{"meta":{"query_hash":"fc855e8bc5ef","filters":{"venue":"Data"},"cohort_total":52,"direct_labels_cover":0,"predictions_cover":52,"exported":52,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/fc855e8bc5ef","api":"https://metacan.xera.ac/api/v1/cohort?venue=Data"},"results":[{"id":"W2339673439","doi":"10.3390/data1010004","title":"Open Access Article Processing Charges (OA APC) Longitudinal Study 2015 Preliminary Dataset","year":2016,"lang":"en","type":"article","venue":"Data","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Merge (version control); Computer science; Download; Data science; Metadata; Open data; Open science; World Wide Web; Census; Data access; Longitudinal data; Publishing; Library science; Information retrieval; Political science; Data mining; Database; Sociology","score_opus":0.9198208547898142,"score_gpt":0.7177078284484214,"score_spread":0.20211302634139283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339673439","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9071911,0.0019968657,0.015646996,0.016999364,0.0010137269,0.0029776082,0.051653143,0.00010251908,0.0024186908],"genre_scores_gemma":[0.99728614,0.000059090402,0.0005239921,0.00013015923,0.00011974149,0.000029475472,0.0007596269,0.00001403604,0.0010777495],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99052376,0.0002944613,0.00066985475,0.00171475,0.0061136824,0.0006834905],"domain_scores_gemma":[0.9913657,0.002153398,0.00028512307,0.0046508675,0.0010632621,0.00048165678],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["bibliometrics","scholarly_communication","open_science","insufficient_payload"],"category_scores_codex":[0.026418641,0.00017065437,0.00032121828,0.011375601,0.00041746697,0.016468562,0.036098868,0.000056177898,0.0023087736],"category_scores_gemma":[0.027902042,0.00008971963,0.00002484797,0.064505234,0.00016614515,0.0139271645,0.047221996,0.00015308936,0.001971128],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060634768,0.00045867814,0.3188733,0.0000023892717,0.000009551337,0.000034240355,0.00002434971,3.4333945e-7,0.0001128273,0.000015584452,0.4815855,0.1988226],"study_design_scores_gemma":[0.0012332553,0.0003824532,0.8229999,0.000021681513,0.000017782637,0.000013070595,0.00037565903,0.0023742972,0.00035145556,0.0013597714,0.17058787,0.00028281423],"about_ca_topic_score_codex":0.0003576526,"about_ca_topic_score_gemma":0.00012646311,"teacher_disagreement_score":0.5041266,"about_ca_system_score_codex":0.000053021984,"about_ca_system_score_gemma":0.00027630705,"threshold_uncertainty_score":0.9998645},"labels":[],"label_agreement":null},{"id":"W2589049976","doi":"10.3390/data2010011","title":"Erratum: Morrison, H., et al. Open Access Article Processing Charges (OA APC) Longitudinal Study 2015 Preliminary Dataset","year":2017,"lang":"en","type":"erratum","venue":"Data","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Data science","score_opus":0.27674736986145604,"score_gpt":0.4640049221509289,"score_spread":0.18725755228947288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589049976","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077178533,0.022628834,0.62004197,0.098509446,0.10106397,0.01448072,0.111088574,0.0018380318,0.02957669],"genre_scores_gemma":[0.049643956,0.0022879387,0.1304263,0.027321758,0.009680905,0.0016223291,0.62871045,0.0009076715,0.14939868],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944531,0.00025314477,0.00068119087,0.0028595196,0.0010122037,0.0007408942],"domain_scores_gemma":[0.98532796,0.000057884834,0.0008217423,0.013354509,0.00017817537,0.00025972127],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.0023460148,0.00057894684,0.00075417885,0.0001843238,0.0007206601,0.011985728,0.051461473,0.00022973905,0.000054031738],"category_scores_gemma":[0.00040596936,0.0005397542,0.000038600945,0.00026502396,0.000091162394,0.015546872,0.06528537,0.0013965984,0.00015690071],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019593985,0.00040176598,0.0011903791,0.000090729875,0.00006193136,0.0002272057,0.00024312973,0.000013651842,0.0000013974332,0.00004454789,0.98678833,0.0109173395],"study_design_scores_gemma":[0.0005709811,0.00015879745,0.006518514,0.00037543933,0.00009800305,0.00004619193,0.0000596369,0.15806323,0.0000031537693,0.00033043692,0.833011,0.00076465483],"about_ca_topic_score_codex":0.0016515447,"about_ca_topic_score_gemma":0.00076403975,"teacher_disagreement_score":0.5176219,"about_ca_system_score_codex":0.00006402802,"about_ca_system_score_gemma":0.0010342752,"threshold_uncertainty_score":0.9997054},"labels":[],"label_agreement":null},{"id":"W2606849632","doi":"10.3390/data2020013","title":"Open Access Article Processing Charges (OA APC) Longitudinal Study 2016 Dataset","year":2017,"lang":"en","type":"article","venue":"Data","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Metadata; Subject (documents); Computer science; Inclusion (mineral); Work (physics); Business model; World Wide Web; Library science; Information retrieval; Accounting; Business; Marketing; Sociology; Social science","score_opus":0.955974598263469,"score_gpt":0.7534249884478179,"score_spread":0.20254960981565107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606849632","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.923103,0.0011861405,0.004831912,0.009537771,0.0015170462,0.0026604342,0.044705052,0.00006522885,0.012393464],"genre_scores_gemma":[0.9970634,0.00005313296,0.00047665325,0.00011112133,0.0001465011,0.000017530385,0.00093867775,0.000011223806,0.0011817467],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99137086,0.00017098826,0.0005620095,0.0015878113,0.005684681,0.00062366336],"domain_scores_gemma":[0.9883916,0.00084950204,0.00049158686,0.008868758,0.0009725697,0.00042601264],"candidate_categories":["metaresearch","bibliometrics","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"category_scores_codex":[0.029944496,0.00015261883,0.00032632737,0.008563331,0.0017310827,0.0882973,0.07266116,0.00005011958,0.0016053305],"category_scores_gemma":[0.04489435,0.00009843582,0.000024505816,0.026363693,0.00022242645,0.019269064,0.07449153,0.0002244199,0.0016917343],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018300228,0.00032653648,0.4682981,0.00000214672,0.0000093396175,0.00003320608,0.000021744929,4.090357e-7,0.000028351464,0.000021405494,0.38069135,0.15054913],"study_design_scores_gemma":[0.00067754945,0.00007600648,0.837412,0.000009098822,0.000010699488,0.0000041472413,0.00022864724,0.0048082205,0.0001054889,0.0010155636,0.15547436,0.0001782315],"about_ca_topic_score_codex":0.0018548504,"about_ca_topic_score_gemma":0.00051905785,"teacher_disagreement_score":0.3691139,"about_ca_system_score_codex":0.000031812084,"about_ca_system_score_gemma":0.00029951776,"threshold_uncertainty_score":0.9995685},"labels":[],"label_agreement":null},{"id":"W2615310803","doi":"10.3390/data3010008","title":"RAE: The Rainforest Automation Energy Dataset for Smart Grid Meter Data Analysis","year":2018,"lang":"en","type":"article","venue":"Data","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Thermostat; Smart meter; Smart grid; Automation; Electricity meter; Computer science; Test data; Real-time computing; Energy (signal processing); Electricity; Engineering; Power (physics); Electrical engineering","score_opus":0.059184727489375526,"score_gpt":0.2833796318320338,"score_spread":0.22419490434265826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2615310803","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042425792,0.00012846911,0.8305111,0.00068453053,0.0019038422,0.00026184256,0.16440693,0.00036169105,0.001317327],"genre_scores_gemma":[0.04121588,0.00006346094,0.009541056,0.00065971154,0.0014691199,0.000058318336,0.9467875,0.000042966716,0.00016200394],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989087,0.000025482415,0.0002451071,0.00038639197,0.00019105957,0.00024323756],"domain_scores_gemma":[0.9939665,0.00011454113,0.000043263946,0.0058062733,0.000024167599,0.000045213677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006316231,0.00014533717,0.00015828002,0.00013902977,0.00011777519,0.0001265948,0.0026644054,0.000039055252,0.00017065086],"category_scores_gemma":[0.00011451515,0.00011052196,0.000028606679,0.00047907574,0.00005548953,0.00071648863,0.0015178791,0.000045622397,0.000081942286],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048735587,0.000006761422,0.000101861246,0.000012570087,0.00076969503,7.5050735e-7,0.000013114346,0.007900079,0.00001613161,0.00047048434,0.98684466,0.0038590317],"study_design_scores_gemma":[0.00009180711,0.000005266448,0.0009856329,0.000001679205,0.0003149365,4.119387e-7,0.0000064416213,0.4783677,0.00005575451,0.000018361505,0.5200741,0.00007788376],"about_ca_topic_score_codex":0.0003395746,"about_ca_topic_score_gemma":0.0037181277,"teacher_disagreement_score":0.82097006,"about_ca_system_score_codex":0.000024097983,"about_ca_system_score_gemma":0.0000096875765,"threshold_uncertainty_score":0.49511728},"labels":[],"label_agreement":null},{"id":"W2769697870","doi":"10.3390/data2040038","title":"Antibody Exchange: Information Extraction of Biological Antibody Donation and a Web-Portal to Find Donors and Seekers","year":2017,"lang":"en","type":"article","venue":"Data","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Killam Trusts; National Institute of Mental Health; University of Oxford","keywords":"Computer science; Donation; Web resource; Resource (disambiguation); World Wide Web; Political science; Law","score_opus":0.045460320271140844,"score_gpt":0.36926028536753175,"score_spread":0.3237999650963909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769697870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961162,0.0001963734,0.0023588717,0.00038322303,0.00009775016,0.00009110865,0.00041368976,0.00000744959,0.0003352868],"genre_scores_gemma":[0.99199325,0.0013471002,0.0016800922,0.00008416025,0.000058860536,0.000002448961,0.004801308,0.0000026052453,0.000030196774],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.999509,0.000016319464,0.00013089155,0.00018303588,0.00006707927,0.00009367578],"domain_scores_gemma":[0.99936545,0.000011352847,0.0001179684,0.00042299207,0.00003064739,0.000051605042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002354821,0.00006957326,0.000091484006,0.00003528468,0.00009907541,0.00004581004,0.0002100113,0.00013555997,0.0000073041056],"category_scores_gemma":[0.00044153337,0.000056469293,0.000009814706,0.000020681022,0.0001585324,0.000030466745,0.00039862955,0.000044120403,0.000002209536],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011781741,0.000034098033,0.06696552,0.00005315076,0.000035319128,0.0000025431762,0.00011397261,3.917883e-7,0.78304607,0.00003771445,0.0033576926,0.14623572],"study_design_scores_gemma":[0.0006408893,0.0003934691,0.78361106,0.000029780027,0.000017810176,0.00003848526,0.00026679778,0.00042149806,0.0068953466,0.000024837982,0.207488,0.00017202679],"about_ca_topic_score_codex":0.00007949224,"about_ca_topic_score_gemma":0.000039204748,"teacher_disagreement_score":0.7761507,"about_ca_system_score_codex":0.0000016272999,"about_ca_system_score_gemma":0.000017956914,"threshold_uncertainty_score":0.2302751},"labels":[],"label_agreement":null},{"id":"W2896324462","doi":"10.3390/data3040042","title":"Tamarisk and Russian Olive Occurrence and Absence Dataset Collected in Select Tributaries of the Colorado River for 2017","year":2018,"lang":"en","type":"article","venue":"Data","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Geological Survey; Walton Family Foundation; McMaster University","keywords":"Riparian zone; Tributary; Tamarix; Geography; Range (aeronautics); Land cover; Vegetation (pathology); Drainage basin; Invasive species; Structural basin; Habitat; Species distribution; Ecology; Forestry; Hydrology (agriculture); Land use; Cartography; Biology; Geology","score_opus":0.021090512430999808,"score_gpt":0.2638277033190783,"score_spread":0.2427371908880785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896324462","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91708004,0.000092302245,0.00011325433,0.00015226503,0.0001237987,0.00082211266,0.08151094,0.000007893942,0.00009739751],"genre_scores_gemma":[0.9975342,0.000034838842,0.0004426008,0.00005442986,0.000013359794,0.000014398489,0.0018869045,0.0000036053257,0.000015666845],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99916726,0.00007727079,0.00014130933,0.0003251384,0.00011880974,0.00017019341],"domain_scores_gemma":[0.9989824,0.00021794808,0.000099187426,0.0006548772,0.000005456731,0.00004007808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039043085,0.000086206244,0.00014245152,0.000017477918,0.00014821254,0.000029237604,0.0005792851,0.00004160804,0.00004872933],"category_scores_gemma":[0.00037042555,0.00006212393,0.0000055307855,0.0002248531,0.00077265524,0.0003737054,0.0008386859,0.000063595515,0.000015623402],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020516259,0.00009835758,0.453381,0.00012116207,0.0000255133,0.000004269021,0.0013372836,0.0000028090735,0.0025628118,0.000102388854,0.5383161,0.0038431773],"study_design_scores_gemma":[0.0010488817,0.00027986968,0.8692052,0.000088373155,0.000029649515,0.000022205712,0.000055452645,0.03193218,0.0011647351,0.00022693299,0.095722064,0.00022444734],"about_ca_topic_score_codex":0.0035240157,"about_ca_topic_score_gemma":0.010220938,"teacher_disagreement_score":0.442594,"about_ca_system_score_codex":0.000029151473,"about_ca_system_score_gemma":0.000021910779,"threshold_uncertainty_score":0.5703524},"labels":[],"label_agreement":null},{"id":"W2906021381","doi":"10.3390/data4010002","title":"A Mobile Air Pollution Monitoring Data Set","year":2018,"lang":"en","type":"article","venue":"Data","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"Ministère de l’Environnement, de la Protection de la nature et des Parcs","keywords":"Environmental science; Nitrogen dioxide; Air pollution; Pollution; Pollutant; Particulates; Sampling (signal processing); Ozone; Meteorology; Computer