{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":9,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":9,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"99b01d623da9","filters":{"venue":"Computer Vision and Pattern Recognition"}},"results":[{"id":"W2969721664","doi":"","title":"ProcSy: Procedural Synthetic Dataset Generation Towards Influence Factor Studies Of Semantic Segmentation Networks","year":2019,"lang":"en","type":"article","venue":"Computer Vision and Pattern Recognition","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Factor (programming language); Natural language processing; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.05097151400720926,"gpt":0.3210912784910192,"spread":0.2701197644838099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002159547,0.0001469087,0.000185463,0.0001108586,0.00008436739,0.0001431795,0.0001976706,0.00005576899,0.0000143],"category_scores_gemma":[0.00002373941,0.0001209032,0.00002607919,0.0001517761,0.00003155851,0.0007602286,0.0001669064,0.0001095431,0.00004727093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001978833,"about_ca_system_score_gemma":0.00001949552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001891444,"about_ca_topic_score_gemma":0.000005448427,"domain_scores_codex":[0.9987913,0.000136334,0.0003069274,0.0004240351,0.0002079523,0.0001334822],"domain_scores_gemma":[0.9992018,0.0000719079,0.0002241816,0.0002962543,0.0001577313,0.00004812696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000749442,0.000046191,0.003553645,0.0002121432,0.00001956608,0.000001118377,0.0004624335,0.0004812921,0.003776394,0.00001648738,0.0006061569,0.9908171],"study_design_scores_gemma":[0.0004290951,0.0003675824,0.05329762,0.0002818354,0.00001459937,0.00002468143,0.00003081124,0.9432465,0.001774127,0.00008964701,0.00023181,0.0002117109],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5417066,0.0000912553,0.4572864,0.0003071546,0.0002505069,0.0002558253,0.00004962197,0.00004762557,0.000005003796],"genre_scores_gemma":[0.9907916,0.0001684054,0.007066421,0.0005047392,0.00008780684,0.00001605784,0.00134912,0.000007364785,0.000008503285],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9906054,"threshold_uncertainty_score":0.4930291,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2971644068","doi":"","title":"GAN Data Augmentation Through Active Learning Inspired Sample Acquisition.","year":2019,"lang":"en","type":"article","venue":"Computer Vision and Pattern Recognition","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Sample (material); Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.04842322416993738,"gpt":0.3216162387348098,"spread":0.2731930145648724,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000177847,0.0001894158,0.0001898683,0.0001110217,0.000176729,0.0002684855,0.0006770049,0.00008037078,0.0001474932],"category_scores_gemma":[0.00001619596,0.0001764157,0.00003057582,0.0001901543,0.00002766053,0.003331227,0.001003329,0.0002105861,0.00019606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003015561,"about_ca_system_score_gemma":0.00001517571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003991237,"about_ca_topic_score_gemma":0.000002705188,"domain_scores_codex":[0.9983101,0.0001762942,0.0002675276,0.0007770754,0.000265345,0.000203626],"domain_scores_gemma":[0.9985989,0.0002637487,0.0001934237,0.0007721707,0.0001000379,0.00007169636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001611353,0.00004735694,0.0005250756,0.00002552125,0.000009301678,0.000003674848,0.0002932099,0.00003345764,0.0009933856,0.00004689148,0.001056522,0.9969495],"study_design_scores_gemma":[0.002348918,0.001108082,0.02153455,0.0007835432,0.00002189858,0.00007674305,0.0001081429,0.912795,0.01732642,0.02056012,0.02240387,0.000932731],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04045453,0.00003647376,0.9578285,0.000250406,0.0003880069,0.0003311076,0.0001031999,0.0004248416,0.0001829966],"genre_scores_gemma":[0.6897653,0.0001664956,0.3051864,0.001782968,0.0001534747,0.00001814605,0.002885331,0.00002086449,0.0000209838],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9960167,"threshold_uncertainty_score":0.7194023,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2971746767","doi":"","title":"Limitations and Biases in Facial Landmark Detection D An Empirical Study on Older Adults with Dementia","year":2019,"lang":"en","type":"article","venue":"Computer Vision and Pattern Recognition","topic":"Face recognition and analysis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Northern British Columbia; University of Regina; University of Toronto; Toronto Rehabilitation Institute","funders":"","keywords":"Landmark; Dementia; Computer science; Artificial