{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":39,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":39,"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":"74bb47395206","filters":{"venue":"Nature Computational Science"}},"results":[{"id":"W4296126438","doi":"10.1038/s43588-022-00311-3","title":"Challenges and opportunities in quantum machine learning","year":2022,"lang":"en","type":"review","venue":"Nature Computational Science","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":652,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Los Alamos National Laboratory; National Nuclear Security Administration; Office of Science; Verily Life Sciences; Advanced Scientific Computing Research; Laboratory Directed Research and Development; U.S. Department of Energy","keywords":"Quantum machine learning; Quantum; Intersection (aeronautics); Computer science; Focus (optics); Artificial intelligence; Quantum computer; Physics; Quantum mechanics; Engineering; Aerospace engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.08765781566270549,"gpt":0.3352398295275563,"spread":0.2475820138648508,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001803872,0.0003636041,0.0007189259,0.0009642062,0.0005691469,0.0002608289,0.001906685,0.0001882621,0.000009633829],"category_scores_gemma":[0.0002684372,0.0003050271,0.0001178328,0.001132831,0.0002928517,0.0003346064,0.001582004,0.002347916,0.00000325727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001473617,"about_ca_system_score_gemma":0.0008653569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007535495,"about_ca_topic_score_gemma":0.000004464281,"domain_scores_codex":[0.9966866,0.0003222775,0.0004185091,0.00108263,0.001035331,0.0004546535],"domain_scores_gemma":[0.9978738,0.001302704,0.0002897154,0.0003110267,0.0000669738,0.0001557177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[3.40051e-7,0.00001907564,4.661702e-7,0.0004652652,0.000005182512,0.00005745691,0.0002698688,0.004931686,1.635765e-8,0.09030887,0.000004946897,0.9039368],"study_design_scores_gemma":[0.00005935842,0.00004971756,0.00004278378,0.0006463964,0.000006617408,0.0002620353,0.00001111653,0.37053,1.641788e-8,0.005949781,0.6221749,0.0002672445],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000009536859,0.9951939,0.00263198,0.0006804738,0.0005371522,0.0002112522,0.000006570363,0.0001362925,0.0005928435],"genre_scores_gemma":[0.00056174,0.9907492,0.008369758,0.000158391,0.00007586143,0.00002237997,0.00002483265,0.00001758566,0.00002021816],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9036696,"threshold_uncertainty_score":0.9999537,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4367626474","doi":"10.1038/s43588-023-00437-y","title":"Fast evaluation of the adsorption energy of organic molecules on metals via graph neural networks","year":2023,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":104,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto; Fleming College","funders":"Agencia Estatal de Investigación; Ministerio de Ciencia e Innovación; National Science Foundation; Vetenskapsrådet; Generalitat de Catalunya; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Adsorption; Artificial neural network; Organic molecules; Molecule; Graph; Computer science; Materials science; Chemistry; Biological system; Chemical engineering; Artificial intelligence; Organic chemistry; Theoretical computer science; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0120194387643537,"gpt":0.2892927609224042,"spread":0.2772733221580506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004074776,0.0001262207,0.0001652379,0.0002351885,0.0002480329,0.00006346868,0.0009836829,0.00008606355,0.0001654767],"category_scores_gemma":[0.001092729,0.00008692064,0.00006417136,0.002846871,0.0007450525,0.0002402817,0.0002293904,0.0001684606,0.00001311812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006156463,"about_ca_system_score_gemma":0.000205734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002248506,"about_ca_topic_score_gemma":0.00001554977,"domain_scores_codex":[0.9960483,0.0003959987,0.0003403211,0.0004182566,0.002537778,0.0002593795],"domain_scores_gemma":[0.9981127,0.0003267877,0.0004091517,0.0002978065,0.0008017508,0.00005178292],"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":[0.000006069899,0.00001269292,0.0002471764,0.000003643949,8.856045e-7,1.175428e-7,0.00004440248,0.608264,0.3874422,0.003406443,0.00002141646,0.0005508799],"study_design_scores_gemma":[0.0001247024,0.00004386372,0.08958786,0.00002200689,0.00001039346,0.000004245915,0.00001074746,0.8150682,0.08343063,0.01161516,0.000002636323,0.00007958221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9573679,0.00005620694,0.04055864,0.0003275562,0.001329233,0.0001647589,0.000009428689,0.00005302147,0.0001332489],"genre_scores_gemma":[0.9983944,0.000001658892,0.001338633,0.0001730786,0.0000551209,0.000009254547,0.000009968237,0.000007755914,0.00001008217],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3040116,"threshold_uncertainty_score":0.3544521,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4281786804","doi":"10.1038/s43588-022-00249-6","title":"Generative aptamer discovery using RaptGen","year":2022,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Advanced biosensing and bioanalysis techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":103,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Core Research for Evolutional Science and Technology; Institute of Genetics; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Aptamer; Systematic evolution of ligands by exponential enrichment; Autoencoder; In silico; Computer science; Artificial intelligence; Generative model; Computational biology; Bayesian probability; Hidden Markov model; Embedding; Machine learning; Pattern recognition (psychology); Generative grammar; Biology; Deep