science; Geography; Chemistry; Telecommunications","score_opus":0.21960301259583265,"score_gpt":0.4140672553854713,"score_spread":0.19446424278963864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906021381","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88461006,0.0008576839,0.018686758,0.01853512,0.004185767,0.0019409442,0.03569238,0.0007322227,0.03475909],"genre_scores_gemma":[0.9880745,0.00008013931,0.0062503633,0.0024292243,0.0006751766,0.0000039781044,0.0021076708,0.000009529773,0.0003694649],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905884,0.00004082806,0.000121049474,0.00034713882,0.0001930128,0.00023911278],"domain_scores_gemma":[0.9975909,0.0000152144285,0.000042066713,0.0022241056,0.0000023925554,0.0001253036],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000621249,0.000060158192,0.00006258287,0.00000968327,0.00018567168,0.000016485488,0.0012641011,0.000039643273,0.00091176806],"category_scores_gemma":[0.00010088545,0.00005548835,0.0000041607004,0.000115544506,0.00013532187,0.0009237317,0.0023871325,0.00007460846,0.0032982132],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016171252,0.000046478253,0.013127037,0.000015499725,0.000004392281,0.0000022751153,0.00073619373,0.000020813477,0.00028310236,0.00001826358,0.93500096,0.05072883],"study_design_scores_gemma":[0.00010520197,0.00007813785,0.056546822,0.00001420876,0.0000055541777,0.0000033920358,0.00014460139,0.0036422492,0.00023107616,0.0000891001,0.9390539,0.00008573659],"about_ca_topic_score_codex":0.001252384,"about_ca_topic_score_gemma":0.00021181715,"teacher_disagreement_score":0.10346442,"about_ca_system_score_codex":0.000057633726,"about_ca_system_score_gemma":0.000017353002,"threshold_uncertainty_score":0.9983221},"labels":[],"label_agreement":null},{"id":"W2910961990","doi":"10.3390/data4010009","title":"UAV-Based 3D Point Clouds of Freshwater Fish Habitats, Xingu River Basin, Brazil","year":2019,"lang":"en","type":"article","venue":"Data","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Point cloud; Tributary; Habitat; Geography; Amazon rainforest; Drainage basin; Structure from motion; Environmental science; Ecology; Hydrology (agriculture); Geology; Cartography; Biology","score_opus":0.014719297930776285,"score_gpt":0.244877636669857,"score_spread":0.23015833873908073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910961990","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9625997,0.000011882363,0.0017248472,0.002396729,0.00018466086,0.00031654237,0.0018864741,0.00006375356,0.030815393],"genre_scores_gemma":[0.9750693,0.0000034573454,0.020601638,0.0015424665,0.000038126054,6.9320254e-7,0.0014226203,0.000017877457,0.0013038197],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991109,0.000031901534,0.00015296105,0.00033406547,0.00020781367,0.00016240343],"domain_scores_gemma":[0.9983552,0.000046034238,0.000060579787,0.0014764237,0.0000070340866,0.000054703556],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00020250537,0.000085731604,0.00011261583,0.00001681899,0.000048208105,0.000018192124,0.0005396157,0.000043646854,0.0023984667],"category_scores_gemma":[0.000027592769,0.00007447505,0.000027249456,0.000114524526,0.00016428449,0.00014117316,0.00035410066,0.00007965562,0.002200427],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032022795,0.0002274702,0.061883677,0.000034338667,0.000024279896,0.0000051057145,0.00045565853,0.0008273721,0.042869642,0.00007079869,0.8699851,0.023584524],"study_design_scores_gemma":[0.0004089646,0.00003741132,0.09429916,0.000023857994,0.00001935394,0.0000033716935,0.000028920214,0.02030908,0.008261232,0.00017435443,0.87624377,0.00019051906],"about_ca_topic_score_codex":0.001516719,"about_ca_topic_score_gemma":0.0005715804,"teacher_disagreement_score":0.034608413,"about_ca_system_score_codex":0.000029401823,"about_ca_system_score_gemma":0.000012378147,"threshold_uncertainty_score":0.99857646},"labels":[],"label_agreement":null},{"id":"W2946576669","doi":"10.3390/data4020072","title":"Climate Data to Undertake Hygrothermal and Whole Building Simulations Under Projected Climate Change Influences for 11 Canadian Cities","year":2019,"lang":"en","type":"article","venue":"Data","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada; Environment and Climate Change Canada","keywords":"Downscaling; Environmental science; Climate change; Cloud cover; Climate model; Precipitation; Climatology; Global warming; Range (aeronautics); Meteorology; Wind speed; Relative humidity; Snow; Geography; Computer science; Cloud computing; Engineering","score_opus":0.09568365112707507,"score_gpt":0.2932047752567594,"score_spread":0.19752112412968437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946576669","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96906424,0.00021566458,0.007990904,0.0006274839,0.00042462975,0.00097525417,0.020177834,0.0003083589,0.00021565054],"genre_scores_gemma":[0.984753,0.0000664646,0.0072551733,0.00038870284,0.00008451355,0.000028932496,0.0073694647,0.000036562407,0.00001718338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921817,0.000008362368,0.00012774032,0.0002689128,0.00006584294,0.00031096165],"domain_scores_gemma":[0.9990571,0.00004950563,0.00001952597,0.00077093096,0.000019436646,0.00008351333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012001088,0.00011007642,0.00010571539,0.00012393753,0.00013346659,0.00010377136,0.00045730209,0.00005933782,0.000021454589],"category_scores_gemma":[0.000016810098,0.00011406938,0.0000065614117,0.00015280717,0.000012974161,0.00075197825,0.00024404492,0.000048395374,0.0000040553728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012186477,0.000008184521,0.014643816,0.00019691061,0.00004768531,8.389726e-7,0.00026895484,0.9725809,0.00105756,0.0063073277,0.0018378719,0.0030377468],"study_design_scores_gemma":[0.0001997269,0.0000133286285,0.0048384606,0.00007445783,0.000021325126,0.0000014652057,0.0000985493,0.9640844,0.000044270953,0.00007254867,0.030349003,0.0002024986],"about_ca_topic_score_codex":0.004248633,"about_ca_topic_score_gemma":0.104386985,"teacher_disagreement_score":0.10013835,"about_ca_system_score_codex":0.000025639278,"about_ca_system_score_gemma":0.000023946774,"threshold_uncertainty_score":0.9119556},"labels":[],"label_agreement":null},{"id":"W2965110601","doi":"10.3390/data4030114","title":"A New Multi-Temporal Forest Cover Classification for the Xingu River Basin, Brazil","year":2019,"lang":"en","type":"article","venue":"Data","topic":"Fish biology, ecology, and behavior","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Land cover; Geography; Forest cover; Biodiversity; Biodiversity hotspot; Structural basin; Drainage basin; Physical geography; Land use; Remote sensing; Ecology; Cartography; Geology; Geomorphology","score_opus":0.0699151837982141,"score_gpt":0.30990601297656106,"score_spread":0.23999082917834696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965110601","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9686028,0.00006955651,0.019003985,0.005417728,0.0015304969,0.0020574364,0.0017769127,0.0000806821,0.0014604328],"genre_scores_gemma":[0.9817182,0.000013309476,0.00870243,0.0013243085,0.000106883046,0.000025913458,0.0014339291,0.000012792641,0.006662232],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992622,0.000023493472,0.000116005394,0.00033937284,0.00007558819,0.00018330228],"domain_scores_gemma":[0.99896216,0.000105398314,0.00006494745,0.00081895944,0.0000044288468,0.00004411497],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00024040868,0.000080508784,0.00008451342,0.0000086315795,0.000096571,0.00002130451,0.0007564587,0.000083483144,0.0020973673],"category_scores_gemma":[0.0000598748,0.000054058633,0.000026776761,0.00005756459,0.00015178103,0.00022978493,0.00037169384,0.000073185714,0.0027652418],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015976702,0.0000406756,0.79221374,0.0000019267898,0.000004716719,3.4763562e-7,0.000033945737,0.0000050992007,0.0028693092,0.000026400512,0.20061518,0.0041727046],"study_design_scores_gemma":[0.00033661592,0.000031742504,0.66419554,0.0000011388361,0.000014786563,0.0000013818137,0.00002545438,0.0030465964,0.00002445038,0.000032304593,0.3322318,0.00005820699],"about_ca_topic_score_codex":0.0008388745,"about_ca_topic_score_gemma":0.002365337,"teacher_disagreement_score":0.1316166,"about_ca_system_score_codex":0.000041165586,"about_ca_system_score_gemma":0.000017302838,"threshold_uncertainty_score":0.9988148},"labels":[],"label_agreement":null},{"id":"W2981217933","doi":"10.3390/data4040141","title":"Capacity Allocation of Game Tickets Using Dynamic Pricing","year":2019,"lang":"en","type":"article","venue":"Data","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Queen's University","keywords":"Ticket; Revenue; Dynamic pricing; Football; Business; Advertising; Club; Sequential game; Microeconomics; Game theory; Marketing; Economics; Computer science; Computer security","score_opus":0.10824663046319602,"score_gpt":0.26262881179176467,"score_spread":0.15438218132856865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981217933","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9920582,0.00021281921,0.004772801,0.000049335482,0.00020710635,0.000074398,0.0004595315,0.0000060769607,0.0021596872],"genre_scores_gemma":[0.9986729,0.000078251076,0.0007367142,0.000041846386,0.000019747882,3.113249e-7,0.00025748354,0.000007800635,0.00018493412],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993725,0.0000017250616,0.00028624773,0.00021144899,0.000023839691,0.00010427475],"domain_scores_gemma":[0.99900335,0.000009143015,0.00022836507,0.00072296115,0.000016271453,0.000019898374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031785766,0.00005378248,0.00016716981,0.00008154857,0.000016662825,0.000016661787,0.0002761798,0.000032486747,0.00032951322],"category_scores_gemma":[0.000021256164,0.000060675335,0.000019095372,0.00011267227,0.00001730084,0.00025959048,0.00009766228,0.00005134892,0.0001911405],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015286298,0.00015019545,0.9069393,0.00029177216,0.0001155089,0.0000014163513,0.00064473314,0.008844257,0.0015777621,0.07802104,0.0005710817,0.0028276201],"study_design_scores_gemma":[0.00012887447,0.000011626721,0.07843235,0.000019392042,0.000004898983,0.0000013817245,0.000013881748,0.9097524,0.00005357524,0.0009020412,0.010581819,0.00009771183],"about_ca_topic_score_codex":0.0005175218,"about_ca_topic_score_gemma":0.000029581743,"teacher_disagreement_score":0.9009082,"about_ca_system_score_codex":0.00003085219,"about_ca_system_score_gemma":0.0000112754005,"threshold_uncertainty_score":0.36079386},"labels":[],"label_agreement":null},{"id":"W2999668563","doi":"10.3390/data5010008","title":"A Python Algorithm for Shortest-Path River Network Distance Calculations Considering River Flow Direction","year":2020,"lang":"en","type":"article","venue":"Data","topic":"Wildlife-Road Interactions and Conservation","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Japan Society for the Promotion of Science","keywords":"Dijkstra's algorithm; Shortest path problem; Computer science; Yen's algorithm; Python (programming language); Algorithm; A* search algorithm; Shortest Path Faster Algorithm; Distance; K shortest path routing; Node (physics); Topology (electrical circuits); Mathematics; Graph; Theoretical computer science; Combinatorics; Physics","score_opus":0.04496736249250134,"score_gpt":0.2628186246520804,"score_spread":0.21785126215957906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999668563","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015141601,0.000055292654,0.98025155,0.0016797605,0.00040583024,0.00042621166,0.0011400317,0.00012486876,0.00077484234],"genre_scores_gemma":[0.41175058,0.0000911838,0.5759222,0.0045343186,0.001243118,0.00015744005,0.0055850623,0.00006495867,0.0006511619],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991428,0.000024218762,0.00016571626,0.00037124514,0.00012844623,0.00016756463],"domain_scores_gemma":[0.9993981,0.00007295505,0.00006046253,0.00037978098,0.000011822798,0.00007684708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000098350254,0.00009481276,0.00009254527,0.00000810425,0.0002303877,0.000043144253,0.00020430826,0.000035515404,0.00038158317],"category_scores_gemma":[0.000080685706,0.00009676646,0.000031287655,0.00019408524,0.00008112068,0.00065772503,0.00021624773,0.00007742795,0.00014356461],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035933408,0.00009022946,0.05435158,0.000008921717,0.000054683984,0.000008633219,0.0008991009,0.03654834,0.0004974217,0.00014585817,0.5861752,0.3211841],"study_design_scores_gemma":[0.0001097164,0.000016383194,0.020444194,0.0000089382,0.000019584686,0.000002393685,0.000021933489,0.6563559,0.000012275059,0.00010697459,0.32280993,0.00009176612],"about_ca_topic_score_codex":0.00034266745,"about_ca_topic_score_gemma":0.00020686544,"teacher_disagreement_score":0.6198076,"about_ca_system_score_codex":0.000060983744,"about_ca_system_score_gemma":0.000009744249,"threshold_uncertainty_score":0.41780683},"labels":[],"label_agreement":null},{"id":"W3001314207","doi":"10.3390/data5010009","title":"Does Land Use and Landscape Contribute to Self-Harm? A Sustainability Cities Framework","year":2020,"lang":"en","type":"article","venue":"Data","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Toronto Metropolitan University","funders":"Canadian Institutes of Health Research; Universidade de Lisboa; Ontario Neurotrauma Foundation","keywords":"Urban sprawl; Geography; Harm; Land use; Environmental planning; Ecology; Political science","score_opus":0.049102323924385315,"score_gpt":0.3580557968721043,"score_spread":0.308953472947719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001314207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6238586,0.00032965656,0.0006152103,0.36962527,0.00040130995,0.00077099114,0.0038098714,0.00024265134,0.00034647097],"genre_scores_gemma":[0.9748842,0.0004763018,0.0011959742,0.022458032,0.0005944643,0.00001231309,0.00015962808,0.000008326144,0.00021072899],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989255,0.0001273794,0.0001348669,0.000273559,0.00018459429,0.00035411192],"domain_scores_gemma":[0.99850667,0.0006519133,0.000027655524,0.0003346415,0.000084894345,0.00039423225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000517267,0.000072848445,0.00016578766,0.000014545355,0.00033889542,0.000283013,0.00036429128,0.00007310208,0.00014781934],"category_scores_gemma":[0.005320113,0.000048849495,0.000013511466,0.00014683323,0.00006825197,0.0004048263,0.00036705134,0.00011835567,0.000012338953],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027543054,0.000012783599,0.9288402,0.00016405247,0.000012920711,0.0000086403215,0.014796238,6.3829276e-7,5.720321e-8,0.010208367,0.045365646,0.0005628699],"study_design_scores_gemma":[0.00014053936,0.000016300697,0.14089642,0.000015332149,0.00001198665,1.0387266e-7,0.010701067,0.00007593366,6.7415704e-7,0.0017675344,0.8462703,0.00010375904],"about_ca_topic_score_codex":0.007746945,"about_ca_topic_score_gemma":0.0034772041,"teacher_disagreement_score":0.8009047,"about_ca_system_score_codex":0.000033261345,"about_ca_system_score_gemma":0.00021322836,"threshold_uncertainty_score":0.99886054},"labels":[],"label_agreement":null},{"id":"W3007795301","doi":"10.3390/data5010020","title":"VARTTA: A Visual Analytics System for Making Sense of Real-Time Twitter Data","year":2020,"lang":"en","type":"article","venue":"Data","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Microblogging; Computer