{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":13,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":13,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"46bc4f172fb1","filters":{"venue":"Environmental Data Science"}},"results":[{"id":"W4225913161","doi":"10.1017/eds.2022.2","title":"Evolution of machine learning in environmental science—A perspective","year":2022,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Government of British Columbia; University of British Columbia","funders":"","keywords":"Parametrization (atmospheric modeling); Perspective (graphical); Computer science; Artificial intelligence; Artificial neural network; Machine learning; Climate science; Data assimilation; Deep learning; Convolutional neural network; General Circulation Model; Climate change; Physics; Meteorology; Ecology","retraction":null,"screen_n_in":null,"score":{"opus":0.01709476070128623,"gpt":0.2403423857968685,"spread":0.2232476250955823,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.00326723,0.0001952904,0.0001915856,0.0002708544,0.001329793,0.00003470502,0.003066578,0.00002777272,0.005378509],"category_scores_gemma":[0.0002233261,0.0001986003,0.0000338355,0.001570441,0.007015243,0.00161517,0.009462032,0.0005289286,0.0002006575],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005339806,"about_ca_system_score_gemma":0.00008290609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001311037,"about_ca_topic_score_gemma":0.00003554123,"domain_scores_codex":[0.9953518,0.000140986,0.0003502716,0.001349001,0.002110489,0.0006974874],"domain_scores_gemma":[0.9986412,0.00005103568,0.0001967115,0.000930243,0.000001330628,0.0001795139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00003359809,0.0005273837,0.3378569,0.000001160677,0.000001877693,0.00001705827,0.0008726016,0.09439182,0.5637677,0.0002475762,0.00003263904,0.002249735],"study_design_scores_gemma":[0.0007447324,0.0006438684,0.6523187,0.000007484208,0.00001415628,0.0001118621,0.003228066,0.3304555,0.006950476,0.0008073635,0.004154177,0.0005636066],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99503,0.0001207305,0.00006567637,0.0001078274,0.0001471631,0.00024394,0.0003264566,0.00003382498,0.003924415],"genre_scores_gemma":[0.9985408,0.00001446946,0.001129995,0.00006219769,0.00001207557,0.0000144076,0.00006510135,0.00001404989,0.0001468652],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5568172,"threshold_uncertainty_score":0.9999703,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385559495","doi":"10.1017/eds.2023.22","title":"Environmental sensor placement with convolutional Gaussian neural processes","year":2023,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute","funders":"Natural Environment Research Council; Engineering and Physical Sciences Research Council; Sight Research UK; UK Research and Innovation; Alan Turing Institute; National Science Foundation","keywords":"Computer science; Gaussian process; Convolutional neural network; Scalability; Gaussian; Flexibility (engineering); Kriging; Artificial intelligence; Machine learning; Probabilistic logic; Anomaly detection; Sampling (signal processing); Data mining; Process (computing); Computer vision; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02121041352193427,"gpt":0.2344499535427245,"spread":0.2132395400207902,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004373988,0.0002760907,0.0001639231,0.0001886883,0.0007075232,0.0003930258,0.003970802,0.00003946712,0.0001846225],"category_scores_gemma":[0.00003019135,0.0002201664,0.0000198057,0.001142958,0.001292085,0.004068795,0.00262331,0.0001702648,0.0009321672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001570823,"about_ca_system_score_gemma":0.0002454552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007455243,"about_ca_topic_score_gemma":0.000004422596,"domain_scores_codex":[0.996179,0.00002837644,0.0002605146,0.001395557,0.00135811,0.0007784358],"domain_scores_gemma":[0.9979798,0.00005787578,0.0001306823,0.001524989,0.000006154416,0.0003005558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000453075,0.005090686,0.3522173,0.0008607078,0.0003298466,0.004003393,0.009746279,0.01141205,0.3494504,0.04601667,0.02571