{"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":"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":[0.99503,0.000120730474,0.00006567637,0.000107827414,0.00014716313,0.00024394001,0.00032645656,0.000033824977,0.003924415],"genre_scores_gemma":[0.9985408,0.000014469458,0.0011299949,0.00006219769,0.000012075568,0.000014407603,0.000065101354,0.000014049893,0.00014686516],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9953518,0.000140986,0.00035027158,0.001349001,0.0021104894,0.0006974874],"domain_scores_gemma":[0.9986412,0.000051035684,0.00019671154,0.000930243,0.0000013306278,0.00017951388],"candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.0032672295,0.00019529035,0.00019158557,0.00027085442,0.0013297925,0.00003470502,0.0030665784,0.000027772723,0.0053785094],"category_scores_gemma":[0.00022332609,0.0001986003,0.000033835502,0.0015704411,0.007015243,0.0016151703,0.0094620325,0.00052892865,0.00020065754],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003359809,0.0005273837,0.33785686,0.0000011606775,0.0000018776932,0.000017058272,0.0008726016,0.09439182,0.5637677,0.0002475762,0.00003263904,0.0022497347],"study_design_scores_gemma":[0.00074473245,0.0006438684,0.65231866,0.0000074842083,0.000014156278,0.00011186206,0.0032280665,0.33045554,0.0069504757,0.00080736354,0.0041541774,0.0005636066],"about_ca_topic_score_codex":0.001311037,"about_ca_topic_score_gemma":0.000035541234,"teacher_disagreement_score":0.5568172,"about_ca_system_score_codex":0.0053398055,"about_ca_system_score_gemma":0.00008290609,"threshold_uncertainty_score":0.9999703},"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":"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":[0.99905837,0.000026095398,0.00045681035,0.00006359022,0.0001217939,0.00009434356,0.000051318046,0.000044930268,0.000082730294],"genre_scores_gemma":[0.9978064,0.000106077554,0.00040154537,0.000013977335,0.000031053718,0.000009495122,0.0013316299,0.000009084176,0.0002907395],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99899894,0.000020023124,0.0001400191,0.00039358417,0.00025930465,0.00018815682],"domain_scores_gemma":[0.9992976,0.0000042546167,0.000054229105,0.0005634287,0.000009602794,0.0000708886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034256923,0.00007035223,0.000057025074,0.00005411773,0.00017372788,0.000036013716,0.0005925947,0.000029186052,0.00003753771],"category_scores_gemma":[0.000048097198,0.000055156066,0.000011483588,0.00016562328,0.0003860104,0.000031898286,0.000414129,0.00004750246,0.00022473272],"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":[0.0000088224615,0.000024313575,0.022335494,0.0000065989934,0.0000060429875,5.091026e-7,0.000108823246,0.00052120455,0.9759542,0.0000046842365,0.0001314948,0.0008978299],"study_design_scores_gemma":[0.00015863882,0.000033528708,0.12064565,0.0000069346784,0.0000044311487,0.0000026883856,0.0005485881,0.0042134067,0.868724,4.85935e-7,0.0055592414,0.000102444516],"about_ca_topic_score_codex":0.000004734008,"about_ca_topic_score_gemma":7.422432e-7,"teacher_disagreement_score":0.10723022,"about_ca_system_score_codex":0.000011700356,"about_ca_system_score_gemma":0.000021961578,"threshold_uncertainty_score":0.28885594},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9983636,0.00006278254,0.00009919738,0.00033840677,0.000114638,0.00025313368,0.0007235614,0.000026013386,0.000018654797],"genre_scores_gemma":[0.99956685,0.000111238274,0.00006320556,0.000033852215,0.00007911329,0.0000011380836,0.0001140012,0.0000030092892,0.00002760345],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99828047,0.00006413857,0.00019592802,0.00047513144,0.0005760203,0.00040833547],"domain_scores_gemma":[0.99916375,0.00016128259,0.000018867278,0.00043352722,0.000004801178,0.00021777219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026325646,0.000109941575,0.00013252116,0.00006039394,0.00034809514,0.00006748374,0.0008764181,0.0000364005,0.00014040098],"category_scores_gemma":[0.000057711433,0.00006922851,0.00002153209,0.0005461219,0.00093490514,0.00064254174,0.00022199817,0.00018579177,0.00011899195