{"meta":{"query_hash":"46bc4f172fb1","filters":{"venue":"Environmental Data Science"},"cohort_total":13,"direct_labels_cover":0,"predictions_cover":13,"exported":13,"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/46bc4f172fb1","api":"https://metacan.xera.ac/api/v1/cohort?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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01709476070128623,"score_gpt":0.2403423857968685,"score_spread":0.22324762509558227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225913161","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010527121,0.47509488,0.057265718,0.30465123,0.0055367807,0.000042951786,0.00027420712,0.00015046906,0.14645672],"genre_scores_gemma":[0.60712326,0.2585326,0.04661373,0.030218283,0.028440619,0.00022174732,0.0002547661,0.00018922897,0.028405795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980136,0.001149622,0.00008077844,0.00030604663,0.00033226243,0.000117625896],"domain_scores_gemma":[0.9935341,0.0047520995,0.00018360022,0.00026851933,0.00090883713,0.0003529854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006208572,0.00071441295,0.0007389565,0.002520393,0.00089938,0.00429577,0.0010003523,0.004148219,0.004269248],"category_scores_gemma":[0.0072581307,0.000389123,0.000532011,0.0015494565,0.009242037,0.0072885975,0.0023508866,0.0060749883,0.0008903866],"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":[0.000025486095,0.0000471029,0.00046545902,0.00017893998,0.000024072633,0.000055497017,0.00019805755,0.0031440742,0.00012320446,0.9501883,0.010000355,0.035549436],"study_design_scores_gemma":[0.000016304559,0.00004620535,0.0008548207,0.00052716763,0.00000875856,0.0000864678,0.00019141396,0.009612717,0.00020004857,0.83336776,0.15505904,0.000029350644],"about_ca_topic_score_codex":0.003443403,"about_ca_topic_score_gemma":0.0020019314,"teacher_disagreement_score":0.006208572,"about_ca_system_score_codex":0.0057611694,"about_ca_system_score_gemma":0.0015610742,"threshold_uncertainty_score":0.04180044},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.034200513288365895,"score_gpt":0.27508206889290776,"score_spread":0.24088155560454186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380482266","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36032885,0.0009448453,0.6255195,0.0022156031,0.00016874645,0.000045071272,0.001248462,0.0055367737,0.003992161],"genre_scores_gemma":[0.826194,0.00026978785,0.16966498,0.00036223256,0.000037712914,0.000033679335,0.0011271706,0.0001243343,0.0021860593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998281,0.00003132703,0.000004948674,0.000047560643,0.000054284115,0.000033703745],"domain_scores_gemma":[0.99960595,0.000100247256,0.000060464587,0.000051847885,0.00013911942,0.000042455824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003806478,0.00059701095,0.0004054924,0.0005906381,0.00020049482,0.00056371134,0.00093740394,0.0005928405,0.0010976875],"category_scores_gemma":[0.00093113456,0.00022909917,0.00023305607,0.00048355813,0.0004284026,0.0010732163,0.0010530319,0.0008615867,0.0004933592],"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":[0.00031983334,0.00036407664,0.054618426,0.00027866976,0.00016200646,0.00019325457,0.00014373833,0.27761543,0.2105743,0.0046242764,0.016646937,0.43445912],"study_design_scores_gemma":[0.000006567366,0.000030727908,0.0052254805,0.000015338239,0.000009431905,0.000024327139,0.000054587286,0.9707491,0.018219247,0.0035548466,0.0020970586,0.000013204217],"about_ca_topic_score_codex":0.006739427,"about_ca_topic_score_gemma":0.011541878,"teacher_disagreement_score":0.006739427,"about_ca_system_score_codex":0.0006514374,"about_ca_system_score_gemma":0.00061986287,"threshold_uncertainty_score":0.013400435},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03664