{"meta":{"query_hash":"8d22b82a7598","filters":{"venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},"cohort_total":48,"direct_labels_cover":0,"predictions_cover":48,"exported":48,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/8d22b82a7598","api":"https://metacan.xera.ac/api/v1/cohort?venue=2022+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29"},"results":[{"id":"W3160314846","doi":"10.1109/cvpr52688.2022.01434","title":"When Does Contrastive Visual Representation Learning Work?","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Resnick Sustainability Institute for Science, Energy and Sustainability, California Institute of Technology; McGill University; California Institute of Technology; Danmarks Grundforskningsfond; National Science Foundation","keywords":"Computer science; Artificial intelligence; Supervised learning; Machine learning; Granularity; Task (project management); Representation (politics); Semi-supervised learning; Feature learning; Field (mathematics); Unsupervised learning; Labeled data; Domain (mathematical analysis); Natural language processing; Pattern recognition (psychology); Artificial neural network; Mathematics","score_opus":0.0420139713652861,"score_gpt":0.29057369130751903,"score_spread":0.24855971994223294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160314846","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15806668,0.00003657594,0.83471835,0.0024620716,0.0019599225,0.0004492956,0.00002034069,0.00041583847,0.0018709139],"genre_scores_gemma":[0.99192303,0.00007736425,0.0033958443,0.0032310165,0.00022560131,0.00009247991,0.00018081628,0.000029921692,0.0008439289],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963484,0.0009851431,0.00049625395,0.0009883819,0.0007734967,0.0004083389],"domain_scores_gemma":[0.9985141,0.00039839474,0.00035681765,0.00029485836,0.00021188837,0.00022395373],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006136494,0.0003309084,0.00037081877,0.000369261,0.00094093295,0.0008023606,0.0004910263,0.00008400816,0.002220969],"category_scores_gemma":[0.000034198045,0.0003011228,0.00012191613,0.00044061113,0.00007674372,0.0006375369,0.00045633095,0.00085303816,0.00022981185],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012089535,0.000189743,0.0014191591,0.000016369422,0.000040325995,0.00006774455,0.0030484386,0.00073017576,0.00057774235,0.0004743778,0.0021959168,0.9911191],"study_design_scores_gemma":[0.0039609303,0.0027996118,0.016356012,0.0003195748,0.00003904089,0.0001275817,0.0021575543,0.94792783,0.0010256579,0.0061544264,0.017739465,0.0013923045],"about_ca_topic_score_codex":0.00003447777,"about_ca_topic_score_gemma":0.000007536409,"teacher_disagreement_score":0.9897268,"about_ca_system_score_codex":0.00007371219,"about_ca_system_score_gemma":0.00005654311,"threshold_uncertainty_score":0.9999441},"labels":[],"label_agreement":null},{"id":"W3184489883","doi":"10.1109/cvpr52688.2022.00566","title":"Parametric Scattering Networks","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; University of Waterloo; Université de Montréal; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Wavelet transform; Wavelet; Scattering; Filter bank; Parametric statistics; Discriminative model; Morlet wavelet; Computer science; Filter (signal processing); Mathematics; Wavelet packet decomposition; Artificial intelligence; Discrete wavelet transform; Pattern recognition (psychology); Computer vision; Statistics; Physics; Optics","score_opus":0.03890684951204379,"score_gpt":0.2652592332562957,"score_spread":0.2263523837442519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184489883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5367186,0.000056191737,0.45962772,0.00038300353,0.001273989,0.00034839564,0.000089970636,0.00033117074,0.0011709573],"genre_scores_gemma":[0.9960316,0.000147625,0.0021033848,0.0010447162,0.00027978703,0.00019870934,0.000107921725,0.000034785004,0.000051495987],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986577,0.00013786864,0.00028055286,0.00039581614,0.0002448348,0.0002831965],"domain_scores_gemma":[0.9993246,0.00017248174,0.00006175009,0.00024852715,0.00004722685,0.0001453988],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001920311,0.00023231463,0.0002624048,0.0001895309,0.00029767118,0.00015890106,0.00019490813,0.00005710014,0.0011032055],"category_scores_gemma":[0.0000032645344,0.00023819359,0.00008195545,0.00041815639,0.000033667664,0.00009596151,0.00012701831,0.0004928136,0.00014010486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009260965,0.00008930051,0.000102094236,0.0000298888,0.00002111753,0.000007696372,0.0000693631,0.0067720697,0.0011638001,0.000068168636,0.0024109522,0.98925626],"study_design_scores_gemma":[0.00054095505,0.0003960182,0.0058962167,0.000075637145,0.000021416967,0.000027841397,0.00006359886,0.98571634,0.0002952334,0.0015977491,0.004870963,0.000498055],"about_ca_topic_score_codex":0.000012552959,"about_ca_topic_score_gemma":0.0000021999524,"teacher_disagreement_score":0.9887582,"about_ca_system_score_codex":0.000035080397,"about_ca_system_score_gemma":0.000007511859,"threshold_uncertainty_score":0.9998099},"labels":[],"label_agreement":null},{"id":"W3205652345","doi":"10.1109/cvpr52688.2022.01213","title":"Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"FLOPS; Computer science; Regularization (linguistics); Hyperparameter; Artificial intelligence; Reduction (mathematics); Artificial neural network; Machine learning; Pruning; Computational complexity theory; Pattern recognition (psychology); Algorithm; Mathematics","score_opus":0.025838379657593485,"score_gpt":0.24675575112125525,"score_spread":0.22091737146366178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205652345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18858004,0.000048084614,0.80711436,0.0013032395,0.00045301448,0.00092594797,0.00010224977,0.00064859784,0.00082447956],"genre_scores_gemma":[0.9459079,0.00015729043,0.04989434,0.0027013887,0.00015730778,0.0006136293,0.00029217283,0.00005815455,0.00021782401],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99679065,0.00040733418,0.00043533478,0.001221674,0.00068900187,0.00045601078],"domain_scores_gemma":[0.99850386,0.00014206479,0.00026043062,0.00072397303,0.00015507815,0.00021459286],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030032874,0.0004277279,0.00037046988,0.00020637864,0.00086588296,0.00034014194,0.0007522278,0.00010114744,0.0002769354],"category_scores_gemma":[0.000002682448,0.00038838157,0.000092596194,0.00067492865,0.00007166686,0.00059094216,0.00045265307,0.00070633076,0.00005804977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089861525,0.00052232115,0.000509276,0.000058321853,0.00006312399,0.000035677454,0.001960601,0.0029679558,0.0006689427,0.0003032823,0.0011705161,0.9916501],"study_design_scores_gemma":[0.0012265433,0.0012022915,0.0008475909,0.00010857208,0.000024543659,0.00021700398,0.00020204282,0.99272716,0.00008931632,0.0011223988,0.0017162452,0.00051630655],"about_ca_topic_score_codex":0.000012971114,"about_ca_topic_score_gemma":0.000008757042,"teacher_disagreement_score":0.9911338,"about_ca_system_score_codex":0.00011797616,"about_ca_system_score_gemma":0.000072759336,"threshold_uncertainty_score":0.9998568},"labels":[],"label_agreement":null},{"id":"W3214794298","doi":"10.1109/cvpr52688.2022.01239","title":"Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Point cloud; Artificial intelligence; Object (grammar); Pairwise comparison; Generalization; Focus (optics); Task (project management); Computer vision; Pattern recognition (psychology); Machine learning; Mathematics","score_opus":0.025958727074325956,"score_gpt":0.23137296378424616,"score_spread":0.2054142367099202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214794298","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9509639,0.00003566531,0.045979176,0.00030415633,0.00084889145,0.000308032,0.00011427248,0.0006258866,0.00081999705],"genre_scores_gemma":[0.9966454,0.00007828326,0.0015629096,0.0009779844,0.00028831075,0.000070885384,0.00026558296,0.000065479406,0.00004515762],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977385,0.00021319604,0.00043932736,0.00061634334,0.0005893019,0.0004033447],"domain_scores_gemma":[0.99919397,0.00010699456,0.00010949836,0.00027766006,0.000120158606,0.00019173454],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002688315,0.00041604412,0.0004589399,0.00031107024,0.0004235589,0.00029963115,0.00027583426,0.000094109404,0.0024111122],"category_scores_gemma":[0.0000040609675,0.0003848833,0.00014478798,0.00033906783,0.000027978384,0.00023201185,0.000125898,0.0006291898,0.000097645505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014908826,0.00024102083,0.0006558842,0.00016066346,0.0002466936,0.000115973606,0.0015510786,0.030953983,0.0015800372,0.0000065874087,0.0019892082,0.9623498],"study_design_scores_gemma":[0.0013469551,0.0007403278,0.0005199403,0.00011949705,0.000085034226,0.00005061609,0.00024599573,0.995925,0.00017135618,0.000039148104,0.00021579675,0.0005403168],"about_ca_topic_score_codex":0.000026066415,"about_ca_topic_score_gemma":0.000015595771,"teacher_disagreement_score":0.964971,"about_ca_system_score_codex":0.000069517446,"about_ca_system_score_gemma":0.00004143194,"threshold_uncertainty_score":0.9998603},"labels":[],"label_agreement":null},{"id":"W3215180973","doi":"10.1109/cvpr52688.2022.00337","title":"Sound-Guided Semantic Image Manipulation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology; National Research Foundation of Korea","keywords":"Embedding; Computer science; Image (mathematics); Encoder; Representation (politics); Artificial intelligence; Modal; Space (punctuation); Sound (geography); Computer vision; Speech recognition; Acoustics","score_opus":0.074580362166011,"score_gpt":0.295785068282097,"score_spread":0.221204706116086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215180973","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17832418,0.000028018116,0.81515026,0.0026694967,0.0015174872,0.00029377782,0.000024588544,0.0002518148,0.0017403773],"genre_scores_gemma":[0.98482835,0.000040343926,0.006413164,0.008002577,0.0002681654,0.000060528033,0.00011437106,0.000025597348,0.000246906],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972446,0.000325791,0.0004813663,0.0008888483,0.000672455,0.00038694864],"domain_scores_gemma":[0.99880767,0.00011132047,0.0002841302,0.0004499593,0.00017925786,0.00016769054],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00048734996,0.00032275778,0.0003366261,0.0003067174,0.0008186584,0.00084566284,0.00059183704,0.00007146634,0.0013854973],"category_scores_gemma":[0.000007968534,0.00031864305,0.00010571712,0.00038895902,0.000059738966,0.0007240481,0.0005144396,0.00045131744,0.00026463048],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027675125,0.00024214634,0.0004896585,0.00010025961,0.000027950962,0.00010838723,0.0010119409,0.0001397064,0.0023139322,0.0008085313,0.018193716,0.9765361],"study_design_scores_gemma":[0.0018613173,0.00094584195,0.005124843,0.00027314486,0.000029343253,0.00039315445,0.00012850431,0.9627748,0.0012130623,0.023447841,0.002776012,0.0010321274],"about_ca_topic_score_codex":0.000033141816,"about_ca_topic_score_gemma":0.00000958863,"teacher_disagreement_score":0.975504,"about_ca_system_score_codex":0.000063379994,"about_ca_system_score_gemma":0.00006509883,"threshold_uncertainty_score":0.99992657},"labels":[],"label_agreement":null},{"id":"W3215313116","doi":"10.1109/cvpr52688.2022.00384","title":"HEAT: Holistic Edge Attention Transformer for Structured Reconstruction","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Raster graphics; Computer vision; Feature (linguistics); Enhanced Data Rates for GSM Evolution; Pixel; Graph; Trigonometry; Edge detection; Feature extraction; Architecture; Transformer; Pattern recognition (psychology); Image processing; Image (mathematics); Theoretical computer science; Engineering; Mathematics","score_opus":0.06765380507398522,"score_gpt":0.2648405278237926,"score_spread":0.19718672274980736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215313116","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96961,0.00006533024,0.022735132,0.0005107065,0.0038734465,0.0005942444,0.0015656681,0.000108965505,0.0009365327],"genre_scores_gemma":[0.9960462,0.00009074855,0.00045296975,0.00091343414,0.00028032743,0.000029956476,0.0019532798,0.000009770826,0.00022331312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981882,0.00028247846,0.00034555316,0.00054508843,0.00032521604,0.00031344502],"domain_scores_gemma":[0.99939483,0.00012791522,0.00007506276,0.00014408004,0.00010509463,0.00015301771],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035487968,0.00025120156,0.00028053703,0.00014053346,0.00077107106,0.00021152517,0.00015335124,0.00008361905,0.0073172697],"category_scores_gemma":[0.000006000839,0.00021713281,0.0001262943,0.00016885542,0.00006264838,0.00026560467,0.000011505551,0.00032123862,0.00009325847],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017662605,0.000034534634,0.0051212786,0.000051102783,0.000021190714,0.0000062432914,0.00019741025,0.000117037016,0.00069113873,0.0000074744767,0.0015282001,0.9920478],"study_design_scores_gemma":[0.0069194655,0.0076009887,0.4175268,0.000518326,0.0001745476,0.00086536026,0.0020867714,0.5420687,0.0010219587,0.0071249153,0.0116961645,0.0023959598],"about_ca_topic_score_codex":0.0001668995,"about_ca_topic_score_gemma":0.00040863705,"teacher_disagreement_score":0.9896518,"about_ca_system_score_codex":0.000014730551,"about_ca_system_score_gemma":0.000030490846,"threshold_uncertainty_score":0.9935902},"labels":[],"label_agreement":null},{"id":"W3216156094","doi":"10.1109/cvpr52688.2022.01753","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":233,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Korea