{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1403,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":1403,"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":"ba17fc1c6f59","filters":{"topic":"Infrastructure Maintenance and Monitoring"}},"results":[{"id":"W2598457882","doi":"10.1111/mice.12263","title":"Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks","year":2017,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":3134,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Convolutional neural network; Sobel operator; Computer science; Artificial intelligence; Robustness (evolution); Pixel; Computer vision; Canny edge detector; Shadow (psychology); Deep learning; Pattern recognition (psychology); Adaptability; Image (mathematics); Edge detection; Image processing","retraction":null,"screen_n_in":null,"score":{"opus":0.004973053066563081,"gpt":0.1899400987236036,"spread":0.1849670456570405,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000107546,0.00042384,0.0003409473,0.0001599202,0.0005953733,0.0003645639,0.0003087662,0.0002278571,0.00002181026],"category_scores_gemma":[0.00004535647,0.0004364282,0.0001008895,0.00009565871,0.00008520947,0.0005085793,0.0001392591,0.0007884286,0.000001243315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001285697,"about_ca_system_score_gemma":0.00001174633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001313697,"about_ca_topic_score_gemma":0.000009972803,"domain_scores_codex":[0.9985781,0.0000180907,0.0003067469,0.0003404466,0.0001783688,0.0005782462],"domain_scores_gemma":[0.999202,0.0000512909,0.000107614,0.0003881938,0.00007605796,0.0001748496],"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":[0.000007514811,0.000002108695,0.002527372,0.00008331297,0.00004129613,0.00001672698,0.00005358192,0.9779424,0.003429384,0.00005725275,0.00002288992,0.01581613],"study_design_scores_gemma":[0.0004746333,0.00004138371,0.1170157,0.00008203555,0.00002555523,0.00005794732,0.000008471576,0.8803628,0.0007083169,0.00005473756,0.0007636041,0.0004048038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3908195,0.0001950761,0.6061382,0.000005672883,0.002340446,0.00008866489,0.000001611592,0.0003272927,0.00008349634],"genre_scores_gemma":[0.9892836,0.00002549051,0.008575122,0.00003103523,0.001982531,0.000007867629,0.0000111154,0.00007792399,0.000005330974],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.598464,"threshold_uncertainty_score":0.9998087,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2768955070","doi":"10.1111/mice.12334","title":"Autonomous Structural Visual Inspection Using Region‐Based Deep Learning for Detecting Multiple Damage Types","year":2017,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":1520,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Visual inspection; Robustness (evolution); Pixel; Pattern recognition (psychology); Computer vision; Deep learning","retraction":null,"screen_n_in":null,"score":{"opus":0.008204456037696393,"gpt":0.2214790530364932,"spread":0.2132745969987968,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010953,0.0004705011,0.0004142252,0.0002346177,0.0009911282,0.0004322034,0.000294028,0.0002261682,0.000004772716],"category_scores_gemma":[0.0001573729,0.0004799895,0.0001235536,0.0001006447,0.00006905491,0.0005620192,0.0001278592,0.0005700694,6.391797e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001928971,"about_ca_system_score_gemma":0.00002328854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002253065,"about_ca_topic_score_gemma":0.00002049193,"domain_scores_codex":[0.998444,0.00001477812,0.0003613593,0.0004164562,0.0001431052,0.0006203654],"domain_scores_gemma":[0.999131,0.0001099436,0.0001584581,0.0003510817,0.00009804041,0.0001514488],"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":[0.00001646604,0.000001790481,0.006176726,0.0002295799,0.00006110409,0.00001174196,0.0002520766,0.9375116,0.01402075,0.00006502331,0.00001676616,0.04163641],"study_design_scores_gemma":[0.000836733,0.0000845093,0.05235176,0.0001614758,0.00003810594,0.00006685619,0.00003451332,0.9402376,0.004809236,0.000133111,0.0007330714,0.0005129819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.492726,0.0001109318,0.5046669,0.000004856409,0.001746098,0.0001712539,0.000002309964,0.000528915,0.00004272565],"genre_scores_gemma":[0.968092,0.00001126743,0.02995123,0.00001644217,0.001780866,0.00001795814,0.00001387962,0.0001115089,0.000004852985],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.475366,"threshold_uncertainty_score":0.9997652,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3024912007","doi":"10.3390/s20102778","title":"Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review","year":2020,"lang":"en","type":"article","venue":"Sensors","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":699,"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":"National Science Foundation","keywords":"Structural health monitoring; Deep learning; Popularity; Computer science; Data science; Cloud computing; Systems engineering; Artificial intelligence; Engineering; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02214039456322951,"gpt":0.2649489017378827,"spread":0.2428085071746531,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007164053,0.0001336603,0.0002201173,0.00001335689,0.0001008255,0.00001596393,0.0001686205,0.0000272656,0.000004119935],"category_scores_gemma":[0.00007462693,0.0001068855,0.00003175886,0.0001572621,0.00003272763,0.0001528901,0.0001010366,0.000314885,0.000003973855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003790188,"about_ca_system_score_gemma":0.000009619322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001738536,"about_ca_topic_score_gemma":0.00001071979,"domain_scores_codex":[0.9991902,0.0000456834,0.0002308404,0.0001804965,0.0001351257,0.0002176271],"domain_scores_gemma":[0.9995701,0.00001997143,0.00007562777,0.0002442029,0.00002689263,0.00006314647],"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":[0.00003881063,0.000004979693,0.01864904,0.009653901,0.0002440343,0.00002151602,0.01027481,0.5793557,0.01959284,0.00004388601,0.001597408,0.360523],"study_design_scores_gemma":[0.001494028,0.0004354666,0.1095044,0.005184209,0.0002244318,0.0001116738,0.002324983,0.5908246,0.08758028,0.0003576518,0.2003267,0.001631489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9922254,0.005042397,0.0007777752,0.0003571087,0.0009602894,0.0002671247,0.00001609704,0.0001788035,0.0001749714],"genre_scores_gemma":[0.9942626,0.004183101,0.001183549,0.00007132763,0.0002419434,0.000001930365,0.000007652206,0.00002898712,0.00001885627],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3588915,"threshold_uncertainty_score":0.4358664,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3045530378","doi":"10.1007/s11831-020-09471-9","title":"Machine Learning Algorithms in Civil Structural Health Monitoring: A Systematic Review","year":2020,"lang":"en","type":"review","venue":"Archives of Computational Methods in Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":502,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Structural health monitoring; Algorithm; Computer science; Cluster analysis; Machine learning; Support vector machine; Domain (mathematical analysis); Artificial intelligence; Construction engineering; Engineering; Structural engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02753050107440204,"gpt":0.3647917994523548,"spread":0.3372612983779528,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006597576,0.0005562954,0.003308868,0.0006828133,0.00002605592,0.00001858754,0.0004011701,0.00009820267,0.000002500042],"category_scores_gemma":[0.0005250382,0.0005219138,0.0003458808,0.0007172426,0.00002392165,0.00008476652,0.0001042548,0.00122876,0.000001249813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002102039,"about_ca_system_score_gemma":0.0001091847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001080444,"about_ca_topic_score_gemma":9.304801e-7,"domain_scores_codex":[0.9967507,0.0004572754,0.001759419,0.0003365839,0.0002574614,0.0004385735],"domain_scores_gemma":[0.9976351,0.001692679,0.0003417316,0.0002001583,0.00001892073,0.0001113828],"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":[4.847103e-7,0.000001804523,0.000003998885,0.4794976,0.00006598848,0.00001006111,0.0001968091,0.277011,6.875846e-7,0.00007281161,3.999283e-7,0.2431383],"study_design_scores_gemma":[0.0001509314,0.00002781043,0.00002664576,0.6384135,0.0001149683,0.00005679291,0.00001519275,0.3548845,0.000003084758,0.0004175045,0.005458801,0.0004301763],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[5.492499e-7,0.7970216,0.2014775,0.000006614845,0.0005040946,0.0008102912,0.00001291542,0.0001154613,0.00005108245],"genre_scores_gemma":[0.00005040968,0.661405,0.3382159,0.000004109581,0.0001040704,0.0001060763,0.00003274019,0.00007951804,0.000002228434],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.2427081,"threshold_uncertainty_score":0.9997233,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2979396152","doi":"10.1109/tie.2019.2945265","title":"SDDNet: Real-Time Crack Segmentation","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Electronics","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":445,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Segmentation; Pyramid (geometry); Pooling; Convolutional neural network; Convolution (computer science); Pattern recognition (psychology); Intersection (aeronautics); Pixel; Range (aeronautics); Image segmentation; Artificial neural network; Test set; Set (abstract data type); Computer vision; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.008833765349411759,"gpt":0.2109811786882521,"spread":0.2021474133388403,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008932696,0.0001877498,0.0001738987,0.0001170071,0.00007963012,0.00003811768,0.0001106624,0.0002268966,0.0004356645],"category_scores_gemma":[0.000001594385,0.0001954875,0.00008264892,0.0002344858,0.00001333135,0.0001734313,4.21917e-7,0.0006006432,0.0004584523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004118698,"about_ca_system_score_gemma":0.00007664361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001830097,"about_ca_topic_score_gemma":0.000008579506,"domain_scores_codex":[0.9989736,0.00002105708,0.0002192775,0.0001810583,0.0001826721,0.0004223539],"domain_scores_gemma":[0.9996199,0.00004138715,0.00003127913,0.0002154486,0.00003030694,0.00006165857],"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":[0.0001226874,0.00003565272,0.00002382825,0.00001764515,0.0001450697,0.000002621749,0.0001852371,0.6386216,0.2814845,0.0001071301,0.002382114,0.07687191],"study_design_scores_gemma":[0.002625917,0.0005810448,0.00003250162,0.00007606674,0.00009071216,0.00001652102,0.0001127318,0.02947618,0.9501908,0.0001915985,0.01597209,0.0006337836],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9162999,0.00004852033,0.06628868,0.00006194022,0.006079489,0.0007506433,0.00003255311,0.0007926019,0.009645613],"genre_scores_gemma":[0.9974416,0.0001965686,0.0002428037,0.00002379061,0.0003851335,0.00003130735,0.000008863526,0.00005647506,0.001613449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6687064,"threshold_uncertainty_score":0.7971749,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2093303892","doi":"10.1016/j.autcon.2013.06.011","title":"Image-based retrieval of concrete crack properties for bridge inspection","year":2013,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":401,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Visualization; Tortuosity; Bridge (graph theory); Representation (politics); Computer science; Cracking; Artificial neural network; Structural engineering; Structural health monitoring; Artificial intelligence; Computer vision; Engineering; Materials science; Geotechnical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01002153999872207,"gpt":0.2130994789372893,"spread":0.2030779389385672,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008580969,0.0000892509,0.0001266551,0.0001512563,0.00003956055,0.00002944912,0.00004120745,0.00007414819,0.00002167491],"category_scores_gemma":[0.00006997053,0.0000886034,0.00003605702,0.0001634125,0.00007115482,0.0003970397,0.000004258584,0.00007480883,0.000008260147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001101809,"about_ca_system_score_gemma":0.00002397409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005346429,"about_ca_topic_score_gemma":0.000002577732,"domain_scores_codex":[0.9993813,0.00001317832,0.0002891352,0.00009617637,0.00009052704,0.0001296552],"domain_scores_gemma":[0.9996132,0.00002616775,0.00007182072,0.0000956926,0.0001756584,0.00001743005],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005808945,0.000003942451,0.005808081,0.0006163958,0.00002737121,3.447597e-7,0.000480649,0.01233034,0.9570889,0.0009307195,0.0009070336,0.02174817],"study_design_scores_gemma":[0.0007541945,0.00004307986,0.04712182,0.000126457,0.000009389702,0.000008592318,0.0001912168,0.5092119,0.4415897,0.0006750593,0.0001203713,0.0001481743],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9522986,0.00002240229,0.04538076,0.00004494856,0.001095171,0.0004530922,0.000004788716,0.0003273611,0.0003729079],"genre_scores_gemma":[0.9803723,0.000004914401,0.01940913,0.000008042915,0.0001176212,0.00005764186,0.0000104697,0.00001518852,0.000004759962],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5154991,"threshold_uncertainty_score":0.3613142,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3033645921","doi":"10.1016/j.autcon.2020.103291","title":"Hybrid pixel-level concrete crack segmentation and quantification across complex backgrounds using deep learning","year":2020,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":395,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Research Manitoba","keywords":"Pixel; Intersection (aeronautics); Segmentation; Convolutional neural network; Artificial intelligence; Computer science; Algorithm; Bounding overwatch; Computer vision; Pattern