{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":284,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":284,"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":"90c5cf1a2766","filters":{"topic":"Fire Detection and Safety Systems"}},"results":[{"id":"W1852719163","doi":"10.1139/cjfr-2014-0347","title":"A survey on technologies for automatic forest fire monitoring, detection, and fighting using unmanned aerial vehicles and remote sensing techniques","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Forest Research","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":622,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"Concordia University","funders":"U.S. Forest Service; National Aeronautics and Space Administration","keywords":"Firefighting; Fire detection; Wildfire suppression; Aerial survey; Remote sensing; Fire control; Field (mathematics); Systems engineering; Aeronautics; Computer science; Environmental science; Engineering; Architectural engineering; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.07671189151839218,"gpt":0.3136299731529901,"spread":0.2369180816345979,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002007887,0.0001266306,0.0002245505,0.0006513054,0.0003220283,0.0001882876,0.0001170599,0.000168561,4.18065e-7],"category_scores_gemma":[0.001565191,0.0001183081,0.00003365858,0.0003228843,0.000138177,0.0001402158,0.00001695763,0.0004051702,6.068654e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003732245,"about_ca_system_score_gemma":0.0002633675,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01183831,"about_ca_topic_score_gemma":0.08671589,"domain_scores_codex":[0.9987991,0.0001149188,0.0003230444,0.0001234046,0.0002325164,0.0004069578],"domain_scores_gemma":[0.9987218,0.000264461,0.00007101505,0.0001338446,0.0004735391,0.0003353292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001956427,0.000007320857,0.0699104,0.0005144248,0.0001528413,0.0002189565,0.001621255,0.003338328,0.004594143,0.00002967658,0.001487113,0.9179299],"study_design_scores_gemma":[0.001608883,0.001609994,0.1429058,0.00233144,0.0000283125,0.001105369,0.003038049,0.8136019,0.02443457,0.002595338,0.006133629,0.0006066897],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962536,0.0007529915,0.002068025,0.00009290766,0.0004212765,0.0002709573,0.00001040055,0.00009247258,0.00003738897],"genre_scores_gemma":[0.9971188,0.0000349779,0.002556768,0.000001912593,0.0002376815,0.000001295356,8.090739e-7,0.00003330465,0.00001441029],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9173232,"threshold_uncertainty_score":0.9947419,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2508764147","doi":"10.3390/s16081310","title":"Airborne Optical and Thermal Remote Sensing for Wildfire Detection and Monitoring","year":2016,"lang":"en","type":"review","venue":"Sensors","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":298,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; Canadian Forest Service; York University","funders":"Ontario Centres of Excellence","keywords":"Drone; Remote sensing; Fire detection; Hyperspectral imaging; Context (archaeology); Computer science; Systems engineering; Environmental science; Environmental monitoring; Engineering; Architectural engineering; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.02214395972269058,"gpt":0.2603073152471543,"spread":0.2381633555244637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001499291,0.0002878484,0.0006524755,0.0001089642,0.00009325934,0.00004306818,0.00003314955,0.0003152517,7.808446e-7],"category_scores_gemma":[0.00004319973,0.000226158,0.0001289969,0.00007512966,0.00003412696,0.00004145866,0.00001628217,0.0001956211,0.00001093774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007786207,"about_ca_system_score_gemma":0.000008063184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008332871,"about_ca_topic_score_gemma":0.000003171291,"domain_scores_codex":[0.9990723,0.00004106975,0.0003095607,0.0002552528,0.00008421243,0.0002375648],"domain_scores_gemma":[0.9994955,0.0001781765,0.00005363012,0.0001621182,0.00001554153,0.00009504188],"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":[0.00000327251,4.175562e-7,1.43481e-7,0.003110743,0.00005759554,0.000004013235,0.00003008331,0.000009751153,0.00007983624,0.000001591486,0.000002905784,0.9966996],"study_design_scores_gemma":[0.0002347511,0.00003839794,0.00002366899,0.008434376,0.0001682833,0.0003610932,0.00002578762,0.01721515,0.0001981696,0.00000813331,0.9728426,0.0004496157],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.004040464,0.9910784,0.00224942,0.0000104447,0.00147025,0.000543932,0.000009981952,0.0003308733,0.0002662821],"genre_scores_gemma":[0.007052655,0.9911785,0.0006204924,0.000001373411,0.0008724665,0.000003026444,0.000001566041,0.0001049944,0.0001649929],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.99625,"threshold_uncertainty_score":0.9222454,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2978858971","doi":"10.1109/iciai.2019.8850815","title":"A Deep Learning Based Forest Fire Detection Approach Using UAV and YOLOv3","year":2019,"lang":"en","type":"article","venue":"","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":238,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Fire detection; Artificial intelligence; Convolutional neural network; Deep learning; Frame rate; RGB color model; Frame (networking); Convolution (computer science); Artificial neural network; Remote sensing; Computer vision; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.007592004548448513,"gpt":0.1746911730090977,"spread":0.1670991684606492,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001216507,0.00009876088,0.0001137847,0.0000605887,0.00006453769,0.00003444899,0.00002999636,0.00008607389,0.00004947677],"category_scores_gemma":[0.00001092485,0.00009447658,0.00003359327,0.0001254286,0.000008111202,0.00009084329,0.000008490258,0.0001415297,0.00004240751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000440618,"about_ca_system_score_gemma":0.000003244428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001035209,"about_ca_topic_score_gemma":0.00005604005,"domain_scores_codex":[0.999497,0.00002855718,0.0001209413,0.0001322135,0.00007901292,0.0001422933],"domain_scores_gemma":[0.999802,0.00002675713,0.00001680932,0.00009586223,0.00001429941,0.00004428773],"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":[0.00001122448,0.000006534796,0.007841115,0.0001944097,0.00001893352,8.188518e-7,0.0001729828,0.9589143,0.01203938,0.00001490437,0.000006178696,0.0207792],"study_design_scores_gemma":[0.0002607022,0.00002761811,0.003323495,0.00001175057,0.000005024944,0.00002288758,0.0002130832,0.9934198,0.001047693,0.000002262481,0.001540867,0.0001247688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6592406,0.00008985918,0.3340624,0.000003471355,0.0002575686,0.000147838,1.67278e-7,0.0003783242,0.005819709],"genre_scores_gemma":[0.9985133,0.00000364391,0.001047047,0.00001330731,0.00004378888,0.000006574335,0.00000206911,0.00002564226,0.0003445721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3392727,"threshold_uncertainty_score":0.3852643,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2569436968","doi":"10.1007/s10846-016-0464-7","title":"Aerial Images-Based Forest Fire Detection for Firefighting Using Optical Remote Sensing Techniques and Unmanned Aerial Vehicles","year":2017,"lang":"en","type":"article","venue":"Journal of Intelligent & Robotic Systems","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":211,"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; National Natural Science Foundation of China; Ağrı İbrahim Çeçen Üniversitesi","keywords":"Optical flow; Firefighting; Fire detection; Artificial intelligence; Computer vision; Computer science; Pixel; Feature (linguistics); Remote sensing; Engineering; Geography; Image (mathematics); Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.02903432783559267,"gpt":0.269197493163856,"spread":0.2401631653282633,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008992893,0.0002664715,0.0006131787,0.000180735,0.0004624085,0.0004740417,0.0001976748,0.0002242933,0.000001541068],"category_scores_gemma":[0.0003161646,0.0002380876,0.0002279915,0.00006341527,0.0000746644,0.0002757232,0.00002881516,0.0002557701,0.000001989846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002710769,"about_ca_system_score_gemma":0.00004409981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002433564,"about_ca_topic_score_gemma":0.00003939259,"domain_scores_codex":[0.9980916,0.00007504226,0.001028546,0.000185371,0.0002915534,0.0003278624],"domain_scores_gemma":[0.9984435,0.0001869559,0.0006220368,0.0002955741,0.0002943716,0.0001575513],"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":[0.00105786,0.00004293208,0.0002030588,0.001855686,0.000429988,0.0002160388,0.0003505965,0.4832391,0.215897,0.000041479,0.0002324245,0.2964338],"study_design_scores_gemma":[0.0006287965,0.0002693172,0.00008324519,0.001262206,0.0000859483,0.001185944,0.0001475595,0.8869853,0.1078178,0.00002887424,0.001256488,0.0002484535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3257607,0.000546509,0.666068,0.00006296942,0.006800501,0.0005313534,0.000003959154,0.0001276553,0.00009839334],"genre_scores_gemma":[0.9863969,0.00004895785,0.0105671,0.000005548981,0.002887395,0.00000164117,0.000001116848,0.0000647839,0.00002653243],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6606362,"threshold_uncertainty_score":0.970893,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2733381601","doi":"10.1016/j.firesaf.2017.06.012","title":"Computer vision for wildfire research: An evolving image dataset for processing and analysis","year":2017,"lang":"en","type":"article","venue":"Fire Safety Journal","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":188,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Frame (networking); Computer science; Ground truth; Field (mathematics); Image processing; Artificial intelligence; Computer vision; Pixel; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.04839038859194959,"gpt":0.3559245179726619,"spread":0.3075341293807123,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001775007,0.0001483071,0.0002851853,0.000202845,0.002447868,0.001103817,0.000329527,0.00009986555,0.00001643189],"category_scores_gemma":[0.000139062,0.0001334131,0.0001235134,0.0001275358,0.00007790844,0.001409896,0.00005850978,0.000309563,0.000003226724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009109497,"about_ca_system_score_gemma":0.00003247943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001771765,"about_ca_topic_score_gemma":0.00005712882,"domain_scores_codex":[0.9987084,0.0000613615,0.0003687849,0.0002334789,0.0002534079,0.0003745477],"domain_scores_gemma":[0.9989434,0.0001161097,0.0001293714,0.0003953898,0.0002061846,0.0002095262],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004812088,0.0000704512,0.001364011,0.000653688,0.0006882173,0.0000339799,0.001454121,0.002952641,0.003237695,0.00002199702,0.08627925,0.9027627],"study_design_scores_gemma":[0.0007459192,0.0001811118,0.02662894,0.0001250615,0.0000843642,0.00009568786,0.0001044209,0.9075952,0.00004125211,0.00008998714,0.06413186,0.0001761703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06920315,0.001356649,0.9211299,0.001851982,0.001597476,0.001198605,0.003106322,0.0002122837,0.0003436416],"genre_scores_gemma":[0.9776513,0.000101704,0.02057979,0.00002593244,0.00104608,0.0000199157,0.0004691631,0.00004574058,0.00006037408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9084482,"threshold_uncertainty_score":0.9999331,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3130567206","doi":"10.3390/drones5010015","title":"Unmanned Aerial Vehicles for Wildland Fires: Sensing, Perception, Cooperation and Assistance","year":2021,"lang":"en","type":"article","venue":"Drones","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":171,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Firefighting; Fire detection; Task (project management); Cover (algebra); Scale (ratio); Aerial survey","retraction":null,"screen_n_in":null,"score":{"opus":0.008225007616847607,"gpt":0.2053960471278135,"spread":0.1971710395109659,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005318132,0.00006891695,0.00009650309,0.00001773573,0.00009679879,0.00005469634,0.00001488833,0.00005305036,0.00001554872],"category_scores_gemma":[0.00002426908,0.00007162061,0.00002169004,0.00005260813,0.00001412064,0.00007055156,0.000004433507,0.00003102589,0.000008235875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002152803,"about_ca_system_score_gemma":0.000008591593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009953065,"about_ca_topic_score_gemma":0.0002183669,"domain_scores_codex":[0.999624,0.00001630095,0.0001156125,0.0001080262,0.00004730045,0.00008875804],"domain_scores_gemma":[0.9998053,0.0000254611,0.00001128196,0.0000763489,0.00005369233,0.00002792776],"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":[0.0002568195,0.00006050883,0.00291812,0.001157786,0.0002236366,0.00003070216,0.006663168,0.01795824,0.8080389,0.001264932,0.05488287,0.1065443],"study_design_scores_gemma":[0.002193009,0.00009011768,0.03217689,0.0001573969,0.00003971776,0.0001234855,0.001342657,0.5677739,0.01498966,0.0001796495,0.3803582,0.0005753367],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.982342,0.0003634999,0.01551832,0.0002844891,0.0008959586,0.0001211375,0.00001808746,0.0001732571,0.0002832556],"genre_scores_gemma":[0.9982713,0.0000774542,0.000629889,0.00003733541,0.000281301,0.000007410117,0.000032099,0.00001515875,0.0006480656],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7930493,"threshold_uncertainty_score":0.2920603,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4214895504","doi":"10.3390/s22051977","title":"Deep