{"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":"6c5de2b011bc","filters":{"venue":"Journal of Geophysical Research Machine Learning and Computation"}},"results":[{"id":"W4409294866","doi":"10.1029/2024jh000409","title":"Comparative and Interpretative Analysis of CNN and Transformer Models in Predicting Wildfire Spread Using Remote Sensing Data","year":2025,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Agence Nationale de la Recherche","keywords":"Remote sensing; Transformer; Computer science; Data mining; Environmental science; Artificial intelligence; Geography; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.05301780255044887,"gpt":0.3959419654192167,"spread":0.3429241628687679,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001855862,0.00008661612,0.0003883295,0.0003907447,0.0001258076,0.00005543215,0.00009055265,0.00003472209,0.000001350097],"category_scores_gemma":[0.0002556233,0.00007306726,0.00002983477,0.0009082485,0.0002020351,0.0004256446,0.0001560315,0.0005727616,1.886783e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006841308,"about_ca_system_score_gemma":0.00002282359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00561715,"about_ca_topic_score_gemma":0.000370838,"domain_scores_codex":[0.9981852,0.0007049099,0.0003375018,0.0002145741,0.0004043591,0.0001535172],"domain_scores_gemma":[0.9984941,0.00114848,0.0001781268,0.00006485444,0.00004933212,0.00006513865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005592906,0.00009762497,0.1286889,0.0001595552,0.000643747,0.00002284989,0.01454132,0.2601554,0.01644696,0.00002646615,0.000008176567,0.5786497],"study_design_scores_gemma":[0.0003321527,0.000199566,0.08722549,0.0002932241,0.00009992259,0.000006249411,0.0005696843,0.9102314,0.00007189427,0.0009190261,0.000004039504,0.0000474052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9127482,0.0002371135,0.08662283,0.0001012486,0.00001259645,0.0001033583,0.000002891377,0.000002978544,0.0001688165],"genre_scores_gemma":[0.9966306,0.00004749583,0.00328542,0.000006098742,0.0000101464,8.51521e-8,0.000005135731,0.000004100013,0.00001090608],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.650076,"threshold_uncertainty_score":0.8491488,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391591814","doi":"10.1029/2024jh000155","title":"A Virtual Solar Wind Monitor at Mars With Uncertainty Quantification Using Gaussian Processes","year":2024,"lang":"en","type":"preprint","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"NASA Headquarters; Nuclear Safety and Security Commission; Irish Research Council; National Science Foundation; Science Foundation Ireland; National Aeronautics and Space Administration","keywords":"Mars Exploration Program; Solar wind; Astrobiology; Environmental science; Gaussian; Remote sensing; Aerospace engineering; Computer science; Meteorology; Physics; Geology; Engineering; Plasma","retraction":null,"screen_n_in":null,"score":{"opus":0.04527142155836497,"gpt":0.3655112043802292,"spread":0.3202397828218642,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001313423,0.0003036113,0.0004726363,0.0005590549,0.0005024064,0.001293737,0.0006418668,0.0001706236,0.000003583897],"category_scores_gemma":[0.0003672452,0.0002205636,0.0001013496,0.0009352735,0.0002080451,0.0003514395,0.001257463,0.003113006,0.00001457948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002235947,"about_ca_system_score_gemma":0.001105527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000263757,"about_ca_topic_score_gemma":0.00001848984,"domain_scores_codex":[0.9964227,0.0005189801,0.0005530235,0.0006258321,0.001450589,0.0004288454],"domain_scores_gemma":[0.9970133,0.0005469518,0.0005834109,0.0002053394,0.00139175,0.0002592911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001372249,0.0007915649,0.007228484,0.007369352,0.0007847147,0.0008563053,0.00927061,0.462858,0.004926169,0.01242842,0.0003195319,0.4917946],"study_design_scores_gemma":[0.0003796119,0.001431704,0.003492656,0.00190636,0.00005866012,0.0002106242,0.0001734207,0.9558627,0.0002412177,0.03569723,0.000217751,0.0003280911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6351646,0.001137146,0.3614964,0.001631777,0.0002145061,0.0002145438,0.000005858979,0.00005702033,0.00007815809],"genre_scores_gemma":[0.9883206,0.0002148256,0.01082294,0.00001211711,0.0003730874,0.000004801637,0.00001252553,0.00003009053,0.0002090462],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4930047,"threshold_uncertainty_score":0.999743,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4404414732","doi":"10.1029/2024jh000243","title":"Using