{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":721,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":721,"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":"fd48f6d97481","filters":{"topic":"Autonomous Vehicle Technology and Safety"}},"results":[{"id":"W2991484432","doi":"10.1109/iccv.2019.00636","title":"PIE: A Large-Scale Dataset and Models for Pedestrian Intention Estimation and Trajectory Prediction","year":2019,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":436,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Pedestrian; Trajectory; Computer science; Anticipation (artificial intelligence); Context (archaeology); Scale (ratio); Artificial intelligence; Key (lock); Estimation; Motion (physics); Human behavior; Machine learning; Data mining; Engineering; Transport engineering; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.008266477558872182,"gpt":0.2063330782095994,"spread":0.1980666006507272,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001089575,0.00006180754,0.00007488023,0.00004613361,0.0000390413,0.00001013114,0.0000259591,0.000100695,0.00001490061],"category_scores_gemma":[0.000004167271,0.00006094512,0.000009956252,0.00002824983,0.00001554239,0.0002479481,0.0000133784,0.00006496407,0.000004646879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001510759,"about_ca_system_score_gemma":0.000003667963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005210512,"about_ca_topic_score_gemma":0.00003071301,"domain_scores_codex":[0.999662,0.000004130005,0.00009789261,0.0001135537,0.00002634351,0.00009606474],"domain_scores_gemma":[0.9998466,0.00001792541,0.00001177382,0.00009431902,0.000007829308,0.00002155502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005056857,0.0003548788,0.03862501,0.00293331,0.0004736222,0.000003355885,0.003469449,0.4298459,0.02332267,0.05038058,0.03063685,0.4194487],"study_design_scores_gemma":[0.0005257016,0.00004796309,0.003511667,0.00000815051,0.00001410427,0.000005507831,0.0001021986,0.992559,0.0002987934,0.001937645,0.0009263981,0.00006288949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4698783,0.0000963601,0.5285361,0.00004776574,0.00006954208,0.0002761766,0.000457039,0.0003035893,0.0003350699],"genre_scores_gemma":[0.9930782,0.00005268995,0.00612198,0.00001496248,0.00000786933,0.00002255535,0.0006182281,0.000009182599,0.0000743877],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5627131,"threshold_uncertainty_score":0.248527,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2771583656","doi":"10.1109/iccvw.2017.33","title":"Are They Going to Cross? A Benchmark Dataset and Baseline for Pedestrian Crosswalk Behavior","year":2017,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":403,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Schema crosswalk; Pedestrian; Baseline (sea); Computer science; Benchmark (surveying); Minimum bounding box; Bounding overwatch; Point (geometry); Artificial intelligence; Machine learning; Pedestrian detection; Pedestrian crossing; Information retrieval; Human–computer interaction; Transport engineering; Image (mathematics); Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02574090554235806,"gpt":0.308778951740207,"spread":0.2830380461978489,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000265772,0.0001403218,0.0001682561,0.00004343475,0.0005148471,0.0001694326,0.0003111143,0.0001448574,0.0000666949],"category_scores_gemma":[0.0001828004,0.0001315809,0.00002947341,0.00001700398,0.00007589121,0.0001977806,0.0001352403,0.0001241604,0.00004035998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002188172,"about_ca_system_score_gemma":0.000008985487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004736347,"about_ca_topic_score_gemma":0.0009163178,"domain_scores_codex":[0.9992895,0.000004930353,0.0001707892,0.0002220729,0.0000460655,0.000266625],"domain_scores_gemma":[0.9991523,0.00005620062,0.00005386035,0.0006239548,0.00002231107,0.00009136253],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002480682,0.0001898041,0.664253,0.0004118083,0.0001590527,0.0001542821,0.0004147128,0.002008686,0.007181454,0.002743016,0.08863082,0.2336053],"study_design_scores_gemma":[0.002067173,0.0001250788,0.7861639,0.00005903436,0.00008590028,0.00004167967,0.0001076754,0.02301064,0.006909359,0.000708431,0.1799139,0.0008072632],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9888474,0.0001007336,0.005667372,0.0005326644,0.0001801619,0.0005216519,0.002837839,0.0004105914,0.0009015448],"genre_scores_gemma":[0.9955004,0.00001635752,0.003647727,0.0001197188,0.00006078336,0.0001043615,0.0001861068,0.00002357256,0.0003410052],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2327981,"threshold_uncertainty_score":0.5365713,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Artificial intelligence; Invariant (physics); Transformer; Benchmark (surveying); Machine learning; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0446215628100976,"gpt":0.2561934175399021,"spread":0.2115718547298045,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002368985,0.0002489679,0.0002609804,0.00021117,0.000392923,0.00005356629,0.0001523087,0.0001535875,0.0008161461],"category_scores_gemma":[0.000003049621,0.0002566099,0.000110077,0.0001254277,0.00005373205,0.0001419147,0.00003587027,0.0005646557,0.00005653159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008882249,"about_ca_system_score_gemma":0.00001843496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004783178,"about_ca_topic_score_gemma":0.00001030398,"domain_scores_codex":[0.9986094,0.00009982035,0.0003604228,0.000424426,0.0002123808,0.0002935399],"domain_scores_gemma":[0.9995385,0.00006894986,0.00005624701,0.0001754715,0.00005491725,0.0001058526],"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":[0.0001055066,0.0002123228,0.0002319689,0.00008662971,0.00005506606,0.000008868852,0.000406324,0.001178909,0.002933852,0.00014403,0.001921737,0.9927148],"study_design_scores_gemma":[0.00199442,0.001051277,0.006957222,0.00006378772,0.00003370154,0.00004482615,0.00007370546,0.9810554,0.002290244,0.0006375902,0.005419381,0.000378462],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.269761,0.00003170818,0.7260926,0.0006194627,0.001455754,0.000628192,0.0006451871,0.0005563928,0.0002096958],"genre_scores_gemma":[0.9967629,0.0001444133,0.00143779,0.0005225313,0.0001583193,0.0003284208,0.0005319137,0.00003828556,0.00007542416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9923363,"threshold_uncertainty_score":0.9999886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2968008415","doi":"10.1109/cvpr.2019.00886","title":"End-To-End Interpretable Neural Motion Planner","year":2019,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":389,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Planner; SAFER; Artificial intelligence; Position (finance); Set (abstract data type); Motion (physics); Trajectory; Motion planning; Data set; Volume (thermodynamics); Lidar; Raw data; Reinforcement learning; Machine learning; Sample (material); Robot; Computer vision; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.004082958647840696,"gpt":0.1837694209499708,"spread":0.1796864623021301,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00005086127,0.00008227101,0.00009593575,0.00006326347,0.00001834556,0.000008382537,0.0001139418,0.00009709968,0.001804199],"category_scores_gemma":[0.000003526803,0.00007470048,0.00002572543,0.0000784282,0.00001036888,0.0001017063,0.00003484699,0.0001490606,0.001911833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003011977,"about_ca_system_score_gemma":0.0000027529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001605822,"about_ca_topic_score_gemma":0.00001218641,"domain_scores_codex":[0.9995596,0.000004986363,0.0000987211,0.0001119349,0.000043926,0.0001807655],"domain_scores_gemma":[0.9997526,0.00001427149,0.000006326899,0.0001856013,0.000006853859,0.00003435047],"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":[0.00008758502,0.00009207306,0.08071131,0.000141521,0.0002271472,0.00003116419,0.001342901,0.3827399,0.07775091,0.04803487,0.01543727,0.3934033],"study_design_scores_gemma":[0.000478027,0.0001315395,0.04761958,0.0000191818,0.00001393658,0.00003300792,0.000155484,0.8868735,0.03248473,0.0007404776,0.03095697,0.0004935903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9108586,0.00003230259,0.01336179,0.0002334941,0.000396217,0.0001180216,0.00000371072,0.001086789,0.07390904],"genre_scores_gemma":[0.9968646,0.000002151567,0.0004540733,0.0001581271,0.00001911781,0.000006001093,0.000005278281,0.00001487154,0.002475764],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5041335,"threshold_uncertainty_score":0.9991083,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3203848864","doi":"10.1109/iccv48922.2021.00375","title":"CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":318,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Benchmark (surveying); Convolution (computer science); Pipeline (software); Code (set theory); Line (geometry); Network topology; Process (computing); Source lines of code; Artificial intelligence; Algorithm; Pattern recognition (psychology); Data mining; Mathematics; Artificial neural network; Software; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01336336142485659,"gpt":0.2583994902228813,"spread":0.2450361287980247,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001649445,0.0003004522,0.0002780273,0.0003068811,0.0001405707,0.0001194641,0.0003548858,0.0003458418,0.003082956],"category_scores_gemma":[0.00004699633,0.000322189,0.0001202685,0.0002552539,0.00005708135,0.0001220508,0.00006676557,0.000656319,0.001301976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003125465,"about_ca_system_score_gemma":0.0001002366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009843381,"about_ca_topic_score_gemma":0.00003002729,"domain_scores_codex":[0.9981961,0.00008208233,0.0003962381,0.00054163,0.0004835911,0.0003003282],"domain_scores_gemma":[0.9988163,0.0002245928,0.00007703962,0.0003991421,0.0003447073,0.0001382341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006844366,0.000889567,0.0008987621,0.00008642813,0.0004803006,0.0005833739,0.0002876497,0.5280378,0.04735731,0.197612,0.02078201,0.2023003],"study_design_scores_gemma":[0.0007268324,0.0004159661,0.005828104,0.0002709606,0.00001245461,0.00004227212,0.00001942013,0.9553571,0.02076042,0.006203925,0.009935742,0.0004268531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09853926,0.000023685,0.8845713,0.004605136,0.004084326,0.0002600229,0.0001887572,0.0005448526,0.007182721],"genre_scores_gemma":[0.9909519,0.00002629289,0.006007364,0.001720817,0.0005164338,0.00004429809,0.0003255596,0.00003234891,0.0003750143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8924126,"threshold_uncertainty_score":0.999923,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2782064812","doi":"10.1109/tiv.2017.2788193","title":"Understanding Pedestrian Behavior in Complex Traffic Scenes","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Vehicles","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":266,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Air Force Office of Scientific Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Pedestrian; Schema crosswalk; Context (archaeology); Pedestrian crossing; Computer science; Transport engineering; Demographics; Meaning (existential); Human–computer interaction; Psychology; Geography; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.10816409996401,"gpt":0.2762930400321242,"spread":0.1681289400681142,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001226879,0.0002119921,0.0002042134,0.0003795582,0.0002055987,0.00002574229,0.0002047702,0.0002182617,0.0003780814],"category_scores_gemma":[0.000001632326,0.0002293798,0.00009261024,0.0003523914,0.0002492337,0.0001039735,0.000001113782,0.0003933812,0.0002529857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003336174,"about_ca_system_score_gemma":0.00002012217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002115048,"about_ca_topic_score_gemma":0.0008465368,"domain_scores_codex":[0.9989113,0.00003000028,0.0003377763,0.0002391756,0.0001231274,0.000358662],"domain_scores_gemma":[0.9995694,0.00006796974,0.00002395022,0.0002469777,0.00002069679,0.00007103334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000532479,0.001586827,0.002608649,0.0001786105,0.0003115172,0.0001250967,0.003887994,0.5231056,0.03065521,0.003056026,0.0008675816,0.4330845],"study_design_scores_gemma":[0.001857135,0.001267204,0.009392626,0.0002107769,0.000185629,0.0001060086,0.003748204,0.4508335,0.5245865,0.001974504,0.00406625,0.001771673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6349203,0.00003610602,0.362895,0.00009259599,0.0003913075,0.0002182447,0.00001627301,0.0007570153,0.0006731926],"genre_scores_gemma":[0.99923,0.0001610724,0.0003614305,0.00003737759,0.0000461535,0.0000526939,0.000002774577,0.00004210894,0.00006639106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4939313,"threshold_uncertainty_score":0.9353839,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3091936287","doi":"10.1155/2020/8867757","title":"Safety of Autonomous Vehicles","year":2020,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":242,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Commercialization; Transport engineering; Automation; Disengagement theory; Process (computing); Occupational safety and health; Vehicle safety; Automotive industry; Business; Computer