0.0003154278,0.0004060161,0.00003557027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002364547,0.0004693929,0.0005345511,0.00001960697,0.0004257476,0.0001250145,0.002634394,0.01451747,0.006147951,0.6662045,0.1659968,0.1426882],"study_design_scores_gemma":[0.002314758,0.001523065,0.004013892,0.0007282593,0.00004366555,0.001872357,0.0001165688,0.4714196,0.01236776,0.335868,0.1693011,0.00043099],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005051653,0.00007345829,0.9871348,0.006067066,0.00148191,0.00005839785,0.00001195885,0.00001243341,0.0001083626],"genre_scores_gemma":[0.9090503,0.00005700469,0.08922163,0.0007234388,0.0009280971,5.379886e-7,0.000007123556,0.000005475929,0.000006423328],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9039986,"threshold_uncertainty_score":0.3648551,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963400571","doi":"10.1109/iros.2018.8594049","title":"Joint 3D Proposal Generation and Object Detection from View Aggregation","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1656,"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":"Computer science; Object detection; Minimum bounding box; Artificial intelligence; Benchmark (surveying); Point cloud; Memory footprint; Computer vision; Feature (linguistics); Orientation (vector space); Feature extraction; Lidar; Object (grammar); Code (set theory); Pattern recognition (psychology); Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02620329913515954,"gpt":0.2564876608302475,"spread":0.230284361695088,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007201787,0.00007596187,0.0000658935,0.00003483864,0.0002001055,0.00009318196,0.0001151446,0.00003434746,0.00001671516],"category_scores_gemma":[0.000014725,0.00006542272,0.00001304589,0.0002301601,0.00004338615,0.0004955815,0.00008178861,0.00005010557,0.00005872855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002798023,"about_ca_system_score_gemma":0.00001820661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003512263,"about_ca_topic_score_gemma":0.0003055911,"domain_scores_codex":[0.9992954,0.00003644377,0.0001377725,0.0003178308,0.0001072619,0.0001052924],"domain_scores_gemma":[0.9995122,0.00002083446,0.00006337387,0.0002835323,0.00007705128,0.00004302079],"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":[0.000001648164,0.00001253733,0.0000310901,0.000001625231,0.000003872501,3.358577e-7,0.000130709,0.00005873249,0.1466895,0.01125402,0.0002009746,0.8416149],"study_design_scores_gemma":[0.0001306023,0.00009525038,0.001421878,0.000007064893,0.00000430061,0.000008954067,0.000003142485,0.681164,0.3004211,0.01348745,0.003130514,0.0001257474],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06076114,0.00008058433,0.9374675,0.0006041484,0.0001869697,0.0002273353,5.695449e-7,0.0001967746,0.0004749552],"genre_scores_gemma":[0.7526262,0.00003602925,0.2465309,0.0002717871,0.0004112245,0.00003439501,0.000004348018,0.000004850551,0.00008028522],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8414892,"threshold_uncertainty_score":0.2667861,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125215748","doi":"10.1109/cvpr.2014.119","title":"The Role of Context for Object Detection and Semantic Segmentation in the Wild","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1475,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Pascal (unit); Computer science; Segmentation; Object detection; Artificial intelligence; Exploit; Context model; Context (archaeology); Pixel; Image segmentation; Object (grammar); Pattern recognition (psychology); Machine learning; Computer vision; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.009141096907340865,"gpt":0.2494392302303552,"spread":0.2402981333230143,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002008991,0.00003051741,0.00003396781,0.0000126063,0.0001087942,0.00002666861,0.0001720051,0.000009527987,1.406346e-7],"category_scores_gemma":[0.00002022941,0.00001668887,0.00001073677,0.000120781,0.00002391229,0.0000981886,0.00002270367,0.00002639008,7.395716e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000490776,"about_ca_system_score_gemma":0.000002651267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001732608,"about_ca_topic_score_gemma":0.0003206642,"domain_scores_codex":[0.9996758,0.00003619482,0.00008408904,0.00008802234,0.00005223079,0.00006368895],"domain_scores_gemma":[0.9992656,0.0005037026,0.00004237509,0.0001639128,0.00001760094,0.000006805551],"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":[0.000003732169,0.000007216989,0.000297851,0.00000207646,0.000001361111,8.135013e-9,0.0003431591,0.000200524,0.007931884,0.08914988,0.00001810637,0.9020442],"study_design_scores_gemma":[0.0002721574,0.0001038464,0.005734679,0.000004465182,0.000003328312,0.000004123287,0.0005303329,0.8645959,0.03509599,0.08822099,0.005377727,0.0000564857],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03980229,0.00008343862,0.9586414,0.0007866968,0.0000229681,0.000344855,1.398951e-7,0.00001525025,0.0003029669],"genre_scores_gemma":[0.9947075,0.00001373338,0.004967025,0.000186534,0.00001366705,0.00009013199,1.97875e-7,0.000001587999,0.00001963183],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9549052,"threshold_uncertainty_score":0.08367682,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2288122362","doi":"10.1109/cvpr.2016.314","title":"Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1318,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia; Microsoft Research","keywords":"Pooling; Computer science; Object detection; Exploit; Pascal (unit); Artificial intelligence; Intuition; Abstraction; Artificial neural network; Context (archaeology); Machine learning; Pattern recognition (psychology); Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.01508798965431453,"gpt":0.2423469466133579,"spread":0.2272589569590434,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001240016,0.0001640311,0.0001604992,0.00008058101,0.0001152519,0.00007200996,0.000312616,0.00004381383,0.000002925029],"category_scores_gemma":[0.00003684058,0.0001038199,0.00001952792,0.0004401377,0.0000586839,0.0005442859,0.0002313706,0.0001697407,0.000004680006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004597337,"about_ca_system_score_gemma":0.00001794946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003188427,"about_ca_topic_score_gemma":0.001148667,"domain_scores_codex":[0.9986943,0.00005166259,0.0002382388,0.0004929608,0.0001252177,0.0003975993],"domain_scores_gemma":[0.9989054,0.000452446,0.0001003933,0.0003837517,0.00004336155,0.0001147113],"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":[0.00001780752,0.00001783876,0.008667635,0.000003387251,0.000004943991,0.00001765175,0.0002749368,0.0063994,0.0005431308,0.006035805,0.00002662387,0.9779909],"study_design_scores_gemma":[0.001668371,0.0002699254,0.02188961,0.0002308977,0.00000664259,0.0001833075,0.0001513058,0.9678478,0.002772221,0.003934751,0.0004061207,0.0006390854],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2387761,0.000269334,0.7589682,0.0009564169,0.0001020177,0.0002700613,2.481967e-7,0.0001831952,0.0004743566],"genre_scores_gemma":[0.98369,0.00004859596,0.01551017,0.0005815253,0.00007294332,0.00004165649,2.34212e-7,0.00001344804,0.00004145265],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9773517,"threshold_uncertainty_score":0.4233654,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2910094941","doi":"10.1016/j.media.2022.102680","title":"The Liver Tumor Segmentation Benchmark (LiTS)","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1164,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"National Cancer Institute; National Institutes of Health; Fonds de Recherche du Québec - Santé; Fondation de l'Association des radiologistes du Québec; International Graduate School of Science and Engineering; Universität Zürich; Deutsche Forschungsgemeinschaft","keywords":"Benchmark (surveying); Segmentation; Computer science; Artificial intelligence; Medical physics; Medicine; Pattern recognition (psychology); Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.007724142912540659,"gpt":0.2656009642944292,"spread":0.2578768213818886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005617029,0.00007964259,0.0001211712,0.00009148031,0.0009141251,0.00009444047,0.001253837,0.00001157418,0.001010731],"category_scores_gemma":[0.0001202665,0.00005859865,0.0001434654,0.002639343,0.00009728655,0.0002100285,0.0006511899,0.0002380598,0.00006076638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006536023,"about_ca_system_score_gemma":0.00004546697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003417503,"about_ca_topic_score_gemma":0.00004581247,"domain_scores_codex":[0.9981198,0.0001929051,0.0002288449,0.0003216941,0.0009128981,0.0002237994],"domain_scores_gemma":[0.9987161,0.0004054899,0.0001013113,0.0005944103,0.0000484159,0.000134255],"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":[0.00001739301,0.0003986204,0.001981643,0.000008671672,0.001095283,0.0005054162,0.001198138,0.009216052,0.001413884,0.04580027,0.06759614,0.8707685],"study_design_scores_gemma":[0.0001622089,0.00003002764,0.002173926,0.000001013879,0.000196667,0.00002095455,0.000145062,0.9451938,0.0003137721,0.00284923,0.04875661,0.0001567828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003332629,0.0004221789,0.9870038,0.008218525,0.00008523368,0.0001253658,0.000003524128,0.00009734214,0.0007114176],"genre_scores_gemma":[0.9018634,0.000432051,0.08322024,0.01009703,0.0002910784,0.0009539301,0.0001125765,0.00002227448,0.003007416],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9359777,"threshold_uncertainty_score":0.9999025,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2468368736","doi":"10.1109/cvpr.2016.236","title":"Monocular 3D Object Detection for Autonomous Driving","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1080,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Object detection; Computer vision; Monocular; Benchmark (surveying); Pipeline (software); Object (grammar); Segmentation; Viola–Jones object detection framework; Set (abstract data type); Image segmentation; Object-class detection; Domain (mathematical analysis); Encoding (memory); Pattern recognition (psychology); Face detection; Facial recognition system; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01423776355678217,"gpt":0.2534866007799436,"spread":0.2392488372231615,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006863492,0.0000706876,0.00006335379,0.00003612456,0.0001281409,0.00003194702,0.0003275385,0.00002775406,0.000006517342],"category_scores_gemma":[0.00002803418,0.00004799068,0.00004212475,0.0001561153,0.00001512339,0.0003680196,0.00008745532,0.00002453267,0.00005791043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005280128,"about_ca_system_score_gemma":0.00001396366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003075734,"about_ca_topic_score_gemma":0.00002207835,"domain_scores_codex":[0.9993441,0.00001047248,0.0001105166,0.0002838184,0.00006251001,0.000188619],"domain_scores_gemma":[0.9992993,0.0001703024,0.00004328476,0.0004001401,0.00003930649,0.00004769293],"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":[9.12164e-7,0.000007768374,0.00003470859,0.000001020958,0.00000322126,2.662582e-7,0.00001274638,0.0001436002,0.04753433,0.0177621,0.0001109889,0.9343883],"study_design_scores_gemma":[0.0006035555,0.000150044,0.001243229,0.00001633918,0.000007235789,0.00002261199,0.000003845269,0.4902638,0.3192923,0.05518511,0.13281,0.0004018562],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002321447,0.00001417115,0.9950271,0.0009377166,0.000127471,0.0002635156,3.895413e-7,0.0004065308,0.0009016717],"genre_scores_gemma":[0.648886,0.000006054413,0.3492022,0.0001317777,0.00007335981,0.0001662391,1.683816e-7,0.000007419223,0.001526761],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9339865,"threshold_uncertainty_score":0.1957003,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3197957534","doi":"10.1609/aaai.v36i3.20144","title":"UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-Wise