{"meta":{"query_hash":"e7d2ed982676","filters":{"venue":"Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018"},"cohort_total":7,"direct_labels_cover":0,"predictions_cover":7,"exported":7,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/e7d2ed982676","api":"https://metacan.xera.ac/api/v1/cohort?venue=Sensors+and+Smart+Structures+Technologies+for+Civil%2C+Mechanical%2C+and+Aerospace+Systems+2018"},"results":[{"id":"W2794552144","doi":"10.1117/12.2295962","title":"Vision-based concrete crack detection technique using cascade features","year":2018,"lang":"en","type":"article","venue":"Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Cascade; Computer science; Structural health monitoring; Artificial intelligence; Face (sociological concept); Delamination (geology); Structural engineering; Bounding overwatch; Sensitivity (control systems); Computer vision; Pattern recognition (psychology); Engineering; Geology","score_opus":0.008387589538341726,"score_gpt":0.23459092837367476,"score_spread":0.22620333883533303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794552144","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081759684,0.00046079868,0.9127832,0.00008004182,0.00009668827,0.00019641175,0.00014885541,0.0015438016,0.00293055],"genre_scores_gemma":[0.5566093,0.0004316311,0.43719572,0.00009026021,0.00008822846,0.00011072345,0.0004730005,0.000097062046,0.0049040923],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936956,0.000034067594,0.00002481954,0.00018087511,0.00030530783,0.000085374595],"domain_scores_gemma":[0.9994616,0.00011251155,0.00005444362,0.0000830501,0.00024925263,0.00003920492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041970232,0.00071085594,0.00087829767,0.001997608,0.00034336562,0.0004624301,0.00092023076,0.0007511102,0.0019931176],"category_scores_gemma":[0.00084769906,0.0003291709,0.0009828162,0.000717896,0.00028836852,0.0009868264,0.00061820797,0.00077596016,0.00081687816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028261333,0.00021625303,0.0032586863,0.0001225869,0.000084682426,0.00023376528,0.000091088004,0.01827577,0.2539111,0.0012082428,0.0025023306,0.71981275],"study_design_scores_gemma":[0.000021325774,0.0004126552,0.009622411,0.00001759847,0.000075127595,0.00084718206,0.00003644697,0.8598404,0.1249021,0.00076436985,0.003415933,0.000044484215],"about_ca_topic_score_codex":0.002946181,"about_ca_topic_score_gemma":0.0039144983,"teacher_disagreement_score":0.002946181,"about_ca_system_score_codex":0.0003493247,"about_ca_system_score_gemma":0.00042992833,"threshold_uncertainty_score":0.0066676736},"labels":[],"label_agreement":null},{"id":"W2794732825","doi":"10.1117/12.2295954","title":"Deep faster R-CNN-based automated detection and localization of multiple types of damage","year":2018,"lang":"en","type":"article","venue":"Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Convolutional neural network; Computer science; Robustness (evolution); Artificial intelligence; Consistency (knowledge bases); Visual inspection; Structural health monitoring; Bridge (graph theory); Computer vision; Pattern recognition (psychology); Engineering; Structural engineering","score_opus":0.0063384259827003455,"score_gpt":0.20752504399611835,"score_spread":0.201186618013418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794732825","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25675628,0.001775678,0.7168593,0.00036320012,0.00026665832,0.00016660705,0.0013323956,0.012965877,0.009513925],"genre_scores_gemma":[0.7776973,0.0005449684,0.20799813,0.00029334874,0.00005513652,0.00009035402,0.0023573,0.00024544518,0.010718004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996356,0.00002526546,0.0000144005635,0.00012795339,0.000111836045,0.000084986386],"domain_scores_gemma":[0.99949014,0.00008659208,0.00009681311,0.00012820175,0.00016845697,0.000029700015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049527694,0.0011221938,0.0006087448,0.0008817973,0.00017372164,0.00046103552,0.0014102021,0.0007071364,0.0025785323],"category_scores_gemma":[0.0010