security; Risk analysis (engineering); Engineering; Computer science; Aeronautics; Automotive engineering; Medicine; Marketing","retraction":null,"screen_n_in":null,"score":{"opus":0.006843731743575368,"gpt":0.2064994454312283,"spread":0.1996557136876529,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006553753,0.00007734884,0.0002154182,0.00005138044,0.00001774103,0.000001496026,0.0001034415,0.00007181368,0.00002013114],"category_scores_gemma":[0.00001017596,0.0000755919,0.00008371487,0.0001356765,0.00003156279,0.0002074824,8.667044e-7,0.0002018803,0.00000237541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002241455,"about_ca_system_score_gemma":0.00002423128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.774831e-7,"about_ca_topic_score_gemma":0.000002588785,"domain_scores_codex":[0.9992409,0.000006164122,0.000516429,0.00005227204,0.00009750598,0.00008673265],"domain_scores_gemma":[0.9996306,0.00002420655,0.0001708644,0.0000536575,0.0000688717,0.00005183535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0002516248,0.00002271541,0.001858325,0.0001024479,0.00008599447,0.0000300258,0.002261344,0.8548429,0.07771474,0.001335686,0.00004454721,0.06144964],"study_design_scores_gemma":[0.00510785,0.001113697,0.6565304,0.0001984412,0.0002394445,0.00003577364,0.001885386,0.009909783,0.3013487,0.003247008,0.0198314,0.0005521568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9665922,0.0005259986,0.03192242,0.0004481595,0.0001403333,0.00005966051,0.00001408806,0.00009920911,0.000197927],"genre_scores_gemma":[0.9922479,0.0002654337,0.007388438,0.00003805117,0.00003898534,6.09738e-7,0.000004712475,0.00001331308,0.000002597303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8449332,"threshold_uncertainty_score":0.3082548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2923088732","doi":"10.1126/scirobotics.aaw4106","title":"Parallel testing of vehicle intelligence via virtual-real interaction","year":2019,"lang":"en","type":"review","venue":"Science Robotics","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":220,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Human–computer interaction","retraction":null,"screen_n_in":null,"score":{"opus":0.06713276179965347,"gpt":0.3189995688411282,"spread":0.2518668070414748,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004323955,0.0002600609,0.0007522181,0.0002991632,0.00009314543,0.00002250152,0.0008237482,0.0002844327,0.00001032783],"category_scores_gemma":[0.0001230296,0.0002366105,0.0001219903,0.001202882,0.0004543852,0.0002283908,0.0001674992,0.0005918962,0.0002218788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002395076,"about_ca_system_score_gemma":0.0002431378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001304049,"about_ca_topic_score_gemma":0.000003132086,"domain_scores_codex":[0.9984763,0.0000211429,0.0005826739,0.0003211675,0.0002230525,0.0003756959],"domain_scores_gemma":[0.9989108,0.0002343297,0.0002106136,0.0004984044,0.00008448566,0.00006133586],"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":[3.795446e-7,0.00000982763,0.000009827711,0.001110551,0.00001294555,0.000001521646,0.00002581112,0.1626023,0.00002676094,0.001398253,0.000004760163,0.834797],"study_design_scores_gemma":[0.00008050889,0.0002510136,0.00003694845,0.007384826,0.00034641,0.0001013348,0.0001054858,0.9311044,0.0003065218,0.0007579025,0.05848103,0.001043609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00005885774,0.8278624,0.1645109,0.00001160664,0.001753783,0.0005652952,0.00001054726,0.0006719417,0.0045547],"genre_scores_gemma":[0.005694701,0.9819569,0.01218933,0.000003908359,0.00003676188,0.00000898405,0.000005072871,0.00003806207,0.00006626702],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8337535,"threshold_uncertainty_score":0.9648697,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3125605478","doi":"10.1109/iros51168.2021.9636035","title":"LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":200,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; ENCODE; Graph; Benchmark (surveying); Theoretical computer science; Artificial intelligence; Encoder; Representation (politics); Robotics; Motion (physics); Robot","retraction":null,"screen_n_in":null,"score":{"opus":0.06709133067816217,"gpt":0.2806834837013816,"spread":0.2135921530232195,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001937706,0.0002140696,0.000266576,0.0001683146,0.0001681934,0.0001552011,0.0001964733,0.0001831977,0.0002082826],"category_scores_gemma":[0.0001016367,0.0002137922,0.0001039367,0.0002025479,0.00005615859,0.000125499,0.0000396385,0.000244435,0.0000340703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001193944,"about_ca_system_score_gemma":0.00003872297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003743222,"about_ca_topic_score_gemma":0.00003656985,"domain_scores_codex":[0.9985895,0.00004420754,0.0004934524,0.0003804154,0.0002198327,0.0002726366],"domain_scores_gemma":[0.9991066,0.000132157,0.0001048133,0.0002343884,0.0003323511,0.00008970821],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001033173,0.0003369339,0.007476083,0.0003974004,0.0009064397,0.0001623927,0.000757569,0.419547,0.01004742,0.4939713,0.006232852,0.06006124],"study_design_scores_gemma":[0.0004797746,0.0000619098,0.001013382,0.0002309164,0.00004216295,0.0001086932,0.0009550652,0.9824653,0.00656638,0.002716563,0.005001733,0.0003580857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07935241,0.0006747358,0.9054706,0.0008886929,0.004185328,0.0006656112,0.0005905186,0.0003342578,0.007837875],"genre_scores_gemma":[0.9968649,0.0006591582,0.0003007118,0.0000287981,0.0002187585,0.0001329224,0.0005923555,0.00002448929,0.001177925],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9175125,"threshold_uncertainty_score":0.8718193,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4285272860","doi":"10.1109/tiv.2022.3188662","title":"Prediction-Uncertainty-Aware Decision-Making for Autonomous Vehicles","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Vehicles","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":188,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Field (mathematics); Motion (physics); Process (computing); Artificial intelligence; Machine learning; Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01766238584454036,"gpt":0.2432090942004313,"spread":0.225546708355891,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003229461,0.0003388863,0.0003214577,0.000414039,0.0011842,0.00004097075,0.0004887586,0.0002023276,0.0006070848],"category_scores_gemma":[0.000008833803,0.0003820727,0.0003012221,0.0003924454,0.0001120893,0.0001417488,0.000007918225,0.00080067,0.00007777686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005859482,"about_ca_system_score_gemma":0.00007131579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001268924,"about_ca_topic_score_gemma":0.00003916747,"domain_scores_codex":[0.9980574,0.0000507478,0.0005913181,0.0004645408,0.0003103473,0.000525701],"domain_scores_gemma":[0.9986572,0.0006262457,0.00006799994,0.0004853219,0.00006729516,0.00009594673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001737578,0.0001379063,0.00003316462,0.00002693164,0.000123714,0.000006204967,0.0003225341,0.7340526,0.0004593103,0.0002913837,0.0008982997,0.2634742],"study_design_scores_gemma":[0.0006881419,0.0006282937,0.0001512313,0.00008531826,0.0001205263,0.00007495121,0.001591816,0.9216698,0.0308951,0.006015562,0.03739118,0.0006881074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1527542,0.0002119088,0.841754,0.0001585971,0.001705148,0.0006406952,0.000691377,0.001866472,0.0002176587],"genre_scores_gemma":[0.996443,0.0001213614,0.001861132,0.0001723616,0.00007525369,0.0009918362,0.00001667828,0.00009878955,0.0002195437],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8436888,"threshold_uncertainty_score":0.9998631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3162665729","doi":"10.1109/tits.2021.3076140","title":"Driving Behavior Analysis Guidelines for Intelligent Transportation Systems","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":162,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Intelligent transportation system; Profiling (computer programming); Data collection; Key (lock); Risk analysis (engineering); Field (mathematics); Variety (cybernetics); Computer science; Advanced driver assistance systems; Data science; Transport engineering; Engineering; Systems engineering; Computer security; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.0463532577251805,"gpt":0.2937293858819122,"spread":0.2473761281567317,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003656979,0.0004857835,0.0007685116,0.0006633364,0.0002889963,0.0000963998,0.0002491199,0.0004738942,0.0001286487],"category_scores_gemma":[0.00000707594,0.0005323126,0.000702843,0.001284582,0.00006288301,0.0002503165,1.782424e-7,0.0003889766,0.00005411399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000237514,"about_ca_system_score_gemma":0.00007978666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001620593,"about_ca_topic_score_gemma":0.001596012,"domain_scores_codex":[0.9965454,0.00006305226,0.001832298,0.0006376653,0.0004309027,0.0004906714],"domain_scores_gemma":[0.9980419,0.0001788361,0.0001854628,0.0005553678,0.0008573307,0.0001810627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000321264,0.0001767078,0.0008676872,0.0002839148,0.00127279,0.00002883064,0.0008037104,0.9868504,0.002040982,0.0009868897,0.0001560852,0.006499808],"study_design_scores_gemma":[0.001508996,0.0003566415,0.006815562,0.0006912571,0.009051242,0.00004358199,0.01214235,0.6732115,0.2653323,0.00007800198,0.02825182,0.002516866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1042187,0.0009656206,0.888738,0.00007392903,0.002971801,0.001114638,0.0008092514,0.001055301,0.00005276755],"genre_scores_gemma":[0.9948764,0.0007598831,0.001238236,0.00003417988,0.0001006354,0.001537616,0.0006095142,0.0001026546,0.0007409009],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8906577,"threshold_uncertainty_score":0.9997128,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2556398113","doi":"10.1109/tvt.2016.2631604","title":"Recent Trends in Driver Safety Monitoring Systems: State of the Art and Challenges","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":157,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Advanced driver assistance systems; Transport engineering; Context (archaeology); Engineering; Intelligent transportation system; Perception; Risk analysis (engineering); Computer science; Computer security; Systems engineering; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.01247891966785702,"gpt":0.2049750611896329,"spread":0.1924961415217759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001260969,0.0001574711,0.0002393644,0.0004823346,0.00006374274,0.000002516691,0.0002041275,0.000312409,0.0000106855],"category_scores_gemma":[0.000003388237,0.0001072512,0.00004759627,0.0004366111,0.0002276164,0.00006162535,0.000004189957,0.0003532108,0.00001111844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001422545,"about_ca_system_score_gemma":0.000008998288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003043228,"about_ca_topic_score_gemma":0.00006057591,"domain_scores_codex":[0.9991363,0.00003389508,0.0002848873,0.0002107769,0.00008986556,0.0002443078],"domain_scores_gemma":[0.9994466,0.00004112704,0.00004176628,0.0004207696,0.00002652631,0.0000232611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001821549,0.00004596352,0.0004301717,0.00003072302,0.00007491368,0.000007714947,0.00008326489,0.01596921,0.01177657,0.0004626158,0.000006170895,0.9710945],"study_design_scores_gemma":[0.003564618,0.0004004396,0.03960809,0.001036242,0.0001159028,0.0001979425,0.0005274192,0.009210097,0.877793,0.001896854,0.06466065,0.0009887269],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9455607,0.006709067,0.03913374,0.005975131,0.0008523328,0.0002885018,0.00003441818,0.001041181,0.0004049149],"genre_scores_gemma":[0.9768553,0.0228446,0.00008443337,0.000002860883,0.000005687633,0.00004700334,1.331066e-7,0.00002226557,0.0001376921],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9701058,"threshold_uncertainty_score":0.4373578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3106149304","doi":"10.3390/s20226532","title":"The Perception System of Intelligent Ground Vehicles in All Weather Conditions: A Systematic Literature Review","year":2020,"lang":"en","type":"review","venue":"Sensors","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":152,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Visibility; Cruise control; Perception; Computer science; Radar; Transport engineering; Environmental science; Engineering; Meteorology; Control (management); Artificial