science; Social media; Analytics; Visual analytics; Data science; Aggregate (composite); Data analysis; Social media analytics; Visualization; World Wide Web; Data mining","score_opus":0.16399634951439704,"score_gpt":0.38296479146433393,"score_spread":0.2189684419499369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007795301","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029851287,0.000012963757,0.9933121,0.00091378106,0.00009852275,0.00015450716,0.0046935854,0.00013628378,0.00037969637],"genre_scores_gemma":[0.62905544,0.0000644067,0.3123728,0.005331211,0.0010525173,0.0000063446187,0.05157403,0.000089271416,0.00045397252],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851936,0.00005132235,0.00036181798,0.0006146462,0.00026787183,0.00018499824],"domain_scores_gemma":[0.99677473,0.00010812807,0.00018841495,0.0027481387,0.000089327164,0.000091230366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045693104,0.000112920054,0.00023934539,0.000056768688,0.00005435259,0.00017344282,0.0030576228,0.000038840735,0.000014403614],"category_scores_gemma":[0.00023375206,0.00010597931,0.000025016701,0.00044037678,0.000028160706,0.00080982543,0.0035998183,0.00004821237,0.00009317207],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045137218,0.00018658092,0.0004075659,0.0010581943,0.00027645243,0.00008961341,0.000933192,0.00017808305,0.0031299654,0.030732697,0.95852536,0.0044371793],"study_design_scores_gemma":[0.00023761835,0.000038693634,0.000020216201,0.000047845588,0.000048551672,0.0000065448944,0.000082252875,0.9460851,0.00014579676,0.0000137531515,0.05315562,0.000118000564],"about_ca_topic_score_codex":0.000009804568,"about_ca_topic_score_gemma":0.0000018709391,"teacher_disagreement_score":0.945907,"about_ca_system_score_codex":0.000011563181,"about_ca_system_score_gemma":0.0000831193,"threshold_uncertainty_score":0.5681875},"labels":[],"label_agreement":null},{"id":"W3013273263","doi":"10.3390/data5020033","title":"Multiple Regression Analysis and Frequent Itemset Mining of Electronic Medical Records: A Visual Analytics Approach Using VISA_M3R3","year":2020,"lang":"en","type":"article","venue":"Data","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Visual analytics; Medical record; Visualization; Analytics; Health records; Data science; Acute kidney injury; Computer science; Electronic medical record; Medicine; Medical emergency; Data mining; Health care; Internal medicine","score_opus":0.291107209982754,"score_gpt":0.4973330205812096,"score_spread":0.20622581059845557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013273263","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98392177,0.00078161893,0.01218991,0.0007909877,0.0001801222,0.0002584709,0.0014563702,0.00006751939,0.0003532253],"genre_scores_gemma":[0.9947329,0.0007596867,0.00096827926,0.0013042337,0.00023501371,0.0000058481237,0.0019577045,0.000015957188,0.000020385478],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998109,0.00031476837,0.0004142323,0.0005069978,0.0002792799,0.00037574102],"domain_scores_gemma":[0.99864095,0.0003907432,0.0002278978,0.00032151313,0.000047560145,0.0003713533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081361196,0.00018842338,0.0004269743,0.00016657793,0.00015787086,0.000015011106,0.00049882045,0.0002173259,0.00040597955],"category_scores_gemma":[0.00046960695,0.00016928997,0.000086387314,0.0008583852,0.00015849239,0.0002584941,0.00041021197,0.0006775993,0.0000072433536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021611452,0.0023832575,0.71626216,0.00068845466,0.012092668,0.00024423734,0.0032176846,0.012377956,0.16461538,0.00021916338,0.033496324,0.052241564],"study_design_scores_gemma":[0.0010360559,0.000052402884,0.000581652,0.000017467846,0.0016887947,0.000015243763,0.0004189256,0.9543979,0.0036258097,0.000006150523,0.037977647,0.00018194669],"about_ca_topic_score_codex":0.00008386489,"about_ca_topic_score_gemma":0.000041065425,"teacher_disagreement_score":0.94201994,"about_ca_system_score_codex":0.000042439522,"about_ca_system_score_gemma":0.00020511418,"threshold_uncertainty_score":0.69034445},"labels":[],"label_agreement":null},{"id":"W3048760234","doi":"10.3390/data5030072","title":"Data Analysis of Land Use Change and Urban and Rural Impacts in Lagos State, Nigeria","year":2020,"lang":"en","type":"article","venue":"Data","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Geography; Thematic map; Land use; Fragmentation (computing); Land cover; Context (archaeology); Rural area; Land use, land-use change and forestry; Raster graphics; Environmental planning; Socioeconomics; Environmental resource management; Cartography; Environmental science; Political science; Ecology; Agriculture","score_opus":0.0950460244658304,"score_gpt":0.2695755398193921,"score_spread":0.1745295153535617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048760234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99026513,0.00014872944,0.0000021713088,0.00018719383,0.000008425056,0.00007630438,0.009287335,0.0000052522682,0.000019475954],"genre_scores_gemma":[0.9957491,0.00023997977,0.00004845278,0.00019282427,0.000014404193,8.7716364e-7,0.0037494595,0.0000032709515,0.0000016288125],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994303,0.000023485321,0.000115920266,0.00023990656,0.00008384859,0.00010652544],"domain_scores_gemma":[0.99924964,0.00002642113,0.000044654633,0.00059323065,0.0000011291426,0.000084944295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014230714,0.000058640482,0.00015676583,0.000025490632,0.000017685668,0.000041316533,0.00037808286,0.000018734974,0.00014593234],"category_scores_gemma":[0.000019364947,0.000043553893,0.000004754176,0.0002691726,0.000012462456,0.001035076,0.0012988512,0.000028574208,0.000010026301],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012725449,0.00000884127,0.997724,0.00002150148,0.000039177732,0.0000044212657,0.0007027732,0.000009790332,0.00014115685,1.03328084e-7,0.0010691471,0.00026638558],"study_design_scores_gemma":[0.00018120081,0.000016642822,0.96284676,0.000009349635,0.000054377073,4.32777e-7,0.000096088224,0.033457,0.000009863369,0.0000020808207,0.0032621198,0.00006406898],"about_ca_topic_score_codex":0.007047221,"about_ca_topic_score_gemma":0.052012045,"teacher_disagreement_score":0.044964824,"about_ca_system_score_codex":0.0000042374445,"about_ca_system_score_gemma":0.0000018573023,"threshold_uncertainty_score":0.99956495},"labels":[],"label_agreement":null},{"id":"W3081119432","doi":"10.3390/data5040096","title":"ASDToolkit: A Novel MATLAB Processing Toolbox for ASD Field Spectroscopy Data","year":2020,"lang":"en","type":"article","venue":"Data","topic":"Calibration and Measurement Techniques","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; McGill University","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Université de Montréal","keywords":"Remote sensing; Spectroradiometer; Environmental science; Computer science; Reference data; Range (aeronautics); Repeatability; Data processing; Optics; Reflectivity; Mathematics; Materials science; Geography; Data mining; Statistics; Physics","score_opus":0.21837982779178816,"score_gpt":0.32776696791963045,"score_spread":0.10938714012784229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081119432","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013673806,0.00019490893,0.99124104,0.002194951,0.000104073035,0.0003116965,0.0024828273,0.00085651973,0.0024772289],"genre_scores_gemma":[0.30918753,0.00018092262,0.6392742,0.011685936,0.0021111153,0.000109749475,0.037020307,0.00020303648,0.00022724314],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993113,0.0000031171248,0.00015119444,0.00026997895,0.00011981586,0.00014455647],"domain_scores_gemma":[0.9990138,0.00002242158,0.000020198091,0.0008659289,0.00001649512,0.00006117559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012799255,0.0000951776,0.00010702184,0.000019590023,0.00003526979,0.00012664952,0.00089303014,0.000044937966,0.00008014773],"category_scores_gemma":[0.00014977994,0.0000964127,0.000011797266,0.00009716023,0.0000066109474,0.00067871186,0.0002230131,0.00009170408,0.000014541379],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001920253,0.000019622772,0.000024887897,0.00024110283,0.000018260913,9.2661827e-7,0.00007613545,0.000014888944,0.13198161,0.0002787735,0.852686,0.014638606],"study_design_scores_gemma":[0.00024667807,0.00002999959,0.000015933489,0.000031791493,0.000019832169,0.0000014947052,0.000025125752,0.2653397,0.061239123,0.00002572063,0.6728768,0.00014782883],"about_ca_topic_score_codex":0.00000581533,"about_ca_topic_score_gemma":0.000015137681,"teacher_disagreement_score":0.3519669,"about_ca_system_score_codex":0.000009372786,"about_ca_system_score_gemma":0.000028478777,"threshold_uncertainty_score":0.3931596},"labels":[],"label_agreement":null},{"id":"W3081939977","doi":"10.3390/data5030075","title":"High-Resolution Surface Water Classifications of the Xingu River, Brazil, Pre and Post Operationalization of the Belo Monte Hydropower Complex","year":2020,"lang":"en","type":"article","venue":"Data","topic":"Fish biology, ecology, and behavior","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; McGill University","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; DigitalGlobe Foundation","keywords":"Operationalization; Hydropower; Land cover; Remote sensing; Geography; Surface water; Pixel; Hydrology (agriculture); Environmental science; Cartography; Land use; Geology; Ecology; Computer science","score_opus":0.04060715776044358,"score_gpt":0.2676884213395465,"score_spread":0.22708126357910294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081939977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912961,0.0000126627,0.00008816407,0.00719227,0.00007160114,0.00020955609,0.0010529744,0.0000057579387,0.00007087489],"genre_scores_gemma":[0.9984138,0.0000093380495,0.00030455604,0.00050748215,0.000010573001,0.0000017607748,0.00063761434,0.0000035178155,0.000111366906],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9994207,0.00007935409,0.00014491902,0.00018253697,0.0000975295,0.00007496588],"domain_scores_gemma":[0.9994879,0.000017390897,0.0000636669,0.00039728178,0.0000141177725,0.000019639452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008458966,0.000052042888,0.00006863314,0.0000034521267,0.00014037051,0.0000064385627,0.0004731819,0.000043883003,0.0003816298],"category_scores_gemma":[0.000045943558,0.000027752016,0.000013800754,0.00007421825,0.0005127267,0.00012919195,0.0006739008,0.000051827028,0.000017211572],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000102103295,0.00006514453,0.3189469,0.0000055440064,0.000006899352,6.965875e-8,0.00039876695,0.0012585352,0.6650491,0.00013012516,0.014072002,0.000056735797],"study_design_scores_gemma":[0.00012351658,0.000024857474,0.9828023,0.000002595025,0.000020455125,8.9721044e-7,0.000049351816,0.0071783685,0.004977937,0.000018339511,0.0047621555,0.000039231236],"about_ca_topic_score_codex":0.0005736383,"about_ca_topic_score_gemma":0.0007005014,"teacher_disagreement_score":0.6638554,"about_ca_system_score_codex":0.000015402084,"about_ca_system_score_gemma":0.000006873811,"threshold_uncertainty_score":0.4178579},"labels":[],"label_agreement":null},{"id":"W3139518835","doi":"10.3390/data6030032","title":"A High-Accuracy GNSS Dataset of Ground Truth Points Collected within Îles-de-Boucherville National Park, Quebec, Canada","year":2021,"lang":"en","type":"article","venue":"Data","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ground truth; Geography; GNSS applications; Cartography; Hyperspectral imaging; Context (archaeology); National park; Phragmites; Remote sensing; Satellite imagery; Biodiversity; Global Positioning System; Wetland; Ecology; Computer science; Archaeology; Artificial intelligence; Biology","score_opus":0.026964539590984733,"score_gpt":0.260057088737131,"score_spread":0.23309254914614627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139518835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.918704,0.000054768338,0.0009150246,0.00340005,0.00030024545,0.00028565034,0.07133508,0.000041901607,0.0049633216],"genre_scores_gemma":[0.9026769,0.000013936393,0.01252731,0.00074203464,0.000052449344,0.0000025070876,0.0831813,0.000016322047,0.0007872349],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99878305,0.00008204647,0.00023430922,0.0003525543,0.00039236655,0.0001556436],"domain_scores_gemma":[0.9986865,0.0001719957,0.00011688233,0.000909751,0.000030028881,0.000084874584],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024182703,0.00008769755,0.000119560464,0.000012784925,0.00011202356,0.00003649295,0.00048330188,0.000035634654,0.0010072377],"category_scores_gemma":[0.0005500933,0.00008759127,0.000009880396,0.00043698767,0.00008537761,0.00017173403,0.00041170756,0.000092845854,0.000050414405],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014261556,0.00011116086,0.00046894356,0.000011014073,0.000036710768,0.000022766315,0.0001167214,0.000367928,0.0058889464,0.0005270186,0.9907547,0.0016797826],"study_design_scores_gemma":[0.00095937675,0.000014856251,0.1229272,0.000038266837,0.000059592094,0.00007366752,0.00054028915,0.018279316,0.009545534,0.0013657665,0.8457216,0.0004745102],"about_ca_topic_score_codex":0.89585215,"about_ca_topic_score_gemma":0.96173674,"teacher_disagreement_score":0.14503312,"about_ca_system_score_codex":0.00026487288,"about_ca_system_score_gemma":0.00067933387,"threshold_uncertainty_score":0.999906},"labels":[],"label_agreement":null},{"id":"W3153173594","doi":"10.3390/data6040039","title":"Exploring Inner-City Residents’ and Foreigners’ Commitment to Improving Air Pollution: Evidence from a Field Survey in Hanoi, Vietnam","year":2021,"lang":"en","type":"article","venue":"Data","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Contingent valuation; Stratified sampling; Air pollution; Willingness to pay; Air quality index; Business; Field survey; Perception; Pollution; Socioeconomics; Geography; Environmental planning; Economic growth; Environmental protection; Environmental resource