137995,0.00047366394,0.0006533499,0.00047046997,0.00030749818,0.0011411455,0.0007106771,0.00061937334,0.0009691557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048650382,0.00029509794,0.005123404,0.00024269488,0.00023819828,0.00042110324,0.00008468044,0.27751294,0.11972237,0.0022751258,0.010193373,0.58340454],"study_design_scores_gemma":[0.000009322275,0.00007811388,0.0024136128,0.000015172441,0.00003571277,0.00011303996,0.000009995288,0.97699475,0.018414851,0.0006350713,0.001266031,0.000014299044],"about_ca_topic_score_codex":0.011097177,"about_ca_topic_score_gemma":0.01701067,"teacher_disagreement_score":0.011097177,"about_ca_system_score_codex":0.0009154777,"about_ca_system_score_gemma":0.0007492747,"threshold_uncertainty_score":0.022065163},"labels":[],"label_agreement":null},{"id":"W2794782535","doi":"10.1117/12.2295952","title":"Identification of large-scale systems with noisy data using an iterated cubature unscented Kalman filter","year":2018,"lang":"en","type":"article","venue":"Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018","topic":"Structural Health Monitoring Techniques","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Kalman filter; Extended Kalman filter; Robustness (evolution); Invariant extended Kalman filter; Control theory (sociology); Computer science; Fast Kalman filter; Covariance; Unscented transform; Nonlinear system; Linear system; Ensemble Kalman filter; Covariance intersection; System identification; Divergence (linguistics); State vector; Covariance matrix; Noise (video); Algorithm; Mathematics; Artificial intelligence; Data mining; Statistics; Measure (data warehouse)","score_opus":0.025969091914488075,"score_gpt":0.2839933880670992,"score_spread":0.2580242961526111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794782535","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003566928,0.00015230064,0.9957402,0.000025447524,0.00001232193,0.000011158093,0.000013160732,0.00017907807,0.0002993978],"genre_scores_gemma":[0.6124211,0.0010844112,0.3826902,0.00011144068,0.00007583333,0.00028192045,0.00029324106,0.00009235163,0.0029495377],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993901,0.00015516956,0.00005811483,0.00016401745,0.00019001531,0.00004254432],"domain_scores_gemma":[0.999161,0.00040367997,0.00014364306,0.00008698337,0.00018845887,0.0000162699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009581485,0.00082954456,0.0010821316,0.0005262561,0.00037853542,0.0007333834,0.00087164517,0.0008431074,0.0008011563],"category_scores_gemma":[0.0028020726,0.00047767392,0.00096401514,0.0005864422,0.0004784081,0.00096781965,0.00078515994,0.001065964,0.00032517625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011295772,0.000042861484,0.0014917771,0.00028824192,0.0001795705,0.00016180692,0.0002543314,0.8209304,0.0124557335,0.009897642,0.00079679483,0.15338778],"study_design_scores_gemma":[0.0000029623468,0.000015939939,0.00019361662,0.0000074637496,0.000008693646,0.000020070227,0.0000065234094,0.9973787,0.0011165978,0.00084427366,0.00039883764,0.0000063712378],"about_ca_topic_score_codex":0.007360827,"about_ca_topic_score_gemma":0.004768852,"teacher_disagreement_score":0.007360827,"about_ca_system_score_codex":0.00048589607,"about_ca_system_score_gemma":0.00088593445,"threshold_uncertainty_score":0.0146359205},"labels":[],"label_agreement":null},{"id":"W2795198781","doi":"10.1117/12.2295961","title":"Damage detection with an autonomous UAV using deep learning","year":2018,"lang":"en","type":"article","venue":"Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Beacon; Global Positioning System; Computer science; Real-time computing; Drone; GPS signals; Convolutional neural network; Deep learning; Bridge (graph theory); Structural health monitoring; Artificial intelligence; Visual inspection; Assisted