intelligence; Geography; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.02280195310904047,"gpt":0.2779844097190068,"spread":0.2551824566099663,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000449708,0.0003384338,0.001710556,0.0001258721,0.00004619961,0.00002161506,0.000328432,0.0004130505,0.000007128489],"category_scores_gemma":[0.00006510273,0.0002162113,0.0003626913,0.0004608151,0.00006704523,0.00003407467,0.00003549024,0.000663259,0.0001602081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003041657,"about_ca_system_score_gemma":0.00002721571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002052541,"about_ca_topic_score_gemma":0.000005343148,"domain_scores_codex":[0.9980229,0.000331863,0.001095528,0.0002136269,0.0001302349,0.0002058338],"domain_scores_gemma":[0.9989675,0.00025273,0.000247468,0.000461609,0.0000343309,0.00003632193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[7.550514e-7,0.000006335866,1.732392e-7,0.9387093,0.000216413,0.00004104276,0.0002618636,0.00003546699,5.512486e-7,0.001475778,0.0001416727,0.05911072],"study_design_scores_gemma":[0.00003393232,0.00001416395,0.000001485164,0.718976,0.0005696585,0.0001918305,0.0003127376,0.001056872,4.347658e-7,0.00002185666,0.2786154,0.0002055901],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00003085387,0.9973477,0.00001283811,0.00005084905,0.0001483762,0.001807287,0.00004633946,0.0002880712,0.00026771],"genre_scores_gemma":[0.0006400901,0.9988467,0.00002263158,0.00001679726,0.00003693618,0.0002524011,0.00005300385,0.00005543434,0.00007606478],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.2784738,"threshold_uncertainty_score":0.8816839,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042633954","doi":"10.3141/2083-11","title":"Probabilistic Framework for Automated Analysis of Exposure to Road Collisions","year":2008,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":143,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Probabilistic logic; Hierarchy; Perspective (graphical); Traffic analysis; Data collection; Collision; Traffic conflict; Data science; Transport engineering; Data mining; Artificial intelligence; Computer security; Floating car data; Engineering; Traffic congestion","retraction":null,"screen_n_in":null,"score":{"opus":0.06735339908335354,"gpt":0.3654327493464628,"spread":0.2980793502631093,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002368986,0.0002004612,0.0006445579,0.001925463,0.0004944319,0.00002165502,0.0009316439,0.0003200671,0.000116476],"category_scores_gemma":[0.0004261223,0.0001605972,0.0005319524,0.005666631,0.0005062383,0.0002216692,0.000004999657,0.001434667,0.000006988798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001960651,"about_ca_system_score_gemma":0.0003654019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007895559,"about_ca_topic_score_gemma":0.007689829,"domain_scores_codex":[0.9956743,0.0003323043,0.001389052,0.0002764392,0.001656331,0.0006715581],"domain_scores_gemma":[0.9948985,0.001336769,0.0002247151,0.0005200547,0.002736949,0.0002830042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00160336,0.0003945075,0.2076366,0.0004486933,0.002075891,0.00008220285,0.007311696,0.754993,0.004648632,0.01210001,0.004366372,0.004338991],"study_design_scores_gemma":[0.0006454216,0.000682394,0.9782867,0.0001728616,0.0002584668,4.346086e-7,0.0006531298,0.01366915,0.001565552,0.002619258,0.001281769,0.0001649022],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9751957,0.0001463391,0.02189211,0.0009238526,0.000230133,0.001182054,0.000226361,0.0001618387,0.00004158514],"genre_scores_gemma":[0.9861919,0.0003911047,0.01303701,0.00001581611,0.00004598705,0.0001445705,0.00002427949,0.00004537468,0.0001039492],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.77065,"threshold_uncertainty_score":0.6548966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386076483","doi":"10.1109/cvpr52729.2023.00140","title":"UniSim: A Neural Closed-Loop Sensor Simulator","year":2023,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":131,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Leverage (statistics); Computer science; Artificial intelligence; Convolutional neural network; Closed loop; Viewpoints; Simulation; Real-time computing; Control engineering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01065282367388336,"gpt":0.2166913990916978,"spread":0.2060385754178144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00006329233,0.0001039322,0.0001133493,0.00009225211,0.00005472103,0.000007943565,0.0001195057,0.0001385201,0.000190603],"category_scores_gemma":[0.00001280336,0.00009748281,0.00004054432,0.000340205,0.0000344777,0.00005397267,0.0000389229,0.0001763427,0.001434439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000201073,"about_ca_system_score_gemma":0.000006164741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004191073,"about_ca_topic_score_gemma":0.000005789736,"domain_scores_codex":[0.999422,0.000007283261,0.0001258696,0.0001178688,0.00005830676,0.0002686444],"domain_scores_gemma":[0.9996672,0.00005049114,0.000007256619,0.0002205932,0.00001038135,0.00004407347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002536474,0.00004004442,0.00882299,0.0001016254,0.000201345,0.0003511346,0.000368767,0.8079194,0.01982249,0.02248489,0.03214264,0.1077194],"study_design_scores_gemma":[0.0002448069,0.0000190504,0.00663875,0.00000261233,0.000006707725,0.000007297008,0.00009385071,0.9736856,0.005207181,0.000467906,0.01344311,0.000183114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9809631,0.00003236229,0.0007075334,0.0004543464,0.0002121269,0.00008673681,0.000005402423,0.007340416,0.01019797],"genre_scores_gemma":[0.9959682,0.00001685536,0.00015959,0.0001019171,0.00003722014,0.000005802551,0.000006372584,0.00002770972,0.003676315],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1657663,"threshold_uncertainty_score":0.999343,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4214496626","doi":"10.1109/tvt.2022.3151651","title":"Highway Decision-Making and Motion Planning for Autonomous Driving via Soft Actor-Critic","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":130,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Tech University; University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Chongqing; National Natural Science Foundation of China","keywords":"Reinforcement learning; Motion planning; Cruise control; Action (physics); Engineering; Optimal control; Motion (physics); Controller (irrigation); Vehicle dynamics; Control (management); Computer science; Simulation; Control engineering; Artificial intelligence; Automotive engineering; Robot","retraction":null,"screen_n_in":null,"score":{"opus":0.00642917467920485,"gpt":0.2252697442058677,"spread":0.2188405695266628,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002099017,0.0002645142,0.0003130501,0.0007876026,0.0009076399,0.00001962998,0.0003029844,0.0004061287,0.00006148263],"category_scores_gemma":[0.00001908104,0.0003182426,0.00009901691,0.0005619489,0.000147546,0.0001215091,0.00001127854,0.0009699686,0.000009597015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002862833,"about_ca_system_score_gemma":0.00002623235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001719902,"about_ca_topic_score_gemma":0.000008503066,"domain_scores_codex":[0.998593,0.00002667467,0.0003433131,0.0004295367,0.0001418491,0.0004655916],"domain_scores_gemma":[0.9992097,0.0002478714,0.0000515814,0.000402972,0.00004117274,0.0000466722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000359651,0.00009213988,0.0001157415,0.0000407275,0.0001273923,0.00004734104,0.0001545352,0.5174728,0.01308572,0.0008927816,0.00005159057,0.4678833],"study_design_scores_gemma":[0.001293575,0.0005564114,0.0003709039,0.00011408,0.0001596306,0.000680163,0.0006109292,0.9320643,0.03852108,0.01637096,0.008378214,0.0008797612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2925339,0.000292443,0.7038337,0.0002928239,0.0004806822,0.0003098056,0.00002300488,0.002206703,0.00002693771],"genre_scores_gemma":[0.9924319,0.00001785732,0.006873925,0.00006099918,0.00001950093,0.0004943376,0.000004414426,0.0000744763,0.00002252537],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6998981,"threshold_uncertainty_score":0.999927,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034269714","doi":"10.1109/tiv.2020.3002505","title":"Learning to Drive by Imitation: An Overview of Deep Behavior Cloning Methods","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Vehicles","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":119,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Modular design; Artificial intelligence; Affordance; Pipeline (software); Deep learning; Orientation (vector space); Task (project management); Human–computer interaction; Machine learning; Systems engineering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.05395145152887176,"gpt":0.3301521474273487,"spread":0.2762006958984769,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001614146,0.0001945545,0.0002644173,0.0001167695,0.0001314894,0.00001471508,0.0002175829,0.0001703006,0.0001830415],"category_scores_gemma":[0.000009770971,0.0002169295,0.000112805,0.0003439316,0.00005597415,0.0001373915,0.000002210161,0.0004941436,0.00007038296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000652221,"about_ca_system_score_gemma":0.00001101705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001196347,"about_ca_topic_score_gemma":0.00001432712,"domain_scores_codex":[0.9989091,0.0001005898,0.0003821805,0.000256219,0.0001268623,0.0002250243],"domain_scores_gemma":[0.9994321,0.0001252899,0.00004561966,0.0001856921,0.00005283453,0.0001584451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003627314,0.00008395906,0.00006706535,0.00004750479,0.00006697882,0.000002705283,0.00344702,0.3369323,0.07726204,0.0001130569,0.00002508277,0.581916],"study_design_scores_gemma":[0.0001324444,0.0005572767,0.000180379,0.00003269966,0.00008401988,0.000003927298,0.001382956,0.1158645,0.8795176,0.00005464232,0.001921464,0.0002681393],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.223871,0.000380863,0.7745942,0.0001719194,0.0001371385,0.0001947508,0.0000147084,0.0005466858,0.00008869224],"genre_scores_gemma":[0.9768738,0.0003972299,0.02238308,0.0001672771,0.00001858209,0.00008172124,0.00000523982,0.00004576111,0.00002735882],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8022556,"threshold_uncertainty_score":0.8846129,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3216996634","doi":"10.1016/j.aap.2021.106500","title":"A proactive lane-changing risk prediction framework considering driving intention recognition and different lane-changing patterns","year":2021,"lang":"en","type":"article","venue":"Accident Analysis & Prevention","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":117,"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":"National Key Research and Development Program of China; Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Bridge (graph theory); Computer science; Advanced driver assistance systems; Artificial neural network; Artificial intelligence; Machine learning; Feature (linguistics); Driving simulator","retraction":null,"screen_n_in":null,"score":{"opus":0.01271813641231024,"gpt":0.2226007970779327,"spread":0.2098826606656225,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004129404,0.0002386428,0.0003574272,0.0008283681,0.0002799532,0.00009334541,0.0000745328,0.0002560044,0.0002122118],"category_scores_gemma":[0.0001405255,0.0002635648,0.0002455188,0.0008494749,0.00002180423,0.000375352,0.0001232737,0.0004706821,0.00001646914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001659311,"about_ca_system_score_gemma":0.000008480538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000278103,"about_ca_topic_score_gemma":0.00118877,"domain_scores_codex":[0.9984373,0.0001489981,0.0004425929,0.0004142206,0.0001855953,0.0003713273],"domain_scores_gemma":[0.9992744,0.0001338591,0.0001813083,0.000265502,0.00008174829,0.00006318455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009934842,0.00005730213,0.9267594,0.00002399773,0.002292042,0.00001961136,0.001321002,0.00226606,0.001167832,0.0001313677,0.00000464991,0.06594682],"study_design_scores_gemma":[0.0005844463,0.00006383483,0.8105728,0.0006066818,0.004302175,0.00004264994,0.00438666,0.1469207,0.01371547,0.01817941,0.00002528001,0.0005998478],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6130858,0.0002252446,0.3859982,0.00002503114,0.0001038634,0.000140985,0.000003556434,0.0003694565,0.0000479183],"genre_scores_gemma":[0.9967909,0.0009884065,0.001472773,0.00001083964,0.00008408133,0.0000735705,0.0004513837,0.00003107459,0.00009698024],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3845254,"threshold_uncertainty_score":0.9999816,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3104639963","doi":"10.1007/s42154-020-00113-1","title":"Deep Reinforcement Learning Enabled Decision-Making for Autonomous Driving at Intersections","year":2020,"lang":"en","type":"article","venue":"Automotive Innovation","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":112,"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":"Reinforcement learning; Computer science; Intersection (aeronautics); Markov decision process; Process (computing); Focus (optics); Artificial intelligence; Generalization; Convolutional neural network; Crash; Path (computing); Deep learning; Machine learning; Markov process; Transport