549960562104,"score_gpt":0.24543912751375108,"score_spread":0.20879362790813005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383040563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97047496,0.00005320776,0.027942412,0.000048763457,0.00003669601,0.000025019302,0.00010626416,0.0004870887,0.0008255709],"genre_scores_gemma":[0.99242,0.00001778598,0.0071028816,0.000012541599,0.0000055745063,0.000006169763,0.00017774731,0.000008612492,0.00024868638],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998963,0.000026964632,0.0000071863965,0.000028794864,0.000021757549,0.000019024348],"domain_scores_gemma":[0.9997422,0.00008035144,0.00003437685,0.000045410994,0.000071515555,0.000026181504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003291596,0.00027289355,0.0001701118,0.0003195757,0.00008747021,0.00023921908,0.0002763773,0.00018664815,0.0007349338],"category_scores_gemma":[0.001224753,0.00009173923,0.000234101,0.00022491332,0.00012734978,0.0002655838,0.00022379139,0.0003113505,0.00014835305],"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":[0.0008697233,0.0007484311,0.051895436,0.00008810296,0.00016601034,0.0001511736,0.00012075195,0.3549601,0.10362797,0.0004960163,0.0018296762,0.48504657],"study_design_scores_gemma":[0.000011358417,0.00006720164,0.011680908,0.0000017246165,0.00000905902,0.000012467384,0.000015706084,0.9753997,0.0125532085,0.00009371652,0.00014996808,0.0000050775707],"about_ca_topic_score_codex":0.0037721023,"about_ca_topic_score_gemma":0.0038251774,"teacher_disagreement_score":0.0037721023,"about_ca_system_score_codex":0.0002452086,"about_ca_system_score_gemma":0.00023869984,"threshold_uncertainty_score":0.007500291},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06838411252735653,"score_gpt":0.2704303668683858,"score_spread":0.20204625434102924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383100035","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026218316,0.000044694545,0.93971,0.00015371206,0.00007673273,0.00017818483,0.0015291806,0.03107354,0.0010156065],"genre_scores_gemma":[0.3748678,0.00013462894,0.61633044,0.00012621192,0.000055922512,0.00024552556,0.005026381,0.0007679954,0.0024451134],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992729,0.00007803658,0.00008670032,0.00029968875,0.00020397549,0.000058754857],"domain_scores_gemma":[0.9981755,0.0005694843,0.00015444067,0.00052829436,0.00043722833,0.00013508635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002052834,0.0008154557,0.0006599196,0.0008234917,0.0008097953,0.0013576961,0.0015504858,0.0006368843,0.0027210163],"category_scores_gemma":[0.004347304,0.0003979313,0.0008894386,0.00075379875,0.00041976874,0.0012405135,0.0013656352,0.00093033514,0.0013665674],"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":[0.0010394116,0.0004997123,0.031287458,0.00024333244,0.0002446919,0.001579266,0.00087957754,0.32646653,0.032640938,0.012728533,0.01885139,0.5735392],"study_design_scores_gemma":[0.000023350534,0.000019813146,0.0009521954,0.000008418507,0.00001071836,0.000048728085,0.000035063535,0.9847778,0.007226102,0.0039046523,0.0029786031,0.000014618608],"about_ca_topic_score_codex":0.012660824,"about_ca_topic_score_gemma":0.009095444,"teacher_disagreement_score":0.012660824,"about_ca_system_score_codex":0.00062910863,"about_ca_system_score_gemma":0.002777905,"threshold_uncertainty_score":0.02517426},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02121041352193427,"score_gpt":0.2344499535427245,"score_spread":0.2132395400207902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385559495","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057329003,0.00029416813,0.93808466,0.00040874633,0.00008977681,0.000037114576,0.00020732044,0.0016763107,0.0018728886],"genre_scores_gemma":[0.8897837,0.00013995856,