learning; Genetics; RNA; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.009713030648766307,"gpt":0.3105372633547858,"spread":0.3008242327060194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002663892,0.00007874594,0.00006402491,0.0000783124,0.0005812586,0.00004436394,0.0002303011,0.00004269739,0.000003335378],"category_scores_gemma":[0.00006202153,0.00007014058,0.0000506252,0.0004828355,0.0002453418,0.00001199616,0.0002604136,0.0001685471,3.486603e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005854834,"about_ca_system_score_gemma":0.0002098398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003750405,"about_ca_topic_score_gemma":0.000001672933,"domain_scores_codex":[0.9989682,0.00003968693,0.00009277636,0.0003489289,0.000403336,0.0001470907],"domain_scores_gemma":[0.9996312,0.00001181925,0.00006484426,0.0001241125,0.0001315015,0.00003650302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001919094,0.00003310156,0.0003801881,7.686433e-7,0.00001237784,0.000002536873,0.00001591503,0.04986797,0.9469169,0.001319078,0.0003204172,0.001111493],"study_design_scores_gemma":[0.0003570135,0.0003132215,0.00386053,0.000006266577,0.00002909551,0.0001475521,0.0001801461,0.07239684,0.8997704,0.007174928,0.01516785,0.0005961737],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9186176,0.0003117553,0.08016725,0.0003225572,0.0001722897,0.00008940541,0.00003955496,0.00002091333,0.0002586766],"genre_scores_gemma":[0.9491494,0.000003688269,0.04953614,0.001029063,0.0001056917,0.000003449941,0.00007199417,0.00000509322,0.00009546425],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04714658,"threshold_uncertainty_score":0.4470629,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4368374143","doi":"10.1038/s43588-023-00440-3","title":"Score-based generative modeling for de novo protein design","year":2023,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":79,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"CIHR Skin Research Training Centre; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Generative grammar; Generative model; Computer science; Protein design; Generative Design; Modular design; Image (mathematics); Protein engineering; Artificial intelligence; Protein structure; Algorithm; Biology; Programming language; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02197950252939696,"gpt":0.3049594280013972,"spread":0.2829799254720003,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004352997,0.00008091221,0.00005450108,0.000069493,0.0002367909,0.00004187532,0.0002294167,0.0001207819,9.653514e-7],"category_scores_gemma":[0.000331052,0.00007277023,0.00003552152,0.0003741047,0.0001081944,0.00000606948,0.00004558196,0.00009425452,0.000001778207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003138922,"about_ca_system_score_gemma":0.0006826133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001307437,"about_ca_topic_score_gemma":0.000003267256,"domain_scores_codex":[0.9991519,0.00002042836,0.00008442735,0.0003000199,0.0002199182,0.0002232594],"domain_scores_gemma":[0.9995111,0.00002977755,0.00003179859,0.00009650982,0.0002719408,0.00005883137],"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":[0.0000297831,0.000004469158,0.00003409604,0.000004346789,0.000002605005,8.123117e-7,0.00000901547,0.7352465,0.2614865,0.002560091,0.00005042356,0.000571357],"study_design_scores_gemma":[0.0002242345,0.00007467063,0.0001996395,0.000007211625,0.000001992092,0.000003323634,0.000003320492,0.8786278,0.09748713,0.02318997,0.00008610288,0.00009455787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2861637,0.00005194496,0.7131115,0.0002673736,0.00005674114,0.0002931702,0.00001475351,0.00001787456,0.00002286146],"genre_scores_gemma":[0.7733631,6.324859e-7,0.2258832,0.000481325,0.0001052339,0.00005412052,0.0000849827,0.000006133925,0.00002133688],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4872283,"threshold_uncertainty_score":0.2967484,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387580187","doi":"10.1038/s43588-023-00526-y","title":"A universal programmable Gaussian boson sampler for drug discovery","year":2023,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Youth Innovation Promotion Association; Engineering and Physical Sciences Research Council; Youth Innovation Promotion Association of the Chinese Academy of Sciences; Research Councils UK; National Natural Science Foundation of China; China Postdoctoral Science Foundation; Chinese Academy of Sciences; UK Research and Innovation","keywords":"Computer science; Scalability; Clique; Quantum computer; Gaussian; Quantum circuit; Unitary state; Theoretical computer science; Parallel computing; Quantum; Computational science; Computer engineering; Quantum network; Mathematics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01324657690590004,"gpt":0.286996088525048,"spread":0.273749511619148,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007950498,0.0001451141,0.0001312516,0.0002642326,0.000835878,0.0007919922,0.001571347,0.00007041052,0.000001657736],"category_scores_gemma":[0.0001364621,0.0001178308,0.0000899788,0.003364329,0.0002075213,0.001456097,0.0005910981,0.000295616,0.0000182196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008651507,"about_ca_system_score_gemma":0.0003635358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001482211,"about_ca_topic_score_gemma":0.00000754628,"domain_scores_codex":[0.9976654,0.0000295016,0.0001776383,0.0006828713,0.0008230789,0.0006215072],"domain_scores_gemma":[0.998692,0.0005285572,0.00009461466,0.0002761536,0.0002565085,0.0001521613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001516902,0.00005486885,0.0009447444,0.00002907735,0.00001183348,0.00002666692,0.0003359811,0.4562184,0.000411184,0.4992831,0.009975564,0.03269338],"study_design_scores_gemma":[0.0002647694,0.00004349436,0.006886574,0.00002999265,0.000002162473,0.00001083265,0.00002108392,0.9369442,0.0002124055,0.04684646,0.008543038,0.00019494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08997271,0.0001283609,0.8961344,0.01039518,0.001764339,0.0005561195,0.00001048214,0.0005969561,0.0004414706],"genre_scores_gemma":[0.9020571,0.000003101893,0.09694725,0.0003818215,0.0002178746,0.00001362297,0.00001876502,0.00000829584,0.0003521693],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8120844,"threshold_uncertainty_score":0.7637199,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4360999013","doi":"10.1038/s43588-023-00419-0","title":"Multi-view manifold learning of human brain-state trajectories","year":2023,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":41,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"National Institute of General Medical Sciences; Canadian Institute for Advanced Research; Institut de Valorisation des Données; Alfred P. Sloan Foundation; National Institutes of Health; National Science Foundation","keywords":"Manifold (fluid mechanics); Nonlinear dimensionality