Customs Service; National Research Foundation of Korea; Ministry of Science and Technology of the People's Republic of China","keywords":"Computer science; Style (visual arts); Transfer (computing); Image (mathematics); Artificial intelligence; Computer vision; Art; Visual arts","score_opus":0.028173930043407902,"score_gpt":0.240075001331752,"score_spread":0.2119010712883441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216156094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06632833,0.00002561464,0.9288647,0.0018188113,0.0008222406,0.00045188473,0.00014114715,0.0001785874,0.0013686796],"genre_scores_gemma":[0.9884328,0.000057747897,0.007132184,0.0036289284,0.00025077353,0.000119175005,0.00016795973,0.000031524938,0.00017885433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970273,0.0005745254,0.0003978165,0.000960556,0.0006172623,0.00042256908],"domain_scores_gemma":[0.998819,0.00017367113,0.00013600019,0.00044876616,0.00021721363,0.00020538308],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036225579,0.0003849141,0.00040103155,0.0002557956,0.0007005353,0.00068053266,0.00049603806,0.00007331884,0.0020795248],"category_scores_gemma":[0.0000049184473,0.00033830473,0.00011815359,0.0003966214,0.00011213021,0.0007772534,0.00022521512,0.00045749758,0.0001518696],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014831906,0.00056849135,0.00006545786,0.000027040747,0.00006442996,0.00011153789,0.0010253864,0.00028785,0.009140959,0.00022746556,0.006453375,0.9818797],"study_design_scores_gemma":[0.006053494,0.010559851,0.002340107,0.0004253964,0.000099032244,0.00039235782,0.00051020464,0.9291417,0.020534426,0.0021395937,0.025615413,0.0021884206],"about_ca_topic_score_codex":0.000033646145,"about_ca_topic_score_gemma":0.000036688878,"teacher_disagreement_score":0.97969127,"about_ca_system_score_codex":0.00006222598,"about_ca_system_score_gemma":0.000060773502,"threshold_uncertainty_score":0.9999069},"labels":[],"label_agreement":null},{"id":"W4221155360","doi":"10.1109/cvpr52688.2022.00503","title":"MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Computer science; Embedding; Knowledge extraction; Construct (python library); Domain knowledge; Question answering; Pipeline (software); Relation (database); Commonsense knowledge; Knowledge base; Artificial intelligence; Domain (mathematical analysis); Bridge (graph theory); Natural language processing; Data mining","score_opus":0.06767699411909972,"score_gpt":0.37926226941430574,"score_spread":0.311585275295206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221155360","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32850057,0.000038879985,0.6688764,0.0007310643,0.0007533727,0.00066328974,0.00004130839,0.00025576504,0.00013934361],"genre_scores_gemma":[0.97984177,0.000020879956,0.018544096,0.0004319355,0.00026112294,0.00050715875,0.00029032823,0.00003430702,0.00006838775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734354,0.0005316333,0.0004614732,0.0010120594,0.0003157188,0.000335585],"domain_scores_gemma":[0.99819994,0.000692323,0.00027948388,0.00034525731,0.00029076164,0.00019222042],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00075057335,0.0003494691,0.00031946448,0.00045105786,0.0009597972,0.0004408958,0.00034075594,0.00012250888,0.00013658196],"category_scores_gemma":[0.0000359179,0.00037679923,0.000097918084,0.0003551563,0.00005932809,0.0005189896,0.00026857023,0.000544189,0.00006086493],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008627146,0.0005197531,0.0008585485,0.00009068382,0.000017357901,0.0000034798625,0.00074078864,0.0018611331,0.0038728565,0.0005009706,0.00029892163,0.99114925],"study_design_scores_gemma":[0.0016673603,0.0009836555,0.018625446,0.00011844054,0.000019006826,0.000031829113,0.00004761305,0.9752714,0.00075626565,0.00074863865,0.0012864396,0.0004439069],"about_ca_topic_score_codex":0.000108899825,"about_ca_topic_score_gemma":0.00004015421,"teacher_disagreement_score":0.9907053,"about_ca_system_score_codex":0.00012127412,"about_ca_system_score_gemma":0.000101751626,"threshold_uncertainty_score":0.9998684},"labels":[],"label_agreement":null},{"id":"W4226213465","doi":"10.1109/cvpr52688.2022.00828","title":"Point Density-Aware Voxels for LiDAR 3D Object Detection","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Hermeneutics and Narrative Identity","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Lidar; Point cloud; Voxel; Computer science; Artificial intelligence; Feature (linguistics); Minimum bounding box; Computer vision; Pattern recognition (psychology); Kernel (algebra); Object detection; Centroid; Feature extraction; Kernel density estimation; Remote sensing; Mathematics; Geography; Statistics; Image (mathematics)","score_opus":0.05659877024076604,"score_gpt":0.26434725163146694,"score_spread":0.2077484813907009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226213465","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9489869,0.000023606637,0.039983343,0.0011253778,0.0048557376,0.001115672,0.0008644379,0.00019790279,0.002847009],"genre_scores_gemma":[0.9949959,0.000048935755,0.000057918474,0.0024944695,0.0007224235,0.00017577532,0.00023395217,0.000031450756,0.001239153],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99816155,0.0002655531,0.0003707473,0.0005511042,0.00035407496,0.0002969645],"domain_scores_gemma":[0.9990272,0.00013801802,0.00018927065,0.00020063973,0.00032235042,0.00012253024],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000392717,0.00027340295,0.00032510274,0.00024381187,0.0013996208,0.00054843596,0.00015751648,0.000059219015,0.0065448224],"category_scores_gemma":[0.000008622051,0.00026310518,0.00014648237,0.00006756511,0.00008991258,0.00025357053,0.00013734233,0.00036484035,0.00014053151],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029311542,0.00046929662,0.0002229101,0.00014272169,0.00010753551,0.000035482542,0.0044234786,0.000017508832,0.0017494586,0.0009996137,0.012302809,0.97923607],"study_design_scores_gemma":[0.013947881,0.0248975,0.009224853,0.0011144051,0.00049808895,0.00028618914,0.009165396,0.35960826,0.020443661,0.04911378,0.50610214,0.0055978126],"about_ca_topic_score_codex":0.00015883446,"about_ca_topic_score_gemma":0.0016226887,"teacher_disagreement_score":0.97363824,"about_ca_system_score_codex":0.000071409944,"about_ca_system_score_gemma":0.000043479085,"threshold_uncertainty_score":0.9999821},"labels":[],"label_agreement":null},{"id":"W4226239637","doi":"10.1109/cvpr52688.2022.00652","title":"ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses","year":2022,"lang":"en","type":"preprint","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Pose; Artificial intelligence; Computer science; Benchmark (surveying); Subspace topology; Prior probability; Machine learning; Unsupervised learning; Set (abstract data type); Pattern recognition (psychology); Computer vision","score_opus":0.03874067111674234,"score_gpt":0.28857380732077514,"score_spread":0.2498331362040328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226239637","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71291006,0.00008431421,0.28207058,0.00067441334,0.0016490263,0.00092544017,0.00018732625,0.0005880388,0.0009107804],"genre_scores_gemma":[0.98732066,0.0006130297,0.0048754667,0.0024398866,0.0005357662,0.00022856283,0.0036964226,0.00008045896,0.00020977322],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945927,0.0010537393,0.0010140713,0.0017874425,0.000998645,0.00055338495],"domain_scores_gemma":[0.9975675,0.00036165013,0.0008327263,0.00058602303,0.0003569228,0.00029517984],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009023153,0.00080631475,0.00071978907,0.00078045786,0.0015928252,0.00183837,0.0005934636,0.00039615482,0.00094769255],"category_scores_gemma":[0.000044020424,0.00086162065,0.00017068771,0.00031265005,0.000072924835,0.00097019697,0.0008388445,0.0023447513,0.0000997232],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069389425,0.0003671553,0.0006146435,0.00034957202,0.00010004577,0.000045435987,0.0018258608,0.0021377844,0.0033238714,0.000093701245,0.0024448638,0.9886277],"study_design_scores_gemma":[0.0015738636,0.0019053698,0.0026003732,0.0013921254,0.00007727108,0.000065659035,0.00019266401,0.98710096,0.0012331251,0.0015669739,0.0010738249,0.0012178128],"about_ca_topic_score_codex":0.00018111826,"about_ca_topic_score_gemma":0.000027041737,"teacher_disagreement_score":0.9874099,"about_ca_system_score_codex":0.00015915859,"about_ca_system_score_gemma":0.000095421776,"threshold_uncertainty_score":0.99996555},"labels":[],"label_agreement":null},{"id":"W4226344270","doi":"10.1109/cvpr52688.2022.00118","title":"RBGNet: Ray-based Grouping for 3D Object Detection","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Point cloud; Object detection; Artificial intelligence; Object (grammar); Feature (linguistics); Computer vision; Point (geometry); Process (computing); RGB color model; Pattern recognition (psychology); Sample (material); Cluster (spacecraft); Detector; Code (set theory); Mathematics","score_opus":0.0476342173372355,"score_gpt":0.2843524919410307,"score_spread":0.2367182746037952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226344270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025306018,0.00002770522,0.9706099,0.0012692283,0.001299237,0.00091907225,0.00008767712,0.0003429143,0.00013826236],"genre_scores_gemma":[0.9494521,0.00004881073,0.043269385,0.0056879786,0.0003352016,0.00091347046,0.00018370895,0.00003940768,0.00006991756],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974235,0.0002701706,0.00043361037,0.0010089402,0.000447614,0.00041615873],"domain_scores_gemma":[0.99844354,0.00040774752,0.000277707,0.0005271224,0.00017712668,0.00016674126],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003626668,0.0003252015,0.00031347823,0.00030301965,0.0009954295,0.00031361615,0.00057971064,0.00007742882,0.00021870299],"category_scores_gemma":[0.000009542167,0.0003403059,0.0001336007,0.00051096786,0.000050875373,0.00039052792,0.0002761081,0.0004313641,0.00006401443],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065470005,0.00014439625,0.000026789183,0.000031028783,0.000012969943,0.000008022163,0.00012830565,0.0021336116,0.0030879427,0.00021047435,0.0010890379,0.99306196],"study_design_scores_gemma":[0.0013549043,0.0014108841,0.0004406002,0.00007248209,0.000014592321,0.000035393437,0.000026957598,0.9818029,0.0022738967,0.0036813188,0.008380494,0.00050561817],"about_ca_topic_score_codex":0.000012272669,"about_ca_topic_score_gemma":0.000020442681,"teacher_disagreement_score":0.99255633,"about_ca_system_score_codex":0.00009367654,"about_ca_system_score_gemma":0.000055833396,"threshold_uncertainty_score":0.9999049},"labels":[],"label_agreement":null},{"id":"W4312251507","doi":"10.1109/cvpr52688.2022.01646","title":"ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Air Force Office of Scientific Research","keywords":"Computer science; Artificial intelligence; Computer vision; Pattern recognition (psychology)","score_opus":0.03531411083796985,"score_gpt":0.2545745376901245,"score_spread":0.21926042685215466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312251507","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46385634,0.00007216613,0.53375995,0.00021266153,0.0007132111,0.00036459632,0.00045941042,0.00025401695,0.00030765525],"genre_scores_gemma":[0.9969461,0.00016574912,0.0015992725,0.0005350307,0.00016905123,0.00009987613,0.0004195644,0.000032356966,0.000032990116],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862254,0.00011672653,0.0004198606,0.0003453175,0.00027918385,0.00021637659],"domain_scores_gemma":[0.99941087,0.00011120693,0.000089792564,0.00014996392,0.00014050333,0.00009765158],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002247975,0.00021050013,0.000343961,0.00018658451,0.00019493198,0.00007936749,0.00014854652,0.00006907006,0.001203512],"category_scores_gemma":[0.000005178495,0.00021402701,0.00011496482,0.00016494938,0.000022155233,0.00009835964,0.000057722358,0.00019169222,0.000017403323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016119184,0.00043103073,0.00048011975,0.00045820093,0.0002881616,0.000013131811,0.0012708484,0.06504701,0.0053279763,0.00006996773,0.005480711,0.92097163],"study_design_scores_gemma":[0.00102614,0.00043497919,0.00008792587,0.00008182195,0.000068077046,0.0000061624073,0.00006516217,0.99599665,0.0009709372,0.00020271982,0.0007929192,0.00026651192],"about_ca_topic_score_codex":0.00002166646,"about_ca_topic_score_gemma":0.000014845541,"teacher_disagreement_score":0.9309496,"about_ca_system_score_codex":0.000035514735,"about_ca_system_score_gemma":0.000033654313,"threshold_uncertainty_score":0.99970955},"labels":[],"label_agreement":null},{"id":"W4312261477","doi":"10.1109/cvpr52688.2022.00517","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":185,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Principle