management; Economics; Psychology; Cartography","score_opus":0.5029405464010799,"score_gpt":0.28265426631804397,"score_spread":0.2202862800830359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153173594","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928754,0.0013747077,0.0026308638,0.0014847831,0.00020930891,0.00013822627,0.0010779161,0.000008553718,0.00020023563],"genre_scores_gemma":[0.99627674,0.0007047967,0.001415483,0.0008517963,0.00005482177,0.00002670299,0.0005799563,0.000008869389,0.0000808666],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988638,0.000035958197,0.0003706808,0.00053864217,0.000029729428,0.00016118446],"domain_scores_gemma":[0.99900085,0.00013080568,0.000098841614,0.0006997512,0.0000053708077,0.00006438661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085730583,0.000092831615,0.0002043952,0.00006802748,0.00006817334,0.000056453562,0.00026493223,0.00004289248,0.00024347435],"category_scores_gemma":[0.0005105743,0.00012092401,0.00001657256,0.00011688637,0.000014968873,0.00092123804,0.0007208556,0.00008988891,0.00012644556],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013935753,0.000025787911,0.9950576,0.00000811574,0.000011855966,0.0000036921558,0.00030273324,0.00009590727,0.000049477632,0.0002767921,0.0011714444,0.0029826749],"study_design_scores_gemma":[0.00025507202,0.000027190894,0.9964655,0.000048470978,0.0000029895361,7.106088e-7,0.00016282755,0.001190631,0.00029194055,0.0006397716,0.0007756394,0.00013924914],"about_ca_topic_score_codex":0.012681537,"about_ca_topic_score_gemma":0.0077415793,"teacher_disagreement_score":0.0049399575,"about_ca_system_score_codex":0.00015020039,"about_ca_system_score_gemma":0.00001441717,"threshold_uncertainty_score":0.9938931},"labels":[],"label_agreement":null},{"id":"W3173858413","doi":"10.3390/data6060068","title":"Analyses of Li-Rich Minerals Using Handheld LIBS Tool","year":2021,"lang":"en","type":"article","venue":"Data","topic":"Laser-induced spectroscopy and plasma","field":"Engineering","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Manitoba Hydro; Western University","funders":"European Social Fund; Fundação para a Ciência e a Tecnologia; Ministério da Ciência, Tecnologia e Ensino Superior; Agence Nationale de la Recherche","keywords":"Laser-induced breakdown spectroscopy; Pellets; Lithium (medication); Materials science; Spectroscopy; Spectrometer; Analytical Chemistry (journal); Chemistry; Environmental chemistry; Optics","score_opus":0.14322863013859913,"score_gpt":0.35107403917310637,"score_spread":0.20784540903450724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173858413","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.993274,0.00052361726,0.0026706993,0.00003046882,0.0002505559,0.00003293582,0.0009008412,0.00006171683,0.0022552027],"genre_scores_gemma":[0.9880364,0.00013027833,0.009951884,0.000044771456,0.00016471387,9.679632e-7,0.0012944099,0.000021211314,0.00035536883],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99943036,0.000016825554,0.00016313668,0.0001537602,0.00009650839,0.00013938663],"domain_scores_gemma":[0.99914783,0.00005612281,0.000020417103,0.00072237215,0.000023748706,0.00002951079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000072921146,0.0000840707,0.00015978761,0.00003757489,0.000024250927,0.000031390082,0.00024314102,0.00005130539,0.0003238214],"category_scores_gemma":[0.0000780846,0.00008120644,0.000022699975,0.00023952432,0.0000094388315,0.0002237557,0.0001242339,0.00008654083,0.000027119626],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026178798,0.000018125915,0.00025144604,0.00006001751,0.00008128186,0.000031922442,0.000031692187,0.005198819,0.98172754,0.000042986663,0.012162209,0.0003913503],"study_design_scores_gemma":[0.00012122655,0.0000060695297,0.00020830776,0.000035043322,0.000059867667,0.000011078434,0.000018551724,0.0651474,0.92384446,0.00003089087,0.01040302,0.000114075796],"about_ca_topic_score_codex":0.000048409438,"about_ca_topic_score_gemma":0.000053009087,"teacher_disagreement_score":0.059948582,"about_ca_system_score_codex":0.000011524042,"about_ca_system_score_gemma":0.00003171331,"threshold_uncertainty_score":0.35456175},"labels":[],"label_agreement":null},{"id":"W3190588453","doi":"10.3390/data6080084","title":"The Automatic Detection of Dataset Names in Scientific Articles","year":2021,"lang":"en","type":"article","venue":"Data","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Computer science; Named-entity recognition; Annotation; Task (project management); Natural language processing; Sentence; Feature (linguistics); Set (abstract data type); Artificial intelligence; Code (set theory); Information retrieval; Baseline (sea); Linguistics; Programming language","score_opus":0.06923547144482206,"score_gpt":0.2931762461491873,"score_spread":0.22394077470436524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3190588453","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5463612,0.00072602415,0.44977295,0.0014628044,0.0007693234,0.00009879962,0.00071654137,0.000054781853,0.000037532274],"genre_scores_gemma":[0.988172,0.000005528274,0.011471068,0.000027526092,0.000009658516,0.0000015763482,0.00029204017,0.0000013622398,0.000019224648],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993723,0.00004966146,0.0001319215,0.00021824922,0.00013840052,0.00008947693],"domain_scores_gemma":[0.9979287,0.00008212581,0.0000318154,0.0019246164,0.00001900294,0.000013747196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055633916,0.000026909502,0.000040386327,0.000026237403,0.000078939556,0.00017928047,0.0011022363,0.000009695138,0.0000037202346],"category_scores_gemma":[0.0002138499,0.000020285066,0.0000050947788,0.00028621888,0.000036471458,0.00039339517,0.0009262192,0.000038724727,0.000013431001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.935897e-7,0.000056695317,0.00068673806,0.000030486633,0.000008232072,0.000017967892,0.0004939306,0.00017048564,0.026905468,0.0053205364,0.005499923,0.9608085],"study_design_scores_gemma":[0.00005955939,0.0000025282113,0.0014746488,0.000012374498,0.0000014531521,0.0000053964823,0.000057709305,0.97185636,0.0131906625,0.001722929,0.01158581,0.000030570198],"about_ca_topic_score_codex":0.000039830946,"about_ca_topic_score_gemma":0.0006182794,"teacher_disagreement_score":0.9716859,"about_ca_system_score_codex":0.0000072935004,"about_ca_system_score_gemma":0.000051158862,"threshold_uncertainty_score":0.20482478},"labels":[],"label_agreement":null},{"id":"W3191944979","doi":"10.3390/data6080090","title":"Canadian Dental Patients with a Single-Unit Implant-Supported Restoration in the Aesthetic Region of the Mouth: Qualitative and Quantitative Patient-Reported Outcome Measures (PROMs)","year":2021,"lang":"en","type":"article","venue":"Data","topic":"Dental Implant Techniques and Outcomes","field":"Dentistry","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"AAID Foundation; American Academy of Implant Dentistry","keywords":"Dentistry; Visual analogue scale; Implant; Medicine; Demographics; Qualitative property; Orthodontics; Perception; Qualitative research; Psychology; Physical therapy; Computer science; Surgery","score_opus":0.15759326794286102,"score_gpt":0.35563654433521036,"score_spread":0.19804327639234934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191944979","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99665755,0.000058033922,0.000051468654,0.00025143317,0.00018101562,0.00050636684,0.0021244497,0.0000178169,0.00015187715],"genre_scores_gemma":[0.99665654,0.0000033051742,0.0002102267,0.00023708948,0.000004029014,0.000012483992,0.0027991391,0.000015522646,0.00006166815],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99801725,0.00049322034,0.00047712587,0.00032724516,0.00046808933,0.00021705116],"domain_scores_gemma":[0.9984039,0.00012920612,0.0003328428,0.00090937276,0.00015916966,0.000065514585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035947104,0.00016195857,0.00022869626,0.00010200769,0.00012883509,0.00008576923,0.0004481247,0.000072835894,0.000010079753],"category_scores_gemma":[0.00031278958,0.00009665951,0.000032940938,0.0003735632,0.00011896556,0.0003176787,0.00019076256,0.00018484933,0.0000046869313],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015298219,0.00025646557,0.97938174,0.000035297293,0.00006654155,0.0014282429,0.011643898,0.0000010099282,0.00017036857,0.00061537506,0.003777253,0.0024708486],"study_design_scores_gemma":[0.0013311823,0.00024551628,0.9645169,0.00017311977,0.0001311615,0.0029390107,0.028061738,0.00004659722,0.00047193337,0.00024276522,0.0015475036,0.00029258776],"about_ca_topic_score_codex":0.04696739,"about_ca_topic_score_gemma":0.48967177,"teacher_disagreement_score":0.44270435,"about_ca_system_score_codex":0.00008421934,"about_ca_system_score_gemma":0.00012877057,"threshold_uncertainty_score":0.95937896},"labels":[],"label_agreement":null},{"id":"W3192980550","doi":"10.3390/data6080085","title":"VISEMURE: A Visual Analytics System for Making Sense of Multimorbidity Using Electronic Medical Record Data","year":2021,"lang":"en","type":"article","venue":"Data","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Multimorbidity; Computer science; Visual analytics; Data science; Analytics; Visualization; Range (aeronautics); Electronic health record; Population; Medical record; Health care; Human–computer interaction; Artificial intelligence; Medicine","score_opus":0.25414144782329173,"score_gpt":0.4631493699357773,"score_spread":0.2090079221124856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192980550","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63155776,0.0055602137,0.3221812,0.0034034853,0.0027167457,0.0042315037,0.024604363,0.0007248053,0.0050199097],"genre_scores_gemma":[0.9748395,0.00012293921,0.005348185,0.00015144776,0.0004793395,0.0000042246684,0.018951163,0.000035847468,0.00006731984],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979467,0.00006735718,0.00042504977,0.000641941,0.00054754404,0.00037143606],"domain_scores_gemma":[0.99679655,0.00015884383,0.00016223502,0.0026481086,0.00011621093,0.00011804816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079163327,0.00014998799,0.00040517098,0.000073288415,0.000057778027,0.000038453425,0.0005813022,0.000083487466,0.00023548825],"category_scores_gemma":[0.0010935063,0.00014651055,0.000054601463,0.0002830072,0.0000710103,0.00023171783,0.0016985426,0.00016960196,0.0000063988646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006601181,0.010112251,0.028421175,0.09835791,0.01872533,0.018738195,0.00048794443,0.0005592612,0.020689838,0.047071457,0.5484253,0.20181014],"study_design_scores_gemma":[0.0023159801,0.00008284835,0.00047656614,0.0010310077,0.0014952117,0.00015719529,0.0007645655,0.9519176,0.00020038323,0.00003047029,0.041341964,0.00018623416],"about_ca_topic_score_codex":0.000101209924,"about_ca_topic_score_gemma":0.00024297267,"teacher_disagreement_score":0.9513583,"about_ca_system_score_codex":0.00018012016,"about_ca_system_score_gemma":0.0014787237,"threshold_uncertainty_score":0.59745264},"labels":[],"label_agreement":null},{"id":"W3205135456","doi":"10.3390/data6100107","title":"The Retreat of Mountain Glaciers since the Little Ice Age: A Spatially Explicit Database","year":2021,"lang":"en","type":"article","venue":"Data","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Science and Engineering Research Board; National Natural Science Foundation of China; Agence Nationale de la Recherche; European Commission","keywords":"Glacier; Geology; Little ice age; Physical geography; Glacier morphology; Climate change; Tidewater glacier cycle; Glacier mass balance; Period (music); Climatology; Cryosphere; Geography; Oceanography; Ice stream; Sea ice","score_opus":0.05518337691283202,"score_gpt":0.2594460833303547,"score_spread":0.20426270641752267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205135456","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.789001,0.05359792,0.0043450207,0.07716643,0.002863286,0.0012495974,0.05074132,0.00014073709,0.020894678],"genre_scores_gemma":[0.96356833,0.0068024197,0.0046053054,0.0028757143,0.00046290702,0.0000048440043,0.01902219,0.000009688028,0.0026485997],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992537,0.000059526767,0.0001424084,0.00019703282,0.00019331726,0.00015401814],"domain_scores_gemma":[0.99808717,0.00059388997,0.000055838187,0.0011878815,0.000043400694,0.000031832456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032471056,0.00006489678,0.000082371145,0.0000032556445,0.0004105626,0.00007108079,0.0007038638,0.00001520685,0.000394776],"category_scores_gemma":[0.00043653333,0.0000348489,0.000019656518,0.00028543052,0.000105243234,0.00016017708,0.0001876448,0.00007792685,0.000037356862],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001454043,0.00010631247,0.48381025,0.00008154789,0.00031701746,0.00022287527,0.0024152887,0.0010520807,0.00042434144,0.008868208,0.32269025,0.17986645],"study_design_scores_gemma":[0.000117760785,0.00001888626,0.2581733,0.000012386836,0.000030338813,0.000005148595,0.002323021,0.007927722,0.00005632803,0.00015985827,0.73109514,0.000080142],"about_ca_topic_score_codex":0.0076658893,"about_ca_topic_score_gemma":0.05308688,"teacher_disagreement_score":0.4084049,"about_ca_system_score_codex":0.0000021663232,"about_ca_system_score_gemma":0.00006886847,"threshold_uncertainty_score":0.99894214},"labels":[],"label_agreement":null},{"id":"W3208023966","doi":"10.3390/data6110113","title":"Nowcasting India Economic Growth Using a Mixed-Data Sampling (MIDAS) Model (Empirical Study with Economic Policy Uncertainty–Consumer Prices Index)","year":2021,"lang":"en","type":"article","venue":"Data","topic":"Market Dynamics and Volatility","field":"Economics, Econometrics and Finance","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nowcasting; Econometrics; Index (typography); Quarter (Canadian coin); Economics; Real gross domestic product; Weighting; Sample (material); Economic indicator; Economic data; Mean squared error; Consumer price index (South Africa); Statistics; Mathematics; Macroeconomics; Monetary policy; Computer science; Geography","score_opus":0.17324816959921102,"score_gpt":0.3447945595625129,"score_spread":0.1715463899633019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208023966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96023285,0.0003456821,0.020169195,0.00031073173,0.00025076282,0.00041105002,0.015914949,0.000051559662,0.002313243],"genre_scores_gemma":[0.9900984,0.000094979536,0.0064859753,0.00017127863,0.00028374948,0.000011659967,0.0027281374,0.000068315785,0.000057514477],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99624693,0.00005827673,0.0010821414,0.0019184711,0.000067356435,0.00062682],"domain_scores_gemma":[0.9952775,0.00025623996,0.0006315325,0.0035878418,0.000043390122,0.00020347418],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016938056,0.00038090974,0.00078339403,0.00034829022,0.000296339,0.00046159475,0.001971617,0.00015465413,0.00021040677],"category_scores_gemma":[0.00039246964,0.00043028797,0.00006254293,0.0002463393,0.000098435405,0.0012531193,0.002971082,0.0003874387,0.00007304886],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006574686,0.00022310912,0.9839438,0.000049476967,0.00028236338,0.000014120874,0.00023030017,0.011506563,0.0000013390043,0.0025906719,0.0003468798,0.00074560277],"study_design_scores_gemma":[0.0008846158,0.00003318097,0.04985548,0.00002135604,0.000040005572,0.000018809986,0.00028245544,0.94273156,8.695853e-7,0.0032282122,0.0024021391,0.00050129805],"about_ca_topic_score_codex":0.006439104,"about_ca_topic_score_gemma":0.006812327,"teacher_disagreement_score":0.93408835,"about_ca_system_score_codex":0.00053303974,"about_ca_system_score_gemma":0.00090724515,"threshold_uncertainty_score":0.99981487},"labels":[],"label_agreement":null},{"id":"W4200268174","doi":"10.3390/data7010001","title":"Datasets