intelligence; Cognitive psychology; Psychology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.05466912814512115,"gpt":0.2922324370851029,"spread":0.2375633089399817,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001683503,0.0001515141,0.0001669467,0.0003106787,0.00009519613,0.00023164,0.00008975372,0.00005320159,0.00002581559],"category_scores_gemma":[0.000006820811,0.0001201832,0.00002686486,0.0002649026,0.00001641226,0.0004719779,0.00006227643,0.0001243411,0.00006250431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001170808,"about_ca_system_score_gemma":0.000008653969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003111904,"about_ca_topic_score_gemma":0.000470379,"domain_scores_codex":[0.9987655,0.0001889578,0.0001952038,0.0005039732,0.0001883753,0.000157997],"domain_scores_gemma":[0.9994612,0.0001384296,0.00006477395,0.0001631812,0.00007000106,0.0001024187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004414961,0.0004163457,0.08258561,0.00001235233,0.00001885766,0.00001010036,0.001414929,0.00002133174,0.00002819698,3.202519e-7,0.00001223584,0.9154356],"study_design_scores_gemma":[0.002639472,0.002426754,0.7652792,0.0002795034,0.00002446417,0.00001942541,0.0004816919,0.2284018,0.0001249344,0.00004154636,0.0000372543,0.0002440033],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.903082,0.00001350453,0.09619884,0.0001388082,0.0001129215,0.0003472412,0.000004900212,0.00005996861,0.00004185238],"genre_scores_gemma":[0.998208,0.00002679226,0.001089288,0.0005612749,0.00003982088,0.00001971551,0.0000427577,0.00000762091,0.000004767091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9151916,"threshold_uncertainty_score":0.490093,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2971668727","doi":"","title":"Deep Probabilistic Regression of Elements of SO(3) using Quaternion Averaging and Uncertainty Injection.","year":2019,"lang":"en","type":"article","venue":"Computer Vision and Pattern Recognition","topic":"Advanced Data Processing Techniques","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Quaternion; Probabilistic logic; Statistics; Regression; Regression analysis; Artificial intelligence; Measurement uncertainty; Mathematics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01887778893913278,"gpt":0.2692569197375203,"spread":0.2503791307983875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001176928,0.0001173391,0.0001716117,0.0001151038,0.00003466702,0.0000248674,0.00004434806,0.0000545766,0.00001558397],"category_scores_gemma":[0.000005821292,0.0001007819,0.00001793052,0.00006907494,0.00003099871,0.0002803068,0.00006848091,0.00007853039,0.000001684607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002294013,"about_ca_system_score_gemma":0.000004351225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000183434,"about_ca_topic_score_gemma":0.000002978478,"domain_scores_codex":[0.9993361,0.00003080119,0.0002666909,0.0001735257,0.0001007278,0.00009216627],"domain_scores_gemma":[0.9996461,0.00003883958,0.0001097082,0.0001106232,0.00006613645,0.00002861599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001977127,0.00002307605,0.006507982,0.0008072615,0.00001122661,7.767905e-7,0.0002539018,0.004542009,0.009379488,0.000001790176,0.0000171537,0.9784356],"study_design_scores_gemma":[0.0003971325,0.0001772845,0.00261131,0.00153414,0.00001145175,0.00001850939,0.00002149668,0.9875404,0.006135941,0.001356462,0.00005042102,0.0001454854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5594717,0.00007683464,0.4401745,0.000002255313,0.00009385973,0.0001114861,0.00000778636,0.00005345386,0.000008116359],"genre_scores_gemma":[0.9700881,0.0001151526,0.02965922,0.00001934839,0.00002643785,0.000002881076,0.00007275591,0.00001516769,9.800922e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9829984,"threshold_uncertainty_score":0.4109765,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2971967504","doi":"","title":"Application of DenseNet in Camera Model Identification and Post-processing Detection","year":2019,"lang":"en","type":"article","venue":"Computer Vision and Pattern Recognition","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; University of Windsor","funders":"","keywords":"Computer science; Identification (biology); Computer vision; Artificial intelligence; Computer graphics (images)","retraction":null,"screen_n_in":null,"score":{"opus":0.01042703376764862,"gpt":0.2380472585473151,"spread":0.2276202247796665,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002188498,0.00009901189,0.0001270638,0.0002215752,0.00006058109,0.0001394325,0.00008863619,0.00007216597,0.000001260862],"category_scores_gemma":[0.000004131039,0.00009713102,0.00001882201,0.0001727595,0.00003008901,0.0006706233,0.00006401989,0.00009321706,0.00001086117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001533436,"about_ca_system_score_gemma":0.00002007844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003254737,"about_ca_topic_score_gemma":0.0000151098,"domain_scores_codex":[0.9991057,0.00004582817,0.0002706749,0.0003547421,0.0001134749,0.0001096121],"domain_scores_gemma":[0.9994747,0.00002604931,0.0001754395,0.0001388028,0.0001487711,0.00003625512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007287252,0.00002022833,0.001747983,0.0001092164,0.000001482345,2.626211e-7,0.0002895161,0.0001350696,0.02617496,0.000005667578,0.000001807183,0.9715065],"study_design_scores_gemma":[0.0003422358,0.00007057715,0.0331769,0.0001218412,0.000004097944,0.00005395311,0.00002254854,0.9566916,0.007977056,0.00141958,0.000005429361,0.000114174],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.464267,0.00005024435,0.5353989,0.0000682414,0.00008380691,0.00009154618,0.000001303766,0.00002621602,0.00001269687],"genre_scores_gemma":[0.9855259,0.00003577209,0.01422444,0.0001449212,0.00002685193,0.000008324439,0.00001788907,0.000006307102,0.000009576282],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9713923,"threshold_uncertainty_score":0.3960888,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2969186079","doi":"","title":"Generalized Zero-Shot Learning via Aligned Variational Autoencoders","year":2019,"lang":"en","type":"article","venue":"Computer Vision and Pattern Recognition","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Shot (pellet); Zero (linguistics); Artificial intelligence; Computer science; One shot; Mathematics; Materials science; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02538265871613206,"gpt":0.2555607806244354,"spread":0.2301781219083034,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003847553,0.0001990033,0.0002074158,0.0001920119,0.0002059013,0.0003820839,0.0002503622,0.00009942606,0.0003640394],"category_scores_gemma":[0.0000107122,0.0001905222,0.00007994338,0.0002099847,0.00002308468,0.0006263297,0.0001805377,0.0001710371,0.0007522333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002697488,"about_ca_system_score_gemma":0.00002620423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001864679,"about_ca_topic_score_gemma":0.000001655153,"domain_scores_codex":[0.9982869,0.0002681742,0.0003092218,0.000543633,0.0003346261,0.0002574702],"domain_scores_gemma":[0.9992004,0.0001591252,0.0001686446,0.0002142311,0.0001214324,0.0001361651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002014319,0.00006013641,0.002769133,0.0000315907,0.00002932667,0.00001144021,0.0009884182,0.0030414,0.001353715,0.000700148,0.0006262201,0.9903683],"study_design_scores_gemma":[0.001247915,0.0002612629,0.01473059,0.0000705339,0.000006763677,0.00004944199,0.0000137067,0.9756128,0.00008288378,0.002290278,0.005333975,0.0002998437],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07217117,0.00003136921,0.9251329,0.0004888431,0.0008165642,0.0001985511,0.000001784092,0.0002457501,0.0009131046],"genre_scores_gemma":[0.874902,0.00003647379,0.1210967,0.003194172,0.0001658181,0.00001230169,0.0001638688,0.00002145513,0.0004071905],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9900685,"threshold_uncertainty_score":0.9668688,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2966777314","doi":"","title":"SANE: Towards Improved Prediction Robustness via Stochastically Activated Network Ensembles","year":2019,"lang":"en","type":"article","venue":"Computer Vision and Pattern Recognition","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Robustness (evolution); Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01189665059216931,"gpt":0.2396290639766663,"spread":0.227732413384497,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003692955,0.0002819849,0.0002964855,0.0001316124,0.0002032553,0.0002974077,0.0003758655,0.0001876652,0.00009876458],"category_scores_gemma":[0.00001919337,0.000256363,0.0000756701,0.000296544,0.00003764494,0.0007779744,0.0004750149,0.0003855525,0.0000845146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004370303,"about_ca_system_score_gemma":0.00003175313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002531824,"about_ca_topic_score_gemma":0.000003303971,"domain_scores_codex":[0.9980195,0.0002238022,0.000358828,0.0007181176,0.0002948185,0.0003849693],"domain_scores_gemma":[0.9989165,0.0001917407,0.0001853286,0.0003884999,0.0001670023,0.0001509213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004667347,0.00004903384,0.0007289813,0.00005005175,0.00002655009,0.000009106736,0.0001281278,0.02039618,0.00197746,0.00002636058,0.0002158721,0.9763456],"study_design_scores_gemma":[0.0009565949,0.0004827598,0.01330855,0.0002190327,0.00001514034,0.0000615184,0.000006373848,0.9835956,0.0002860065,0.0005723091,0.0001877634,0.0003083484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1692492,0.00002223027,0.8278897,0.0002596273,0.001773667,0.0003519812,0.00000488559,0.00032633,0.0001223692],"genre_scores_gemma":[0.9233372,0.00001614545,0.07518723,0.0005949033,0.0006860729,0.00001486094,0.0001021316,0.00002842015,0.00003302248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9760373,"threshold_uncertainty_score":0.9999889,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2982305100","doi":"","title":"Discriminative