0.106751196,0.00017710146,0.00004263365,0.000037867765,0.00033722684,0.00008064724,0.0026497624],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953127,0.00009439493,0.000022018474,0.00016405452,0.00011355328,0.000074691336],"domain_scores_gemma":[0.99880576,0.00051892595,0.00014976754,0.00015771051,0.00030984977,0.00005794751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011738625,0.00086153625,0.00074293715,0.00073834276,0.00034314345,0.0007853758,0.0018732614,0.0012418979,0.0014069724],"category_scores_gemma":[0.0040945746,0.00063939707,0.0006848517,0.0010572049,0.0007500791,0.0013337365,0.0009794128,0.0014503332,0.0004323641],"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":[0.00006212787,0.000025157331,0.0010024185,0.000016907932,0.000021704771,0.000024818235,0.000016093018,0.96314955,0.0009577836,0.0019207835,0.0005402827,0.03226242],"study_design_scores_gemma":[0.0000019585027,0.0000052109876,0.00007931374,0.0000012570929,0.0000018552356,0.000002642067,0.000001263222,0.99867284,0.0003160895,0.00084356964,0.000072272196,0.0000016738452],"about_ca_topic_score_codex":0.03594775,"about_ca_topic_score_gemma":0.03167021,"teacher_disagreement_score":0.03594775,"about_ca_system_score_codex":0.0018184191,"about_ca_system_score_gemma":0.0014019108,"threshold_uncertainty_score":0.071476996},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16066557079738614,"score_gpt":0.3548466895345715,"score_spread":0.19418111873718535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389641434","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1219828,0.00012596528,0.87540925,0.00014799807,0.0000326434,0.000121852325,0.00017986707,0.00079544814,0.0012041755],"genre_scores_gemma":[0.5062557,0.000039709787,0.49220136,0.0001232159,0.000043367636,0.00018264534,0.0005688509,0.00012126606,0.00046383514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99688965,0.0012185995,0.00022785712,0.00051894004,0.0009219346,0.00022302885],"domain_scores_gemma":[0.98695683,0.008013341,0.0013498951,0.001474148,0.001888617,0.0003172334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005006385,0.00054911297,0.0009778091,0.004621147,0.0009939602,0.0018189681,0.0017622154,0.0013718101,0.00088133366],"category_scores_gemma":[0.018228598,0.00034202743,0.0006551407,0.00203076,0.0012763226,0.0008651756,0.0014429973,0.0011153909,0.0002423211],"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":[0.00083785824,0.00074716564,0.09683299,0.00031824765,0.0006511695,0.00055281195,0.0010313994,0.2368203,0.029184353,0.03726481,0.006110413,0.5896484],"study_design_scores_gemma":[0.000043969238,0.00008177595,0.00940733,0.000024611782,0.000028054701,0.00019351338,0.00012433434,0.9751823,0.005244773,0.008448679,0.0011780494,0.00004254214],"about_ca_topic_score_codex":0.0028489341,"about_ca_topic_score_gemma":0.005128697,"teacher_disagreement_score":0.005006385,"about_ca_system_score_codex":0.0009366669,"about_ca_system_score_gemma":0.0015971824,"threshold_uncertainty_score":0.026476622},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.37050968127198275,"score_gpt":0.4768085917294069,"score_spread":0.10629891045742418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393443031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1214933,0.00019989394,0.8751872,0.00047737706,0.000045127785,0.00026523095,0.00034727514,0.0007410971,0.0012434759],"genre_scores_gemma":[0.6599556,0.00013394193,0.33774132,0.00010988947,0.00008582409,0.00049501786,0.0007299941,0.0000748247,0.00067354186],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925895,0.0059049674,0.00022783215,0.0005626687,0.0005304414,0.00018464844],"domain_scores_gemma":[0.88247174,0.11138231,0.0014604987,0.0022109137,0.0021352535,0.00033934898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