of compositionality; Computer science; Set (abstract data type); Task (project management); Artificial intelligence; Natural language processing; Language model; Field (mathematics); State (computer science); Programming language","score_opus":0.042859049951476526,"score_gpt":0.31686812750494875,"score_spread":0.2740090775534722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312261477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2280766,0.000047468828,0.7679021,0.0019478196,0.00047274784,0.0007839287,0.00018536781,0.00023741674,0.00034659382],"genre_scores_gemma":[0.97343403,0.000026011137,0.023178808,0.002361622,0.00020283752,0.00032946203,0.00038954974,0.00002894611,0.000048719157],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972237,0.00040389993,0.00046223254,0.001033601,0.0005248436,0.00035174686],"domain_scores_gemma":[0.9983299,0.00051133183,0.00025632256,0.0004847668,0.0002175214,0.00020019432],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006912344,0.00033774227,0.00036783185,0.00026477707,0.0010281884,0.00058615935,0.00052606716,0.00007798632,0.00015310958],"category_scores_gemma":[0.000018295636,0.00033292006,0.00010215689,0.00025452673,0.00007934779,0.00038788762,0.0005616833,0.0005084338,0.00003028885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012125031,0.00059314485,0.00030295868,0.00018738522,0.00004934161,0.000025558391,0.0040286053,0.0029440266,0.0032096335,0.007885403,0.0010201518,0.97963256],"study_design_scores_gemma":[0.0011950467,0.00090892805,0.0027894154,0.00014064324,0.000018373974,0.00006951799,0.00007815531,0.9791534,0.00012146692,0.014439977,0.0006448157,0.00044028388],"about_ca_topic_score_codex":0.00015809447,"about_ca_topic_score_gemma":0.00001398406,"teacher_disagreement_score":0.97919226,"about_ca_system_score_codex":0.00007116452,"about_ca_system_score_gemma":0.000052477004,"threshold_uncertainty_score":0.99991226},"labels":[],"label_agreement":null},{"id":"W4312281441","doi":"10.1109/cvpr52688.2022.00734","title":"Generalized Category Discovery","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":201,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Geomechanica (Canada)","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science","score_opus":0.0500751412206696,"score_gpt":0.265972821927312,"score_spread":0.2158976807066424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312281441","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26301354,0.00014252304,0.7220315,0.0044469675,0.004624021,0.00063036,0.00019042923,0.00040839257,0.0045122914],"genre_scores_gemma":[0.98352027,0.00026878467,0.0045665475,0.010502018,0.0003297473,0.00013242233,0.00021413279,0.000028272356,0.0004377979],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969402,0.00049588014,0.00045443373,0.0009981019,0.0006603695,0.00045104345],"domain_scores_gemma":[0.9987401,0.00012831192,0.00021624661,0.00060896523,0.000101956924,0.00020446235],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00043466047,0.00036699127,0.00040778096,0.000284036,0.0006787601,0.0008852215,0.0008421577,0.000083557774,0.000986007],"category_scores_gemma":[0.000004835028,0.00032578607,0.00015056763,0.00036113424,0.00006812413,0.00070462533,0.00074036355,0.0005191835,0.00020961574],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006351916,0.00035199625,0.00023147541,0.00003163829,0.000037449674,0.00015876953,0.000620391,0.00018353303,0.0005653711,0.003516225,0.020160658,0.97407895],"study_design_scores_gemma":[0.0052257823,0.004737924,0.0072026756,0.00019468108,0.00005109117,0.0005084428,0.00027070695,0.9079094,0.00095664646,0.038354967,0.032163586,0.002424076],"about_ca_topic_score_codex":0.000083257924,"about_ca_topic_score_gemma":0.000013853659,"teacher_disagreement_score":0.9716549,"about_ca_system_score_codex":0.00006193095,"about_ca_system_score_gemma":0.00008061627,"threshold_uncertainty_score":0.9999272},"labels":[],"label_agreement":null},{"id":"W4312314147","doi":"10.1109/cvpr52688.2022.00071","title":"Frame Averaging for Equivariant Shape Space Learning","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Equivariant map; Generalization; Computer science; Autoencoder; Artificial intelligence; Piecewise; Euclidean space; Homogeneous space; Algorithm; Mathematics; Theoretical computer science; Pattern recognition (psychology); Deep learning; Geometry; Pure mathematics; Mathematical analysis","score_opus":0.037609731627951004,"score_gpt":0.25298821578330954,"score_spread":0.21537848415535854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312314147","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23962258,0.000069600865,0.7575001,0.0006050649,0.0008832186,0.00022755857,0.00009730898,0.00034893953,0.0006456298],"genre_scores_gemma":[0.99670255,0.00015297919,0.0013994188,0.0008502345,0.00026099538,0.00009540536,0.0002620195,0.000051303676,0.00022511734],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984206,0.00012715334,0.00032118283,0.00047391618,0.00031426825,0.00034286207],"domain_scores_gemma":[0.9993635,0.00015446507,0.00008221542,0.00017686785,0.00009076753,0.00013217285],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033774125,0.0002741779,0.00033755953,0.000260953,0.00048189837,0.0002427663,0.00017596822,0.00007339978,0.0018734459],"category_scores_gemma":[0.0000073638384,0.00028763516,0.00014384228,0.00018446145,0.000019940842,0.00012788297,0.00010665403,0.00058320776,0.000079965066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043265725,0.000079834484,0.00016864021,0.000115544506,0.00010418678,0.000024633402,0.00077173614,0.0962597,0.0020521018,0.000049044684,0.00333094,0.8970004],"study_design_scores_gemma":[0.0006561435,0.0003618892,0.0000879569,0.00012600319,0.00003831362,0.00001822124,0.00017356584,0.99440086,0.00023973743,0.000617579,0.0028897254,0.00039003397],"about_ca_topic_score_codex":0.000015729822,"about_ca_topic_score_gemma":0.0000042221595,"teacher_disagreement_score":0.89814115,"about_ca_system_score_codex":0.000053242806,"about_ca_system_score_gemma":0.000018802255,"threshold_uncertainty_score":0.99995756},"labels":[],"label_agreement":null},{"id":"W4312325116","doi":"10.1109/cvpr52688.2022.01606","title":"Learning Program Representations for Food Images and Cooking Recipes","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Compute Canada","funders":"","keywords":"Computer science; Artificial intelligence; Computer graphics (images); Computer vision; Multimedia","score_opus":0.04658781759865796,"score_gpt":0.3236402620936274,"score_spread":0.27705244449496946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312325116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2620736,0.00009854061,0.7252323,0.009039834,0.0010889556,0.0009661983,0.00015324482,0.00064510724,0.0007022214],"genre_scores_gemma":[0.98104936,0.00014812239,0.016726093,0.0010398304,0.00021670033,0.00020292256,0.00017308463,0.000024366766,0.0004195156],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979742,0.00031594955,0.00032881682,0.00073235825,0.0003455168,0.00030311322],"domain_scores_gemma":[0.9988807,0.00034081144,0.000211126,0.00025119775,0.00017941515,0.00013678316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042437075,0.00022787336,0.00027128623,0.00025124472,0.0009052258,0.0006777323,0.00031153273,0.000055017153,0.00009331022],"category_scores_gemma":[0.000032044332,0.0002278264,0.000087791865,0.00026980008,0.00005865567,0.00030582433,0.0003346388,0.0005111914,0.000012293292],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021455748,0.00016328463,0.0007133669,0.00004017145,0.0000298375,0.000010345897,0.00058273104,0.0003378968,0.0002216528,0.00034177615,0.0015910352,0.99594647],"study_design_scores_gemma":[0.0015810463,0.005630583,0.0019710022,0.00018479499,0.000034694818,0.000095542804,0.000469015,0.97174513,0.0004308563,0.006234358,0.0110487845,0.0005741725],"about_ca_topic_score_codex":0.000010632257,"about_ca_topic_score_gemma":0.000008111642,"teacher_disagreement_score":0.9953723,"about_ca_system_score_codex":0.000023011262,"about_ca_system_score_gemma":0.000043166547,"threshold_uncertainty_score":0.9290491},"labels":[],"label_agreement":null},{"id":"W4312339971","doi":"10.1109/cvpr52688.2022.00373","title":"Kubric: A scalable dataset generator","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia; McGill University; University of Toronto","funders":"","keywords":"Computer science; Python (programming language); Scalability; Reuse; Generator (circuit theory); Ground truth; Code generation; Software; Architecture; Source code; Machine learning; Artificial intelligence; Software engineering; Data mining; Distributed computing; Database; Programming language; Computer security","score_opus":0.04847059047974639,"score_gpt":0.29179396151082965,"score_spread":0.24332337103108326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312339971","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021119637,0.00010004889,0.9705487,0.0031578238,0.0024240073,0.00044635643,0.0010383944,0.0003221395,0.000842915],"genre_scores_gemma":[0.86559623,0.00059680454,0.069421224,0.058502927,0.0008711823,0.00035402857,0.0035438873,0.000111374444,0.0010023181],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967597,0.0004003851,0.00047865673,0.0011389115,0.0007260109,0.0004963332],"domain_scores_gemma":[0.99843,0.00013745979,0.0002239378,0.00075388124,0.00014599811,0.00030869],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00045983944,0.00037593866,0.00038687093,0.00035327335,0.0008396394,0.00067863474,0.0009115012,0.000060113623,0.0021152266],"category_scores_gemma":[0.0000108713675,0.0003620509,0.00009378666,0.0005092711,0.000066798566,0.00086072175,0.0010212314,0.00058827584,0.00047828152],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028096742,0.0002181888,0.00009647546,0.00001972568,0.000015840418,0.000087418186,0.00017893987,0.00007632775,0.0013267463,0.00026445425,0.07273697,0.92495084],"study_design_scores_gemma":[0.001752648,0.001111446,0.00054279744,0.00012474917,0.000014038872,0.00023953663,0.00008821579,0.88053584,0.0014626308,0.0025849096,0.11067903,0.0008641312],"about_ca_topic_score_codex":0.000027105287,"about_ca_topic_score_gemma":0.0000059935383,"teacher_disagreement_score":0.9240867,"about_ca_system_score_codex":0.000067974,"about_ca_system_score_gemma":0.00008192648,"threshold_uncertainty_score":0.9998832},"labels":[],"label_agreement":null},{"id":"W4312372711","doi":"10.1109/cvpr52688.2022.00495","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":204,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Focus (optics); Information retrieval; Representation (politics); ENCODE; Pooling; Recall; Natural language processing; Artificial intelligence; Similarity (geometry); Text retrieval; Code (set theory); Function (biology); Image (mathematics); Linguistics","score_opus":0.03439024797878233,"score_gpt":0.32644121003245424,"score_spread":0.2920509620536719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312372711","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4102937,0.00002858537,0.5840504,0.0030542435,0.0010195368,0.0007496413,0.00020724667,0.00033651982,0.00026012005],"genre_scores_gemma":[0.9874263,0.000024653997,0.007792443,0.0031564517,0.0003643972,0.00032369126,0.0004684079,0.000043900327,0.00039977024],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99654275,0.00045581584,0.0005904011,0.0012202935,0.00070194283,0.0004888052],"domain_scores_gemma":[0.99787146,0.00048906833,0.0003623997,0.000753598,0.00028797478,0.00023552604],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009117155,0.00038962113,0.0003962401,0.00035970824,0.001055059,0.00083268137,0.0009489253,0.00012274641,0.00077392167],"category_scores_gemma":[0.0000510013,0.0004004747,0.00020450952,0.00048173717,0.00009146509,0.00051541516,0.00061130244,0.0007279167,0.00025861236],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021023967,0.000495816,0.0022335022,0.0000938766,0.000053344153,0.000025027739,0.0011319579,0.00083150185,0.0054607126,0.0011726569,0.005133914,0.98315746],"study_design_scores_gemma":[0.0026523795,0.0015709979,0.037148517,0.000113955684,0.000027789536,0.00010190958,0.000102081714,0.9497818,0.0008196452,0.0030965684,0.003813624,0.0007707585],"about_ca_topic_score_codex":0.00014470644,"about_ca_topic_score_gemma":0.000015572956,"teacher_disagreement_score":0.9823867,"about_ca_system_score_codex":0.00010085636,"about_ca_system_score_gemma":0.000080539736,"threshold_uncertainty_score":0.99984473},"labels":[],"label_agreement":null},{"id":"W4312416140","doi":"10.1109/cvpr52688.2022.01562","title":"SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Leverage (statistics); Cluster analysis; Artificial intelligence; False positive paradox; Key (lock); Pattern recognition (psychology); Annotation","score_opus":0.06442381366281381,"score_gpt":0.29854877849399686,"score_spread":0.23412496483118306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312416140","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2580509,0.000009041349,0.7385729,0.00069849263,0.0007817168,0.0007608291,0.00004662256,0.00044272823,0.00063675176],"genre_scores_gemma":[0.98853636,0.000041745167,0.0074397074,0.0024882664,0.0003547323,0.00046100552,0.00034086982,0.00004166555,0.00029567082],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972449,0.0004496551,0.00043791087,0.0009453707,0.00052270165,0.00039949082],"domain_scores_gemma":[0.998745,0.00018524144,0.0003026798,0.00030233155,0.00028655725,0.00017819555],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00041462248,0.00037928481,0.00036859044,0.0004178356,0.0016177961,0.0007855902,0.00037932378,0.00008807948,0.0007598439],"category_scores_gemma":[0.0000052270334,0.00035993077,0.00012155009,0.000309864,0.000037747872,0.00087997405,0.0002508462,0.00063307694,0.00007272044],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001575939,0.0003840867,0.00017597713,0.000121721096,0.00010297072,0.000036424994,0.0024956262,0.00045109764,0.0047216527,0.00024295493,0.0013898106,0.9897201],"study_design_scores_gemma":[0.003990235,0.006352511,0.0009390613,0.00032920047,0.00006121812,0.00021009258,0.00054386473,0.9740889,0.0036066344,0.001870645,0.0069610556,0.0010466024],"about_ca_topic_score_codex":0.000023907158,"about_ca_topic_score_gemma":0.00004612466,"teacher_disagreement_score":0.9886735,"about_ca_system_score_codex":0.00010444117,"about_ca_system_score_gemma":0.000055550725,"threshold_uncertainty_score":0.99988526},"labels":[],"label_agreement":null},{"id":"W4312458841","doi":"10.1109/cvpr52688.2022.00359","title":"Modular Action Concept Grounding in Semantic Video Prediction","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Action (physics); Task (project management); Generalization; Object (grammar); Modular design; Machine learning; Minimum bounding box; Exploit; Bounding overwatch; Natural language processing; Image (mathematics)","score_opus":0.05111951061090442,"score_gpt":0.3018798975331176,"score_spread":0.2507603869222132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312458841","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4457001,0.00001646418,0.55085444,0.0014895365,0.001061418,0.0004132434,0.000041615567,0.00023827935,0.00018490637],"genre_scores_gemma":[0.9947589,0.00004581147,0.0030863148,0.0013774859,0.00021669427,0.00024138256,0.00018638327,0.000024261739,0.000062780215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969688,0.0006281324,0.0004915929,0.0009640662,0.00059385074,0.00035354044],"domain_scores_gemma":[0.9987961,0.00020591762,0.00024930545,0.000496368,0.00010399026,0.00014831773],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058939477,0.0002922155,0.0003096399,0.0005034421,0.0005888255,0.0003817811,0.00053912157,0.000090408896,0.0004758391],"category_scores_gemma":[0.000015318406,0.00031584903,0.00008311683,0.0005867538,0.000053085227,0.00059519673,0.00038023447,0.0008140736,0.00011886718],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034441637,0.0003406825,0.0030728711,0.000036791644,0.00002366758,0.000030577175,0.0013823676,0.0041390127,0.0039029708,0.0007703364,0.000811522,0.98545474],"study_design_scores_gemma":[0.0011092837,0.0006151628,0.05792396,0.000110704335,0.00001044194,0.00007306029,0.000116968804,0.93601334,0.00028096745,0.0025313024,0.0008512975,0.00036351412],"about_ca_topic_score_codex":0.00033304148,"about_ca_topic_score_gemma":0.000031713666,"teacher_disagreement_score":0.98509127,"about_ca_system_score_codex":0.00016018131,"about_ca_system_score_gemma":0.00004882285,"threshold_uncertainty_score":0.99992937},"labels":[],"label_agreement":null},{"id":"W4312465973","doi":"10.1109/cvpr52688.2022.00664","title":"MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Pose; Artificial intelligence; Monocular; Latency (audio); Bundle adjustment; Task (project management); Calibration; Task analysis; Computer vision; Machine learning; Pattern recognition (psychology); Mathematics; Engineering; Statistics","score_opus":0.06631774104697905,"score_gpt":0.2829277449719134,"score_spread":0.21661000392493437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312465973","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46788338,0.0001279752,0.522679,0.0014026964,0.0042644897,0.0009156461,0.0005680147,0.0005384357,0.0016204033],"genre_scores_gemma":[0.9787722,0.00031642368,0.011102136,0.0075381882,0.0006180986,0.0002077825,0.0010178217,0.000056641897,0.00037066787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952817,0.00089347316,0.0007950074,0.0014760781,0.0010071936,0.0005465673],"domain_scores_gemma":[0.9978908,0.00031133526,0.00038475604,0.00078485435,0.0002771069,0.0003512039],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005911012,0.00057803903,0.00066045945,0.00051196746,0.0010438024,0.00086122693,0.0008746639,0.00015313519,0.0057134884],"category_scores_gemma":[0.000015952453,0.00055188395,0.00022202285,0.00045895836,0.0000771329,0.0010582694,0.0007260622,0.0008617048,0.0010301793],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009368942,0.00049227074,0.0005288122,0.000031364336,0.000062034895,0.00006884119,0.0009902306,0.000048185204,0.0033488967,0.00004056714,0.004785977,0.9895091],"study_design_scores_gemma":[0.0052373456,0.0027577793,0.0066447123,0.0005289162,0.00010445676,0.00020463299,0.00035292498,0.9376348,0.0043294695,0.003344388,0.036921006,0.001939527],"about_ca_topic_score_codex":0.00016356782,"about_ca_topic_score_gemma":0.000096588665,"teacher_disagreement_score":0.98756963,"about_ca_system_score_codex":0.000094049145,"about_ca_system_score_gemma":0.000081224265,"threshold_uncertainty_score":0.99974763},"labels":[],"label_agreement":null},{"id":"W4312477916","doi":"10.1109/cvpr52688.2022.01404","title":"Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Consistency (knowledge bases); Computer science; Margin (machine learning); Code (set theory); Sample (material); Point (geometry); Momentum (technical analysis); Algorithm; Artificial intelligence; Machine learning; Chemistry; Mathematics; Programming language","score_opus":0.08498805987629938,"score_gpt":0.2888137516274756,"score_spread":0.2038256917511762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312477916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1739138,0.000052111973,0.82162315,0.001569651,0.00088573655,0.00052141276,0.00006577659,0.00028857775,0.0010798046],"genre_scores_gemma":[0.99206555,0.00012940647,0.0042473334,0.0029793645,0.00017719294,0.000070884686,0.000092221526,0.000033572243,0.00020447402],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99651134,0.00079975877,0.00045871155,0.0010411612,0.00070635736,0.0004826527],"domain_scores_gemma":[0.998508,0.00046643437,0.00032059464,0.00024562952,0.0001765747,0.00028276333],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007025251,0.00042958464,0.00048217905,0.00037735232,0.0014673602,0.001086807,0.0003312349,0.000116534815,0.0005033424],"category_scores_gemma":[0.000045476572,0.00042340852,0.00009370645,0.0004090649,0.00012960231,0.0006340934,0.00049643125,0.0011932806,0.000033181826],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030140032,0.00024951942,0.0022492367,0.00012317211,0.00017824995,0.0002171641,0.017132496,0.0014315934,0.00469628,0.0069677676,0.0012897793,0.96516335],"study_design_scores_gemma":[0.0053728037,0.003137539,0.011940526,0.0006451602,0.000054206037,0.00043436265,0.01272874,0.95008093,0.0007299056,0.010487576,0.00271878,0.0016694885],"about_ca_topic_score_codex":0.000040796884,"about_ca_topic_score_gemma":0.00001276526,"teacher_disagreement_score":0.9634938,"about_ca_system_score_codex":0.00015412769,"about_ca_system_score_gemma":0.00010416537,"threshold_uncertainty_score":0.9999502},"labels":[],"label_agreement":null},{"id":"W4312523916","doi":"10.1109/cvpr52688.2022.01509","title":"Multi-Modal Dynamic Graph Transformer for Visual Grounding","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Initialization; Transformer; Ground; Modal; Graph; Ground truth; Artificial intelligence; Data mining; Pattern recognition (psychology); Theoretical computer science; Voltage","score_opus":0.04175260766584023,"score_gpt":0.32924491239606796,"score_spread":0.28749230473022774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312523916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21552795,0.000016135615,0.78061014,0.0017803652,0.0008463611,0.00074828265,0.00012291654,0.00025482776,0.000093004564],"genre_scores_gemma":[0.9668524,0.00003987338,0.029860854,0.002097001,0.000106101914,0.0006090317,0.0002985841,0.000038262937,0.000097891396],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971735,0.00032397654,0.00048071126,0.0010469904,0.00050712656,0.00046773485],"domain_scores_gemma":[0.9987014,0.000310492,0.00021798928,0.00040436283,0.00015520351,0.00021053058],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00056501594,0.00036883628,0.00036532368,0.00043762394,0.0010395746,0.00044415373,0.000710237,0.00009134837,0.0004922473],"category_scores_gemma":[0.000010078155,0.00037496988,0.00018795134,0.00042339202,0.00006743616,0.00038934962,0.00020215657,0.00061742694,0.00010714824],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005950466,0.0004801673,0.00041736927,0.00005672762,0.000038759914,0.000009050889,0.0008136295,0.0003573734,0.0040874924,0.00055419677,0.00040180277,0.99272394],"study_design_scores_gemma":[0.0019495039,0.0011820605,0.008995846,0.00006698782,0.000019186537,0.00005783324,0.00007838245,0.983728,0.00020697287,0.0021597114,0.0010088645,0.00054666004],"about_ca_topic_score_codex":0.00010057065,"about_ca_topic_score_gemma":0.000035368615,"teacher_disagreement_score":0.99217725,"about_ca_system_score_codex":0.000087338834,"about_ca_system_score_gemma":0.000060911552,"threshold_uncertainty_score":0.99987024},"labels":[],"label_agreement":null},{"id":"W4312526008","doi":"10.1109/cvpr52688.2022.00888","title":"Few-shot Learning with Noisy Labels","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Machine learning; Transformer; Single shot; Pattern recognition (psychology); Engineering","score_opus":0.05155474951415761,"score_gpt":0.26713971540313314,"score_spread":0.21558496588897552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312526008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1586089,0.000050361,0.8297245,0.002733047,0.0013489551,0.00050302985,0.000032315194,0.00055881817,0.006440071],"genre_scores_gemma":[0.9862994,0.0000834176,0.0064118463,0.0056425617,0.00017192608,0.00010560865,0.00013077864,0.000040902894,0.0011135881],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964506,0.0007015993,0.00043926656,0.0010208624,0.00089261524,0.00049504824],"domain_scores_gemma":[0.9985073,0.000256383,0.00031159507,0.00043693086,0.00021186209,0.00027587832],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00065003557,0.00039502754,0.00040040273,0.00038662777,0.0010485837,0.0007645344,0.0006654842,0.00008142309,0.0019813662],"category_scores_gemma":[0.000013911732,0.00036489233,0.00009671592,0.0005752139,0.000081098064,0.0005631343,0.00045401853,0.001027507,0.0003369311],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001112817,0.00025601682,0.0009862018,0.000037121055,0.000049678663,0.00016459613,0.0020300183,0.0016720039,0.00090721285,0.0011520485,0.002501554,0.9901323],"study_design_scores_gemma":[0.0045945277,0.0059638685,0.0068201097,0.0003736034,0.00003907379,0.00049528456,0.00096385734,0.9189445,0.00068653544,0.0017383092,0.0576501,0.0017302291],"about_ca_topic_score_codex":0.000029575265,"about_ca_topic_score_gemma":0.000014982588,"teacher_disagreement_score":0.988402,"about_ca_system_score_codex":0.00006853503,"about_ca_system_score_gemma":0.00009865465,"threshold_uncertainty_score":0.9998803},"labels":[],"label_agreement":null},{"id":"W4312539501","doi":"10.1109/cvpr52688.2022.00255","title":"Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto; Sunnybrook Health Science Centre; McGill University","funders":"","keywords":"Computer science; Consistency (knowledge bases); Pixel; Transformer; Artificial intelligence; Class (philosophy); Observable; Image (mathematics); Computer vision; Machine learning; Pattern recognition (psychology); Engineering","score_opus":0.10548477742640627,"score_gpt":0.2952703571092695,"score_spread":0.18978557968286325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312539501","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058088206,0.000023457364,0.93698096,0.0019729096,0.0013680591,0.0006693134,0.00012097615,0.00021514998,0.0005609735],"genre_scores_gemma":[0.9778334,0.00010074644,0.0168899,0.0038349847,0.00013837358,0.000279121,0.0003299148,0.000032650118,0.0005609112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971761,0.00032886508,0.0005536934,0.0008753099,0.0006062655,0.00045976293],"domain_scores_gemma":[0.9988311,0.00014560475,0.00025366677,0.00030016134,0.00025048095,0.00021899388],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005613792,0.0003274949,0.00037047602,0.00026026537,0.0009778424,0.0005288567,0.0004840666,0.00009772162,0.00045299597],"category_scores_gemma":[0.000009421873,0.0003413361,0.00021363048,0.00026639,0.00007495761,0.00064756937,0.00017950918,0.0003981448,0.000062094565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001950121,0.0003639819,0.00035609645,0.00010633698,0.000074661584,0.000026668482,0.0017306304,0.01121573,0.004815534,0.0028221288,0.00311715,0.9751761],"study_design_scores_gemma":[0.0018364686,0.00083708204,0.00055780506,0.000088995446,0.000026960346,0.00003307797,0.0001644433,0.99089843,0.00020279123,0.0024844343,0.0024092824,0.00046022952],"about_ca_topic_score_codex":0.000020676773,"about_ca_topic_score_gemma":0.000038297494,"teacher_disagreement_score":0.9796827,"about_ca_system_score_codex":0.000070418464,"about_ca_system_score_gemma":0.00016247426,"threshold_uncertainty_score":0.99990386},"labels":[],"label_agreement":null},{"id":"W4312545381","doi":"10.1109/cvpr52688.2022.00312","title":"Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; Vector Institute","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Interpolation (computer graphics); Consistency (knowledge bases); Constraint (computer-aided design); Computer vision; Scale (ratio); Shadow (psychology); Generalization; Pixel; Pattern recognition (psychology); Image (mathematics); Mathematics","score_opus":0.07243037119685516,"score_gpt":0.2973142349716297,"score_spread":0.2248838637747745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312545381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12578516,0.000032910637,0.8691393,0.00092425407,0.0027309505,0.00036191623,0.000041138595,0.00030638283,0.0006779574],"genre_scores_gemma":[0.98529416,0.000035666995,0.011557031,0.0025133828,0.00025547453,0.00010444586,0.00015843322,0.000028145372,0.00005328415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996317,0.0009948974,0.000632855,0.000995373,0.0006452133,0.00041462673],"domain_scores_gemma":[0.99840087,0.00032649463,0.00037209666,0.0004921123,0.0002191635,0.00018924849],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012214091,0.0003718116,0.00044728082,0.0004619968,0.00078871805,0.0005167943,0.0005109917,0.00010966908,0.0007409012],"category_scores_gemma":[0.000025250229,0.00038367492,0.00015833467,0.00050896703,0.00007129676,0.0006988232,0.00032974881,0.00064559776,0.00009823842],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006524533,0.00011392331,0.0014459586,0.000027140502,0.000028727567,0.000037803165,0.0015560278,0.00004614043,0.0011365608,0.00013658343,0.00033445298,0.9950714],"study_design_scores_gemma":[0.0018731296,0.0024056295,0.013475487,0.00022421435,0.000025552283,0.0003567737,0.00028565887,0.96159077,0.0013408494,0.014546447,0.002874277,0.0010011939],"about_ca_topic_score_codex":0.00012744578,"about_ca_topic_score_gemma":0.00019099728,"teacher_disagreement_score":0.99407023,"about_ca_system_score_codex":0.00008069492,"about_ca_system_score_gemma":0.000088444,"threshold_uncertainty_score":0.99986154},"labels":[],"label_agreement":null},{"id":"W4312602363","doi":"10.1109/cvpr52688.2022.00129","title":"GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Huawei Technologies; Compute Canada; Automotive Research Center","keywords":"Computer science; Artificial intelligence; Robustness (evolution); Segmentation; Code (set theory); Image (mathematics); Unsupervised learning; Computer vision; Pattern recognition (psychology); Image segmentation; Artificial neural network; Set (abstract data type)","score_opus":0.03295431514156284,"score_gpt":0.25568719733899314,"score_spread":0.22273288219743032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312602363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09235118,0.000028749344,0.90165234,0.003743414,0.0011678303,0.00042631195,0.00006824591,0.00014217594,0.00041972395],"genre_scores_gemma":[0.96941,0.00009101624,0.018846057,0.010340129,0.0005087088,0.00017016842,0.00028856637,0.00003341846,0.0003119106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99660164,0.0009047272,0.00042628395,0.0010040187,0.000643487,0.0004198637],"domain_scores_gemma":[0.9988883,0.00013979424,0.00013689754,0.00036483625,0.0001714312,0.00029874145],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00053493923,0.0003434849,0.0003452433,0.00023777946,0.00088188774,0.00073307694,0.0005205447,0.0000686335,0.0015135687],"category_scores_gemma":[0.000014335094,0.0003366155,0.00010738223,0.00037258049,0.00004507062,0.0004338252,0.0005122558,0.0005637604,0.00018245839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004672541,0.00023100153,0.000069603615,0.000012166664,0.000030273472,0.000033654833,0.0010133177,0.0020626737,0.04036746,0.00006153762,0.035576258,0.92049533],"study_design_scores_gemma":[0.0009810686,0.0018177504,0.00034003067,0.00005518332,0.000013694456,0.00003079632,0.00010472515,0.9768371,0.0069630556,0.00026485435,0.011987268,0.0006044931],"about_ca_topic_score_codex":0.000032684475,"about_ca_topic_score_gemma":0.000008568589,"teacher_disagreement_score":0.9747744,"about_ca_system_score_codex":0.000076216646,"about_ca_system_score_gemma":0.000054134987,"threshold_uncertainty_score":0.99990857},"labels":[],"label_agreement":null},{"id":"W4312635677","doi":"10.1109/cvpr52688.2022.00509","title":"Generating Diverse and Natural 3D Human Motions from Text","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":485,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Motion (physics); Computer science; Representation (politics); Set (abstract data type); Artificial intelligence; Snippet; Sampling (signal processing); Computer vision; Space (punctuation); Text generation; Function (biology); Information retrieval; Programming language","score_opus":0.04597789898601981,"score_gpt":0.2749500740160118,"score_spread":0.22897217502999198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312635677","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8383657,0.000061372964,0.15788017,0.0007515218,0.0017529434,0.0003142041,0.00019842974,0.00024316019,0.00043253356],"genre_scores_gemma":[0.99061555,0.0000991587,0.0042949547,0.0038513,0.00039965624,0.00006733802,0.00043991837,0.000020038673,0.00021211087],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755216,0.00038250786,0.00040124464,0.000877152,0.00047771845,0.00030919202],"domain_scores_gemma":[0.99900854,0.000115234165,0.00021824807,0.00033136722,0.0001420786,0.00018453889],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024600085,0.0003114294,0.00030033258,0.0003120321,0.0014828154,0.0006725581,0.00036297415,0.00007535558,0.0017854108],"category_scores_gemma":[0.0000059971076,0.00031502632,0.00008858837,0.0002289924,0.0000824778,0.0006643599,0.0005150898,0.0005976959,0.00015816298],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001202773,0.00019926537,0.00026292467,0.000015954824,0.000038273432,0.000052919742,0.0010026572,0.000053776097,0.0051232073,0.0002215806,0.0037505557,0.9892669],"study_design_scores_gemma":[0.0031619896,0.0015979175,0.014450091,0.00027713913,0.00006330355,0.00018371236,0.00053269847,0.96665114,0.0014050634,0.0062835747,0.004009026,0.0013843419],"about_ca_topic_score_codex":0.00012927983,"about_ca_topic_score_gemma":0.00005360017,"teacher_disagreement_score":0.9878825,"about_ca_system_score_codex":0.00005070933,"about_ca_system_score_gemma":0.000031593427,"threshold_uncertainty_score":0.9999302},"labels":[],"label_agreement":null},{"id":"W4312683064","doi":"10.1109/cvpr52688.2022.00004","title":"Table of Contents","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Diverse Scientific and Economic Studies","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Automation, Chinese Academy of Sciences; Institute for Infocomm Research; University of Chinese Academy of Sciences; Skolkovo Institute of Science and Technology; Agency for Defense Development; Technische Universität München; Tsinghua University; Beijing Normal University; Yonsei University; Sun Yat-sen University; Chinese Academy of Sciences; City University of Hong Kong; Wayne State University; University of Technology Sydney; Beijing Institute of Technology; Hong Kong Baptist University; Johns Hopkins University; University of Sydney; University of Science and Technology of China; Nanyang Technological University; Hong Kong University of Science and Technology; University of Toronto; Seoul National University; Tencent; National University of Singapore; Chinese University of Hong Kong; Huazhong University of Science and Technology; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Institut national de recherche en informatique et en automatique (INRIA); Nvidia","keywords":"Table (database); Computer science; Database","score_opus":0.1016055954196378,"score_gpt":0.23909394363733671,"score_spread":0.1374883482176989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312683064","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78056353,0.00057812314,0.017486475,0.0015798112,0.014657477,0.00092199654,0.0077269473,0.00013719653,0.17634842],"genre_scores_gemma":[0.98726654,0.00026914442,0.00016048836,0.0013397338,0.000087221895,0.000044978726,0.000106664,0.000015631062,0.010709616],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985259,0.00004385925,0.0005374897,0.00056569575,0.00008821164,0.00023883345],"domain_scores_gemma":[0.9992016,0.000055166725,0.0003646565,0.00022925767,0.00006255291,0.00008675567],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00042150763,0.00017385955,0.00045387255,0.00026062437,0.00028964962,0.000105430496,0.00022242912,0.00004293583,0.024641352],"category_scores_gemma":[0.00000878148,0.00019515604,0.00009732908,0.00016492572,0.000084874555,0.00017638505,0.00023739619,0.00018602508,0.0019254545],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003262868,0.0013932318,0.02263099,0.00020754585,0.00042505842,0.00004505384,0.0033173817,0.00027700377,0.00038826512,0.014566779,0.59044933,0.36597306],"study_design_scores_gemma":[0.013080646,0.005149147,0.030755695,0.0004724999,0.000086958615,0.000090734786,0.004992314,0.22030514,0.0013615342,0.03830519,0.682058,0.0033421656],"about_ca_topic_score_codex":0.000114940325,"about_ca_topic_score_gemma":0.0000073484402,"teacher_disagreement_score":0.3626309,"about_ca_system_score_codex":0.000036086833,"about_ca_system_score_gemma":0.000011856436,"threshold_uncertainty_score":0.99885166},"labels":[],"label_agreement":null},{"id":"W4312709677","doi":"10.1109/cvpr52688.2022.01005","title":"Exploiting Explainable Metrics for Augmented SGD","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of New Brunswick","funders":"","keywords":"Computer science; Stochastic gradient descent; Generalization; Exploit; Artificial intelligence; Machine learning; Overhead (engineering); Deep learning; Learning to rank; Artificial neural network; Measure (data warehouse); Rank (graph theory); Layer (electronics); Deep neural networks; Network architecture; Data mining; Ranking (information retrieval); Mathematics","score_opus":0.07788462505945132,"score_gpt":0.3020840148417718,"score_spread":0.22419938978232046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312709677","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028539399,0.000045759494,0.9665362,0.0020761949,0.0010368332,0.00088400266,0.0001137072,0.00031440542,0.0004534674],"genre_scores_gemma":[0.94285035,0.00019251907,0.047233716,0.006981296,0.00038450278,0.0015074436,0.0003411709,0.000054576172,0.00045445043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730563,0.00022464454,0.0004767408,0.0009838148,0.0005207269,0.0004884206],"domain_scores_gemma":[0.9982078,0.000526542,0.0002984195,0.00053025445,0.00023547989,0.00020148222],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004316493,0.00031598267,0.00033682532,0.00039082498,0.0010603302,0.00036145383,0.0007419902,0.00006183607,0.00029335884],"category_scores_gemma":[0.000019474064,0.0003294998,0.00011862029,0.0008286324,0.000042049334,0.00055031985,0.0005833844,0.00040768602,0.00006702144],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041186442,0.00022750576,0.00006208444,0.000037561207,0.000021328218,0.000018679077,0.00027821286,0.0005979648,0.00096702384,0.0024144473,0.009816179,0.9855178],"study_design_scores_gemma":[0.0017810981,0.0015174695,0.00021581679,0.000100620746,0.00001977992,0.000081546656,0.00021334784,0.9536358,0.0021881335,0.014293135,0.025221402,0.0007318366],"about_ca_topic_score_codex":0.000008870848,"about_ca_topic_score_gemma":0.0000043081163,"teacher_disagreement_score":0.984786,"about_ca_system_score_codex":0.00009844797,"about_ca_system_score_gemma":0.00004777456,"threshold_uncertainty_score":0.9999157},"labels":[],"label_agreement":null},{"id":"W4312717468","doi":"10.1109/cvpr52688.2022.01145","title":"GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Adjacency