recognition (psychology); Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.04331559413787201,"gpt":0.2807973856158583,"spread":0.2374817914779863,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000129095,0.0001412358,0.0001510866,0.00007229657,0.0001605639,0.0001148957,0.00004813924,0.00006536765,0.00002413161],"category_scores_gemma":[0.00004383632,0.0001683425,0.00002311853,0.0001909799,0.00006800306,0.000553097,0.00001916555,0.0001862198,0.000009680847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001389584,"about_ca_system_score_gemma":0.00001010256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001896438,"about_ca_topic_score_gemma":0.000005866987,"domain_scores_codex":[0.9990774,0.00004418835,0.0003443401,0.0002009189,0.0001333521,0.000199741],"domain_scores_gemma":[0.9996684,0.00003510869,0.0001053386,0.00007350155,0.00006643268,0.00005125605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002798162,0.000001868837,0.03445433,0.000255988,0.00003855279,0.000003482284,0.00441276,0.1760335,0.625845,0.0008902248,0.00003333947,0.158003],"study_design_scores_gemma":[0.0005198207,0.00001881578,0.04345019,0.00003984019,0.00001133395,0.00005869232,0.002651729,0.9349921,0.01762369,0.0001447773,0.0002873858,0.0002016327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.723825,0.00003040174,0.2752559,0.00004027022,0.0003932704,0.0001306423,0.000005951572,0.0002356784,0.00008286444],"genre_scores_gemma":[0.9701324,0.00003426202,0.02953205,0.00003020221,0.0001615908,0.00001070472,0.0000737366,0.00002280842,0.000002310051],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7589586,"threshold_uncertainty_score":0.6864807,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2804948039","doi":"10.1111/mice.12375","title":"Autonomous UAVs for Structural Health Monitoring Using Deep Learning and an Ultrasonic Beacon System with Geo‐Tagging","year":2018,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":376,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Global Positioning System; Beacon; Bridge (graph theory); Structural health monitoring; Computer science; Convolutional neural network; Real-time computing; Artificial intelligence; Deep learning; Ultrasonic sensor; GPS signals; Computer vision; Remote sensing; Assisted GPS; Engineering; Telecommunications; Geography; Acoustics","retraction":null,"screen_n_in":null,"score":{"opus":0.004909401045395913,"gpt":0.2188677157867856,"spread":0.2139583147413897,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002046339,0.0006166601,0.0006183981,0.0002643308,0.0005516434,0.0002829904,0.0001927762,0.0001856182,0.000003185302],"category_scores_gemma":[0.00001473979,0.0005697021,0.00005971829,0.0002239698,0.00009141778,0.0005800296,0.00008405917,0.0005435052,3.587216e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003439529,"about_ca_system_score_gemma":0.00004440059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003087419,"about_ca_topic_score_gemma":0.00001224959,"domain_scores_codex":[0.9977604,0.00002751697,0.0004683921,0.0005844022,0.0001928574,0.0009664528],"domain_scores_gemma":[0.9990704,0.00007759086,0.0001301424,0.0002537877,0.0001191844,0.000348916],"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":[0.00004000132,0.000003243275,0.005879785,0.001483299,0.0001945843,0.00001397778,0.003004409,0.8889898,0.01349833,0.0008164212,0.00001612301,0.08605999],"study_design_scores_gemma":[0.0008373996,0.0004854071,0.01714776,0.0007396956,0.00004281466,0.0004633659,0.0005227975,0.9757352,0.002339866,0.0000381843,0.000943447,0.0007039987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5810475,0.0009037837,0.4156128,0.000005207404,0.001425143,0.0002802571,0.00000597163,0.0006899582,0.00002942688],"genre_scores_gemma":[0.9077339,0.00005713801,0.08879991,0.00001809695,0.003214727,0.00001963094,0.00001325379,0.0001407054,0.000002674123],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3268129,"threshold_uncertainty_score":0.9996755,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3011200270","doi":"10.1002/stc.2551","title":"CrackU‐net: A novel deep convolutional neural network for pixelwise pavement crack detection","year":2020,"lang":"en","type":"article","venue":"Structural Control and Health Monitoring","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":342,"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":"Natural Science Foundation of Shaanxi Province","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Net (polyhedron); Pattern recognition (psychology); Artificial neural network; Mathematics; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.02187878553343378,"gpt":0.2610333528454232,"spread":0.2391545673119894,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001400166,0.0002816971,0.0003666798,0.00003800148,0.0004592305,0.0000740375,0.0001021832,0.00009296383,0.00000474853],"category_scores_gemma":[0.0000208629,0.0002625151,0.00008734607,0.0001119201,0.00003374718,0.0001981556,0.00002609776,0.0003072312,0.000001324778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000171512,"about_ca_system_score_gemma":0.00002934077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005009661,"about_ca_topic_score_gemma":0.00002248321,"domain_scores_codex":[0.9983598,0.00001622957,0.0004181357,0.0003001413,0.0001799931,0.0007256736],"domain_scores_gemma":[0.9993408,0.00005764834,0.00009653722,0.0001026913,0.00008774032,0.0003145496],"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":[0.0006022199,0.000008978248,0.03951139,0.00169452,0.0003666484,0.000007722133,0.002404523,0.6858384,0.04857821,0.001286734,0.0005570588,0.2191436],"study_design_scores_gemma":[0.004432447,0.0004497999,0.1875861,0.0001064025,0.00005357274,0.00002403373,0.0003034004,0.7996711,0.00119207,0.0007096014,0.00488038,0.0005910777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7982649,0.007320361,0.1779033,0.002783348,0.01094964,0.001921439,0.0001074832,0.0007050647,0.00004449156],"genre_scores_gemma":[0.9887902,0.00006982742,0.003396573,0.0004743881,0.007122868,0.00008649438,0.00001053749,0.00004322039,0.000005960533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2185525,"threshold_uncertainty_score":0.9999827,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392611940","doi":"10.1016/j.autcon.2024.105328","title":"Deep learning-based structural health monitoring","year":2024,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":332,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Structural health monitoring; Deep learning; Computer science; Artificial intelligence; Engineering; Data science; Construction engineering; Structural engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.005679921312433956,"gpt":0.2455702572547211,"spread":0.2398903359422872,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001260813,0.0001308132,0.0001234775,0.0002875083,0.00008282538,0.00009989831,0.00005180172,0.00007408916,0.00003301378],"category_scores_gemma":[0.00001798692,0.000136321,0.00003801365,0.0003481316,0.00002872709,0.0003007069,0.00000653356,0.0003062618,0.00002138982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003752419,"about_ca_system_score_gemma":0.00004067606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002633541,"about_ca_topic_score_gemma":0.000008423279,"domain_scores_codex":[0.9991607,0.00002976214,0.0002751662,0.0001573813,0.0001375963,0.0002393573],"domain_scores_gemma":[0.9997811,0.00003753818,0.00002849042,0.00008788699,0.00002433276,0.00004061014],"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":[0.000002258743,8.360602e-7,0.01308365,0.0002317042,0.000012194,0.000005394295,0.000531323,0.6155112,0.0007277807,0.001022415,0.0000376617,0.3688335],"study_design_scores_gemma":[0.0001670391,0.00001894667,0.03364167,0.0002752803,0.0000037834,0.00003572741,0.0003121246,0.9604447,0.003110128,0.0007573026,0.001074344,0.0001589954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8512592,0.001519682,0.1312049,0.0001670789,0.01190085,0.0002391569,0.00000200149,0.002867143,0.0008400301],"genre_scores_gemma":[0.9923436,0.00003849432,0.007144785,0.000007151989,0.0003965701,0.00002054584,0.00001203589,0.0000269987,0.000009786479],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3686745,"threshold_uncertainty_score":0.5559011,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2467386812","doi":"10.1016/j.jom.2016.05.002","title":"Partial least squares path modeling: Time for some serious second thoughts","year":2016,"lang":"en","type":"article","venue":"Journal of Operations Management","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":296,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Wilfrid Laurier University; Public Safety Canada","funders":"","keywords":"Partial least squares regression; Computer science; Rule of thumb; Structural equation modeling; Path (computing); Desk; Scale (ratio); Operations research; Industrial engineering; Econometrics; Management science; Algorithm; Machine learning; Mathematics; Economics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.007665261342616678,"gpt":0.219863750318061,"spread":0.2121984889754443,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001345703,0.0001003273,0.0001330138,0.00009864146,0.00008807665,0.00006406674,0.0001178528,0.00002395776,0.00005346515],"category_scores_gemma":[0.000007716797,0.00006558972,0.00007728641,0.00003897698,0.000008604848,0.0004090437,0.00001912679,0.00005643774,0.00001571344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008311924,"about_ca_system_score_gemma":0.00001170644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.898574e-7,"about_ca_topic_score_gemma":0.000001948614,"domain_scores_codex":[0.9993243,0.000008023499,0.0003031342,0.00007131221,0.0001202232,0.0001730296],"domain_scores_gemma":[0.9997134,0.000009354681,0.00003297999,0.0001114091,0.0000842603,0.00004862391],"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":[0.00003885091,0.00003115724,0.0000202864,0.00008504936,0.0002549349,0.00003702335,0.0002675615,0.9423339,0.0153504,0.00488402,0.01068069,0.02601613],"study_design_scores_gemma":[0.004254151,0.0004854879,0.0003754584,0.0005652573,0.000255509,0.0001114634,0.0005070851,0.7820656,0.02886126,0.004597403,0.1771771,0.0007442096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.335931,0.0002271012,0.6595507,0.0004886845,0.002063669,0.0003832772,0.00002120635,0.00006293126,0.001271432],"genre_scores_gemma":[0.9876667,0.00008609189,0.009408411,0.000042026,0.001320281,0.00002042643,0.000001466392,0.00002234797,0.001432262],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6517357,"threshold_uncertainty_score":0.2674671,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4200478585","doi":"10.1177/14759217211053776","title":"Efficient attention-based deep encoder and decoder for automatic crack segmentation","year":2021,"lang":"en","type":"article","venue":"Structural Health Monitoring","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":291,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Computer science; Segmentation; Upsampling; Artificial intelligence; Encoder; Activation function; Ground truth; Convolutional neural network; Artificial neural network; Pattern recognition (psychology); Computer vision; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01061468104800626,"gpt":0.2870019397863203,"spread":0.276387258738314,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001132139,0.0002006769,0.0002238482,0.00007284546,0.0003065019,0.00007160676,0.00006033024,0.00006835774,0.00001271997],"category_scores_gemma":[0.00002985433,0.000196521,0.0000602839,0.0001362861,0.00002205734,0.00007296631,0.00001877306,0.0001457926,0.000001928987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002867602,"about_ca_system_score_gemma":0.00006937711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001290265,"about_ca_topic_score_gemma":0.000008834772,"domain_scores_codex":[0.9987279,0.00002505183,0.0003454077,0.0002471076,0.0001767909,0.0004777696],"domain_scores_gemma":[0.9994405,0.00008599672,0.00006609441,0.0001598496,0.0001082508,0.0001393367],"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":[0.00002380037,0.00001140476,0.03836232,0.003433428,0.0000995829,0.0000142433,0.002169876,0.532668,0.03576472,0.0001502304,0.0001155195,0.3871869],"study_design_scores_gemma":[0.001044614,0.00004922328,0.09470958,0.0003018658,0.00002493454,0.00002385024,0.001023777,0.8754972,0.02654671,0.0002957488,0.0001265743,0.0003559038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9544501,0.001208726,0.03970364,0.0001153813,0.003886644,0.0003547588,0.0000134183,0.0002369623,0.00003035172],"genre_scores_gemma":[0.9382631,0.00002376731,0.06092549,0.00004537034,0.0005937083,0.00006276902,0.0000266189,0.00003919861,0.0000199292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.386831,"threshold_uncertainty_score":0.8013892,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996338922","doi":"10.1061/(asce)is.1943-555x.0000512","title":"Data Analytics in Asset Management: Cost-Effective Prediction of the Pavement Condition Index","year":2019,"lang":"en","type":"article","venue":"Journal of Infrastructure Systems","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":289,"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":"Asset management; Computer science; Predictive modelling; Asset (computer security); Decision tree; Index (typography); Field (mathematics); Data mining; Random forest; Pavement management; Ensemble learning; Machine learning; Engineering; Transport engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.00911362593683386,"gpt":0.2312955214759615,"spread":0.2221818955391276,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004383806,0.0001517844,0.0003201603,0.0002282943,0.00002222702,0.00003188854,0.000458341,0.0001075741,0.00001432614],"category_scores_gemma":[0.00001671372,0.000102018,0.0000653939,0.0002933051,0.00002400653,0.0003246476,0.00008838002,0.0004109619,0.000001308454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002834189,"about_ca_system_score_gemma":0.00002369185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006525738,"about_ca_topic_score_gemma":0.000004407363,"domain_scores_codex":[0.9985834,0.00006045753,0.0006604097,0.0001139023,0.0003991392,0.000182658],"domain_scores_gemma":[0.9989548,0.00003501143,0.0003975942,0.0004476495,0.0001281001,0.00003679199],"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":[0.00003089069,0.00001204934,0.245777,0.0007038423,0.0003876671,0.00001498011,0.0002547738,0.7401592,0.004662664,0.0005407634,0.004122324,0.003333859],"study_design_scores_gemma":[0.001772105,0.0001034933,0.9046307,0.001390383,0.0001102043,0.0001536553,0.001560434,0.07628083,0.001973273,0.0005821085,0.01126814,0.0001746557],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.973305,0.0002393704,0.01267334,0.00001459219,0.01008246,0.001693101,0.0002911947,0.00002281477,0.001678059],"genre_scores_gemma":[0.999384,0.00004186858,0.0001480396,0.000008870373,0.0003505992,0.000008810095,0.00001806079,0.00001795834,0.00002177546],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6638783,"threshold_uncertainty_score":0.4160174,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106238010","doi":"10.1016/j.autcon.2005.02.006","title":"Automated detection of cracks in buried concrete pipe images","year":2005,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":282,"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":"Engineering; Structural engineering; Geology; Geotechnical engineering; Forensic engineering; Computer science; Engineering drawing","retraction":null,"screen_n_in":null,"score":{"opus":0.003379130086011609,"gpt":0.2125145381431527,"spread":0.209135408057141,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001381958,0.0001102283,0.0001569778,0.000348836,0.00002275786,0.00001558492,0.00005071334,0.0001132828,0.00002231025],"category_scores_gemma":[0.00004072867,0.0001245692,0.00002659372,0.0003587714,0.0000485643,0.000400552,0.000008209957,0.0001442575,0.000008891004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001966778,"about_ca_system_score_gemma":0.00001489155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005211181,"about_ca_topic_score_gemma":0.00003718483,"domain_scores_codex":[0.9991648,0.00002703022,0.0004167414,0.0001159091,0.0001090165,0.0001664628],"domain_scores_gemma":[0.9997066,0.00003040867,0.00007953537,0.0001114043,0.00005267417,0.00001941764],"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":[0.00002270044,0.000004183678,0.00931864,0.0001184542,0.00001703256,0.00000298144,0.000768721,0.09319229,0.7208621,0.0003188875,0.00008469174,0.1752893],"study_design_scores_gemma":[0.0006530365,0.00001434852,0.08218783,0.00009717397,0.000005497641,0.00002908956,0.0002323405,0.408901,0.5072464,0.0002189261,0.0002672575,0.000147029],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9883111,0.00004871999,0.008684956,0.00003023502,0.0008068065,0.000155118,0.000003247391,0.0007149942,0.001244833],"genre_scores_gemma":[0.9935504,0.00002145577,0.006239644,0.000005777496,0.000136071,0.00002081995,0.000006084262,0.00001462897,0.000005151081],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3157087,"threshold_uncertainty_score":0.5079786,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2013530697","doi":"10.1016/j.aap.2006.09.009","title":"Empirical Bayes before–after safety studies: Lessons learned from two decades of experience and future directions","year":2006,"lang":"en","type":"article","venue":"Accident Analysis & Prevention","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":266,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Sophistication; Crash; Bayes' theorem; Ranking (information retrieval); Empirical research; Risk analysis (engineering); Computer science; Regression toward the mean; Engineering; Transport engineering; Data science; Operations research; Statistics; Bayesian probability; Machine learning; Mathematics; Artificial intelligence; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.02028807076043185,"gpt":0.336758892368909,"spread":0.3164708216084772,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001036313,0.0001458427,0.0003033132,0.0001993657,0.00009070767,0.00003136215,0.00007981846,0.00006464204,0.00008091382],"category_scores_gemma":[0.00001469273,0.0001282556,0.0002015793,0.0005208252,0.00003957898,0.0002400572,0.00004410172,0.0001041199,0.000001708431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007278588,"about_ca_system_score_gemma":0.000005339748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000223302,"about_ca_topic_score_gemma":0.004984645,"domain_scores_codex":[0.9990574,0.00003753612,0.0003496606,0.0002286805,0.0001595574,0.0001671296],"domain_scores_gemma":[0.9995958,0.00003447091,0.00007601969,0.0001950845,0.00006787328,0.00003076795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002113526,0.00001675464,0.9426725,0.000005780299,0.001084276,0.000003009456,0.00298482,0.004754707,0.0009432547,0.00009535412,0.00007994456,0.04733849],"study_design_scores_gemma":[0.0002389125,0.00001515378,0.9856834,0.00004550221,0.0009605416,9.023039e-7,0.001647527,0.001335472,0.00287026,0.003928337,0.003113718,0.0001603129],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.988179,0.003824714,0.007339335,0.0001517518,0.0002650662,0.00007244742,0.000001803837,0.0000747115,0.00009117606],"genre_scores_gemma":[0.9961216,0.001722612,0.001417037,0.000005997646,0.0005530787,0.00003002324,0.00003406855,0.00001249194,0.0001031213],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04717818,"threshold_uncertainty_score":0.5230113,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2737163017","doi":"10.1016/j.autcon.2017.06.024","title":"Remote sensing of concrete bridge decks using unmanned aerial vehicle infrared thermography","year":2017,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":256,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Thermography; Bridge (graph theory); Delamination (geology); Computer science; Nondestructive testing; Remote sensing; Visual inspection; Process (computing); Hammer; Engineering; Marine engineering; Structural engineering; Artificial intelligence; Infrared; Geology","retraction":null,"screen_n_in":null,"score":{"opus":0.01342299857372124,"gpt":0.2462672094173049,"spread":0.2328442108435836,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001282071,0.0001176235,0.0001764608,0.0001768035,0.0001546528,0.00006608576,0.00009710503,0.0001112494,0.000008894708],"category_scores_gemma":[0.00006320392,0.0001324429,0.00005145983,0.0001088838,0.0001247248,0.0003782688,0.00002322378,0.0001174747,0.00000186953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007301012,"about_ca_system_score_gemma":0.00002187455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002147274,"about_ca_topic_score_gemma":0.00001138296,"domain_scores_codex":[0.9992418,0.00002445958,0.0003183411,0.0001203645,0.0001180527,0.0001769969],"domain_scores_gemma":[0.9994012,0.00001936982,0.0001862159,0.0002911464,0.00007558136,0.00002651915],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006645873,0.000001476007,0.01648104,0.0001735153,0.00008779798,0.00001190616,0.001215866,0.01103212,0.6171036,0.0007406069,0.00008452038,0.3530011],"study_design_scores_gemma":[0.001240965,0.00001528486,0.1827408,0.0003510925,0.00002727337,0.00006235763,0.0001890716,0.6949726,0.1165197,0.003452878,0.0001358732,0.0002921708],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.974058,0.00001920555,0.02147603,0.00000883722,0.002510286,0.0001281824,0.000004955312,0.0001516737,0.001642838],"genre_scores_gemma":[0.976665,0.00001181512,0.02307596,0.000004678431,0.0002169593,4.051157e-7,0.000004159291,0.00001848978,0.0000025256],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6839405,"threshold_uncertainty_score":0.5400866,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3021470593","doi":"10.1016/j.conbuildmat.2020.119397","title":"A cost effective solution for pavement crack inspection using cameras and deep neural networks","year":2020,"lang":"en","type":"article","venue":"Construction and Building Materials","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":242,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Discriminator; Computer science; Feature (linguistics); Convolutional neural network; Deconvolution; Artificial neural network; Artificial intelligence; Layer (electronics); Generator (circuit theory); Deep learning; Computer vision; Pattern recognition (psychology); Algorithm; Materials science","retraction":null,"screen_n_in":null,"score":{"opus":0.01605780200932707,"gpt":0.2422186045702031,"spread":0.226160802560876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007578357,0.0001289309,0.000168696,0.00003873426,0.0001742755,0.000107049,0.00002100133,0.00006948434,0.000006199367],"category_scores_gemma":[0.00001935593,0.0001279017,0.00001881008,0.00005637725,0.00005804035,0.0001522641,0.00002175906,0.00005970474,1.782182e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005620257,"about_ca_system_score_gemma":0.000002605874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001181081,"about_ca_topic_score_gemma":0.000001371609,"domain_scores_codex":[0.9994317,0.00001910992,0.0001657668,0.0001642746,0.00004138377,0.0001778242],"domain_scores_gemma":[0.9997974,0.00002077665,0.00004783095,0.00003980942,0.00003375394,0.00006043936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004698407,0.000001262257,0.0007016125,0.0001332119,0.000031185,7.97782e-7,0.0002090007,0.01483692,0.9059243,0.0003528763,0.0000220309,0.07773984],"study_design_scores_gemma":[0.0008572852,0.00006922925,0.001496312,0.00006316482,0.00006305482,0.00007951326,0.0002327872,0.5747331,0.4212729,0.0001845341,0.0006878175,0.0002602603],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6508571,0.0000994343,0.34698,0.00002670453,0.001480761,0.0004178215,0.00000583349,0.0001278735,0.000004515925],"genre_scores_gemma":[0.9884172,0.00005421304,0.01058037,0.00005647826,0.0008134316,0.00005385261,0.000005434605,0.00001878931,2.463676e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5598962,"threshold_uncertainty_score":0.5215681,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2133251833","doi":"10.1007/s12544-015-0156-6","title":"Review of remote sensing methodologies for pavement management and assessment","year":2015,"lang":"en","type":"article","venue":"European Transport Research Review","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":216,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Office of Naval Research","keywords":"Bridge (graph theory); Process (computing); Construction engineering; Transport engineering; Pavement management; Engineering; Computer science; Risk analysis (engineering); Remote sensing; Civil engineering; Geography; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.2695762037981445,"gpt":0.4343564956821344,"spread":0.1647802918839898,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007962391,0.0001489527,0.0004132586,0.00007408184,0.00004220963,0.000008598603,0.0001758419,0.00001526489,0.00000838649],"category_scores_gemma":[0.00008937844,0.0001182965,0.00008905394,0.000217162,0.00006022786,0.00005559119,0.00004328867,0.0002321691,0.000004361525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006873412,"about_ca_system_score_gemma":0.00002402232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005017058,"about_ca_topic_score_gemma":9.529552e-7,"domain_scores_codex":[0.9982951,0.0003173681,0.000466593,0.0002127309,0.0003604967,0.0003477413],"domain_scores_gemma":[0.9991767,0.00007468029,0.00004599375,0.0003409678,0.0002486356,0.0001130008],"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":[0.000003742905,0.000002415075,0.00001212649,0.1482226,0.00007027428,0.00004702018,0.00004729579,0.00001670781,0.00008205983,0.0003567664,0.01150438,0.8396346],"study_design_scores_gemma":[0.0002382447,0.0000827997,0.0005619684,0.0850453,0.00009781127,0.000006613523,0.00006486518,0.00008588903,0.0003599998,0.0004244113,0.9128757,0.0001564106],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001010057,0.809278,0.1537905,0.0003720736,0.0002719394,0.001800183,0.000008686177,0.00009940306,0.03427825],"genre_scores_gemma":[0.0007166045,0.7162567,0.2825966,0.0002037496,0.00006962918,0.000005303883,0.00001504721,0.00003300182,0.0001034421],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9013713,"threshold_uncertainty_score":0.4823993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2905053868","doi":"10.1016/j.autcon.2018.12.006","title":"Deep learning-based automatic volumetric damage quantification using depth camera","year":2018,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":208,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Spall; Convolutional neural network; Computer science; Artificial intelligence; Pixel; Scanner; Volume (thermodynamics); Deep learning; Computer vision; Pattern recognition (psychology); Structural engineering; Engineering; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01162063859261269,"gpt":0.2456796234227854,"spread":0.2340589848301727,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000204181,0.0001565688,0.000155403,0.0006215432,0.0001567499,0.00007507236,0.00008840543,0.0001238675,0.00008016729],"category_scores_gemma":[0.0001210384,0.0001776742,0.00003736915,0.0009618688,0.0001044495,0.0003701448,0.000009678996,0.0002015279,0.00005606773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003124546,"about_ca_system_score_gemma":0.00003422981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005833588,"about_ca_topic_score_gemma":0.00005615049,"domain_scores_codex":[0.9989312,0.00005985087,0.000383895,0.0001905897,0.0001827685,0.0002516748],"domain_scores_gemma":[0.9994739,0.00004799488,0.0001176594,0.0001924574,0.000128781,0.00003925959],"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":[0.000007023647,0.00001356749,0.06105734,0.0001521411,0.00002438592,0.000003690024,0.0005864866,0.6232851,0.0155197,0.0004938839,0.0000496817,0.298807],"study_design_scores_gemma":[0.0002844627,0.0000224357,0.09021302,0.00006780365,0.00001323048,0.00001918842,0.0002219285,0.9003902,0.008294921,0.0001395903,0.0001630385,0.0001701567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6543854,0.00002400469,0.3430542,0.000008194531,0.001354748,0.0001334459,5.212814e-7,0.0005514771,0.0004880326],"genre_scores_gemma":[0.9655888,0.000004662575,0.03407745,0.00001086863,0.0002456425,0.00001691417,0.00001880553,0.00003007132,0.000006773589],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3112034,"threshold_uncertainty_score":0.7245342,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3026393200","doi":"10.1016/j.autcon.2020.103250","title":"LiDAR-equipped