Perspective with Transformer","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1017,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Segmentation; Encoder; Computer science; Transformer; Channel (broadcasting); Artificial intelligence; Ambiguity; Pattern recognition (psychology); Computer network; Programming language; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.05825692916390028,"gpt":0.2837522452940704,"spread":0.2254953161301701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003674394,0.0002104062,0.0002136222,0.0001155633,0.0007176123,0.0001237212,0.002227196,0.0000417626,0.00007375517],"category_scores_gemma":[0.00006566154,0.000140045,0.00008549949,0.001606777,0.0003125542,0.0003582549,0.0001977481,0.0007665737,0.00001030062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001452058,"about_ca_system_score_gemma":0.0001075633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003754003,"about_ca_topic_score_gemma":0.0004136447,"domain_scores_codex":[0.9981021,0.0000428326,0.000387737,0.0005915884,0.0005292505,0.0003464984],"domain_scores_gemma":[0.9987762,0.0002456782,0.0002529465,0.0003662751,0.0003051729,0.00005373667],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009657871,0.0001325203,0.00007500543,0.000003714286,0.00001547042,8.384702e-7,0.01639427,0.004501271,0.005810731,0.9685891,0.00003396533,0.004346519],"study_design_scores_gemma":[0.00006547766,0.000267892,0.0003184964,0.00007187133,0.00001656155,0.0000134819,0.007239548,0.06994282,0.07082673,0.8507678,0.0002112608,0.0002580562],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4865827,0.0002281904,0.3726185,0.1180468,0.0008134125,0.003913747,0.00008513049,0.0004037672,0.01730774],"genre_scores_gemma":[0.9977705,0.00003225706,0.001204844,0.0005056754,0.00004776337,0.0003546349,8.724839e-7,0.00001525103,0.00006815416],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5111879,"threshold_uncertainty_score":0.5710871,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2517954747","doi":"10.1007/978-3-319-46976-8_19","title":"The Importance of Skip Connections in Biomedical Image Segmentation","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":991,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal; Polytechnique Montréal","funders":"Mitacs","keywords":"Computer science; Upsampling; Path (computing); Residual; Segmentation; Artificial intelligence; Image (mathematics); Image segmentation; Pattern recognition (psychology); Computer vision; Algorithm; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.01373374754625272,"gpt":0.2756294804930322,"spread":0.2618957329467795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006161827,0.0002701791,0.0002876413,0.0003947631,0.0002530584,0.0001205201,0.002339927,0.0001463871,0.000009169531],"category_scores_gemma":[0.0001137878,0.0001845283,0.00007372272,0.0008829916,0.00136944,0.0004742933,0.000697298,0.0004322311,0.00001830303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002583746,"about_ca_system_score_gemma":0.0002914248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003937726,"about_ca_topic_score_gemma":0.0001587074,"domain_scores_codex":[0.9973464,0.0000329022,0.0006209628,0.0009021488,0.0006472925,0.0004502884],"domain_scores_gemma":[0.99688,0.001305139,0.0003972455,0.001155609,0.0001649091,0.00009709116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005659437,0.00003595756,0.0002112521,0.00001444822,0.000006533518,0.00002304436,0.0002455937,0.002515041,0.002778285,0.1862065,0.00005185246,0.8079058],"study_design_scores_gemma":[0.0004870322,0.0001505123,0.000637396,0.0003422197,0.000005385862,0.00006340582,5.356878e-7,0.178868,0.004383448,0.8112588,0.003250815,0.0005524316],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001344608,0.0002589569,0.9931024,0.004256748,0.0006706205,0.0004419505,0.00000681205,0.00006423876,0.0010638],"genre_scores_gemma":[0.1437498,0.0004306843,0.8532297,0.001285816,0.0005857457,0.0001125043,0.000008304872,0.00005089426,0.0005465851],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8073534,"threshold_uncertainty_score":0.7524846,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2560311620","doi":"10.1007/978-3-319-50835-1_22","title":"Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":903,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Softmax function; Artificial intelligence; Computer science; Segmentation; Intersection (aeronautics); Pattern recognition (psychology); Object (grammar); Image segmentation; Artificial neural network; Deep learning; Object detection; Deep neural networks; Pixel; Computer vision; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.01384282197705767,"gpt":0.2666441925100097,"spread":0.252801370532952,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005233369,0.0004475248,0.0003805025,0.0006743174,0.000256492,0.0003320421,0.001930644,0.0002303006,0.000008593292],"category_scores_gemma":[0.00004376619,0.0004042519,0.000123094,0.0006549648,0.0003513957,0.001287548,0.0007610056,0.00055152,0.000006588805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00061376,"about_ca_system_score_gemma":0.00008195706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000066158,"about_ca_topic_score_gemma":0.0001610943,"domain_scores_codex":[0.9968468,0.00004088312,0.0005625768,0.001454455,0.0004204433,0.0006748707],"domain_scores_gemma":[0.9976555,0.0007865393,0.0003551207,0.0009142912,0.00016728,0.0001212377],"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":[0.000006976522,0.00001101522,0.00001582652,0.000009617093,0.000002932245,0.000008492966,0.0001982732,0.3541289,0.0003731347,0.006781053,0.000006336618,0.6384575],"study_design_scores_gemma":[0.0003962502,0.0001005018,0.0000428807,0.0001555508,0.000003795829,0.00002510334,2.850041e-7,0.929703,0.0004493525,0.06858109,0.0001195485,0.0004226427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005842088,0.0001846381,0.9957886,0.0007628924,0.001668164,0.00096921,0.000003861474,0.000156949,0.0004072814],"genre_scores_gemma":[0.1293245,0.00004987841,0.8686163,0.0009936937,0.0007197898,0.00012577,0.00001260047,0.00005148605,0.0001059034],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6380348,"threshold_uncertainty_score":0.9998409,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3117804044","doi":"10.1007/978-3-030-01270-0_39","title":"Deep Continuous Fusion for Multi-sensor 3D Object Detection","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":841,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Fuse (electrical); Benchmark (surveying); Artificial intelligence; Computer vision; Lidar; Object detection; Detector; Exploit; Object (grammar); ENCODE; Feature (linguistics); Image sensor; State (computer science); Sensor fusion; Pattern recognition (psychology); Algorithm; Remote sensing","retraction":null,"screen_n_in":null,"score":{"opus":0.02506021675575439,"gpt":0.275280890487304,"spread":0.2502206737315497,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000489398,0.0005519692,0.0005092032,0.0005590127,0.0005817561,0.0003424214,0.002575487,0.0003613361,0.00001489262],"category_scores_gemma":[0.0001395679,0.000518576,0.0001662815,0.0006664967,0.0006596483,0.0005150302,0.0009784854,0.0005561203,0.00008064784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003090159,"about_ca_system_score_gemma":0.0001686094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000824189,"about_ca_topic_score_gemma":0.0002718933,"domain_scores_codex":[0.9961199,0.0000290364,0.0005451449,0.001937479,0.0006024659,0.0007660323],"domain_scores_gemma":[0.9967343,0.0006223251,0.0004189761,0.001555195,0.0004927585,0.0001764107],"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":[0.00001310856,0.00003095936,0.000007373599,0.00002238218,0.000007220385,0.00001086713,0.0003440738,0.02022894,0.001913891,0.001705406,0.00001523428,0.9757006],"study_design_scores_gemma":[0.000393466,0.0002917622,0.000041909,0.0001128218,0.000009623157,0.00006686332,1.540437e-7,0.9448817,0.006223205,0.04290477,0.004465949,0.0006077243],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007706627,0.0002321029,0.9954938,0.0002048411,0.001978857,0.00131612,0.000005363841,0.0003510759,0.0003407804],"genre_scores_gemma":[0.01690461,0.00004842986,0.980378,0.000945624,0.001004092,0.00008842195,0.000006611996,0.00005508374,0.0005691009],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9750928,"threshold_uncertainty_score":0.9997266,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962767316","doi":"10.1109/isbi.2019.8759329","title":"A Novel Focal Tversky Loss Function With Improved Attention U-Net for Lesion Segmentation","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":835,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Dice; Segmentation; Computer science; Artificial intelligence; Pyramid (geometry); Image segmentation; Function (biology); Image (mathematics); Pattern recognition (psychology); Computer vision; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01841908127527159,"gpt":0.2587298785665166,"spread":0.240310797291245,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000749193,0.0001065902,0.00008583834,0.00004731659,0.000103806,0.00005806108,0.0001984581,0.00004118036,0.00000936615],"category_scores_gemma":[0.000002764357,0.00008586916,0.00003869694,0.0002663339,0.0000159442,0.0007212638,0.00005737778,0.00005513366,0.00005835921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000565119,"about_ca_system_score_gemma":0.00002073996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008866871,"about_ca_topic_score_gemma":0.00002126608,"domain_scores_codex":[0.9991269,0.000008628038,0.0001423425,0.000395046,0.0001419829,0.0001851039],"domain_scores_gemma":[0.9993685,0.00006159022,0.0001003257,0.0003276174,0.00009549275,0.00004639703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002154439,0.0001601788,0.001081303,0.00003289464,0.00002543903,2.585026e-7,0.00005451548,0.004016322,0.8298764,0.08529149,0.0005752142,0.0786705],"study_design_scores_gemma":[0.003913596,0.001305555,0.01181149,0.00002722057,0.00003006118,0.00002538491,0.00008369571,0.9506594,0.02342256,0.004399619,0.003881505,0.0004399322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04954156,0.000003654636,0.9483062,0.0005353527,0.000177554,0.0009891292,0.000002265175,0.0001840249,0.0002602548],"genre_scores_gemma":[0.6584812,0.000003260121,0.3393269,0.0003666581,0.00006148253,0.000204111,0.00004398323,0.00001318951,0.001499098],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9466431,"threshold_uncertainty_score":0.3501643,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951517617","doi":"10.1109/cvpr.2019.00752","title":"Multi-Task Multi-Sensor Fusion for 3D Object Detection","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":761,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmark (surveying); Object detection; Computer science; Artificial intelligence; Task (project management); Exploit; Object (grammar); Computer vision; Sensor fusion; Pattern recognition (psychology); Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02649599619983401,"gpt":0.2848787664625302,"spread":0.2583827702626962,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008656884,0.0001211917,0.0001134009,0.00006073263,0.0001483467,0.00004601053,0.0003929471,0.0000588419,0.00001427839],"category_scores_gemma":[0.00002530678,0.0001052558,0.00006587497,0.0002991009,0.00001445454,0.0003256459,0.0001416242,0.00008570269,0.0004007281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004174322,"about_ca_system_score_gemma":0.00001328277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001277295,"about_ca_topic_score_gemma":0.00005930419,"domain_scores_codex":[0.9989746,0.00002074375,0.0001698331,0.0004681574,0.0001121087,0.0002545933],"domain_scores_gemma":[0.9990366,0.0001531164,0.00007537579,0.0005865291,0.00008396235,0.00006442871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002013314,0.0001707217,0.0004138009,0.00002106903,0.00001077508,8.28661e-7,0.0001686492,0.004870171,0.6659572,0.002135786,0.0002217549,0.3260092],"study_design_scores_gemma":[0.0007248778,0.0000769383,0.002003138,0.000004631537,0.000002802343,0.000006231575,0.00001157041,0.9516295,0.03024618,0.000172354,0.01495283,0.000168977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01424747,0.00002424332,0.9835942,0.0001988768,0.0003660706,0.000966071,0.000002279991,0.0003982442,0.0002024937],"genre_scores_gemma":[0.3147095,0.000007847878,0.6820177,0.0002613586,0.00004627584,0.0001145761,0.000002431014,0.0000112842,0.002828999],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9467593,"threshold_uncertainty_score":0.5150682,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2991471181","doi":"10.1109/iccv.2019.00533","title":"Gated-SCNN: Gated Shape CNNs for Semantic Segmentation","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":737,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto; University of Waterloo","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Benchmark (surveying); Noise (video); Computer vision; Representation (politics); Focus (optics); Pattern recognition (psychology); Boundary (topology); Architecture; Image segmentation; Image (mathematics); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0204940933020382,"gpt":0.2824852809530363,"spread":0.2619911876509981,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006836867,0.0001017868,0.0001012246,0.00004755846,0.00008700415,0.00006266852,0.0004331172,0.00003504639,0.00009556585],"category_scores_gemma":[0.000006985197,0.00009176454,0.00004311914,0.0003810472,0.00001334417,0.0004109701,0.00009358166,0.00005323122,0.000535928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003019785,"about_ca_system_score_gemma":0.00001874233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003618987,"about_ca_topic_score_gemma":0.000004904115,"domain_scores_codex":[0.9990935,0.00001420126,0.0001731383,0.0003601057,0.0001260235,0.0002330451],"domain_scores_gemma":[0.9992352,0.0001253617,0.00007144559,0.0004335286,0.0000763189,0.00005811804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003403328,0.0002345175,0.0023843,0.0001041675,0.00006459486,0.000003473926,0.0005592314,0.01719052,0.1965085,0.5442382,0.02135104,0.2173275],"study_design_scores_gemma":[0.0005213788,0.00008745215,0.0006463597,0.00001009702,0.000005927378,0.000006742953,0.00002330164,0.9488212,0.03028839,0.00752596,0.01185414,0.0002090502],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04566313,0.00001689283,0.9494368,0.00146454,0.0001875928,0.0008910551,0.000002103539,0.0003937503,0.001944174],"genre_scores_gemma":[0.7864669,0.00001016743,0.2090379,0.001060709,0.00004752585,0.00006734557,0.00002413901,0.00001448434,0.00327078],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9316307,"threshold_uncertainty_score":0.6888449,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962971773","doi":"10.1109/cvpr.2017.668","title":"Deep Pyramidal Residual Networks","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":687,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Residual; Convolutional neural network; Upsampling; Computer science; Benchmark (surveying); Artificial intelligence; Feature (linguistics); Deep learning; Dimension (graph theory); Pattern recognition (psychology); Generalization; Residual neural network; Pooling; Artificial neural network; Network architecture; Image (mathematics); Algorithm; Mathematics; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.03010212868599168,"gpt":0.2971226287962158,"spread":0.2670205001102242,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001571601,0.0003098227,0.0002977985,0.00006430243,0.0003907749,0.0006033842,0.00468662,0.0003211721,0.00002207001],"category_scores_gemma":[0.00003468544,0.000292595,0.0001167283,0.00009501901,0.0001258878,0.000289776,0.00609278,0.000921813,0.0001205994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005869801,"about_ca_system_score_gemma":0.00008673555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002892556,"about_ca_topic_score_gemma":0.00007005796,"domain_scores_codex":[0.9979111,0.00004309016,0.0003005816,0.001011631,0.0002810474,0.00045254],"domain_scores_gemma":[0.995428,0.0001164924,0.0003391693,0.00385378,0.0001034406,0.0001591023],"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":[0.000003698168,0.00004482769,0.0001316006,0.00001583199,0.00003505131,0.00002844688,0.00006573759,0.5490425,0.000009586151,0.2896966,0.01481157,0.1461146],"study_design_scores_gemma":[0.00009082182,0.00001041495,0.001196664,0.00002426427,0.000008040281,0.00001013641,0.000001360162,0.8765046,0.00005967604,0.1143558,0.007351295,0.000386888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001428336,0.0004606141,0.9740669,0.003006687,0.001072795,0.0004024385,0.000001457768,0.0007155617,0.02013075],"genre_scores_gemma":[0.4534211,0.0004890475,0.5363629,0.001175964,0.002126426,0.0003677949,0.0000537923,0.00006005829,0.005942896],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4532783,"threshold_uncertainty_score":0.9999526,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2516141709","doi":"10.1145/3007787.3001138","title":"Cnvlutin","year":2016,"lang":"en","type":"article","venue":"ACM SIGARCH Computer Architecture News","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":639,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of Toronto","funders":"","keywords":"Computer science; Multiplication (music); Operand; Computation; Overhead (engineering); Parallel computing; Efficient energy use; Fraction (chemistry); State (computer science); Algorithm; Arithmetic; Computer hardware; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01560700340416213,"gpt":0.2567286129807016,"spread":0.2411216095765395,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001439035,0.0002895793,0.0002453185,0.0001673857,0.0001968039,0.00009535169,0.003748959,0.00007473055,0.00002611285],"category_scores_gemma":[0.00009804605,0.0001855301,0.0001316563,0.0006037579,0.0001273437,0.0003040867,0.00212576,0.0002659776,0.0003435062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005498826,"about_ca_system_score_gemma":0.00005789545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007039327,"about_ca_topic_score_gemma":0.0000224666,"domain_scores_codex":[0.9975824,0.0001396307,0.000328049,0.000881936,0.0003961992,0.0006717261],"domain_scores_gemma":[0.9957933,0.001128543,0.000110086,0.002625724,0.00007447973,0.0002678819],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006067488,0.00003096638,0.000283936,0.000003512244,0.0000126328,0.00001403719,0.0001778011,0.0005448352,0.005428725,0.01891732,0.007051363,0.9675288],"study_design_scores_gemma":[0.001447851,0.0003629068,0.006358832,0.000100553,0.000009266447,0.0002674868,0.000002038807,0.007641048,0.007823505,0.4057811,0.5692179,0.0009875116],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004555518,0.00006105741,0.9603595,0.03287324,0.0003742674,0.0003487736,0.000003610277,0.0006966607,0.00072733],"genre_scores_gemma":[0.2080746,0.00003141189,0.786678,0.00379519,0.0009136295,0.00008163513,0.000002319141,0.0000326703,0.0003905721],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9665413,"threshold_uncertainty_score":0.7565699,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3136424010","doi":"10.1016/j.media.2021.102035","title":"Loss odyssey in medical image segmentation","year":2021,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":618,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Segmentation; Computer science; Dice; Artificial intelligence; Function (biology); Hausdorff distance; Loss function; Boundary (topology); Benchmark (surveying); Image segmentation; Mathematics; Geography; Statistics; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.02602045313479882,"gpt":0.3855040646034736,"spread":0.3594836114686747,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001236884,0.0004948057,0.002434032,0.000806583,0.0001117747,0.0002114846,0.002791936,0.000531085,0.002177654],"category_scores_gemma":[0.001212124,0.0004143536,0.00112061,0.009672324,0.0002824693,0.0005088295,0.001062869,0.001270043,0.0003690562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002315676,"about_ca_system_score_gemma":0.0008025012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000446269,"about_ca_topic_score_gemma":0.0001825909,"domain_scores_codex":[0.9934042,0.0007470667,0.001468868,0.001363606,0.002411006,0.0006052745],"domain_scores_gemma":[0.9961274,0.00103272,0.0004495098,0.001519711,0.0001550136,0.000715608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[2.674819e-7,0.0001280042,0.000007652737,0.0004714188,0.0004279803,0.001760237,0.00002805139,0.000004435325,4.93812e-7,0.0005421234,0.001356381,0.9952729],"study_design_scores_gemma":[0.0004190932,0.00002077861,0.0000170423,0.003700453,0.00326897,0.0002476946,0.00001861339,0.04441783,0.000008077558,0.0004435167,0.9464445,0.0009934835],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[7.202627e-7,0.5075225,0.4907232,0.001135619,0.00007393076,0.0002013767,0.00000675782,0.00008444151,0.000251488],"genre_scores_gemma":[0.000004535128,0.9583774,0.03961429,0.0006668722,0.0002562257,0.0002971145,0.0005281306,0.00003271284,0.0002226966],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9942794,"threshold_uncertainty_score":0.9998308,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963730812","doi":"10.1109/tmi.2018.2878669","title":"HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation","year":2019,"lang":"","type":"article","venue":"Espace ÉTS (ETS)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":582,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Segmentation; Abstraction; Artificial intelligence; Convolutional neural network; Representation (politics); Modal; Modality (human–computer interaction); Pattern recognition (psychology); Modalities; Deep learning; Path (computing); Pyramid (geometry); Layer (electronics); Image segmentation; Feature learning; Ranking (information retrieval); Metric (unit); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02677478251896863,"gpt":0.2958204707536173,"spread":0.2690456882346486,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004159097,0.0007703882,0.0007348749,0.0002585755,0.0006564821,0.0005341417,0.001432772,0.000311751,0.0002413674],"category_scores_gemma":[0.0002335968,0.00084576,0.000334155,0.001278912,0.0002467096,0.001309654,0.0005078131,0.0005436986,0.003160483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002993223,"about_ca_system_score_gemma":0.0002665934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002680244,"about_ca_topic_score_gemma":0.00007706276,"domain_scores_codex":[0.9949075,0.0002527336,0.0008340133,0.001982397,0.0006741281,0.001349245],"domain_scores_gemma":[0.9954085,0.0009632618,0.0006695894,0.001862193,0.000649686,0.0004467512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009277526,0.001664218,0.002366286,0.0004846537,0.0003427393,0.00005593039,0.01036564,0.01423313,0.8196916,0.02453255,0.01352077,0.1118148],"study_design_scores_gemma":[0.006214077,0.0007224444,0.004907132,0.0001493435,0.0001381774,0.00009871914,0.0005908728,0.9269949,0.03162633,0.000866377,0.02618467,0.001507008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2482498,0.000538513,0.7380676,0.005398712,0.001742446,0.004930509,0.00009952833,0.0004426553,0.0005302387],"genre_scores_gemma":[0.6462668,0.0001314286,0.33981,0.00102412,0.0004479667,0.0005520065,0.00007014904,0.0001435573,0.01155397],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9127617,"threshold_uncertainty_score":0.9993993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3080980548","doi":"10.1109/tnnls.2020.3015992","title":"Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review","year":2020,"lang":"en","type":"review","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":574,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Point cloud; Lidar; Computer science; Deep learning; Artificial intelligence; Segmentation; Object detection; Discriminative model; Field (mathematics); Milestone; Feature (linguistics); Key (lock); Point (geometry); Task (project management); Machine learning; Data science; Remote sensing; Systems engineering; Engineering; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.02805834395490626,"gpt":0.2917329016432967,"spread":0.2636745576883904,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0006504984,0.0007741958,0.002247405,0.0002370985,0.0006951257,0.0003070127,0.0008497222,0.0003669701,0.000004187068],"category_scores_gemma":[0.00004458931,0.0007026326,0.0005972623,0.001392039,0.0000610949,0.0003154076,0.00002032647,0.003225137,0.00001721358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001924037,"about_ca_system_score_gemma":0.00008141878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001467825,"about_ca_topic_score_gemma":0.00001190205,"domain_scores_codex":[0.9952351,0.001069832,0.001317178,0.001367435,0.0002704553,0.0007399857],"domain_scores_gemma":[0.9966058,0.001641429,0.0007870262,0.0005932242,0.00007381345,0.0002986705],"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":[0.000002471731,0.00001889743,4.970006e-7,0.003915195,0.00003229896,0.00001268787,0.00003471209,0.4041271,8.614303e-8,0.00009741625,0.00003561265,0.591723],"study_design_scores_gemma":[0.0001304764,0.000177263,4.409607e-7,0.01087346,0.0001280088,0.0001344988,0.000007550703,0.5238148,4.79811e-8,0.000004146847,0.4643471,0.0003821852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[3.8898e-7,0.502178,0.4952889,0.0001545854,0.000513271,0.001572941,0.000001145356,0.0002745242,0.00001621163],"genre_scores_gemma":[0.003659781,0.9923412,0.001077206,0.0001712848,0.0003700637,0.001895733,0.0000179859,0.0001259535,0.0003408586],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5913408,"threshold_uncertainty_score":0.9995425,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3130423852","doi":"10.1016/j.array.2021.100057","title":"Deep learning for object detection and scene perception in self-driving cars: Survey, challenges, and open issues","year":2021,"lang":"en","type":"article","venue":"Array","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":559,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Deep learning; Self driving; Artificial intelligence; Computer science; Object detection; Perception; Implementation; Open research; Scalability; Machine learning; Human–computer interaction; Engineering; Transport engineering; Psychology; Pattern recognition (psychology); Software engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03883518648875101,"gpt":0.3038080404009055,"spread":0.2649728539121545,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000319565,0.00007497244,0.0001133197,0.00002978057,0.0001495963,0.0001157308,0.0001671452,0.00003720144,0.000001346006],"category_scores_gemma":[0.00007927116,0.00008125526,0.00001037436,0.0001436443,0.00001341863,0.0004587184,0.000182609,0.00009625794,0.00000162947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003209515,"about_ca_system_score_gemma":0.00001151863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008005206,"about_ca_topic_score_gemma":0.004316716,"domain_scores_codex":[0.9991782,0.0001357016,0.0001067238,0.0003759715,0.00005718984,0.0001462291],"domain_scores_gemma":[0.9994867,0.0002007612,0.00004258522,0.0001783428,0.00005285846,0.00003868879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000005160778,0.00003528634,0.008049421,0.00002361048,0.000008869724,0.000002251976,0.004457066,0.000685566,0.03368117,0.0006232175,0.00000511613,0.9524233],"study_design_scores_gemma":[0.0005276013,0.0001132263,0.8364844,0.00004883575,0.000005843621,0.0000396432,0.0004463403,0.1503356,0.003931342,0.00312325,0.004695422,0.0002484338],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3420729,0.00659468,0.6490981,0.001117325,0.0001094974,0.0005765489,4.552523e-7,0.0001592289,0.0002712323],"genre_scores_gemma":[0.9262165,0.004379383,0.06920981,0.0000339031,0.00003851558,0.00006907986,0.000003544419,0.000008372955,0.00004086557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9521748,"threshold_uncertainty_score":0.3313493,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4393308750","doi":"10.1007/s11554-024-01436-6","title":"Slim-neck by GSConv: a lightweight-design for real-time detector architectures","year":2024,"lang":"en","type":"article","venue":"Journal of Real-Time Image Processing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":546,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Computer science; Detector; Code (set theory); Enhanced Data Rates for GSM Evolution; State (computer science); Convolutional code; Computer engineering; Real-time computing; Computer hardware; Artificial intelligence; Embedded system; Algorithm; Telecommunications; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01309747618737339,"gpt":0.2808434033432951,"spread":0.2677459271559217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006210245,0.0003561698,0.0004999642,0.000337141,0.0003215479,0.0009009744,0.001202221,0.0001099558,0.00003070253],"category_scores_gemma":[0.0001306807,0.0002821714,0.0002573999,0.0008600556,0.0001049975,0.001280309,0.0001444418,0.0004182281,0.00007434732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001422855,"about_ca_system_score_gemma":0.0003999269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002101345,"about_ca_topic_score_gemma":1.712119e-7,"domain_scores_codex":[0.9974264,0.0001020073,0.0008231921,0.0005559509,0.0005029178,0.0005895562],"domain_scores_gemma":[0.9975338,0.0007736469,0.0006047637,0.0004139316,0.000393295,0.0002805504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007280739,0.00006045055,0.000001493051,0.0001826913,0.00005071174,0.00007489092,0.0004064761,0.0005264783,0.8407878,0.0000867233,0.03522382,0.1225257],"study_design_scores_gemma":[0.0009851521,0.0008300459,0.00003208964,0.001262262,0.0001621867,0.001366436,0.0000156291,0.582661,0.3617574,0.03375418,0.01629387,0.0008798008],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006152376,0.002254488,0.9866465,0.00298416,0.0001709403,0.0005009837,0.00001252198,0.0004037839,0.0008742764],"genre_scores_gemma":[0.02796873,0.0003515371,0.9686844,0.0001608773,0.0008291848,0.00006567161,0.000004181645,0.0001044561,0.001830939],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5821345,"threshold_uncertainty_score":0.999963,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394828356","doi":"10.1109/access.2024.3389497","title":"GPT (Generative Pre-Trained Transformer)— A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions","year":2024,"lang":"en","type":"review","venue":"IEEE Access","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":541,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Transformer; Architecture; Natural language understanding; Emerging technologies; Natural language; Generative grammar; Artificial intelligence; Risk analysis (engineering); Engineering; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.06809467507185797,"gpt":0.3767735784109343,"spread":0.3086789033390764,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001413839,0.0007201479,0.001356137,0.0004256397,0.0004371887,0.0002708971,0.00204621,0.0003424258,0.000003250241],"category_scores_gemma":[0.000009008593,0.0005661117,0.0003501507,0.001927746,0.0001107694,0.000588568,0.0002878991,0.00104291,0.00003699493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001371847,"about_ca_system_score_gemma":0.0001455179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002550233,"about_ca_topic_score_gemma":0.000007005651,"domain_scores_codex":[0.9967566,0.0001443327,0.0007723565,0.00152999,0.0003354818,0.0004612684],"domain_scores_gemma":[0.9978827,0.0001874034,0.0003979548,0.001278225,0.000147816,0.0001059573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[8.120308e-7,0.00003433726,2.841906e-9,0.01616785,0.0001079455,0.000008837453,0.00005401745,0.00000788099,0.000002388714,0.008031562,0.0005548553,0.9750295],"study_design_scores_gemma":[0.00006521576,0.00003293674,2.341573e-7,0.01222446,0.0005089333,0.0001135546,0.00001755768,0.0001556268,0.000009990015,0.002573005,0.9837721,0.0005263882],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[7.752356e-8,0.9229065,0.06716212,0.00419575,0.0005897608,0.003682071,0.0000550074,0.001212876,0.0001958444],"genre_scores_gemma":[0.000002431873,0.9893314,0.003394298,0.000251355,0.0008213322,0.005992934,0.00006680693,0.00007020622,0.00006929565],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9832172,"threshold_uncertainty_score":0.999679,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2796265726","doi":"10.1109/cvpr.2018.00257","title":"Practical Block-Wise Neural Network Architecture Generation","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":539,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Computer science; Block (permutation group theory); Pipeline (software); Artificial intelligence; Network architecture; Artificial neural network; Machine learning; Convolutional neural network; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.04924483087433017,"gpt":0.3224370522342925,"spread":0.2731922213599623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020329,0.0003801591,0.0002952554,0.0000690512,0.0002792945,0.0003576689,0.001298394,0.0003101041,0.00003614294],"category_scores_gemma":[0.00006059624,0.0003333275,0.0001405945,0.000382183,0.0001112399,0.0002332281,0.002755604,0.001063902,0.0001502713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006409176,"about_ca_system_score_gemma":0.0001521997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006762059,"about_ca_topic_score_gemma":0.00003462735,"domain_scores_codex":[0.9973044,0.0001624301,0.000410968,0.001195246,0.0003901655,0.0005367702],"domain_scores_gemma":[0.9971855,0.0001940385,0.000282993,0.001955113,0.0001757611,0.0002066086],"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":[0.000007529772,0.00007840765,0.00004236662,0.00001675467,0.00003730519,0.0000228297,0.00008871706,0.6079895,0.0002517792,0.06440818,0.3066809,0.0203757],"study_design_scores_gemma":[0.0001003957,0.00005075211,0.0001063934,0.00001653784,0.00001925103,0.000100346,7.562663e-7,0.9193782,0.0003941204,0.04657957,0.03279653,0.0004571592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00208912,0.00009961997,0.9751765,0.0170345,0.001683555,0.0006914029,0.000003607279,0.0007214972,0.002500219],"genre_scores_gemma":[0.1087452,0.00004229688,0.8808079,0.002743818,0.006431777,0.0002293463,0.00005708502,0.0000372744,0.0009054017],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3113887,"threshold_uncertainty_score":0.9999119,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2776622059","doi":"10.1109/iccv.2017.556","title":"3D