list; CAD; Adjacency matrix; Graph; Vertex (graph theory); Theoretical computer science; Symbol (formal); Spotting; Raster graphics; Artificial intelligence; Pattern recognition (psychology); Algorithm; Engineering drawing","score_opus":0.03216264739353678,"score_gpt":0.27145013738135443,"score_spread":0.23928748998781765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312717468","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2696314,0.000047758167,0.7249325,0.0012984119,0.0015063292,0.0012876043,0.000115967334,0.0004934867,0.0006865587],"genre_scores_gemma":[0.9784631,0.00014586703,0.01638052,0.003464575,0.000342208,0.00076775585,0.0002599268,0.0000500983,0.00012591999],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99588764,0.0005517519,0.00083906023,0.0012395435,0.000762445,0.00071956095],"domain_scores_gemma":[0.9981733,0.0003809273,0.00040575562,0.0004905299,0.00033249945,0.00021696914],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001491928,0.0004654638,0.0005607063,0.0006763001,0.0007311678,0.0006018544,0.0007668111,0.00015880517,0.00040196723],"category_scores_gemma":[0.000025894476,0.0004995126,0.0002237671,0.00079506764,0.00007337367,0.00066489447,0.0004662261,0.0007143771,0.00007364344],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007329542,0.00029635915,0.0018037725,0.00010220547,0.000033074084,0.00004803425,0.0006079914,0.000096921234,0.0018437332,0.00055350334,0.0043658805,0.99017525],"study_design_scores_gemma":[0.007832041,0.006859628,0.028833518,0.0024817162,0.00010461338,0.00048739664,0.0006751769,0.8581124,0.004506378,0.08123181,0.0053159897,0.0035593228],"about_ca_topic_score_codex":0.000079833444,"about_ca_topic_score_gemma":0.000053325577,"teacher_disagreement_score":0.9866159,"about_ca_system_score_codex":0.00014305266,"about_ca_system_score_gemma":0.00010055488,"threshold_uncertainty_score":0.99974567},"labels":[],"label_agreement":null},{"id":"W4312723735","doi":"10.1109/cvpr52688.2022.01354","title":"TubeFormer-DeepLab: Video Mask Transformer","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Segmentation; Transformer; Task (project management); Artificial intelligence; Image segmentation; Computer vision; Natural language processing; Pattern recognition (psychology)","score_opus":0.037876617348983455,"score_gpt":0.27413317807829907,"score_spread":0.2362565607293156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312723735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07226875,0.000050308503,0.91748595,0.005715551,0.0014018123,0.0007331025,0.00013487751,0.00041559397,0.0017940763],"genre_scores_gemma":[0.9809313,0.00028711825,0.008234154,0.00923211,0.00028172863,0.0004318372,0.00018048007,0.000044552726,0.00037671713],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99687076,0.00026392462,0.0005464228,0.0010986386,0.0006883189,0.00053196494],"domain_scores_gemma":[0.99850327,0.00021068098,0.00020973268,0.0006648071,0.00013531317,0.0002761781],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000312025,0.00040607413,0.00038706194,0.0003026627,0.0008492902,0.00033119597,0.00090291724,0.00008647839,0.001106327],"category_scores_gemma":[0.0000041760054,0.0003921844,0.00014455595,0.0006469087,0.00008306202,0.00069978414,0.00031150633,0.0006989651,0.00038580294],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041669122,0.00021059849,0.0000824052,0.00002162844,0.000022149925,0.000031089625,0.0004492615,0.00026034968,0.0015234541,0.0013994939,0.0055971257,0.9903608],"study_design_scores_gemma":[0.004267851,0.0042152302,0.0027819104,0.00026794273,0.00005895414,0.0006723507,0.00025251924,0.85415184,0.0059830504,0.03436048,0.090539806,0.0024480885],"about_ca_topic_score_codex":0.000016395968,"about_ca_topic_score_gemma":0.00001718959,"teacher_disagreement_score":0.9879127,"about_ca_system_score_codex":0.0000818034,"about_ca_system_score_gemma":0.000060367078,"threshold_uncertainty_score":0.999853},"labels":[],"label_agreement":null},{"id":"W4312725636","doi":"10.1109/cvpr52688.2022.01037","title":"Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Leverage (statistics); Computer science; Generative grammar; Artificial intelligence; Image translation; Segmentation; Image (mathematics); Domain (mathematical analysis); Translation (biology); Pattern recognition (psychology); Generative model; Computer vision; Mathematics; Biology","score_opus":0.052366632458381364,"score_gpt":0.26766020803597096,"score_spread":0.2152935755775896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312725636","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1814879,0.0000467398,0.8143302,0.0020484908,0.001006138,0.00042936328,0.00025656683,0.00019098895,0.00020356674],"genre_scores_gemma":[0.9692677,0.000075195356,0.02539579,0.004216788,0.00045410843,0.00012995163,0.00024844153,0.00004111058,0.00017088692],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961485,0.0007432304,0.0005046657,0.001227938,0.0007342643,0.0006413815],"domain_scores_gemma":[0.9982407,0.0003383979,0.00032538455,0.0006120861,0.00022460401,0.00025882502],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0005908732,0.00048445055,0.00050842133,0.00018565959,0.0015146445,0.0009793005,0.00072138355,0.00009264168,0.0005976573],"category_scores_gemma":[0.000017377512,0.0004238679,0.00013413395,0.00044572295,0.00012120967,0.0005816547,0.00055534893,0.00040553382,0.000074974785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019665206,0.00036902845,0.0010293295,0.000032638396,0.00011596065,0.00018531272,0.0020114456,0.0074663702,0.015100801,0.00019381147,0.004976901,0.96832174],"study_design_scores_gemma":[0.0031313475,0.0022158644,0.0017623937,0.00016787252,0.000028661594,0.00019976452,0.0005216205,0.9782516,0.0075719315,0.00090926,0.0041154907,0.0011242394],"about_ca_topic_score_codex":0.00018239599,"about_ca_topic_score_gemma":0.00015340078,"teacher_disagreement_score":0.9707852,"about_ca_system_score_codex":0.00006521931,"about_ca_system_score_gemma":0.00008462252,"threshold_uncertainty_score":0.9998213},"labels":[],"label_agreement":null},{"id":"W4312731878","doi":"10.1109/cvpr52688.2022.00862","title":"HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":391,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Artificial intelligence; Invariant (physics); Transformer; Benchmark (surveying); Machine learning; Mathematics; Engineering","score_opus":0.044621562810097604,"score_gpt":0.2561934175399021,"score_spread":0.2115718547298045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312731878","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.269761,0.00003170818,0.72609264,0.0006194627,0.0014557544,0.000628192,0.0006451871,0.00055639277,0.00020969582],"genre_scores_gemma":[0.9967629,0.00014441328,0.0014377905,0.00052253134,0.00015831934,0.0003284208,0.0005319137,0.000038285558,0.000075424156],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986094,0.00009982035,0.00036042277,0.00042442602,0.00021238082,0.00029353987],"domain_scores_gemma":[0.99953854,0.000068949856,0.00005624701,0.00017547153,0.000054917247,0.00010585265],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023689854,0.00024896793,0.0002609804,0.00021117003,0.00039292302,0.00005356629,0.00015230868,0.00015358752,0.00081614614],"category_scores_gemma":[0.000003049621,0.00025660993,0.00011007703,0.00012542767,0.00005373205,0.00014191472,0.00003587027,0.0005646557,0.000056531586],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105506595,0.00021232282,0.00023196885,0.000086629705,0.000055066055,0.000008868852,0.00040632405,0.0011789089,0.0029338521,0.00014402995,0.0019217371,0.99271476],"study_design_scores_gemma":[0.00199442,0.0010512769,0.006957222,0.000063787724,0.000033701537,0.00004482615,0.00007370546,0.9810554,0.0022902444,0.0006375902,0.0054193814,0.000378462],"about_ca_topic_score_codex":0.0000047831777,"about_ca_topic_score_gemma":0.000010303985,"teacher_disagreement_score":0.99233633,"about_ca_system_score_codex":0.00008882249,"about_ca_system_score_gemma":0.000018434965,"threshold_uncertainty_score":0.9999886},"labels":[],"label_agreement":null},{"id":"W4312757006","doi":"10.1109/cvpr52688.2022.01940","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Arkansas Biosciences Institute","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Action recognition; Transformer; Machine learning","score_opus":0.08637720170306316,"score_gpt":0.27890917139729915,"score_spread":0.19253196969423597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312757006","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47243878,0.000018472037,0.5177229,0.0013105726,0.001879647,0.0012425777,0.00020580927,0.00055415824,0.004627059],"genre_scores_gemma":[0.98692244,0.00022970921,0.006671094,0.0037207783,0.00029895946,0.0007624157,0.0010555637,0.000050627863,0.00028842446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959142,0.00064549904,0.0007572369,0.0012967167,0.0008113824,0.000574954],"domain_scores_gemma":[0.998678,0.000117772695,0.000268478,0.00039911986,0.00024164825,0.00029496438],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00071827293,0.00047573223,0.00049118,0.0011684997,0.0006885454,0.00053181214,0.00047117876,0.00015680926,0.00095237116],"category_scores_gemma":[0.00001160445,0.00049939565,0.00018137503,0.0011121313,0.00004412369,0.0012074704,0.00015943572,0.00080170564,0.00040642344],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015111991,0.0008684178,0.0001658899,0.00006783943,0.000030759875,0.000020491234,0.0008245056,0.00017140791,0.0023508118,0.00006982336,0.002914103,0.9923648],"study_design_scores_gemma":[0.009096718,0.005524878,0.034110095,0.0010838965,0.00011851232,0.00066416647,0.0014131744,0.91854846,0.005725638,0.008538726,0.011398716,0.003776995],"about_ca_topic_score_codex":0.00008795592,"about_ca_topic_score_gemma":0.00011230533,"teacher_disagreement_score":0.98858786,"about_ca_system_score_codex":0.00021066253,"about_ca_system_score_gemma":0.0000691587,"threshold_uncertainty_score":0.9999609},"labels":[],"label_agreement":null},{"id":"W4312772600","doi":"10.1109/cvpr52688.2022.00951","title":"Anomaly Detection via Reverse Distillation from One-Class Embedding","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":732,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Embedding; Computer science; Distillation; Anomaly detection; Class (philosophy); Bottleneck; Generalizability theory; Simple (philosophy); Anomaly (physics); Artificial intelligence; Representation (politics); Heuristics; Encoder; Benchmark (surveying); Machine learning; Mathematics","score_opus":0.03558917404709445,"score_gpt":0.267354595315034,"score_spread":0.2317654212679396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312772600","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14942788,0.000013687839,0.847443,0.00085259083,0.0007759631,0.0004115614,0.00010208606,0.00044297503,0.00053029787],"genre_scores_gemma":[0.98852277,0.00006531848,0.008713028,0.0019117895,0.000249353,0.00022836837,0.00015466906,0.000025410298,0.00012926637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974336,0.00030334241,0.00048147058,0.0009592974,0.0005263946,0.00029590057],"domain_scores_gemma":[0.99863636,0.00014205351,0.00033179845,0.0005527925,0.0001638906,0.00017307897],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031010207,0.00030174942,0.00030565055,0.00031973675,0.0009070916,0.00040784825,0.00047767677,0.00011185773,0.00095615286],"category_scores_gemma":[0.000005139078,0.00033051585,0.00012633615,0.00048642044,0.00005068892,0.0005231527,0.00039106765,0.00050446356,0.00017341999],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003611946,0.00017029738,0.00016501291,0.000012198975,0.000024070712,0.000010071244,0.00023605581,0.000096791075,0.008588663,0.00024082785,0.000791359,0.98962855],"study_design_scores_gemma":[0.0008242492,0.0011367884,0.005278611,0.00008993761,0.000030564006,0.00006605428,0.0000804283,0.9667654,0.0074676434,0.00881765,0.008729978,0.0007127212],"about_ca_topic_score_codex":0.00022035858,"about_ca_topic_score_gemma":0.000048130794,"teacher_disagreement_score":0.9889158,"about_ca_system_score_codex":0.00013078253,"about_ca_system_score_gemma":0.000034844958,"threshold_uncertainty_score":0.9999571},"labels":[],"label_agreement":null},{"id":"W4312804251","doi":"10.1109/cvpr52688.2022.00445","title":"Sparse