Learning and Transformer Approaches for UAV-Based Wildfire Detection and Segmentation","year":2022,"lang":"en","type":"article","venue":"Sensors","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":161,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada; Western Canada Research Grid; Compute Canada","keywords":"Deep learning; Computer science; Artificial intelligence; Segmentation; Machine learning; Transformer; Random forest; Architecture; Engineering; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.01273605018138506,"gpt":0.1944636379400951,"spread":0.18172758775871,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001060524,0.00006957186,0.00007407041,0.00006111968,0.000225396,0.00001587446,0.00001189459,0.00002708056,0.000007967664],"category_scores_gemma":[0.000004988742,0.00007731914,0.00002373602,0.00007206979,0.00001124183,0.00003512877,0.000001995712,0.00009569792,6.345027e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003815757,"about_ca_system_score_gemma":0.0000019092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001193048,"about_ca_topic_score_gemma":0.00003126374,"domain_scores_codex":[0.9996129,0.0000313898,0.00009273713,0.0001021045,0.00006744454,0.00009341062],"domain_scores_gemma":[0.999893,0.00003281914,0.00001419896,0.00002853732,0.00000373219,0.00002777973],"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":[0.00009558685,0.00001050893,0.0009188146,0.0002399877,0.00004604413,0.00000110647,0.003155354,0.5734235,0.02619256,0.00001592068,0.00001011514,0.3958905],"study_design_scores_gemma":[0.0005159538,0.00009780601,0.001120881,0.000003040803,0.00001230141,0.00001695435,0.002596128,0.9797962,0.00645936,0.000008858947,0.009265161,0.0001074003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9677729,0.0002246035,0.03098268,0.00004581609,0.0001930894,0.0003030054,0.000003277744,0.0001838572,0.0002907779],"genre_scores_gemma":[0.9995117,0.00001320504,0.0002104268,0.00001071144,0.00002620179,0.00009115334,0.000009090169,0.00002007082,0.0001074135],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4063727,"threshold_uncertainty_score":0.3152983,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3186499362","doi":"10.18280/ts.380324","title":"Forest Fire Recognition Based on Feature Extraction from Multi-View Images","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":147,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Preprocessor; Pattern recognition (psychology); Feature (linguistics); Feature extraction; Hue; Segmentation; Similarity (geometry); Computer vision; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01955420345335343,"gpt":0.2237653851795965,"spread":0.204211181726243,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008904222,0.0001621502,0.0001514203,0.00004444064,0.00007615615,0.00005583189,0.00004844723,0.0001027956,0.001209409],"category_scores_gemma":[0.00001241826,0.0001651946,0.0001005285,0.0001306435,0.000008883694,0.00012162,0.000004436726,0.0001907025,0.0002041156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008205503,"about_ca_system_score_gemma":0.0000140918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004139636,"about_ca_topic_score_gemma":0.0001355656,"domain_scores_codex":[0.999178,0.00005922785,0.0001987672,0.0002068706,0.0001988067,0.0001583449],"domain_scores_gemma":[0.999644,0.00006699918,0.00003437857,0.0001341503,0.00005461102,0.00006586582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002187059,0.0006826165,0.002102191,0.0005828428,0.0002853705,0.0003068493,0.0005553561,0.09329778,0.2238092,0.00001363283,0.03457878,0.6435667],"study_design_scores_gemma":[0.00199747,0.0001189328,0.04999372,0.0004656846,0.00006470615,0.00001888335,0.0002121587,0.8256966,0.06897251,0.00003268604,0.05191815,0.0005084601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7961134,0.002266921,0.1845751,0.001990892,0.004553826,0.001239189,0.0009305353,0.002138576,0.006191547],"genre_scores_gemma":[0.9970862,0.00005527516,0.001589602,0.0002172389,0.0003009933,0.00005354119,0.0004621033,0.00003169615,0.0002033974],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7323989,"threshold_uncertainty_score":0.9997036,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2035290160","doi":"10.1080/152873901300343470","title":"CHARACTERIZATION OF VOLATILE ORGANIC COMPOUNDS IN SMOKE AT MUNICIPAL STRUCTURAL FIRES","year":2001,"lang":"en","type":"article","venue":"Journal of Toxicology and Environmental Health","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Propene; Ethylbenzene; Toluene; Benzene; Styrene; Environmental chemistry; Chemistry; Naphthalene; Volatile organic compound; Gas chromatography; Organic chemistry; Chromatography; Catalysis","retraction":null,"screen_n_in":null,"score":{"opus":0.01061372069930539,"gpt":0.2253964423139137,"spread":0.2147827216146083,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000137305,0.00006396846,0.0002073746,0.0000766683,0.00004437446,0.000002293365,0.00004234827,0.00006818061,0.0001579895],"category_scores_gemma":[0.00000225063,0.00006068899,0.00002454932,0.00004325443,0.00003901054,0.00007796576,0.00001589064,0.0001336574,0.000001358007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002194774,"about_ca_system_score_gemma":0.000007564046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000200436,"about_ca_topic_score_gemma":0.0001854659,"domain_scores_codex":[0.9993331,0.0000527359,0.000385035,0.00004605029,0.0000689024,0.0001141892],"domain_scores_gemma":[0.9997309,0.00002008753,0.0001393272,0.00004710381,0.000001777357,0.00006075205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002348117,0.0000702959,0.3987157,0.0001110125,0.00004259092,0.00002346893,0.00299782,0.001176264,0.5900621,0.000006961783,0.00005770798,0.006501242],"study_design_scores_gemma":[0.0006326058,0.0003585371,0.9840649,0.00002654011,0.000003471251,0.0005378295,0.0001945452,0.01045775,0.00238575,0.00001139735,0.001267025,0.00005963813],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9990853,0.0003287229,0.00002417963,0.0001274252,0.0003265686,0.00005690746,0.000008186375,0.000005264721,0.00003745137],"genre_scores_gemma":[0.9989201,0.0008942912,0.00001831197,0.00006952852,0.00004180062,5.666216e-7,0.000008397232,0.000007492774,0.0000395145],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5876763,"threshold_uncertainty_score":0.2474825,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3038510778","doi":"10.1139/juvs-2020-0009","title":"Forest fire flame and smoke detection from UAV-captured images using fire-specific color features and multi-color space local binary pattern","year":2020,"lang":"en","type":"article","venue":"Journal of Unmanned Vehicle Systems","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":106,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fire detection; Smoke; Computer science; Artificial intelligence; Remote sensing; Range (aeronautics); Environmental science; Computer vision; Pattern recognition (psychology); Geography; Meteorology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02027515789426762,"gpt":0.2123984909515592,"spread":0.1921233330572915,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002397477,0.0003007523,0.0005798572,0.0001051305,0.0001687432,0.0001931641,0.0001356889,0.0002626162,0.000005420543],"category_scores_gemma":[0.0000343076,0.0002684129,0.0001210268,0.0002092787,0.00007206766,0.0003559884,0.00004379633,0.000493724,0.000006167785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001423648,"about_ca_system_score_gemma":0.00001746676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005260337,"about_ca_topic_score_gemma":0.0001015546,"domain_scores_codex":[0.9983308,0.0001480839,0.0006702528,0.0002609752,0.0003065373,0.0002833597],"domain_scores_gemma":[0.9990059,0.0001142384,0.0003061633,0.0001487142,0.0001291939,0.0002958159],"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":[0.001192299,0.000118922,0.01246578,0.001477471,0.0008049416,0.0008811718,0.006030064,0.2316282,0.7133407,0.000005320141,0.00415941,0.02789576],"study_design_scores_gemma":[0.001784688,0.0004178199,0.03435545,0.0003783118,0.00005879746,0.0005613534,0.002306364,0.9504549,0.007283933,0.000002335681,0.002072499,0.0003235347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9694808,0.01157484,0.01658119,0.0003606162,0.001505481,0.0003356271,0.00004285105,0.0001087179,0.000009882683],"genre_scores_gemma":[0.9985042,0.0003331198,0.0001683723,0.00004686464,0.0008456449,0.000006512078,0.000003031643,0.00006431874,0.00002790079],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7188267,"threshold_uncertainty_score":0.9999768,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2906161342","doi":"10.1109/tcsvt.2018.2889193","title":"3D Parallel Fully Convolutional Networks for Real-Time Video Wildfire Smoke Detection","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":98,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"Key Laboratory of System Control and Information Processing; Fundamental Research Fund of Shandong University; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Smoke; Computer science; Convolutional neural network; Fire detection; Artificial intelligence; Segmentation; Image segmentation; Object detection; Convolution (computer science); Deep learning; Computer vision; Pattern recognition (psychology); Remote sensing; Artificial neural network; Geography; Meteorology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01417253048745199,"gpt":0.2214863867249879,"spread":0.207313856237536,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003402634,0.0003314098,0.0004917155,0.000502686,0.0006164106,0.00006456261,0.0001667662,0.0006299044,0.00001300894],"category_scores_gemma":[0.00001522629,0.0003445384,0.0001686932,0.0004120971,0.0002016805,0.0001515515,0.000001423853,0.0002655262,0.00003126137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001887252,"about_ca_system_score_gemma":0.00002983212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00013741,"about_ca_topic_score_gemma":0.0001870614,"domain_scores_codex":[0.9981766,0.00003826934,0.0006114073,0.0004833226,0.0001560194,0.0005343496],"domain_scores_gemma":[0.9990166,0.0001965602,0.0001102919,0.0003783184,0.0001810743,0.0001171202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001034594,0.0004276664,0.0001717947,0.002092155,0.002527956,0.00001527112,0.0007630785,0.2483544,0.1862214,0.005238914,0.007950323,0.5452024],"study_design_scores_gemma":[0.002246043,0.001278383,0.0001147344,0.0001676399,0.0001217149,0.0003401895,0.0001981739,0.9340361,0.007789217,0.0002772295,0.05277709,0.0006535005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03472289,0.0004421434,0.9571398,0.00009899134,0.003999178,0.001621149,0.0001542448,0.001541177,0.0002804382],"genre_scores_gemma":[0.9971526,0.0001564088,0.0001700251,0.00003261398,0.0004159428,0.001492884,0.00001033164,0.00008756253,0.0004816708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9624296,"threshold_uncertainty_score":0.9999006,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2794499044","doi":"10.1007/s10846-018-0803-y","title":"Learning-Based Smoke Detection for Unmanned Aerial Vehicles Applied to Forest Fire Surveillance","year":2018,"lang":"en","type":"article","venue":"Journal of Intelligent & Robotic Systems","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":97,"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; National Natural Science Foundation of China","keywords":"Fire detection; Smoke; Computer science; Hue; Artificial intelligence; Fuzzy logic; RGB color model; Remote sensing; Segmentation; Environmental science; Computer vision; Engineering; Geography; Meteorology","retraction":null,"screen_n_in":null,"score":{"opus":0.01654922962386471,"gpt":0.23379533411017,"spread":0.2172461044863052,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008811381,0.0002354746,0.0005246605,0.0002394551,0.0001518483,0.0001115338,0.0002216891,0.0001578804,0.00001242752],"category_scores_gemma":[0.0001791013,0.0002107147,0.0002095728,0.0002967285,0.00003223505,0.0000692498,0.00001185283,0.0002150506,0.00007316079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002770936,"about_ca_system_score_gemma":0.00003932879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006771187,"about_ca_topic_score_gemma":0.0001570276,"domain_scores_codex":[0.9980808,0.00008443466,0.0009852975,0.0001726114,0.0003422029,0.0003346403],"domain_scores_gemma":[0.9986538,0.000209003,0.0003128017,0.0001906913,0.0004388601,0.0001948571],"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":[0.0003583588,0.00002393795,0.0006979878,0.0002288227,0.0001112463,0.000003065051,0.0002874219,0.9868133,0.005571632,0.00002117313,0.0008350064,0.005048046],"study_design_scores_gemma":[0.001074852,0.00199445,0.002653046,0.0004116613,0.00004162437,0.0001374567,0.0008809034,0.934203,0.02510298,0.00001504756,0.03303423,0.0004507897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3437949,0.0002631961,0.6433966,0.00006793912,0.01135232,0.0007450972,0.000003737214,0.0001733458,0.0002029034],"genre_scores_gemma":[0.9969112,0.00001278099,0.0002011897,0.00002757754,0.00260699,0.00004288515,0.000002606791,0.00006395304,0.0001308116],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6531163,"threshold_uncertainty_score":0.8592695,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W754511852","doi":"10.1007/s11760-015-0789-x","title":"Automatic