reduction; Cognitive science; Artificial intelligence; State (computer science); Computer science; Manifold alignment; Neuroscience; Psychology; Engineering; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.04350426684592334,"gpt":0.3349643886223415,"spread":0.2914601217764182,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008570387,0.0001386805,0.0001717248,0.0003374809,0.0009224624,0.00006514268,0.0004464446,0.00005543174,0.00001906188],"category_scores_gemma":[0.01419892,0.0001284347,0.00006334464,0.00299009,0.0006431398,0.0003600479,0.0002283759,0.0004380546,0.00006797755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007364374,"about_ca_system_score_gemma":0.0001624383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001218526,"about_ca_topic_score_gemma":0.00001406827,"domain_scores_codex":[0.9976603,0.00009791375,0.0002199077,0.0006079124,0.001090465,0.0003234589],"domain_scores_gemma":[0.9936927,0.005699407,0.0001357993,0.0001275081,0.0002752124,0.00006940038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00001906096,0.000106252,0.009374972,0.00007221671,0.0000104407,0.00003095866,0.001427134,0.1024866,0.7867383,0.09530813,0.002116597,0.002309255],"study_design_scores_gemma":[0.0007685117,0.0002790619,0.8243287,0.00008918423,0.000007670733,0.00003469932,0.0001985123,0.06721584,0.07702616,0.0241913,0.005368887,0.0004915006],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904947,0.0001017226,0.001983744,0.005085337,0.0007869038,0.0002423483,0.00002208281,0.0003471318,0.0009360461],"genre_scores_gemma":[0.9971278,0.000006710165,0.0009692656,0.001268084,0.00005105318,0.00000986843,0.000004616108,0.00001111739,0.0005514662],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8149537,"threshold_uncertainty_score":0.9941049,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411100483","doi":"10.1038/s43588-025-00798-6","title":"Advancing real-time infectious disease forecasting using large language models","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Army Research Office; Centers for Disease Control and Prevention; Merck KGaA; National Science Foundation; U.S. Department of Health and Human Services; U.S. Department of Defense","keywords":"Infectious disease (medical specialty); Disease; Computer science; Medicine; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.07656215060837927,"gpt":0.4281039677513484,"spread":0.3515418171429691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001362015,0.0001312711,0.0002056139,0.0001572412,0.0006629093,0.00004715971,0.0002540132,0.00007172046,0.0000159948],"category_scores_gemma":[0.01304615,0.0001072692,0.000064273,0.001048051,0.0001697811,0.0002658634,0.0003407855,0.000271681,0.000003654427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003503808,"about_ca_system_score_gemma":0.0003048861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003267363,"about_ca_topic_score_gemma":0.00001524293,"domain_scores_codex":[0.9984807,0.00006397566,0.0002440323,0.0004031353,0.0004282934,0.00037988],"domain_scores_gemma":[0.9957913,0.003579096,0.0001173558,0.0001467622,0.000258848,0.0001066758],"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":[0.00002115681,0.0001239046,0.00985194,0.00012867,0.0000218796,0.00002754698,0.0004085997,0.599465,0.001105825,0.3862698,0.0007338289,0.001841889],"study_design_scores_gemma":[0.0001008247,0.000004590262,0.004583697,0.00006084132,0.0000109807,0.000001309573,0.00001899713,0.583393,0.0000113494,0.4117119,0.00002723534,0.0000753347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6187959,0.000299976,0.3767541,0.0007239351,0.0001842707,0.0002474384,0.00001895163,0.0002019273,0.002773535],"genre_scores_gemma":[0.9343535,0.000003319399,0.06456737,0.0009566569,0.00005556285,0.000006371894,0.000003774517,0.000005733869,0.00004773071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3155576,"threshold_uncertainty_score":0.9952674,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313366884","doi":"10.1038/s43588-022-00382-2","title":"A machine learning route between band mapping and band structure","year":2022,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Horizon 2020 Framework Programme; Max-Planck-Gesellschaft; Deutsche Forschungsgemeinschaft; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Computer science; Artificial intelligence; Pipeline (software); Machine learning; Scalability; Electronic band structure; Physics; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.007556286675695394,"gpt":0.2575494992656701,"spread":0.2499932125899747,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002317742,0.0001958166,0.0002284569,0.0002702269,0.002612832,0.0004622427,0.0009222717,0.0000690158,0.0009964204],"category_scores_gemma":[0.0006636053,0.0001783492,0.0000287584,0.001144537,0.0006198951,0.0004874134,0.0005901477,0.0009385759,0.00001357295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001645151,"about_ca_system_score_gemma":0.0002638816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006033817,"about_ca_topic_score_gemma":0.000006006416,"domain_scores_codex":[0.9965816,0.0002652757,0.0002875491,0.0008089208,0.001583239,0.0004734296],"domain_scores_gemma":[0.9988385,0.0004257855,0.000231275,0.0001822929,0.000147404,0.0001746752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002144382,0.00001817117,0.1057275,0.00002790418,0.000004299259,0.00001527607,0.001304251,0.421366,0.466524,0.003104366,0.00007459227,0.0018121],"study_design_scores_gemma":[0.001131102,0.0003291911,0.753101,0.00004537159,0.00002003462,0.0003967587,0.0002894174,0.1724791,0.02377378,0.03083369,0.01652524,0.001075287],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9930981,0.0003448067,0.004038511,0.0009101465,0.0007029717,0.0001802301,0.0001259904,0.0001313227,0.0004679164],"genre_scores_gemma":[0.9825502,0.000001657059,0.01674205,0.0004117827,0.0001434408,0.00000865135,0.0000434964,0.0000130416,0.00008569707],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6473735,"threshold_uncertainty_score":0.9999168,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4300861583","doi":"10.1038/s43588-022-00315-z","title":"Homeostatic coordination and up-regulation of neural activity by activity-dependent myelination","year":2022,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":21,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Hospital for Sick Children; University