for the Determination of Evaporative Flux from Distilled Water and Saturated Brine Using Bench-Scale Atmospheric Simulators","year":2021,"lang":"en","type":"article","venue":"Data","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Distilled water; Environmental science; Brine; Evaporative cooler; Flux (metallurgy); Evaporation; Meteorology; Atmospheric sciences; Chemistry; Geology; Chromatography","score_opus":0.027597781109062487,"score_gpt":0.2740399333876724,"score_spread":0.2464421522786099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200268174","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98791397,0.00008351699,0.008617586,0.00042702226,0.00007845081,0.00021402998,0.0026036396,0.0000071044205,0.000054700733],"genre_scores_gemma":[0.9851451,0.00001874446,0.0039293603,0.000108880115,0.000012905499,0.0000039210704,0.01070801,0.000004033365,0.00006905775],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946743,0.00003087634,0.00010219999,0.00023369821,0.000068881855,0.00009688854],"domain_scores_gemma":[0.99947906,0.00008869175,0.000036496604,0.00037613543,0.000005449571,0.000014194054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011736985,0.00006442184,0.00009196045,0.0000018074477,0.00014146748,0.000012489978,0.00017520452,0.000021192935,0.00025291336],"category_scores_gemma":[0.000036447447,0.000038078637,0.000008754047,0.00005258288,0.00014920939,0.00021075521,0.0009219035,0.000028202434,0.000007002965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007806273,0.0007579325,0.5432238,0.00021204885,0.001248531,0.00012264246,0.010034047,0.022240764,0.24657492,0.00007615598,0.070170365,0.10455817],"study_design_scores_gemma":[0.0011618349,0.000047176207,0.10630229,0.00001580751,0.00039903293,0.000002431298,0.0005114583,0.8140722,0.030183092,0.0009859239,0.04606165,0.00025713418],"about_ca_topic_score_codex":0.00025311197,"about_ca_topic_score_gemma":0.00033113832,"teacher_disagreement_score":0.79183143,"about_ca_system_score_codex":0.000010605272,"about_ca_system_score_gemma":0.0000017424505,"threshold_uncertainty_score":0.2769224},"labels":[],"label_agreement":null},{"id":"W4205402457","doi":"10.3390/data7010006","title":"Multi-Temporal Surface Water Classification for Four Major Rivers from the Peruvian Amazon","year":2022,"lang":"en","type":"article","venue":"Data","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; National Research Council Canada; McGill University","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Amazon rainforest; Surface water; Geography; Environmental science; Satellite imagery; Hydrology (agriculture); Remote sensing; Physical geography; Geology; Ecology","score_opus":0.08291226371513943,"score_gpt":0.28159673490848935,"score_spread":0.19868447119334992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205402457","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92762727,0.00006102262,0.045673754,0.016818566,0.0009809182,0.0022635367,0.0055385036,0.00011705378,0.00091936],"genre_scores_gemma":[0.9709093,0.0000111070185,0.018805658,0.000409432,0.00003848011,0.000059221733,0.008095445,0.00001217129,0.0016591949],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999125,0.000059760343,0.00009614798,0.00033186795,0.00022245782,0.0001647557],"domain_scores_gemma":[0.99913645,0.0000298156,0.000037324975,0.00076771446,0.0000018028932,0.000026904163],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036836392,0.00007276926,0.000054882945,0.0000058899923,0.00038534708,0.000042344935,0.0009735281,0.000012655205,0.0023224826],"category_scores_gemma":[0.0000057411553,0.00004692393,0.000022288626,0.000048256406,0.000044322565,0.00022222404,0.0015868671,0.00007185186,0.00026108045],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087290486,0.00030944395,0.36080137,0.000007864987,0.00008711389,0.000007518343,0.0012223979,0.0021244101,0.027834056,0.00017816608,0.5995677,0.0077726785],"study_design_scores_gemma":[0.0005553831,0.000031193886,0.14652461,8.4219454e-7,0.000039190632,2.2212672e-7,0.00096561183,0.070014864,0.00017559943,0.00014768887,0.7814273,0.00011749896],"about_ca_topic_score_codex":0.003829378,"about_ca_topic_score_gemma":0.0013631246,"teacher_disagreement_score":0.21427678,"about_ca_system_score_codex":0.000082915416,"about_ca_system_score_gemma":0.000003710431,"threshold_uncertainty_score":0.9985895},"labels":[],"label_agreement":null},{"id":"W4212765637","doi":"10.3390/data7020024","title":"British Columbia’s Index of Multiple Deprivation for Community Health Service Areas","year":2022,"lang":"en","type":"article","venue":"Data","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; BC Centre for Disease Control; Provincial Health Services Authority","funders":"","keywords":"Equity (law); Index (typography); Environmental health; Medicine; Health care; Public health; Population; Geography; Gerontology; Socioeconomics; Economic growth; Nursing; Political science; Sociology","score_opus":0.12394931355095584,"score_gpt":0.378678742068399,"score_spread":0.2547294285174432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212765637","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96684563,0.00023249327,0.00060760084,0.016120525,0.00049310987,0.0011394763,0.013573736,0.000069720314,0.000917725],"genre_scores_gemma":[0.98656535,0.00005720423,0.00036078237,0.008979705,0.000054044853,0.000044133514,0.003671439,0.0000064062665,0.0002609132],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988399,0.00041887834,0.0001946434,0.00010589982,0.0002221315,0.00021854455],"domain_scores_gemma":[0.9988528,0.0004174027,0.00011719972,0.00047171008,0.00006179927,0.00007911341],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0021487065,0.00002577422,0.00012063586,0.000011177489,0.0015094813,0.0000668289,0.0007806814,0.000022330934,0.00036908884],"category_scores_gemma":[0.00066318613,0.000046397985,0.0000135823775,0.00018763763,0.00003646095,0.00016558723,0.0004957136,0.00014538347,6.6472904e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008972259,0.0001283614,0.7210005,0.00025497633,0.000006981832,2.3062827e-7,0.003554754,0.000009051076,3.3083668e-7,0.0004920406,0.26086545,0.013678361],"study_design_scores_gemma":[0.0003059348,0.000020115984,0.49180865,0.00001666166,0.0000021796702,4.2699892e-7,0.015349066,0.00039693608,1.3702473e-7,0.0005770795,0.49147445,0.000048381746],"about_ca_topic_score_codex":0.9648728,"about_ca_topic_score_gemma":0.98627055,"teacher_disagreement_score":0.23060898,"about_ca_system_score_codex":0.0001086309,"about_ca_system_score_gemma":0.0005107591,"threshold_uncertainty_score":0.99979043},"labels":[],"label_agreement":null},{"id":"W4224228288","doi":"10.3390/data7040042","title":"Climate Data to Support the Adaptation of Buildings to Climate Change in Canada","year":2022,"lang":"en","type":"article","venue":"Data","topic":"Wind and Air Flow Studies","field":"Environmental Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"National Research Council Canada","funders":"Infrastructure Canada; Environment and Climate Change Canada","keywords":"Climate change; Environmental science; Climate model; Range (aeronautics); Climatology; Meteorology; Adaptation (eye); Extreme weather; Environmental resource management; Computer science; Geography; Engineering; Ecology; Geology","score_opus":0.09060035913212995,"score_gpt":0.2827019086819242,"score_spread":0.19210154954979425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224228288","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96787906,0.000030701285,0.00001866566,0.0072453064,0.00023599809,0.00043700944,0.02343851,0.000008879024,0.0007058891],"genre_scores_gemma":[0.9962055,0.000036038124,0.00041275012,0.0020879055,0.000024556284,0.00003324118,0.0011811148,0.0000058292985,0.000013077139],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99906474,0.000025960526,0.00013311191,0.00028461937,0.0002754258,0.00021611073],"domain_scores_gemma":[0.99895805,0.000025076504,0.00003521015,0.00094191555,0.0000015473805,0.0000382261],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00049106614,0.00005548564,0.00007991696,0.000014899909,0.00014232664,0.0000070309025,0.0014224249,0.0000041446688,0.00068567705],"category_scores_gemma":[0.000030282255,0.000043851138,0.000004094327,0.00024848394,0.000015455089,0.00018965377,0.008896206,0.000054138236,0.00004081417],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058958758,0.000084536056,0.3936349,0.000025838555,0.000010935859,0.00003943249,0.0051702186,0.0032391571,0.0009831409,0.00010622088,0.40417507,0.19247161],"study_design_scores_gemma":[0.00013662958,0.000066883724,0.3218142,0.000010735875,0.000009562182,0.000002546674,0.0039054672,0.006215213,0.000040271927,0.00000464867,0.6676532,0.000140641],"about_ca_topic_score_codex":0.76870733,"about_ca_topic_score_gemma":0.936224,"teacher_disagreement_score":0.2634781,"about_ca_system_score_codex":0.00011554287,"about_ca_system_score_gemma":0.000023596629,"threshold_uncertainty_score":0.99911964},"labels":[],"label_agreement":null},{"id":"W4225402556","doi":"10.3390/data7050057","title":"Multi-Layer Web Services Discovery Using Word Embedding and Clustering Techniques","year":2022,"lang":"en","type":"article","venue":"Data","topic":"Service-Oriented Architecture and Web Services","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Cluster analysis; Web service; tf–idf; Word2vec; Cosine similarity; Information retrieval; Hierarchical clustering; WordNet; Word embedding; Web mining; Artificial intelligence; Embedding; World Wide Web; Term (time)","score_opus":0.04792049577603731,"score_gpt":0.3111653434231159,"score_spread":0.2632448476470786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225402556","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49620655,0.0011734054,0.49893156,0.0008204192,0.0008202452,0.0004332675,0.0006111406,0.000715723,0.00028767515],"genre_scores_gemma":[0.67286247,0.000039049643,0.32409272,0.0025275783,0.00014496403,0.00001982591,0.00025264753,0.000025579853,0.000035130346],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849313,0.000085007865,0.00019495624,0.00066767953,0.00027266523,0.0002865521],"domain_scores_gemma":[0.99832404,0.00005497813,0.00010203322,0.0014361488,0.000018038565,0.000064754706],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003246029,0.00016489095,0.00015557156,0.00015331623,0.0004775573,0.00043106824,0.0026753414,0.000028974413,0.000012443511],"category_scores_gemma":[0.0000022009679,0.00015677526,0.000021275799,0.0004193217,0.000016604965,0.0019205506,0.011058595,0.00021607643,0.0000023050713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002252797,0.001016026,0.02067612,0.0024298069,0.00054262555,0.0006741414,0.04527626,0.016917363,0.5225243,0.0034038394,0.0013092037,0.38500506],"study_design_scores_gemma":[0.00018153986,0.000022500584,0.00031932222,0.000052597796,0.000013082489,0.00007664728,0.0007848113,0.97493553,0.00061195827,0.0001010511,0.022669703,0.0002312648],"about_ca_topic_score_codex":0.00051319646,"about_ca_topic_score_gemma":0.0006377532,"teacher_disagreement_score":0.9580182,"about_ca_system_score_codex":0.000026465164,"about_ca_system_score_gemma":0.000038634967,"threshold_uncertainty_score":0.9969398},"labels":[],"label_agreement":null},{"id":"W4281878817","doi":"10.3390/data7060073","title":"Quality Control Impacts on Total Precipitation Gauge Records for Montane Valley and Ridge Sites in SW Alberta, Canada","year":2022,"lang":"en","type":"article","venue":"Data","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates - Technology Futures; Canada Foundation for Innovation; Alberta Environment and Parks","keywords":"Precipitation; Ridge; Rain gauge; Environmental science; Hydrology (agriculture); Orographic lift; Noise (video); Snow; Watershed; Physical geography; Climatology; Meteorology; Geology; Geography","score_opus":0.04699274541030582,"score_gpt":0.2664780589345688,"score_spread":0.21948531352426295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281878817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97697663,0.00033489338,0.000014666464,0.0016526473,0.00023855628,0.00026484908,0.020297376,0.000004456871,0.00021594552],"genre_scores_gemma":[0.98940307,0.0000287557,0.00015827177,0.00068728416,0.000040935556,0.000007844984,0.009505765,0.0000018382909,0.00016623372],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999307,0.000052915366,0.00014788641,0.00020288177,0.00013929923,0.0001500507],"domain_scores_gemma":[0.9987703,0.0009026705,0.000051502266,0.0002164761,0.000012745296,0.000046335466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029140673,0.00006297321,0.00011146393,0.000009965777,0.00021113794,0.000019640196,0.00014068867,0.000010738036,0.00045185754],"category_scores_gemma":[0.00032677842,0.000056832436,0.0000094536545,0.000090983085,0.000010374466,0.000113096314,0.000033253193,0.00005935908,0.0000014694438],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002089344,0.00002382684,0.9081998,0.000015321586,0.000025163781,0.0000036172767,0.00033732908,0.002160811,0.0000059088684,0.00007954707,0.08011826,0.008821504],"study_design_scores_gemma":[0.00046309148,0.00011502569,0.9410805,0.0000021216363,0.0000061987744,0.000001341319,0.00058769115,0.01976476,3.164436e-7,0.00006134899,0.03784097,0.00007660232],"about_ca_topic_score_codex":0.9498631,"about_ca_topic_score_gemma":0.9960811,"teacher_disagreement_score":0.046218008,"about_ca_system_score_codex":0.0000161797,"about_ca_system_score_gemma":0.000089365036,"threshold_uncertainty_score":0.49475235},"labels":[],"label_agreement":null},{"id":"W4295765220","doi":"10.3390/data7090132","title":"Dataset of Psychological Scales and Physiological Signals Collected for Anxiety Assessment Using a Portable Device","year":2022,"lang":"en","type":"article","venue":"Data","topic":"Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes","field":"Psychology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Anxiety; CLIPS; Beck Anxiety Inventory; Psychology; Audiology; Beck Depression Inventory; Medicine; Computer science; Artificial