Graph Neural Networks for RGBD Semantic Segmentation","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":525,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Unary operation; Computer science; Segmentation; Artificial intelligence; Point cloud; Pattern recognition (psychology); Graph; Representation (politics); Theoretical computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02800042271662722,"gpt":0.3040027723263105,"spread":0.2760023496096833,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007766511,0.00009861248,0.00009062616,0.00003004135,0.000704144,0.0002729339,0.0009515956,0.00003272416,0.000005429544],"category_scores_gemma":[0.00001540222,0.00008849016,0.00005533196,0.00007874023,0.00004741601,0.000755722,0.0001861602,0.00006282829,0.00001074651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001195154,"about_ca_system_score_gemma":0.000007821553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007700201,"about_ca_topic_score_gemma":0.00003621618,"domain_scores_codex":[0.9991909,0.00001132984,0.0001426284,0.0003146235,0.00009585442,0.0002446878],"domain_scores_gemma":[0.9987601,0.00009285887,0.0001416486,0.0008924088,0.0000487821,0.00006416865],"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":[0.00001568753,0.00008135717,0.002209626,0.00001880459,0.0000283089,0.000005518781,0.0000849215,0.1106954,0.001439,0.2876986,0.01051656,0.5872061],"study_design_scores_gemma":[0.0002454822,0.00003206271,0.00252919,0.000002906786,0.000005199136,0.000004709604,0.000002779558,0.9845051,0.0005347228,0.01115049,0.0008649966,0.0001223594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002186734,0.00003029479,0.9938167,0.002079034,0.0003421033,0.0004476567,8.478986e-7,0.0001833712,0.0009132453],"genre_scores_gemma":[0.7665144,0.00001719437,0.2318545,0.0006448479,0.0001654805,0.0001350056,0.000006060008,0.00001005691,0.0006525155],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8738096,"threshold_uncertainty_score":0.5415777,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4377241880","doi":"10.3390/electronics12102323","title":"DC-YOLOv8: Small-Size Object Detection Algorithm Based on Camera Sensor","year":2023,"lang":"en","type":"article","venue":"Electronics","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":505,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Artificial intelligence; Object detection; Upsampling; Object (grammar); Precision and recall; Feature (linguistics); Context (archaeology); Point (geometry); Computer vision; Pattern recognition (psychology); Algorithm; Image (mathematics); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01266948918731378,"gpt":0.2480874451694479,"spread":0.2354179559821341,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001831439,0.0001828466,0.0001441899,0.0001194459,0.0002705318,0.00006794908,0.000536108,0.00008137942,0.000007726397],"category_scores_gemma":[0.00007190628,0.000186927,0.00008090081,0.001696683,0.00002725574,0.0001241539,0.00008568248,0.0003864532,0.0004336897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002088346,"about_ca_system_score_gemma":0.0001133014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003740849,"about_ca_topic_score_gemma":0.00003760534,"domain_scores_codex":[0.9983102,0.00007533743,0.0001840053,0.0005407199,0.0002498946,0.0006398343],"domain_scores_gemma":[0.9985538,0.0004749657,0.00008662081,0.0007348924,0.0000592988,0.00009046934],"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":[0.00001549193,0.00007408165,0.00001635477,0.000006617018,0.00001771336,0.00002393664,0.00007174033,0.04018153,0.02035174,0.003798787,0.0009981039,0.9344439],"study_design_scores_gemma":[0.000314202,0.0003146128,0.0003948399,0.000006760942,0.000006540457,0.00001317453,0.000004769619,0.8923317,0.05274258,0.004128464,0.04947808,0.000264291],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0138291,0.0001947505,0.9814213,0.001974171,0.0002872569,0.0003809778,0.000003682158,0.001395153,0.0005136059],"genre_scores_gemma":[0.7571549,0.0007527819,0.232477,0.004372126,0.00074738,0.0005713945,0.00003797056,0.0001407617,0.00374564],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9341796,"threshold_uncertainty_score":0.7622663,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4319300975","doi":"10.1109/wacv56688.2023.00614","title":"HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation","year":2023,"lang":"en","type":"article","venue":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":477,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Encoder; Segmentation; Artificial intelligence; Transformer; Convolutional neural network; Image segmentation; Pattern recognition (psychology); Scale-space segmentation; Computer vision; Voltage","retraction":null,"screen_n_in":null,"score":{"opus":0.04367816882844694,"gpt":0.3724825427121474,"spread":0.3288043738837004,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004435034,0.0003544748,0.0004334071,0.0005461372,0.0004239651,0.0001786107,0.001517102,0.000185343,0.00008287039],"category_scores_gemma":[0.00002450139,0.000350309,0.0002811537,0.001728015,0.0003068897,0.0006862064,0.0002733899,0.0003650018,0.0002670192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009177534,"about_ca_system_score_gemma":0.0002077106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001572975,"about_ca_topic_score_gemma":0.00002637056,"domain_scores_codex":[0.9964584,0.0001118514,0.0009973837,0.001071919,0.000801135,0.0005593327],"domain_scores_gemma":[0.997299,0.000589075,0.0003319196,0.0009749351,0.0004540852,0.0003510444],"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":[0.0001646433,0.00144636,0.000160699,0.0002326445,0.0001789688,0.00001138309,0.001574857,0.01009776,0.1095349,0.054305,0.01982262,0.8024701],"study_design_scores_gemma":[0.001164096,0.0002427716,0.0006318408,0.0001188316,0.00002434783,0.00001714417,0.00009752841,0.9798535,0.008594164,0.005955681,0.002929886,0.0003701838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00468381,0.000009815155,0.9864501,0.005491118,0.0003383564,0.002099939,0.0001118199,0.000449897,0.0003650807],"genre_scores_gemma":[0.2641385,0.0001668498,0.731347,0.0007899248,0.000400765,0.002129032,0.0003572732,0.0000765506,0.0005940708],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9697558,"threshold_uncertainty_score":0.9998949,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3045897451","doi":"10.3390/s20154220","title":"Deep Learning Sensor Fusion for Autonomous Vehicle Perception and Localization: A Review","year":2020,"lang":"en","type":"review","venue":"Sensors","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":469,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Perception; Computer science; Sensor fusion; Set (abstract data type); Anticipation (artificial intelligence); Human–computer interaction; Range (aeronautics); Artificial intelligence; Deep learning; Real-time computing; Engineering; Simulation","retraction":null,"screen_n_in":null,"score":{"opus":0.03555695354953219,"gpt":0.3170844727122842,"spread":0.281527519162752,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001397555,0.0003159583,0.0008827788,0.00006382861,0.0002876518,0.00007069793,0.0003594071,0.0001428292,0.000009341513],"category_scores_gemma":[0.0001204069,0.0002833935,0.0002148141,0.0006294,0.00004131927,0.0001248632,0.0002132771,0.0003035211,0.0001026801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009337368,"about_ca_system_score_gemma":0.00005125339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000103195,"about_ca_topic_score_gemma":8.622376e-7,"domain_scores_codex":[0.998173,0.0001851243,0.0004793643,0.0007539972,0.0001563586,0.0002521474],"domain_scores_gemma":[0.9987403,0.0002617516,0.000352545,0.0004228911,0.000085117,0.0001374065],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[5.161995e-7,0.00000511543,2.267903e-7,0.007543508,0.000008946628,0.000003463505,0.0000521722,0.0005041846,5.468095e-7,0.0005006457,0.0001995133,0.9911811],"study_design_scores_gemma":[0.00005524546,0.00003938609,7.040562e-7,0.004454664,0.0001187316,0.00006177757,0.00000518192,0.1713862,1.527363e-7,0.00007494589,0.8235636,0.0002393484],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.324895e-7,0.7366028,0.2613406,0.0004009061,0.00006528118,0.001298617,0.000002707547,0.0002341239,0.00005451067],"genre_scores_gemma":[0.000002189557,0.9746305,0.02417723,0.0004218775,0.000193499,0.00021453,0.00006666081,0.00004444647,0.0002490664],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9909418,"threshold_uncertainty_score":0.9999618,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963809933","doi":"10.1109/tpami.2017.2706685","title":"3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":430,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Office of Naval Research; Toyota Motor Corporation; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Nvidia","keywords":"Artificial intelligence; Computer vision; Computer science; Object detection; Object (grammar); Object-class detection; Class (philosophy); Pattern recognition (psychology); Face detection; Facial recognition system","retraction":null,"screen_n_in":null,"score":{"opus":0.04354686040000782,"gpt":0.3256726781947614,"spread":0.2821258177947536,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002514746,0.000273202,0.00035682,0.0003593457,0.001302031,0.0005142318,0.0007664545,0.0000769621,0.00001689536],"category_scores_gemma":[0.00001408542,0.0002446081,0.0002942838,0.0005269281,0.0001172605,0.0007858884,0.00001616329,0.0002539791,0.00001201204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006137387,"about_ca_system_score_gemma":0.0000288525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004733865,"about_ca_topic_score_gemma":0.001719439,"domain_scores_codex":[0.9982108,0.00006923981,0.0004243372,0.0007488315,0.000213366,0.0003334661],"domain_scores_gemma":[0.9980177,0.000212726,0.0003362601,0.00117186,0.0001390217,0.0001224929],"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":[0.00002092125,0.0000802054,0.0001346909,0.00001862867,0.0002583624,0.00000349148,0.00008780944,0.04955916,0.006554653,0.00003501014,0.000001886083,0.9432452],"study_design_scores_gemma":[0.0000922099,0.0000847439,0.0003922855,0.00001692812,0.0003009367,0.00001385648,0.00001106201,0.7375475,0.2607038,0.0005206831,0.0000665233,0.0002494508],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006852094,0.00004376439,0.9918632,0.0002986954,0.0002840455,0.0004581242,0.00005012832,0.0001152086,0.00003474093],"genre_scores_gemma":[0.9837689,0.0001594758,0.01554797,0.0002031916,0.00005184639,0.0001215926,0.000002842271,0.00001972103,0.000124476],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9769168,"threshold_uncertainty_score":0.9999982,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2795276939","doi":"10.1109/cvpr.2018.00096","title":"Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":429,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Polygon (computer graphics); Annotation; Artificial