of Ottawa; University Health Network","funders":"CIHR Skin Research Training Centre; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Neuroscience; Myelin; Homeostatic plasticity; Oligodendrocyte; Neuroplasticity; Axon; Premovement neuronal activity; Neural activity; Homeostasis; Mechanism (biology); Biology; Chemistry; Central nervous system; Neurotransmission; Physics; Metaplasticity; Cell biology; Receptor","retraction":null,"screen_n_in":null,"score":{"opus":0.01165149262008552,"gpt":0.2696882692544466,"spread":0.258036776634361,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005416443,0.0001049064,0.0001084258,0.0002409977,0.0007658019,0.00007146139,0.000215306,0.00004262214,0.00003237159],"category_scores_gemma":[0.0004780652,0.0001062063,0.00002738636,0.001066831,0.0002608148,0.0007150804,0.0001853401,0.0003650845,9.832336e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001834679,"about_ca_system_score_gemma":0.00009673469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001639583,"about_ca_topic_score_gemma":0.000002269426,"domain_scores_codex":[0.997811,0.0001589596,0.0001434838,0.0004695059,0.001246504,0.0001705437],"domain_scores_gemma":[0.9989826,0.0004734762,0.0002345843,0.00009833111,0.0001523705,0.00005865251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006295307,0.00009832703,0.0003215682,0.00001024595,0.000001133843,6.772099e-7,0.00008763972,0.04490795,0.9120245,0.007459775,0.0001053761,0.03491982],"study_design_scores_gemma":[0.0003929361,0.0001519857,0.1058971,0.000003045065,0.000005025996,0.00002930354,0.00001848488,0.8196731,0.06579711,0.007815205,0.00008142908,0.0001352968],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9896638,0.00002217783,0.007266388,0.001916786,0.0006733158,0.0002553786,0.00007363266,0.00003516804,0.00009336537],"genre_scores_gemma":[0.9994187,0.000001917373,0.0001336152,0.0002634141,0.00001851891,0.00001522465,0.00001780973,0.000006927323,0.0001238111],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8462274,"threshold_uncertainty_score":0.5890006,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388721914","doi":"10.1038/s43588-023-00544-w","title":"Predictive analyses of regulatory sequences with EUGENe","year":2023,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"U.S. Department of Health and Human Services; National Institutes of Health; National Institute of General Medical Sciences; Canadian Institute for Advanced Research; National Human Genome Research Institute; U.S. National Library of Medicine; Deutsche Forschungsgemeinschaft","keywords":"Deep learning; Workflow; Computer science; Interoperability; Artificial intelligence; Genomics; Set (abstract data type); Deep sequencing; Software; Data science; Machine learning; World Wide Web; Genome; Programming language; Biology; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.009639506463573306,"gpt":0.298329943301521,"spread":0.2886904368379477,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001864767,0.00005630967,0.00005816479,0.00007295829,0.00008713649,0.00001232393,0.0002097636,0.00005822003,0.000002238113],"category_scores_gemma":[0.00005384551,0.00004378358,0.00002203091,0.0005646257,0.000360424,0.0000045663,0.00006757011,0.00005683208,0.000001603767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001230921,"about_ca_system_score_gemma":0.0002848928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003363525,"about_ca_topic_score_gemma":0.000003754617,"domain_scores_codex":[0.999285,0.000009798424,0.00008428558,0.0002121339,0.0003012592,0.000107554],"domain_scores_gemma":[0.999527,0.00001810648,0.00006681629,0.0001085032,0.0002421705,0.00003740118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00001974345,0.00001386648,0.003615803,0.000008114833,0.00002396187,0.00000163501,0.00003885958,0.4579305,0.5362262,0.001605093,0.0001585498,0.0003576728],"study_design_scores_gemma":[0.0003660034,0.0004543736,0.6032926,0.00002815769,0.00002097436,0.00002447004,0.0001425138,0.1340779,0.2542798,0.006807182,0.0002611512,0.0002448429],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956296,0.0001510803,0.003634945,0.00007586448,0.00005524466,0.00005016979,0.00002311303,0.000009425695,0.0003705309],"genre_scores_gemma":[0.994222,0.00001097276,0.005575915,0.00005495814,0.00003510736,0.000002357918,0.00006135031,0.000003748837,0.00003359455],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5996768,"threshold_uncertainty_score":0.1785442,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391105010","doi":"10.1038/s43588-023-00578-0","title":"Language models for quantum simulation","year":2024,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto; Perimeter Institute; University of Waterloo","funders":"","keywords":"Computer science; Quantum; Physics; Quantum mechanics","retraction":null,"screen_n_in":null,"score":{"opus":0.01195099473052037,"gpt":0.3145427120767464,"spread":0.3025917173462261,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006711895,0.0001271638,0.00009708891,0.0002812068,0.0003662345,0.0006595076,0.0009053432,0.0000827445,0.000002200514],"category_scores_gemma":[0.0001451446,0.0001043631,0.00007669115,0.001363369,0.0001188463,0.0008214048,0.0001740966,0.0003052439,0.00001249875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006410688,"about_ca_system_score_gemma":0.0003333236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003285938,"about_ca_topic_score_gemma":5.656019e-7,"domain_scores_codex":[0.9982433,0.00001869885,0.0001689727,0.0006175154,0.0006429361,0.0003085643],"domain_scores_gemma":[0.9985507,0.0008736384,0.00003642932,0.0002164892,0.0002262572,0.00009645287],"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":[9.976129e-7,0.000007156927,8.902156e-7,0.00001087862,0.000002312374,0.000003718885,0.0004234303,0.6308236,0.0001253794,0.3317481,0.00007990621,0.03677363],"study_design_scores_gemma":[0.00006559081,0.00003020274,0.0001668787,0.00003038074,0.000001782311,0.00001260728,0.000005337041,0.7762087,0.00008780826,0.2225004,0.0007753592,0.000114916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01623987,0.001031057,0.9789298,0.001746797,0.001205286,0.0001881805,0.00001087136,0.0004394017,0.0002087533],"genre_scores_gemma":[0.8100451,6.893458e-7,0.1893471,0.0003737324,0.0001899002,0.000006561411,0.000007153027,0.000007050579,0.00002269643],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7938053,"threshold_uncertainty_score":0.6359647,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392058032","doi":"10.1038/s43588-024-00600-z","title":"Accelerating