intelligence; Psychiatry","score_opus":0.2868376409991922,"score_gpt":0.48392305682227665,"score_spread":0.19708541582308448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295765220","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77155083,0.0042132367,0.009320599,0.00014190271,0.0007039012,0.0016129507,0.21142411,0.000086789165,0.0009456689],"genre_scores_gemma":[0.92806304,0.00094996847,0.015174894,0.0005800793,0.00012972689,0.0003537379,0.05458039,0.000033126402,0.00013502702],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972966,0.00035740584,0.00048248915,0.0011487718,0.00031153893,0.00040319664],"domain_scores_gemma":[0.9977576,0.0004859893,0.00037662376,0.0011250878,0.00014140445,0.000113268914],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007939902,0.000244494,0.00044150194,0.00017946344,0.00041119926,0.00003641534,0.00088858436,0.00011024531,0.002763894],"category_scores_gemma":[0.00030610888,0.0002062888,0.00004922868,0.00093729683,0.00018795964,0.0002035503,0.0011067354,0.0002443906,0.000007903603],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010624953,0.0051040594,0.09193675,0.00011277835,0.00050835195,0.000022186408,0.00017284142,0.000026042831,0.01071104,0.0003312596,0.8543072,0.035705026],"study_design_scores_gemma":[0.0057143574,0.0018610057,0.35372752,0.000037077614,0.00044384392,0.00017024724,0.0024015917,0.0021914302,0.00021899721,0.0020496345,0.6303829,0.0008013654],"about_ca_topic_score_codex":0.00009895925,"about_ca_topic_score_gemma":0.000009561633,"teacher_disagreement_score":0.26179078,"about_ca_system_score_codex":0.00004453012,"about_ca_system_score_gemma":0.000050777795,"threshold_uncertainty_score":0.9981477},"labels":[],"label_agreement":null},{"id":"W4308532027","doi":"10.3390/data7110154","title":"Dataset on Force Myography for Human–Robot Interactions","year":2022,"lang":"en","type":"article","venue":"Data","topic":"Muscle activation and electromyography studies","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research","keywords":"Electrical impedance myography; Wearable computer; Robot; Computer science; Biosignal; Human–robot interaction; Human–computer interaction; Simulation; Artificial intelligence; Medicine; Computer vision; Embedded system","score_opus":0.06786186037731555,"score_gpt":0.3114669405129129,"score_spread":0.24360508013559734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308532027","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049183708,0.0013508791,0.13543469,0.005666903,0.00640477,0.0038664367,0.76809496,0.0029622398,0.0270354],"genre_scores_gemma":[0.8749923,0.000028179693,0.00064888026,0.00055554055,0.00011991495,0.00030878492,0.1232006,0.000030259207,0.000115536226],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994927,0.000010072897,0.00009803144,0.00016908046,0.000087113694,0.00014302396],"domain_scores_gemma":[0.99927104,0.00006253433,0.00001715819,0.00061938516,0.000007014537,0.000022876719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007568689,0.000076712524,0.000074402094,0.00013916662,0.0003476274,0.000020291938,0.0003712003,0.000007695854,0.0001770326],"category_scores_gemma":[0.000011243932,0.00008393242,0.000030159548,0.00021461742,0.0000109753655,0.00014896259,0.00016746653,0.00012667889,0.0000022470506],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008638129,0.000038015067,0.000049420167,0.000014385449,0.0000998983,4.2424887e-7,0.000037158985,0.0009414477,0.0019517858,0.0010393091,0.9886644,0.0071551483],"study_design_scores_gemma":[0.00019807926,0.000058323352,0.0010963336,0.0000024310134,0.000013068176,0.0000013469999,0.00011736272,0.002277784,0.00019806008,0.00027688974,0.99564976,0.00011059456],"about_ca_topic_score_codex":0.000011882811,"about_ca_topic_score_gemma":0.00003060461,"teacher_disagreement_score":0.8258086,"about_ca_system_score_codex":0.000017467319,"about_ca_system_score_gemma":0.0000025481056,"threshold_uncertainty_score":0.34226647},"labels":[],"label_agreement":null},{"id":"W4310086065","doi":"10.3390/data7120171","title":"Experimental and Nonlinear Finite Element Analysis Data for an Innovative Buckling Restrained Bracing System to Rehabilitate Seismically Deficient Structures","year":2022,"lang":"en","type":"article","venue":"Data","topic":"Seismic Performance and Analysis","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"American University of Sharjah; University of Sharjah","keywords":"Bracing; Structural engineering; Finite element method; Buckling; Displacement (psychology); Bar (unit); Core (optical fiber); Nonlinear system; Ductility (Earth science); Engineering; Computer science; Geology; Materials science; Brace; Composite material; Creep","score_opus":0.03651205743686507,"score_gpt":0.3012978444924219,"score_spread":0.26478578705555683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310086065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9116838,0.00017779385,0.07149936,0.00010975614,0.00009812043,0.00031816837,0.015960097,0.00012853605,0.000024387775],"genre_scores_gemma":[0.9568438,0.0000027728943,0.020585166,0.00024153461,0.000077413184,0.000049056536,0.022171015,0.000023390283,0.0000058874643],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846005,0.00003779899,0.0003870171,0.00060043234,0.0002470165,0.0002676745],"domain_scores_gemma":[0.9980601,0.00008255583,0.000054692027,0.0016765096,0.00004240105,0.00008372429],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006778992,0.0001641027,0.00028590215,0.00032407852,0.00025970888,0.0000817591,0.00095685275,0.000022697579,0.000023673756],"category_scores_gemma":[0.00005605583,0.00016541073,0.000029073517,0.0011262442,0.000020023326,0.00036081945,0.0011773917,0.00012775748,0.0000012230616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071585826,0.00005966468,0.0005035501,0.00013671372,0.0008730834,0.0000056556314,0.0024293694,0.9775446,0.012259888,0.00010104101,0.002069644,0.0039452137],"study_design_scores_gemma":[0.00025212005,0.000108620094,0.00022538194,0.000010292179,0.00019467526,0.000002329323,0.007084698,0.97872937,0.0005057753,0.0000035393869,0.012682135,0.00020104746],"about_ca_topic_score_codex":0.00011547145,"about_ca_topic_score_gemma":0.000021716995,"teacher_disagreement_score":0.050914194,"about_ca_system_score_codex":0.00010708698,"about_ca_system_score_gemma":0.000024945757,"threshold_uncertainty_score":0.67452544},"labels":[],"label_agreement":null},{"id":"W4311720354","doi":"10.3390/data7120174","title":"Determination of Soil Behavior during Evaporation Using Geotechnical Datasets","year":2022,"lang":"en","type":"article","venue":"Data","topic":"Soil and Unsaturated Flow","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Soil water; Evaporation; Environmental science; Geotechnical engineering; Soil science; Distilled water; Shrinkage; Soil test; Water retention; Inert; Hydrology (agriculture); Geology; Materials science; Chemistry; Composite material","score_opus":0.041266360120063794,"score_gpt":0.2759279325646784,"score_spread":0.2346615724446146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311720354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9915127,0.000059620474,0.0012914382,0.00000570203,0.00018957932,0.000076564305,0.0067466022,0.0000953506,0.000022410031],"genre_scores_gemma":[0.9882131,0.000005652399,0.00075839786,0.0000034750783,0.000031736938,0.00000938382,0.010962825,0.000011973105,0.0000034070065],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995155,0.000015059353,0.00013409481,0.0001172905,0.00013698742,0.00008107249],"domain_scores_gemma":[0.999433,0.000008706585,0.000026638467,0.000506356,0.00000811458,0.000017189868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010442403,0.000052090636,0.00006310049,0.000054290227,0.0000679405,0.0000100225525,0.00027359359,0.000026518554,0.00007046837],"category_scores_gemma":[0.000015071984,0.00006006554,0.000009077773,0.0001322809,0.000009309171,0.00025211615,0.0002591131,0.00012007758,0.000002281487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058470498,0.00027875978,0.0015297511,0.00028341022,0.00004535223,0.00016874542,0.00024900283,0.3145841,0.5589909,0.00006190952,0.006612483,0.11713713],"study_design_scores_gemma":[0.00019443351,0.000011142856,0.0037325297,0.0000070996184,0.00003996639,0.00003660678,0.000033943987,0.98391485,0.01046193,0.000008175945,0.0014505541,0.000108752756],"about_ca_topic_score_codex":0.00003331019,"about_ca_topic_score_gemma":0.000011292,"teacher_disagreement_score":0.6693308,"about_ca_system_score_codex":0.00003793514,"about_ca_system_score_gemma":0.000010295688,"threshold_uncertainty_score":0.24494016},"labels":[],"label_agreement":null},{"id":"W4312116644","doi":"10.3390/data8010004","title":"LoRaWAN Path Loss Measurements in an Urban Scenario including Environmental Effects","year":2022,"lang":"en","type":"article","venue":"Data","topic":"IoT Networks and Protocols","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Path loss; Computer science; Environmental data; Path (computing); Linear regression; Environmental science; Path analysis (statistics); Set (abstract data type); Regression analysis; Telecommunications; Machine learning; Wireless; Computer network","score_opus":0.06952734318477873,"score_gpt":0.27283611503086364,"score_spread":0.20330877184608492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312116644","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98652077,0.0008722789,0.0012157619,0.000033959637,0.0010724792,0.007746144,0.0010506732,0.00030593952,0.001182021],"genre_scores_gemma":[0.9975274,0.000004326831,0.00019744568,0.000054969063,0.00011902674,0.00062767795,0.0014272946,0.000029053135,0.00001280429],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911416,0.00007522849,0.00012876035,0.00021941194,0.0002309903,0.00023147932],"domain_scores_gemma":[0.9992875,0.00001601699,0.000016995758,0.0006252059,0.000001031537,0.00005329174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039826526,0.00010672996,0.000108105036,0.0000429891,0.00009500055,0.000032229036,0.00055983756,0.000025961672,0.00013988934],"category_scores_gemma":[0.000004561358,0.00012084676,0.000011312469,0.00009360327,0.0000112544085,0.00025102808,0.0006208606,0.00023255894,0.000027575123],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012344384,0.0006074781,0.7731806,0.00034129535,0.00011782155,0.0003691637,0.0033000691,0.095610514,0.019251546,0.00005909192,0.05425481,0.052784152],"study_design_scores_gemma":[0.0042992113,0.00052453415,0.07329244,0.00020633153,0.000043500513,0.00003109645,0.0002503608,0.42470962,0.002826917,0.00020496975,0.49217173,0.0014392604],"about_ca_topic_score_codex":0.00001743463,"about_ca_topic_score_gemma":0.000025547788,"teacher_disagreement_score":0.69988817,"about_ca_system_score_codex":0.00017733377,"about_ca_system_score_gemma":0.000008292465,"threshold_uncertainty_score":0.49279878},"labels":[],"label_agreement":null},{"id":"W4318776785","doi":"10.3390/data8020034","title":"Neural Coreference Resolution for Dutch Parliamentary Documents with the DutchParliament Dataset","year":2023,"lang":"en","type":"article","venue":"Data","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Coreference; Computer science; Natural language processing; Artificial intelligence; Task (project management); Resolution (logic); Metadata; Annotation; Cluster analysis; Information retrieval; World Wide Web","score_opus":0.06760614956412057,"score_gpt":0.3378913798641697,"score_spread":0.27028523030004914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318776785","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007382289,0.0012833112,0.9274636,0.037989326,0.00060957187,0.0020441194,0.021109995,0.0020671675,0.000050639108],"genre_scores_gemma":[0.27530175,0.00013450916,0.6194713,0.006832469,0.0002774937,0.00045487343,0.09708374,0.000050199975,0.00039367325],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99865794,0.0000440527,0.00013690745,0.000530301,0.00032754338,0.0003032723],"domain_scores_gemma":[0.99757695,0.00011850021,0.00009073981,0.002131094,0.000036330435,0.00004637071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005075952,0.00012803164,0.0000999772,0.000053271524,0.00022138596,0.00028511733,0.0037289925,0.000030194342,0.0000068864338],"category_scores_gemma":[0.00004403254,0.000075816286,0.000011996511,0.0004124343,0.000059110876,0.0011436236,0.0019309705,0.00012754678,0.00003384108],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002689077,0.000018355226,0.00010798076,0.000020442003,0.000015865822,0.000015812415,0.000100799094,0.0000080472855,0.00022071814,0.0017789737,0.9679003,0.029785866],"study_design_scores_gemma":[0.0012941003,0.00047865193,0.0011861005,0.00015373138,0.00007405408,0.000060479386,0.00032913854,0.36270306,0.003920071,0.014161259,0.6148356,0.0008037017],"about_ca_topic_score_codex":0.00027207768,"about_ca_topic_score_gemma":0.00017172792,"teacher_disagreement_score":0.362695,"about_ca_system_score_codex":0.000034817676,"about_ca_system_score_gemma":0.000042739204,"threshold_uncertainty_score":0.69294584},"labels":[],"label_agreement":null},{"id":"W4322504372","doi":"10.3390/data8030048","title":"Reconstructed River Water Temperature Dataset for Western Canada 1980–2018","year":2023,"lang":"en","type":"article","venue":"Data","topic":"Fish Ecology and Management Studies","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria; Environment and Climate Change Canada","funders":"","keywords":"Environmental science; Baseline (sea); Climate change; Water quality; Air temperature; Ecosystem; Calibration; Aquatic ecosystem; Climatology; Hydrology (agriculture); Geology; Ecology; Oceanography; Statistics","score_opus":0.02553500704588468,"score_gpt":0.23705610665922555,"score_spread":0.21152109961334087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322504372","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81300646,0.000007827564,0.000022921917,0.01506699,0.0017634192,0.0008850265,0.16735603,0.00012564473,0.0017656562],"genre_scores_gemma":[0.30631727,0.00012886389,0.0013157141,0.01793674,0.0002586231,0.00014983142,0.6518451,0.000044930723,0.022002934],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99928993,0.000013775467,0.00008098282,0.00030380618,0.00008049179,0.00023103382],"domain_scores_gemma":[0.9993278,0.00002984406,0.000015563584,0.0005963136,0.0000017589355,0.000028767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001394156,0.000072497205,0.00007744062,0.00001168935,0.00018964632,0.00001265542,0.0005120626,0.000030174027,0.0007125188],"category_scores_gemma":[0.000025947422,0.000052910367,0.0000055609707,0.00006954795,0.00010521049,0.00020882851,0.0014677239,0.000046674,0.00074263],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048497504,0.000004138993,0.037113573,0.0000065424842,0.00002078612,0.000010597403,0.000032146614,0.0000051366515,0.00006658807,0.0000031899099,0.96254057,0.00019187687],"study_design_scores_gemma":[0.00015721854,0.000007868292,0.13553154,0.0000016660754,0.000014835665,0.0000013083709,0.000047706653,0.000072293784,0.00007379454,0.000060160182,0.8639487,0.000082922976],"about_ca_topic_score_codex":0.049916103,"about_ca_topic_score_gemma":0.86067826,"teacher_disagreement_score":0.8107621,"about_ca_system_score_codex":0.00003349376,"about_ca_system_score_gemma":0.000007762235,"threshold_uncertainty_score":0.9564106},"labels":[],"label_agreement":null},{"id":"W4324355422","doi":"10.3390/data8030061","title":"TKGQA