781,0.1947017],"study_design_scores_gemma":[0.002051304,0.0009708026,0.660558,0.0001231084,0.00004154575,0.0008377553,0.002142676,0.2946794,0.01321736,0.0008719897,0.02234652,0.002159562],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8058684,0.0004649872,0.1792326,0.005012352,0.000908946,0.001369928,0.002589601,0.001126724,0.003426476],"genre_scores_gemma":[0.9874138,0.0001266568,0.01147996,0.0002753368,0.00005202451,0.00002595598,0.0002753904,0.00001460575,0.0003362928],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3362331,"threshold_uncertainty_score":0.9998457,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407998460","doi":"10.1017/eds.2024.53","title":"OpenForest: a data catalog for machine learning in forest monitoring","year":2025,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Institut de Valorisation des Données; Deutsche Forschungsgemeinschaft; Canadian Institute for Advanced Research","keywords":"Computer science; Data science; Forestry; Artificial intelligence; Machine learning; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.03437498071578052,"gpt":0.3017214673339243,"spread":0.2673464866181438,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001080246,0.0001391613,0.0001228533,0.00008459633,0.0005111798,0.0001095754,0.003274333,0.00003710606,0.00005617109],"category_scores_gemma":[0.000192375,0.0001353334,0.00001403537,0.0005356279,0.0008038715,0.001486562,0.004857577,0.000183133,0.0001740397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002653693,"about_ca_system_score_gemma":0.00003681404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001521218,"about_ca_topic_score_gemma":0.0008008701,"domain_scores_codex":[0.9979575,0.0000222113,0.0002351096,0.001035758,0.0003432552,0.0004062046],"domain_scores_gemma":[0.9976479,0.00009476161,0.00006277983,0.002102673,0.0000011197,0.00009070189],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002000698,0.0001725155,0.864271,0.000009270905,0.000005499972,0.000004386287,0.0001774068,0.005368114,0.04039706,0.000178582,0.001624449,0.0877717],"study_design_scores_gemma":[0.0004349313,0.00002783148,0.6222515,0.00003242747,0.00001384611,0.000006996486,0.0002088839,0.2559857,0.001767545,0.0002661103,0.1187619,0.0002422615],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9717398,0.0002690212,0.01274085,0.0009205618,0.0004214277,0.001291231,0.001337245,0.00009768471,0.01118223],"genre_scores_gemma":[0.9854185,0.00007281638,0.01209309,0.00006959161,0.00002519859,0.000009650813,0.00145054,0.00001041013,0.0008502271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2506176,"threshold_uncertainty_score":0.6084581,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4380482266","doi":"10.1017/eds.2023.8","title":"Toward low-cost automated monitoring of life below water with deep learning","year":2023,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Identification and Quantification in Food","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; Fisheries and Oceans Canada; Dalhousie University","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Ocean Frontier Institute","keywords":"Underwater; Marine ecosystem; Computer science; Deep learning; Scale (ratio); Environmental science; Fish <Actinopterygii>; Ecosystem; Range (aeronautics); Artificial intelligence; Deep sea; Environmental resource management; Machine learning; Fishery; Oceanography; Ecology; Engineering; Geography; Geology; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.0342005132883659,"gpt":0.2750820688929078,"spread":0.2408815556045419,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003425692,0.00007035223,0.00005702507,0.00005411773,0.0001737279,0.00003601372,0.0005925947,0.00002918605,0.00003753771],"category_scores_gemma":[0.0000480972,0.00005515607,0.00001148359,0.0001656233,0.0003860104,0.00003189829,0.000414129,0.00004750246,0.0002247327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001170036,"about_ca_system_score_gemma":0.00002196158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004734008,"about_ca_topic_score_gemma":7.422432e-7,"domain_scores_codex":[0.9989989,0.00002002312,0.0001400191,0.0003935842,0.0002593047,0.0001881568],"domain_scores_gemma":