discovery in organic redox flow batteries","year":2024,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Advanced battery technologies research","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; Structural Genomics Consortium; Muscular Dystrophy Canada; University of Toronto","funders":"Canada First Research Excellence Fund","keywords":"Flow battery; Redox; Battery (electricity); Computer science; Energy storage; Field (mathematics); Flow (mathematics); Biochemical engineering; Data science; Nanotechnology; Environmental science; Process engineering; Engineering; Materials science; Chemistry; Physics; Inorganic chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01075449243694403,"gpt":0.290593022168445,"spread":0.2798385297315009,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001982916,0.00008785853,0.00007062043,0.0003142181,0.00008455632,0.0003235645,0.0003789736,0.00008127689,0.000059748],"category_scores_gemma":[0.0002382677,0.00007923719,0.0000146698,0.001813709,0.0002084474,0.00108975,0.0001374391,0.000656943,0.00003102264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002516032,"about_ca_system_score_gemma":0.0001039178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.32743e-7,"about_ca_topic_score_gemma":0.000008142701,"domain_scores_codex":[0.9989209,0.00000628871,0.0001213722,0.0002594587,0.0004255375,0.0002664518],"domain_scores_gemma":[0.9996001,0.0002152709,0.000006060118,0.0001069088,0.0000445059,0.00002719226],"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":[0.000001758506,0.000006476849,0.0004992771,0.00005869955,0.000004101403,0.0000538444,0.0001490798,0.9103362,0.03197233,0.006484005,0.0003839512,0.05005026],"study_design_scores_gemma":[0.00005063961,0.00001095121,0.009578765,0.00007731723,5.952961e-7,0.00001921089,0.00004052843,0.9701621,0.004840015,0.01422721,0.0008518833,0.0001407939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7837353,0.001843711,0.2084428,0.001691393,0.001130699,0.0001882336,0.00001836087,0.001115754,0.001833785],"genre_scores_gemma":[0.9767272,0.00001346904,0.02307935,0.00006412447,0.00004733597,0.000008563243,0.000006486714,0.00001214137,0.00004133293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1929919,"threshold_uncertainty_score":0.3231199,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407235352","doi":"10.1038/s43588-024-00764-8","title":"A statistical framework for multi-trait rare variant analysis in large-scale whole-genome sequencing studies","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; McGill University; University of Calgary; Université Laval; University of Saskatchewan; Université de Montréal; Providence Health Care","funders":"National Institute on Minority Health and Health Disparities; National Center for Research Resources; National Institute of Biomedical Imaging and Bioengineering; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Center for Advancing Translational Sciences; National Human Genome Research Institute; National Institute of Mental Health; National Heart, Lung, and Blood Institute; National Institute on Aging; National Cancer Institute; Mississippi State Department of Health; National Institute of Neurological Disorders and Stroke; Evans Medical Foundation; National Institute of Diabetes and Digestive and Kidney Diseases; Johns Hopkins University; Jackson State University; U.S. Department of Veterans Affairs; Wake Forest University; American Diabetes Association; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Trait; Whole genome sequencing; Computational biology; Scale (ratio); Biology; Evolutionary biology; Genetics; Genome; Statistics; Computer science; Mathematics; Gene; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.02284864972858161,"gpt":0.369801713637589,"spread":0.3469530639090074,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009719924,0.00009997157,0.0002132503,0.0001995672,0.0002321832,0.00002412501,0.0002304394,0.0002055013,0.000004437852],"category_scores_gemma":[0.002603466,0.00009137434,0.00007242188,0.001050891,0.0001815078,0.000004956397,0.0001169952,0.0001853669,0.000001025013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001137945,"about_ca_system_score_gemma":0.0003708619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006918109,"about_ca_topic_score_gemma":0.0001830013,"domain_scores_codex":[0.9987754,0.00006274455,0.0002477237,0.0004655881,0.0001522278,0.0002963535],"domain_scores_gemma":[0.9990579,0.0003276265,0.00007719221,0.0001341594,0.0003550038,0.00004815623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00008415356,0.0002810605,0.1680727,0.00007657288,0.0008617579,0.00001059673,0.001080769,0.6895863,0.0172375,0.1199825,0.0007354999,0.001990557],"study_design_scores_gemma":[0.0004877867,0.00005966857,0.8120876,0.00001847585,0.00008761814,0.000002197176,0.0005297209,0.1480621,0.00009191098,0.03727976,0.001119162,0.000173975],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1388491,0.0008975344,0.8587602,0.0008630232,0.0001415714,0.000164724,0.0002825703,0.00000584738,0.00003540397],"genre_scores_gemma":[0.6511406,0.000009187547,0.3477647,0.0007626244,0.00003285795,0.00002365651,0.0002219827,0.000002436334,0.00004188575],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6440149,"threshold_uncertainty_score":0.3726138,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4281892973","doi":"10.1038/s43588-022-00253-w","title":"AI-powered aptamer generation","year":2022,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Advanced biosensing and bioanalysis techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria; University of Alberta","funders":"","keywords":"Aptamer; Identification (biology); Computer science; Task (project management); Artificial intelligence; Computational biology; Engineering; Biology; Systems