025240114,0.00069237506,0.0010592126,0.0030906321,0.0012379487,0.001646502,0.0016022178,0.0015991651,0.0033049409],"category_scores_gemma":[0.081556186,0.0004936309,0.0016479078,0.003035339,0.0013214364,0.0014130103,0.0014823377,0.0023973237,0.00049439864],"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":[0.0015750509,0.0006753319,0.083799474,0.00051228394,0.0007835451,0.0007578557,0.0041763554,0.38713378,0.003677486,0.12929712,0.004862858,0.38274887],"study_design_scores_gemma":[0.000056981284,0.000034581735,0.0021092973,0.000021865157,0.000027844317,0.00003299381,0.00012802548,0.9750206,0.00051041244,0.021532957,0.00050626125,0.00001817059],"about_ca_topic_score_codex":0.013509863,"about_ca_topic_score_gemma":0.013880653,"teacher_disagreement_score":0.025240114,"about_ca_system_score_codex":0.001371842,"about_ca_system_score_gemma":0.0011134577,"threshold_uncertainty_score":0.13348407},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.014298986316749755,"score_gpt":0.20246080525008575,"score_spread":0.188161818933336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396681541","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99094886,0.00010587082,0.0065712403,0.000051022704,0.000005867479,0.000051205992,0.0010087367,0.00025344052,0.0010038017],"genre_scores_gemma":[0.9863578,0.000059119713,0.010757284,0.0000102519725,0.0000034581788,0.000018193932,0.0022629483,0.000023472774,0.0005075782],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997305,0.000027894363,0.000016073873,0.00007013216,0.00009433859,0.000060934788],"domain_scores_gemma":[0.99903226,0.00012857084,0.00014246229,0.00006405792,0.00056927337,0.00006348097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033581705,0.00028997945,0.00021748843,0.0024213595,0.00082216505,0.0007767229,0.00062580215,0.00031083357,0.00023423674],"category_scores_gemma":[0.0013643478,0.00011476516,0.0002930251,0.0019389347,0.00028321886,0.00021510525,0.0003858892,0.00017459727,0.00012703855],"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":[0.00025274308,0.00013626745,0.7679687,0.00012316211,0.00023100892,0.00024320115,0.001260931,0.06575694,0.020616435,0.0013108907,0.0042240713,0.13787569],"study_design_scores_gemma":[0.000011785858,0.000016006326,0.6793086,0.000024166091,0.000030303469,0.000036872825,0.00088986405,0.3123891,0.004515365,0.00041944522,0.0023253805,0.000033075794],"about_ca_topic_score_codex":0.7236888,"about_ca_topic_score_gemma":0.79200464,"teacher_disagreement_score":0.27631122,"about_ca_system_score_codex":0.0026261841,"about_ca_system_score_gemma":0.0037478784,"threshold_uncertainty_score":0.5558769},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03184813726813573,"score_gpt":0.26959947381725363,"score_spread":0.2377513365491179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406473311","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07403274,0.017948287,0.40415514,0.43512067,0.013287323,0.0011398975,0.0013943292,0.009785821,0.04313578],"genre_scores_gemma":[0.5680082,0.010480705,0.36529413,0.023459725,0.009679418,0.0013941332,0.0023646846,0.007003269,0.012315756],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6201513,0.2708111,0.025743522,0.019126829,0.058954477,0.005212862],"domain_scores_gemma":[0.09359784,0.5858912,0.022318624,0.22286506,0.06485497,0.010472341],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4098137,0.0011125682,0.0016103879,0.010247992,0.0080558015,0.0410426,0.0071990276,0.0063342107,0.008464647],"category_scores_gemma":[0.7314834,0.001177302,0.0024304884,0.01364327,0.022794446,0.049318194,0.029962065,0.009329168,0.0030777345],"study_design_candidate":"qualitative","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":[0.00084716675,0.00051400217,0.03691331,0.0027735336,0.0005393055,0.001485