engineering; Engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01179573186215257,"gpt":0.2403560624740193,"spread":0.2285603306118668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001958273,0.0001795396,0.0001936147,0.0002340575,0.0003338736,0.00002631413,0.0001456081,0.0001679212,0.0001442087],"category_scores_gemma":[0.0005849319,0.000203113,0.00005695332,0.0008502669,0.00003860046,0.0002334174,0.00009528708,0.0003297929,0.00007194983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004217894,"about_ca_system_score_gemma":0.00002375302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001995962,"about_ca_topic_score_gemma":0.00001680992,"domain_scores_codex":[0.9988736,0.0000138309,0.0004679496,0.0002532712,0.0001016773,0.0002896727],"domain_scores_gemma":[0.9993138,0.000197777,0.0001182971,0.0001320059,0.0002074789,0.00003066338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003972974,0.00001114579,0.00251002,0.00004319846,0.0001102721,0.000003817044,0.00209369,0.9206206,0.005113729,0.007029074,0.0007483811,0.06167632],"study_design_scores_gemma":[0.0003915582,0.0001376045,0.002955345,0.00005046545,0.0000171922,0.000005277557,0.000309084,0.9845968,0.005233247,0.001073396,0.005005274,0.0002247532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2522728,0.00001982663,0.7431313,0.0003230483,0.0002281536,0.0003133498,8.903955e-7,0.001874891,0.001835771],"genre_scores_gemma":[0.9932175,0.000005515919,0.006130212,0.0002967431,0.00009237578,0.00008915491,0.00003905184,0.00004328482,0.00008617998],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7409447,"threshold_uncertainty_score":0.8282709,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098380626","doi":"10.5539/mas.v8n1p88","title":"Driving Behavior and Traffic Safety: An Acceleration-Based Safety Evaluation Procedure for Smartphones","year":2014,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":110,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; Global Positioning System; Acceleration; Accelerometer; Usability; Warning system; Mobile device; Transport engineering; Simulation; Automotive engineering; Real-time computing; Human–computer interaction; Telecommunications; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0133053312685987,"gpt":0.2446282977562307,"spread":0.231322966487632,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001221151,0.0001531123,0.0001519107,0.0001254078,0.000573368,0.00006759756,0.0002632412,0.0001224546,0.00001123059],"category_scores_gemma":[0.00004478394,0.0001547398,0.0000197581,0.0002322636,0.0002538693,0.0002483279,0.00002363279,0.0001261418,0.000004139532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001161964,"about_ca_system_score_gemma":0.0001246975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.094822e-7,"about_ca_topic_score_gemma":0.00005889988,"domain_scores_codex":[0.9987907,0.00001170508,0.0002202962,0.0004057968,0.0002586936,0.0003127533],"domain_scores_gemma":[0.9994559,0.00005931117,0.00004080399,0.0002796466,0.00007630484,0.00008803827],"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":[0.0000328813,0.00005101239,0.0008038421,0.00003761299,0.000004153414,1.218521e-7,0.0006275714,0.2926168,0.2051443,0.002693545,0.000008970175,0.4979792],"study_design_scores_gemma":[0.0005267833,0.00003569676,0.02086812,0.000006520097,0.00002250794,0.000001579054,0.00003607338,0.9675467,0.009797611,0.0008549283,0.0001104651,0.0001930327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6303424,0.00001815674,0.3679426,0.00008034497,0.00006777998,0.0006723601,0.000004111591,0.0004135928,0.0004586474],"genre_scores_gemma":[0.9940134,0.000002713708,0.005503662,0.00005743075,0.00003478495,0.0003389648,0.00001924479,0.00002212992,0.000007676043],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6749299,"threshold_uncertainty_score":0.6310105,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3209562871","doi":"10.1109/tvt.2021.3121985","title":"Driving Tasks Transfer Using Deep Reinforcement Learning for Decision-Making of Autonomous Vehicles in Unsignalized Intersection","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Intersection (aeronautics); Reinforcement learning; Task (project management); Transfer of learning; Computer science; Engineering; Artificial intelligence; Transport engineering; Systems engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.009138235964359212,"gpt":0.2388026039510148,"spread":0.2296643679866556,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002162914,0.0002621233,0.0004609404,0.0009372163,0.0001807776,0.0000125582,0.0002015805,0.0006678236,0.0000710359],"category_scores_gemma":[0.00003809069,0.0003100036,0.000204254,0.0008860273,0.0001349985,0.0001261227,0.000004455746,0.0008166173,0.000004466026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003512635,"about_ca_system_score_gemma":0.00006698487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007456531,"about_ca_topic_score_gemma":0.0002048226,"domain_scores_codex":[0.9983858,0.0000418043,0.0006504362,0.0003722163,0.0001328454,0.0004168535],"domain_scores_gemma":[0.9992761,0.0001917588,0.000055108,0.0003446545,0.0001035953,0.00002878916],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005063226,0.00006117587,0.00008475172,0.00005161368,0.0001107882,0.00002740179,0.0001947461,0.8259463,0.09549447,0.0003717114,0.000001056879,0.07760531],"study_design_scores_gemma":[0.0007663199,0.0001307711,0.00004293544,0.0003212606,0.00006569026,0.00007308867,0.0005111307,0.6877621,0.3089426,0.0009506832,0.0001866538,0.0002467649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4243772,0.0001594973,0.5745441,0.0000447682,0.0001904612,0.000207731,0.000001478619,0.0004443448,0.00003048356],"genre_scores_gemma":[0.9914737,0.00007262832,0.008243633,0.00002148607,0.00001008544,0.0001030242,0.000003142018,0.00005921186,0.00001303035],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5670966,"threshold_uncertainty_score":0.9999352,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2022826790","doi":"10.1109/itsc.2010.5625287","title":"Threat assessment design for driver assistance system at intersections","year":2010,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":104,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; Ford Motor Company","keywords":"Computer science; Advanced driver assistance systems; Computer security; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01097604688600558,"gpt":0.2311919297908322,"spread":0.2202158829048266,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000106618,0.00008916891,0.0001021332,0.00003862472,0.0001280924,0.000008323006,0.0001027718,0.0001437637,0.00009983035],"category_scores_gemma":[0.000003626803,0.00008040516,0.00004566881,0.00004957437,0.00003532831,0.00005693244,0.00002076501,0.0001752166,0.00004789738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001661186,"about_ca_system_score_gemma":0.00001011363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000410933,"about_ca_topic_score_gemma":0.00023114,"domain_scores_codex":[0.9995654,0.0000056004,0.0001165468,0.0001183646,0.00003643173,0.0001576723],"domain_scores_gemma":[0.9996689,0.00006032227,0.00001415269,0.0002052842,0.00002094616,0.00003037871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007282354,0.0001132052,0.02052177,0.0003620471,0.00053055,0.00001950957,0.0003903227,0.02561301,0.2500375,0.64992,0.03470241,0.0177169],"study_design_scores_gemma":[0.0009660072,0.0001145953,0.02486526,0.00003282151,0.00006957875,0.00007592329,0.0004156622,0.8725098,0.07280035,0.001181743,0.02641838,0.000549897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1266146,0.00001226695,0.8505059,0.00007476429,0.0006667198,0.000250562,0.000006054488,0.001476376,0.02039276],"genre_scores_gemma":[0.9588299,0.000002411095,0.03964066,0.00001106883,0.00003154108,0.00012242,0.000002614043,0.00001750209,0.001341911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8468968,"threshold_uncertainty_score":0.3278827,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2909761845","doi":"10.1109/iros.2018.8594388","title":"Deep Multi-Sensor Lane Detection","year":2018,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":103,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Computer vision; Artificial intelligence; Field (mathematics); Image (mathematics); Artificial neural network; Lidar; Remote sensing; Geography; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.008670715388683263,"gpt":0.2063909118632159,"spread":0.1977201964745327,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00003305632,0.00005512647,0.00005235661,0.00003610922,0.00004835334,0.00000337913,0.00005241528,0.0001050187,0.0002449282],"category_scores_gemma":[0.000006506642,0.0000508248,0.00001518157,0.00006515835,0.00004329688,0.00003314745,0.00001015668,0.00008641692,0.0009875163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002002585,"about_ca_system_score_gemma":0.000001376023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008898291,"about_ca_topic_score_gemma":0.0002865759,"domain_scores_codex":[0.9997175,0.000003582171,0.00006742127,0.00006871155,0.00002265278,0.0001201192],"domain_scores_gemma":[0.9998375,0.00000743007,0.00000517839,0.0001179379,0.00001269329,0.00001928968],"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":[0.0000285771,0.00007011387,0.004536102,0.00003751789,0.0001334869,0.00001915719,0.0005438744,0.00251565,0.1896204,0.003560367,0.0006528171,0.7982819],"study_design_scores_gemma":[0.0003371701,0.00006555405,0.01607628,0.000002316383,0.000007334342,0.00002534975,0.00007035979,0.6864879,0.2829315,0.0002403948,0.01356639,0.000189473],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2903892,0.00004377355,0.685932,0.00004514145,0.0002767826,0.00006050999,4.699371e-7,0.002454901,0.02079723],"genre_scores_gemma":[0.9911233,0.000006850998,0.008184463,0.00003442525,0.00006418561,0.000003631337,5.860417e-7,0.00001107861,0.0005714912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7980925,"threshold_uncertainty_score":0.9997903,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386066695","doi":"10.1109/cvpr52729.2023.01319","title":"ReasonNet: End-to-End Driving with Temporal and Global Reasoning","year":2023,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":94,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; End-to-end principle; Benchmark (surveying); Artificial intelligence; Anticipation (artificial intelligence); Perception; Exploit; Event (particle physics); Adverse weather; Software deployment; Computer vision; Machine learning; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.005094810900067455,"gpt":0.203345527121647,"spread":0.1982507162215795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000127968,0.0001270725,0.0001352792,0.00006079249,0.00008713465,0.00002007812,0.00009691263,0.0001020501,0.00006700006],"category_scores_gemma":[0.00001671061,0.000110616,0.00001505484,0.0004256811,0.00004687066,0.00008483482,0.00006782605,0.0001267899,0.0001183548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005088665,"about_ca_system_score_gemma":0.00001434794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006012905,"about_ca_topic_score_gemma":0.0004339681,"domain_scores_codex":[0.9993227,0.000007093206,0.0001058979,0.0001859904,0.00008057975,0.0002977472],"domain_scores_gemma":[0.9996901,0.00002506013,0.00001090955,0.0001766236,0.00001004647,0.00008725714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003422482,0.00001674861,0.7960687,0.00005703639,0.000187536,0.0002484624,0.0005895442,0.01132628,0.0009070722,0.04345544,0.006265494,0.1408435],"study_design_scores_gemma":[0.0007872956,0.0001916179,0.8529109,0.0001480707,0.00003570427,0.0002186737,0.0009766321,0.123342,0.001673844,0.001455442,0.01744571,0.0008140383],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9668089,0.00006149689,0.00640231,0.0004528213,0.00005909482,0.0001030865,0.000005788893,0.003095076,0.02301147],"genre_scores_gemma":[0.9940292,0.0000179937,0.005473083,0.00004228551,0.00002675288,0.00001139959,0.00000648537,0.00002051263,0.0003722897],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1400295,"threshold_uncertainty_score":0.4510791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3080564557","doi":"10.1177/0278364920950795","title":"On infusing reachability-based safety assurance within planning frameworks for human–robot vehicle interactions","year":2020,"lang":"en","type":"article","venue":"The International Journal of Robotics Research","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Reachability; Computer science; Leverage (statistics); Trajectory; Active safety; Collision; Anticipation (artificial intelligence); Controller (irrigation); Planner; Collision avoidance; Robot; Advanced driver assistance systems; Simulation; Engineering; Computer security; Automotive engineering; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.08787062107509358,"gpt":0.3845815219330926,"spread":0.2967109008579991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001791128,0.0001065037,0.000178701,0.0001877343,0.000211019,0.00007239651,0.0008506123,0.0001452081,0.00001977136],"category_scores_gemma":[0.001281929,0.00008509314,0.00009805657,0.0002140478,0.0001486634,0.0001280958,0.00007558408,0.002348348,0.00001066093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003351103,"about_ca_system_score_gemma":0.0001514757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000039646,"about_ca_topic_score_gemma":0.000008837033,"domain_scores_codex":[0.9984068,0.0001015054,0.0004862939,0.0001149976,0.0006692595,0.0002211604],"domain_scores_gemma":[0.9974762,0.001328017,0.000127276,0.0001633692,0.0008104261,0.00009474978],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003368738,0.00004134268,0.0002534291,0.00001636468,0.0001236909,0.00001945626,0.0006864867,0.9783883,0.00703176,0.01017008,0.001363611,0.001568575],"study_design_scores_gemma":[0.001314107,0.0005082421,0.001116849,0.0003868035,0.00002144991,0.00003540001,0.0005504726,0.9550594,0.009238666,0.02909538,0.002485815,0.0001873922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3292492,0.0002182579,0.6188309,0.04870252,0.001146735,0.0003777668,0.00002576134,0.0001640809,0.001284818],"genre_scores_gemma":[0.9919518,0.000009789163,0.007288222,0.0003814322,0.000307845,0.000005589838,0.000004906139,0.00002548719,0.00002493811],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6627026,"threshold_uncertainty_score":0.9999533,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4384161746","doi":"10.1109/tits.2023.3291196","title":"Pedestrian