engineering; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.007334456239723464,"gpt":0.302409602229916,"spread":0.2950751459901926,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002886022,0.00006562725,0.0000496272,0.00007460337,0.0004908943,0.00003001526,0.0002083245,0.00004666073,0.000008786408],"category_scores_gemma":[0.00007126915,0.00006108981,0.0000393367,0.0004363244,0.0001561414,0.00000610032,0.0001630888,0.00017815,0.000001175527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003973999,"about_ca_system_score_gemma":0.0001409458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001748633,"about_ca_topic_score_gemma":0.000002601984,"domain_scores_codex":[0.9990225,0.00003027372,0.00009009624,0.0003215416,0.0004089681,0.0001265617],"domain_scores_gemma":[0.9996006,0.000006498552,0.0000497457,0.0001282307,0.0001763266,0.00003860635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001300555,0.00003950082,0.0002445285,6.641826e-7,0.00000720683,0.000001670126,0.00001074935,0.0106306,0.978263,0.002380412,0.004044299,0.004364389],"study_design_scores_gemma":[0.0004322081,0.000470817,0.005432037,0.000003502271,0.00001977334,0.0001248472,0.00005931109,0.06948353,0.7859951,0.006631162,0.1307575,0.0005901899],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9249079,0.000626682,0.06802076,0.004262212,0.0006095821,0.0002236362,0.00005570994,0.00008576692,0.001207773],"genre_scores_gemma":[0.980987,0.000004217263,0.01526521,0.003323678,0.0001413859,0.000006411207,0.0001828523,0.000004399274,0.0000848967],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1922679,"threshold_uncertainty_score":0.3775612,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405248633","doi":"10.1038/s43588-024-00735-z","title":"A simulated annealing algorithm for randomizing weighted networks","year":2024,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Canada Research Chairs; Government of Canada; Natural Sciences and Engineering Research Council of Canada; Fondation Brain Canada; Michael J. Fox Foundation for Parkinson's Research","keywords":"Simulated annealing; Algorithm; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.005995640519837306,"gpt":0.3093278762039367,"spread":0.3033322356840994,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006238287,0.000121538,0.0001575078,0.0001875242,0.0003515031,0.0003021412,0.0002671365,0.00005313404,0.00005155264],"category_scores_gemma":[0.00001434496,0.0001048562,0.0001370302,0.001423257,0.0001151058,0.0002244216,0.00006287083,0.0003043673,0.000003381839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005075916,"about_ca_system_score_gemma":0.0001393013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001228907,"about_ca_topic_score_gemma":5.037474e-7,"domain_scores_codex":[0.9987963,0.00002077206,0.0002005705,0.0003948984,0.0003152663,0.0002721623],"domain_scores_gemma":[0.9987599,0.000733921,0.00004942925,0.00009775707,0.0002882518,0.00007070911],"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":[0.00001382951,0.00002068233,0.000165028,0.000004714799,0.00006574588,0.000001667681,0.00005464865,0.5870686,0.00007878616,0.07448095,0.001074261,0.3369711],"study_design_scores_gemma":[0.0003327799,0.000009897609,0.0001018199,0.00004107855,0.00002317281,8.159973e-7,0.000005944594,0.9308909,0.0001095592,0.06629729,0.002066069,0.0001207455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005392286,0.0007075544,0.9925036,0.0001730722,0.0002987901,0.0002691619,0.00001625799,0.000187613,0.0004516246],"genre_scores_gemma":[0.8820766,8.105874e-7,0.1171153,0.00007999971,0.0005775642,0.00001449984,0.00009735792,0.00001043025,0.0000273883],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8766843,"threshold_uncertainty_score":0.4275913,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4417152112","doi":"10.1038/s43588-025-00906-6","title":"SciSciGPT: advancing human–AI collaboration in the science of science","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kellogg's (Canada)","funders":"Northwestern University; National Science Foundation","keywords":"Transparency (behavior); Testbed; Domain (mathematical analysis); Design science; Design science research; Maturity (psychological); Scope (computer science)","retraction":null,"screen_n_in":null,"score":{"opus":0.031999207090962,"gpt":0.4601782248313903,"spread":0.4281790177404283,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.0496879,0.000142611,0.0002042599,0.00378722,0.002919954,0.002226219,0.007754151,0.00004955969,0.0000211656],"category_scores_gemma":[0.0202615,0.00009450134,0.00004472416,0.05712195,0.01066203,0.002723872,0.001341695,0.0004019684,0.00001931168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000360898,"about_ca_system_score_gemma":0.004147124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003517391,"about_ca_topic_score_gemma":0.00007166208,"domain_scores_codex":[0.988559,0.0001230902,0.0007901266,0.001489952,0.008431337,0.0006064663],"domain_scores_gemma":[0.9928051,0.00167727,0.0003357277,0.00123994,0.003827112,0.0001147993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001165299,0.0001666296,0.006032695,0.000008737332,0.000001680067,0.000003894073,0.001838511,0.16556,0.02322336,0.7807196,0.005238998,0.01719424],"study_design_scores_gemma":[0.0004492787,0.00006590744,0.3216568,0.0001110038,0.000006735648,0.000006462573,0.003788105,0.2797708,0.006181876,0.3839359,0.003775068,0.0002521018],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.936698,0.0001504298,0.02998822,0.009416089,0.00314872,0.0005580377,0.00001434994,0.00004148418,0.01998473],"genre_scores_gemma":[0.9908953,5.964152e-7,0.007810589,0.001130384,0.00003181058,0.000006027484,0.000002425578,0.000002035377,0.0001208196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3967837,"threshold_uncertainty_score":0.9988096,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4417112906","doi":"10.1038/s43588-025-00917-3","title":"Gradient-based optimization of complex nanoparticle heterostructures enabled by deep learning on heterogeneous graphs","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"Lawrence Berkeley National Laboratory","keywords":"Leverage (statistics); Deep learning; Artificial neural network; Deep neural networks; Inverse problem; Graph; Nanosensor; Nonlinear