],"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":[0.00006558714,0.000011009133,0.86928225,0.000010406071,0.0000043341142,0.0000018756333,0.00007341075,0.00074832386,0.035058126,0.0000013782981,0.000008517445,0.09473478],"study_design_scores_gemma":[0.00015986666,0.00039416508,0.9489836,0.0000036628396,0.0000073429055,0.0000017208134,0.00007169974,0.042632297,0.0073439907,0.000009043085,0.0003028689,0.00008973568],"about_ca_topic_score_codex":0.00079710694,"about_ca_topic_score_gemma":0.00024449287,"teacher_disagreement_score":0.094645046,"about_ca_system_score_codex":0.0000073439696,"about_ca_system_score_gemma":0.000012538242,"threshold_uncertainty_score":0.3444697},"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":"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":[0.99052787,0.000017548555,0.004702895,0.0020174612,0.00017441624,0.0006997561,0.0008775856,0.00003266739,0.00094982004],"genre_scores_gemma":[0.9948032,0.00003767225,0.004485674,0.00016614284,0.000016119806,0.0000566115,0.00025688251,0.000004830419,0.00017286612],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99861336,0.000026530402,0.00018937048,0.00045125882,0.00041254816,0.00030694087],"domain_scores_gemma":[0.9990992,0.00016335938,0.00006175671,0.0006437967,0.0000010222784,0.00003085893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014147558,0.000089450514,0.00008575959,0.000061713436,0.00040167317,0.000023045499,0.0012885007,0.00002431823,0.00008515612],"category_scores_gemma":[0.0001402553,0.00006757124,0.000018194483,0.00068839634,0.0012099894,0.0010190764,0.0010573741,0.000067097564,0.0000703453],"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":[0.000048752314,0.0006539229,0.6895135,0.00003197447,0.000020555592,0.000009491977,0.004292204,0.016570926,0.24360855,0.00076626264,0.022946028,0.021537822],"study_design_scores_gemma":[0.0002789336,0.00004985119,0.9290227,0.000014310683,0.000013516196,0.0000024072988,0.0005469973,0.062024157,0.00070573145,0.0009798239,0.0062673516,0.00009420473],"about_ca_topic_score_codex":0.00010656512,"about_ca_topic_score_gemma":0.00007131995,"teacher_disagreement_score":0.24290282,"about_ca_system_score_codex":0.000058119236,"about_ca_system_score_gemma":0.0000062237727,"threshold_uncertainty_score":0.44582567},"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":"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":[0.8058684,0.00046498716,0.17923261,0.005012352,0.000908946,0.0013699281,0.0025896013,0.0011267238,0.0034264761],"genre_scores_gemma":[0.98741376,0.00012665683,0.011479964,0.0002753368,0.000052024512,0.00002595598,0.0002753904,0.0000146057455,0.00033629278],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996179,0.000028376437,0.00026051456,0.0013955572,0.0013581098,0.0007784358],"domain_scores_gemma":[0.99797976,0.00005787578,0.00013068231,0.0015249894,0.0000061544165,0.00030055578],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00043739876,0.00027609072,0.00016392315,0.00018868833,0.0007075232,0.00039302578,0.003970802,0.000039467115,0.00018462249],"category_scores_gemma":[0.000030191346,0.00022016637,0.000019805699,0.0011429576,0.001292085,0.0040687947,0.0026233098,0.00017026476,0.00093216717],"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":[0.00045307496,0.005090686,0.3522173,0.00086070783,0.00032984657,0.0040033935,0.009746279,0.011412048,0.34945044,0.046016667,0.025717812,0.19470175],"study_design_scores_gemma":[0.0020513043,0.0009708026,0.660558,0.00012310836,0.00004154575,0.00083775533,0.0021426762,0.29467937,0.01321736,0.0008719897,0.022346523,0.0021595624],"about_ca_topic_score_codex":0.0000074552427,"about_ca_topic_score_gemma":0.000004422596,"teacher_disagreement_score":0.33623308,"about_ca_system_score_codex":0.00015708232,"about_ca_system_score_gemma":0.00024545522,"threshold_uncertainty_score":0.99984574},"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":"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":[0.8231576,0.000008508883,0.16696724,0.0001636149,0.00009634873,0.00072701456,0.008278099,0.000051963736,0.00054959196],"genre_scores_gemma":[0.8960974,0.00010825013,0.10243824,0.000053881053,0.000009708505,0.000029305884,0.0012266351,0.00001599772,0.000020569687],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99719685,0.00003727605,0.00042917486,0.0012501285,0.0005662324,0.0005203481],"domain_scores_gemma":[0.99713224,0.0002897106,0.00013812481,0.002336268,0.0000021074968,0.00010154276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004314637,0.00014862363,0.00018506558,0.00010538241,0.00024011797,0.000038175483,0.0026322259,0.00005368475,0.00011336843],"category_scores_gemma":[0.00044000748,0.00015014167,0.000022836048,0.00073864136,0.00061085715,0.0018524241,0.0048214756,0.00010981163,0.00008627174],"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":[0.00003081933,0.00020523964,0.010847683,0.000031924425,0.000002264286,6.0512264e-7,0.00029380422,0.062227778,0.9159171,0.00018285937,0.00006928932,0.010190642],"study_design_scores_gemma":[0.00037373407,0.000024214893,0.060597416,0.000014004718,0.00001239612,0.0000024057138,0.00024478405,0.9367129,0.001275631,0.00038089257,0.0002059599,0.00015561689],"about_ca_topic_score_codex":0.00024362215,"about_ca_topic_score_gemma":0.00016526844,"teacher_disagreement_score":0.91464144,"about_ca_system_score_codex":0.000221538,"about_ca_system_score_gemma":0.000030649062,"threshold_uncertainty_score":0.6122599},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37830275,0.0035180063,0.5460491,0.040212132,0.0028570427,0.0019157459,0.009474925,0.00039209228,0.017278174],"genre_scores_gemma":[0.9731275,0.005288589,0.019456875,0.00045758905,0.00016958313,0.0000341054,0.0011927257,0.000006574466,0.0002664503],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987055,0.00014410028,0.000119730634,0.0004926486,0.00032951013,0.00020848373],"domain_scores_gemma":[0.99887,0.0003126432,0.00003392024,0.0006237046,0.00000731761,0.00015237978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001072793,0.000070598086,0.00007211043,0.00007786833,0.00035778485,0.0002350825,0.00081856246,0.00005313986,0.00059605466],"category_scores_gemma":[0.00020359422,0.00007070224,0.0000059102463,0.00026465743,0.00040192684,0.00060321676,0.00075844675,0.00010752507,0.00012337799],"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":[0.0000052081855,0.00006318408,0.028956693,0.000016649989,0.000008440867,0.0000011982906,0.023102527,0.0000053216972,0.05574158,0.031159798,0.0022922927,0.8586471],"study_design_scores_gemma":[0.000061755534,0.00002566224,0.06075214,0.000016262498,0.000007787462,9.925317e-7,0.0023979654,0.008893374,0.00008551268,0.0034626345,0.9241232,0.000172689],"about_ca_topic_score_codex":0.009549919,"about_ca_topic_score_gemma":0.004438734,"teacher_disagreement_score":0.92183095,"about_ca_system_score_codex":0.00023118482,"about_ca_system_score_gemma":0.00006083887,"threshold_uncertainty_score":0.9970456},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9968167,0.0002135784,0.000038917402,0.00093024556,0.00038380903,0.0001264316,0.001154449,0.0000050078534,0.00033085048],"genre_scores_gemma":[0.9992745,0.00008398345,0.000069767855,0.00037254556,0.00002675534,2.028179e-7,0.000108848566,0.0000021196736,0.00006127291],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99863327,0.00006523525,0.00017191937,0.00029553528,0.0006050958,0.00022892945],"domain_scores_gemma":[0.99914,0.0001970753,0.000031810425,0.0005929088,0.000002015402,0.000036188743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007634048,0.00008754532,0.00007337138,0.000031206215,0.00023966216,0.000087415996,0.0016075873,0.0000123897,0.0005229109],"category_scores_gemma":[0.000052232757,0.000046635203,0.00001829971,0.00034299833,0.0007482352,0.0006034546,0.0002129856,0.00013613685,0.000009988448],"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":[0.00001508731,0.000043732056,0.96618366,0.00010948139,0.000014331794,0.000088788416,0.0024180561,0.0045572384,0.0010467289,0.000106002895,0.0005900111,0.024826897],"study_design_scores_gemma":[0.00005015192,0.000014678459,0.9102353,0.00005394902,0.000010719651,0.00004424504,0.004255363,0.0839183,0.00007315