Trajectory Prediction in Pedestrian-Vehicle Mixed Environments: A Systematic Review","year":2023,"lang":"en","type":"review","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Pedestrian; Trajectory; Computer science; Machine learning; Artificial intelligence; Motion (physics); Data mining; Transport engineering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.04420379350282414,"gpt":0.2710701641497105,"spread":0.2268663706468863,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007894896,0.0008696411,0.003044026,0.0009811361,0.0001352543,0.00003966436,0.0004673529,0.0009837161,0.00007543481],"category_scores_gemma":[0.000009787058,0.0008419866,0.000842818,0.001216253,0.00007431139,0.0002000482,4.709494e-7,0.001281659,0.001257277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008208068,"about_ca_system_score_gemma":0.0001210978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007492999,"about_ca_topic_score_gemma":0.0003078416,"domain_scores_codex":[0.9944905,0.0003898342,0.003377912,0.0007009436,0.000505291,0.0005354923],"domain_scores_gemma":[0.9982201,0.0003575606,0.0004431758,0.0007960551,0.00002760939,0.0001555185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000007331168,0.0001382205,9.80596e-7,0.9474585,0.0006920252,0.00005494289,0.0001807113,0.03318589,0.000001373563,0.00002274329,0.0001218787,0.01813542],"study_design_scores_gemma":[0.0005554454,0.0001763494,0.000008156027,0.8973852,0.005766068,0.00005710547,0.0004610007,0.004476113,0.00005609008,0.000009145568,0.08963931,0.001410024],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001533497,0.8561488,0.133981,0.000006549717,0.001983827,0.00567332,0.0008488343,0.001285153,0.00005714543],"genre_scores_gemma":[0.003742459,0.989867,0.00001156214,0.000009886483,0.00005019428,0.004794641,0.0003281888,0.0002395528,0.000956563],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.1339694,"threshold_uncertainty_score":0.9995204,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3036171677","doi":"10.1109/tiv.2020.3003889","title":"Real-Time Driver Maneuver Prediction Using LSTM","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Vehicles","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":91,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Advanced driver assistance systems; Position (finance); Gaze; Simulation; Artificial intelligence; Driving simulator; Driving simulation; Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.02099235853308386,"gpt":0.2206843270319956,"spread":0.1996919684989117,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0000633384,0.0002272201,0.0002080405,0.0001251561,0.0001768343,0.00001999972,0.0001824878,0.0002516772,0.0005567538],"category_scores_gemma":[0.000001837479,0.0002457639,0.000130273,0.0002538119,0.00009211487,0.0001647319,0.000001791608,0.0004397427,0.0007960107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000141842,"about_ca_system_score_gemma":0.00001918973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001885805,"about_ca_topic_score_gemma":0.000004213834,"domain_scores_codex":[0.9989335,0.00002889649,0.0003191393,0.0002770922,0.0001562675,0.0002851087],"domain_scores_gemma":[0.9995397,0.00004714549,0.00003031445,0.0002245628,0.00003075265,0.0001275279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001025541,0.00009656658,0.0001070317,0.00005541514,0.0002091739,0.00002178072,0.0008321779,0.777604,0.1892394,0.0001203412,0.0006482101,0.03096332],"study_design_scores_gemma":[0.0001775718,0.0001170364,0.000173376,0.00002688238,0.00006666474,0.00001324334,0.00009532318,0.5970087,0.4005619,0.00009328107,0.001426664,0.000239368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5217244,0.00002832981,0.4747824,0.0001763632,0.0003371598,0.0001914266,0.00005899497,0.001818276,0.0008826252],"genre_scores_gemma":[0.997981,0.0003603005,0.0012344,0.0001097733,0.00007636902,0.0000173119,0.000004039629,0.00005730197,0.0001595565],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4762565,"threshold_uncertainty_score":0.9999995,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391516317","doi":"10.1007/978-981-99-8850-1_1","title":"MARS: An Instance-Aware, Modular and Realistic Simulator for Autonomous Driving","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":89,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Modular design; Mars Exploration Program; Simulation; Human–computer interaction; Computer graphics (images); Programming language; Astrobiology","retraction":null,"screen_n_in":null,"score":{"opus":0.009681250064464578,"gpt":0.226166072874737,"spread":0.2164848228102724,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002843631,0.0003746176,0.0003885354,0.0004049114,0.0001350208,0.0001249397,0.0005564249,0.0004724619,0.000006620963],"category_scores_gemma":[0.00002064991,0.0003747172,0.00005706909,0.000151875,0.0004590031,0.0001922375,0.0002120708,0.0006382086,0.000006723939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002569166,"about_ca_system_score_gemma":0.0001001386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005000046,"about_ca_topic_score_gemma":0.00009579269,"domain_scores_codex":[0.9983328,0.000004178484,0.0003107417,0.0007609263,0.0001699672,0.0004214022],"domain_scores_gemma":[0.9990777,0.0001876001,0.00004714479,0.0005433744,0.00004848951,0.00009573391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003124464,0.000005002556,0.00002603335,0.0001648886,0.00001977086,0.00004451915,0.0002284055,0.6666367,0.00007725851,0.0194844,0.000004365615,0.3133055],"study_design_scores_gemma":[0.0001005361,0.00007262397,0.00005037254,0.0002208972,0.00001574788,0.00002347879,1.809566e-7,0.8495232,0.0001590162,0.1474907,0.001983252,0.000360004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002490159,0.0009594217,0.9937518,0.00009402828,0.0008656848,0.0003675673,0.00003102665,0.0007564942,0.0006837771],"genre_scores_gemma":[0.9602074,0.00006729022,0.03908652,0.000124138,0.0002387194,0.00001537433,0.0000123364,0.00007940749,0.0001688103],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9577172,"threshold_uncertainty_score":0.9998705,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3173280621","doi":"10.1109/cvpr46437.2021.00095","title":"SceneGen: Learning to Generate Realistic Traffic Scenes","year":2021,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Heuristics; Computer science; Fidelity; Artificial intelligence; Set (abstract data type); Autoregressive model; Perception; Scale (ratio); Machine learning; Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.007642319670971317,"gpt":0.201149160636231,"spread":0.1935068409652597,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007021886,0.0001054857,0.0001301306,0.00005241855,0.00008780802,0.00001784334,0.00008966197,0.0001080879,0.0002999903],"category_scores_gemma":[0.00003181683,0.0001102372,0.00003338879,0.0002379482,0.00001678822,0.0000335477,0.00003416191,0.0001859347,0.0003437033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003607506,"about_ca_system_score_gemma":0.00002328633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003416209,"about_ca_topic_score_gemma":0.00005052463,"domain_scores_codex":[0.9993877,0.00001800091,0.000137088,0.0001657892,0.00005492179,0.0002364676],"domain_scores_gemma":[0.9996939,0.00002032962,0.000007083602,0.0001782879,0.00003144353,0.00006895536],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002896131,0.00001200016,0.0002696948,0.00002128966,0.00003239464,0.00007781334,0.0001559509,0.9134431,0.01460872,0.003524042,0.001601941,0.06625015],"study_design_scores_gemma":[0.0005213239,0.00008085202,0.005603078,0.00004621935,0.00004229883,0.0001408094,0.0006080694,0.7019793,0.2128822,0.0003413314,0.07684357,0.0009108938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9678076,0.0005210227,0.01316108,0.0006240353,0.0002281383,0.00006230624,0.00000234113,0.002200287,0.0153932],"genre_scores_gemma":[0.9929676,0.00008262653,0.003953463,0.0001542612,0.00005737421,0.000008852396,0.00001078276,0.00002582744,0.002739209],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2114638,"threshold_uncertainty_score":0.4495341,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3119361198","doi":"10.1109/iv47402.2020.9304591","title":"Do They Want to Cross? Understanding Pedestrian Intention for Behavior Prediction","year":2020,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":87,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pedestrian; Anticipation (artificial intelligence); Computer science; Task (project management); Trajectory; Action (physics); Scale (ratio); Work (physics); Point (geometry); Estimation; Human behavior; Artificial intelligence; Machine learning; Human–computer interaction; Transport engineering; Engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.06394491759693305,"gpt":0.2703499997218086,"spread":0.2064050821248755,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007144092,0.00008052967,0.00008596863,0.00004112517,0.00008709985,0.00002917024,0.0000824691,0.0001107868,0.0000451157],"category_scores_gemma":[0.00002265537,0.00007735955,0.00004627473,0.00007283181,0.00001450649,0.00009161219,0.0000210006,0.0001002814,0.00003225642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001217956,"about_ca_system_score_gemma":0.00000672062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004983733,"about_ca_topic_score_gemma":0.00002085945,"domain_scores_codex":[0.9995099,0.000003621848,0.0001501805,0.0001363581,0.00004628223,0.0001536331],"domain_scores_gemma":[0.9998063,0.00001428789,0.00001164174,0.00008764987,0.00001489623,0.00006524789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000896378,0.0002896684,0.2040747,0.000789047,0.0005168317,0.00004253225,0.01221141,0.07812225,0.1711883,0.4020875,0.01458093,0.1152005],"study_design_scores_gemma":[0.009010298,0.003423103,0.1563637,0.0001949625,0.0005484399,0.00006603521,0.01639598,0.6128529,0.1146043,0.05781638,0.0260779,0.002646039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3832135,0.00001272432,0.6114186,0.0008819307,0.0002257191,0.0004429815,0.00002997538,0.00137028,0.002404236],"genre_scores_gemma":[0.9985293,0.000006966658,0.001189306,0.0000676847,0.00004820709,0.00007011058,0.00001129013,0.00001848485,0.00005867433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6153157,"threshold_uncertainty_score":0.3154631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891742881","doi":"10.1109/tte.2018.2870819","title":"A Cognitive Advanced Driver Assistance Systems Architecture for Autonomous-Capable Electrified Vehicles","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Transportation Electrification","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":86,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Canada Excellence Research Chairs, Government of Canada; Eurostars; Canada Research Chairs","keywords":"Architecture; Cognitive architecture; Acceleration; Computer science; Advanced driver assistance systems; Control (management); Energy management; Battery (electricity); Energy (signal processing); Automotive engineering; Cognition; Simulation; Engineering; Artificial intelligence; Power (physics)","retraction":null,"screen_n_in":null,"score":{"opus":0.008988577682531607,"gpt":0.2257820151622249,"spread":0.2167934374796933,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001612103,0.0002784375,0.0002617583,0.0002834035,0.0004077693,0.0000288819,0.0001603233,0.0003378499,0.0000236772],"category_scores_gemma":[0.000005236853,0.0003136169,0.0001215084,0.0005610062,0.0001386361,0.0002230415,1.271543e-8,0.0004170861,0.00004940206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001710947,"about_ca_system_score_gemma":0.00007390469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001061078,"about_ca_topic_score_gemma":0.0001765423,"domain_scores_codex":[0.998496,0.00003383653,0.000457334,0.0004244061,0.0001647777,0.0004236333],"domain_scores_gemma":[0.999163,0.0001557159,0.0001062432,0.0002534171,0.0002484861,0.0000731067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009220701,0.0002376712,0.00002413786,0.000154976,0.000285765,0.000001758889,0.001302646,0.1151768,0.7339944,0.003085,0.0001582391,0.1446565],"study_design_scores_gemma":[0.001435927,0.0004518746,0.002049943,0.00006397936,0.0001444869,0.000003973616,0.0001370588,0.03221035,0.9605572,0.0005341285,0.001973149,0.0004379097],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1865972,0.0001601809,0.8103213,0.00009602831,0.000328691,0.0009688204,0.0001787116,0.001099839,0.0002492855],"genre_scores_gemma":[0.9968672,0.0001142252,0.001468205,0.00005759334,0.00006282315,0.0008658368,0.0001248394,0.00006968107,0.0003695345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8102701,"threshold_uncertainty_score":0.9999316,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4289792821","doi":"10.1109/tiv.2022.3196396","title":"Verification and Validation Methods for Decision-Making and Planning of Automated Vehicles: A Review","year":2022,"lang":"en","type":"review","venue":"IEEE