system","retraction":null,"screen_n_in":null,"score":{"opus":0.005558610148396685,"gpt":0.2685541761931333,"spread":0.2629955660447366,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009933561,0.000199982,0.0002373419,0.0003223555,0.0006973908,0.0002383707,0.0008599039,0.0001053666,0.0003084846],"category_scores_gemma":[0.0008827276,0.000175256,0.00005780972,0.001391739,0.0008952111,0.0002380317,0.000135016,0.0002702452,0.0000138152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00010834,"about_ca_system_score_gemma":0.000171818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002485897,"about_ca_topic_score_gemma":0.000003380593,"domain_scores_codex":[0.9972494,0.0002127625,0.0003963509,0.0006674482,0.0010437,0.0004303866],"domain_scores_gemma":[0.9985589,0.0004022063,0.0002807892,0.0002535583,0.0003970555,0.0001075022],"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":[0.00003250003,0.00003522972,0.0006587983,0.00001380736,0.000001343364,0.000001032113,0.00003710772,0.5883095,0.4089349,0.00174889,0.00004252826,0.0001844277],"study_design_scores_gemma":[0.0003515613,0.0001374464,0.004724107,0.00003590014,0.000004893118,0.000004444721,0.000009379166,0.6965666,0.2958072,0.002115763,0.00009210566,0.0001505462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9303284,0.00009186111,0.0679867,0.0002945169,0.0006416702,0.0002209205,0.0000187597,0.000123151,0.0002940532],"genre_scores_gemma":[0.9614936,0.00000114058,0.03762876,0.0007914329,0.00001334207,0.00001023676,0.00003129519,0.00000924636,0.00002097543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1131277,"threshold_uncertainty_score":0.7146731,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4390274368","doi":"10.1038/s43588-023-00580-6","title":"Dendritic excitability controls overdispersion","year":2023,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"General Dynamics (Canada); University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interval (graph theory); Attractor; Neuronal firing; Neuroscience; Dispersion (optics); Computer science; Function (biology); Cable theory; Statistical physics; Dendrite (mathematics); Range (aeronautics); Biological system; Physics; Mathematics; Psychology; Biology; Mathematical analysis; Electrophysiology; Materials science","retraction":null,"screen_n_in":null,"score":{"opus":0.01703851229776557,"gpt":0.2984889458744503,"spread":0.2814504335766847,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000479292,0.00008683861,0.00008260549,0.0001794192,0.000526636,0.0001193954,0.0003321603,0.00006502684,0.00003898269],"category_scores_gemma":[0.002166719,0.00007343459,0.0000477336,0.002012503,0.0003967098,0.0003932673,0.0001208904,0.0002696358,0.0002207069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009075618,"about_ca_system_score_gemma":0.0001098911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002646486,"about_ca_topic_score_gemma":0.000001584964,"domain_scores_codex":[0.9981326,0.00004647066,0.0001301344,0.0005163748,0.0008824056,0.0002919612],"domain_scores_gemma":[0.99871,0.0008862588,0.0000447798,0.0001355393,0.0001219025,0.0001015117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003481415,0.00006738916,0.001745548,0.00001412666,0.000001322639,0.00003307819,0.00007623987,0.04428248,0.6772885,0.2701491,0.0007377164,0.005569697],"study_design_scores_gemma":[0.0004314992,0.00007214429,0.3061085,0.00001433354,0.000003257287,0.00004023362,0.00001978464,0.533471,0.007971962,0.1503049,0.001340101,0.0002222478],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9925849,0.00001124046,0.00162311,0.002557643,0.001176344,0.0001815933,0.00001877855,0.0002023373,0.00164398],"genre_scores_gemma":[0.9977452,0.000002714693,0.0002641176,0.001790426,0.00007058923,0.000005881533,0.000007104317,0.000005140934,0.0001088824],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6693165,"threshold_uncertainty_score":0.4050512,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3164594474","doi":"10.1038/s43588-021-00075-2","title":"A dynamic metabolic map for diabetes","year":2021,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Pancreatic function and diabetes","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Queen's University; Government of Canada; U.S. Department of Health and Human Services","keywords":"Diabetes mellitus; Carbohydrate metabolism; Type 2 diabetes; Computer science; Medicine; Endocrinology","retraction":null,"screen_n_in":null,"score":{"opus":0.007742317669071546,"gpt":0.2987727463970558,"spread":0.2910304287279842,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002227158,0.00006808739,0.0001398315,0.00009387111,0.0001510218,0.00003847615,0.00007231152,0.00005982165,0.00008365988],"category_scores_gemma":[0.001071332,0.00005649441,0.00006193947,0.0005936895,0.0001515209,0.00009486474,0.00002754674,0.0001305077,0.0000269571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004075338,"about_ca_system_score_gemma":0.0005426354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.866414e-7,"about_ca_topic_score_gemma":4.494134e-7,"domain_scores_codex":[0.9990367,0.000009100537,0.0001033334,0.0002605136,0.000396721,0.0001936204],"domain_scores_gemma":[0.9988768,0.0002931973,0.00003146173,0.0001049892,0.0005780715,0.0001155535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001910395,0.001145451,0.1060694,0.0006248158,0.0003547794,0.0000507343,0.0004568309,0.01231519,0.4695074,0.3323103,0.02058546,0.05638852],"study_design_scores_gemma":[0.0023891,0.0001425833,0.5399898,0.0001084068,0.0001357456,0.00003824801,0.0000586651,0.3213415,0.03450231,0.03826692,0.06273473,0.0002920103],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9709415,0.004580541,0.009762106,0.01102014,0.001007244,0.0002869557,0.00003035034,0.00009018696,0.002280914],"genre_scores_gemma":[0.934852,0.000003433182,0.0595496,0.004924048,0.00006274761,0.00001646662,0.00006958572,0.000004979594,0.0005171158],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4350051,"threshold_uncertainty_score":0.2303775,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402758992","doi":"10.1038/s43588-024-00676-7","title":"Using labels to limit AI misuse in health","year":2024,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute","funders":"","keywords":"Limit (mathematics); Computer science; Artificial