UAV path planning considering potential locations of defects for bridge inspection","year":2020,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":207,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Concordia University","keywords":"Visibility; Lidar; Bridge (graph theory); Computer science; Path (computing); Motion planning; Viewpoints; Ranging; Sampling (signal processing); Real-time computing; Genetic algorithm; Computer vision; Artificial intelligence; Simulation; Remote sensing; Robot; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01447947265697696,"gpt":0.2364202046838427,"spread":0.2219407320268657,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007294827,0.0001101254,0.0001543079,0.0001409606,0.00007363963,0.00002543361,0.0000471351,0.00008323632,0.000005448969],"category_scores_gemma":[0.00008247476,0.0001317385,0.00004737562,0.0002273111,0.00004007679,0.0002722024,0.00001106195,0.0001123035,0.000002589337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008384553,"about_ca_system_score_gemma":0.00003059111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001169563,"about_ca_topic_score_gemma":0.000002398819,"domain_scores_codex":[0.9992443,0.00001475971,0.0003431952,0.0001412811,0.00009913124,0.0001573067],"domain_scores_gemma":[0.9996722,0.0000373662,0.00009493019,0.00008069074,0.00007766068,0.00003712062],"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":[0.00006155437,0.00001413027,0.02863069,0.000740211,0.0000727937,0.000006987927,0.003792727,0.7417206,0.1876156,0.005629948,0.0006539364,0.03106077],"study_design_scores_gemma":[0.00156421,0.00009990131,0.09111233,0.0003291841,0.00004724599,0.00007760711,0.001476801,0.7825563,0.1199895,0.001978462,0.0003976857,0.0003708073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6787917,0.00003826215,0.3193669,0.00004343719,0.0009151809,0.0002213916,0.000008100867,0.0003633098,0.0002516953],"genre_scores_gemma":[0.9882074,0.000008390102,0.01142048,0.0000191109,0.0002608311,0.00003909161,0.00002392496,0.00001999989,7.623255e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3094157,"threshold_uncertainty_score":0.5372139,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2058350584","doi":"10.1111/j.1467-8667.2009.00632.x","title":"Fuzzy Monte Carlo Simulation and Risk Assessment in Construction","year":2009,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":207,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Natural Resources; University of Alberta","funders":"","keywords":"Monte Carlo method; Probabilistic logic; Fuzzy logic; Computer science; Range (aeronautics); Uncertainty analysis; Reliability engineering; Probability distribution; Construct (python library); Mathematical optimization; Data mining; Risk analysis (engineering); Operations research; Artificial intelligence; Simulation; Engineering; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.002812116848648407,"gpt":0.1979950191693164,"spread":0.195182902320668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001068963,0.0003215881,0.0003150291,0.0002483336,0.0000751031,0.000108243,0.00008492257,0.0001564503,0.000003540125],"category_scores_gemma":[0.00001674062,0.0003219886,0.00003810643,0.000205549,0.00002845137,0.0003734844,0.00003894207,0.0005461851,3.660875e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001121091,"about_ca_system_score_gemma":0.00001169917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001166034,"about_ca_topic_score_gemma":0.000007847682,"domain_scores_codex":[0.998862,0.00001634428,0.0003318537,0.0002895894,0.0001333574,0.0003669111],"domain_scores_gemma":[0.9995698,0.00005550641,0.00005142872,0.0001725838,0.00003771366,0.000113],"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":[0.000003925935,0.000002323355,0.008524861,0.00004768486,0.00002131447,0.000007743715,0.0002596577,0.9130105,0.0006910752,0.0004211633,0.00003491882,0.07697476],"study_design_scores_gemma":[0.000401208,0.00004784222,0.3381745,0.0000882302,0.00001348485,0.0000319814,0.00002783757,0.6595842,0.00008780164,0.0008989513,0.0004026055,0.000241389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8687446,0.0004307996,0.1290454,0.00001572368,0.0009393244,0.0001649266,0.000006285681,0.0002935149,0.0003594577],"genre_scores_gemma":[0.9718912,0.0003060576,0.02725229,0.00002532608,0.0004871156,0.000005275604,0.000003234297,0.0000275663,0.00000188643],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3296497,"threshold_uncertainty_score":0.9999232,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2900760155","doi":"10.3390/s18113845","title":"Road Surface Monitoring Using Smartphone Sensors: A Review","year":2018,"lang":"en","type":"review","venue":"Sensors","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":197,"is_retracted":false,"has_abstract":true,"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","keywords":"Road surface; Anomaly detection; Key (lock); Anomaly (physics); Smartphone application; Computer science; Real-time computing; Plan (archaeology); Remote sensing; Transport engineering; Computer security; Engineering; Artificial intelligence; Geography; Civil engineering; Multimedia","retraction":null,"screen_n_in":null,"score":{"opus":0.04244868212734403,"gpt":0.3120904995979918,"spread":0.2696418174706477,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003549319,0.000960193,0.00234407,0.0001673293,0.000138765,0.00007300657,0.0003941891,0.000484351,0.00006181829],"category_scores_gemma":[0.00009262878,0.0008397444,0.0006807024,0.0006357895,0.00007477876,0.0001139028,0.0001004246,0.000844905,0.0004946184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005067426,"about_ca_system_score_gemma":0.00009217159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003413111,"about_ca_topic_score_gemma":9.68092e-7,"domain_scores_codex":[0.9970334,0.0001306379,0.0009836499,0.0005734011,0.0003697984,0.00090914],"domain_scores_gemma":[0.9984646,0.00007573324,0.0002530843,0.0008837039,0.0001330753,0.0001898122],"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":[0.000002578695,0.00001099802,0.00001104445,0.1973596,0.0006915863,0.0002061984,0.0001775097,0.00488599,0.00003060451,0.00000416317,0.005309959,0.7913098],"study_design_scores_gemma":[0.00006728898,0.00001132146,0.000002219965,0.1434776,0.0007099604,0.0002062108,0.00002010401,0.0003789626,0.00007501039,0.000003152704,0.8542483,0.0007998196],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001716853,0.9896806,0.00001751519,0.000002644031,0.006017046,0.0007091064,0.00003203657,0.0005533618,0.001270821],"genre_scores_gemma":[0.00002961116,0.9932801,0.002234133,0.000008700718,0.003627716,0.00001573268,0.000021178,0.0003141255,0.0004687032],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8489383,"threshold_uncertainty_score":0.9994053,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3080613661","doi":"10.1016/j.cemconcomp.2020.103781","title":"Classification and quantification of cracks in concrete structures using deep learning image-based techniques","year":2020,"lang":"en","type":"article","venue":"Cement and Concrete Composites","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":195,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Mitacs; Western University","keywords":"Visual inspection; Computer science; Artificial intelligence; Image processing; Classifier (UML); Orientation (vector space); Deep learning; Process (computing); Computer vision; Pattern recognition (psychology); Structural engineering; Image (mathematics); Engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01786448341269545,"gpt":0.2399618785992652,"spread":0.2220973951865697,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006641012,0.0001159225,0.0001625724,0.00006579821,0.00005001191,0.00004123135,0.00005170627,0.00005268339,0.000006242065],"category_scores_gemma":[0.00001730712,0.0001163818,0.00001717839,0.00009060022,0.0000812482,0.0001035803,0.00001987743,0.0001267693,2.020759e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002092415,"about_ca_system_score_gemma":0.000006057356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001209342,"about_ca_topic_score_gemma":5.44779e-7,"domain_scores_codex":[0.9994226,0.0000249487,0.0002130686,0.0001456039,0.0000733566,0.0001204012],"domain_scores_gemma":[0.9997516,0.00003692157,0.00006312661,0.00006458172,0.00004442009,0.00003933844],"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":[0.00002269431,1.503835e-7,0.01670085,0.0001295098,0.000009801998,8.873544e-7,0.0003476314,0.0009738299,0.9785006,0.0003821563,0.000004570862,0.002927308],"study_design_scores_gemma":[0.000291015,0.00006185151,0.01213773,0.00007505818,0.00002185866,0.000001179674,0.0003383715,0.3916475,0.5949701,0.00005517624,0.0002473899,0.000152822],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9711367,0.000756687,0.02760858,0.00006128426,0.00004237322,0.0001631422,0.000002359275,0.00008737882,0.0001414591],"genre_scores_gemma":[0.9897016,0.0001052055,0.01006974,0.00003235885,0.00004982458,0.000006526544,0.00001978849,0.00001423773,7.460131e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3906736,"threshold_uncertainty_score":0.4745911,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3106651141","doi":"10.1061/(asce)cp.1943-5487.0000945","title":"Development of an Image Data Set of Construction Machines for Deep Learning Object Detection","year":2020,"lang":"en","type":"article","venue":"Journal of Computing in Civil Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":187,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Object detection; Computer science; Machine learning; Deep learning; Set (abstract data type); Automation; Field (mathematics); Object (grammar); Data set; Perspective (graphical); Image (mathematics); Computer vision; Pattern recognition (psychology); Engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01342358108316537,"gpt":0.2389459280326969,"spread":0.2255223469495315,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004235956,0.0001227022,0.0002974009,0.0001766696,0.00002650844,0.00001376991,0.0002108861,0.00005049848,0.00000158024],"category_scores_gemma":[0.0002032329,0.000125944,0.00004469057,0.000186197,0.00001073758,0.0002517302,0.00004969954,0.0002965989,8.066728e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005473753,"about_ca_system_score_gemma":0.00002549348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001904838,"about_ca_topic_score_gemma":0.00001142465,"domain_scores_codex":[0.9989408,0.0000118186,0.000648323,0.00009457001,0.0001422905,0.0001621724],"domain_scores_gemma":[0.9994555,0.00007626744,0.0002241085,0.00009291934,0.0001014409,0.00004981069],"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":[0.00001709459,0.000002719594,0.0003569837,0.0003653791,0.00003661132,0.000002523847,0.001528164,0.7798957,0.1758145,0.000005114956,0.000001165993,0.04197407],"study_design_scores_gemma":[0.0004064683,0.00006615652,0.002716026,0.000244298,0.0000144885,0.00004118256,0.0003410387,0.9104246,0.08538068,0.000007089709,0.0002499877,0.0001080208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5366926,0.00006285589,0.4627961,0.000002372806,0.0003578632,0.00004152531,0.000001391726,0.0000266163,0.00001871396],"genre_scores_gemma":[0.8002099,0.000005793857,0.1994565,0.000001164905,0.0003009645,3.84209e-7,0.000003542682,0.00002162662,9.258004e-8],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2635174,"threshold_uncertainty_score":0.5135848,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4224255587","doi":"10.3390/s22083044","title":"Road Condition Monitoring Using Smart Sensing and Artificial Intelligence: A Review","year":2022,"lang":"en","type":"review","venue":"Sensors","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":185,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Drone; Computer science; Systems engineering; Data science; Engineering; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.07052316807765835,"gpt":0.3342369705640771,"spread":0.2637138024864187,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003220385,0.000471047,0.001147166,0.0002104646,0.0001930377,0.00005623304,0.0001054264,0.00018109,0.00005199335],"category_scores_gemma":[0.00008554789,0.000461384,0.0002445724,0.0003704097,0.00004117934,0.00009248562,0.00008032197,0.000751919,0.00001389372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003749364,"about_ca_system_score_gemma":0.00004262945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002688966,"about_ca_topic_score_gemma":7.237645e-7,"domain_scores_codex":[0.9982103,0.0001088317,0.0006562619,0.0003026749,0.0002389955,0.0004830091],"domain_scores_gemma":[0.9993557,0.00008658523,0.0001533622,0.0002757705,0.0000258583,0.0001026752],"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":[4.585702e-7,0.000001659877,7.400121e-7,0.02168906,0.00006813797,0.00003093045,0.00007585212,0.0004836717,0.000003613428,0.00001609184,0.00003602665,0.9775938],"study_design_scores_gemma":[0.00001433349,0.00001132675,0.000001142323,0.04825711,0.0006885153,0.0004690922,0.0002140396,0.002093772,0.00004959851,0.00006485928,0.9474813,0.0006548679],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0003621069,0.9946094,0.0002221084,0.000002015654,0.003756045,0.0004857878,0.00001882259,0.0002012067,0.0003425765],"genre_scores_gemma":[0.000142124,0.9975246,0.0008613238,0.000008685173,0.001276012,0.00001409102,0.00003580498,0.0001206145,0.00001677728],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9769389,"threshold_uncertainty_score":0.9997838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2913697492","doi":"10.1016/j.autcon.2019.01.017","title":"Sewer