fire pixel detection using image processing: a comparative analysis of rule-based and machine learning-based methods","year":2015,"lang":"en","type":"article","venue":"Signal Image and Video Processing","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":92,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Pixel; Fire detection; Computer science; Benchmark (surveying); Artificial intelligence; Context (archaeology); Image processing; Image (mathematics); Computer vision; Pattern recognition (psychology); Engineering; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.04341498095650066,"gpt":0.320289042287953,"spread":0.2768740613314523,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008855839,0.0002766271,0.0006204685,0.0004542473,0.0002336615,0.0002213404,0.00007090106,0.0001062459,0.00001684207],"category_scores_gemma":[0.00009115921,0.0002590843,0.00009364549,0.00113258,0.0001542512,0.0004904514,0.00002520822,0.000260033,0.000001089059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007773525,"about_ca_system_score_gemma":0.00009677281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009589786,"about_ca_topic_score_gemma":0.00002719646,"domain_scores_codex":[0.9984609,0.0002657286,0.0004926553,0.0002984436,0.0002384336,0.0002438731],"domain_scores_gemma":[0.9990962,0.0001299692,0.0002299741,0.0001079256,0.0002723643,0.0001636091],"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":[0.0001409025,0.00007418676,0.0009628675,0.002462195,0.0003290114,0.00001006182,0.003690637,0.08721226,0.544744,5.305885e-7,0.000006084462,0.3603673],"study_design_scores_gemma":[0.0006653392,0.00008457914,0.0004606617,0.0002143521,0.0004977114,0.00001164742,0.0005742927,0.905794,0.09136119,0.00001916259,0.00006020127,0.000256883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3359133,0.001968832,0.6615325,0.00001496552,0.00003254636,0.000141471,0.000006107349,0.000246724,0.0001435374],"genre_scores_gemma":[0.9596985,0.000003083391,0.04017442,0.0000244795,0.00002893567,0.00001601512,0.00001283593,0.00003059809,0.00001113688],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8185817,"threshold_uncertainty_score":0.9999861,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3198090248","doi":"10.3390/rs13173527","title":"Wildfire Segmentation Using Deep Vision Transformers","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Transformer; Artificial intelligence; Architecture; Image segmentation; Pixel; Computer vision; Locality; Pattern recognition (psychology); Geography; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01037577293287493,"gpt":0.2327936083841358,"spread":0.2224178354512608,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007078786,0.0001001095,0.0001165328,0.00005406711,0.00009594129,0.00003981241,0.00001619036,0.00006943401,0.000009785411],"category_scores_gemma":[0.000007528031,0.0001138062,0.00006377453,0.0002226053,0.000009413028,0.000114566,0.000003994116,0.00009567399,0.00002124009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001304819,"about_ca_system_score_gemma":0.00001295547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003605883,"about_ca_topic_score_gemma":0.00005210685,"domain_scores_codex":[0.9993669,0.00003191227,0.0001811199,0.000125507,0.0001327965,0.0001617661],"domain_scores_gemma":[0.9997983,0.00001562879,0.00001662212,0.00009532936,0.00002431336,0.00004983562],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002868631,0.000001313178,0.000002278012,0.0000425423,0.00001778148,0.00003163709,0.0004549099,0.02473352,0.4540454,0.000001024898,0.00001596718,0.5206507],"study_design_scores_gemma":[0.0001852103,0.000005850819,0.00004954379,0.00009330942,0.00001219763,0.0002319375,0.0005116422,0.9361121,0.06113008,0.00001835539,0.001524569,0.0001252165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5170968,0.0002455392,0.4786635,0.00004578261,0.0008197076,0.00006550735,5.391208e-7,0.0002292848,0.00283327],"genre_scores_gemma":[0.9845036,0.00008154064,0.01517724,0.00004862908,0.0001071923,3.67975e-9,0.000008527592,0.00003232807,0.00004100185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9113786,"threshold_uncertainty_score":0.4640882,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4213187122","doi":"10.3390/rs14040992","title":"Active Fire Detection from Landsat-8 Imagery Using Deep Multiple Kernel Learning","year":2022,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":80,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Remote sensing; Deep learning; Dilation (metric space); Artificial intelligence; Pixel; Satellite; Convolutional neural network; Satellite imagery; Pattern recognition (psychology); Geology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01054777749243627,"gpt":0.195938404566833,"spread":0.1853906270743967,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001406878,0.0001657082,0.0002019427,0.000102207,0.0005273477,0.00004440628,0.00005323927,0.0000698597,0.00003693732],"category_scores_gemma":[0.00006551926,0.0002040386,0.0000992924,0.0002704458,0.00001299359,0.0001121907,0.00005494907,0.0005539917,0.00002363733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004198836,"about_ca_system_score_gemma":0.00001104164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001350711,"about_ca_topic_score_gemma":0.0001335581,"domain_scores_codex":[0.9989187,0.0001457049,0.000224894,0.0002344256,0.0002166662,0.0002596738],"domain_scores_gemma":[0.9995517,0.0001231397,0.00006616433,0.000167783,0.000030054,0.00006114565],"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":[0.00002977634,0.000002299584,0.00002527956,0.00001254191,0.00003947975,0.00003313732,0.00102625,0.4218829,0.2128021,4.876333e-8,0.000007128066,0.3641391],"study_design_scores_gemma":[0.0003149294,0.00001600959,0.0003006597,0.00002565113,0.00001690599,0.0001281487,0.0014849,0.9736679,0.0197339,0.00001398276,0.004073087,0.0002239614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.87256,0.000168128,0.1245809,0.00001097166,0.001376779,0.0001155088,0.000006410402,0.0006178847,0.0005634528],"genre_scores_gemma":[0.997513,0.00001044843,0.002007574,0.0000237048,0.0002908186,7.097979e-8,0.00001762708,0.00006851854,0.00006826314],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.551785,"threshold_uncertainty_score":0.8320452,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4361277442","doi":"10.3390/rs15071821","title":"Deep Learning Approaches for Wildland Fires Remote Sensing: Classification, Detection, and Segmentation","year":2023,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Deep learning; Segmentation; Artificial intelligence; Market segmentation; Machine learning; Fire detection; Remote sensing; Geography; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03648153055778519,"gpt":0.2340152294937734,"spread":0.1975336989359882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000324166,0.0001702523,0.000181368,0.000194357,0.0003439013,0.00009343542,0.00002851863,0.0001270524,7.274216e-7],"category_scores_gemma":[0.0001179449,0.0001878774,0.00005648403,0.0003824982,0.00003049395,0.00009984063,0.00001274728,0.000160373,0.00002050644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000898525,"about_ca_system_score_gemma":0.000006874995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005661904,"about_ca_topic_score_gemma":0.0001101445,"domain_scores_codex":[0.9989888,0.000062548,0.0002851721,0.0002650944,0.0001382024,0.000260169],"domain_scores_gemma":[0.9995179,0.0001310006,0.00006660113,0.0001504371,0.00006299688,0.00007102915],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001339632,5.61323e-7,0.000007309869,0.0001331678,0.00003326506,0.000002434251,0.0009629137,0.05586927,0.03457839,0.000002156429,0.00005643206,0.9083407],"study_design_scores_gemma":[0.0003141169,0.00002263154,0.0007539329,0.00005837749,0.00002109641,0.00008989108,0.001276041,0.9873635,0.003508809,0.0001599831,0.006226475,0.0002051317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2269594,0.0001406079,0.7703125,0.0001589226,0.0005438362,0.0003355773,9.805945e-7,0.001073011,0.0004751426],"genre_scores_gemma":[0.9870442,0.0001214439,0.0121522,0.00001911268,0.0002631943,5.081642e-8,0.00002955399,0.00006745879,0.0003028021],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9314942,"threshold_uncertainty_score":0.7661418,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2475020744","doi":"10.1109/icuas.2016.7502546","title":"Vision-based forest fire detection in aerial images for firefighting using UAVs","year":2016,"lang":"en","type":"article","venue":"","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Firefighting; Artificial intelligence; Computer science; Optical flow; Computer vision; Feature (linguistics); Fire detection; Thresholding; Pixel; Remote sensing; Image (mathematics); Geography; Engineering; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.01059584265696785,"gpt":0.2285963781090632,"spread":0.2180005354520954,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001544243,0.0001159727,0.0001344846,0.00009359157,0.00006770265,0.00002696184,0.00005311995,0.00009359736,0.0000484419],"category_scores_gemma":[0.00006440514,0.00008462428,0.00006784188,0.0001249634,0.00001203404,0.0001489968,0.000006666728,0.00004334944,0.00001793744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001419953,"about_ca_system_score_gemma":0.00001117853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001419889,"about_ca_topic_score_gemma":0.0004872449,"domain_scores_codex":[0.9992919,0.00001735406,0.0002493172,0.0001455691,0.00008219578,0.0002136603],"domain_scores_gemma":[0.9996439,0.0001394803,0.00002657951,0.0001205944,0.00002901088,0.0000404089],"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":[0.0001386565,0.000026266,0.001411646,0.0002003756,0.00001886848,0.000004010004,0.00007004636,0.0333259,0.7219741,0.00003018718,0.0005860762,0.2422138],"study_design_scores_gemma":[0.001288973,0.00006036142,0.002141845,0.0001367918,0.000004164998,0.000004686788,0.00002213778,0.8493732,0.1402555,0.00004113146,0.006467202,0.000204036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7024435,0.00003235939,0.2947769,0.00008718928,0.001336064,0.0003197149,0.00001158567,0.0004226401,0.0005700137],"genre_scores_gemma":[0.9985714,0.000002715352,0.0009675318,0.00001535569,0.0002344213,0.00003882216,0.000001466714,0.00003230411,0.0001359808],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8160473,"threshold_uncertainty_score":0.3450878,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2015115674","doi":"10.1016/s1352-2310(99)00341-6","title":"Chemical characterisation of the haze in Brunei Darussalam during the 1998 episode","year":2000,"lang":"en","type":"article","venue":"Atmospheric Environment","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":70,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Smiths Detection (Canada)","funders":"","keywords":"Haze; Environmental chemistry; Benzene; BTEX; Pollution; Toluene; Ethylbenzene; Air pollution; Pollutant; Xylene; Environmental science; Chemistry; Smoke; Human health; Organic chemistry; Environmental health","retraction":null,"screen_n_in":null,"score":{"opus":0.001905579752272176,"gpt":0.1370951754064157,"spread":0.1351895956541436,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008333431,0.0001008382,0.0001111758,0.000001322788,0.00003758635,0.000006468209,0.000140458,0.00005363983,0.0004059556],"category_scores_gemma":[0.000002584684,0.00006685888,0.00005690462,0.00009681285,0.00004486812,0.00004260501,0.00002043701,0.000129053,0.0001068723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001337612,"about_ca_system_score_gemma":0.000002079975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006737174,"about_ca_topic_score_gemma":0.000009952278,"domain_scores_codex":[0.9993148,0.00003215557,0.0002475316,0.0001080075,0.0001560543,0.0001413979],"domain_scores_gemma":[0.9996408,0.00001450423,0.00003192027,0.0002909974,7.965616e-7,0.00002103487],"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":[0.00009229455,0.0002617579,0.150256,0.000266013,0.0001524031,0.000009278152,0.006329405,0.4094892,0.3383175,0.00003902493,0.0004760958,0.09431104],"study_design_scores_gemma":[0.0003443976,0.000009029734,0.9147682,0.00003227046,0.000007385924,0.00001114092,0.00006163942,0.03145074,0.01179424,0.000007972577,0.04136966,0.0001433431],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99842,0.0001245562,0.00006309792,0.0001739965,0.0001321149,0.0001887162,0.000001688613,0.00003788016,0.0008579544],"genre_scores_gemma":[0.9987712,0.000152448,0.00009233219,0.00003124366,0.00004493394,0.0000362528,0.000001314918,0.00001859242,0.0008517011],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7645122,"threshold_uncertainty_score":0.4444929,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2899895176","doi":"10.3390/s18113780","title":"A Video Based Fire Smoke Detection Using Robust AdaBoost","year":2018,"lang":"en","type":"article","venue":"Sensors","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":59,"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":"Priority Academic Program Development of Jiangsu Higher Education Institutions; Government of Jiangsu Province; National Natural Science Foundation of China","keywords":"Artificial intelligence; AdaBoost; Smoke; Computer vision; Computer science; Histogram; Fire detection; Pattern recognition (psychology); Classifier (UML); Histogram of oriented