Explainable AI and Transfer Learning to Understand and Predict the Maintenance of Atlantic Blocking With Limited Observational Data","year":2024,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Army Research Office; Climate Extremes; Schmidt Family Foundation; National Science Foundation","keywords":"Blocking (statistics); Observational study; Transfer of learning; Observational learning; Computer science; Artificial intelligence; Psychology; Mathematics education; Mathematics; Computer network; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.09927608756865201,"gpt":0.3485107465980402,"spread":0.2492346590293882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008950715,0.00008387391,0.0001487777,0.0001433708,0.000198532,0.0001546507,0.00007429274,0.00002556653,0.00000127656],"category_scores_gemma":[0.0001596265,0.00005527601,0.0000149376,0.0003273523,0.00008031491,0.0002423961,0.00005967672,0.0007687322,1.260992e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002239639,"about_ca_system_score_gemma":0.00004109723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001037494,"about_ca_topic_score_gemma":0.0000136959,"domain_scores_codex":[0.9990333,0.0001341474,0.0001890529,0.0001260649,0.0003462171,0.0001712557],"domain_scores_gemma":[0.999013,0.000709503,0.00002433402,0.00004336809,0.0001354788,0.00007432429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001596319,0.0000167564,0.01218401,0.0004590034,0.0001436339,0.00004155525,0.00335961,0.942338,0.003704966,0.001150082,0.0000442911,0.0363984],"study_design_scores_gemma":[0.000234693,0.0003665819,0.005747949,0.0007664105,0.0000250745,0.00008932634,0.0005920978,0.9911919,0.00004108626,0.0004341767,0.0004486933,0.00006198535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8911846,0.0009589233,0.1073565,0.0003688576,0.00002595695,0.0000510524,0.000001915552,0.00001724319,0.00003499512],"genre_scores_gemma":[0.9986253,0.0001969559,0.001018363,0.000008421386,0.0000996822,4.444283e-7,0.000007808268,0.00001620977,0.00002679698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1074407,"threshold_uncertainty_score":0.3339801,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407618483","doi":"10.1029/2024jh000360","title":"PEGSGraph: A Graph Neural Network for Fast Earthquake Characterization Based on Prompt ElastoGravity Signals","year":2025,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Seismology and Earthquake Studies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"European Research Council; Grand Équipement National De Calcul Intensif; European Commission","keywords":"Magnitude (astronomy); Seismology; Geology; Amplitude; Warning system; Earthquake simulation; Convolutional neural network; Slip (aerodynamics); Earthquake warning system; Focal mechanism; Computer science; Artificial intelligence; Fault (geology); Engineering; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.02630571733381363,"gpt":0.3405917755114418,"spread":0.3142860581776281,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001570325,0.000129402,0.0002757457,0.0004107395,0.0006911936,0.0001655689,0.0002152485,0.00006036805,0.00000105782],"category_scores_gemma":[0.0004055013,0.0001059916,0.0001345092,0.0008737288,0.0001247083,0.0002013439,0.00008085596,0.0007672469,0.000001682603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001642225,"about_ca_system_score_gemma":0.00009318526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001981056,"about_ca_topic_score_gemma":0.000003588716,"domain_scores_codex":[0.9979907,0.0007068948,0.0002782598,0.00024898,0.0004357504,0.0003394094],"domain_scores_gemma":[0.9975308,0.001510474