452,0.043004815,0.0062309834,0.0026905977,0.28941196,0.07515033,0.5404386],"study_design_scores_gemma":[0.00037485192,0.00058185577,0.010986652,0.005861552,0.00030658193,0.0012622979,0.013301273,0.010184592,0.008917808,0.6240358,0.32369453,0.0004922019],"about_ca_topic_score_codex":0.00291213,"about_ca_topic_score_gemma":0.0021725448,"teacher_disagreement_score":0.5901863,"about_ca_system_score_codex":0.0057817674,"about_ca_system_score_gemma":0.02383485,"threshold_uncertainty_score":0.7278048},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Arctic; Thermohaline circulation; The arctic; Oceanography; Cluster analysis; Structural basin; Geology; Computer science; Artificial intelligence; Paleontology","score_opus":0.019412605574885767,"score_gpt":0.2225008684301353,"score_spread":0.20308826285524953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407343186","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7256801,0.0064343214,0.040771756,0.005860304,0.008550943,0.00034274184,0.11026166,0.0057523944,0.09634579],"genre_scores_gemma":[0.7701126,0.002905792,0.05546182,0.000532976,0.00058263727,0.00010492123,0.0718935,0.0016062257,0.09679971],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99975914,0.000011339351,0.000014758657,0.000060893017,0.00011942303,0.00003437894],"domain_scores_gemma":[0.9987803,0.000073909345,0.000049474518,0.000056802393,0.0009765943,0.00006283273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031603654,0.00040443096,0.00031698553,0.0023564545,0.0017649275,0.0015074012,0.00079526374,0.0005242934,0.0074861445],"category_scores_gemma":[0.0013590422,0.0001591568,0.0004837933,0.002989868,0.0004084463,0.00027256671,0.0004265444,0.00035941508,0.0024291384],"study_design_candidate":"observational","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":[0.00031302994,0.00006951851,0.20124209,0.00060156424,0.00022517458,0.0012362299,0.0014435876,0.021878177,0.015505351,0.0034874056,0.42043608,0.33356184],"study_design_scores_gemma":[0.00003327272,0.000033568333,0.7533425,0.00026941486,0.00012139936,0.00028582322,0.0031897076,0.03429133,0.0063227573,0.0019307416,0.20002264,0.00015688535],"about_ca_topic_score_codex":0.89542466,"about_ca_topic_score_gemma":0.959618,"teacher_disagreement_score":0.104575336,"about_ca_system_score_codex":0.0036821913,"about_ca_system_score_gemma":0.005760818,"threshold_uncertainty_score":0.21038234},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.034374980715780525,"score_gpt":0.3017214673339243,"score_spread":0.26734648661814375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407998460","genre_codex":"dataset","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023513574,0.0014518531,0.014896792,0.00043966793,0.00016142719,0.00030905812,0.949495,0.025905367,0.004989496],"genre_scores_gemma":[0.0029193417,0.0004326124,0.018651191,0.00016432819,0.000044919045,0.00046739986,0.97471344,0.0019283013,0.00067853817],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99547726,0.0007427784,0.0009674178,0.00082475704,0.0016720431,0.00031573683],"domain_scores_gemma":[0.98148304,0.00610737,0.0016377497,0.0062593347,0.0032266201,0.0012857296],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.005591738,0.0019277582,0.0016007447,0.015623154,0.0011679534,0.003592812,0.0038028285,0.0022342391,0.02296119],"category_scores_gemma":[0.025128266,0.0009381889,0.0013555011,0.018995063,0.00065487635,0.0059211594,0.005688865,0.0023630238,0.026921183],"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":[0.00020683672,0.00015162284,0.0060632923,0.002302613,0.00011378075,0.0001610548,0.00016237123,0.003351169,0.0013509442,0.0074293367,0.89602226,0.08268475],"study_design_scores_gemma":[0.00014291256,0.00003893978,0.008613291,0.0008135504,0.000036782207,0.00017798379,0.000103148