[0.9992976,0.000004254617,0.00005422911,0.0005634287,0.000009602794,0.0000708886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000008822461,0.00002431357,0.02233549,0.000006598993,0.000006042987,5.091026e-7,0.0001088232,0.0005212046,0.9759542,0.000004684237,0.0001314948,0.0008978299],"study_design_scores_gemma":[0.0001586388,0.00003352871,0.1206456,0.000006934678,0.000004431149,0.000002688386,0.0005485881,0.004213407,0.868724,4.85935e-7,0.005559241,0.0001024445],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9990584,0.0000260954,0.0004568103,0.00006359022,0.0001217939,0.00009434356,0.00005131805,0.00004493027,0.00008273029],"genre_scores_gemma":[0.9978064,0.0001060776,0.0004015454,0.00001397733,0.00003105372,0.000009495122,0.00133163,0.000009084176,0.0002907395],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1072302,"threshold_uncertainty_score":0.2888559,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4383100035","doi":"10.1017/eds.2023.11","title":"A novel workflow for streamflow prediction in the presence of missing gauge observations","year":2023,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Agriculture and Agri-Food Canada","funders":"DeepMind","keywords":"Streamflow; Missing data; Imputation (statistics); Categorical variable; Flood forecasting; Computer science; Warning system; Leverage (statistics); Flood myth; Regression; Econometrics; Environmental science; Data mining; Statistics; Artificial intelligence; Machine learning; Drainage basin; Cartography; Mathematics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.06838411252735653,"gpt":0.2704303668683858,"spread":0.2020462543410292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001414756,0.00008945051,0.00008575959,0.00006171344,0.0004016732,0.0000230455,0.001288501,0.00002431823,0.00008515612],"category_scores_gemma":[0.0001402553,0.00006757124,0.00001819448,0.0006883963,0.001209989,0.001019076,0.001057374,0.00006709756,0.0000703453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005811924,"about_ca_system_score_gemma":0.000006223773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001065651,"about_ca_topic_score_gemma":0.00007131995,"domain_scores_codex":[0.9986134,0.0000265304,0.0001893705,0.0004512588,0.0004125482,0.0003069409],"domain_scores_gemma":[0.9990992,0.0001633594,0.00006175671,0.0006437967,0.000001022278,0.00003085893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004875231,0.0006539229,0.6895135,0.00003197447,0.00002055559,0.000009491977,0.004292204,0.01657093,0.2436085,0.0007662626,0.02294603,0.02153782],"study_design_scores_gemma":[0.0002789336,0.00004985119,0.9290227,0.00001431068,0.0000135162,0.000002407299,0.0005469973,0.06202416,0.0007057315,0.0009798239,0.006267352,0.00009420473],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9905279,0.00001754855,0.004702895,0.002017461,0.0001744162,0.0006997561,0.0008775856,0.00003266739,0.00094982],"genre_scores_gemma":[0.9948032,0.00003767225,0.004485674,0.0001661428,0.00001611981,0.0000566115,0.0002568825,0.000004830419,0.0001728661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2429028,"threshold_uncertainty_score":0.4458257,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4393443031","doi":"10.1017/eds.2023.44","title":"Ideology from topic mixture statistics: inference method and example application to carbon tax public opinion","year":2024,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Climate Change Communication and Perception","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Ideology; Inference; Public opinion; Statistics; Political