,0.0001994073,0.00008700183,0.0005836483,0.00008865506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008675023,0.0003481053,0.01711431,0.0001068403,0.0001250822,0.0000185596,0.0003879888,0.1263869,0.001125442,0.006783473,0.0004367902,0.846299],"study_design_scores_gemma":[0.0007432196,0.001893678,0.2392539,0.000124228,0.0000117033,0.000004971572,0.00001427632,0.743342,0.00003918494,0.01296776,0.001520049,0.00008500929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4047361,0.00010491,0.5915124,0.003212881,0.0001673673,0.0001805759,0.000001691014,0.00002627316,0.00005777398],"genre_scores_gemma":[0.9954923,0.00002764778,0.003882451,0.0002517247,0.0001786467,0.00001232158,0.0000133281,0.000005885253,0.0001356592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8462139,"threshold_uncertainty_score":0.5316172,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409661310","doi":"10.1029/2024jh000521","title":"Machine Learning Detection of Melting Layers From Radar Observations","year":2025,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Horace H. Rackham School of Graduate Studies, University of Michigan; National Aeronautics and Space Administration; National Science Foundation","keywords":"Radar; Remote sensing; Computer science; Environmental science; Artificial intelligence; Geology; Materials science; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.05461448376755523,"gpt":0.3326295027074679,"spread":0.2780150189399127,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001245416,0.00008794251,0.000245768,0.0002715093,0.0004630029,0.00006611842,0.0001077949,0.00005403647,0.00006422473],"category_scores_gemma":[0.001413645,0.00006829995,0.00007628418,0.0005866207,0.00009685667,0.0001832564,0.00002678275,0.001004934,0.000005240237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001075492,"about_ca_system_score_gemma":0.00005335686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003211497,"about_ca_topic_score_gemma":0.0001317991,"domain_scores_codex":[0.9979774,0.0008092018,0.0004037996,0.0001471651,0.0004747832,0.0001876778],"domain_scores_gemma":[0.9966534,0.00263378,0.0002411399,0.00004383607,0.0003319746,0.00009590707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00030013,0.00006517593,0.4499819,0.00003583732,0.00008802966,0.000005822711,0.00036307,0.2187947,0.007763126,0.0003433207,0.000007247648,0.3222517],"study_design_scores_gemma":[0.0003430279,0.0004577566,0.4396012,0.00003484966,0.00001644985,0.000001055922,0.0001394483,0.5469599,0.00008975438,0.01171567,0.0005963499,0.00004458876],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.978272,0.0009430636,0.01948751,0.000427911,0.00008373882,0.00007236204,0.000006656418,0.00001450727,0.0006923178],"genre_scores_gemma":[0.997717,0.0001172053,0.001845252,0.0000230108,0.00009681944,3.124593e-7,0.00004448414,0.000002738275,0.0001531897],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3281652,"threshold_uncertainty_score":0.4854844,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403608950","doi":"10.1029/2024jh000239","title":"Estimating Interplanetary Magnetic Field Conditions at Mercury's Orbit From MESSENGER Magnetosheath Observations Using a Feedforward Neural Network","year":2024,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Planetary Science and Exploration","field":"Physics and Astronomy","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Environment Research Council; Nuclear Safety and Security Commission; Irish Research Council; University of British Columbia; Sight Research UK; Laureate Education; Office of Nuclear Energy; Discovery Eye Foundation; National Aeronautics and Space Administration; Science Foundation Ireland; National Science Foundation","keywords":"Magnetosheath; Magnetosphere; Solar wind; Magnetopause; Physics; Interplanetary magnetic field; Geophysics; Spacecraft; Mercury's magnetic field; Magnetic field; Computational