gradients; Luminance; Engineering; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02455662488489826,"gpt":0.2167378825340213,"spread":0.192181257649123,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009497887,0.0001289529,0.0001219776,0.00008376331,0.0001305764,0.00002856114,0.00005285774,0.000105715,0.000122294],"category_scores_gemma":[0.00002875431,0.0001341906,0.00006211516,0.0002531302,0.00003549369,0.00005728708,0.000006472699,0.0001098626,0.0001648442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001058955,"about_ca_system_score_gemma":0.00000970871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002360874,"about_ca_topic_score_gemma":0.0002479634,"domain_scores_codex":[0.9993068,0.00003239295,0.0001770487,0.0001481514,0.0001276318,0.000207986],"domain_scores_gemma":[0.9996233,0.00002380764,0.00002384928,0.0002070375,0.00005415243,0.0000678681],"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":[0.00009464248,0.0000277153,0.0008731892,0.0001955844,0.00009110957,0.00002878523,0.0008823849,0.8667924,0.09013434,0.00001078344,0.0007650882,0.04010392],"study_design_scores_gemma":[0.0002236032,0.00004096621,0.001423105,0.00003470404,0.000009265684,0.00002509962,0.00009542168,0.9447865,0.03872298,0.000002373563,0.01447069,0.0001652961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9881856,0.00003691554,0.006981298,0.00002288216,0.001631892,0.000119297,0.000005671513,0.0005834695,0.002433007],"genre_scores_gemma":[0.9989009,0.000002153066,0.0003720895,0.00004853153,0.0004455452,0.0000037497,0.000001659511,0.00004082387,0.000184508],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07799403,"threshold_uncertainty_score":0.5472136,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1432470681","doi":"10.1049/iet-ipr.2014.0935","title":"Benchmarking of wildland fire colour segmentation algorithms","year":2015,"lang":"en","type":"article","venue":"IET Image Processing","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Benchmarking; Computer science; Segmentation; Artificial intelligence; Algorithm; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.01620113855745962,"gpt":0.2441727222618977,"spread":0.2279715837044381,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001836095,0.00009332842,0.0001319657,0.0000473762,0.00004400087,0.00005128368,0.00005928427,0.00004964406,0.00001156579],"category_scores_gemma":[0.00001758052,0.0000939353,0.00002633526,0.0001818825,0.00002211704,0.0002957233,0.00001515711,0.00007812001,0.00001164526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005779596,"about_ca_system_score_gemma":0.00002945524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002122159,"about_ca_topic_score_gemma":0.000004327499,"domain_scores_codex":[0.9993642,0.00001591299,0.000219794,0.00009835807,0.0001702141,0.0001315493],"domain_scores_gemma":[0.9997005,0.00001130295,0.00005803455,0.00007335236,0.0000959309,0.00006091233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003284453,0.00004646432,0.001811438,0.001077169,0.00004769355,0.0000187053,0.00701181,0.02525454,0.06582218,0.000002124129,0.00473911,0.8941359],"study_design_scores_gemma":[0.0006436441,0.00005798174,0.0005046492,0.0001849635,0.00001520497,0.00003890937,0.00124444,0.9776667,0.01773825,0.00005491323,0.001648647,0.0002016997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7574793,0.003024935,0.2229432,0.0001285011,0.001905187,0.0004494095,0.00002084627,0.0008712769,0.01317737],"genre_scores_gemma":[0.9884462,0.00001069883,0.01125854,0.00001599049,0.0001439821,0.00001051219,0.000009335724,0.00002139195,0.00008329697],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9524121,"threshold_uncertainty_score":0.3830571,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4214663719","doi":"10.3390/f13030383","title":"A Vision-Based Detection and Spatial Localization Scheme for Forest Fire Inspection from UAV","year":2022,"lang":"en","type":"article","venue":"Forests","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Global Positioning System; Computer vision; Firefighting; Geographic coordinate system; Artificial intelligence; Inertial measurement unit; Frame (networking); Remote sensing; Environmental science; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.005535185830692411,"gpt":0.1993133310578946,"spread":0.1937781452272022,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008649389,0.0001050869,0.000105777,0.00008308444,0.0003263319,0.00003162777,0.00004576588,0.00006010054,0.00004090209],"category_scores_gemma":[0.00002555819,0.0001193692,0.00004683192,0.0001600012,0.00001420392,0.00007883876,0.0000167986,0.00009923406,0.000006116984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001427184,"about_ca_system_score_gemma":0.00001118518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009595357,"about_ca_topic_score_gemma":0.01254347,"domain_scores_codex":[0.9993572,0.00002434663,0.0001745574,0.000169807,0.0001463783,0.0001276813],"domain_scores_gemma":[0.9997221,0.00004825312,0.00003664432,0.0001188905,0.0000280295,0.00004610499],"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":[0.0004588914,0.00008652756,0.04582153,0.0002362206,0.00007385437,0.000005500889,0.0005919609,0.8554726,0.009099576,0.00009411087,0.002848434,0.08521081],"study_design_scores_gemma":[0.0006928677,0.0001864935,0.05063688,0.00001210843,0.00000770337,0.000003862963,0.00004364286,0.9330319,0.001056811,0.0002099504,0.01399087,0.0001268831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5626375,0.00009695425,0.4351892,0.00002894021,0.001108553,0.0003688261,0.00004978574,0.000474883,0.00004529856],"genre_scores_gemma":[0.9992177,0.000002632794,0.0001227473,0.00003142396,0.0001911741,0.0002590568,0.0001158406,0.00003497096,0.00002445812],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4365802,"threshold_uncertainty_score":0.699955,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2744502852","doi":"10.6028/nist.gcr.02-843-1","title":"Analysis of needs and existing capabilities for full-scale fire resistance testing","year":2008,"lang":"en","type":"report","venue":"","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of Standards and Technology; Victoria University; Commonwealth Scientific and Industrial Research Organisation; National Research Council Canada; Canadian Institute of Steel Construction","keywords":"Forensic engineering; Fireproofing; Environmental science; Engineering; Civil engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.04486944966902952,"gpt":0.2544651165547133,"spread":0.2095956668856838,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000359346,0.0002347864,0.0008094275,0.0004171697,0.00009522529,0.00001884225,0.00007893356,0.0002352834,0.00001885032],"category_scores_gemma":[0.0004010058,0.0002333078,0.0002339199,0.0008658181,0.00005738826,0.00004277239,0.00001670008,0.0001411456,5.306172e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001441423,"about_ca_system_score_gemma":0.00007625697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005570411,"about_ca_topic_score_gemma":0.002242638,"domain_scores_codex":[0.9985621,0.00001531811,0.0007007853,0.0002151014,0.0002997651,0.0002069174],"domain_scores_gemma":[0.9986496,0.0004587375,0.0001688625,0.0002820023,0.0003842457,0.00005657562],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003639591,0.000240171,0.1068441,0.1476865,0.03678716,0.00008361105,0.03726503,0.190352,0.01281269,0.0003458616,0.270091,0.1971279],"study_design_scores_gemma":[0.0006355229,0.0001660773,0.01980253,0.001738285,0.003260974,0.0001750465,0.005692524,0.5014841,0.0005235739,0.00003241306,0.4644734,0.002015545],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2783284,0.01374832,0.00917242,0.00003426564,0.002125718,0.001175438,0.0006889573,0.001427891,0.6932986],"genre_scores_gemma":[0.9476911,0.0007733977,0.004655072,0.000005219405,0.0003442364,0.0001105281,0.00009221557,0.00009774353,0.04623052],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6693627,"threshold_uncertainty_score":0.9514014,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2799675047","doi":"10.1117/12.2304936","title":"Wildland fires detection and segmentation using deep learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Convolutional neural network; Segmentation; Computer science; Deep learning; Pixel; Fire detection; Artificial intelligence; Image segmentation; Artificial neural network; Environmental science; Remote sensing; Machine learning; Geography; Architectural engineering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.008805987703908915,"gpt":0.2121827805514412,"spread":0.2033767928475323,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005517203,0.00005292286,0.00004839597,0.00004528876,0.000106685,0.00002914291,0.00001210043,0.00003574912,0.00004918696],"category_scores_gemma":[0.000006639158,0.00005110994,0.00001015684,0.00007140906,0.00001465065,0.00009896856,0.000004837877,0.00004732897,0.00002198221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002813162,"about_ca_system_score_gemma":9.799776e-7,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007596447,"about_ca_topic_score_gemma":0.0002167305,"domain_scores_codex":[0.9997129,0.00001401571,0.00008222453,0.0000668054,0.00004819444,0.00007588307],"domain_scores_gemma":[0.9999028,0.00001026041,0.00001083957,0.0000350451,0.00001534479,0.00002571484],"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":[0.00002271898,0.000005153451,0.009129602,0.00008843599,0.00005237163,0.000001617528,0.002252239,0.02906313,0.6237518,0.00001476438,0.00005068663,0.3355674],"study_design_scores_gemma":[0.0001579638,0.00004278636,0.00567539,0.00000834293,0.000004984259,0.00002806055,0.0003011626,0.9685319,0.02205915,0.000006903195,0.00309988,0.00008348263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8766038,0.00006139551,0.1206194,0.000003766657,0.0003403773,0.00005249586,1.180411e-7,0.0002632304,0.002055428],"genre_scores_gemma":[0.9991341,0.00001412922,0.0005274178,0.00001045255,0.0001462914,0.000002220516,5.538528e-7,0.00001093338,0.0001538554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9394687,"threshold_uncertainty_score":0.2084203,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401244789","doi":"10.1016/j.aej.2024.07.066","title":"Optimization of automated garbage recognition model based on ResNet-50 and weakly supervised CNN for sustainable urban development","year":2024,"lang":"en","type":"article","venue":"Alexandria Engineering Journal","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":44,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Garbage; Sustainable development; Computer science; Artificial intelligence; Residual neural network; Pattern recognition (psychology); Development (topology); Environmental science; Agricultural engineering; Machine learning; Mathematics; Engineering; Deep learning; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.009260302313678038,"gpt":0.1943468564685202,"spread":0.1850865541548422,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000349514,0.0001702011,0.0001858818,0.0003707802,0.00007901893,0.0001220203,0.00005893514,0.0001009872,0.00002170911],"category_scores_gemma":[0.00005382831,0.0001709329,0.0000611228,0.0001866698,0.000007103647,0.0002007572,0.000007053065,0.0001770926,0.000002520187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001498636,"about_ca_system_score_gemma":0.00006199654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001457208,"about_ca_topic_score_gemma":3.945863e-7,"domain_scores_codex":[0.9990668,0.00001308405,0.0003774951,0.0001365864,0.0001562168,0.000249828],"domain_scores_gemma":[0.9996032,0.00008079616,0.00002938109,0.00008513968,0.0001035158,0.00009797752],"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":[0.00003260398,0.000009157495,0.000003629825,0.0006987741,0.00004932249,0.000009175378,0.0002482637,0.9933176,0.003017826,0.00004285047,0.001393358,0.001177449],"study_design_scores_gemma":[0.0005533442,0.00007104802,0.00005170922,0.0004440278,0.00002289724,0.00003190638,0.00004718821,0.992089,0.003627287,0.000007986022,0.00286147,0.000192105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03566174,0.0005516476,0.961496,0.00003505027,0.0005679391,0.0003222403,0.00001157955,0.0008933658,0.0004604308],"genre_scores_gemma":[0.9536335,0.00006097385,0.04575019,0.00001034314,0.0001266414,0.00004195366,0.00003276162,0.00007599966,0.0002676589],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9179717,"threshold_uncertainty_score":0.6970441,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401645683","doi":"10.3390/en17164059","title":"A Review of Hydrogen Leak Detection Regulations and Technologies","year":2024,"lang":"en","type":"review","venue":"Energies","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":43,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"Office of Energy Research and Development; Natural Resources Canada; National Research Council Canada","keywords":"Leak; Leak detection; Risk analysis (engineering); Business; Computer science; Environmental science; Engineering; Environmental engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01983112006446955,"gpt":0.2627951068650693,"spread":0.2429639868005997,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110018,0.0002200373,0.0007981044,0.0002518392,0.00002717708,0.00001443469,0.00009221317,0.0002166069,0.000005554373],"category_scores_gemma":[0.00003952519,0.0001720301,0.0002130309,0.0004546671,0.00004312916,0.0000434413,0.00004308017,0.0001886359,0.00002867973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004730266,"about_ca_system_score_gemma":0.00001557165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007059283,"about_ca_topic_score_gemma":0.00003226191,"domain_scores_codex":[0.9991971,0.00002792362,0.0004391333,0.0001590891,0.00007961196,0.0000971236],"domain_scores_gemma":[0.9996018,0.00003564738,0.00007086854,0.0002592742,0.00001840824,0.0000139813],"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":[8.451757e-8,8.362848e-7,1.188691e-8,0.2325195,0.00008915681,8.367317e-7,0.00000986515,0.00007295168,0.000006470399,0.00008873475,0.0009090248,0.7663025],"study_design_scores_gemma":[0.00001078521,0.000008102556,7.014112e-8,0.09607883,0.0003475945,0.0000620991,0.00001944752,0.0001987803,0.0000663875,0.00003398187,0.903034,0.0001399694],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000002778496,0.9973879,0.0000362288,0.00001216838,0.0003989509,0.0002403063,0.00001887085,0.001130612,0.0007722221],"genre_scores_gemma":[0.0002124826,0.9992183,0.0000254214,0.000002290514,0.00004404231,0.0001392523,0.00001191069,0.0000457604,0.0003005042],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9021249,"threshold_uncertainty_score":0.7015185,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4366547628","doi":"10.3390/f14040838","title":"Omni-Dimensional Dynamic Convolution Meets Bottleneck Transformer: A Novel Improved High Accuracy Forest Fire Smoke Detection Model","year":2023,"lang":"en","type":"article","venue":"Forests","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":43,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Government of Jiangsu Province","keywords":"Computer science; Fire detection; Bottleneck; Smoke; Convolutional neural network; Environmental science; Remote sensing; Artificial intelligence; Architectural engineering; Engineering; Geography; Meteorology","retraction":null,"screen_n_in":null,"score":{"opus":0.01166928567823236,"gpt":0.2214945600472119,"spread":0.2098252743689795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001708904,0.0002840304,0.0002583553,0.0002020265,0.0001962126,0.0000392586,0.0001420556,0.0002529878,0.00002069523],"category_scores_gemma":[0.00004579314,0.0002900062,0.0001611027,0.0004755547,0.00003480532,0.0003187379,0.00001854821,0.0002446736,0.0001795427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002364128,"about_ca_system_score_gemma":0.00003914403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004231206,"about_ca_topic_score_gemma":0.006680428,"domain_scores_codex":[0.9984817,0.00001540652,0.0004164462,0.0003185566,0.0002848967,0.0004829847],"domain_scores_gemma":[0.9993772,0.00007280074,0.00005890916,0.0002850209,0.00006983226,0.0001362668],"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":[0.0001165059,0.00004423963,0.0004130472,0.0002372074,0.0001066543,0.000007449151,0.0002661465,0.8657789,0.1170016,0.0002393179,0.0008966873,0.01489224],"study_design_scores_gemma":[0.0009967057,0.00007319514,0.05267152,0.0000527026,0.00002097597,0.00003074231,0.00002072717,0.9418882,0.002528911,0.0003203977,0.00108448,0.0003114483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9590782,0.00009450975,0.03673972,0.0001929755,0.001594735,0.0005042326,0.0001183532,0.001559602,0.0001176788],"genre_scores_gemma":[0.9988658,0.00004163416,0.0001992507,0.00003213584,0.00009790915,0.0001557566,0.0001627518,0.00008676461,0.0003580326],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1144727,"threshold_uncertainty_score":0.9999552,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4319316164","doi":"10.3390/f14020315","title":"Multi-Scale Forest Fire Recognition Model Based on Improved YOLOv5s","year":2023,"lang":"en","type":"article","venue":"Forests","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Adaptability; Computer science; Fire detection; Environmental science; Scale (ratio); Remote sensing; Engineering; Ecology; Geography; Cartography; Architectural engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02300552395265005,"gpt":0.2259685318274747,"spread":0.2029630078748247,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001033384,0.0001355514,0.0001218703,0.0001110432,0.00006710069,0.00002184012,0.00007890241,0.000118541,0.00002258024],"category_scores_gemma":[0.00002639986,0.0001346793,0.00007977047,0.0002512461,0.00001238386,0.0000691867,0.000009936193,0.0001272139,0.0009794976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005439535,"about_ca_system_score_gemma":0.00001073172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004291002,"about_ca_topic_score_gemma":0.002328745,"domain_scores_codex":[0.9992856,0.00001334144,0.0001754366,0.0001657443,0.0001174796,0.000242348],"domain_scores_gemma":[0.9996301,0.00003364186,0.00002054868,0.0002113676,0.00002711539,0.00007723767],"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":[0.00003879805,0.00003119711,0.002602499,0.0001223112,0.00001338266,0.000007717244,0.0001777272,0.9682699,0.003152031,0.000003216631,0.006182453,0.01939873],"study_design_scores_gemma":[0.0005514344,0.0000488887,0.02869714,0.00004717525,0.0000043929,0.00000152011,0.00001669349,0.9689831,0.0007049938,0.00006909208,0.0007143053,0.0001612518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9451467,0.00001653527,0.04865765,0.0001265942,0.00123598,0.0004681318,0.0001165257,0.002480335,0.001751501],"genre_scores_gemma":[0.997953,0.000005443419,0.0008787128,0.00005599716,0.00008623819,0.0001036045,0.0001352033,0.00005101869,0.0007307756],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05280626,"threshold_uncertainty_score":0.9997984,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3133806306","doi":"10.1109/tii.2021.3064845","title":"Tensor-Based Approach for Liquefied Natural Gas Leakage Detection From Surveillance Thermal Cameras: A Feasibility Study in Rural Areas","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"IntelliView Technologies (Canada); Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Leakage (economics); Liquefied natural gas; Background subtraction; Computer science; Residual; Thermal; Artificial intelligence; Natural gas; Environmental science; Engineering; Waste management; Algorithm; Pixel; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.03633067353197567,"gpt":0.2415406569504676,"spread":0.2052099834184919,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003875208,0.0002800176,0.0004149023,0.0001882348,0.0001578449,0.00009862422,0.0001304021,0.0003110897,0.00002683816],"category_scores_gemma":[0.00004335147,0.0002809864,0.0001825217,0.0005311331,0.00002979207,0.0002710735,0.000001236521,0.0008257021,0.000009532487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003729093,"about_ca_system_score_gemma":0.00009181618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003343179,"about_ca_topic_score_gemma":0.001464453,"domain_scores_codex":[0.9982375,0.0001635193,0.0008448088,0.0001656146,0.0002726688,0.0003159236],"domain_scores_gemma":[0.9990528,0.0002587936,0.00009885114,0.0003804783,0.000121404,0.00008771005],"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":[0.0009091906,0.0005606419,0.001226227,0.00009610163,0.0001765578,0.000003940398,0.002247079,0.9629758,0.002414927,7.202404e-7,0.00005304084,0.02933576],"study_design_scores_gemma":[0.006821089,0.0002998596,0.001909176,0.00005195412,0.00003956627,0.000006343865,0.008347465,0.9462486,0.03569906,0.000003047372,0.000122174,0.0004516535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7437316,0.00001148299,0.2528323,0.00001849286,0.001715304,0.001146021,0.0001541654,0.0002640944,0.0001265141],"genre_scores_gemma":[0.9990181,0.000003152112,0.0004118784,0.00004102798,0.0001504476,0.0002569642,0.0000508745,0.0000340009,0.00003352169],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2552865,"threshold_uncertainty_score":0.9999642,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4366420362","doi":"10.3390/f14040833","title":"An Improved Forest Fire and Smoke Detection Model Based on YOLOv5","year":2023,"lang":"en","type":"article","venue":"Forests","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Smoke; Computer science; Feature (linguistics); Deep learning; Environmental science; Feature extraction; Fire prevention; Artificial intelligence; Remote sensing; Geography; Meteorology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01146285747047359,"gpt":0.2201460487562567,"spread":0.2086831912857831,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009620067,0.0001162349,0.00009910487,0.0001072667,0.00007889624,0.00003107271,0.00005645816,0.000101578,0.000004912051],"category_scores_gemma":[0.00001418937,0.0001138735,0.00003432146,0.0001891686,0.00001305671,0.0000859597,0.000006783579,0.0001034596,0.00004532877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003621513,"about_ca_system_score_gemma":0.000006583296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009585045,"about_ca_topic_score_gemma":0.001895441,"domain_scores_codex":[0.9994249,0.00001265781,0.0001247188,0.0001562867,0.00009474696,0.0001866964],"domain_scores_gemma":[0.999653,0.00002172552,0.00001492127,0.0002097757,0.00001508996,0.00008547882],"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":[0.00004620002,0.00001316245,0.005752506,0.00009301778,0.00001088508,0.000005853551,0.0001941709,0.9615903,0.004181657,0.00002761579,0.0004715585,0.02761302],"study_design_scores_gemma":[0.0002787345,0.0001184442,0.09151293,0.00001465587,0.00000336169,0.000002468239,0.00001829174,0.9064612,0.0009645447,0.0001148891,0.0003921981,0.0001182468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9861964,0.00001213434,0.01171347,0.00003989302,0.0004294468,0.0001713743,0.00001165519,0.001049388,0.000376219],"genre_scores_gemma":[0.9995999,0.000004992104,0.00004789722,0.00003623642,0.00007592036,0.00004787908,0.00001882943,0.00003825152,0.0001300704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08576042,"threshold_uncertainty_score":0.4643627,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394819366","doi":"10.3390/fire7040140","title":"YOLO-Based Models for Smoke and Wildfire Detection in Ground and Aerial Images","year":2024,"lang":"en","type":"article","venue":"Fire","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Smoke; Firefighting; Environmental science; Vegetation (pathology); Fire detection; Terrain; Remote sensing; Computer science; Meteorology; Cartography; Geography; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01645147607088426,"gpt":0.2222521695086211,"spread":0.2058006934377368,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008168639,0.00008722438,0.000105255,0.00006520303,0.00003930276,0.00006932414,0.0000198896,0.00008010581,0.000002892348],"category_scores_gemma":[0.000007682541,0.00008715451,0.00002382325,0.00008538972,0.00001562388,0.0001402314,0.00000530748,0.00007441155,0.000001674787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003561631,"about_ca_system_score_gemma":0.0000062131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001615301,"about_ca_topic_score_gemma":0.0001369554,"domain_scores_codex":[0.9995874,0.000009789849,0.0001133107,0.0001357684,0.00004393432,0.0001098532],"domain_scores_gemma":[0.9998561,0.00004302791,0.000005876362,0.00005930701,0.000004978129,0.00003070577],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000299647,0.00003444085,0.0004662019,0.003694276,0.0001267327,0.00005237032,0.002702695,0.03762066,0.03237822,0.0004136637,0.003099387,0.9191117],"study_design_scores_gemma":[0.0003814286,0.00004824978,0.001860076,0.00008404161,0.000007186447,0.00001405607,0.00003496015,0.9883842,0.002156771,0.0003147447,0.006596706,0.0001176106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9847598,0.002258396,0.01104406,0.0001400715,0.0009733558,0.0002568347,0.00002723197,0.0003358397,0.0002044192],"genre_scores_gemma":[0.9995543,0.00004959623,0.00006761968,0.00001661228,0.0001418158,0.00006263879,0.000005032216,0.00002311508,0.00007930614],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9507635,"threshold_uncertainty_score":0.3554058,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396605531","doi":"10.1109/tie.2024.3387089","title":"Early Wildfire Detection and Distance Estimation Using Aerial Visible-Infrared Images","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Electronics","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":true,"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":"Artificial intelligence; Computer vision; Computer science; Global Positioning System; Segmentation; Triangulation; False alarm; Remote sensing; Fire detection; Monocular; Feature (linguistics); Image segmentation; Satellite; Aerial image; Image (mathematics); Geography; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01497459384278958,"gpt":0.229801966966461,"spread":0.2148273731236715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000145721,0.0002207214,0.00019445,0.0002327628,0.0002226914,0.0002294861,0.00006189547,0.0002908606,0.00002051979],"category_scores_gemma":[0.000005971594,0.0002417123,0.00008691393,0.0005349074,0.00003560552,0.0003948075,5.398679e-7,0.000688041,0.00002011409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004364194,"about_ca_system_score_gemma":0.00007930886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006868822,"about_ca_topic_score_gemma":0.00005246355,"domain_scores_codex":[0.998872,0.00004845748,0.0003110986,0.0002611262,0.0001934542,0.000313882],"domain_scores_gemma":[0.9996496,0.00006527271,0.00002684808,0.0001580289,0.0000178514,0.000082378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002907546,0.00002733198,0.000002024884,0.000107424,0.0002294253,0.00001078747,0.000346716,0.3479452,0.07373467,0.00007849598,0.0001805452,0.5770466],"study_design_scores_gemma":[0.0007690992,0.000254182,0.00001308899,0.0001558758,0.00008818255,0.000066482,0.00002632024,0.8717301,0.1173418,0.0001344484,0.009084335,0.0003359905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1980105,0.0005382396,0.7958668,0.0000372398,0.004151147,0.0003143987,0.00003606584,0.0008574165,0.0001882189],"genre_scores_gemma":[0.9989837,0.0001546627,0.0001122353,0.000005512928,0.0004364461,0.00003777025,0.000002533767,0.00005995907,0.0002071952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8009732,"threshold_uncertainty_score":0.9856743,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1969910747","doi":"10.1007/bf03187040","title":"Progress