intelligence; Encoder; Segmentation; Recurrent neural network; Generalization; Graph; Pattern recognition (psychology); Machine learning; Artificial neural network; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01251701619102445,"gpt":0.2939386130024038,"spread":0.2814215968113793,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004501501,0.0000641158,0.00006019619,0.0000535459,0.00006399355,0.00001947771,0.0002524066,0.0000118811,0.00001470274],"category_scores_gemma":[0.000007065738,0.00004921817,0.000009985582,0.0004183027,0.00006734598,0.0002331253,0.00008211184,0.00003465488,0.00003947861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000233683,"about_ca_system_score_gemma":0.00001775603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001394294,"about_ca_topic_score_gemma":0.00001752586,"domain_scores_codex":[0.9993864,0.00001927947,0.0001272872,0.0002195578,0.0001464193,0.0001010419],"domain_scores_gemma":[0.9993328,0.00006649081,0.0001165266,0.0003424932,0.0001091956,0.00003242305],"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":[0.0003180584,0.0009555048,0.001399541,0.00003667304,0.0001086812,0.00000788505,0.007331468,0.04952301,0.322636,0.2567783,0.01065816,0.3502467],"study_design_scores_gemma":[0.0005889374,0.0005251259,0.005271584,0.00002982209,0.00001013983,0.00001708885,0.0001897758,0.5584095,0.4324031,0.001296755,0.001037996,0.0002201022],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08707049,0.00000440264,0.9114949,0.0002516616,0.00005376407,0.0001861861,0.00001287661,0.00005904859,0.0008667366],"genre_scores_gemma":[0.8213392,7.1986e-7,0.178409,0.0001413971,0.00002497712,0.00001707691,0.00003082926,0.000003330753,0.0000334288],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7342687,"threshold_uncertainty_score":0.2007059,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2965182628","doi":"10.1109/cvpr.2019.00902","title":"UPSNet: A Unified Panoptic Segmentation Network","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":422,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Inference; Convolution (computer science); Representation (politics); Task (project management); Computer vision; Class (philosophy); Pixel; Panopticon; Image segmentation; Code (set theory); Pattern recognition (psychology); Artificial neural network; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02628135047772449,"gpt":0.2801040390594792,"spread":0.2538226885817547,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001340404,0.0002614602,0.0002383509,0.00006285414,0.0000963924,0.0001848291,0.001443691,0.0001459801,0.00002023842],"category_scores_gemma":[0.000007798254,0.0002556071,0.00009317126,0.0003863581,0.00002501646,0.0001528839,0.001935387,0.000468716,0.0004183851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008338453,"about_ca_system_score_gemma":0.0001276723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000622054,"about_ca_topic_score_gemma":0.000007797677,"domain_scores_codex":[0.9981638,0.00006718429,0.0003186099,0.0008276855,0.0002627559,0.0003599876],"domain_scores_gemma":[0.9977758,0.0001228073,0.0002460472,0.001683551,0.00008378336,0.00008799956],"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":[0.000003974516,0.00003330195,0.0002351374,0.0000470455,0.00002626921,0.00000157599,0.00008025038,0.7997379,0.0001521763,0.1360326,0.01281696,0.05083283],"study_design_scores_gemma":[0.000376842,0.00005962483,0.00202039,0.0001266134,0.00003121598,0.000008736715,0.000009289623,0.7536798,0.0004880211,0.2156025,0.02665136,0.0009456317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001033438,0.000457421,0.988601,0.0007463043,0.001372101,0.00100082,0.000002268956,0.0004885799,0.006298119],"genre_scores_gemma":[0.2025131,0.0004848464,0.7900978,0.001230885,0.00083439,0.0004564421,0.0001349239,0.00004992191,0.004197771],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2014796,"threshold_uncertainty_score":0.9999896,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2925148167","doi":"10.1109/cvpr42600.2020.01164","title":"nuScenes: A Multimodal Dataset for Autonomous Driving","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":379,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Nutrasource","funders":"","keywords":"Computer science; Lidar; Artificial intelligence; Benchmark (surveying); Computer vision; Object detection; Segmentation; Bounding overwatch; Suite; Radar; Field (mathematics); Minimum bounding box; Software deployment; Tracking (education); Image (mathematics); Remote sensing; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.04817872216276899,"gpt":0.3202832048929103,"spread":0.2721044827301414,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00008033249,0.0002739214,0.0002908253,0.00005091379,0.000140905,0.0002076573,0.002457465,0.0001374492,0.00001083146],"category_scores_gemma":[0.00005771949,0.0002714469,0.0001154734,0.0001678219,0.00003260179,0.0002130758,0.003591608,0.0003562922,0.0000835758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006958199,"about_ca_system_score_gemma":0.0001455888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001927282,"about_ca_topic_score_gemma":0.00002172773,"domain_scores_codex":[0.9980288,0.00002371995,0.0003248357,0.001139167,0.0001549576,0.0003284806],"domain_scores_gemma":[0.9977596,0.0002574946,0.0001866561,0.001567247,0.0000570478,0.0001719914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001993243,0.0003102166,0.0001690932,0.0004532988,0.0001762901,0.00003374026,0.0006886371,0.08583282,0.002238031,0.3081477,0.3911021,0.2108281],"study_design_scores_gemma":[0.0001618355,0.0000207986,0.00008942038,0.00002042825,0.00001045624,0.000003900393,0.000003455627,0.8683165,0.00047804,0.03544584,0.09510647,0.0003428425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008017245,0.0000388311,0.9896647,0.006979718,0.0003827502,0.001156566,0.0008985904,0.000574235,0.0002243967],"genre_scores_gemma":[0.04804616,0.00001504089,0.9463562,0.001612633,0.0003506484,0.0008893699,0.002567455,0.00003052173,0.000131923],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7824837,"threshold_uncertainty_score":0.9999738,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962752334","doi":"10.15353/vsnl.v3i1.171","title":"Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":369,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Nvidia","keywords":"Computer science; Object detection; Artificial intelligence; Inference; Speedup; Computer vision; Object (grammar); Frame rate; Viola–Jones object detection framework; Deep learning; Leverage (statistics); Real-time computing; Pattern recognition (psychology); Parallel computing; Face detection","retraction":null,"screen_n_in":null,"score":{"opus":0.01108084151276349,"gpt":0.2947790650750308,"spread":0.2836982235622673,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000737422,0.0001664772,0.0003598315,0.0002517497,0.0004942059,0.0006482385,0.0005843819,0.00004074675,4.854961e-7],"category_scores_gemma":[0.00008223992,0.0001439178,0.0000971076,0.000154877,0.00006334554,0.001304346,0.0001176939,0.0001651374,0.000007522757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001632983,"about_ca_system_score_gemma":0.0001230722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002563317,"about_ca_topic_score_gemma":0.00000375176,"domain_scores_codex":[0.9982656,0.0001083153,0.0007371812,0.0002697294,0.0004027056,0.0002164593],"domain_scores_gemma":[0.9975579,0.0003714092,0.001173015,0.000315897,0.0004619439,0.0001198633],"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":[0.0003543676,0.0002801405,0.003431054,0.0005401568,0.0001119744,0.000116251,0.002371053,0.5049073,0.03252675,0.0219666,0.001832571,0.4315618],"study_design_scores_gemma":[0.001173946,0.0001286688,0.01127811,0.0006078048,0.00001033122,0.001035782,0.0002663499,0.983197,0.0001932283,0.001477876,0.0004617651,0.0001691231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05815003,0.0002148928,0.9395736,0.000619074,0.0006931587,0.0003908923,0.000005605532,0.00005327349,0.0002994802],"genre_scores_gemma":[0.9751888,0.00001617265,0.02437007,0.00003566136,0.0002615877,0.00001478777,0.000002038595,0.00001462718,0.00009624627],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9170388,"threshold_uncertainty_score":0.6250979,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2010132303","doi":"10.1109/cvpr.2011.5995720","title":"Learning to share visual appearance for multiclass object detection","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":339,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Object (grammar); Hierarchy; Object detection; Task (project management); Cognitive neuroscience of visual object recognition; Hierarchical database model; Pattern recognition (psychology); Object model; Class (philosophy); Machine learning; Statistical model; Computer vision; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03498099483991979,"gpt":0.2934471307625395,"spread":0.2584661359226197,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007169489,0.00008304602,0.00007292199,0.00004744968,0.0001810452,0.00003161835,0.0003387427,0.00002854475,0.000005177104],"category_scores_gemma":[0.0000488985,0.00007911659,0.00003688758,0.00034629,0.000009938779,0.0002730531,0.000113702,0.00008043493,0.0001099156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000255655,"about_ca_system_score_gemma":0.00000803443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001007303,"about_ca_topic_score_gemma":0.00004152034,"domain_scores_codex":[0.9992294,0.00001648866,0.0001151951,0.0003331096,0.00008242767,0.0002233583],"domain_scores_gemma":[0.9995564,0.00003953279,0.0000394345,0.0002156352,0.00006931125,0.00007966639],"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":[0.0000480426,0.00009458479,0.0003547022,0.00001897488,0.00001178594,0.000001634205,0.002176428,0.006309577,0.0585406,0.01285733,0.0002105419,0.9193758],"study_design_scores_gemma":[0.0003491887,0.000496338,0.004606655,0.00001793587,0.000003698569,0.000007857449,0.00009522378,0.8105429,0.1703345,0.002396804,0.01082795,0.0003209263],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0196983,0.00001024621,0.978389,0.0001121758,0.00009356963,0.0004223615,3.981532e-7,0.0003928045,0.0008812065],"genre_scores_gemma":[0.8301859,0.000001174765,0.168829,0.0002289831,0.00004680113,0.0002161395,5.008701e-7,0.000008630265,0.0004828618],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9190549,"threshold_uncertainty_score":0.3226281,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220827132","doi":"10.1109/tits.2022.3158253","title":"Edge YOLO: Real-Time Intelligent Object Detection System Based on Edge-Cloud Cooperation in Autonomous Vehicles","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":334,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"King Saud University","keywords":"Cloud computing; Computer science; Object detection; Enhanced Data Rates for GSM Evolution; Convolutional neural network; Reliability (semiconductor); Real-time computing; Edge computing; Artificial intelligence; Feature extraction; Deep learning; Feature (linguistics); Energy consumption; Pruning; Intelligent transportation system; Embedded system; Engineering; Power (physics); Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.01914620768282576,"gpt":0.2451328142284102,"spread":0.2259866065455844,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008421845,0.0004695879,0.0004825156,0.0008536827,0.0008778854,0.0001595436,0.0007567862,0.0001550336,0.00007075694],"category_scores_gemma":[0.000004656302,0.0005231208,0.0002448611,0.002016051,0.00005748845,0.0004083557,0.000002493968,0.0006757311,0.0002588457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001614239,"about_ca_system_score_gemma":0.0001994991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003412301,"about_ca_topic_score_gemma":0.0002355622,"domain_scores_codex":[0.9955394,0.000664888,0.001342477,0.001097315,0.0008361578,0.000519737],"domain_scores_gemma":[0.9977842,0.0005107301,0.0003688822,0.0009473535,0.0001989135,0.0001899329],"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":[0.0002893072,0.0004346939,0.00001702794,0.00006462488,0.00002672003,0.00002188612,0.0009750155,0.9766583,0.01054561,0.001441471,0.00005164633,0.009473735],"study_design_scores_gemma":[0.0006317988,0.0008738411,0.0002837202,0.0001531844,0.0000389981,0.00002634939,0.0007651263,0.9022936,0.09171245,0.00002857469,0.002579207,0.000613177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04689333,0.00004545581,0.9466019,0.0001805701,0.002991989,0.002011516,0.0001278596,0.0009223776,0.0002249579],"genre_scores_gemma":[0.9955717,0.00003697239,0.0009344876,0.0001131946,0.00009839811,0.002677939,0.00006627281,0.00006828509,0.0004327616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9486784,"threshold_uncertainty_score":0.9997221,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034681889","doi":"10.1109/cvpr42600.2020.01308","title":"Squeeze-and-Attention Networks for Semantic Segmentation","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":330,"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":"Pascal (unit); Segmentation; Computer science; Artificial intelligence; Pixel; Convolution (computer science); Context (archaeology); Pattern recognition (psychology); Grid; Image segmentation; Machine learning; Artificial neural network; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03345037281667305,"gpt":0.2995651833011245,"spread":0.2661148104844515,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008804196,0.0001930643,0.0001967068,0.00004636309,0.0001272962,0.0001864824,0.0005231829,0.0001288076,0.000003257018],"category_scores_gemma":[0.00001304838,0.0001929601,0.00009018027,0.0001654062,0.00002437829,0.0001922869,0.0009520191,0.0002466739,0.00001081175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003897409,"about_ca_system_score_gemma":0.00002531761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005847464,"about_ca_topic_score_gemma":0.000006379153,"domain_scores_codex":[0.9986382,0.00002959216,0.0002709698,0.0007301314,0.0001287841,0.0002023692],"domain_scores_gemma":[0.9990528,0.0001247374,0.0001879494,0.0004699105,0.00007150132,0.00009306095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002736081,0.00009515326,0.0004186778,0.0004528959,0.0001300798,0.000004568021,0.0002906858,0.1816923,0.003581755,0.5276168,0.01633138,0.2693583],"study_design_scores_gemma":[0.0001759974,0.00002766526,0.0005263966,0.00002523858,0.00002221447,0.000002839176,0.000005461101,0.9238491,0.0001968858,0.07416657,0.0007937045,0.0002079436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005459876,0.0001290942,0.9902502,0.006723727,0.0004397073,0.001305554,0.000004209898,0.0004046867,0.0001968266],"genre_scores_gemma":[0.3904827,0.000247319,0.6058213,0.001431634,0.0004579038,0.0009721256,0.0001710076,0.00002929022,0.0003867011],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7421568,"threshold_uncertainty_score":0.7868685,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4247198796","doi":"10.1109/micro.2016.7783722","title":"Stripes: Bit-serial deep neural network computing","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":329,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Speedup; Energy (signal processing); Artificial neural network; Deep neural networks; Efficient energy use; Set (abstract data type); Variance (accounting); Representation (politics); Parallel computing; Computer engineering; Algorithm; Real-time computing; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01743468266604897,"gpt":0.2561888464617708,"spread":0.2387541637957218,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001136009,0.000144302,0.0001375094,0.0000312071,0.0002162296,0.00007984576,0.000951682,0.00004513795,0.00004005905],"category_scores_gemma":[0.00002349252,0.00009452725,0.00005673706,0.0005100532,0.00005249996,0.0004650915,0.0004189857,0.00007898141,0.0001733208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003227304,"about_ca_system_score_gemma":0.00001515289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003576505,"about_ca_topic_score_gemma":0.00001551074,"domain_scores_codex":[0.9985949,0.0000473219,0.0002498968,0.0004497214,0.0001725865,0.0004855965],"domain_scores_gemma":[0.9987424,0.0003435364,0.00009586044,0.0006389695,0.0000511778,0.0001280285],"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":[0.000007551901,0.00002704547,0.0009116009,0.000001925616,0.000009484516,0.000006392112,0.00004015585,0.02645991,0.001779565,0.3411299,0.004235475,0.625391],"study_design_scores_gemma":[0.001340693,0.0001547698,0.005585589,0.00003538956,0.000008436125,0.00005977638,0.0000114749,0.8908784,0.002330221,0.07033636,0.02845794,0.0008009365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01096555,0.00004910241,0.9832885,0.002494634,0.0006661327,0.0001778906,4.815097e-7,0.0006101878,0.001747519],"genre_scores_gemma":[0.8250045,0.000009020854,0.1728446,0.0008395805,0.0009559174,0.00001113516,8.237798e-7,0.000011836,0.0003225812],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8644185,"threshold_uncertainty_score":0.3854709,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2793268137","doi":"10.1109/lgrs.2018.2795531","title":"Fully Convolutional Networks for Semantic Segmentation of Very High Resolution Remotely Sensed Images Combined With DSM","year":2018,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":318,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Upsampling; Computer science; Segmentation; Benchmark (surveying); Artificial intelligence; Digital surface; Convolutional neural network; Semantics (computer science); Computer vision; Convolution (computer science); Pattern recognition (psychology); Remote sensing; Image (mathematics); Artificial neural network; Geology; Lidar","retraction":null,"screen_n_in":null,"score":{"opus":0.01229400361480815,"gpt":0.2364067822291,"spread":0.2241127786142919,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002367879,0.0001643919,0.000185362,0.0001161434,0.0004939684,0.00007786923,0.0002282505,0.00005155176,2.638271e-7],"category_scores_gemma":[0.00002317088,0.0001427262,0.00003775825,0.0005940375,0.0008074764,0.0004141986,0.00005542134,0.0001001446,0.000001783054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004672993,"about_ca_system_score_gemma":0.00004735355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000104316,"about_ca_topic_score_gemma":0.00002973988,"domain_scores_codex":[0.9984809,0.00005693133,0.000259422,0.0005327816,0.0002855583,0.0003843971],"domain_scores_gemma":[0.9988977,0.0002028345,0.0002380281,0.0003623085,0.0002204383,0.00007870953],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003048044,0.0000353286,0.00005776156,0.00005082201,0.0000301282,0.00001756245,0.0004322678,0.01741388,0.8478363,0.001075753,0.002685911,0.1300595],"study_design_scores_gemma":[0.0007032636,0.0003492774,0.003558105,0.0001015596,0.00001897828,0.00009742176,0.00001975124,0.9710386,0.0225502,0.001222945,0.00010987,0.0002300643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2848252,0.00001530472,0.711657,0.002786237,0.0003436444,0.0002946572,0.000002427272,0.00006598887,0.000009543706],"genre_scores_gemma":[0.5878493,0.00001461082,0.4106522,0.001272869,0.0001571228,3.758888e-7,0.000005744986,0.000008650438,0.00003905657],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9536247,"threshold_uncertainty_score":0.5820208,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401386967","doi":"10.1109/lra.2024.3440097","title":"DriveGPT4: Interpretable End-to-End Autonomous Driving Via Large Language Model","year":2024,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":316,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Huawei Technologies (Canada)","funders":"National Natural Science Foundation of China","keywords":"End-to-end principle; Computer science; Language model; End of history; Artificial intelligence; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.008262373931495188,"gpt":0.2518810611154174,"spread":0.2436186871839222,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001291405,0.0001574325,0.0001366958,0.000156074,0.0001597401,0.0003507145,0.0003385552,0.0000405293,0.000006880937],"category_scores_gemma":[0.000007395236,0.000156347,0.00004713997,0.0003779884,0.00002626988,0.0006154322,0.0001492665,0.0001559279,0.00008215843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007136637,"about_ca_system_score_gemma":0.00002478502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004008636,"about_ca_topic_score_gemma":0.000007716859,"domain_scores_codex":[0.9988326,0.00002432239,0.0002275639,0.0004290608,0.0001753979,0.0003110514],"domain_scores_gemma":[0.9993523,0.00009718454,0.00004931226,0.0003659479,0.00002060712,0.0001146831],"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":[4.345646e-7,0.00001655042,0.00001810708,0.00002385089,0.00001574517,0.00001658641,0.001581237,0.8814071,0.0603378,0.02647063,0.001981657,0.02813026],"study_design_scores_gemma":[0.00006436335,0.00001067475,0.0001219873,0.00004975606,0.000009062791,0.00001664309,0.000007797491,0.9962739,0.001333047,0.0010417,0.0008903808,0.0001807381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02365375,0.00008693798,0.9648674,0.01002147,0.0003708629,0.0001973293,0.000005719584,0.00067755,0.0001190335],"genre_scores_gemma":[0.8169503,0.000007579738,0.1801169,0.002630512,0.00008303758,0.00002933264,0.000006240447,0.00001848112,0.0001575926],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7932966,"threshold_uncertainty_score":0.6375644,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3109915642","doi":"10.1109/tits.2021.3096854","title":"A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving","year":2021,"lang":"en","type":"review","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":308,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Probabilistic logic; Computer science; Object detection; Object (grammar); Artificial intelligence; Code (set theory); Range (aeronautics); Machine learning; Deep learning; Key (lock); Data mining; Pattern recognition (psychology); Engineering; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.1020871759141939,"gpt":0.3579890518995406,"spread":0.2559018759853467,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003953953,0.0006479783,0.002021786,0.0005249062,0.0002221123,0.0001382207,0.0004898416,0.0001923592,0.000007481976],"category_scores_gemma":[0.000006281887,0.0006018422,0.0003272771,0.001904447,0.00004837708,0.0002724261,0.000001495895,0.0008440474,0.00005289113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004281918,"about_ca_system_score_gemma":0.0001700157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004857947,"about_ca_topic_score_gemma":0.0006263742,"domain_scores_codex":[0.9956711,0.0006458852,0.001679506,0.001288197,0.0003792548,0.0003360813],"domain_scores_gemma":[0.9975873,0.0006876747,0.0005406385,0.0008847959,0.0001559778,0.0001435632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007351827,0.00146221,0.00000206843,0.01752491,0.0003485862,0.00005056695,0.001976353,0.04224102,0.000001797623,0.001157034,0.00002673236,0.9352013],"study_design_scores_gemma":[0.00145076,0.003122611,0.0001028532,0.2438899,0.005767847,0.0003571478,0.002010583,0.01663274,0.0002330008,0.0001176478,0.7212177,0.005097196],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001234335,0.5124349,0.482837,0.000009954665,0.0004145203,0.004106394,0.00002631783,0.0001369799,0.00002161081],"genre_scores_gemma":[0.03634788,0.9581052,0.0002468138,0.00004095288,0.00003103071,0.005063596,0.00002738334,0.00004222498,0.00009491771],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9301042,"threshold_uncertainty_score":0.9996433,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161893161","doi":"","title":"3D