Transactions on Intelligent Vehicles","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":84,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Systems engineering; Hierarchy; Range (aeronautics); Reliability engineering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.06416434948146378,"gpt":0.3921944433084235,"spread":0.3280300938269597,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007802529,0.0003561676,0.001042195,0.0003878206,0.0002196046,0.00001982883,0.000204423,0.0003278172,0.00005830862],"category_scores_gemma":[0.00007146779,0.0003519997,0.0002390705,0.0003499218,0.00008968839,0.00007713048,0.000005139974,0.0005010397,0.000003578434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001371902,"about_ca_system_score_gemma":0.00004677259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001997515,"about_ca_topic_score_gemma":6.331014e-7,"domain_scores_codex":[0.9982271,0.0001725898,0.0008861354,0.0003874779,0.0001198033,0.0002068978],"domain_scores_gemma":[0.9971547,0.002175431,0.0002346373,0.0003439267,0.0000431494,0.00004813202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001396554,0.00002812972,2.220846e-7,0.01579836,0.0001828692,7.8635e-7,0.00009818932,0.002275187,0.0000118508,0.00004273986,0.00006554343,0.9814821],"study_design_scores_gemma":[0.0001880913,0.0002395889,0.000003244541,0.05945416,0.002118841,0.00009313659,0.0001588082,0.07538985,0.001830143,0.0005603418,0.8591122,0.0008515907],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000348359,0.5726779,0.4258933,0.00000505481,0.0001872,0.0006992207,0.00006088892,0.0004249327,0.00001666622],"genre_scores_gemma":[0.00155723,0.9771098,0.02061748,0.00001757894,0.00001348605,0.0005781038,0.00002099524,0.00007618123,0.000009093554],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9806306,"threshold_uncertainty_score":0.9998932,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3191907322","doi":"10.1109/iccv48922.2021.01531","title":"Bifold and Semantic Reasoning for Pedestrian Behavior Prediction","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":81,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Pedestrian; Artificial intelligence; Modalities; Machine learning; Benchmark (surveying); Categorical variable; Trajectory; Representation (politics); Encoding (memory); Decoding methods; Parsing; Human–computer interaction","retraction":null,"screen_n_in":null,"score":{"opus":0.02191209137745254,"gpt":0.269649960127515,"spread":0.2477378687500624,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001365042,0.0001929691,0.0002033037,0.000142306,0.0001168541,0.0001247461,0.0002024396,0.0001875373,0.0003018306],"category_scores_gemma":[0.0000205398,0.0002057987,0.00007727367,0.0001041206,0.00003828004,0.0001685775,0.00007437328,0.0002671535,0.00004814083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009146622,"about_ca_system_score_gemma":0.00005078973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006392918,"about_ca_topic_score_gemma":0.00002000015,"domain_scores_codex":[0.9988861,0.00002669116,0.0003034066,0.00038293,0.0001941117,0.0002067297],"domain_scores_gemma":[0.9993626,0.00007916035,0.0000549543,0.0002221697,0.0002073155,0.00007379993],"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":[0.0002400829,0.0006631567,0.009706334,0.0002302772,0.0006066932,0.0004270674,0.0006456542,0.01085352,0.05154141,0.1066627,0.0187429,0.7996802],"study_design_scores_gemma":[0.00096147,0.0002392487,0.01266001,0.0002658742,0.000040153,0.0001073538,0.00005571801,0.9707589,0.007559524,0.001024201,0.006026237,0.0003013511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6803196,0.0001474637,0.3088081,0.001938653,0.004334182,0.0004373796,0.0001692567,0.0005894199,0.003255902],"genre_scores_gemma":[0.9922429,0.000237096,0.006322213,0.0001030547,0.0003441619,0.00005844114,0.0001218684,0.00002656322,0.0005436994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9599053,"threshold_uncertainty_score":0.8392226,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4376457019","doi":"10.1109/tits.2023.3270887","title":"Uncertainties in Onboard Algorithms for Autonomous Vehicles: Challenges, Mitigation, and Perspectives","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":81,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Risk analysis (engineering); Software deployment; Context (archaeology); Commercialization; Computer science; Systems engineering; Engineering; Transport engineering; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.04115902531664435,"gpt":0.2534863769107184,"spread":0.2123273515940741,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002340224,0.0002138855,0.0002692013,0.0004726943,0.0001263224,0.00002264347,0.000099843,0.0002241318,0.000006751721],"category_scores_gemma":[0.000002261397,0.0002362917,0.00008673389,0.0003499087,0.00009115667,0.0001464084,1.671337e-7,0.0002269293,0.00002629041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001443067,"about_ca_system_score_gemma":0.00002574794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004288524,"about_ca_topic_score_gemma":0.0003465198,"domain_scores_codex":[0.9987647,0.00002611004,0.0004784174,0.0003194376,0.0001317347,0.0002795877],"domain_scores_gemma":[0.9995058,0.000153858,0.00004115441,0.0001684814,0.00007096145,0.00005976214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005522958,0.00008835884,0.0001225259,0.0005096775,0.0002083528,0.000007776434,0.02345236,0.9199485,0.0006867981,0.007382169,0.0000654054,0.0474728],"study_design_scores_gemma":[0.002545674,0.0009322358,0.01583188,0.0006618804,0.0001715865,0.00001976607,0.1167396,0.7897555,0.06016336,0.002713027,0.008810581,0.001654897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.372869,0.00249662,0.6201136,0.000413312,0.0009988174,0.001054489,0.0002778211,0.001692975,0.00008338808],"genre_scores_gemma":[0.9951972,0.003602451,0.0002611465,0.000007094611,0.00004012108,0.0006471418,0.00002948513,0.00004627574,0.0001690934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6223282,"threshold_uncertainty_score":0.9635698,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388208052","doi":"10.1109/tiv.2023.3327715","title":"DriveLLM: Charting the Path Toward Full Autonomous Driving With Large Language Models","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Vehicles","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":80,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Path (computing); Computer science; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01539693520225278,"gpt":0.2261415528987847,"spread":0.2107446176965319,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002990766,0.000281805,0.0002288889,0.0002126111,0.0004111045,0.00004495598,0.0003485831,0.0001817601,0.00009343578],"category_scores_gemma":[0.000002811461,0.0002130553,0.0001255395,0.0005126926,0.0001056031,0.0001711267,0.000005049733,0.0006725855,0.0004611652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001086877,"about_ca_system_score_gemma":0.00002658214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001832611,"about_ca_topic_score_gemma":0.0001266748,"domain_scores_codex":[0.9985378,0.00004101875,0.0003272528,0.0003029046,0.0002070701,0.0005839546],"domain_scores_gemma":[0.999252,0.000156169,0.00004679286,0.0004312566,0.00003227174,0.00008156603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004857492,0.00009803852,0.00007246094,0.00005526778,0.00021983,0.00005932885,0.008616942,0.8916153,0.006179297,0.001174771,0.0001749889,0.09168517],"study_design_scores_gemma":[0.0002613741,0.0001377421,0.0001669824,0.00008161683,0.00005534133,0.00002909393,0.004595693,0.8827114,0.1103043,0.0004891419,0.0007785225,0.000388742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4235258,0.00008172196,0.5729529,0.0003178042,0.0002196148,0.0002201731,0.00002985812,0.002199298,0.0004528437],"genre_scores_gemma":[0.9987312,0.0002478949,0.0003459707,0.00008713261,0.00004592722,0.0001225408,0.000005768955,0.00007785385,0.0003357175],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5752054,"threshold_uncertainty_score":0.8688145,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3201745857","doi":"10.1109/tiv.2021.3117840","title":"An Enabling Trajectory Planning Scheme for Lane Change Collision Avoidance on Highways","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Vehicles","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Beijing Municipal Science and Technology Commission; Beijing Nova Program; Ministry of Science and Technology of the People's Republic of China","keywords":"Trajectory; Waypoint; Computer science; Control theory (sociology); Collision avoidance; Controller (irrigation); Quadratic programming; Acceleration; Kinematics; Collision; Motion planning; Real-time computing; Simulation; Mathematical optimization; Robot; Mathematics; Artificial intelligence; Control (management)","retraction":null,"screen_n_in":null,"score":{"opus":0.04845953061388596,"gpt":0.277147869064543,"spread":0.228688338450657,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001631399,0.0002502071,0.0002469292,0.0002014928,0.0003161448,0.00003450954,0.0001933625,0.0002839412,0.00004795065],"category_scores_gemma":[0.00000567624,0.000270601,0.0001299543,0.0002384921,0.00005142167,0.0001732576,0.000001112337,0.0004970996,0.00006643567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001433616,"about_ca_system_score_gemma":0.00002802685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007940069,"about_ca_topic_score_gemma":0.000037752,"domain_scores_codex":[0.9987735,0.00003675048,0.0002975635,0.0003706891,0.0001504135,0.0003710922],"domain_scores_gemma":[0.9992174,0.0002024042,0.00003551682,0.0003821437,0.00006507109,0.0000974483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004160041,0.0007133652,0.0001134486,0.0002480571,0.0002418709,0.00007427199,0.002136582,0.6970665,0.1484527,0.001408268,0.0003501661,0.1487787],"study_design_scores_gemma":[0.0003235317,0.0002899656,0.0001764554,0.0001629341,0.00002652126,0.00001166726,0.0004016174,0.1244051,0.8693715,0.0001572903,0.004351113,0.00032232],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4557616,0.0004694869,0.541162,0.0001148116,0.0006658076,0.0002787819,0.00008613736,0.001328815,0.0001325394],"genre_scores_gemma":[0.9955954,0.0003895974,0.003289736,0.0001871105,0.0001319446,0.0002200668,0.00002011251,0.00006594595,0.0001000836],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7209188,"threshold_uncertainty_score":0.9999746,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4383109074","doi":"10.1109/icra48891.2023.10160984","title":"GoRela: Go Relative for Viewpoint-Invariant Motion Forecasting","year":2023,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":78,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; ENCODE; Leverage (statistics); Inference; Invariant (physics); Artificial intelligence; Graph; Reference frame; Computation; Context (archaeology); Machine learning; Theoretical computer science; Frame (networking); Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0291254997773316,"gpt":0.224037517030781,"spread":0.1949120172534494,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002345636,0.00009688618,0.0001196901,0.00006535385,0.0001258401,0.00000870294,0.00007934733,0.0001594462,0.00004435352],"category_scores_gemma":[0.00007551367,0.00009098033,0.00005630285,0.0002473095,0.00003165737,0.000119761,0.0000278652,0.0001513374,0.0003477655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005032049,"about_ca_system_score_gemma":0.000007918541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002349735,"about_ca_topic_score_gemma":0.00001154093,"domain_scores_codex":[0.9994007,0.000006896361,0.0001740188,0.0001315159,0.00004052551,0.0002463215],"domain_scores_gemma":[0.9996862,0.0001222719,0.00001947823,0.0001249355,0.00001985701,0.00002719718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002980075,0.00003212727,0.001188402,0.0002590095,0.000311245,0.00003559775,0.001500806,0.09588736,0.002324198,0.5589293,0.02250784,0.3169943],"study_design_scores_gemma":[0.0002593588,0.00003172052,0.00148287,0.00001517439,0.00001377489,0.000006782238,0.00007195697,0.9622952,0.001789477,0.02780397,0.006091945,0.0001378125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07496046,0.0001076547,0.8851787,0.001519974,0.000429475,0.0005583186,0.00002099949,0.006295432,0.03092894],"genre_scores_gemma":[0.9869794,0.00002722506,0.01125378,0.000049439,0.00004200101,0.00008653739,0.00003063904,0.00003482268,0.001496213],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9120189,"threshold_uncertainty_score":0.4469938,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4381733133","doi":"10.1109/tits.2023.3285440","title":"Self-Learned Autonomous Driving at Unsignalized Intersections: A Hierarchical Reinforced Learning Approach for Feasible Decision-Making","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":76,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Artificial neural network; Motion planning; Machine learning; Collision avoidance; Collision; Simulation; Computer