Dataset: Using Question Answering to Guide and Validate the Evolution of Temporal Knowledge Graph","year":2023,"lang":"en","type":"article","venue":"Data","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Bank of Canada","funders":"","keywords":"Knowledge graph; Computer science; Question answering; Graph; Parsing; Information retrieval; Process (computing); Artificial intelligence; Natural language processing; Theoretical computer science","score_opus":0.1071454944889778,"score_gpt":0.3625074726673969,"score_spread":0.2553619781784191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324355422","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08492439,0.000114715214,0.9134264,0.00037293273,0.0002467632,0.000115573464,0.00067108474,0.00007466873,0.00005346602],"genre_scores_gemma":[0.8841936,0.000025159135,0.11363296,0.0000760062,0.00013548674,0.000004288825,0.0018767165,0.000011166247,0.00004460639],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992457,0.000056597662,0.00016075939,0.00029866563,0.00011303275,0.00012522799],"domain_scores_gemma":[0.99848807,0.000036799498,0.00004307896,0.0013713299,0.000025281734,0.0000354118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085723033,0.000057380927,0.00006901362,0.0000956306,0.00008646787,0.000059797858,0.001049734,0.00001911347,0.0000012382529],"category_scores_gemma":[0.00008094545,0.000046308567,0.0000069988682,0.00043884033,0.000020939853,0.0005189946,0.002216542,0.000045140547,0.000013510385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037849954,0.00019155626,0.05658204,0.0005711958,0.00016905145,0.000064123706,0.009637585,0.03407161,0.07778551,0.16308056,0.24048729,0.41732162],"study_design_scores_gemma":[0.00007742698,0.000010515904,0.0030443016,0.000047097725,0.0000075638945,0.000006795929,0.00007006378,0.97712225,0.00024535312,0.0014056498,0.017876724,0.00008627885],"about_ca_topic_score_codex":0.0015755313,"about_ca_topic_score_gemma":0.00019496586,"teacher_disagreement_score":0.9430506,"about_ca_system_score_codex":0.000025607604,"about_ca_system_score_gemma":0.000045968896,"threshold_uncertainty_score":0.27627608},"labels":[],"label_agreement":null},{"id":"W4391431000","doi":"10.3390/data9020029","title":"A Comprehensive Data Pipeline for Comparing the Effects of Momentum on Sports Leagues","year":2024,"lang":"en","type":"article","venue":"Data","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland","keywords":"League; Pipeline (software); Momentum (technical analysis); Data science; Computer science; Engineering; Economics; Physics; Financial economics; Mechanical engineering","score_opus":0.1447833057300096,"score_gpt":0.3015851041325388,"score_spread":0.1568017984025292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391431000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75912637,0.09322491,0.048807584,0.00697159,0.016674852,0.003563842,0.058372073,0.00026858036,0.012990231],"genre_scores_gemma":[0.9938167,0.0011561522,0.00012422452,0.00016876652,0.00022880295,0.0000044970607,0.0037460523,0.000016774922,0.0007380583],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990462,0.0000024543983,0.00035323677,0.00041342012,0.000040841147,0.0001438679],"domain_scores_gemma":[0.99792063,0.0001789121,0.0001249756,0.0017348874,0.000015166976,0.000025422865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038302626,0.00009535495,0.00026256492,0.000084066894,0.000055887485,0.00006594407,0.0009195714,0.00002692289,0.000046670662],"category_scores_gemma":[0.0000595003,0.00007509077,0.000033962147,0.000120890465,0.00003994354,0.0002148287,0.00043610137,0.000089219764,0.000046471432],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007645709,0.00022799101,0.02574456,0.0022408064,0.00034478444,0.000027322985,0.00044508558,0.0006315398,0.000028315375,0.15524341,0.7996015,0.015388226],"study_design_scores_gemma":[0.00012612992,0.000019627267,0.002835378,0.00008051565,0.000014625961,8.465734e-7,0.000016060932,0.41215792,0.000024285813,0.0009283249,0.5837256,0.00007074015],"about_ca_topic_score_codex":0.00009573051,"about_ca_topic_score_gemma":0.000016418046,"teacher_disagreement_score":0.41152638,"about_ca_system_score_codex":0.00001049309,"about_ca_system_score_gemma":0.000011798945,"threshold_uncertainty_score":0.30621126},"labels":[],"label_agreement":null},{"id":"W4402134537","doi":"10.3390/data9090104","title":"Interruption Audio & Transcript: Derived from Group Affect and Performance Dataset","year":2024,"lang":"en","type":"article","venue":"Data","topic":"Personal Information Management and User Behavior","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Modalities; Set (abstract data type); Modal; Affect (linguistics); Artificial intelligence; Speech recognition; Machine learning; Data mining; Psychology; Communication","score_opus":0.5195471768816884,"score_gpt":0.4779622355328907,"score_spread":0.0415849413487977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402134537","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96579164,0.0004494138,0.009946185,0.0006029852,0.0005396513,0.00013174668,0.022216387,0.00007141342,0.00025057263],"genre_scores_gemma":[0.9495454,0.00018971645,0.00095060817,0.00033568701,0.000084574975,0.00000639235,0.048557274,0.0000059841773,0.0003243651],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998682,0.000045184497,0.0002705195,0.0003962098,0.0004837116,0.00012234613],"domain_scores_gemma":[0.9988143,0.00015748262,0.00003974764,0.0009154693,0.000015621232,0.00005737974],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010536773,0.00009860168,0.00011349777,0.0001525295,0.00008836502,0.000820177,0.000965774,0.000032673077,0.0010098264],"category_scores_gemma":[0.00008322644,0.00007233722,0.000020974292,0.00024257752,0.000050550538,0.0032853691,0.00043676305,0.00010156243,0.0017253266],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046339024,0.000020432199,0.0058826134,0.000023547369,0.000029019699,0.0000069295374,0.0009887806,0.000001759009,0.0023854435,0.00016237902,0.75383157,0.23662119],"study_design_scores_gemma":[0.00015278764,0.000022566774,0.0973394,0.000038387476,0.00003083211,0.0000031124414,0.00020873667,0.0202799,0.000036355363,0.0001390481,0.8816279,0.00012094294],"about_ca_topic_score_codex":0.0000707461,"about_ca_topic_score_gemma":0.00025418904,"teacher_disagreement_score":0.23650025,"about_ca_system_score_codex":0.000010979607,"about_ca_system_score_gemma":0.000009220642,"threshold_uncertainty_score":0.9999034},"labels":[],"label_agreement":null},{"id":"W4403764039","doi":"10.3390/data9110123","title":"Sustainable Transportation Characteristics Diary—Example of Older (50+) Cyclists","year":2024,"lang":"en","type":"article","venue":"Data","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transport engineering; Geography; Gerontology; Medicine; Engineering","score_opus":0.03274830892476594,"score_gpt":0.3137914969987436,"score_spread":0.28104318807397766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403764039","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6905236,0.0022478818,0.25875717,0.0043981513,0.0029360985,0.0015793603,0.017573448,0.0014588498,0.020525435],"genre_scores_gemma":[0.98304325,0.00017239101,0.00092488993,0.000028887462,0.00009836282,0.0000040764735,0.013319992,0.000009341692,0.0023988236],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925387,0.000039394436,0.00017984648,0.00018836728,0.00019521949,0.00014327886],"domain_scores_gemma":[0.999526,0.00009763013,0.000043352575,0.00022442693,0.000066518005,0.000042050375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005085923,0.000050734816,0.000079319936,0.00005938287,0.00011842561,0.00006654159,0.00021806317,0.000051604904,0.00017571962],"category_scores_gemma":[0.000067078116,0.00005241289,0.000016975471,0.00024869805,0.00006154364,0.00052363373,0.000004871372,0.000055452365,0.000013062375],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000691911,0.00026731825,0.09263642,0.0014393129,0.0001404096,0.00019626216,0.17884803,0.0005664053,0.0003913439,0.60671407,0.08835106,0.03038015],"study_design_scores_gemma":[0.00012047044,0.000009393421,0.26736388,0.000091803675,0.000068013534,2.0363596e-7,0.0040935352,0.0015962475,0.00002898768,0.00051538285,0.72596365,0.00014843183],"about_ca_topic_score_codex":0.006754747,"about_ca_topic_score_gemma":0.0009780759,"teacher_disagreement_score":0.6376126,"about_ca_system_score_codex":0.000015028854,"about_ca_system_score_gemma":0.0001366004,"threshold_uncertainty_score":0.99985933},"labels":[],"label_agreement":null},{"id":"W4403764051","doi":"10.3390/data9110122","title":"Towards a Taxonomy Machine: A Training Set of 5.6 Million Arthropod Images","year":2024,"lang":"en","type":"article","venue":"Data","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Guelph","funders":"Ministry of Colleges and Universities; Canada First Research Excellence Fund; Ministero dello Sviluppo Economico; Ontario Ministry of Economic Development, Job Creation and Trade; Guanacaste Dry Forest Conservation Fund; Genome Canada; Ontario Genomics; Forest Conservation Fund; Polar Knowledge Canada","keywords":"Taxonomy (biology); Arthropod; Artificial intelligence; Set (abstract data type); Training set; Computer science; Natural language processing; Ecology; Biology; Programming language","score_opus":0.1436977197374064,"score_gpt":0.3139530033199601,"score_spread":0.17025528358255373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403764051","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31680843,0.007988499,0.013259744,0.011000249,0.0019370959,0.0013531444,0.155206,0.0007052075,0.49174166],"genre_scores_gemma":[0.99235463,0.0003642346,0.00066076766,0.00013628871,0.00005346219,0.000016697579,0.006077916,0.000010649565,0.00032536435],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993692,0.000014183667,0.00010971921,0.00023226571,0.00014589696,0.0001287019],"domain_scores_gemma":[0.9995313,0.000013851152,0.00002083517,0.000389773,0.0000021201474,0.000042073058],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016394697,0.00006749753,0.00007881739,0.000017211307,0.000033423505,0.000035799138,0.00032277603,0.000023877508,0.060932983],"category_scores_gemma":[0.000025462447,0.000057058485,0.000024130823,0.00017574565,0.00012108422,0.00022960968,0.00042508144,0.000059056863,0.0009168705],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011913628,0.000048170652,0.0018105354,0.00006396097,0.000028907982,0.000035815265,0.0006381955,0.0000039697843,0.0061761937,0.00086490787,0.7482016,0.24211583],"study_design_scores_gemma":[0.00009071879,0.000018859926,0.0058147623,0.000017687169,0.000011694419,0.00001088668,0.0010165779,0.0010707774,0.00081274024,0.000043738466,0.99100846,0.000083121275],"about_ca_topic_score_codex":0.00033687358,"about_ca_topic_score_gemma":0.00014769529,"teacher_disagreement_score":0.67554617,"about_ca_system_score_codex":0.00006461256,"about_ca_system_score_gemma":0.00000936678,"threshold_uncertainty_score":0.999861},"labels":[],"label_agreement":null},{"id":"W4403874483","doi":"10.3390/data9110125","title":"Enhancing Access Across Europe for Documents Published According to Freedom of Information Act: Applying Woogle Design and Technique to Estonian Public Information Act Document","year":2024,"lang":"en","type":"article","venue":"Data","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Estonian; Freedom of information; Public access; Political science; Computer science; Information retrieval; Public information; World Wide Web; Public administration; Law; Linguistics","score_opus":0.04938026663383825,"score_gpt":0.3405888488246131,"score_spread":0.29120858219077483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403874483","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00676191,0.00002508736,0.98901236,0.0016374699,0.0004141018,0.0016753139,0.000071360555,0.00023474352,0.00016763984],"genre_scores_gemma":[0.6212167,0.000017913584,0.37734157,0.0005756566,0.000045338365,0.0004767942,0.0003055278,0.000009902021,0.000010566886],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99847746,0.000036887515,0.00050113094,0.00030976432,0.00030681293,0.0003679305],"domain_scores_gemma":[0.9983588,0.0002204595,0.00014085972,0.0009803816,0.00017827832,0.000121246085],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0019152302,0.00015676238,0.00019283261,0.00038527237,0.00017221243,0.0068888464,0.0025050712,0.000062951774,0.0000038626645],"category_scores_gemma":[0.0010706028,0.00013767365,0.000021168058,0.000927967,0.000019769848,0.04700531,0.0031806554,0.00010161176,0.000024628453],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005213841,0.000026574065,0.0007756387,0.00081221014,0.00007008245,0.0000028467896,0.007269779,0.0004752627,0.0045066117,0.011341656,0.013219682,0.96144754],"study_design_scores_gemma":[0.0016610529,0.0007289785,0.0055085896,0.0015743566,0.0000665094,0.0000765156,0.0033734476,0.17446624,0.12077369,0.0046454407,0.68543035,0.0016948227],"about_ca_topic_score_codex":0.0001490947,"about_ca_topic_score_gemma":0.000029770996,"teacher_disagreement_score":0.9597527,"about_ca_system_score_codex":0.000066186534,"about_ca_system_score_gemma":0.00015354034,"threshold_uncertainty_score":0.9941421},"labels":[],"label_agreement":null},{"id":"W4404073012","doi":"10.3390/data9110129","title":"Data Hub for Life Cycle Assessment of Climate Change Solutions—Hydrogen Case Study","year":2024,"lang":"en","type":"article","venue":"Data","topic":"Environmental Impact and Sustainability","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Innovation Council; National Research Council Canada","funders":"","keywords":"Climate change; Life-cycle assessment; Environmental science; Climatology; Computer