Object Recognition with Deep Belief Nets","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":304,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Discriminative model; Pattern recognition (psychology); Deep belief network; Cognitive neuroscience of visual object recognition; Generative model; Convolutional neural network; Task (project management); Viewpoints; Deep learning; Boltzmann machine; Object (grammar); Set (abstract data type); Test set; Test data; Support vector machine; Generative grammar","retraction":null,"screen_n_in":null,"score":{"opus":0.01536777206003292,"gpt":0.2419744101046343,"spread":0.2266066380446014,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003478235,0.00008118747,0.00006486513,0.00003422889,0.00009754115,0.00004665872,0.0002979779,0.00002277694,0.00002158064],"category_scores_gemma":[0.000004543446,0.00006300333,0.0000154112,0.0004178321,0.00001483794,0.0003826661,0.00003044465,0.000071809,0.000177481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001625418,"about_ca_system_score_gemma":0.00001209256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002316619,"about_ca_topic_score_gemma":0.00001842963,"domain_scores_codex":[0.9993293,0.00001290021,0.0000925892,0.0002661918,0.0001199725,0.0001790742],"domain_scores_gemma":[0.9994588,0.00003834791,0.00003918381,0.000354418,0.00004863635,0.00006064181],"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":[0.000004330316,0.00004981877,0.00002567432,6.251153e-7,0.000002554397,0.000005255027,0.00005929129,0.0009614817,0.0004447374,0.01961361,0.0008042559,0.9780284],"study_design_scores_gemma":[0.002056075,0.002286218,0.02572079,0.00007563864,0.00002996158,0.0004459841,0.00003917615,0.4716371,0.02690945,0.4115637,0.05743177,0.001804172],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002444847,0.00003232177,0.9679756,0.002310889,0.00002721982,0.0001582214,2.626865e-7,0.0003608833,0.02668974],"genre_scores_gemma":[0.3933516,0.00002003929,0.60242,0.00374093,0.00005385231,0.00002137454,0.000005220114,0.000004875708,0.0003820382],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9762242,"threshold_uncertainty_score":0.2569201,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2777795072","doi":"10.1109/iccv.2017.378","title":"SGN: Sequential Grouping Networks for Instance Segmentation","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":299,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pascal (unit); Computer science; Pixel; Segmentation; Object (grammar); Image segmentation; Artificial intelligence; Pattern recognition (psychology); Artificial neural network; Line segment; Sequence (biology); Line (geometry); Computer vision; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04461782187604923,"gpt":0.3267294372387387,"spread":0.2821116153626894,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008789895,0.00007919681,0.00007389667,0.00001765149,0.0007506523,0.0002847637,0.0008691281,0.00003044571,0.000003851093],"category_scores_gemma":[0.00001644996,0.00007685465,0.00003878394,0.00006006877,0.00003862985,0.001025561,0.0001889647,0.00005488842,0.000009278036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000321697,"about_ca_system_score_gemma":0.00001288819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005717327,"about_ca_topic_score_gemma":0.00003047163,"domain_scores_codex":[0.9992788,0.000008707369,0.0001318777,0.0002883126,0.00008702519,0.0002052455],"domain_scores_gemma":[0.9989635,0.00005423787,0.000152277,0.0007321106,0.00004987115,0.00004804412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009101947,0.0000256862,0.0004282764,0.000007626029,0.00001151967,0.000001639717,0.00006853604,0.02885428,0.002577636,0.7392978,0.002344064,0.2263738],"study_design_scores_gemma":[0.0003876248,0.0000265586,0.001402481,0.000009284729,0.000003574886,0.00000382261,0.000005693538,0.9731234,0.002521762,0.01695435,0.005397142,0.0001642889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001391919,0.00003052329,0.9945763,0.001222404,0.0003808179,0.0003758547,8.640251e-7,0.0001563035,0.001864964],"genre_scores_gemma":[0.6383951,0.00001894416,0.3603871,0.0004149124,0.0002030084,0.0001353639,0.00000348103,0.000006764133,0.0004353529],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9442691,"threshold_uncertainty_score":0.5773486,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2799738340","doi":"10.1016/j.media.2019.02.009","title":"Constrained-CNN losses for weakly supervised segmentation","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":282,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Kahnawake Education Center","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Leverage (statistics); Computer science; Segmentation; Iterated function; Mathematical optimization; Differentiable function; Artificial intelligence; Dual (grammatical number); Pixel; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0113012703349794,"gpt":0.2936607132017627,"spread":0.2823594428667833,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000242667,0.0001127253,0.0002452605,0.0001536091,0.00008571257,0.00009525158,0.0006477513,0.00005592716,0.0005673956],"category_scores_gemma":[0.0001407747,0.00009848409,0.000203818,0.001425089,0.00008720926,0.0004222263,0.0001055419,0.00009644982,0.0002114994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000253768,"about_ca_system_score_gemma":0.00005594831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009539893,"about_ca_topic_score_gemma":0.000009577391,"domain_scores_codex":[0.9985665,0.00004173299,0.0002776969,0.000422414,0.0004495489,0.0002420844],"domain_scores_gemma":[0.9986756,0.0004115815,0.00008585292,0.0005238134,0.0001273703,0.0001757495],"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":[0.00004624775,0.0007138632,0.01954319,0.0001664109,0.002471037,0.00006733307,0.000680828,0.004452173,0.09364945,0.08169131,0.01148876,0.7850294],"study_design_scores_gemma":[0.0006435411,0.00005836511,0.001445551,0.00001000657,0.0002882908,0.000004990115,0.00005922544,0.9847953,0.005670786,0.002770979,0.004011978,0.0002409382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01911923,0.00004006743,0.9748856,0.004698119,0.00005805049,0.0002958975,0.000007144426,0.0001223386,0.0007735765],"genre_scores_gemma":[0.7087473,0.00005347203,0.2879939,0.002174629,0.0001183982,0.0001461319,0.0001154566,0.00001200701,0.0006386329],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9803432,"threshold_uncertainty_score":0.6212584,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2136836265","doi":"","title":"Adaptive dropout for training deep neural networks","year":2013,"lang":"en","type":"article","venue":"neural information processing systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":280,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Dropout (neural networks); MNIST database; Computer science; Artificial intelligence; Artificial neural network; Feature (linguistics); Boltzmann machine; Deep belief network; Restricted Boltzmann machine; Stochastic gradient descent; Pattern recognition (psychology); Convolutional neural network; Machine learning; Gradient descent; Deep learning; Backpropagation","retraction":null,"screen_n_in":null,"score":{"opus":0.03198876176642353,"gpt":0.2623541483614051,"spread":0.2303653865949816,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001742303,0.0002409663,0.0002513643,0.0001332559,0.0005361879,0.001099221,0.0007374412,0.0001033319,0.000003246236],"category_scores_gemma":[0.00004398571,0.0002144411,0.00007649128,0.0005951151,0.00005497367,0.008921999,0.0001023381,0.000213284,0.0000488699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007187587,"about_ca_system_score_gemma":0.00003559096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001756599,"about_ca_topic_score_gemma":0.000001609815,"domain_scores_codex":[0.9981577,0.00004346713,0.0007097769,0.000276028,0.0002867118,0.0005263464],"domain_scores_gemma":[0.998305,0.0001530632,0.0005425934,0.0003658377,0.0004783446,0.0001551675],"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":[0.0000064519,0.000009153422,0.00002730403,0.00006638201,0.000006723537,2.754708e-7,0.001690027,0.4083112,0.00003837342,0.01029106,0.000878065,0.578675],"study_design_scores_gemma":[0.000289654,0.00006830336,0.00008848021,0.00002963092,0.000004844844,0.00004508556,0.000522561,0.9957029,0.00001889275,0.0006666981,0.00231625,0.000246656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001684411,0.0002447148,0.9939305,0.0006971702,0.0006547029,0.00141096,0.000002594391,0.0006021471,0.0007728419],"genre_scores_gemma":[0.9786201,0.000002413998,0.01889288,0.0009002767,0.0002740725,0.001178846,0.0000297021,0.00001675906,0.00008499255],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9769356,"threshold_uncertainty_score":0.9999377,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2581624817","doi":"10.48550/arxiv.1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":268,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Computer science; Computation; Machine translation; Artificial neural network; Language model; Artificial intelligence; Layer (electronics); Translation (biology); Machine learning; Language translation; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.0848082490162567,"gpt":0.2135652458888167,"spread":0.12875699687256,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001381674,0.0001732252,0.0001738458,0.00004612949,0.0008411005,0.0001060214,0.002713661,0.00007824716,0.00001343223],"category_scores_gemma":[0.00003220516,0.0001434971,0.0001150094,0.0003583329,0.0001897682,0.000684171,0.0006740626,0.000204025,0.00002297332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002947714,"about_ca_system_score_gemma":0.00002027254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003351,"about_ca_topic_score_gemma":0.0000876814,"domain_scores_codex":[0.99879,0.00007448136,0.000147984,0.0005139583,0.000075596,0.000397943],"domain_scores_gemma":[0.9974241,0.0001405803,0.0002828275,0.001941822,0.0001012801,0.0001094258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004131392,0.0001770348,0.01174335,0.000007194967,0.000064531,0.0002335536,0.0003067732,0.4431343,0.0003658707,0.5373931,0.003236788,0.003296176],"study_design_scores_gemma":[0.0004145,0.00003306386,0.004797014,0.00000911787,0.00001852636,0.00001009006,0.00002936941,0.9827024,0.0003070243,0.005385359,0.006086052,0.0002074448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2065127,0.00006583061,0.7905393,0.0007792255,0.0003242675,0.000258607,0.000003869408,0.0001620659,0.001354145],"genre_scores_gemma":[0.9980142,0.00006456624,0.0006327114,0.0003093615,0.00008744022,0.000001048037,0.000002387172,0.00001241332,0.0008759386],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7915015,"threshold_uncertainty_score":0.646915,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}