Non-local CRF","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Enhanced Data Rates for GSM Evolution; Minimum bounding box; Gaussian; Pattern recognition (psychology); Segmentation; Flexibility (engineering); Sparse approximation; Bounding overwatch; Pixel; Salient; Boundary (topology); Algorithm; Mathematics; Image (mathematics)","score_opus":0.04541062104570697,"score_gpt":0.2828704253041557,"score_spread":0.2374598042584487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312804251","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1608314,0.000015747393,0.8320169,0.0016696077,0.0032376144,0.00036060528,0.0000453285,0.0002894538,0.0015333283],"genre_scores_gemma":[0.9922389,0.0000785716,0.0012640912,0.005542423,0.00020875833,0.00011308341,0.00008168335,0.000024111067,0.00044841532],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99683553,0.00045613621,0.00050098303,0.0009970581,0.000781871,0.00042844273],"domain_scores_gemma":[0.9987683,0.00009083175,0.00022067272,0.0004909354,0.00016776835,0.00026145417],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044419046,0.00035162666,0.00035594846,0.00040797584,0.00077759783,0.00048330767,0.00065535447,0.00009662128,0.0019047732],"category_scores_gemma":[0.000005228887,0.00034649932,0.00015976396,0.00051830994,0.000088009605,0.00051339157,0.0005355114,0.0006117282,0.00060972077],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047901583,0.0003534793,0.00017243394,0.000025346215,0.000021535596,0.00006976559,0.00052411325,0.00014272802,0.0011302889,0.00045057692,0.0067067123,0.99035513],"study_design_scores_gemma":[0.0020550103,0.0032656763,0.005652477,0.00013303226,0.000020280542,0.00028812943,0.00027388378,0.973057,0.0017939714,0.0032337438,0.009314364,0.00091243646],"about_ca_topic_score_codex":0.000051751034,"about_ca_topic_score_gemma":0.000020393787,"teacher_disagreement_score":0.9894427,"about_ca_system_score_codex":0.000082350445,"about_ca_system_score_gemma":0.000067756104,"threshold_uncertainty_score":0.9998987},"labels":[],"label_agreement":null},{"id":"W4312810855","doi":"10.1109/cvpr52688.2022.00878","title":"Styleformer: Transformer based Generative Adversarial Networks with Style Vector","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Tellabs (Canada)","funders":"","keywords":"Computer science; Transformer; Normalization (sociology); Artificial intelligence; Visualization; Computation; Generative grammar; Generator (circuit theory); Computer vision; Algorithm; Voltage; Engineering","score_opus":0.02206577613607771,"score_gpt":0.22939547177485983,"score_spread":0.20732969563878212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312810855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011800151,0.00003375915,0.98264134,0.002040839,0.0016541171,0.0006211856,0.00011694571,0.00015103864,0.0009405969],"genre_scores_gemma":[0.9797281,0.00006538083,0.013628982,0.005422028,0.0005966886,0.00018220587,0.00020425224,0.000037701266,0.00013467904],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965936,0.0006552937,0.00044659473,0.0010542927,0.0007039409,0.00054629706],"domain_scores_gemma":[0.9986021,0.00020873165,0.00023732871,0.00046001488,0.00022947676,0.0002623505],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044146273,0.00048920035,0.000494328,0.0002505191,0.00092920894,0.000536857,0.0005896824,0.0001021668,0.0016380938],"category_scores_gemma":[0.000004563527,0.00040596374,0.00015613137,0.00048028983,0.00010709272,0.0006431531,0.00015556412,0.0006141385,0.000048216833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004992442,0.0005063318,0.00013836284,0.0000266685,0.00014685038,0.00010459312,0.0008638235,0.035335455,0.0011835792,0.00031776744,0.008113623,0.9527637],"study_design_scores_gemma":[0.0024835593,0.0028759176,0.0006112108,0.0000900457,0.000035866982,0.000035051035,0.00009272334,0.98698145,0.0016778437,0.00014236549,0.0042863055,0.0006876557],"about_ca_topic_score_codex":0.00005564231,"about_ca_topic_score_gemma":0.00005689905,"teacher_disagreement_score":0.9690124,"about_ca_system_score_codex":0.00008837998,"about_ca_system_score_gemma":0.00014591988,"threshold_uncertainty_score":0.99983925},"labels":[],"label_agreement":null},{"id":"W4312899461","doi":"10.1109/cvpr52688.2022.01806","title":"UNIST: Unpaired Neural Implicit Shape Translation Network","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Translation (biology); Generality; Artificial intelligence; Representation (politics); Artificial neural network; Machine translation; Code (set theory); Domain (mathematical analysis); Natural language processing; Position (finance); Grid; Point (geometry); Pattern recognition (psychology); Geometry; Programming language; Mathematics","score_opus":0.046694095253511876,"score_gpt":0.24576656450399953,"score_spread":0.19907246925048766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312899461","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6552131,0.00020857141,0.33938766,0.0009812203,0.0016825222,0.00034229262,0.00022087814,0.0006531983,0.0013105583],"genre_scores_gemma":[0.9971733,0.0001729428,0.00050393195,0.0011911055,0.00034337663,0.000051255396,0.0004635151,0.000043258537,0.000057333487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983062,0.00017658126,0.0003918557,0.00044405516,0.00034522405,0.00033607715],"domain_scores_gemma":[0.9994189,0.000086907814,0.00007316391,0.00021679216,0.0000652561,0.00013895679],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023712525,0.00029028306,0.0003328471,0.00019089544,0.00040664495,0.00018010773,0.00018360827,0.000077869096,0.0019060347],"category_scores_gemma":[0.0000014062861,0.00030198172,0.00014097035,0.00031471456,0.000025250418,0.00014117117,0.000056785575,0.0004494181,0.000073684074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031298172,0.00004914721,0.0001679382,0.00003810316,0.00005064167,0.000018068127,0.00023503437,0.09366774,0.0005019415,0.000009443331,0.0032421595,0.9019885],"study_design_scores_gemma":[0.0005988038,0.00027735284,0.00055782223,0.00007096269,0.000042597512,0.000022754088,0.000045068155,0.99632776,0.00006030171,0.00062306394,0.00099809,0.0003754217],"about_ca_topic_score_codex":0.00001955506,"about_ca_topic_score_gemma":0.000020231675,"teacher_disagreement_score":0.90266,"about_ca_system_score_codex":0.00004084122,"about_ca_system_score_gemma":0.000014302172,"threshold_uncertainty_score":0.99994326},"labels":[],"label_agreement":null},{"id":"W4312906857","doi":"10.1109/cvpr52688.2022.01361","title":"A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University; Vector Institute; York University","funders":"York University","keywords":"Computer science; Representation (politics); ENCODE; Artificial intelligence; Segmentation; Action (physics); Object (grammar); Code (set theory); Dynamic programming; Key (lock); Machine learning; Computer vision; Pattern recognition (psychology); Algorithm; Programming language","score_opus":0.03171531342754412,"score_gpt":0.2764183902390483,"score_spread":0.24470307681150416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312906857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13468987,0.000052146184,0.85981566,0.0018567746,0.0025964777,0.0005475755,0.000033535463,0.0002595673,0.00014838124],"genre_scores_gemma":[0.98418754,0.0006142706,0.0046643517,0.009306882,0.00014230133,0.00018222656,0.0008409816,0.00002537986,0.00003604186],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967609,0.00053341215,0.0007470748,0.00073104765,0.00077409775,0.00045343649],"domain_scores_gemma":[0.998336,0.00020138333,0.00047866628,0.00044245776,0.00030944275,0.00023204043],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005740874,0.00041654558,0.00041071695,0.0005843842,0.001049154,0.0018926271,0.0005632229,0.00012744118,0.0011385919],"category_scores_gemma":[0.000011727266,0.0004231337,0.00014139414,0.0004832409,0.00006848735,0.004169824,0.0004730362,0.0007263793,0.00034970438],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006488046,0.00015428176,0.00013348965,0.00006187643,0.00003431235,0.0000270493,0.0026546386,0.0011403076,0.00004643824,0.00020253992,0.0011664178,0.9943138],"study_design_scores_gemma":[0.0012093369,0.0010867107,0.0014659587,0.00026748868,0.00002307645,0.0000777196,0.00072553154,0.98847073,0.00012215412,0.0041051605,0.0018110585,0.0006350805],"about_ca_topic_score_codex":0.000072309434,"about_ca_topic_score_gemma":0.000106634434,"teacher_disagreement_score":0.9936787,"about_ca_system_score_codex":0.00014996224,"about_ca_system_score_gemma":0.000078135075,"threshold_uncertainty_score":0.999822},"labels":[],"label_agreement":null},{"id":"W4312906868","doi":"10.1109/cvpr52688.2022.01147","title":"CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"CAD; Computer science; Constructive solid geometry; Artificial neural network; Artificial intelligence; Parametric statistics; Net (polyhedron); Solid modeling; Interpretability; Constructive; Computer Aided Design; Generalizability theory; Ground truth; Topology (electrical circuits); Algorithm; Machine learning; Geometry; Engineering drawing; Mathematics","score_opus":0.03519507238058299,"score_gpt":0.23895416711399733,"score_spread":0.20375909473341436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312906868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6895164,0.00008321154,0.30618545,0.00026501523,0.00031630075,0.00025736282,0.00015819623,0.00039859515,0.0028194531],"genre_scores_gemma":[0.9983147,0.00014338028,0.00037613665,0.0005525044,0.0001416583,0.00003966086,0.00020705047,0.000052899777,0.00017200083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980766,0.00024911176,0.00031975572,0.00053089485,0.00047400582,0.00034962173],"domain_scores_gemma":[0.999289,0.00013600849,0.000113995266,0.00015061622,0.00014126304,0.00016913562],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023460548,0.0003641569,0.0004406294,0.00029137207,0.00044827652,0.00020230992,0.00018051437,0.00007329455,0.0010401864],"category_scores_gemma":[0.0000036720578,0.0003336399,0.000108332824,0.00026008138,0.000043936183,0.00017805235,0.000070938564,0.00080868806,0.00010022587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021078625,0.00023149028,0.0010407366,0.00008913394,0.0003993927,0.0001487303,0.0022422816,0.28104782,0.0020784147,0.00002942443,0.003053112,0.70942867],"study_design_scores_gemma":[0.00083589804,0.001102361,0.0017674781,0.00021594814,0.00006631696,0.00004277392,0.0005866195,0.993828,0.00041327893,0.000078601595,0.00053350924,0.00052921363],"about_ca_topic_score_codex":0.00007854153,"about_ca_topic_score_gemma":0.000043523392,"teacher_disagreement_score":0.7127802,"about_ca_system_score_codex":0.00008175056,"about_ca_system_score_gemma":0.000033967935,"threshold_uncertainty_score":0.99991155},"labels":[],"label_agreement":null},{"id":"W4312999101","doi":"10.1109/cvpr52688.2022.01694","title":"Modeling sRGB Camera Noise with Normalizing Flows","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; York University","funders":"","keywords":"Computer science; RGB color model; Noise (video); Artificial intelligence; Computer vision; Noise reduction; Dark-frame subtraction; Noise measurement; Image noise; Image sensor; Image (mathematics); Image processing; Median filter","score_opus":0.05232009435441503,"score_gpt":0.2808313286522276,"score_spread":0.22851123429781256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312999101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17194737,0.000055208668,0.82492334,0.0008893505,0.0009519245,0.0002738324,0.0000313079,0.00020230435,0.000725326],"genre_scores_gemma":[0.94477785,0.000084527564,0.047959138,0.0065746615,0.00025391244,0.000087556225,0.00007540453,0.00003911207,0.00014784368],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966258,0.00065790926,0.00046051663,0.00097595155,0.00079052843,0.0004893136],"domain_scores_gemma":[0.99865824,0.00015286848,0.00016320315,0.0005533758,0.0002423813,0.00022990322],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078296365,0.00039482053,0.00042822142,0.00037820116,0.0008522646,0.0007529454,0.00072063354,0.0000733914,0.000502139],"category_scores_gemma":[0.000007235757,0.00035287117,0.000111068875,0.00045818285,0.000043863813,0.0007130777,0.0005003018,0.0006858334,0.00010084194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001602522,0.00021578593,0.00009023429,0.0000458068,0.000040484112,0.0002678384,0.0013289418,0.009406931,0.0025238635,0.00018500697,0.0011113448,0.9846235],"study_design_scores_gemma":[0.001513212,0.0011685166,0.00010784032,0.00017244022,0.000019274352,0.0002487586,0.00009854657,0.9935282,0.00071729714,0.001071324,0.0007826729,0.0005719206],"about_ca_topic_score_codex":0.00012803325,"about_ca_topic_score_gemma":0.000020346472,"teacher_disagreement_score":0.98412126,"about_ca_system_score_codex":0.00006252555,"about_ca_system_score_gemma":0.000100906494,"threshold_uncertainty_score":0.99989235},"labels":[],"label_agreement":null},{"id":"W4313007980","doi":"10.1109/cvpr52688.2022.01273","title":"AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Pose; Artificial