Quantization for Fast Similarity Search.","year":2019,"lang":"en","type":"article","venue":"Computer Vision and Pattern Recognition","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Discriminative model; Computer science; Artificial intelligence; Quantization (signal processing); Nearest neighbor search; Pattern recognition (psychology); Similarity (geometry); Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.03834193686331022,"gpt":0.3198599817939886,"spread":0.2815180449306784,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002054379,0.0001293035,0.000147289,0.0001075302,0.00009992712,0.0001885852,0.0001938518,0.000060771,0.00001580004],"category_scores_gemma":[0.00001039784,0.0001114271,0.00005371564,0.0001379997,0.00002497264,0.0008562549,0.0001831316,0.0000981191,0.00004357681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001671222,"about_ca_system_score_gemma":0.00001042216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004822344,"about_ca_topic_score_gemma":0.000001373917,"domain_scores_codex":[0.9990429,0.00006690437,0.0001687163,0.0004019229,0.0001465595,0.0001729591],"domain_scores_gemma":[0.9993353,0.0001447137,0.00006515337,0.0002034424,0.0001882134,0.00006314984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001180905,0.00003838617,0.0004321016,0.00005903313,0.000004418176,0.000001446116,0.0002296147,0.000002899203,0.0004707611,0.0002822364,0.0002732464,0.998194],"study_design_scores_gemma":[0.001725515,0.002405703,0.02193645,0.0004796273,0.00001635991,0.00003599359,0.00006830099,0.8921936,0.05067812,0.02535118,0.004406101,0.0007030134],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03435512,0.00003098541,0.9641998,0.0003384314,0.0002485405,0.000504921,0.00001867355,0.000170456,0.0001330026],"genre_scores_gemma":[0.8478537,0.0001080676,0.1505284,0.001177397,0.0001127336,0.00001942325,0.000123562,0.00001432402,0.00006240176],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9974911,"threshold_uncertainty_score":0.4543865,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2971547406","doi":"","title":"SANE: Exploring Adversarial Robustness With Stochastically Activated Network Ensembles","year":2019,"lang":"en","type":"article","venue":"Computer Vision and Pattern Recognition","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan; University of Waterloo","funders":"","keywords":"Robustness (evolution); Adversarial system; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02462234266608005,"gpt":0.2352726368110287,"spread":0.2106502941449487,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002679044,0.0002800052,0.0002989093,0.0001255014,0.0002046995,0.0003040996,0.0003696459,0.0001052386,0.00007914036],"category_scores_gemma":[0.00001319739,0.0002325447,0.00005103696,0.0003091778,0.00004131383,0.001092564,0.0004157358,0.0003577776,0.00008867754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003223972,"about_ca_system_score_gemma":0.00003090266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001588413,"about_ca_topic_score_gemma":0.000004724478,"domain_scores_codex":[0.9981273,0.0001854509,0.0002645967,0.0006848786,0.0003438138,0.0003939774],"domain_scores_gemma":[0.9988898,0.0003202047,0.0001541926,0.0003646509,0.0001273512,0.0001438182],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001526418,0.00005201098,0.001890896,0.00005734571,0.00004235452,0.0000480956,0.0003145319,0.1136378,0.0002970682,0.0001542426,0.0001469927,0.8832061],"study_design_scores_gemma":[0.002005611,0.0007696621,0.008543449,0.0006150849,0.0000217381,0.00009267916,0.00003024219,0.986504,0.000224382,0.0003177637,0.0003361609,0.0005392428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3254226,0.00001106384,0.6728725,0.0001562353,0.001003719,0.0002208533,0.000001250466,0.0001972224,0.0001146437],"genre_scores_gemma":[0.9025594,0.00001383955,0.09629587,0.0003696502,0.0006593554,0.00001824016,0.00003691269,0.00002900828,0.00001772005],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8826668,"threshold_uncertainty_score":0.9482899,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}