544,0.00009254219,0.0011684295,0.00008319094],"about_ca_topic_score_codex":0.26362377,"about_ca_topic_score_gemma":0.34030902,"teacher_disagreement_score":0.079361066,"about_ca_system_score_codex":0.000031173127,"about_ca_system_score_gemma":0.00021227298,"threshold_uncertainty_score":0.74127984},"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":"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":[0.99669385,0.00034621937,0.0002976872,0.0009261448,0.0009335285,0.0001400433,0.000163055,0.000050254646,0.00044921585],"genre_scores_gemma":[0.99885625,0.00027744577,0.00069425715,0.000054965167,0.000017606053,0.000011781057,0.0000583861,0.000004450267,0.000024887708],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9977888,0.000015685604,0.00019556403,0.0012637629,0.0003392052,0.00039699115],"domain_scores_gemma":[0.9976034,0.000045867608,0.000016944836,0.002272603,0.0000019537977,0.00005919192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00412328,0.000092170856,0.00008084374,0.0001796926,0.00019276053,0.0001228662,0.0014818378,0.000028034767,0.000028325117],"category_scores_gemma":[0.00041858334,0.00007335356,0.000009242182,0.001400111,0.0012930147,0.00079013157,0.0009096093,0.00020355852,0.000023284456],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027445908,0.000083592706,0.009103724,0.000030602903,9.716225e-7,0.0000016588699,0.00054210605,0.0015278594,0.82006013,0.00011967209,0.00007861066,0.1684483],"study_design_scores_gemma":[0.00013775333,0.0000047583712,0.8057806,0.0000640172,0.0000032297378,7.0649054e-7,0.00058302295,0.17593025,0.013562239,0.00015099149,0.0036380733,0.00014436603],"about_ca_topic_score_codex":0.0003195703,"about_ca_topic_score_gemma":0.00016235419,"teacher_disagreement_score":0.80649793,"about_ca_system_score_codex":0.00035039082,"about_ca_system_score_gemma":0.00007649073,"threshold_uncertainty_score":0.47641668},"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":"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":[0.7616015,0.0073481943,0.00008838547,0.0064341635,0.07749918,0.0063094627,0.020735791,0.000071471884,0.11991182],"genre_scores_gemma":[0.95141244,0.0008602122,0.00006201592,0.001036039,0.000106983905,0.000010262025,0.0007229768,0.000027778793,0.0457613],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9957277,0.00028703958,0.0005810968,0.0010149496,0.0017898834,0.00059931196],"domain_scores_gemma":[0.99669564,0.00013209695,0.00031974365,0.0027573209,0.0000033287163,0.00009189999],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014998325,0.00037247414,0.00034566715,0.000074076685,0.0005225007,0.00009647135,0.0067998692,0.00013160185,0.0018872204],"category_scores_gemma":[0.00014321278,0.00021706804,0.000067100686,0.0009694506,0.002118825,0.0005050621,0.004782547,0.00087393133,0.000022836537],"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":[0.000043556476,0.00052787655,0.036841247,0.00030902802,0.0000745877,0.00011372437,0.0023001772,0.0054457085,0.007920649,0.00003907636,0.9419342,0.0044501163],"study_design_scores_gemma":[0.00085603056,0.000110310066,0.50022715,0.0009590648,0.0002628475,0.00007948529,0.0064598564,0.022417262,0.0014821566,0.00028967936,0.46543345,0.0014227113],"about_ca_topic_score_codex":0.307227,"about_ca_topic_score_gemma":0.28407073,"teacher_disagreement_score":0.4765008,"about_ca_system_score_codex":0.00082077086,"about_ca_system_score_gemma":0.0004328872,"threshold_uncertainty_score":0.99902517},"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":"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":[0.97173977,0.0002690212,0.012740847,0.0009205618,0.00042142769,0.0012912313,0.0013372446,0.00009768471,0.011182235],"genre_scores_gemma":[0.9854185,0.00007281638,0.012093094,0.00006959161,0.000025198593,0.000009650813,0.0014505397,0.000010410126,0.00085022714],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99795747,0.0000222113,0.00023510963,0.0010357577,0.00034325517,0.00040620464],"domain_scores_gemma":[0.99764794,0.00009476161,0.00006277983,0.0021026728,0.0000011197001,0.00009070189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