intelligence; Estimator; Motion capture; 3D pose estimation; Generalization; Computer vision; Machine learning; Orientation (vector space); Pattern recognition (psychology); Motion (physics); Mathematics","score_opus":0.08461681226342394,"score_gpt":0.3228882606346563,"score_spread":0.23827144837123237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313007980","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0875335,0.00002651499,0.9072632,0.0008258534,0.0015100574,0.0008513646,0.0016058929,0.00022606093,0.00015753882],"genre_scores_gemma":[0.9570056,0.000065588654,0.013704624,0.0033122108,0.0005324951,0.0005239879,0.024382064,0.00004607097,0.00042736094],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99684715,0.0004184733,0.0006488537,0.0010291921,0.0006626789,0.0003936715],"domain_scores_gemma":[0.9985282,0.00011316565,0.00042861112,0.0004220376,0.00032831132,0.00017970162],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000697552,0.00037308747,0.0003277889,0.00038573274,0.0016544372,0.0010916631,0.0004025289,0.00013107313,0.0010888376],"category_scores_gemma":[0.000015612737,0.0004079641,0.00011034223,0.00029523703,0.00005580807,0.0015142864,0.00018658345,0.00041635658,0.00015624853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005652629,0.00038303356,0.000027237787,0.000050464118,0.000028305481,0.000007969624,0.0003700252,0.002103086,0.0075750784,0.0003694369,0.051474575,0.93755424],"study_design_scores_gemma":[0.0018095587,0.0017996804,0.00025179287,0.000057744506,0.0000258156,0.000047018715,0.000052388732,0.9826696,0.0029579038,0.0023488244,0.0074351975,0.00054445356],"about_ca_topic_score_codex":0.00006732942,"about_ca_topic_score_gemma":0.000030046194,"teacher_disagreement_score":0.98056656,"about_ca_system_score_codex":0.00013120861,"about_ca_system_score_gemma":0.000058587622,"threshold_uncertainty_score":0.9999453},"labels":[],"label_agreement":null},{"id":"W4313013512","doi":"10.1109/cvpr52688.2022.00716","title":"Part-based Pseudo Label Refinement for Unsupervised Person Re-identification","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":278,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Discriminative model; Computer science; Artificial intelligence; Smoothing; Context (archaeology); Cluster analysis; Similarity (geometry); Noise (video); Exploit; Machine learning; Pattern recognition (psychology); Feature (linguistics); Identification (biology); Code (set theory); Source code; Feature learning; Task (project management); Data mining; Image (mathematics)","score_opus":0.13511414583861167,"score_gpt":0.3274952700900095,"score_spread":0.19238112425139783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313013512","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07965615,0.000045479104,0.9099608,0.006020615,0.0026782937,0.0007979684,0.00024322887,0.00028034693,0.0003171322],"genre_scores_gemma":[0.9566188,0.000087160275,0.03319826,0.008010814,0.00036862734,0.00068859244,0.0006625543,0.000046874316,0.00031836057],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965976,0.00070313155,0.0005387986,0.0010861781,0.0006517505,0.00042255633],"domain_scores_gemma":[0.9981435,0.0004028693,0.00031699103,0.0006714729,0.0002954255,0.00016974652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015183117,0.00034150115,0.00038976184,0.00032114916,0.0007749685,0.0005537642,0.00066078315,0.00008794845,0.00064858637],"category_scores_gemma":[0.000025401798,0.0003422551,0.00014717216,0.0003973841,0.00004786167,0.00032319513,0.0001690612,0.000358567,0.00007245215],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010488339,0.0004020462,0.00030866763,0.000089865876,0.000033304168,0.000016780301,0.00047929748,0.00017095103,0.0022697877,0.00032352368,0.010646743,0.98515415],"study_design_scores_gemma":[0.0045312312,0.0026423638,0.0042206626,0.00023953401,0.00003773866,0.000026912447,0.00020415468,0.96629506,0.0041876086,0.002377238,0.014269674,0.00096780766],"about_ca_topic_score_codex":0.000028675922,"about_ca_topic_score_gemma":0.000023886081,"teacher_disagreement_score":0.98418635,"about_ca_system_score_codex":0.00008052568,"about_ca_system_score_gemma":0.000098662254,"threshold_uncertainty_score":0.99990296},"labels":[],"label_agreement":null},{"id":"W4313018251","doi":"10.1109/cvpr52688.2022.01668","title":"A Versatile Multi-View Framework for LiDAR-based 3D Object Detection with Guidance from Panoptic Segmentation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Lidar; Computer science; Object detection; Panopticon; Segmentation; Computer vision; Artificial intelligence; Object (grammar); Image segmentation; Remote sensing; Geography","score_opus":0.04952368373759086,"score_gpt":0.29843731774443555,"score_spread":0.2489136340068447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313018251","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048330646,0.000052863204,0.9486059,0.0006658236,0.00070734555,0.0011575979,0.00019372262,0.00026055225,0.00002555233],"genre_scores_gemma":[0.7279787,0.00004856852,0.26711783,0.0032466345,0.00015822196,0.0011388405,0.00025550497,0.00003357294,0.000022127197],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974461,0.00029176704,0.00041645882,0.0010278462,0.0004718552,0.00034598267],"domain_scores_gemma":[0.99812394,0.00061550934,0.0003636483,0.0005469312,0.00020082833,0.00014911778],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002172045,0.0003442686,0.0003302723,0.0001843238,0.0007383413,0.00031582222,0.0004792095,0.00008459975,0.00022848119],"category_scores_gemma":[0.000013212906,0.00033082283,0.00008914299,0.00050355075,0.000057066707,0.00040913944,0.00016644686,0.00043214523,0.00005332472],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016033632,0.00026206413,0.00015219879,0.00004185841,0.000031147356,0.000010422941,0.00035758558,0.002670792,0.0033880628,0.00012290802,0.0001940461,0.9926086],"study_design_scores_gemma":[0.0022757978,0.00211368,0.0015401145,0.00030753348,0.00003877502,0.000018130453,0.000076976474,0.9805018,0.0073394002,0.003886419,0.0012768748,0.00062450685],"about_ca_topic_score_codex":0.000029359071,"about_ca_topic_score_gemma":0.0000498919,"teacher_disagreement_score":0.99198407,"about_ca_system_score_codex":0.00011867953,"about_ca_system_score_gemma":0.00007238058,"threshold_uncertainty_score":0.9999144},"labels":[],"label_agreement":null},{"id":"W4313034350","doi":"10.1109/cvpr52688.2022.01155","title":"Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Reverse engineering; Point cloud; Computer science; CAD; Extrusion; Software; Computer Aided Design; Point (geometry); Sketch; Cylinder; Engineering drawing; Artificial intelligence; Algorithm; Geometry; Mathematics; Programming language; Engineering","score_opus":0.024242445103602125,"score_gpt":0.2247384180681203,"score_spread":0.20049597296451818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313034350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60284734,0.00007441285,0.39336422,0.00041744107,0.0019314844,0.00026110886,0.00025538422,0.00042950702,0.00041911507],"genre_scores_gemma":[0.99514335,0.00017522242,0.0022408958,0.0016102259,0.00030632043,0.00006221336,0.00032845844,0.000061999155,0.00007133038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803805,0.00011496771,0.00042329263,0.0006000663,0.00046032088,0.00036330568],"domain_scores_gemma":[0.9991506,0.00011074398,0.00006798821,0.00032486828,0.00008415222,0.00026166346],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002555955,0.0003653848,0.00040373314,0.00038056515,0.00025232678,0.0002131955,0.00022710691,0.00009638379,0.0018475327],"category_scores_gemma":[0.000009392601,0.00038937657,0.00012904797,0.00030829015,0.000014518438,0.00014871356,0.0001806759,0.00056054967,0.00023761483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009239285,0.00015502663,0.00011409383,0.000082555955,0.00016080546,0.0001198779,0.002164448,0.44292897,0.007573148,0.000011053009,0.010291003,0.5363066],"study_design_scores_gemma":[0.0006577662,0.0003023323,0.0002562677,0.00021002944,0.000042988126,0.000015626418,0.00025415368,0.9960051,0.0004799367,0.00018272102,0.0010545393,0.00053853623],"about_ca_topic_score_codex":0.00012605356,"about_ca_topic_score_gemma":0.000022377435,"teacher_disagreement_score":0.55307615,"about_ca_system_score_codex":0.00010045278,"about_ca_system_score_gemma":0.000022134256,"threshold_uncertainty_score":0.9998558},"labels":[],"label_agreement":null},{"id":"W4313171465","doi":"10.1109/cvpr52688.2022.00037","title":"How Much More Data Do I Need? Estimating Requirements for Downstream Tasks","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Task (project management); Function (biology); Set (abstract data type); Downstream (manufacturing); Data set; Estimator; Data validation; Machine learning; Artificial intelligence; Data mining; Database; Engineering","score_opus":0.09217580612085,"score_gpt":0.33219020574482816,"score_spread":0.24001439962397816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313171465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025042634,0.000037770777,0.9633465,0.0072744344,0.002663228,0.0005858458,0.0005113598,0.00027424353,0.00026402736],"genre_scores_gemma":[0.8573268,0.00004274159,0.13395812,0.0048316824,0.000948514,0.00024304763,0.001990978,0.00005713739,0.0006009526],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99674207,0.00032264544,0.0004188525,0.0013090648,0.0007296917,0.00047767887],"domain_scores_gemma":[0.9979623,0.00024966022,0.00033811943,0.0010584155,0.00017861558,0.00021289855],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007894691,0.0003830954,0.00039580528,0.00028061104,0.0009076283,0.0013751218,0.0015077208,0.00007813188,0.0002977069],"category_scores_gemma":[0.000039473332,0.00036227828,0.00009649215,0.00032215464,0.000057167283,0.00079115306,0.0013792684,0.000582374,0.000032736993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023701203,0.00017164138,0.00019993413,0.000059401158,0.000032008473,0.000027158952,0.00041567048,0.0001629992,0.00015607984,0.0001627825,0.015238574,0.98335004],"study_design_scores_gemma":[0.0013639546,0.0009829063,0.00023586325,0.00017036092,0.00001936858,0.00007483111,0.00020199007,0.9874207,0.00011140404,0.0019007068,0.007025153,0.0004928063],"about_ca_topic_score_codex":0.000043648557,"about_ca_topic_score_gemma":0.0000046061323,"teacher_disagreement_score":0.98725766,"about_ca_system_score_codex":0.00004591286,"about_ca_system_score_gemma":0.000071615956,"threshold_uncertainty_score":0.99988294},"labels":[],"label_agreement":null},{"id":"W4313184971","doi":"10.1109/cvpr52688.2022.01642","title":"MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea","keywords":"Computer science; Modal; Modality (human–computer interaction); Segmentation; Adaptation (eye); Modalities; Domain adaptation; Consistency (knowledge bases); Test data; Scheme (mathematics); Artificial intelligence; Pattern recognition (psychology); Machine learning; Mathematics","score_opus":0.0619686168823289,"score_gpt":0.2893112902145141,"score_spread":0.22734267333218522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313184971","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022253435,0.000018902063,0.97286177,0.0021095718,0.0012248232,0.0008673975,0.0001301459,0.0002885771,0.00024536005],"genre_scores_gemma":[0.8692679,0.000073897914,0.12106928,0.007090164,0.0002647409,0.00045084418,0.00066138577,0.000054998793,0.0010668184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969879,0.00041484833,0.00056240463,0.0009563721,0.0006676389,0.00041083657],"domain_scores_gemma":[0.99825394,0.00055408856,0.00037152405,0.00035484676,0.00027038474,0.00019520646],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00070666155,0.00035502165,0.00035756457,0.00038810904,0.00085548987,0.000599466,0.0004742187,0.00008946349,0.0007614257],"category_scores_gemma":[0.00003913018,0.00037319728,0.00013133802,0.0003624793,0.000051993113,0.00068085495,0.00025658184,0.00040186392,0.0002803986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007801777,0.00034639277,0.00009727986,0.000054782442,0.000025227,0.00001867874,0.0018476668,0.0013288592,0.0043733534,0.00024612388,0.0017681057,0.98981553],"study_design_scores_gemma":[0.0024727862,0.0013998047,0.0016254573,0.00008314742,0.00002204901,0.000048136684,0.0002919764,0.9902536,0.00054280204,0.0006651985,0.002093706,0.0005012938],"about_ca_topic_score_codex":0.00002432139,"about_ca_topic_score_gemma":0.000012586282,"teacher_disagreement_score":0.9893142,"about_ca_system_score_codex":0.000094483876,"about_ca_system_score_gemma":0.00009526887,"threshold_uncertainty_score":0.99987197},"labels":[],"label_agreement":null}]}