physics; Astronomy","retraction":null,"screen_n_in":null,"score":{"opus":0.04567446733168854,"gpt":0.3512440316039304,"spread":0.3055695642722419,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004429007,0.0001124138,0.0001861798,0.0001355661,0.0004497799,0.0002475291,0.00009518166,0.00003071961,0.0001462266],"category_scores_gemma":[0.00005289057,0.00009443382,0.00007176885,0.0003562085,0.00006225151,0.0005046155,0.00006732441,0.0007954725,0.00003475406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000293959,"about_ca_system_score_gemma":0.00006955124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001076297,"about_ca_topic_score_gemma":0.00001688891,"domain_scores_codex":[0.9986006,0.0002560916,0.000302995,0.0001828245,0.0004063543,0.0002511358],"domain_scores_gemma":[0.99856,0.001036373,0.0000953557,0.00005041019,0.0001367066,0.0001211976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001515995,0.0001035572,0.07059994,0.00006475671,0.0001596661,0.00009086879,0.001559278,0.8354297,0.01341839,0.0008505374,0.002828937,0.07474276],"study_design_scores_gemma":[0.000150452,0.0004829614,0.01764691,0.0001559196,0.00004154303,0.00001652651,0.0001350531,0.9713358,0.0000174869,0.009493046,0.0004338475,0.00009039832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9822755,0.0006047367,0.01559581,0.00105976,0.000257327,0.0000790505,0.00002048427,0.0000188843,0.00008843965],"genre_scores_gemma":[0.9941193,0.00001054052,0.004262181,0.00003393835,0.0010395,0.00000210524,0.000404631,0.000009739416,0.0001180889],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1359061,"threshold_uncertainty_score":0.38509,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410497542","doi":"10.1029/2025jh000627","title":"Enhanced Hardrock Seismic Imaging Through Multi‐Scale Information‐Guided Unsupervised Learning","year":2025,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Noise reduction; Noise (video); Feature (linguistics); Computer science; Pattern recognition (psychology); Filter (signal processing); Workflow; Energy (signal processing); Wavelet; Reflection (computer programming); SIGNAL (programming language); Geology; Artificial intelligence; Algorithm; Computer vision; Mathematics; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02351596648432496,"gpt":0.3343809349895149,"spread":0.31086496850519,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001140716,0.000119884,0.000229146,0.0003541659,0.0005643793,0.0002302212,0.0001669689,0.00004367009,0.00005692852],"category_scores_gemma":[0.0005372976,0.00009882033,0.000081562,0.0004931742,0.0001284221,0.0008858453,0.00004230337,0.001231353,0.00003961686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002054157,"about_ca_system_score_gemma":0.0001167444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002886152,"about_ca_topic_score_gemma":0.00000503536,"domain_scores_codex":[0.9981257,0.0005098571,0.0004026827,0.0001427919,0.000530739,0.0002882794],"domain_scores_gemma":[0.9986689,0.0005238689,0.0001903566,0.00005471128,0.0004684665,0.000093675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001803445,0.00005149974,0.06953371,0.0001073361,0.00004387748,0.000008386074,0.001929255,0.05110438,0.0008037767,0.00004289053,0.001956176,0.8742384],"study_design_scores_gemma":[0.0007475718,0.0002245206,0.02940049,0.0001542496,0.00001223662,0.00001671515,0.0009330304,0.9504761,0.0008494342,0.002304822,0.01477803,0.0001027708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6228143,0.0006874827,0.3692991,0.002642774,0.0001925763,0.0001496475,0.000003050673,0.00009757048,0.004113528],"genre_scores_gemma":[0.9934003,0.0002471639,0.005121788,0.0004787057,0.00006977364,6.597494e-7,0.00003567976,0.000003520645,0.0006424193],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8993717,"threshold_uncertainty_score":0.5349687,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415278026","doi":"10.1029/2025jh000957","title":"Season‐Net: A Deep Learning Framework for Bias Correction of Seasonal Forecasting Models","year":2025,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"United Nations University Institute for Water, Environment, and Health","funders":"DeepMind","keywords":"Quantile; Deep learning; Probabilistic logic; Brier score; Climate model; Forecast skill; Probabilistic