damage detection from imbalanced CCTV inspection data using deep convolutional neural networks with hierarchical classification","year":2019,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":175,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Deep learning; Process (computing); Offset (computer science); Pattern recognition (psychology); Contextual image classification; Machine learning; Artificial neural network; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.0116575526586173,"gpt":0.2227223710027695,"spread":0.2110648183441522,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001296623,0.0001778205,0.0001710581,0.0002004273,0.0001082867,0.00007200413,0.0001404541,0.0001703943,0.000038542],"category_scores_gemma":[0.00001933703,0.0001808756,0.0000226439,0.0003889014,0.00007433258,0.0009704718,0.00003353749,0.0003646999,0.00001043593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003647216,"about_ca_system_score_gemma":0.00002502804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001045824,"about_ca_topic_score_gemma":0.0001398925,"domain_scores_codex":[0.9988002,0.0000558471,0.0003405877,0.0003501783,0.00021666,0.0002365862],"domain_scores_gemma":[0.9993118,0.00005144458,0.0001137219,0.0004016114,0.00007979145,0.00004162937],"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":[0.0000652044,0.000009215335,0.05984883,0.00002231163,0.00003323721,0.000001654574,0.0001205248,0.8855376,0.02613089,0.0003692723,0.00001324952,0.02784807],"study_design_scores_gemma":[0.0005548599,0.00001652113,0.2332382,0.00004062658,0.0000140017,0.00003381495,0.0002023414,0.7648371,0.0007021521,0.0001622462,0.00003969844,0.0001584919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7050555,0.0000195379,0.2918946,0.00001315594,0.002224159,0.0002155778,0.00001074971,0.0003853789,0.0001813243],"genre_scores_gemma":[0.9888449,0.000009953919,0.01029625,0.00001282593,0.0004649305,0.00001566358,0.0003236397,0.00002933398,0.000002460441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2837894,"threshold_uncertainty_score":0.7375892,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991760957","doi":"10.1061/(asce)1076-0342(2002)8:3(86)","title":"Modeling Bridge Deterioration Using Case-based Reasoning","year":2002,"lang":"en","type":"article","venue":"Journal of Infrastructure Systems","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":173,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Concordia University; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Bridge (graph theory); Reuse; Case-based reasoning; Computer science; Engineering; Construction engineering; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01950439526824477,"gpt":0.2257122032323612,"spread":0.2062078079641164,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002523986,0.0002470743,0.0003927607,0.0002745408,0.0001280005,0.0001561713,0.0001545186,0.0001638782,0.00002411978],"category_scores_gemma":[0.00005045909,0.0002096766,0.000137068,0.0002130762,0.00001923039,0.0004328573,0.00001235312,0.000456207,0.000002177571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003261872,"about_ca_system_score_gemma":0.00003008332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003374735,"about_ca_topic_score_gemma":0.000003045012,"domain_scores_codex":[0.9984226,0.00004615169,0.0007769178,0.0001154081,0.0003117908,0.0003271365],"domain_scores_gemma":[0.9991295,0.00002087593,0.0002471501,0.0001916991,0.0002848973,0.0001259176],"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":[0.000007068844,0.000002327494,0.0004978047,0.0001050775,0.00004614844,0.0006590268,0.0003477201,0.9837692,0.01243083,0.00002310406,0.000306805,0.00180488],"study_design_scores_gemma":[0.0004205065,0.00004426155,0.0001287924,0.0003986272,0.00004519815,0.01344443,0.0002631586,0.9838898,0.0007854805,0.00002992994,0.0003365779,0.0002131939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7294737,0.0009949643,0.2658348,0.000004399111,0.003356471,0.00009264657,0.00000425782,0.00005867741,0.0001801315],"genre_scores_gemma":[0.9859608,0.00001776911,0.01212213,0.0000150966,0.001822944,0.00000149457,8.288417e-7,0.00005398425,0.000004919064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2564872,"threshold_uncertainty_score":0.8550363,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2271158160","doi":"10.1109/tim.2015.2509278","title":"Automatic Crack Detection and Measurement Based on Image Analysis","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":163,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Process (computing); Measure (data warehouse); Computer vision; Robot; Truck; Field (mathematics); Artificial intelligence; Computer science; Image processing; Machine vision; Engineering; Image (mathematics); Data mining; Mathematics; Automotive engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0152582428402552,"gpt":0.2135242042316524,"spread":0.1982659613913972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000312442,0.000190179,0.0001612957,0.0003446776,0.0001631191,0.00005248697,0.00003666943,0.00005399524,0.00007952244],"category_scores_gemma":[0.000006598842,0.0001462184,0.00007148849,0.0002184085,0.00003564276,0.0001651999,4.515494e-7,0.00009308068,0.00000997443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004652514,"about_ca_system_score_gemma":0.00001739916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001170406,"about_ca_topic_score_gemma":0.0001010804,"domain_scores_codex":[0.9987238,0.00003753372,0.0002412613,0.0002196182,0.0005840551,0.0001937316],"domain_scores_gemma":[0.9995727,0.00001761887,0.00004075003,0.0001555502,0.000116507,0.00009686042],"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":[0.00005386077,0.00005162431,0.0001165134,0.0000773666,0.0003657088,0.000001213393,0.0002066779,0.01087014,0.2738886,0.000006768782,0.00002437895,0.7143372],"study_design_scores_gemma":[0.002688469,0.0003214045,0.01634214,0.0002907428,0.0006612552,0.000003912842,0.0002766269,0.1076279,0.8709962,0.00005747547,0.0002953218,0.0004385353],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2030379,0.00001512354,0.7954814,0.0001137421,0.0006200889,0.0002454365,0.000009263209,0.0001786766,0.0002983295],"genre_scores_gemma":[0.9986443,0.00005477132,0.001076541,0.00007578138,0.00002992528,0.00008842735,5.414877e-7,0.00001943841,0.00001025867],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7956064,"threshold_uncertainty_score":0.5962614,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W28313688","doi":"10.17226/23348","title":"Automated Pavement Distress Collection Techniques","year":2004,"lang":"en","type":"book","venue":"Transportation Research Board eBooks","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":143,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Distress; Computer science; Psychology; Clinical psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.01922233882244176,"gpt":0.2932812568430448,"spread":0.2740589180206031,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002440644,0.00034743,0.0003283048,0.0004751924,0.0002045424,0.0000809878,0.0002353182,0.0004466468,0.00006420865],"category_scores_gemma":[0.000004385478,0.0003597788,0.0001298943,0.0001043525,0.0001503104,0.00006343714,0.000006651411,0.001036568,0.00002509473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001891071,"about_ca_system_score_gemma":0.0005262689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002339698,"about_ca_topic_score_gemma":0.0008716004,"domain_scores_codex":[0.997753,0.00002880485,0.0004570292,0.000339119,0.000833652,0.0005884388],"domain_scores_gemma":[0.9991523,0.0000392969,0.00005564469,0.0003160521,0.0003029724,0.0001337521],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005224761,0.0001526192,0.0003326757,0.01507627,0.002208133,0.001884467,0.01833973,0.03384471,0.04094746,0.06726626,0.7035833,0.1158419],"study_design_scores_gemma":[0.00139447,0.0004422216,0.003712321,0.003883091,0.0001537532,0.000003528382,0.0002450306,0.001523624,0.1318604,0.02651608,0.8284483,0.001817154],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.004261796,0.0002427722,0.003667609,0.00003784488,0.001291303,0.002641136,0.000370653,0.007834325,0.9796526],"genre_scores_gemma":[0.1445993,0.0002651601,0.002834005,0.0000325751,0.000859701,0.0009947029,0.001416343,0.0004161103,0.848582],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1403375,"threshold_uncertainty_score":0.9998854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3087776899","doi":"10.3390/s20195564","title":"An Automated Machine-Learning Approach for Road Pothole Detection Using Smartphone Sensor Data","year":2020,"lang":"en","type":"article","venue":"Sensors","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":141,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"Innovate UK; University of Illinois at Urbana-Champaign","keywords":"Pothole (geology); Computer science; Road surface; Random forest; Robustness (evolution); Real-time computing; Global Positioning System; Artificial intelligence; Machine learning; Data mining; Engineering; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.02932383318337611,"gpt":0.2633845644882231,"spread":0.234060731304847,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001178072,0.0001887791,0.000192044,0.00005829952,0.0001518021,0.00006088309,0.0001913113,0.0001002731,0.000004613164],"category_scores_gemma":[0.00007159473,0.0001901811,0.00003956982,0.0001862361,0.00001810476,0.0002040758,0.00004157695,0.0002445374,0.000005745964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004832915,"about_ca_system_score_gemma":0.000008707952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005816633,"about_ca_topic_score_gemma":0.000004131263,"domain_scores_codex":[0.9990183,0.00003557492,0.0001902616,0.0003156344,0.000112396,0.0003278154],"domain_scores_gemma":[0.9994875,0.00001448115,0.00004024317,0.0003076453,0.00003878219,0.0001113341],"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":[0.00002568351,0.000004423815,0.0003036185,0.00008445307,0.00003151168,0.000004442086,0.000488228,0.8116421,0.1822028,0.000001429822,0.00004038915,0.005170927],"study_design_scores_gemma":[0.0003098283,0.00004137582,0.0005622509,0.000009116917,0.00003008104,0.00001921972,0.0004375639,0.9671538,0.02972553,0.000002101294,0.001485861,0.0002232948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9045638,0.00004962095,0.09254766,0.00001390542,0.0004221554,0.0002305804,0.00006744367,0.001894499,0.0002102581],"genre_scores_gemma":[0.9521284,0.000005494192,0.04690032,0.00003198288,0.0006440174,0.000004683387,0.0001935127,0.00007802953,0.00001358066],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1555117,"threshold_uncertainty_score":0.7755359,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3127380385","doi":"10.1061/(asce)is.1943-555x.0000602","title":"Using Machine Learning to Examine Impact of Type of Performance Indicator on Flexible Pavement Deterioration Modeling","year":2021,"lang":"en","type":"article","venue":"Journal of Infrastructure Systems","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":137,"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":"Random forest; Conventional PCI; Computer science; International Roughness Index; Machine learning; Predictive modelling; Artificial intelligence; Algorithm; Regression; Data mining; Statistics; Mathematics; Engineering; Surface finish","retraction":null,"screen_n_in":null,"score":{"opus":0.02507078273532522,"gpt":0.280486056063361,"spread":0.2554152733280358,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002654587,0.0001835121,0.0004636094,0.000296332,0.00004172472,0.00002614222,0.0001284973,0.00009436873,0.00002083024],"category_scores_gemma":[0.00006122542,0.0001420674,0.0001135356,0.0003167261,0.000010948,0.0001673428,0.00002802171,0.0003379047,6.939939e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002837907,"about_ca_system_score_gemma":0.0001309539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002107684,"about_ca_topic_score_gemma":8.868051e-7,"domain_scores_codex":[0.9985312,0.00004184956,0.000780254,0.00009562333,0.0003471165,0.0002039544],"domain_scores_gemma":[0.9989197,0.00001869476,0.0003894023,0.0001571506,0.0004240121,0.00009104204],"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":[0.00003939345,0.00000411532,0.01086297,0.0001722137,0.00008473986,0.000005373012,0.000375771,0.6763717,0.3113619,0.000008481983,0.000009474517,0.0007038942],"study_design_scores_gemma":[0.000656758,0.0009952128,0.01004325,0.001497282,0.00006379756,0.0002793207,0.0006145571,0.8032811,0.182131,0.00002160474,0.0001633891,0.0002526875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9773002,0.0004918812,0.02072369,0.000001749914,0.001292372,0.00009226462,0.0000066441,0.00001443734,0.00007675785],"genre_scores_gemma":[0.9953029,0.00006037311,0.004184668,0.000003872564,0.0004055375,6.897862e-7,0.000003473397,0.00003084524,0.000007679924],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1292309,"threshold_uncertainty_score":0.5793342,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169659806","doi":"10.1260/1369-4332.17.3.303","title":"Achievements and Challenges in Machine Vision-Based Inspection of Large Concrete Structures","year":2014,"lang":"en","type":"article","venue":"Advances in Structural Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":137,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Engineering and Physical Sciences Research Council; National Science Foundation","keywords":"Computer science; Visual inspection; Machine vision; Construction