science; Economics; Oceanography; Geology","score_opus":0.15678831602495247,"score_gpt":0.4059222087149405,"score_spread":0.24913389268998803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404073012","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9793214,0.00023539986,0.00058035407,0.00032421967,0.00012153291,0.0013968024,0.017386986,0.00005077542,0.0005825369],"genre_scores_gemma":[0.9966593,0.00007131607,0.0010059796,0.00007471827,0.000057135585,0.000065453576,0.0020228578,0.000016393446,0.00002689429],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985395,0.00006568213,0.0002455666,0.0005939446,0.00023516857,0.00032012336],"domain_scores_gemma":[0.99740094,0.00007657728,0.00004267759,0.0023546873,0.0000021925723,0.00012293889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012197723,0.000119691846,0.00014623087,0.000023156232,0.00016227085,0.000045600285,0.0009290454,0.000033923316,0.0006288469],"category_scores_gemma":[0.00007042263,0.00010548646,0.00002643228,0.00014004312,0.00012780698,0.0010892694,0.0047125677,0.00008314267,0.000054463006],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000075993725,0.0069840653,0.7761865,0.0009562745,0.0004198176,0.002158273,0.004860628,0.00082571845,0.00096269435,0.0004177498,0.034532227,0.17162006],"study_design_scores_gemma":[0.0011320543,0.0007063547,0.2082609,0.00004163165,0.00049626746,0.00023286924,0.015077431,0.70899415,0.00003165648,0.00044255704,0.06393193,0.0006522052],"about_ca_topic_score_codex":0.001590726,"about_ca_topic_score_gemma":0.0009964971,"teacher_disagreement_score":0.70816845,"about_ca_system_score_codex":0.00013996336,"about_ca_system_score_gemma":0.00002060948,"threshold_uncertainty_score":0.68854326},"labels":[],"label_agreement":null},{"id":"W4407296790","doi":"10.3390/data10020024","title":"Visual Footprint of Separation Through Membrane Distillation on YouTube","year":2025,"lang":"en","type":"article","venue":"Data","topic":"Membrane Separation Technologies","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Footprint; Separation (statistics); Distillation; Chromatography; Computer science; Process engineering; Environmental science; Chemistry; Engineering; Geography; Machine learning; Archaeology","score_opus":0.042027780235211226,"score_gpt":0.35747430704520217,"score_spread":0.31544652680999097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407296790","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88357806,0.000025860576,0.016934333,0.0011896226,0.00024197661,0.000434245,0.00018002254,0.0001970667,0.097218834],"genre_scores_gemma":[0.997783,0.000023030827,0.0011821678,0.0000904776,0.000008634687,0.0000052680457,0.00044627496,0.0000035997343,0.00045755575],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99920917,0.000026112248,0.00019651516,0.00028504306,0.00019245628,0.00009073131],"domain_scores_gemma":[0.9990689,0.000049228838,0.00007377824,0.0007920265,0.0000056346253,0.000010391782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001485148,0.000075266245,0.00009852488,0.00002947263,0.00005124692,0.000014091729,0.00043605274,0.000056682715,0.0003424466],"category_scores_gemma":[0.00017862913,0.00006683914,0.000014091001,0.0002491408,0.00010586547,0.00021823758,0.00046584735,0.000060625727,0.00019184715],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042706195,0.0008939925,0.03676224,0.00019362944,0.00012564923,0.0000058187543,0.001116663,0.024502104,0.56867266,0.09909041,0.07079814,0.19741164],"study_design_scores_gemma":[0.00066818134,0.00018724836,0.06348823,0.000056024997,0.00004201913,0.0000012724015,0.00026213482,0.032621782,0.78024036,0.0056662573,0.11646824,0.00029826886],"about_ca_topic_score_codex":0.0001474944,"about_ca_topic_score_gemma":0.0000914725,"teacher_disagreement_score":0.21156769,"about_ca_system_score_codex":0.00004385207,"about_ca_system_score_gemma":0.000008338999,"threshold_uncertainty_score":0.37495503},"labels":[],"label_agreement":null},{"id":"W4409090063","doi":"10.3390/data10040049","title":"Predictors of Immune Fitness and the Alcohol Hangover: Survey Data from UK and Irish Adults","year":2025,"lang":"en","type":"article","venue":"Data","topic":"Health Promotion and Cardiovascular Prevention","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Irish; Psychology; Survey data collection; Demography; Statistics; Sociology; Mathematics; Philosophy; Linguistics","score_opus":0.06829445173036965,"score_gpt":0.3543744911376602,"score_spread":0.28608003940729054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409090063","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95874864,0.014507307,0.005551422,0.0020569137,0.00050923624,0.0012002601,0.016600803,0.000034076704,0.000791372],"genre_scores_gemma":[0.97281027,0.0023611996,0.000088460525,0.00020164417,0.00006149631,0.0000061057845,0.024223162,0.000005961822,0.00024168156],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985694,0.00059641903,0.00025994013,0.00030945483,0.00017460714,0.000090153764],"domain_scores_gemma":[0.997552,0.00019355312,0.000066735425,0.0020903647,0.000050395614,0.00004698383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004187224,0.00006803517,0.00027127104,0.000028102859,0.000052013675,0.000014270289,0.00033853052,0.000060068425,0.000057856207],"category_scores_gemma":[0.0010070285,0.000046922574,0.000024216642,0.000115210336,0.00012830258,0.00011152464,0.0009286689,0.00011309218,0.0000030209226],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013335571,0.0002824409,0.5570929,0.0014927282,0.002537442,0.000014248625,0.0007792936,3.527592e-7,0.00022614538,0.000081509286,0.22027047,0.21588887],"study_design_scores_gemma":[0.00521454,0.000017948372,0.98086596,0.00031833968,0.0002500654,0.000004419287,0.000101903526,0.0012604541,0.000041846037,0.000021920092,0.011861768,0.000040850442],"about_ca_topic_score_codex":0.0041102404,"about_ca_topic_score_gemma":0.00037405087,"teacher_disagreement_score":0.42377302,"about_ca_system_score_codex":0.0000061591277,"about_ca_system_score_gemma":0.00006785466,"threshold_uncertainty_score":0.62134814},"labels":[],"label_agreement":null},{"id":"W4413788822","doi":"10.3390/data10090138","title":"A Curated Dataset of Regional Meteor Events with Simultaneous Optical and Infrasound Observations (2006–2011)","year":2025,"lang":"en","type":"article","venue":"Data","topic":"Astro and Planetary Science","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Laboratory Directed Research and Development; Sandia National Laboratories; U.S. Department of Energy; National Nuclear Security Administration; National Science Foundation","keywords":"Meteor (satellite); Infrasound; Meteoroid; Geology; Computer science; Meteorology; Environmental science; Acoustics; Physics; Astronomy","score_opus":0.03781690681622607,"score_gpt":0.27528224317643446,"score_spread":0.2374653363602084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413788822","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75647634,0.000118910706,0.07384053,0.0007033746,0.000084902254,0.00032977492,0.1675979,0.000018252857,0.00083003065],"genre_scores_gemma":[0.89187145,0.000002436837,0.009989895,0.00008131791,0.00002184108,0.0000018131313,0.097814456,0.0000022890972,0.00021451994],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994755,0.000014701829,0.00011689184,0.00019718219,0.000093594805,0.000102165526],"domain_scores_gemma":[0.99922186,0.00019748452,0.00005629951,0.0004572534,0.00002747397,0.000039600876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000792791,0.00006575626,0.00009150582,0.00002349163,0.000057371843,0.000015989286,0.00032259928,0.000012412927,0.00012411253],"category_scores_gemma":[0.00001675527,0.000050887644,0.000005028061,0.00011131472,0.0000784315,0.00023424956,0.00013969268,0.00006292444,0.000010488377],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001619744,0.00025866533,0.78742075,0.00003266584,0.00027671803,0.000009358138,0.00006477105,0.0014301899,0.0009311923,0.01314328,0.18260643,0.013663997],"study_design_scores_gemma":[0.0018742828,0.00024738538,0.33890906,0.0001359585,0.00030387504,0.000010552918,0.00047479031,0.10793642,0.00014833566,0.0018538288,0.5476012,0.0005043261],"about_ca_topic_score_codex":0.0003139715,"about_ca_topic_score_gemma":0.000030715295,"teacher_disagreement_score":0.44851172,"about_ca_system_score_codex":0.0000018237457,"about_ca_system_score_gemma":0.00007446032,"threshold_uncertainty_score":0.2075138},"labels":[],"label_agreement":null},{"id":"W4415402372","doi":"10.3390/data10100167","title":"Beyond the List: A Framework for the Design of Next-Generation MEDLINE Search Tools","year":2025,"lang":"en","type":"article","venue":"Data","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Exploratory search; Core (optical fiber); Analytics; Exploratory analysis; Visual analytics; Key (lock)","score_opus":0.3416572491239892,"score_gpt":0.3815665633292202,"score_spread":0.03990931420523097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415402372","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029377663,0.0008156883,0.979703,0.01840831,0.00032940926,0.00030157168,0.00005021655,0.00002027799,0.000077761826],"genre_scores_gemma":[0.27662364,0.00026164786,0.71824425,0.0039408286,0.00035621566,0.000068432135,0.00018531215,0.000005915262,0.000313751],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993822,0.00007312934,0.00011995593,0.0001890549,0.00012547312,0.00011019385],"domain_scores_gemma":[0.99585575,0.0024261659,0.00003116869,0.001625088,0.00005329392,0.000008557959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009607386,0.00004845279,0.00007451987,0.000020393021,0.00015181118,0.00021398897,0.002719639,0.00003575207,0.000004920315],"category_scores_gemma":[0.0009033773,0.000024201194,0.000017285181,0.00021880548,0.000061756524,0.00028380266,0.00068281457,0.00007744694,0.0000024539418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012010034,0.000028961067,0.00007138034,0.000018608303,0.00004452292,7.506341e-7,0.00053331413,0.00047211052,0.0015325038,0.69917226,0.10106957,0.19704401],"study_design_scores_gemma":[0.00010478254,0.000029910232,0.00043445823,0.00001669074,0.000018953768,0.0000010563841,0.00013247936,0.9373164,0.005299964,0.04467268,0.011923995,0.000048584963],"about_ca_topic_score_codex":0.000037724116,"about_ca_topic_score_gemma":0.000024428235,"teacher_disagreement_score":0.93684435,"about_ca_system_score_codex":0.0000054716384,"about_ca_system_score_gemma":0.00009935519,"threshold_uncertainty_score":0.50538117},"labels":[],"label_agreement":null},{"id":"W4415864397","doi":"10.3390/data10110180","title":"NutritionVerse3D2D: Large 3D Object and 2D Image Food Dataset for Dietary Intake Estimation","year":2025,"lang":"en","type":"article","venue":"Data","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Waterloo","funders":"National Research Council Sri Lanka","keywords":"Benchmark (surveying); Viewpoints; Process (computing); Food intake; Object (grammar); Pairwise comparison; Image (mathematics); Face (sociological concept)","score_opus":0.04826100366341042,"score_gpt":0.34371247882373784,"score_spread":0.29545147516032744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415864397","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015879283,0.008386074,0.026992181,0.022143796,0.0005158866,0.002423449,0.92205036,0.00012210097,0.0014868537],"genre_scores_gemma":[0.11281385,0.0011479756,0.063198954,0.0048423344,0.0003080278,0.00012970615,0.81743765,0.00001781042,0.00010370309],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993817,0.000008648985,0.00013382721,0.0002548847,0.000087349035,0.00013355356],"domain_scores_gemma":[0.99937737,0.0000793133,0.000024924671,0.00043566345,0.000042213785,0.000040526884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000146016,0.00007991161,0.00015241357,0.000047508453,0.00013831623,0.000021193902,0.00009897732,0.00003385906,0.00003785463],"category_scores_gemma":[0.00020339739,0.00007288513,0.000018258099,0.000093790186,0.00004054307,0.00018677027,0.00027609352,0.00005853191,0.000012009615],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022230587,0.00026723102,0.00056758075,0.0006075707,0.0001089421,0.0000058237742,0.000011311431,9.041165e-8,0.0001316563,0.00076883414,0.99421394,0.0030947241],"study_design_scores_gemma":[0.0046356996,0.0003163275,0.010425071,0.00024013189,0.0002906359,0.000012178096,0.00023888868,0.004665985,0.00008872354,0.0023921526,0.97657764,0.000116537645],"about_ca_topic_score_codex":0.000028784601,"about_ca_topic_score_gemma":0.00006322647,"teacher_disagreement_score":0.10461274,"about_ca_system_score_codex":0.000016539529,"about_ca_system_score_gemma":0.00002340211,"threshold_uncertainty_score":0.29721695},"labels":[],"label_agreement":null},{"id":"W7106546220","doi":"10.3390/data10120195","title":"DECOVID: A UK Two-Center Harmonized Database of Acute Care Electronic Health Records for COVID-19 Research","year":2025,"lang":"en","type":"article","venue":"Data","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Global Health Research","funders":"Leeds Biomedical Research Centre; Medical Research Council; NIHR Cambridge Biomedical Research Centre; University College London Hospitals NHS Foundation Trust; British Heart Foundation; University College London; Innovation and Technology Commission; Research Councils UK; University Hospitals Birmingham NHS Foundation Trust; Department of Health and Social Care; National Institute for Health and Care Research; Birmingham Biomedical Research Centre; Engineering and Physical Sciences Research Council; UK Research and Innovation; Royal Academy of Engineering; Wellcome Trust; Wellcome","keywords":"Electronic health record; Health records; Raw data; Acute care; Health care; Electronic database; Health data; Exploratory research","score_opus":0.15151998667923636,"score_gpt":0.5125048844023236,"score_spread":0.3609848977230872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106546220","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025172785,0.004424416,0.90949976,0.067988195,0.0008228169,0.0026273874,0.011469522,0.00026541197,0.00038521417],"genre_scores_gemma":[0.51469237,0.0031573635,0.399761,0.03378278,0.00049087,0.0007550717,0.045525633,0.00011499754,0.0017199381],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961579,0.00079622,0.0005028283,0.001101059,0.0004916513,0.00095035497],"domain_scores_gemma":[0.9938053,0.00096616073,0.00017434082,0.0044306177,0.0003269058,0.00029666745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038406693,0.00016651725,0.00034685843,0.00041434073,0.00045129348,0.000117754804,0.00506632,0.00006232217,0.00003759667],"category_scores_gemma":[0.0015694068,0.00016366654,0.00005345048,0.0010537133,0.00008002636,0.000363352,0.0034999198,0.0006736501,0.000014800902],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006828601,0.00026803027,0.026335275,0.005347175,0.00030935009,0.000036001456,0.0036556814,0.000059268696,0.000174492,0.09713532,0.7010779,0.16491866],"study_design_scores_gemma":[0.0038002476,0.0005563092,0.0004260816,0.00026199062,0.000022809925,0.000016154012,0.00022937493,0.08093273,0.00013077333,0.002864387,0.9104913,0.00026786025],"about_ca_topic_score_codex":0.0068537127,"about_ca_topic_score_gemma":0.0037993155,"teacher_disagreement_score":0.5121751,"about_ca_system_score_codex":0.0006110038,"about_ca_system_score_gemma":0.006137364,"threshold_uncertainty_score":0.99975973},"labels":[],"label_agreement":null}]}