GPS; Engineering; Telecommunications","score_opus":0.008482150627451607,"score_gpt":0.2151657905703628,"score_spread":0.2066836399429112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795198781","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36442307,0.00077616,0.62685084,0.00044335664,0.00012690733,0.000077335484,0.00024848455,0.0035416814,0.0035120996],"genre_scores_gemma":[0.9249366,0.00011020416,0.072904654,0.00008498336,0.000016968053,0.000026684163,0.00017133025,0.00002110607,0.0017274601],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998908,0.000009821433,0.0000041896146,0.000038621783,0.000032558426,0.00002398868],"domain_scores_gemma":[0.999841,0.00004136018,0.00003320165,0.000025312791,0.000044275264,0.000014896198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015862034,0.0005703633,0.0003042705,0.0004069849,0.00018056903,0.00027356957,0.00054530235,0.00064038107,0.00057586754],"category_scores_gemma":[0.00045008317,0.000251436,0.00026939568,0.00024384355,0.00025846905,0.00050616264,0.0004079422,0.0005093613,0.00017373967],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028616036,0.00022680033,0.0083468845,0.00008925493,0.00010878553,0.00042590933,0.00009707973,0.54992574,0.074368194,0.0014409777,0.003165962,0.3615183],"study_design_scores_gemma":[0.0000033130916,0.000040370185,0.0009391351,0.00000333157,0.000005113049,0.000029340821,0.0000069129696,0.9939031,0.004418454,0.00038937334,0.0002582373,0.0000032996559],"about_ca_topic_score_codex":0.006751241,"about_ca_topic_score_gemma":0.009020684,"teacher_disagreement_score":0.006751241,"about_ca_system_score_codex":0.0005257387,"about_ca_system_score_gemma":0.00035614602,"threshold_uncertainty_score":0.01342386},"labels":[],"label_agreement":null},{"id":"W2795205653","doi":"10.1117/12.2295947","title":"Automated air-coupled impact echo based non-destructive testing using machine learning","year":2018,"lang":"en","type":"article","venue":"Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Automation; Computer science; Echo (communications protocol); Ground-penetrating radar; Artificial neural network; Non-regression testing; Integration testing; Nondestructive testing; Radar; Repeatability; Test strategy; Software performance testing; Reliability engineering; Artificial intelligence; Engineering; Software; Mechanical engineering","score_opus":0.017980140644589276,"score_gpt":0.26881789865489475,"score_spread":0.2508377580103055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795205653","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101440124,0.000119714496,0.89480853,0.000050657105,0.000019887522,0.00008519532,0.000057545785,0.0016931514,0.0017252424],"genre_scores_gemma":[0.76507556,0.00008606068,0.2322634,0.00006365659,0.00001795275,0.00014040657,0.00015156716,0.000053524273,0.0021478946],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99964356,0.00006775663,0.000018245806,0.00008933995,0.00015075419,0.000030300615],"domain_scores_gemma":[0.9991954,0.00036914507,0.00011841736,0.00011531593,0.00017715458,0.00002460431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037218627,0.00049194036,0.00037530065,0.00045557358,0.00017056773,0.00043992026,0.00067059905,0.00041246478,0.0013357506],"category_scores_gemma":[0.0009932129,0.00019225646,0.00022625741,0.00034048484,0.0003069297,0.0006006474,0.00046877758,0.00035669867,0.00046730155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027091085,0.00038758808,0.0045480425,0.00016294872,0.00006283803,0.00012692227,0.000120896824,0.13495032,0.1261159,0.0011756866,0.0009702972,0.7311076],"study_design_scores_gemma":[0.0000077281,0.00012984705,0.0030932263,0.0000060529346,0.00000807813,0.0000640209,0.000016320637,0.9741062,0.021413404,0.00068942545,0.00045378637,0.00001188073],"about_ca_topic_score_codex":0.00096925366,"about_ca_topic_score_gemma":0.0018387929,"teacher_disagreement_score":0.0013357506,"about_ca_system_score_codex":0.00023654841,"about_ca_system_score_gemma":0.00034357028,"threshold_uncertainty_score":0.0044685006},"labels":[],"label_agreement":null},{"id":"W2795331216","doi":"10.1117/12.2295966","title":"Automated damage-sensitive feature extraction using unsupervised convolutional neural networks","year":2018,"lang":"en","type":"article","venue":"Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Pattern