engineering; Set (abstract data type); Engineering; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.004621237346969653,"gpt":0.2319632681178019,"spread":0.2273420307708322,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001320403,0.0002135787,0.0002816043,0.0002419195,0.00002282598,0.00001090213,0.000115306,0.00007736663,0.000004443369],"category_scores_gemma":[0.00004942246,0.0001999023,0.00002658396,0.0001642321,0.00002732356,0.0003160386,0.00003172141,0.0002402101,1.898831e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000661891,"about_ca_system_score_gemma":0.000003474513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001140211,"about_ca_topic_score_gemma":0.00006550584,"domain_scores_codex":[0.9990346,0.00001412858,0.0002996776,0.0001971002,0.0001412342,0.0003132341],"domain_scores_gemma":[0.9996845,0.00006864451,0.00004071638,0.0001479944,0.00001720953,0.00004092906],"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":[0.00002887752,0.000001507102,0.01557879,0.0008179348,0.00001327016,0.000005314794,0.0003618016,0.9119887,0.01258545,0.009523669,8.746798e-7,0.04909387],"study_design_scores_gemma":[0.001552108,0.0000874125,0.1722122,0.0003117839,0.000006318123,0.000007673821,0.0001053453,0.807916,0.01386941,0.001234133,0.002293563,0.0004039495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9814274,0.01285999,0.004010835,0.00002079627,0.0009678736,0.0001468536,0.00001025984,0.0001704583,0.0003854844],"genre_scores_gemma":[0.994406,0.001494792,0.003960318,0.000008030892,0.00008626389,0.000008742446,0.000006040188,0.0000293365,5.119911e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1566335,"threshold_uncertainty_score":0.815178,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3000110218","doi":"10.1155/2020/6412562","title":"Automated Pavement Crack Damage Detection Using Deep Multiscale Convolutional Features","year":2020,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":137,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Pixel; Deep learning; Noise (video); Process (computing); Pattern recognition (psychology); Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.007317009610048299,"gpt":0.2297082347808916,"spread":0.2223912251708433,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000444439,0.0001093284,0.0001484618,0.00006024951,0.0000515814,0.00001340547,0.0000562619,0.00005264455,0.00001075821],"category_scores_gemma":[0.00001072919,0.0001041139,0.00007447966,0.0001294552,0.00001402168,0.0003888857,9.595798e-7,0.0002034811,0.00000106443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008976213,"about_ca_system_score_gemma":0.00001409563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002261503,"about_ca_topic_score_gemma":0.00001615424,"domain_scores_codex":[0.9992459,0.000008560077,0.0003435319,0.00007315695,0.0001930759,0.0001357398],"domain_scores_gemma":[0.9995983,0.00001247869,0.0001360391,0.00003844947,0.0001372894,0.00007745536],"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":[0.00003949111,0.000004344614,0.0004886842,0.00003956231,0.00002811917,0.00001913947,0.0007950856,0.727276,0.2690107,0.00001009771,0.00001236652,0.002276389],"study_design_scores_gemma":[0.001893627,0.0001854239,0.5958535,0.0001394816,0.0001072755,0.00003112086,0.001173238,0.2295026,0.1698522,0.0001364262,0.0008455901,0.0002794434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9052124,0.0001712825,0.0935184,0.00003298276,0.0008425312,0.00007562508,0.000006764923,0.0001267793,0.00001324041],"genre_scores_gemma":[0.9798058,0.00003739,0.01974688,0.00003761511,0.0003394445,0.000001331607,0.00001057389,0.00001943427,0.000001540167],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5953648,"threshold_uncertainty_score":0.4245644,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2674352656","doi":"10.1016/j.autcon.2017.06.008","title":"Machine vision-based model for spalling detection and quantification in subway networks","year":2017,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":131,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Spall; Artificial intelligence; Computer science; Machine vision; Algorithm; Image processing; Machine learning; Engineering; Computer vision; Image (mathematics); Structural engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0106491069224853,"gpt":0.2508803314358804,"spread":0.2402312245133951,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002099623,0.00009300315,0.0001024482,0.0001696249,0.0001573872,0.00009432976,0.00005502844,0.000104234,0.000001091485],"category_scores_gemma":[0.00005408054,0.000103122,0.00001898784,0.00005799334,0.0000371097,0.0003545536,0.000006688876,0.0001113742,4.550728e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001005631,"about_ca_system_score_gemma":0.000009840933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003960541,"about_ca_topic_score_gemma":0.0005074991,"domain_scores_codex":[0.9994181,0.000009972637,0.0002330334,0.0001435314,0.00005881192,0.0001365998],"domain_scores_gemma":[0.9996566,0.0000369438,0.00008762351,0.0001631692,0.00003708872,0.00001863626],"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":[0.00001382652,0.000002422882,0.01005325,0.00003999345,0.000002093254,1.900385e-7,0.00005875312,0.8683104,0.002920816,0.0006027435,0.000001791607,0.1179937],"study_design_scores_gemma":[0.0005055977,0.000007908352,0.05655447,0.00007511758,0.000003873994,0.000002540498,0.00002270108,0.9384199,0.002902366,0.001391685,0.00001565426,0.00009815509],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3271798,0.00003198126,0.6717629,0.00002995915,0.0006420431,0.0001879368,0.000001960989,0.00008788668,0.00007547504],"genre_scores_gemma":[0.9890376,0.00003099411,0.01076294,0.000004875837,0.00007613343,0.00005840943,0.00001144916,0.00001473621,0.000002908328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6618577,"threshold_uncertainty_score":0.4205193,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2018299540","doi":"10.1061/(asce)cp.1943-5487.0000179","title":"Automated Visual Recognition of Dump Trucks in Construction Videos","year":2011,"lang":"en","type":"article","venue":"Journal of Computing in Civil Engineering","topic":"Infrastructure Maintenance and Monitoring","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":"University of Toronto","funders":"","keywords":"Truck; Heavy equipment; Engineering; Control (management); Histogram of oriented gradients; Computer science; Histogram; Transport engineering; Artificial intelligence; Automotive engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.009672425582679762,"gpt":0.2119388900153907,"spread":0.2022664644327109,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003683092,0.0001393633,0.0003137662,0.000598441,0.00001008925,0.000009204162,0.0001022484,0.0001248168,0.00001106143],"category_scores_gemma":[0.00008305602,0.0001468072,0.00006530607,0.0003425322,0.00001548057,0.0001587116,0.00001770043,0.0005132985,8.119647e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001332207,"about_ca_system_score_gemma":0.0000206178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001335179,"about_ca_topic_score_gemma":0.00001206821,"domain_scores_codex":[0.9987933,0.00001620941,0.0007400459,0.00007328716,0.0001427996,0.00023433],"domain_scores_gemma":[0.9995818,0.00006085646,0.0001690605,0.00006213583,0.00008430841,0.00004183097],"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":[0.00003347671,0.00002759781,0.02076618,0.0002973549,0.00005406767,0.00009178468,0.002393566,0.9351269,0.02658716,0.00008065969,0.0000186369,0.01452259],"study_design_scores_gemma":[0.001092819,0.0001093692,0.1495714,0.001892788,0.00001662366,0.0003203464,0.0003122067,0.8108651,0.03523744,0.0002967285,0.00002039329,0.0002648329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9662285,0.00008915126,0.03154894,0.00000154152,0.001382129,0.00005446519,6.230579e-7,0.0001195735,0.0005750439],"genre_scores_gemma":[0.9828384,0.00002218006,0.01694646,0.000002366141,0.000163694,6.231642e-7,5.697025e-7,0.00002547418,2.619608e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1288052,"threshold_uncertainty_score":0.5986626,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4225137532","doi":"10.1093/tse/tdac026","title":"Computer vision for road imaging and pothole detection: a state-of-the-art review of systems and algorithms","year":2022,"lang":"en","type":"review","venue":"Transportation Safety and Environment","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":129,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; Central Universities in China; Science and Technology Commission of Shanghai Municipality","keywords":"Pothole (geology); Computer science; Artificial intelligence; Segmentation; Deep learning; Convolutional neural network; Bottleneck; Point cloud; Machine learning; Object detection; Image processing; Cloud computing; Image segmentation; Computer vision; Algorithm; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.008762328827551279,"gpt":0.2272413915187325,"spread":0.2184790626911812,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001855706,0.0001626155,0.0005394805,0.00003278361,0.00006345513,0.000005283018,0.00003946483,0.00003313544,0.000006673333],"category_scores_gemma":[9.405773e-7,0.0001263851,0.0000880866,0.00004005561,0.00004147419,0.00005085849,0.000008264047,0.0001039304,1.421709e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003569875,"about_ca_system_score_gemma":0.000005366745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005023472,"about_ca_topic_score_gemma":8.771041e-7,"domain_scores_codex":[0.9991444,0.00002469631,0.0004691433,0.000155302,0.0001153014,0.00009111055],"domain_scores_gemma":[0.9996778,0.00003558028,0.0001475573,0.0001077342,0.000005021,0.00002634877],"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":[0.000003936741,0.000002548447,0.000005029225,0.05790857,0.00003292538,6.287954e-7,0.00008361456,0.001010036,0.000004345062,0.000004902421,0.00001463586,0.9409288],"study_design_scores_gemma":[0.0001648191,0.00003489762,0.0008924948,0.01333233,0.000272345,0.00001440393,0.00001750272,0.001203094,0.000006048303,0.000006590547,0.9839163,0.000139147],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002799276,0.9631021,0.03572614,0.000008307489,0.0002807314,0.000677992,0.000157348,0.00001032907,0.000009063995],"genre_scores_gemma":[0.0002085039,0.9989353,0.0006398005,0.000007776654,0.00003452344,0.00006671774,0.00006939221,0.00002146692,0.00001656413],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9839017,"threshold_uncertainty_score":0.5153835,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155647581","doi":"10.1139/l04-029","title":"Conceptual cost estimation of building projects with regression analysis and neural networks","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":126,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Cost estimate; Artificial neural network; Estimation; Regression analysis; Computer science; Scope (computer science); Regression; Range (aeronautics); Conceptual model; Linear regression; Conceptual design; Machine learning; Data mining; Econometrics; Statistics; Engineering; Mathematics; Systems engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.005000484566313654,"gpt":0.1882971831675333,"spread":0.1832966986012196,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000919545,0.0001246173,0.0002388159,0.0004456745,0.00003521445,0.0000274583,0.0000756617,0.00005452484,0.000004775074],"category_scores_gemma":[0.00003336768,0.0001034967,0.00004809987,0.0004041244,0.00003770135,0.000198067,0.000004024344,0.0002211284,2.501802e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001396999,"about_ca_system_score_gemma":0.00008119721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002483368,"about_ca_topic_score_gemma":0.007021739,"domain_scores_codex":[0.9993731,0.000004120064,0.0002282232,0.00006296355,0.00009732106,0.0002342291],"domain_scores_gemma":[0.9995366,0.00001912269,0.00007791507,0.00007359422,0.00007405454,0.0002186921],"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":[0.000003666619,5.793789e-7,0.002157988,0.00002316161,0.0001162412,0.00004698807,0.0004297215,0.9952779,0.000492977,0.0001839802,0.000008663847,0.001258162],"study_design_scores_gemma":[0.0006106539,0.00008737834,0.01054847,0.0005670403,0.0002232431,0.0001964201,0.0002138097,0.9835882,0.003647398,0.00002351419,0.00007765677,0.0002162283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5233427,0.0005845515,0.4756888,0.000009773961,0.0002640025,0.00005258977,0.000001845955,0.00001402353,0.00004171783],"genre_scores_gemma":[0.9956706,0.000015714,0.004161004,0.000004194302,0.0001250727,0.00000136545,0.000001361367,0.00001972671,9.380696e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4723279,"threshold_uncertainty_score":0.4220474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166566694","doi":"10.1061/(asce)0733-947x(2001)127:1(21)","title":"Prediction of Operating Speed on Three-Dimensional Highway Alignments","year":2001,"lang":"en","type":"article","venue":"Journal of Transportation Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":125,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Toronto Metropolitan University","funders":"Core Research for Evolutional Science and Technology","keywords":"Operating speed; Geometric design; Consistency (knowledge bases); Design speed; Highway engineering; Computer science; Transport engineering; Crest; Simulation; Engineering; Civil