001080246,0.00013916129,0.00012285326,0.00008459633,0.0005111798,0.00010957544,0.0032743334,0.000037106056,0.000056171095],"category_scores_gemma":[0.00019237504,0.00013533341,0.000014035372,0.00053562794,0.0008038715,0.0014865616,0.0048575774,0.00018313296,0.00017403965],"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":[0.000020006975,0.00017251549,0.864271,0.000009270905,0.0000054999723,0.000004386287,0.0001774068,0.0053681144,0.040397063,0.00017858205,0.0016244494,0.0877717],"study_design_scores_gemma":[0.00043493125,0.00002783148,0.6222515,0.000032427466,0.000013846115,0.0000069964863,0.00020888394,0.25598574,0.0017675454,0.0002661103,0.11876191,0.0002422615],"about_ca_topic_score_codex":0.0015212185,"about_ca_topic_score_gemma":0.0008008701,"teacher_disagreement_score":0.2506176,"about_ca_system_score_codex":0.0002653693,"about_ca_system_score_gemma":0.00003681404,"threshold_uncertainty_score":0.6084581},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9388581,0.000030193965,0.0054277335,0.0009968359,0.0003343505,0.0004174069,0.00049888686,0.000100498655,0.053335972],"genre_scores_gemma":[0.95654565,0.00004532348,0.038629778,0.00032147366,0.00006223571,0.000005157619,0.00095027784,0.00001275838,0.0034273549],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99818945,0.00003649445,0.00020553406,0.00080376514,0.00047358687,0.0002911754],"domain_scores_gemma":[0.9985962,0.000036425434,0.00006648884,0.0012037295,0.0000013093656,0.00009584382],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003141101,0.00014768796,0.000114795774,0.000047694863,0.00050885737,0.00015231378,0.0011721557,0.000035909892,0.0025886246],"category_scores_gemma":[0.000034647477,0.00014296157,0.000022796092,0.0004019984,0.0016526257,0.0017389623,0.0013825292,0.00008958045,0.0043579265],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010065796,0.00006505172,0.0027729445,7.739966e-7,0.000004410146,0.0000020608288,0.000108420645,0.000027034448,0.964139,0.000023615592,0.0077975164,0.025049103],"study_design_scores_gemma":[0.0009848963,0.000078366524,0.54412687,0.0000369525,0.000102972066,0.000017913788,0.0009544222,0.030952217,0.3568121,0.0022898198,0.062859856,0.00078360713],"about_ca_topic_score_codex":0.00048618004,"about_ca_topic_score_gemma":0.00007365833,"teacher_disagreement_score":0.6073269,"about_ca_system_score_codex":0.00020081637,"about_ca_system_score_gemma":0.000023984727,"threshold_uncertainty_score":0.99832314},"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":"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":[0.0014331578,0.00033169775,0.9919171,0.00013971888,0.00026870865,0.00034069875,0.0008365053,0.00029092116,0.0044414955],"genre_scores_gemma":[0.45432574,0.00054812763,0.54306656,0.00022416281,0.00003947122,0.00008472259,0.0005743346,0.000032852986,0.0011040168],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988332,0.000007951466,0.00018023033,0.00044388248,0.00025102694,0.00028372547],"domain_scores_gemma":[0.99904007,0.00008689004,0.000024745574,0.0007853427,0.000003803291,0.00005916998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003325074,0.0001274547,0.00010104375,0.00012991905,0.00020545567,0.00007231079,0.00093957945,0.000027655915,0.00014310057],"category_scores_gemma":[0.000069878886,0.00012648267,0.000023565914,0.00023551032,0.0004267101,0.0014451679,0.00046639875,0.000080213336,0.00005755325],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016323518,0.000080441045,0.00051312434,0.000070175105,0.000024844125,0.0000038013568,0.00011375052,0.010723799,0.9025307,0.0032919727,0.007595447,0.075035624],"study_design_scores_gemma":[0.00031274933,0.00003570914,0.013797371,0.00007615557,0.000028914861,0.0000070472283,0.000093290895,0.71714294,0.17530991,0.0056748865,0.087015636,0.0005054105],"about_ca_topic_score_codex":0.0000020579707,"about_ca_topic_score_gemma":5.54211e-7,"teacher_disagreement_score":0.7272208,"about_ca_system_score_codex":0.0001681099,"about_ca_system_score_gemma":0.000030486808,"threshold_uncertainty_score":0.51578134},"labels":[],"label_agreement":null}]}