science; Econometrics; Sociology; Economics; Mathematics; Epistemology; Law; Politics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.3705096812719827,"gpt":0.4768085917294069,"spread":0.1062989104574242,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001072793,0.00007059809,0.00007211043,0.00007786833,0.0003577849,0.0002350825,0.0008185625,0.00005313986,0.0005960547],"category_scores_gemma":[0.0002035942,0.00007070224,0.000005910246,0.0002646574,0.0004019268,0.0006032168,0.0007584468,0.0001075251,0.000123378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002311848,"about_ca_system_score_gemma":0.00006083887,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009549919,"about_ca_topic_score_gemma":0.004438734,"domain_scores_codex":[0.9987055,0.0001441003,0.0001197306,0.0004926486,0.0003295101,0.0002084837],"domain_scores_gemma":[0.99887,0.0003126432,0.00003392024,0.0006237046,0.00000731761,0.0001523798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005208185,0.00006318408,0.02895669,0.00001664999,0.000008440867,0.000001198291,0.02310253,0.000005321697,0.05574158,0.0311598,0.002292293,0.8586471],"study_design_scores_gemma":[0.00006175553,0.00002566224,0.06075214,0.0000162625,0.000007787462,9.925317e-7,0.002397965,0.008893374,0.00008551268,0.003462635,0.9241232,0.000172689],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3783028,0.003518006,0.5460491,0.04021213,0.002857043,0.001915746,0.009474925,0.0003920923,0.01727817],"genre_scores_gemma":[0.9731275,0.005288589,0.01945687,0.000457589,0.0001695831,0.0000341054,0.001192726,0.000006574466,0.0002664503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.921831,"threshold_uncertainty_score":0.9970456,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389641434","doi":"10.1017/eds.2023.40","title":"A novel heuristic method for detecting overfit in unsupervised classification of climate model data","year":2023,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Climate variability and models","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Environment Research Council; Sight Research UK; UK Research and Innovation; National Science Foundation","keywords":"Overfitting; Computer science; Cluster analysis; Robustness (evolution); Heuristic; Machine learning; Artificial intelligence; Mixture model; Data mining; Class (philosophy); Gaussian; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.1606655707973861,"gpt":0.3548466895345715,"spread":0.1941811187371854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004314637,0.0001486236,0.0001850656,0.0001053824,0.000240118,0.00003817548,0.002632226,0.00005368475,0.0001133684],"category_scores_gemma":[0.0004400075,0.0001501417,0.00002283605,0.0007386414,0.0006108572,0.001852424,0.004821476,0.0001098116,0.00008627174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000221538,"about_ca_system_score_gemma":0.00003064906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002436222,"about_ca_topic_score_gemma":0.0001652684,"domain_scores_codex":[0.9971969,0.00003727605,0.0004291749,0.001250128,0.0005662324,0.0005203481],"domain_scores_gemma":[0.9971322,0.0002897106,0.0001381248,0.002336268,0.000002107497,0.0001015428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003081933,0.0002052396,0.01084768,0.00003192442,0.000002264286,6.051226e-7,0.0002938042,0.06222778,0.9159171,0.0001828594,0.00006928932,0.01019064],"study_design_scores_gemma":[0.0003737341,0.00002421489,0.06059742,0.00001400472,0.00001239612,0.000002405714,0.0002447841,0.9367129,0.001275631,0.0003808926,0.0002059599,0.0001556169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8231576,0.000008508883,0.1669672,0.0001636149,0.00009634873,0.0007270146,0.008278099,0.00005196374,0.000549592],"genre_scores_gemma":[0.8960974,0.0001082501,0.1024382,0.00005388105,0.000009708505,0.00002930588,0.001226635,0.00001599772,0.00002056969],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9146414,"threshold_uncertainty_score":0.6122599,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4412734594","doi":"10.1017/eds.2025.10013","title":"Tree semantic segmentation from aerial image time series","year":2025,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Computer Research Institute of Montréal","funders":"","keywords":"Tree (set theory); Series (stratigraphy); Artificial intelligence; Computer science; Aerial image; Segmentation; Image (mathematics); Computer vision; Pattern recognition (psychology); Mathematics; Geology","retraction":null,"screen_n_in":null,"score":{"opus":0.007343167933572374,"gpt":0.2351329130290553,"spread":0.2277897450954829,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003141101,0.000147688,0.0001147958,0.00004769486,0.0005088574,0.0001523138,0.001172156,0.00003590989,0.002588625],"category_scores_gemma":[0.00003464748,0.0001429616,0.00002279609,0.0004019984,0.001652626,0.001738962,0.001382529,0.00008958045,0.004357927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002008164,"about_ca_system_score_gemma":0.00002398473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00048618,"about_ca_topic_score_gemma":0.00007365833,"domain_scores_codex":[0.9981894,0.00003649445,0.0002055341,0.0008037651,0.0004735869,0.0002911754],"domain_scores_gemma":[0.9985962,0.00003642543,0.00006648884,0.00120373,0.000001309366,0.00009584382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0000100658,0.00006505172,0.002772945,7.739966e-7,0.000004410146,0.000002060829,0.0001084206,0.00002703445,0.964139,0.00002361559,0.007797516,0.0250491],"study_design_scores_gemma":[0.0009848963,0.00007836652,0.5441269,0.0000369525,0.0001029721,0.00001791379,0.0009544222,0.03095222,0.3568121,0.00228982,0.06285986,0.0007836071],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9388581,0.00003019397,0.005427734,0.0009968359,0.0003343505,0.0004174069,0.0004988869,0.0001004987,0.05333597],"genre_scores_gemma":[0.9565457,0.00004532348,0.03862978,0.0003214737,0.00006223571,0.000005157619,0.0009502778,0.00001275838,0.003427355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6073269,"threshold_uncertainty_score":0.9983231,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396681541","doi":"10.1017/eds.2024.13","title":"Unsupervised clustering identifies thermohaline staircases in the Canada Basin of the Arctic Ocean","year":2024,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Manitoba; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Temperature salinity diagrams; Stratification (seeds); Salinity; Arctic; Thermohaline circulation; Geology; Structural basin; The arctic; Computer science; Climatology; Oceanography; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01429898631674975,"gpt":0.2024608052500858,"spread":0.188161818933336,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007634048,0.00008754532,0.00007337138,0.00003120621,0.0002396622,0.000087416,0.001607587,0.0000123897,0.0005229109],"category_scores_gemma":[0.00005223276,0.0000466352,0.00001829971,0.0003429983,0.0007482352,0.0006034546,0.0002129856,0.0001361368,0.000009988448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003117313,"about_ca_system_score_gemma":0.000212273,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2636238,"about_ca_topic_score_gemma":0.340309,"domain_scores_codex":[0.9986333,0.00006523525,0.0001719194,0.0002955353,0.0006050958,0.0002289294],"domain_scores_gemma":[0.99914,0.0001970753,0.00003181042,0.0005929088,0.000002015402,0.00003618874],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001508731,0.00004373206,0.9661837,0.0001094814,0.00001433179,0.00008878842,0.002418056,0.004557238,0.001046729,0.0001060029,0.0005900111,0.0248269],"study_design_scores_gemma":[0.00005015192,0.00001467846,0.9102353,0.00005394902,0.00001071965,0.00004424504,0.004255363,0.0839183,0.00007315544,0.00009254219,0.00116843,0.00008319094],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968167,0.0002135784,0.0000389174,0.0009302456,0.000383809,0.0001264316,0.001154449,0.000005007853,0.0003308505],"genre_scores_gemma":[0.9992745,0.00008398345,0.00006976786,0.0003725456,0.00002675534,2.028179e-7,0.0001088486,0.000002119674,0.00006127291],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07936107,"threshold_uncertainty_score":0.7412798,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406473311","doi":"10.1017/eds.2024.35","title":"Improving the reproducibility in geoscientific papers: lessons learned from a Hackathon in climate science","year":2025,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Biomedical and Engineering Education","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Natural Environment Research Council; Engineering and Physical Sciences Research Council; Canada Research Chairs; University of Cambridge; Natural Sciences and Engineering Research Council of Canada; McMaster University; Alan Turing Institute; European Commission; National Oceanic and Atmospheric Administration; Sight Research UK","keywords":"Reproducibility; Data science; Computer science; Information