security; Robot","retraction":null,"screen_n_in":null,"score":{"opus":0.02080559067488945,"gpt":0.2610225130872331,"spread":0.2402169224123436,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004849454,0.00036947,0.0004579897,0.0007927323,0.0006661356,0.00006678366,0.0002499816,0.0004148826,0.00007262857],"category_scores_gemma":[0.00001392404,0.0003999526,0.0003476149,0.0009292836,0.00006611195,0.0002091137,0.000001045647,0.0006685826,0.0001626557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004590741,"about_ca_system_score_gemma":0.00005239827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001535974,"about_ca_topic_score_gemma":0.00005660093,"domain_scores_codex":[0.9976267,0.00007067486,0.0009468971,0.0005143192,0.0003045399,0.0005368599],"domain_scores_gemma":[0.9987373,0.0005906972,0.0001190936,0.0003219176,0.0001057417,0.0001252709],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000174889,0.00004108526,0.00005042251,0.000251254,0.0002601509,0.000007402201,0.002280042,0.9857355,0.0009851495,0.0006581742,0.00007739395,0.009478519],"study_design_scores_gemma":[0.0006500099,0.0001670916,0.00008618457,0.0002212811,0.0001087136,0.00002256915,0.001508679,0.9869733,0.006361732,0.00009741032,0.003363731,0.0004393058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08668124,0.00006584833,0.9056176,0.00002209128,0.001116459,0.001161469,0.00004392711,0.004888749,0.0004026116],"genre_scores_gemma":[0.9925624,0.0002214519,0.00487091,0.00001321093,0.00005240475,0.001031641,0.00009257611,0.0001183323,0.00103709],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9058812,"threshold_uncertainty_score":0.9998452,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3201917469","doi":"10.1109/iccv48922.2021.00753","title":"Where are you heading? Dynamic Trajectory Prediction with Expert Goal Examples","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Computer science; Inference; Trajectory; Machine learning; Artificial intelligence; Key (lock); Code (set theory)","retraction":null,"screen_n_in":null,"score":{"opus":0.01459402291113371,"gpt":0.2471229547466728,"spread":0.2325289318355391,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001089905,0.0003131705,0.0002962536,0.0001853591,0.0001255898,0.0001366725,0.0003936024,0.0002412806,0.00115879],"category_scores_gemma":[0.000006944572,0.0002991355,0.00009821956,0.0001771729,0.00007716074,0.0002754795,0.00007916955,0.0005119587,0.000155362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002926243,"about_ca_system_score_gemma":0.00008910846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001299012,"about_ca_topic_score_gemma":0.0002024097,"domain_scores_codex":[0.9983451,0.00005757236,0.000364834,0.0005445269,0.0003950431,0.0002929234],"domain_scores_gemma":[0.9990929,0.00006689963,0.00008729608,0.0003829821,0.0002717187,0.00009821751],"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":[0.0008998082,0.001741272,0.01094368,0.0003722713,0.002266982,0.002254874,0.003262013,0.1513586,0.1166103,0.03272814,0.08874165,0.5888205],"study_design_scores_gemma":[0.001096744,0.0003564173,0.0138444,0.0008086986,0.00001796384,0.0001755643,0.0003277181,0.9552458,0.005585648,0.0003841188,0.02160451,0.0005524223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.566689,0.0008002538,0.4071058,0.005954916,0.006477054,0.0004171504,0.0002595111,0.0016994,0.01059685],"genre_scores_gemma":[0.9928981,0.0006593517,0.004740049,0.0002243575,0.0003357824,0.00003527425,0.0001303189,0.00004683826,0.0009299132],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8038872,"threshold_uncertainty_score":0.9999461,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3094973372","doi":"10.1109/ojvt.2020.3036582","title":"A Review of Driving Simulation Technology and Applications","year":2020,"lang":"en","type":"review","venue":"IEEE Open Journal of Vehicular Technology","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto; McMaster University","funders":"","keywords":"Chassis; Powertrain; Computer science; Driving simulator; Simulation; Automotive engineering; Perception; Human–computer interaction; Systems engineering; Control engineering; Engineering; Aerospace engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02005849789594969,"gpt":0.3144009603268409,"spread":0.2943424624308912,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00048191,0.0004063059,0.002876651,0.001462537,0.00007270514,0.00001671683,0.001723128,0.001321555,0.00001693378],"category_scores_gemma":[0.0001718112,0.0003614261,0.0002849699,0.002234477,0.0003388729,0.0001529463,0.0003443824,0.00166358,0.00001790835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001181232,"about_ca_system_score_gemma":0.0002068625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.82806e-7,"about_ca_topic_score_gemma":6.857013e-7,"domain_scores_codex":[0.9975886,0.00006300991,0.001658349,0.0002934318,0.0001324475,0.0002641907],"domain_scores_gemma":[0.9977667,0.0001158621,0.001200855,0.0006059823,0.0002375307,0.00007310611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000110872,0.00002342128,0.000006859546,0.02280321,0.0003893218,0.00004998663,0.000003506075,0.0002055519,0.00002320963,0.001857317,0.0001327123,0.9745038],"study_design_scores_gemma":[0.0001772859,0.0001280391,3.810132e-7,0.0437494,0.000897267,0.001100535,0.00001223588,0.0003821187,0.00008774616,0.001662069,0.9515273,0.0002756273],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001323754,0.982049,0.01578414,0.0004461724,0.00009852158,0.001213632,0.00001183841,0.0002301227,0.0001533141],"genre_scores_gemma":[0.0007797734,0.9959008,0.003021556,0.00003458534,0.00005634446,0.0001212745,0.00000485972,0.00007430533,0.000006572918],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9742281,"threshold_uncertainty_score":0.999975,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3154724615","doi":"10.1016/j.trc.2021.103453","title":"A context-aware pedestrian trajectory prediction framework for automated vehicles","year":2021,"lang":"en","type":"article","venue":"Transportation Research Part C Emerging Technologies","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":73,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Pedestrian; Interpretability; Computer science; Trajectory; Context (archaeology); Machine learning; Block (permutation group theory); Artificial intelligence; Pedestrian detection; Resource (disambiguation); Focus (optics); Data mining; Engineering; Transport engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.05551739709267645,"gpt":0.3363987626836402,"spread":0.2808813655909637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004573383,0.0002051062,0.0002704386,0.0003608468,0.0004031482,0.00003518302,0.0003245902,0.0006452097,0.00004698779],"category_scores_gemma":[0.0002909713,0.000225884,0.0001073978,0.0009160154,0.0003269318,0.0001827686,0.00001460235,0.0009046559,0.00001992018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000104258,"about_ca_system_score_gemma":0.000108025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001565047,"about_ca_topic_score_gemma":0.0002613791,"domain_scores_codex":[0.9981871,0.00004952901,0.0004367969,0.0003976806,0.0003011582,0.0006276874],"domain_scores_gemma":[0.9988045,0.0003556396,0.0000430758,0.0004566048,0.0002916223,0.00004856164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000443775,0.0006827664,0.06610629,0.003338023,0.001563977,0.0005404557,0.005575461,0.06500531,0.03732517,0.2956715,0.06943078,0.4543165],"study_design_scores_gemma":[0.003186623,0.000585419,0.05289354,0.001095594,0.0001448312,0.00001773899,0.04080299,0.2540673,0.3478053,0.1183226,0.1794818,0.001596149],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8242317,0.00363148,0.115079,0.004594089,0.0005776741,0.001182313,0.0005641963,0.04990831,0.0002312337],"genre_scores_gemma":[0.9911205,0.001074851,0.006816493,0.00001381078,0.00003780835,0.0005792397,0.0002347695,0.00005300998,0.00006948833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4527204,"threshold_uncertainty_score":0.9211282,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2967833234","doi":"10.1016/j.trc.2019.08.003","title":"Risk-based autonomous vehicle motion control with considering human driver’s behaviour","year":2019,"lang":"en","type":"article","venue":"Transportation Research Part C Emerging Technologies","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":73,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Innovate UK","keywords":"Trajectory; Motion (physics); Path (computing); Control (management); Computer science; Active safety; Vehicle dynamics; Motion planning; Model predictive control; Simulation; Engineering; Control theory (sociology); Automotive engineering; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02035050304572326,"gpt":0.2770651136658813,"spread":0.256714610620158,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005097797,0.0002562237,0.0003154799,0.0005521881,0.0003992033,0.0000351685,0.0004012941,0.0003666184,0.0001249277],"category_scores_gemma":[0.00003229158,0.0002493995,0.00007130834,0.0006043173,0.0004266294,0.0002322953,0.00001219821,0.001208603,0.0001066326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000142174,"about_ca_system_score_gemma":0.00005149929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001254788,"about_ca_topic_score_gemma":0.0004878301,"domain_scores_codex":[0.9980034,0.00006119722,0.0003956749,0.0004380445,0.0004067408,0.0006949055],"domain_scores_gemma":[0.9989484,0.0001353199,0.00008599611,0.0006145829,0.0001636222,0.00005207093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006386083,0.00008922467,0.8172882,0.0001351434,0.0001322899,0.00006951323,0.000274662,0.1525331,0.01318579,0.006676912,0.0002727044,0.009278663],"study_design_scores_gemma":[0.007569037,0.001213996,0.5722747,0.0004054416,0.0001844289,0.000006183054,0.005168337,0.1464487,0.2516272,0.005814833,0.007510434,0.001776646],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9821159,0.0001342895,0.008640251,0.0005878434,0.00007582585,0.0007375281,0.00005306367,0.007314145,0.0003411702],"genre_scores_gemma":[0.9982951,0.00006092986,0.001240956,0.000009385763,0.00001010269,0.0002131338,0.00005274089,0.00005900095,0.00005863728],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2450134,"threshold_uncertainty_score":0.9999958,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1183861445","doi":"10.1016/j.comcom.2015.08.010","title":"A real-time lane marking localization, tracking and communication system","year":2015,"lang":"en","type":"article","venue":"Computer Communications","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":72,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Hough transform; Computer vision; Artificial intelligence; Line (geometry); Kalman filter; Tracking (education); Filter (signal processing); Probabilistic logic; Tracking system; Pattern recognition (psychology); Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02113860294717502,"gpt":0.2240648600401915,"spread":0.2029262570930165,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003111904,0.0001082358,0.0001517612,0.00008659888,0.000246248,0.00004738939,0.000663109,0.0001096385,0.000002645507],"category_scores_gemma":[0.000009315881,0.0001222455,0.00001971619,0.0001863709,0.0001334124,0.00014819,0.000363627,0.0001982052,0.00005397664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001102509,"about_ca_system_score_gemma":0.00001912355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003438473,"about_ca_topic_score_gemma":0.00001874307,"domain_scores_codex":[0.9993373,0.0001147024,0.0002457103,0.0001044485,0.00006514286,0.0001326552],"domain_scores_gemma":[0.9982082,0.0001190411,0.00004755847,0.001468023,0.0000891025,0.00006804435],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003092127,0.0003178605,0.02396665,0.0004900713,0.0005650437,0.00001454565,0.01599419,0.09477331,0.001215758,0.5002179,0.02778046,0.3346333],"study_design_scores_gemma":[0.0002445529,0.00001304445,0.002326206,0.00008423349,0.00001760177,0.0000410465,0.000151347,0.986188,0.00003747656,0.00080282,0.009941156,0.000152529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0500091,0.005603231,0.8826586,0.001686,0.0002270424,0.000627999,0.00001767736,0.00702912,0.05214122],"genre_scores_gemma":[0.938227,0.0005552734,0.06102182,0.00002689093,0.0000224864,0.00002341832,0.00007434493,0.00002432226,0.00002446876],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8914147,"threshold_uncertainty_score":0.4985027,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137355359","doi":"10.3141/2393-09","title":"Application of Computer Vision to Diagnosis of Pedestrian Safety Issues","year":2013,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of British Columbia","funders":"","keywords":"Pedestrian; Intersection (aeronautics); Computer science; Transport engineering; Collision; Computer security; Risk analysis (engineering); Engineering; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.03082890627923999,"gpt":0.3406954679642102,"spread":0.3098665616849702,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002239589,0.0001784926,0.0004705556,0.001061568,0.0001788721,0.00002680075,0.0009452464,0.000202146,0.0002158003],"category_scores_gemma":[0.00006546311,0.0001439505,0.0002236965,0.002012243,0.0002957784,0.0003541202,0.000009854144,0.001031641,0.00005143057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001415733,"about_ca_system_score_gemma":0.0001334496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006268934,"about_ca_topic_score_gemma":0.008512307,"domain_scores_codex":[0.995861,0.0003232378,0.001428354,0.0002431118,0.00159663,0.0005476711],"domain_scores_gemma":[0.9960812,0.0005749317,0.0002229042,0.0004753403,0.002339358,0.0003062224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001460535,0.000539273,0.5588938,0.001053046,0.0003392051,0.00001962371,0.005814621,0.08544315,0.04535318,0.003311367,0.01698444,0.2807878],"study_design_scores_gemma":[0.00059767,0.000919928,0.9642237,0.0002811259,0.00002141571,2.148273e-7,0.0004479596,0.001909364,0.02048877,0.001644296,0.009325279,0.0001402897],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9645822,0.0001277593,0.02915338,0.004370944,0.0001783444,0.001420153,0.00005358013,0.00004610924,0.00006750324],"genre_scores_gemma":[0.9908872,0.0006533553,0.008107882,0.00002318201,0.00007736722,0.0001436338,0.000009605628,0.00003985762,0.0000579349],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4053299,"threshold_uncertainty_score":0.9476795,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4200631182","doi":"10.1016/j.trc.2022.103926","title":"A