engineering; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.009788205530650953,"gpt":0.1966323229746938,"spread":0.1868441174440428,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001213632,0.0001176601,0.0001793275,0.000159501,0.00002060899,0.000008025633,0.0000690883,0.00005336759,0.00002070574],"category_scores_gemma":[0.00001188245,0.0001080286,0.00008084251,0.0001228385,0.000006091387,0.0002092025,9.337247e-7,0.0001795919,9.920424e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005841415,"about_ca_system_score_gemma":0.00001099864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002625544,"about_ca_topic_score_gemma":0.000001779686,"domain_scores_codex":[0.9990441,0.000003024991,0.0004853485,0.00005832109,0.0002720488,0.0001371967],"domain_scores_gemma":[0.9996635,0.0000273137,0.00009567273,0.00006368487,0.0000966291,0.00005313862],"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":[0.00001420668,0.000009274258,0.003856856,0.00003506826,0.00005405346,0.00002381499,0.0001342878,0.8794739,0.1155706,0.00007790222,0.00005825808,0.0006917482],"study_design_scores_gemma":[0.002332706,0.0004293944,0.4208843,0.001297165,0.0001343446,0.0001175952,0.0001187745,0.3269207,0.2446763,0.00007701721,0.002613296,0.0003984695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9641971,0.00008001136,0.03415892,0.00001176598,0.001340681,0.00005250703,0.00001323417,0.00004758832,0.00009820551],"genre_scores_gemma":[0.9960076,0.00002734252,0.003610532,0.000006583536,0.0003079098,8.008146e-7,0.000008525756,0.00002420206,0.000006525758],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5525532,"threshold_uncertainty_score":0.4405277,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2097221445","doi":"10.1016/j.autcon.2005.02.007","title":"Segmentation of buried concrete pipe images","year":2005,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":125,"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":"Piping; Pipeline transport; Pipeline (software); Segmentation; Engineering; Canalisation; Nominal Pipe Size; Trenchless technology; Image segmentation; Image processing; Computer science; Civil engineering; Structural engineering; Image (mathematics); Artificial intelligence; Mechanical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.003780278290669983,"gpt":0.2133111761124862,"spread":0.2095308978218162,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007221165,0.00007016359,0.00009088292,0.0001325905,0.00001962133,0.00001122522,0.00003408964,0.00004977167,0.00004717192],"category_scores_gemma":[0.00001362446,0.00007671722,0.00001969067,0.0001400827,0.00003599497,0.0003198778,0.000004861066,0.00006423358,0.000008690738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000900841,"about_ca_system_score_gemma":0.000009378927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001003745,"about_ca_topic_score_gemma":0.000002456798,"domain_scores_codex":[0.99948,0.00001216031,0.0002516826,0.00007011235,0.00008888908,0.00009712644],"domain_scores_gemma":[0.9997966,0.00001770526,0.00005548399,0.00007500529,0.00004113433,0.00001408783],"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":[0.00001218031,0.000002385556,0.009855581,0.0001168394,0.00002567439,9.689664e-7,0.001091422,0.05356407,0.6181626,0.00228061,0.0004835836,0.314404],"study_design_scores_gemma":[0.0006436853,0.00001428792,0.0271318,0.00006909535,0.00001015649,0.00002274766,0.0005205568,0.05602389,0.9141513,0.0005478995,0.0007137476,0.0001508399],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9665832,0.00004613432,0.02929163,0.00004879391,0.0007444466,0.0001230821,0.000004305526,0.0002138388,0.002944572],"genre_scores_gemma":[0.9690521,0.00002175823,0.03070821,0.000007295385,0.0001699581,0.00001214584,0.0000104109,0.000008734737,0.000009432602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3142532,"threshold_uncertainty_score":0.3128437,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2072586327","doi":"10.1139/l04-092","title":"Traffic load modelling and factors influencing the accuracy of predicted extremes","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Weigh in motion; Truck; Monte Carlo method; Bridge (graph theory); Sensitivity (control systems); Computer science; Engineering; Simulation; Statistics; Mathematics; Automotive engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0079041279491496,"gpt":0.1737985851847089,"spread":0.1658944572355593,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001508218,0.0001494742,0.0001996072,0.0002034445,0.0000528756,0.00003790199,0.0001719478,0.0000620372,0.0000179718],"category_scores_gemma":[0.0001003481,0.000116516,0.00006244718,0.0001421966,0.00002850094,0.0002856974,0.00000607789,0.0003209389,2.045197e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001951711,"about_ca_system_score_gemma":0.0001932051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001603524,"about_ca_topic_score_gemma":0.006230372,"domain_scores_codex":[0.9991464,0.000005416864,0.0003495625,0.00005958784,0.000143509,0.0002955246],"domain_scores_gemma":[0.9993905,0.00007991774,0.00007726672,0.0001072609,0.0001115347,0.0002334968],"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":[0.000001152061,5.457928e-7,0.0006039955,0.0000412537,0.00004116619,0.00000677734,0.002725642,0.9936942,0.001186347,0.00002587949,0.0001026423,0.001570353],"study_design_scores_gemma":[0.0003747265,0.0000342292,0.006770841,0.0005700013,0.00006125118,0.0001332409,0.0008693347,0.9751486,0.004668171,0.00002311584,0.01105128,0.0002951708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9836468,0.002809211,0.01273017,0.00002447737,0.000489702,0.00005116462,0.000005764235,0.00002664922,0.0002161268],"genre_scores_gemma":[0.9989752,0.00008897479,0.0005575116,0.000006946867,0.0003370916,7.318828e-7,3.799737e-7,0.00002867542,0.00000451439],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01854561,"threshold_uncertainty_score":0.4751385,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3215735958","doi":"10.1016/j.istruc.2021.10.088","title":"Vibration-based multiclass damage detection and localization using long short-term memory networks","year":2021,"lang":"en","type":"article","venue":"Structures","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":123,"is_retracted":false,"has_abstract":false,"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; Western University","keywords":"Benchmark (surveying); Computer science; Pattern recognition (psychology); Artificial intelligence; Convolutional neural network; Novelty detection; Bridge (graph theory); Artificial neural network; Binary classification; Novelty; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.007399391193497955,"gpt":0.2214294804103774,"spread":0.2140300892168795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003383914,0.0001434526,0.0001161015,0.00005562801,0.0001388983,0.00008972605,0.00004111872,0.0001110277,0.00002107471],"category_scores_gemma":[0.00001955706,0.0001439414,0.00002883541,0.0001366457,0.00003365975,0.000141764,0.00001805506,0.0001467171,2.238075e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006215762,"about_ca_system_score_gemma":0.00001718684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009235217,"about_ca_topic_score_gemma":0.00009604233,"domain_scores_codex":[0.9993724,0.00002200116,0.0001480214,0.0001658114,0.00009818943,0.0001935862],"domain_scores_gemma":[0.9997028,0.00002204929,0.00001923199,0.0001450688,0.00006195634,0.00004885773],"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":[0.00000468456,0.000001066157,0.006079638,0.00005193399,0.00001622506,0.00001905656,0.00008896254,0.909606,0.0728757,0.00002303223,0.000007580776,0.01122609],"study_design_scores_gemma":[0.0001501648,0.000005185264,0.05199955,0.00002825408,0.00002073919,0.00001551065,0.00006622297,0.7755623,0.1718819,0.0001100989,0.00001762577,0.0001425006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5902978,0.0001876901,0.4084837,0.000001850677,0.0007866556,0.00005859157,0.000001690174,0.00009927198,0.0000827465],"genre_scores_gemma":[0.9972361,0.00001240971,0.002220075,0.00004225849,0.0004318159,0.000003300681,0.00001822525,0.0000312001,0.000004644856],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4069383,"threshold_uncertainty_score":0.5869762,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1970120865","doi":"10.1007/s006030200009","title":"Technical Note Estimation of the Joint Roughness Coefficient (JRC) by Visual Comparison","year":2002,"lang":"en","type":"article","venue":"Rock Mechanics and Rock Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":120,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Joint (building); Surface finish; Estimation; Mathematics; Geology; Computer science; Statistics; Engineering; Structural engineering; Mechanical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.006493052908003356,"gpt":0.2078808343097298,"spread":0.2013877814017264,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006211778,0.000182144,0.0002287549,0.0000547636,0.00009478738,0.00002097417,0.0001156403,0.0001155579,0.000007326141],"category_scores_gemma":[0.00002972532,0.0001456029,0.00005799914,0.0001774423,8.014111e-7,0.00006266261,0.00008837815,0.000249933,0.000002679533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006832279,"about_ca_system_score_gemma":0.000003141328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002720856,"about_ca_topic_score_gemma":6.856708e-7,"domain_scores_codex":[0.9991233,0.000005486498,0.0002911195,0.0001408558,0.0001840992,0.000255081],"domain_scores_gemma":[0.9996924,0.00001992826,0.00004574373,0.0001572407,0.00002826123,0.00005638025],"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":[9.752609e-7,0.00001272072,0.000005430964,0.00008664643,0.00000705191,4.338764e-7,0.000136405,0.942874,0.05432491,0.001207585,0.0003618521,0.0009820579],"study_design_scores_gemma":[0.0001557374,0.0000269529,0.00003550604,0.0001091922,0.00001727249,0.0000108855,0.00002538114,0.9390061,0.05955255,0.00003166866,0.0008663938,0.0001623271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0122376,0.0006290852,0.9859722,0.0000188363,0.0007819679,0.0001389978,0.000005941834,0.0001619317,0.0000534787],"genre_scores_gemma":[0.9986619,0.00005543101,0.001139056,0.000007459723,0.00007049726,0.00001067388,0.000002349077,0.00003539001,0.00001729179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9864243,"threshold_uncertainty_score":0.5937513,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3011931516","doi":"10.1111/mice.12549","title":"Postdisaster image-based damage detection and repair cost estimation of reinforced concrete buildings using dual convolutional neural networks","year":2020,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":118,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Convolutional neural network; Computer science; Identification (biology); Artificial neural network; Reinforced concrete; Dual (grammatical number); Artificial intelligence; Reliability engineering; Risk analysis (engineering); Machine learning; Structural engineering; Engineering; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.004896695296489259,"gpt":0.1828219904729464,"spread":0.1779252951764571,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00008037774,0.0003366379,0.0003548627,0.0001234799,0.00009049077,0.00007543295,0.00008342459,0.000157588,0.000008955732],"category_scores_gemma":[0.00004069151,0.0003486489,0.00007770079,0.0002145819,0.00007888924,0.0004101816,0.00008444935,0.0003755947,2.100039e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006231093,"about_ca_system_score_gemma":0.0000143201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005997449,"about_ca_topic_score_gemma":4.8448e-7,"domain_scores_codex":[0.9987927,0.00001553801,0.0004086656,0.0002860495,0.0001547716,0.000342292],"domain_scores_gemma":[0.9994475,0.0000678807,0.00009018252,0.0001407452,0.00007849492,0.0001751848],"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":[0.00002709431,2.723374e-7,0.0001461141,0.0002867385,0.00004058863,0.000007432241,0.0002010841,0.9366904,0.0599209,0.00009223408,0.00004174479,0.002545355],"study_design_scores_gemma":[0.000720272,0.00009758185,0.006335673,0.0001237555,0.00004044687,0.00005877492,0.00002448973,0.9860856,0.006102028,0.000009217782,0.00008218028,0.0003199642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4960615,0.00008455797,0.5030819,0.000008527445,0.0003868768,0.0001313742,0.000007753966,0.0002279601,0.000009581648],"genre_scores_gemma":[0.9561346,0.000009712181,0.04313498,0.00009046304,0.0005558983,0.000005984324,0.00001911855,0.00004863811,5.808693e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4600731,"threshold_uncertainty_score":0.9998965,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3112944626","doi":"10.1016/j.autcon.2020.103516","title":"Review of image-based analysis and applications in construction","year":2020,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","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":"Construction engineering; Computer science; Risk analysis (engineering); Visualization; Sustainability; Resilience (materials science); Data science; Sizing; Systems engineering; Engineering; Artificial intelligence; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.004901278774654697,"gpt":0.2228674154568282,"spread":0.2179661366821735,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008848697,0.00008402719,0.0002082291,0.0002691899,0.00001746362,0.0000097349,0.00003790316,0.00004958904,0.00002602202],"category_scores_gemma":[0.00003873917,0.00009108382,0.00003776911,0.001163709,0.00006457209,0.0001588763,0.000006480667,0.00009577411,0.000001352469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005151799,"about_ca_system_score_gemma":0.00001701403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002032971,"about_ca_topic_score_gemma":0.00001181776,"domain_scores_codex":[0.9993325,0.00002303799,0.0003602266,0.0001235702,0.00007528452,0.00008541302],"domain_scores_gemma":[0.9997173,0.00003001928,0.00008154726,0.00009059666,0.00005286605,0.00002767005],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002158587,0.00002457486,0.5266594,0.01525975,0.0002241944,0.000002689269,0.0007493816,0.06206919,0.02291475,0.00771528,0.000196023,0.3641632],"study_design_scores_gemma":[0.00180232,0.00005108491,0.4172846,0.003619625,0.0004992182,0.00002551702,0.00129032,0.524963,0.0456422,0.001927753,0.002175011,0.0007193143],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4861856,0.002977388,0.5073453,0.0004378683,0.0003389437,0.0008564094,0.00002571361,0.0003754068,0.001457394],"genre_scores_gemma":[0.9710057,0.001144774,0.02763412,0.00007141619,0.00004643342,0.00005280992,0.00003611404,0.000008412611,2.46975e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4848201,"threshold_uncertainty_score":0.371429,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2639936844","doi":"10.1016/j.autcon.2017.05.005","title":"Integrated