in research and application of water mist fire suppression technology","year":2003,"lang":"en","type":"article","venue":"Chinese Science Bulletin","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Army Research Laboratory; National Research Council Canada; Underwriters Laboratories","keywords":"Mist; Environmental science; Meteorology; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.01113789938389656,"gpt":0.2833983957415873,"spread":0.2722604963576908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008670863,0.00005895432,0.00009085245,0.0002704526,0.00008978347,0.00001696597,0.0001493562,0.0000590886,0.00002372029],"category_scores_gemma":[0.00006803442,0.00003947343,0.000007299763,0.0008062412,0.0005050969,0.00003461213,0.00003410416,0.0001330521,0.0000303278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002920266,"about_ca_system_score_gemma":0.000009478518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000115354,"about_ca_topic_score_gemma":0.000004969737,"domain_scores_codex":[0.9992541,0.00002141898,0.0001457593,0.0001734421,0.0001943239,0.0002109364],"domain_scores_gemma":[0.9996802,0.00001646133,0.00001003549,0.00018587,0.00007096204,0.00003648873],"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":[0.00003427988,0.0001700829,0.1919274,0.0005225783,0.000005111299,0.00001033821,0.002533393,0.0008014578,0.7459459,0.002281928,0.00129624,0.05447138],"study_design_scores_gemma":[0.001497817,0.0002479067,0.09269571,0.0002702227,0.000002144649,0.0001380833,0.001150949,0.08238304,0.6601955,0.003173818,0.1576584,0.0005864714],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970395,0.00032104,0.0001020674,0.0005730302,0.00009940917,0.000188425,5.969778e-7,0.00005906417,0.001616854],"genre_scores_gemma":[0.9996526,0.00001002045,0.000193055,0.000002210094,0.000007709325,0.00004525966,5.554774e-7,0.000006035908,0.00008253198],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1563621,"threshold_uncertainty_score":0.186105,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399880721","doi":"10.1109/lgrs.2024.3417624","title":"Application of Explainable Artificial Intelligence in Predicting Wildfire Spread: An ASPP-Enabled CNN Approach","year":2024,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.01259044647226819,"gpt":0.2216278704247412,"spread":0.209037423952473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004532879,0.0001242438,0.0001522401,0.0002287531,0.00009248229,0.00006784189,0.00008803691,0.00007104594,3.703036e-7],"category_scores_gemma":[0.00001449984,0.0001192668,0.00002951645,0.0006279432,0.0001109512,0.0002815104,0.00001079815,0.0001832754,0.000004318139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005454307,"about_ca_system_score_gemma":0.00001418622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000985182,"about_ca_topic_score_gemma":0.00006465715,"domain_scores_codex":[0.9989073,0.00003476335,0.0003016337,0.0003175077,0.0001786353,0.0002601215],"domain_scores_gemma":[0.9996815,0.00003916429,0.00002975594,0.0001791599,0.00001249667,0.00005796662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008312859,0.000008490738,0.00003909527,0.0003090441,0.000007226416,0.00001873212,0.003037206,0.04075785,0.3230719,0.00003596194,0.00003128739,0.6326749],"study_design_scores_gemma":[0.00002411898,0.00001734292,0.0001850313,0.0001672447,0.000004794043,0.00005409036,0.0007529548,0.9867957,0.0115053,0.0001153978,0.0002496479,0.0001283515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4936117,0.0001065112,0.5051476,0.0001080833,0.0005206588,0.0001342823,9.07958e-7,0.000160593,0.0002095989],"genre_scores_gemma":[0.9929378,0.00002900952,0.006799208,0.00006248449,0.0001338,4.75149e-7,0.000002401926,0.00001662677,0.00001818351],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9460379,"threshold_uncertainty_score":0.486356,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394748062","doi":"10.3390/fire7040135","title":"Fire and Smoke Detection Using Fine-Tuned YOLOv8 and YOLOv7 Deep Models","year":2024,"lang":"en","type":"article","venue":"Fire","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Smoke; Environmental science; Fire detection; Computer science; Environmental resource management; Engineering; Meteorology; Geography; Architectural engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0195636977771859,"gpt":0.2134469938236127,"spread":0.1938832960464268,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007644082,0.0001387668,0.0001381617,0.00006010924,0.00009547704,0.00008823826,0.0000324402,0.0001282575,0.0000209647],"category_scores_gemma":[0.000008572121,0.0001370154,0.00003538574,0.0001592918,0.00002219413,0.0002032205,0.00002060776,0.0001507534,0.00001294833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004852524,"about_ca_system_score_gemma":0.000005935025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001915105,"about_ca_topic_score_gemma":0.00009734601,"domain_scores_codex":[0.9993879,0.00001664702,0.000157991,0.0001934113,0.00008300252,0.0001610179],"domain_scores_gemma":[0.9997674,0.00003026038,0.00001070868,0.0001123781,0.00001340852,0.00006580003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005013855,0.00001805482,0.0004694511,0.002191027,0.0002776488,0.0001264005,0.00527828,0.07469071,0.03042836,0.0002708611,0.0007615383,0.8854375],"study_design_scores_gemma":[0.0001233557,0.00002415991,0.0006718033,0.00009278803,0.00001830739,0.0001341591,0.00006933065,0.993641,0.001271784,0.0001750478,0.003619161,0.0001590577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9825183,0.006989883,0.008224478,0.00006467657,0.000918836,0.0001277372,0.0000102531,0.0005902575,0.0005555428],"genre_scores_gemma":[0.9993351,0.0001579507,0.0001098082,0.00001745037,0.000146244,0.00001016822,0.000003085738,0.00003639317,0.0001838406],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9189503,"threshold_uncertainty_score":0.5587326,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1992652813","doi":"10.1145/2769493.2769516","title":"Cooking risk analysis to enhance safety of elderly people in smart kitchen","year":2015,"lang":"en","type":"article","venue":"","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Smoke; Environmental science; Combustor; Relative humidity; Residence; Waste management; Computer science; Combustion; Engineering; Chemistry; Meteorology; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.007441603879389139,"gpt":0.226367125409043,"spread":0.2189255215296538,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003797257,0.00008246728,0.0002659727,0.0002444377,0.00001248993,0.000008378661,0.00008225546,0.00005195352,0.00007481774],"category_scores_gemma":[0.0000561799,0.00008123366,0.00007086337,0.001109872,0.000004077384,0.00005469725,0.00001397546,0.00008225109,0.0000669154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007824614,"about_ca_system_score_gemma":0.00001016891,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002596542,"about_ca_topic_score_gemma":0.01841811,"domain_scores_codex":[0.999258,0.00003484889,0.0003100928,0.0001172801,0.0001416971,0.0001380782],"domain_scores_gemma":[0.9995908,0.0000411111,0.0000290225,0.0002026974,0.00004545523,0.00009095345],"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":[0.000103781,0.00005111216,0.1886802,0.00007797623,0.0007469347,0.000003874268,0.01152898,0.7486616,0.00426059,0.0001177743,0.00203571,0.04373147],"study_design_scores_gemma":[0.001110022,0.0002702515,0.3317077,0.00007332995,0.0002836754,0.000004785506,0.00397477,0.5690507,0.03795188,0.00005959173,0.05465805,0.0008552071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.857697,0.00009265533,0.117487,0.00005529608,0.0002655307,0.0001533787,0.000008404295,0.0001706188,0.02407007],"genre_scores_gemma":[0.9988354,0.00001354256,0.0005576726,0.00001282965,0.00001921029,0.000008627958,0.000002528311,0.00001039622,0.0005397194],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1796109,"threshold_uncertainty_score":0.9994932,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2492628054","doi":"10.1142/9789812791177_0003","title":"Estimation of Live Fuel Moisture Content","year":2003,"lang":"en","type":"book-chapter","venue":"Series in remote sensing","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Water content; Environmental science; Estimation; Content (measure theory); Mathematics; Geology; Engineering; Geotechnical engineering; Systems engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0177687054407611,"gpt":0.201811774569028,"spread":0.1840430691282669,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009976752,0.0002480861,0.0004137023,0.0001516099,0.00002199966,0.00001412074,0.00004541316,0.0003454963,0.00001955951],"category_scores_gemma":[0.00003224712,0.0002726417,0.00009640179,0.00003757966,0.00005682656,0.0000635979,0.00001306024,0.0003324607,0.00002496263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001504755,"about_ca_system_score_gemma":0.00001258961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009656898,"about_ca_topic_score_gemma":0.000389652,"domain_scores_codex":[0.999064,0.00001581382,0.0004531519,0.0001636114,0.0001620019,0.0001414603],"domain_scores_gemma":[0.9995129,0.00002670717,0.000111507,0.0002521457,0.00006327328,0.00003344692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001352905,0.00000706703,0.000002287019,0.004369321,0.000394837,0.0002829627,0.006222964,0.105958,0.003564854,0.007806927,0.001707899,0.8695476],"study_design_scores_gemma":[0.001250303,0.0002262205,0.0001451296,0.008184355,0.000144217,0.001054202,0.001501788,0.6593376,0.005742007,0.01692959,0.3032672,0.002217442],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.001432541,0.002916807,0.01508338,0.0001056386,0.004019544,0.0006174829,0.0000260849,0.0003755155,0.975423],"genre_scores_gemma":[0.63359,0.002066674,0.0353937,0.0002119605,0.0004601096,2.915166e-7,0.0001253554,0.0005086307,0.3276432],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8673301,"threshold_uncertainty_score":0.9999726,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3105393511","doi":"10.1007/s11042-021-11766-3","title":"STCNet: spatiotemporal cross network for industrial smoke detection","year":2022,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ministry of Education and Child Care","funders":"Jiangsu Provincial Key Research and Development Program; Priority Academic Program Development of Jiangsu Higher Education Institutions; National Natural Science Foundation of China","keywords":"Computer science; Feature (linguistics); Smoke; Artificial intelligence; Motion (physics); Path (computing); Code (set theory); Task (project management); Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.04146220603052695,"gpt":0.2531490601909085,"spread":0.2116868541603815,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001732998,0.00009581722,0.0001130069,0.00003567279,0.0004866853,0.0000616902,0.00007643866,0.00006782525,0.00005432204],"category_scores_gemma":[0.00001252269,0.0001083565,0.00004626832,0.0001898477,0.00002365677,0.00007050137,0.00002618507,0.000169937,0.000007143738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005721997,"about_ca_system_score_gemma":0.00001117415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004549305,"about_ca_topic_score_gemma":0.00003866128,"domain_scores_codex":[0.9993356,0.00001858123,0.0002153571,0.0001607946,0.00009795549,0.0001717027],"domain_scores_gemma":[0.9996274,0.00009841243,0.00003979315,0.0001454183,0.00002462672,0.00006436955],"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":[0.00006098029,0.00004686961,0.002855993,0.00005254321,0.00006290626,4.415836e-7,0.0002773108,0.1108632,0.002123128,0.0006418089,0.00512312,0.8778917],"study_design_scores_gemma":[0.0008872633,0.00005357717,0.005615539,0.000002764069,0.00001214263,0.000006568194,0.00008528425,0.25254,0.0006703288,0.0002291406,0.7397045,0.0001928484],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3480809,0.00121899,0.6279485,0.000611425,0.00553072,0.008721679,0.002884149,0.002145942,0.002857789],"genre_scores_gemma":[0.9933999,0.00001284274,0.0008334019,0.00004220087,0.001087763,0.004200755,0.0001871594,0.0000282009,0.0002078469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8776988,"threshold_uncertainty_score":0.4418651,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2083251578","doi":"10.1109/crv.2010.29","title":"Flame Region Detection Based on Histogram Backprojection","year":2010,"lang":"en","type":"article","venue":"","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Histogram; Fire detection; Artificial intelligence; Computer vision; Computer science; Detector; Projection (relational algebra); Smoke; False alarm; Pattern recognition (psychology); Algorithm; Engineering; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.005867017714848875,"gpt":0.1770134905702745,"spread":0.1711464728554257,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000932324,0.0001082225,0.00008224107,0.0001578003,0.00006984844,0.0000250019,0.00004635939,0.0001386029,0.0001112839],"category_scores_gemma":[0.00001737939,0.0001023399,0.00006376584,0.0001984492,0.0000127902,0.0000682293,0.000002408014,0.0002664532,0.0002560898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007021208,"about_ca_system_score_gemma":0.00000548077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007831076,"about_ca_topic_score_gemma":0.0004777304,"domain_scores_codex":[0.9994606,0.00001508397,0.0001402681,0.0001362095,0.0001150948,0.0001327204],"domain_scores_gemma":[0.9996626,0.00001863537,0.00001730888,0.0002229984,0.00002659481,0.00005187585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001096082,0.00008385946,0.0003617802,0.0001214456,0.00002600028,0.00001024393,0.0001533836,0.02505129,0.4291058,0.0004286465,0.006570338,0.5379776],"study_design_scores_gemma":[0.0003094435,0.0001062625,0.001537926,0.00000856202,0.000004352967,0.00003074684,0.00002590779,0.7576023,0.04655321,0.00001655555,0.1936163,0.0001884885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3393507,0.00001218386,0.3951626,0.0002505395,0.01673617,0.0006635681,0.000001600915,0.005770137,0.2420525],"genre_scores_gemma":[0.9983254,0.000001675179,0.0002212538,0.00006565936,0.0002327404,0.0000305459,0.000002474838,0.00002692344,0.001093322],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.732551,"threshold_uncertainty_score":0.4173301,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4288047839","doi":"10.1109/icuas54217.2022.9836119","title":"An Early Forest Fire Detection System Based on DJI M300 Drone and H20T Camera","year":2022,"lang":"en","type":"article","venue":"2022 International Conference on Unmanned Aircraft Systems (ICUAS)","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"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":"Drone; Computer science; Robustness (evolution); Artificial intelligence; Fire detection; Remote sensing; RGB color model; On board; Computer vision; Constant false alarm rate; False alarm; Engineering; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.01184794685068429,"gpt":0.2134361499640807,"spread":0.2015882031133964,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005153175,0.0004108751,0.0004182256,0.0004785777,0.0004749171,0.0002704045,0.0004885344,0.0001490803,0.0002635654],"category_scores_gemma":[0.0000245047,0.0004444086,0.0001223894,0.0003138357,0.00004108467,0.0002626688,0.00005986928,0.0006144533,0.0001545662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008735987,"about_ca_system_score_gemma":0.00005360669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008500925,"about_ca_topic_score_gemma":0.0001701638,"domain_scores_codex":[0.9969747,0.0003284677,0.0006510737,0.0006236426,0.001039638,0.0003824731],"domain_scores_gemma":[0.9988205,0.00009858067,0.0001808701,0.0005108401,0.0001759375,0.0002132426],"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":[0.001159134,0.0004819953,0.004694917,0.000984283,0.0005740047,0.0003400379,0.001483176,0.9227935,0.02780492,0.0271798,0.003513522,0.008990686],"study_design_scores_gemma":[0.0009795682,0.0008914628,0.003027439,0.0002281638,0.00001763907,0.0001098405,0.001804997,0.9856378,0.0004823179,0.00001687868,0.006321818,0.0004820116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9481864,0.0001883935,0.01098633,0.0006706545,0.01576921,0.001677932,0.0007131841,0.00205628,0.01975165],"genre_scores_gemma":[0.9972511,0.00001102107,0.00001518886,0.0001224474,0.0003712354,0.0006660577,0.0001469225,0.00008660075,0.001329449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06284434,"threshold_uncertainty_score":0.9998007,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2961252543","doi":"10.1109/isass.2019.8757707","title":"A Survey on Forest Fire Monitoring Using Unmanned Aerial Vehicles","year":2019,"lang":"en","type":"article","venue":"","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Damages; Flexibility (engineering); Fire detection; Computer science; Remote sensing; Environmental science; Firefighting; Environmental resource management; Engineering; Architectural engineering; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.02622813269794623,"gpt":0.232985215962171,"spread":0.2067570832642248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001351194,0.0001053844,0.0001310165,0.00004200467,0.00003871884,0.00003510847,0.00006669998,0.00007361212,0.00005458601],"category_scores_gemma":[0.00001339289,0.00009887187,0.00003985404,0.0001148951,0.000004787667,0.00006972671,0.0000109752,0.00008507885,0.0003475977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006394995,"about_ca_system_score_gemma":0.000005932146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000773224,"about_ca_topic_score_gemma":0.0001461252,"domain_scores_codex":[0.9994255,0.00002854483,0.0001476096,0.0001133168,0.0001148682,0.0001701282],"domain_scores_gemma":[0.9997011,0.00005459363,0.0000140084,0.0001656735,0.00001936768,0.00004524747],"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":[0.0001560302,0.00003733022,0.5193238,0.0001707562,0.0001172096,0.000008767114,0.0003750332,0.4227392,0.04624758,0.0001176812,0.001513065,0.009193494],"study_design_scores_gemma":[0.0005641896,0.00006593983,0.4680981,0.0000836177,0.000003358379,0.00000360085,0.00008125174,0.5198855,0.009186619,0.00000581454,0.00175302,0.0002689483],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9933093,0.00002963682,0.0001797679,0.000005264193,0.003333404,0.0001270753,0.000005200222,0.0003301072,0.002680206],"genre_scores_gemma":[0.9989793,0.000004162449,0.00005541023,0.00000671353,0.0002785708,0.000002632756,0.000003684353,0.00002929145,0.000640287],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09714628,"threshold_uncertainty_score":0.4467781,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2978477598","doi":"10.1109/iciai.2019.8850811","title":"Wildfire Flame and Smoke Detection Using Static Image Features and Artificial Neural Network","year":2019,"lang":"en","type":"article","venue":"","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Fire detection; Smoke; Computer science; Artificial neural network; Signature (topology); Block (permutation group theory); Artificial intelligence; Damages; Remote sensing; Environmental science; Computer vision; Engineering; Geology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.008868607028045022,"gpt":0.2048186579554647,"spread":0.1959500509274197,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007632644,0.0001067232,0.0001242423,0.00004028234,0.00006983592,0.00007958706,0.00002095253,0.00006316544,0.00002194189],"category_scores_gemma":[0.000005181565,0.00009891912,0.00002012613,0.0000935748,0.00001856106,0.0001433732,0.0000123196,0.0001134188,0.000009449261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002080885,"about_ca_system_score_gemma":0.000002474253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000144888,"about_ca_topic_score_gemma":0.0001618534,"domain_scores_codex":[0.9994801,0.00002164406,0.0001337213,0.0001279585,0.0000713532,0.0001652347],"domain_scores_gemma":[0.9998096,0.0000273728,0.00001689981,0.00008800904,0.000008045648,0.00005002405],"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":[0.0002327083,0.00002644005,0.01875999,0.0009432453,0.0002364398,0.00003429383,0.002321384,0.203459,0.5509936,0.0003865174,0.001547566,0.2210588],"study_design_scores_gemma":[0.0001983928,0.00004523619,0.03465448,0.00002840624,0.00001129449,0.000119588,0.0002141574,0.9603763,0.00362952,0.00009574164,0.0004349849,0.0001919312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9958524,0.000168271,0.002162721,0.00002848118,0.000713053,0.0001628102,0.00000116095,0.0002164835,0.0006946793],"genre_scores_gemma":[0.9993477,0.000009872157,0.0002800619,0.00003873983,0.0001642322,0.000002408448,0.000001055307,0.00002080604,0.0001351641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7569173,"threshold_uncertainty_score":0.4033805,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3120076703","doi":"10.1007/s00521-020-05541-y","title":"Patchwise dictionary learning for video forest fire smoke detection in wavelet domain","year":2021,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Block (permutation group theory); Pattern recognition (psychology); Pixel; Feature (linguistics); Wavelet; Computer vision; Smoke; Process (computing); Mathematics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.00967830815352519,"gpt":0.2247843299505702,"spread":0.215106021797045,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008784243,0.00008854012,0.000106328,0.00004225552,0.0002355015,0.00003311734,0.00003460837,0.00005060519,0.000002066868],"category_scores_gemma":[0.00001517094,0.000100452,0.00004058355,0.0002293709,0.00001302607,0.00004099148,0.0000174979,0.000174582,0.000002963011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003415213,"about_ca_system_score_gemma":0.000006029896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002899124,"about_ca_topic_score_gemma":0.0001058328,"domain_scores_codex":[0.9994025,0.00002673689,0.0001947184,0.0001788594,0.00005444078,0.0001427469],"domain_scores_gemma":[0.9996835,0.0001185911,0.00002702088,0.00009517738,0.00003353656,0.00004214852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001743066,0.00005484779,0.01180478,0.0003215169,0.00003068495,0.000007614005,0.0005950999,0.2752961,0.01402206,0.0006873343,0.0002009197,0.6969616],"study_design_scores_gemma":[0.0003283747,0.00002263332,0.02609101,0.00002494739,0.00000485728,0.00006302029,0.0002522137,0.9378322,0.0007989847,0.0003133532,0.03413573,0.0001326906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8858582,0.0002682563,0.1127211,0.0001440019,0.0001685582,0.0002722421,0.000004736019,0.0003032421,0.0002596575],"genre_scores_gemma":[0.9991882,0.0000199292,0.0003517183,0.00004180917,0.0001873636,0.0001268627,0.00002454134,0.0000184414,0.00004115277],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.696829,"threshold_uncertainty_score":0.4096315,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4283755424","doi":"10.1016/j.firesaf.2022.103629","title":"RGB image-based hybrid model for automatic prediction of flashover in compartment fires","year":2022,"lang":"en","type":"article","venue":"Fire Safety Journal","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"National Research Council","keywords":"RGB color model; Artificial intelligence; Process (computing); Arc flash; Artificial neural network; Computer science; Computer vision; Test data; Simulation; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01344377607871202,"gpt":0.2109344355085827,"spread":0.1974906594298707,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004798118,0.0001272636,0.0002485566,0.000137506,0.0001918232,0.00001760549,0.0001312617,0.00002687234,0.0002248158],"category_scores_gemma":[0.00001993972,0.0001332104,0.0001535003,0.0001376661,0.00001593121,0.0001136044,0.00001955035,0.0002804538,0.000004203311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004179094,"about_ca_system_score_gemma":0.00007003622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006297424,"about_ca_topic_score_gemma":0.000006956053,"domain_scores_codex":[0.9986895,0.00006541959,0.0006234465,0.0001033797,0.0003050226,0.0002131717],"domain_scores_gemma":[0.9995745,0.00006341204,0.0001147679,0.000136643,0.00004359534,0.00006703384],"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":[0.00009167899,0.00006006753,0.0002612103,0.0001334709,0.00003680676,0.000006450473,0.0003523254,0.983426,0.001036242,0.00001102284,0.009617938,0.004966727],"study_design_scores_gemma":[0.001528025,0.0001068889,0.003184316,0.00005770346,0.00001409808,0.00009140654,0.00009872197,0.9893213,0.0005313524,0.0000875156,0.004874071,0.0001045889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6470746,0.0005455168,0.3450289,0.0006442363,0.002985863,0.00111419,0.001320438,0.0003852155,0.0009011019],"genre_scores_gemma":[0.9978787,0.00001529919,0.001762839,0.00003471742,0.00007770098,0.00007338255,0.00004029374,0.00002883123,0.00008821703],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3508042,"threshold_uncertainty_score":0.5432163,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3139146945","doi":"10.18280/i2m.200108","title":"Forest Fire Detection Using Wireless Multimedia Sensor Networks and Image Compression","year":2021,"lang":"en","type":"article","venue":"Instrumentation Mesure Métrologie","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; Wireless sensor network; Image compression; Real-time computing; Data transmission; Energy consumption; Data compression; Wireless; Image sensor; Base station; Fire detection; Image processing; Computer network; Artificial intelligence; Telecommunications; Electrical