recognition (psychology); Feature extraction; Support vector machine; Novelty detection; Feature (linguistics); Unsupervised learning; Test data; Feature learning; Machine learning; Deep learning; Novelty","score_opus":0.010827495920053923,"score_gpt":0.2374454245919931,"score_spread":0.2266179286719392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795331216","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20771216,0.0004833782,0.78619915,0.00014302469,0.00006585309,0.00010146043,0.000634944,0.0026604075,0.0019995917],"genre_scores_gemma":[0.82819825,0.00034415672,0.16561265,0.00010259821,0.000049368347,0.00011842354,0.0022144704,0.00008312239,0.0032769742],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99962723,0.000030648458,0.000021534413,0.00011815228,0.00012681766,0.000075535434],"domain_scores_gemma":[0.99957687,0.00008230853,0.00011419683,0.00008406914,0.00012362491,0.000019040503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003474982,0.0010369004,0.0006093807,0.0012445042,0.00020006552,0.00037969355,0.00073022774,0.0005500564,0.0005870786],"category_scores_gemma":[0.00094960607,0.00034192964,0.0007375227,0.00081196224,0.0003473637,0.0008430628,0.00076109223,0.0006092951,0.00031268972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026126922,0.00033222884,0.011170011,0.00019907216,0.00016453218,0.0004111926,0.00012814195,0.1326842,0.15584895,0.0016202423,0.0044230204,0.692757],"study_design_scores_gemma":[0.000010502221,0.000101183534,0.013341945,0.00001626324,0.000034025896,0.00018096568,0.00003457709,0.9406203,0.042170167,0.001818186,0.0016480499,0.000023829914],"about_ca_topic_score_codex":0.0031332478,"about_ca_topic_score_gemma":0.0055741207,"teacher_disagreement_score":0.0031332478,"about_ca_system_score_codex":0.000458444,"about_ca_system_score_gemma":0.00048270385,"threshold_uncertainty_score":0.0062299967},"labels":[],"label_agreement":null},{"id":"W2796305543","doi":"10.1117/12.2295959","title":"Automated volumetric damage detection and quantification using region-based convolution neural networks and an inexpensive depth camera","year":2018,"lang":"en","type":"article","venue":"Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Pixel; Volume (thermodynamics); Computer vision; Fuse (electrical); Spall; Segmentation; Materials science; Engineering","score_opus":0.016992390356681958,"score_gpt":0.2465565993788125,"score_spread":0.22956420902213054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796305543","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16678423,0.0005308635,0.8269232,0.000070800794,0.000043183798,0.00009083168,0.00049399,0.0028422582,0.0022206402],"genre_scores_gemma":[0.66420263,0.00041138017,0.3315316,0.00007517376,0.000023462917,0.00010312851,0.0007618944,0.00009990021,0.0027909086],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996295,0.00003323803,0.000014669117,0.00010320929,0.00017384799,0.00004551704],"domain_scores_gemma":[0.9996253,0.00006598479,0.000096951604,0.000081920174,0.00011269794,0.000017014083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034205074,0.0006997305,0.00039936515,0.0009713063,0.00011843169,0.00041215896,0.0007806044,0.0005333031,0.0012331082],"category_scores_gemma":[0.0007600558,0.00034061488,0.0003680377,0.0004606812,0.00021915163,0.00075601594,0.0006629735,0.00033265247,0.00044249676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035568443,0.0001545134,0.0074870377,0.00024150664,0.00010972022,0.00019295655,0.000100893616,0.09482454,0.3898131,0.0014286794,0.0018076915,0.5034836],"study_design_scores_gemma":[0.000011584517,0.00020723284,0.013345663,0.000028566821,0.00005128379,0.00039495612,0.00003911483,0.84861124,0.13387285,0.000886964,0.002516513,0.00003400978],"about_ca_topic_score_codex":0.0029690969,"about_ca_topic_score_gemma":0.005712287,"teacher_disagreement_score":0.0029690969,"about_ca_system_score_codex":0.0005291326,"about_ca_system_score_gemma":0.00041339904,"threshold_uncertainty_score":0.0059036016},"labels":[],"label_agreement":null}]}