detection and tracking of workforce and equipment from construction jobsite videos","year":2017,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":111,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Workforce; Process (computing); Recall; Precision and recall; Tracking (education); Productivity; Computer science; Construction industry; Construction engineering; Engineering; Artificial intelligence; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.0101665419074562,"gpt":0.2271405341027873,"spread":0.2169739921953311,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009991566,0.0001143762,0.0001527849,0.0001399755,0.0001429773,0.00009915237,0.00004629743,0.0001070093,0.000008302647],"category_scores_gemma":[0.00005740905,0.0001205995,0.00001673201,0.00006329486,0.0001506688,0.0005843812,0.00002032988,0.0001336489,7.050544e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007950226,"about_ca_system_score_gemma":0.000008493515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002010889,"about_ca_topic_score_gemma":0.00009140133,"domain_scores_codex":[0.9993537,0.00001749593,0.0002788865,0.0001457503,0.00008801984,0.0001161391],"domain_scores_gemma":[0.9995881,0.00003052846,0.0001502068,0.0001502682,0.00005291889,0.00002794742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001498376,0.000001802934,0.06890028,0.00004181449,0.00001863712,9.395314e-7,0.0004016539,0.0009373214,0.06657188,0.0006406225,0.000002028254,0.8624681],"study_design_scores_gemma":[0.001024307,0.00003093625,0.7304416,0.0004923439,0.00003392977,0.00007022615,0.001206664,0.1297419,0.1313344,0.005105521,0.0002538722,0.0002643183],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9663695,0.00008769624,0.03158301,0.00001518125,0.001199018,0.0001298888,0.000005859789,0.0001130987,0.0004967121],"genre_scores_gemma":[0.9897968,0.0001137938,0.009972349,0.000002562566,0.00008508484,0.00001047435,0.000005484062,0.00001111515,0.00000230967],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8622037,"threshold_uncertainty_score":0.4917904,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2021428030","doi":"10.1111/j.1467-8667.2006.00458.x","title":"Comparison of Two Evolutionary Algorithms for Optimization of Bridge Deck Repairs","year":2006,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":106,"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":"Bridge (graph theory); Computer science; Genetic algorithm; Prioritization; Selection (genetic algorithm); Deck; Operations research; Evolutionary algorithm; Optimization problem; Bridge maintenance; Mathematical optimization; Reliability engineering; Engineering; Artificial intelligence; Management science; Machine learning; Algorithm; Structural engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.007563008613780916,"gpt":0.2336712894310342,"spread":0.2261082808172533,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007605508,0.000262836,0.0004524813,0.0001898793,0.00004856298,0.0000177506,0.0001398149,0.0001156804,0.00000684343],"category_scores_gemma":[0.00001449656,0.0002700946,0.0001010415,0.0002033004,0.00004433975,0.0001726082,0.00005007223,0.0001585486,1.305331e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005874036,"about_ca_system_score_gemma":0.00001626392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001607166,"about_ca_topic_score_gemma":0.000002383848,"domain_scores_codex":[0.9987727,0.00000742791,0.0005598568,0.000214239,0.0001477223,0.0002980868],"domain_scores_gemma":[0.9994283,0.00007639388,0.0001128883,0.0001981428,0.0001281133,0.00005621101],"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":[0.000007398462,0.000008990666,0.004966203,0.0003572236,0.00004331073,7.885309e-7,0.0001193349,0.9843913,0.005521556,0.0008931542,0.001252318,0.002438413],"study_design_scores_gemma":[0.000578034,0.0000745535,0.09095311,0.0001458198,0.00002902568,0.00001576031,0.00001156789,0.9018222,0.005088089,0.0004234381,0.000623455,0.0002349419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1862916,0.0006689237,0.8116548,0.00000375166,0.000891968,0.0001853955,0.00002899499,0.0001834383,0.00009106999],"genre_scores_gemma":[0.7896737,0.00001955385,0.2096514,0.000003449074,0.0005562703,0.00001134436,0.00004378277,0.00003821425,0.000002309978],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6033821,"threshold_uncertainty_score":0.9999751,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061004358","doi":"10.1109/itsc.2010.5625290","title":"An automatic image recognition system for winter road surface condition classification","year":2010,"lang":"en","type":"article","venue":"","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":106,"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":"Support vector machine; Artificial intelligence; RGB color model; Computer science; Feature (linguistics); Feature extraction; Contextual image classification; Road surface; Computer vision; Pattern recognition (psychology); Surface (topology); Feature vector; Image (mathematics); Engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.009891579045755005,"gpt":0.2439729985223395,"spread":0.2340814194765845,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001155549,0.00009594073,0.00008871257,0.00003647252,0.00005397298,0.00006072812,0.0000645813,0.000084427,0.00006501736],"category_scores_gemma":[0.00001152882,0.00008738921,0.0000332474,0.0000416955,0.00001410115,0.0003506496,0.000002901733,0.0001071069,0.0000646052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005300641,"about_ca_system_score_gemma":0.000005882478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000597986,"about_ca_topic_score_gemma":0.00001379209,"domain_scores_codex":[0.9995018,0.000007714987,0.0001616557,0.0001141822,0.00005977383,0.0001548358],"domain_scores_gemma":[0.9996606,0.00001608586,0.00002859213,0.0001629297,0.00008966107,0.00004215751],"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":[0.000003323984,0.000005415835,0.0000781757,0.0001755714,0.00001052656,4.831257e-7,0.0001062142,0.0001943208,0.9712067,0.0002747243,0.0007903224,0.02715425],"study_design_scores_gemma":[0.0004414172,0.00004750735,0.01265483,0.00008454611,0.00002985922,0.00002018623,0.0009645947,0.4624067,0.5221269,0.0004050375,0.0005441113,0.0002742992],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9165108,0.000002159219,0.07686712,0.00001545119,0.001742725,0.0002731199,0.00002040432,0.0007795863,0.003788602],"genre_scores_gemma":[0.9796563,7.288558e-7,0.01978575,0.000009040758,0.0003163811,0.000044548,0.0001216321,0.00002656089,0.00003899769],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4622124,"threshold_uncertainty_score":0.3563628,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W162282658","doi":"10.17226/14325","title":"Quality Management of Pavement Condition Data Collection","year":2009,"lang":"en","type":"book","venue":"National Academies Press eBooks","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":106,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Data collection; Quality (philosophy); Data quality; Pavement management; Transport engineering; State highway; Business; Process (computing); Data management; Engineering; Operations management; Computer science; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.05751967600385853,"gpt":0.3206697256194109,"spread":0.2631500496155523,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000342961,0.0002326172,0.0002732429,0.0001196474,0.00005819833,0.00001770616,0.0004167363,0.0003857797,0.00001840525],"category_scores_gemma":[0.00001003401,0.0002465971,0.00005638905,0.00001617953,0.00004672024,0.0001013726,0.0001365846,0.00049584,0.00000393593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004483975,"about_ca_system_score_gemma":0.00005767389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004809761,"about_ca_topic_score_gemma":0.000001088944,"domain_scores_codex":[0.9982661,0.00001990388,0.0005124919,0.000267914,0.0007555556,0.000178015],"domain_scores_gemma":[0.9992867,0.00005293072,0.0001875986,0.0002757316,0.0001630528,0.00003404088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002689494,0.00001432224,0.000003488648,0.001935768,0.0008340803,0.000005161243,0.0001953375,0.004978574,0.0005293997,0.3223232,0.642118,0.02703575],"study_design_scores_gemma":[0.0004928447,0.00002254322,0.0004869423,0.0006172514,0.0001049418,0.000003495353,0.00001709451,0.001128975,0.005899311,0.0403755,0.9504271,0.0004239607],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00005247644,0.0005009386,0.001505215,0.00000847309,0.0005149703,0.0004226261,0.0003310633,0.000152226,0.996512],"genre_scores_gemma":[0.01549317,0.0009465523,0.003084999,0.0001185037,0.001475781,0.000113369,0.00276274,0.0000842159,0.9759207],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3083091,"threshold_uncertainty_score":0.9999986,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2019106986","doi":"10.1016/s0008-8846(99)00212-4","title":"A new image analysis technique for the quantitative assessment of microcracks in cement-based materials","year":2000,"lang":"en","type":"article","venue":"Cement and Concrete Research","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":101,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"Electricité de France","keywords":"Thresholding; Sorting; Materials science; Cement; Matrix (chemical analysis); Reproducibility; Process (computing); Cracking; Image processing; Histogram; Porosity; Computer science; Image (mathematics); Composite material; Biological system; Artificial intelligence; Mathematics; Algorithm; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03071416536778678,"gpt":0.3714855685544123,"spread":0.3407714031866256,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009029484,0.00009004446,0.0001906699,0.0002073048,0.0000678178,0.0000494758,0.0001282498,0.00003950719,0.000405675],"category_scores_gemma":[0.00001277704,0.0000664218,0.0000445966,0.000366998,0.00005922135,0.00005112634,0.0000222071,0.0001203664,0.000001006826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006689179,"about_ca_system_score_gemma":0.00005201423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002285307,"about_ca_topic_score_gemma":0.00001791007,"domain_scores_codex":[0.9991145,0.00005355794,0.000217354,0.0001329618,0.0001916355,0.0002899587],"domain_scores_gemma":[0.9995109,0.0001999258,0.0000195202,0.0001542577,0.00008061129,0.0000347746],"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":[0.0000991894,0.000002382915,0.0008199455,0.0001378188,0.0002351063,0.000002459444,0.0002716246,0.001246646,0.9889937,0.0007707681,0.0005462226,0.006874125],"study_design_scores_gemma":[0.001130752,0.000253859,0.004689175,0.0001135413,0.0001080864,3.430117e-7,0.000792072,0.01914674,0.9689552,0.0002666987,0.004362767,0.0001807918],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8224636,0.0005984952,0.172273,0.0002851813,0.00009687733,0.00205693,0.00006679113,0.00003452345,0.002124641],"genre_scores_gemma":[0.9841325,0.0002395329,0.01514424,0.000008687395,0.00004066065,0.0002600778,0.00001647611,0.00001209692,0.0001457717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1616689,"threshold_uncertainty_score":0.4441857,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4367680609","doi":"10.1177/14759217231168212","title":"Deep learning-based concrete defects classification and detection using semantic segmentation","year":2023,"lang":"en","type":"article","venue":"Structural Health Monitoring","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":100,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Convolutional neural network; Segmentation; Deep learning; Pattern recognition (psychology); Histogram of oriented gradients; Contextual image classification; Machine learning; Classifier (UML); Image segmentation; Histogram; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02244567678710882,"gpt":0.2947964006468159,"spread":0.2723507238597072,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001737779,0.0001946188,0.0001851487,0.0002067019,0.0004477673,0.00006531025,0.00005628568,0.00008824977,0.000002026062],"category_scores_gemma":[0.0000279653,0.0002014007,0.00003512839,0.0003833389,0.00002942357,0.0002095627,0.00001800545,0.0002988797,0.000005681998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003649133,"about_ca_system_score_gemma":0.000024525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008165626,"about_ca_topic_score_gemma":0.00000899445,"domain_scores_codex":[0.9987811,0.00005347605,0.000275457,0.000229012,0.0001887048,0.0004722117],"domain_scores_gemma":[0.9995725,0.00005480381,0.00008994516,0.0001146792,0.00004791097,0.0001202251],"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":[0.00002899092,4.284119e-7,0.09719503,0.001035422,0.00003308378,0.000008233775,0.001597167,0.438095,0.321204,0.00002050367,0.000004610342,0.1407775],"study_design_scores_gemma":[0.000319535,0.00005242779,0.2267057,0.000121112,0.00001163326,0.00001100722,0.000831052,0.7327328,0.03890841,0.00006296204,0.00004038639,0.0002030806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894203,0.0003162747,0.006515086,0.00001742358,0.002738928,0.0002478641,0.000001211664,0.000728297,0.00001464405],"genre_scores_gemma":[0.9977795,0.0001088562,0.001364502,0.000008889699,0.0006497875,0.00001895058,0.00001487052,0.00004787524,0.000006742968],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2946377,"threshold_uncertainty_score":0.8212882,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}