515,0.0076074577,0.0018571559,0.012147465,0.9683737,0.00008761634],"about_ca_topic_score_codex":0.007854529,"about_ca_topic_score_gemma":0.013074852,"teacher_disagreement_score":0.99619716,"about_ca_system_score_codex":0.0013326653,"about_ca_system_score_gemma":0.003391909,"threshold_uncertainty_score":0.07681286},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.007343167933572374,"score_gpt":0.23513291302905526,"score_spread":0.2277897450954829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412734594","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75297254,0.0018166166,0.2185033,0.0005545369,0.0003727736,0.00016120975,0.007956198,0.011303876,0.0063589276],"genre_scores_gemma":[0.90240324,0.0004316255,0.079179995,0.00012454124,0.00010701023,0.000047205653,0.015372999,0.00020243398,0.0021308667],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999777,0.000017810333,0.0000130993185,0.00008892063,0.000053583546,0.000049522474],"domain_scores_gemma":[0.999689,0.00007827656,0.000054485256,0.00006177386,0.000090379406,0.000026217162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037872058,0.00083581195,0.0004610964,0.002443194,0.00023973601,0.0007303064,0.00061695423,0.00074629526,0.001653181],"category_scores_gemma":[0.0007981418,0.00017832418,0.0007859924,0.0015161602,0.00029344164,0.00086035376,0.0004244711,0.0005810296,0.0010540652],"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":[0.00068457425,0.0005057243,0.0253866,0.00043932706,0.00034175673,0.000450325,0.00016471512,0.32408625,0.09795756,0.0027207443,0.016914802,0.5303475],"study_design_scores_gemma":[0.0000073392816,0.000057443067,0.012087888,0.000025022677,0.000031553805,0.00009481614,0.00009862789,0.9690345,0.013996364,0.0016993268,0.0028511423,0.00001581353],"about_ca_topic_score_codex":0.010468484,"about_ca_topic_score_gemma":0.01568684,"teacher_disagreement_score":0.010468484,"about_ca_system_score_codex":0.00053161226,"about_ca_system_score_gemma":0.00050571415,"threshold_uncertainty_score":0.020815074},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.008286408837300545,"score_gpt":0.25665568870885797,"score_spread":0.2483692798715574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413478742","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13863169,0.00032995638,0.85716105,0.00043519182,0.000066163906,0.00003993283,0.00027930824,0.00068916957,0.002367662],"genre_scores_gemma":[0.89440346,0.000129813,0.1014322,0.00010663431,0.000027337708,0.000050336534,0.00051308,0.000093062845,0.003244052],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985075,0.000052918556,0.0000070770143,0.000035035147,0.000034702585,0.00001951304],"domain_scores_gemma":[0.99941313,0.0004132055,0.00004262352,0.000045276804,0.00006510602,0.00002069206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007019794,0.000393563,0.0003068255,0.00021217992,0.00017201646,0.00034902274,0.00066101266,0.0005928879,0.00097589334],"category_scores_gemma":[0.0019630147,0.00030691447,0.00043890288,0.00026297692,0.00053437566,0.00041573032,0.000476891,0.0010500451,0.00020991612],"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":[0.00002146308,0.000013072819,0.00036296647,0.000011971903,0.000013054965,0.000017975932,0.000015590958,0.9828798,0.0009238893,0.0030505015,0.0003478279,0.012341918],"study_design_scores_gemma":[6.7657123e-7,0.0000018200076,0.000039542258,7.4854836e-7,4.031747e-7,0.0000011203207,9.2669575e-7,0.9993643,0.00014176978,0.00040191633,0.00004614132,6.758289e-7],"about_ca_topic_score_codex":0.012123943,"about_ca_topic_score_gemma":0.012800095,"teacher_disagreement_score":0.012123943,"about_ca_system_score_codex":0.0006105723,"about_ca_system_score_gemma":0.0005297773,"threshold_uncertainty_score":0.024106741},"labels":[],"label_agreement":null}]}