forecasting","retraction":null,"screen_n_in":null,"score":{"opus":0.08992008324415134,"gpt":0.357978887542862,"spread":0.2680588042987107,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001689304,0.00008814616,0.0002502423,0.000225587,0.0004331024,0.00007676546,0.00009163874,0.00006959141,0.00003522202],"category_scores_gemma":[0.002531628,0.00006807257,0.0001008614,0.0004691001,0.00008987902,0.0001760912,0.00001622919,0.00093023,0.000001634178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001007565,"about_ca_system_score_gemma":0.00006208885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001289124,"about_ca_topic_score_gemma":0.00003121152,"domain_scores_codex":[0.9982735,0.0005660483,0.0003317234,0.0001484995,0.0004464378,0.0002338022],"domain_scores_gemma":[0.9932557,0.005852356,0.0002415473,0.00003268629,0.0005092905,0.0001084609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000333545,0.00003090614,0.04499364,0.00004754099,0.00003300803,0.00000151233,0.0002706682,0.6797271,0.00001707144,0.001290006,0.00001612103,0.2732389],"study_design_scores_gemma":[0.0003083231,0.0007393974,0.04252051,0.0001021224,0.00001641378,0.000002414485,0.0001753183,0.8417976,0.000005589879,0.113961,0.0003220305,0.00004928885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6722399,0.0006035948,0.3256868,0.0002404415,0.0001279848,0.0001141454,0.000002453748,0.00001003406,0.0009746951],"genre_scores_gemma":[0.9903399,0.0000621379,0.009108324,0.00001877931,0.0001408403,0.000001020938,0.00002308499,0.000003246425,0.0003026847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3181,"threshold_uncertainty_score":0.4041438,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414561732","doi":"10.1029/2025jh000769","title":"Leveraging Sparse Autoencoders to Reveal Interpretable Features in Geophysical Models","year":2025,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Jet Propulsion Laboratory; National Aeronautics and Space Administration","keywords":"Perceptron; Set (abstract data type); Feature (linguistics); Artificial neural network; Aggregate (composite); Pattern recognition (psychology); Representation (politics); ENCODE","retraction":null,"screen_n_in":null,"score":{"opus":0.0310335110787255,"gpt":0.3672593779348382,"spread":0.3362258668561127,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001190453,0.0001237115,0.0002914894,0.0006370863,0.00009047319,0.0001136556,0.0001339251,0.00005724929,0.000001910409],"category_scores_gemma":[0.000341021,0.0001138803,0.00006461995,0.0007082284,0.00002949034,0.0002098764,0.00005568882,0.001340567,0.000002889444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001088214,"about_ca_system_score_gemma":0.00004114559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000135378,"about_ca_topic_score_gemma":0.000004171168,"domain_scores_codex":[0.9985014,0.0003208248,0.0003277228,0.0001472124,0.0004082747,0.0002946057],"domain_scores_gemma":[0.9988503,0.0007282726,0.00003455495,0.00006776317,0.000187948,0.0001311249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007372911,0.00002864808,0.0005945954,0.00007403947,0.00002596915,0.00001172398,0.0008204466,0.97128,0.001005472,0.0003317697,0.0002431288,0.02551048],"study_design_scores_gemma":[0.0004676704,0.0001374297,0.01423445,0.0002483656,0.000005567394,0.000004647492,0.0001121183,0.9747838,0.00009222099,0.009452906,0.0003702244,0.00009062455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.632995,0.000266841,0.3654761,0.0003337096,0.0001001519,0.0000719368,3.749268e-7,0.00003666886,0.000719222],"genre_scores_gemma":[0.9851105,0.00005885493,0.01425739,0.00002037443,0.00009068847,0.000003884279,0.000002048475,0.00001619662,0.000440089],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3521155,"threshold_uncertainty_score":0.582417,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403547445","doi":"10.1029/2024jh000180","title":"A Machine Learning Zircon Trace Element Tool to Predict Porphyry Deposit Type and Resource Size","year":2024,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Zircon; Trace element; Geology; Geochemistry; TRACE (psycholinguistics); Resource (disambiguation); Computer science; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.02064792294817338,"gpt":0.3216426911934498,"spread":0.3009947682452765,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002127134,0.0001456251,0.0002339377,0.0001853179,0.0003414484,0.0004815813,0.0002422904,0.00006449511,0.00001022166],"category_scores_gemma":[0.00176998,0.0001192049,0.00005614134,0.0007414056,0.00005607642,0.0002520611,0.0003244969,0.001629808,0.00001150033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004504801,"about_ca_system_score_gemma":0.00009999761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008541943,"about_ca_topic_score_gemma":0.000001788839,"domain_scores_codex":[0.9977508,0.0005147028,0.0003432782,0.0003458113,0.0007059246,0.0003395372],"domain_scores_gemma":[0.9979103,0.001282294,0.000104372,0.00008919219,0.0003923471,0.0002214998],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004530845,0.0002267077,0.01055122,0.0006091582,0.0002020366,0.000637283,0.004214272,0.04900096,0.04109668,0.004246857,0.001125135,0.8876366],"study_design_scores_gemma":[0.0004423599,0.002276782,0.01118359,0.0003349546,0.00001796991,0.000287857,0.0001302138,0.9184134,0.0006772114,0.004036689,0.06200882,0.0001901311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8132594,0.004025635,0.1695633,0.01127401,0.0001448012,0.0002283083,0.000001352353,0.0001360844,0.001367133],"genre_scores_gemma":[0.9920112,0.0001491567,0.006038639,0.00005207432,0.0002256149,0.000002814234,0.000003515603,0.00000726205,0.001509682],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8874465,"threshold_uncertainty_score":0.7080794,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415503615","doi":"10.1029/2025jh000678","title":"Generative Adversarial Networks for Downscaling Hourly Precipitation in the Canadian Prairies","year":2025,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Meteorological Phenomena and Simulations","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":"BGC Engineering (Canada); University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Downscaling; Climate model; Precipitation; Benchmark (surveying); Climate change; Key (lock); Fidelity; Spatial ecology; Coupled model intercomparison project; Adversarial system","retraction":null,"screen_n_in":null,"score":{"opus":0.04368227263063241,"gpt":0.3513988275452843,"spread":0.3077165549146519,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002001763,0.00005333595,0.0001219462,0.0002101711,0.0005541607,0.0001580686,0.00009079387,0.00004294501,0.00000821931],"category_scores_gemma":[0.0009066319,0.00003322768,0.00003817446,0.0003491094,0.00007860509,0.0001218878,0.000005208504,0.0005584442,0.000001166138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001517925,"about_ca_system_score_gemma":0.0001449753,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02822185,"about_ca_topic_score_gemma":0.07799961,"domain_scores_codex":[0.9985602,0.0007075825,0.0002028268,0.00009093398,0.0002496759,0.0001887304],"domain_scores_gemma":[0.996944,0.002666443,0.00007139859,0.00002418671,0.000225438,0.00006860196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002160617,0.00001893755,0.07949232,0.000009488906,0.00001825369,0.000003283932,0.0008368819,0.807407,0.000005296727,0.00240647,0.000138218,0.1094478],"study_design_scores_gemma":[0.0002952977,0.000378031,0.3431112,0.00001282115,0.000005568692,9.09946e-7,0.0001667039,0.6313209,4.103689e-7,0.0240096,0.0006728597,0.00002574241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9342661,0.0005417318,0.05610057,0.00716143,0.0001695743,0.0003278947,0.000007469634,0.000004986845,0.001420183],"genre_scores_gemma":[0.9985862,0.0000172472,0.0009971412,0.0001095477,0.0001958778,0.000001481236,0.00003951831,0.00000106512,0.00005193099],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2636188,"threshold_uncertainty_score":0.9782493,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4412201725","doi":"10.1029/2025jh000639","title":"A Multimodal Deep Learning Approach for Soil Moisture Downscaling Using Remote Sensing and Weather Data","year":2025,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Soil Moisture and Remote Sensing","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Hatch; National Institute of Food and Agriculture; U.S. Department of Agriculture","keywords":"Downscaling; Environmental science; Transferability; Remote sensing; Water content; Meteorology; Computer science; Machine learning; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.03673824536663338,"gpt":0.356958868913497,"spread":0.3202206235468636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001737844,0.0001370271,0.0002653249,0.0001444186,0.0006706297,0.0001617886,0.0001340791,0.00008827035,0.000001071565],"category_scores_gemma":[0.0007583691,0.0001093545,0.00005660749,0.0003286228,0.0002000209,0.0001896056,0.0003671582,0.001166765,8.925201e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008062457,"about_ca_system_score_gemma":0.00002963533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0029202,"about_ca_topic_score_gemma":0.0001124622,"domain_scores_codex":[0.9981494,0.000464062,0.0002846507,0.0003360753,0.0004657572,0.0003000685],"domain_scores_gemma":[0.9988499,0.000662617,0.0001693994,0.0001004606,0.0001070409,0.0001106136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000162307,0.00003374413,0.003149588,0.00005793522,0.00004606574,0.000009306706,0.0005490351,0.1223044,0.007665416,0.000006773644,0.00002606535,0.8659893],"study_design_scores_gemma":[0.0006688099,0.0001627125,0.01241629,0.0001112915,0.00004439012,0.00005909859,0.0004425537,0.9838164,0.00006068575,0.001393111,0.0007207874,0.0001038371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4812679,0.0004192308,0.5170981,0.0003111163,0.00004431724,0.000123406,3.683377e-7,0.00001329466,0.000722249],"genre_scores_gemma":[0.9186994,0.00006533995,0.08080705,0.00003885728,0.0001885303,5.197061e-8,0.00001255754,0.00001593554,0.0001722206],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8658855,"threshold_uncertainty_score":0.5158009,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408382020","doi":"10.1029/2024jh000528","title":"Selecting Observationally Constrained Global Climate Model Ensembles Using Autoencoders and Transfer Learning","year":2025,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Climate variability and models","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":"Transfer of learning; Computer science; Artificial intelligence; Climate model; Climate change; Ecology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.05346093572333434,"gpt":0.3717161218159152,"spread":0.3182551860925809,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001681553,0.0001010659,0.0001941209,0.00007450046,0.0005701414,0.000113747,0.00006997051,0.00005516167,0.00001019267],"category_scores_gemma":[0.0004453751,0.00009111883,0.00004929588,0.0003679505,0.0002134279,0.0002518049,0.0001135793,0.0007224283,0.000001285433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001342479,"about_ca_system_score_gemma":0.00008071453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003158493,"about_ca_topic_score_gemma":0.00002635915,"domain_scores_codex":[0.9983686,0.0003961798,0.0003051063,0.00019995,0.0004547576,0.0002754254],"domain_scores_gemma":[0.9991125,0.0005702217,0.00007572732,0.00003024874,0.0001125607,0.0000987198],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001148952,0.00005589927,0.06407252,0.00004509436,0.00001987536,0.000003412563,0.0003707551,0.9158438,0.005843141,0.00212453,0.000004306477,0.01150181],"study_design_scores_gemma":[0.0004672604,0.0001826959,0.02142767,0.00007929237,0.00001981518,0.00001728779,0.0001851573,0.9614956,0.00001884338,0.01600192,0.00003210272,0.00007232551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8460709,0.00004972546,0.1526816,0.0005149183,0.00001657958,0.00007043544,0.000001635263,0.00001388494,0.0005803215],"genre_scores_gemma":[0.9905287,0.00007807763,0.009279713,0.0000409848,0.0000223491,9.613364e-7,0.000003140984,0.00000560347,0.00004048048],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1444578,"threshold_uncertainty_score":0.4385124,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}