retrieval; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03184813726813573,"gpt":0.2695994738172536,"spread":0.2377513365491179,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00412328,0.00009217086,0.00008084374,0.0001796926,0.0001927605,0.0001228662,0.001481838,0.00002803477,0.00002832512],"category_scores_gemma":[0.0004185833,0.00007335356,0.000009242182,0.001400111,0.001293015,0.0007901316,0.0009096093,0.0002035585,0.00002328446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003503908,"about_ca_system_score_gemma":0.00007649073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003195703,"about_ca_topic_score_gemma":0.0001623542,"domain_scores_codex":[0.9977888,0.0000156856,0.000195564,0.001263763,0.0003392052,0.0003969911],"domain_scores_gemma":[0.9976034,0.00004586761,0.00001694484,0.002272603,0.000001953798,0.00005919192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000002744591,0.00008359271,0.009103724,0.0000306029,9.716225e-7,0.00000165887,0.000542106,0.001527859,0.8200601,0.0001196721,0.00007861066,0.1684483],"study_design_scores_gemma":[0.0001377533,0.000004758371,0.8057806,0.0000640172,0.000003229738,7.064905e-7,0.0005830229,0.1759302,0.01356224,0.0001509915,0.003638073,0.000144366],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966938,0.0003462194,0.0002976872,0.0009261448,0.0009335285,0.0001400433,0.000163055,0.00005025465,0.0004492158],"genre_scores_gemma":[0.9988562,0.0002774458,0.0006942571,0.00005496517,0.00001760605,0.00001178106,0.0000583861,0.000004450267,0.00002488771],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8064979,"threshold_uncertainty_score":0.4764167,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413478742","doi":"10.1017/eds.2025.10015","title":"Discrete variational autoencoders for synthetic nighttime visible satellite imagery","year":2025,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Advanced Image Fusion Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Satellite; Remote sensing; Satellite imagery; Computer science; Artificial intelligence; Computer vision; Meteorology; Geography; Physics; Astronomy","retraction":null,"screen_n_in":null,"score":{"opus":0.008286408837300545,"gpt":0.256655688708858,"spread":0.2483692798715574,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003325074,0.0001274547,0.0001010437,0.000129919,0.0002054557,0.00007231079,0.0009395794,0.00002765591,0.0001431006],"category_scores_gemma":[0.00006987889,0.0001264827,0.00002356591,0.0002355103,0.0004267101,0.001445168,0.0004663987,0.00008021334,0.00005755325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001681099,"about_ca_system_score_gemma":0.00003048681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002057971,"about_ca_topic_score_gemma":5.54211e-7,"domain_scores_codex":[0.9988332,0.000007951466,0.0001802303,0.0004438825,0.0002510269,0.0002837255],"domain_scores_gemma":[0.9990401,0.00008689004,0.00002474557,0.0007853427,0.000003803291,0.00005916998],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001632352,0.00008044104,0.0005131243,0.00007017511,0.00002484412,0.000003801357,0.0001137505,0.0107238,0.9025307,0.003291973,0.007595447,0.07503562],"study_design_scores_gemma":[0.0003127493,0.00003570914,0.01379737,0.00007615557,0.00002891486,0.000007047228,0.0000932909,0.7171429,0.1753099,0.005674887,0.08701564,0.0005054105],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001433158,0.0003316978,0.9919171,0.0001397189,0.0002687087,0.0003406988,0.0008365053,0.0002909212,0.004441496],"genre_scores_gemma":[0.4543257,0.0005481276,0.5430666,0.0002241628,0.00003947122,0.00008472259,0.0005743346,0.00003285299,0.001104017],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7272208,"threshold_uncertainty_score":0.5157813,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4383040563","doi":"10.1017/eds.2023.15","title":"Neural style transfer between observed and simulated cloud images to improve the detection performance of tropical cyclone precursors","year":2023,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Tropical and Extratropical Cyclones Research","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Precursory Research for Embryonic Science and Technology; Core Research for Evolutional