generative car-following model conditioned on driving styles","year":2022,"lang":"en","type":"article","venue":"Transportation Research Part C Emerging Technologies","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":65,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Generative grammar; Trajectory; Generative model; Driving simulation; Driving simulator; Process (computing); Artificial intelligence; Variable (mathematics); Component (thermodynamics); Calibration; Simulation; Machine learning; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04430271926385397,"gpt":0.3153941251161301,"spread":0.2710914058522761,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006357612,0.0001986713,0.0002284114,0.0006663001,0.001173631,0.00002270967,0.0004914918,0.0001598458,0.00008938348],"category_scores_gemma":[0.0000575772,0.0002217493,0.0001013788,0.0008533174,0.0002098197,0.0001622552,0.00004538417,0.001328044,0.00001779312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002264473,"about_ca_system_score_gemma":0.00005546353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001334715,"about_ca_topic_score_gemma":0.00007446837,"domain_scores_codex":[0.9980522,0.00007291053,0.0003366327,0.0003680392,0.0005863093,0.0005839166],"domain_scores_gemma":[0.9993271,0.000130228,0.00003870004,0.0004108101,0.00005774894,0.0000354341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000251199,0.00007376628,0.002234825,0.00003735512,0.0001229077,0.0001016984,0.001282853,0.8843611,0.0141067,0.08486469,0.00721669,0.00557229],"study_design_scores_gemma":[0.00180118,0.0006336407,0.003634511,0.0001357748,0.00006915368,0.000004921066,0.04071167,0.708102,0.1623902,0.05582575,0.02519673,0.001494378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9798221,0.0003047006,0.008887139,0.002113585,0.0001358201,0.0004403256,0.0001071032,0.006930465,0.001258756],"genre_scores_gemma":[0.99713,0.0001523932,0.00142275,0.00002397965,0.00001154967,0.0008881403,0.0001248613,0.00004595319,0.0002003099],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.176259,"threshold_uncertainty_score":0.9042675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3006895970","doi":"10.1109/cvpr42600.2020.01443","title":"Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":61,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Pedestrian; Graph; Inference; Adjacency matrix; Social graph; Trajectory; Artificial intelligence; Convolutional neural network; Kernel (algebra); Machine learning; Metric (unit); Adjacency list; Theoretical computer science; Algorithm; Mathematics; Social media; Geography; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02981061727944787,"gpt":0.2525841906084555,"spread":0.2227735733290077,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000182438,0.0003862316,0.0005095639,0.00009845183,0.000598264,0.00003229808,0.0003089782,0.001150156,0.0001187137],"category_scores_gemma":[0.000007097767,0.0004601766,0.0004165322,0.0001391619,0.0001883377,0.00006892595,0.0001625955,0.001146201,0.000010409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002101476,"about_ca_system_score_gemma":0.00009068308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003675641,"about_ca_topic_score_gemma":0.0001886277,"domain_scores_codex":[0.9983485,0.00004355767,0.0005257016,0.0004544353,0.0001734844,0.0004543568],"domain_scores_gemma":[0.99955,0.00003557116,0.0001287827,0.0001573297,0.00006600867,0.00006227322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003369906,0.0001837033,0.01872452,0.001651116,0.002269754,0.00002107904,0.002327159,0.2516182,0.0006368348,0.2291723,0.4857167,0.007341505],"study_design_scores_gemma":[0.00245125,0.0002283958,0.1438759,0.00005656155,0.000447901,0.000009274278,0.0001806152,0.5809968,0.0002176667,0.2455592,0.02411705,0.001859342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5156721,0.001382887,0.423086,0.008635385,0.00705925,0.005318097,0.00290812,0.02303688,0.01290123],"genre_scores_gemma":[0.9927514,0.000007036645,0.001570539,0.0001303301,0.002654126,0.0003484677,0.002322309,0.00008245773,0.0001332932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4770793,"threshold_uncertainty_score":0.999785,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3174203047","doi":"10.15607/rss.2021.xvii.029","title":"Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Odometry; Probabilistic logic; Pattern recognition (psychology); Feature (linguistics); Radar; Unsupervised learning; Mobile robot; Robot","retraction":null,"screen_n_in":null,"score":{"opus":0.005271317232354826,"gpt":0.1915073177536094,"spread":0.1862360005212546,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008461451,0.00009040673,0.0001228142,0.00004819619,0.0001028994,0.00002051033,0.00004270094,0.0001450675,0.00007637899],"category_scores_gemma":[0.00009861265,0.00009195247,0.00001785717,0.0001974059,0.00003832202,0.00007861475,0.00003304817,0.0003237234,0.00001703203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002643442,"about_ca_system_score_gemma":0.00001366448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001198609,"about_ca_topic_score_gemma":0.000003208758,"domain_scores_codex":[0.9995677,0.00001835566,0.0000945287,0.0001305207,0.00005104329,0.0001378231],"domain_scores_gemma":[0.9997562,0.00007075017,0.00001019308,0.0001094295,0.00002116976,0.00003222337],"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":[0.00002842146,0.000115234,0.01988308,0.000954806,0.0003804986,0.0002192242,0.00181531,0.2387971,0.04436744,0.0920167,0.001855123,0.5995671],"study_design_scores_gemma":[0.0006331409,0.00003821036,0.01122583,0.00004410253,0.00003456592,0.0001010093,0.0003742834,0.9730758,0.008460466,0.003477242,0.002249444,0.0002859172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9376386,0.001460237,0.04668776,0.0006151616,0.0001179442,0.0001112778,0.00000138022,0.001831416,0.01153619],"genre_scores_gemma":[0.9820917,0.00004281506,0.01724618,0.00003213087,0.000009027242,0.000004458373,0.00001650617,0.00001600685,0.0005411499],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7342787,"threshold_uncertainty_score":0.3749713,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2031081486","doi":"10.1145/2641798.2641807","title":"Lane detection and tracking system based on the MSER algorithm, hough transform and kalman filter","year":2014,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":59,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Ottawa","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Hough transform; Computer vision; Artificial intelligence; Kalman filter; Computer science; Tracking (education); Pixel; Algorithm; Pattern recognition (psychology); Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.005353732338655945,"gpt":0.1671099159344176,"spread":0.1617561835957617,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000175831,0.0000904839,0.00008984586,0.00003651894,0.00009817713,0.0000151263,0.00004352416,0.000107878,0.00001464317],"category_scores_gemma":[0.000003509731,0.00006043644,0.00001601866,0.00004331762,0.00003200744,0.00004594662,0.000004411317,0.0001541011,0.000006972346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001821354,"about_ca_system_score_gemma":0.000001355888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009277356,"about_ca_topic_score_gemma":0.00003327604,"domain_scores_codex":[0.9996337,0.0000156438,0.00008868083,0.0001006616,0.00004311404,0.0001182002],"domain_scores_gemma":[0.9997734,0.00007467667,0.000008462097,0.0001162889,0.000005791758,0.00002139767],"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":[0.00001041769,0.000007523675,0.0001539518,0.00009140747,0.00002393142,0.000002328204,0.0001486563,0.000973355,0.001101438,0.002199812,0.00003487706,0.9952523],"study_design_scores_gemma":[0.0003057934,0.00006850424,0.004497194,0.00002654597,0.00001312878,0.00001728941,0.0001156239,0.9593081,0.03330655,0.0001654686,0.002054555,0.0001212595],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3170449,0.00007360838,0.6581439,0.0007598339,0.0001385262,0.0002777489,0.00000486332,0.001377026,0.02217956],"genre_scores_gemma":[0.9992095,0.000006521523,0.0005962549,0.00008551533,0.00002927335,0.00001241513,8.006734e-7,0.00001354575,0.00004614997],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.995131,"threshold_uncertainty_score":0.2464527,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2786973885","doi":"10.1155/2018/9702730","title":"Investigations on Driver Unique Identification from Smartphone’s GPS Data Alone","year":2018,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":57,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Global Positioning System; Telematics; Identification (biology); Computer science; Random forest; Classifier (UML); Data mining; Artificial intelligence; Machine learning; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.01546164424212296,"gpt":0.2426002152810179,"spread":0.227138571038895,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001343313,0.00009327147,0.0001398495,0.0001168219,0.00006839108,0.000008783173,0.0002491242,0.00009880241,0.00003643766],"category_scores_gemma":[0.00002482833,0.00009416293,0.00003139811,0.0001542856,0.00008522103,0.0006146033,0.00000244455,0.0002365371,0.00003061764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004618664,"about_ca_system_score_gemma":0.00003074882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006447761,"about_ca_topic_score_gemma":0.0001608862,"domain_scores_codex":[0.9991902,0.0000119908,0.000448706,0.0001204395,0.0001328036,0.00009583147],"domain_scores_gemma":[0.9992906,0.00004223399,0.000186432,0.0003095631,0.0001218314,0.00004927853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0004178456,0.0002696875,0.01629959,0.00006555259,0.000513709,0.00007713387,0.006367248,0.3044256,0.557544,0.008403414,0.003162232,0.102454],"study_design_scores_gemma":[0.001014828,0.000157635,0.8370727,0.0001085153,0.0001025439,0.000005712496,0.0001957509,0.004090168,0.1358499,0.01553338,0.005653705,0.0002151773],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9041687,0.00007896715,0.09463004,0.0002725239,0.0005024541,0.00007293244,0.00008558314,0.0001099962,0.00007886701],"genre_scores_gemma":[0.9844241,0.0001357444,0.01492249,0.00005385031,0.0001429014,0.000002133693,0.0002904432,0.00001717645,0.00001121665],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8207731,"threshold_uncertainty_score":0.3839853,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3118743384","doi":"10.1109/iv47402.2020.9304552","title":"Identifying the Operational Design Domain for an Automated Driving System through Assessed Risk","year":2020,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Huawei Technologies (Canada)","funders":"Huawei Technologies","keywords":"Automotive industry; Domain (mathematical analysis); Set (abstract data type); Computer science; Risk analysis (engineering); Transport engineering; Engineering; Mathematics; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.03980776729237362,"gpt":0.2740720499105536,"spread":0.23426428261818,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003289336,0.0001243572,0.0001428612,0.00001681297,0.0003502046,0.00006984048,0.0002508128,0.0001247005,0.00002146969],"category_scores_gemma":[0.00003359904,0.00009291958,0.00004423342,0.0001383127,0.00003136136,0.0002899661,0.00002788073,0.0001698133,0.00003292831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005437984,"about_ca_system_score_gemma":0.0000253092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009480037,"about_ca_topic_score_gemma":0.00001038266,"domain_scores_codex":[0.9992507,0.00007152539,0.0002239019,0.0001741717,0.00008216166,0.0001975214],"domain_scores_gemma":[0.9995629,0.0001629535,0.00003277467,0.0001745013,0.00002973205,0.00003712242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004204567,0.00004526152,0.001724653,0.000286437,0.0004732629,0.00001299351,0.005479531,0.7141567,0.04898136,0.2161653,0.01036854,0.002263894],"study_design_scores_gemma":[0.0002700935,0.00003939438,0.001034173,0.00001114151,0.00002144769,0.000006258211,0.001143613,0.9888196,0.007267075,0.0006939126,0.0005582538,0.000135032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06789076,0.00005010021,0.9245608,0.0003732474,0.0001079867,0.0004312388,0.00000819737,0.005633292,0.0009443762],"genre_scores_gemma":[0.9113736,0.000005977204,0.08830254,0.0001143379,0.00006854434,0.00008613108,0.00001057952,0.00002791041,0.00001034497],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8434829,"threshold_uncertainty_score":0.378915,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}