engineering; Engineering; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01562378216302365,"gpt":0.2449331036651284,"spread":0.2293093215021047,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001334445,0.0001648691,0.0001890972,0.0000537852,0.0001494131,0.00007299873,0.00004648415,0.0001695049,0.00002759474],"category_scores_gemma":[0.00002801529,0.0001682509,0.00004965242,0.0001816572,0.00004401477,0.0002177067,0.00002726491,0.0001985003,0.000008393478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008356323,"about_ca_system_score_gemma":0.00001268785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004432595,"about_ca_topic_score_gemma":0.0001067925,"domain_scores_codex":[0.9990282,0.0001152975,0.0002782607,0.0002174937,0.0001427889,0.0002179743],"domain_scores_gemma":[0.9995782,0.00007340709,0.00005887648,0.0001483011,0.00006784316,0.00007333235],"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":[0.00008542104,0.00003455775,0.02265675,0.0001682404,0.00014036,0.00007456226,0.0004624727,0.2224133,0.5320107,0.00000784143,0.0001654389,0.2217803],"study_design_scores_gemma":[0.0006227203,0.00002547594,0.02938229,0.00003228244,0.00002540396,0.00009448726,0.0002659727,0.9309174,0.03818614,0.00001323685,0.0002672222,0.0001673329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.941706,0.0002711365,0.05601187,0.00005872641,0.0013218,0.0001635588,0.000008281239,0.0003439345,0.0001146715],"genre_scores_gemma":[0.997138,0.0001285553,0.00242762,0.00005009348,0.00015284,0.00001550569,0.00003447635,0.00002822657,0.00002469392],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7085041,"threshold_uncertainty_score":0.6861075,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2742600586","doi":"10.1016/j.firesaf.2017.06.001","title":"Fire Safety Science: Proceedings of the 12th International Symposium","year":2017,"lang":"en","type":"article","venue":"Fire Safety Journal","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":21,"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":"Fire safety; Engineering; Forensic engineering; Poison control; Aeronautics; Medical emergency; Medicine; Civil engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.007072957785251548,"gpt":0.2190202791897978,"spread":0.2119473214045462,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008379658,0.0001644226,0.0002054407,0.00005514469,0.001508852,0.0003070559,0.001451214,0.0000918216,0.0002500876],"category_scores_gemma":[0.0001628787,0.0001190388,0.0001837989,0.0001700108,0.0003018872,0.0007550523,0.0001705319,0.0004886237,0.00002521537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000284399,"about_ca_system_score_gemma":0.00008622545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000174556,"about_ca_topic_score_gemma":0.000004946847,"domain_scores_codex":[0.9982905,0.000007817745,0.0005225823,0.0001635055,0.000714607,0.0003009891],"domain_scores_gemma":[0.9988675,0.00001770886,0.0003284042,0.0002917093,0.0003561655,0.0001385547],"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":[0.001192721,0.0003906658,0.1170744,0.0009021912,0.001384428,0.00006408905,0.01615694,0.02563475,0.2682191,0.00973265,0.06137373,0.4978743],"study_design_scores_gemma":[0.002023101,0.0001008233,0.5537481,0.0008898687,0.00004944988,0.001792001,0.0007398744,0.1055792,0.01733164,0.000358611,0.3167676,0.0006197519],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7496802,0.0002307898,0.0003518354,0.009076185,0.0221144,0.000453906,0.00008734322,0.0002296765,0.2177757],"genre_scores_gemma":[0.9978484,0.0002710649,0.0000793721,0.00003525772,0.0007261428,0.000002715147,7.155051e-7,0.00002357855,0.001012788],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4972546,"threshold_uncertainty_score":0.999791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401379778","doi":"10.1109/jiot.2024.3439228","title":"A Trustable Federated Learning Framework for Rapid Fire Smoke Detection at the Edge in Smart Home Environments","year":2024,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Smoke; Enhanced Data Rates for GSM Evolution; Edge computing; Fire detection; Human–computer interaction; Multimedia; Artificial intelligence; Architectural engineering; Engineering; Waste management","retraction":null,"screen_n_in":null,"score":{"opus":0.0119055592556682,"gpt":0.2223884978677452,"spread":0.210482938612077,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006017432,0.0001427233,0.0001888512,0.000123861,0.0001155422,0.0001769425,0.0001341942,0.0001465861,0.0001457975],"category_scores_gemma":[0.00006015417,0.0001121916,0.0001471648,0.0001388657,0.0000249477,0.0002377481,0.0000193944,0.0008494633,0.00003611037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003391927,"about_ca_system_score_gemma":0.000009903686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006483355,"about_ca_topic_score_gemma":0.00002222678,"domain_scores_codex":[0.998976,0.00006442118,0.000418469,0.0001322516,0.0001812009,0.0002276544],"domain_scores_gemma":[0.9996087,0.0001673462,0.00007913823,0.00007859391,0.00001517283,0.00005106651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001114813,0.0001365618,0.002822974,0.001629058,0.001635173,0.0001901085,0.0372937,0.145191,0.2576565,0.0001322535,0.01353166,0.5386661],"study_design_scores_gemma":[0.0005435068,0.0002639979,0.0006943292,0.001021347,0.00003200166,0.0005148644,0.0005149045,0.8176681,0.08843451,0.0004103293,0.08963986,0.0002622666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8699671,0.001858722,0.1222436,0.0001273274,0.005202725,0.0001847894,0.000002361207,0.0001089288,0.0003044531],"genre_scores_gemma":[0.9973276,0.0001705669,0.00011433,0.00003502479,0.0002071034,0.00001933244,0.000001265459,0.00004322764,0.002081496],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6724771,"threshold_uncertainty_score":0.457504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3204384816","doi":"10.18280/ts.380420","title":"Thermal Fault Diagnosis of Electrical Equipment in Substations Based on Image Fusion","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Fault (geology); Electrical equipment; Artificial intelligence; Convolutional neural network; Computer science; Image (mathematics); Infrared; Fusion; Thermal; Artificial neural network; Segmentation; Computer vision; Image fusion; Pattern recognition (psychology); Engineering; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01103750040826883,"gpt":0.2181308174452485,"spread":0.2070933170369796,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001456012,0.00009988473,0.0001428252,0.0001165511,0.00002711692,0.00001329398,0.0000529081,0.00004287234,0.0009278374],"category_scores_gemma":[0.00001418978,0.00009979975,0.00006594072,0.0002929873,0.00001011359,0.00004312708,0.000006070016,0.00009996626,0.00002160824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009661201,"about_ca_system_score_gemma":0.00002263638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001564381,"about_ca_topic_score_gemma":0.00003651947,"domain_scores_codex":[0.9990819,0.00006570255,0.0003183939,0.0001231361,0.0002474733,0.0001634453],"domain_scores_gemma":[0.9996818,0.0001147108,0.00002652177,0.00009521934,0.00003778422,0.0000439453],"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":[0.0001173114,0.0008673015,0.007036487,0.0001906455,0.00006019022,0.0001067907,0.001264273,0.4841636,0.4740078,0.0003369958,0.001863654,0.02998494],"study_design_scores_gemma":[0.001538996,0.0001825325,0.05057504,0.0001055268,0.00001298468,0.000001572222,0.0001236534,0.7398183,0.2057396,0.000009408043,0.001694248,0.0001981479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885946,0.00007979378,0.007901214,0.0002345884,0.0001498486,0.0002153407,0.00002102776,0.00008896321,0.002714621],"genre_scores_gemma":[0.9994527,0.00001563017,0.0002625113,0.00008714638,0.00003550643,0.00008431799,0.00002592,0.00001442957,0.00002185211],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2682682,"threshold_uncertainty_score":0.9999855,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4360616779","doi":"10.1016/j.jag.2023.103257","title":"A satellite imagery smoke detection framework based on the Mahalanobis distance for early fire identification and positioning","year":2023,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Smoke; Environmental science; Remote sensing; Pixel; Computer science; Artificial intelligence; Meteorology; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.01234881451070842,"gpt":0.2140173702149092,"spread":0.2016685557042008,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004905347,0.00009459119,0.00009425083,0.0001822492,0.0001392876,0.000222646,0.0000802267,0.0000682969,0.000006167662],"category_scores_gemma":[0.0000743672,0.00007985552,0.00004668657,0.000201534,0.00001811689,0.0004392649,0.000006959812,0.0001380965,0.00001156775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003634427,"about_ca_system_score_gemma":0.000009535242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003169492,"about_ca_topic_score_gemma":0.000003996664,"domain_scores_codex":[0.9990755,0.00001260602,0.0004582949,0.00006949937,0.0002918507,0.00009226493],"domain_scores_gemma":[0.9992263,0.0002011077,0.0002364579,0.00007503096,0.0002251709,0.00003593328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001409946,0.0000469792,0.005168799,0.0004314627,0.0003287671,0.000004829026,0.008446092,0.171715,0.01284131,0.02421595,0.0008283108,0.7745626],"study_design_scores_gemma":[0.0004942716,0.00005207791,0.2045898,0.0001225889,0.00001209327,0.00001048508,0.0002987254,0.7824643,0.003553661,0.002393532,0.005889388,0.0001190344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8500532,0.00002991093,0.1471979,0.001192969,0.0007988553,0.0002849569,0.00001960584,0.0001006891,0.0003219822],"genre_scores_gemma":[0.9988636,0.0001337142,0.00045343,0.0002774243,0.0001503427,0.00003116038,0.00004750559,0.0000110307,0.00003177173],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7744435,"threshold_uncertainty_score":0.3256414,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2901133594","doi":"10.1139/juvs-2018-0022","title":"Wildfire early warning system based on wireless sensors and unmanned aerial vehicle","year":2018,"lang":"en","type":"article","venue":"Journal of Unmanned Vehicle Systems","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"University of Technology Sydney","keywords":"Warning system; Environmental science; Bluetooth; Early warning system; Bluetooth Low Energy; Computer science; Remote sensing; Meteorology; Wireless; Geography; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.007093146641072555,"gpt":0.195747008429172,"spread":0.1886538617880994,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001033343,0.0003663451,0.0007764964,0.0004103935,0.0002810903,0.0002177076,0.0002628678,0.0002809564,0.000007931243],"category_scores_gemma":[0.00004719287,0.0003256279,0.0001889938,0.0004001659,0.00009560969,0.0003199072,0.00002276596,0.0004766759,0.00009548607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002991288,"about_ca_system_score_gemma":0.00004820063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009935927,"about_ca_topic_score_gemma":0.000008330694,"domain_scores_codex":[0.997105,0.0003164278,0.001141898,0.0002684705,0.0006740101,0.0004942048],"domain_scores_gemma":[0.9984252,0.0001627976,0.0004675464,0.0003507143,0.0002521756,0.0003415667],"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":[0.01054651,0.0007851522,0.04388335,0.0106439,0.003372652,0.002628566,0.01952709,0.4294141,0.4211749,0.002390884,0.02452843,0.0311044],"study_design_scores_gemma":[0.003709423,0.001673566,0.008054377,0.002213859,0.0000710076,0.000496678,0.001712431,0.9699389,0.005418811,0.000003163412,0.006141585,0.0005661601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913823,0.0002945642,0.000810168,0.0001085402,0.005502942,0.0003282464,0.00001124001,0.0003216878,0.001240284],"genre_scores_gemma":[0.9971828,0.00001213458,0.00003899721,0.0000301898,0.002487779,0.000009303009,0.00000135761,0.00009911972,0.0001382833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5405248,"threshold_uncertainty_score":0.9999196,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406322613","doi":"10.1109/jstars.2025.3528652","title":"Edge Computing-Based Real-Time Forest Fire Detection Using UAV Thermal and Color Images","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Fire Detection and Safety Systems","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Aeronautical Science Foundation of China; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Computer vision; Artificial intelligence; Remote sensing; Enhanced Data Rates for GSM Evolution; Environmental science; Geology","retraction":null,"screen_n_in":null,"score":{"opus":0.01180441617033151,"gpt":0.2142651961308161,"spread":0.2024607799604846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002282156,0.0001248887,0.0002359162,0.0002097609,0.0001639772,0.00006240218,0.00003538482,0.000119551,8.340973e-7],"category_scores_gemma":[0.00003079385,0.0001226653,0.00002964591,0.0005173621,0.00003691922,0.00006084783,0.000007772013,0.0002769876,2.23676e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000685925,"about_ca_system_score_gemma":0.00006283379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000914946,"about_ca_topic_score_gemma":0.0001908216,"domain_scores_codex":[0.9991763,0.00003611432,0.000418417,0.0001033638,0.0001104953,0.0001553457],"domain_scores_gemma":[0.9994948,0.00009199981,0.0001120223,0.00007647373,0.0001825962,0.00004208865],"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":[0.00004909932,0.00001138494,0.0005654779,0.0001528145,0.00005848692,0.00001211539,0.0002026914,0.2141373,0.606885,0.00001634621,0.00002591198,0.1778835],"study_design_scores_gemma":[0.0005448142,0.00002547644,0.04992782,0.0002014302,0.00002257397,0.00004215587,0.00003820725,0.9310349,0.01767088,0.00004553045,0.0003397393,0.00010645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9494877,0.0001000605,0.0494364,0.00008473187,0.0003678756,0.0001356726,0.000001295695,0.00005388636,0.000332347],"genre_scores_gemma":[0.9826339,0.00006225903,0.01704787,0.00003656345,0.0001662922,4.323739e-8,0.000001140114,0.00001431118,0.0000375647],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7168977,"threshold_uncertainty_score":0.5002145,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}