Science and Technology; Japan Society for the Promotion of Science","keywords":"Tropical cyclone; Cloud computing; Observational study; Computer science; Cyclone (programming language); Artificial intelligence; Artificial neural network; Transfer of learning; Remote sensing; Meteorology; Environmental science; Machine learning; Geography; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03664549960562104,"gpt":0.2454391275137511,"spread":0.2087936279081301,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002632565,0.0001099416,0.0001325212,0.00006039394,0.0003480951,0.00006748374,0.0008764181,0.0000364005,0.000140401],"category_scores_gemma":[0.00005771143,0.00006922851,0.00002153209,0.0005461219,0.0009349051,0.0006425417,0.0002219982,0.0001857918,0.0001189919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000734397,"about_ca_system_score_gemma":0.00001253824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007971069,"about_ca_topic_score_gemma":0.0002444929,"domain_scores_codex":[0.9982805,0.00006413857,0.000195928,0.0004751314,0.0005760203,0.0004083355],"domain_scores_gemma":[0.9991637,0.0001612826,0.00001886728,0.0004335272,0.000004801178,0.0002177722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006558714,0.00001100913,0.8692822,0.00001040607,0.000004334114,0.000001875633,0.00007341075,0.0007483239,0.03505813,0.000001378298,0.000008517445,0.09473478],"study_design_scores_gemma":[0.0001598667,0.0003941651,0.9489836,0.00000366284,0.000007342906,0.000001720813,0.00007169974,0.0426323,0.007343991,0.000009043085,0.0003028689,0.00008973568],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9983636,0.00006278254,0.00009919738,0.0003384068,0.000114638,0.0002531337,0.0007235614,0.00002601339,0.0000186548],"genre_scores_gemma":[0.9995669,0.0001112383,0.00006320556,0.00003385221,0.00007911329,0.000001138084,0.0001140012,0.000003009289,0.00002760345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09464505,"threshold_uncertainty_score":0.3444697,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407343186","doi":"10.1017/eds.2024.56","title":"Unsupervised clustering identifies thermohaline staircases in the Canada Basin of the Arctic Ocean – CORRIGENDUM","year":2025,"lang":"en","type":"erratum","venue":"Environmental Data Science","topic":"Methane Hydrates and Related Phenomena","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Arctic; Thermohaline circulation; The arctic; Oceanography; Cluster analysis; Structural basin; Geology; Computer science; Artificial intelligence; Paleontology","retraction":null,"screen_n_in":null,"score":{"opus":0.01941260557488577,"gpt":0.2225008684301353,"spread":0.2030882628552495,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001499832,0.0003724741,0.0003456672,0.00007407668,0.0005225007,0.00009647135,0.006799869,0.0001316018,0.00188722],"category_scores_gemma":[0.0001432128,0.000217068,0.00006710069,0.0009694506,0.002118825,0.0005050621,0.004782547,0.0008739313,0.00002283654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008207709,"about_ca_system_score_gemma":0.0004328872,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.307227,"about_ca_topic_score_gemma":0.2840707,"domain_scores_codex":[0.9957277,0.0002870396,0.0005810968,0.00101495,0.001789883,0.000599312],"domain_scores_gemma":[0.9966956,0.0001320969,0.0003197436,0.002757321,0.000003328716,0.00009189999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00004355648,0.0005278765,0.03684125,0.000309028,0.0000745877,0.0001137244,0.002300177,0.005445709,0.007920649,0.00003907636,0.9419342,0.004450116],"study_design_scores_gemma":[0.0008560306,0.0001103101,0.5002272,0.0009590648,0.0002628475,0.00007948529,0.006459856,0.02241726,0.001482157,0.0002896794,0.4654334,0.001422711],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7616015,0.007348194,0.00008838547,0.006434164,0.07749918,0.006309463,0.02073579,0.00007147188,0.1199118],"genre_scores_gemma":[0.9514124,0.0008602122,0.00006201592,0.001036039,0.0001069839,0.00001026203,0.0007229768,0.00002777879,0.0457613],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4765008,"threshold_uncertainty_score":0.9990252,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}