intelligence; Psychology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2200922754446732,"gpt":0.5638664346535956,"spread":0.3437741592089224,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007557676,0.00006054525,0.00009185394,0.0003893822,0.0001346874,0.00007020298,0.00009295357,0.00006407081,0.00003211627],"category_scores_gemma":[0.0004614712,0.0000537974,0.00001963085,0.002027322,0.00008102554,0.0001733527,0.00002343611,0.0003832447,0.00006892817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004969634,"about_ca_system_score_gemma":0.002424479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003619523,"about_ca_topic_score_gemma":0.00006601303,"domain_scores_codex":[0.9987597,0.00001955266,0.0002368823,0.0002949045,0.0004477717,0.0002411198],"domain_scores_gemma":[0.9992669,0.0001853939,0.00002054263,0.00008251062,0.0002411018,0.0002035814],"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":[0.0001290081,0.0004627582,0.04251779,0.001102686,0.00001680593,0.0001250425,0.01647846,0.2883725,0.009206387,0.1287254,0.008726849,0.5041364],"study_design_scores_gemma":[0.00008018541,0.0004409181,0.08153293,0.002367176,0.000009337958,0.0002006485,0.0006523275,0.8393806,0.005562653,0.04986289,0.01957254,0.0003377734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8836677,0.002021931,0.01668473,0.09534457,0.001550022,0.0004243916,0.00000397644,0.00006899952,0.00023369],"genre_scores_gemma":[0.9692906,0.000009376803,0.01891897,0.01151176,0.000211476,0.000004120963,0.000005717957,0.000005387141,0.00004256667],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5510081,"threshold_uncertainty_score":0.4300922,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7117725920","doi":"10.1038/s43588-025-00924-4","title":"MATTERIX: toward a digital twin for robotics-assisted chemistry laboratory automation","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto; Public Health Ontario","funders":"","keywords":"Workflow; Modular design; Virtual Laboratory; Rendering (computer graphics); Graphics; Scalability; Automation","retraction":null,"screen_n_in":null,"score":{"opus":0.006261251077759137,"gpt":0.294315736134926,"spread":0.2880544850571669,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000948252,0.0001776615,0.0001863953,0.0001447917,0.0005693397,0.0008923265,0.0009561711,0.00014206,0.0001593808],"category_scores_gemma":[0.001451225,0.0001643448,0.00004817234,0.001181831,0.0006141889,0.0007921091,0.0002280835,0.0002085432,0.00006899575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002364013,"about_ca_system_score_gemma":0.0007571057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000345069,"about_ca_topic_score_gemma":4.921519e-7,"domain_scores_codex":[0.9978037,0.00003668946,0.0003323215,0.0006571483,0.0007698965,0.0004001967],"domain_scores_gemma":[0.998478,0.000310813,0.0001845943,0.0002556381,0.000667388,0.000103577],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003394209,0.0000556166,0.0006533751,0.0001462684,0.000002839283,0.000002043731,0.0001068902,0.1000386,0.8937348,0.004098617,0.0006738402,0.0004532555],"study_design_scores_gemma":[0.001688831,0.0000851112,0.2440091,0.0003023864,0.00002542815,0.00004860487,0.0001404779,0.4067374,0.316094,0.02676866,0.003095037,0.001005006],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8581731,0.00006406029,0.1344184,0.003880819,0.001492216,0.0003911537,0.0001703814,0.000345046,0.001064878],"genre_scores_gemma":[0.9313018,2.786346e-7,0.06772451,0.0005914071,0.00008826299,0.00003277044,0.00003615441,0.000008704698,0.0002160565],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5776408,"threshold_uncertainty_score":0.8604726,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415045887","doi":"10.1038/s43588-025-00884-9","title":"Transforming psychiatry with computational and brain-based methods","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Trinity College","funders":"","keywords":"Interpretability; Normative; Mental health; Foundation (evidence); Grounded theory; MEDLINE","retraction":null,"screen_n_in":null,"score":{"opus":0.01468727612404083,"gpt":0.3461333837988688,"spread":0.331446107674828,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007932408,0.0001642734,0.0001519831,0.0003830641,0.001006699,0.000133151,0.0002885856,0.00007481503,0.000009225231],"category_scores_gemma":[0.004194565,0.0001359553,0.00003593196,0.002020977,0.00110924,0.0003346896,0.00006390761,0.0003901134,0.000002848405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009165387,"about_ca_system_score_gemma":0.001054446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003565801,"about_ca_topic_score_gemma":0.00001052026,"domain_scores_codex":[0.9979612,0.0001081206,0.0001709501,0.0007628861,0.0007354029,0.0002614926],"domain_scores_gemma":[0.9886389,0.01084983,0.00006494998,0.0001146697,0.000253516,0.00007808273],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001165114,0.0001100434,0.004417099,0.00004950225,0.00001293751,0.000004106837,0.0001235113,0.2572479,0.007289752,0.7155004,0.001252655,0.01387551],"study_design_scores_gemma":[0.002113962,0.0002608045,0.1298193,0.0001740692,0.00002780491,0.00008444719,0.0001000457,0.4684342,0.01466412,0.3780344,0.005712549,0.0005743927],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09189714,0.0002297372,0.813397,0.08945587,0.0007672829,0.0003824341,0.00001751944,0.0001470683,0.003705924],"genre_scores_gemma":[0.7924801,5.266862e-7,0.181872,0.02555776,0.00002901038,0.00001481965,0.000002325274,0.000005793849,0.00003761412],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.700583,"threshold_uncertainty_score":0.7742818,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4300861812","doi":"10.1038/s43588-022-00320-2","title":"The role of ADM in brain function","year":2022,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Neuroscience and Neuropharmacology Research","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Brain function; Neuroscience; Neural activity; Information transmission; Brain activity and meditation; Transmission (telecommunications); Function (biology); Psychology; Physics; Biology; Computer science; Electroencephalography; Telecommunications; Cell biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01698892071527686,"gpt":0.3445687360609841,"spread":0.3275798153457073,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001185511,0.00005657135,0.00005794788,0.0002291381,0.00143689,0.00004229631,0.0009463528,0.00001951532,0.00004808533],"category_scores_gemma":[0.001420782,0.00004348338,0.00002488876,0.002938068,0.000900912,0.0002108872,0.0003936834,0.0006915363,0.000006738623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006490086,"about_ca_system_score_gemma":0.0003850172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000387903,"about_ca_topic_score_gemma":0.000002499522,"domain_scores_codex":[0.9976369,0.0002519156,0.0001484691,0.0003849049,0.001288467,0.0002893769],"domain_scores_gemma":[0.9980326,0.001664162,0.00007025193,0.0001169705,0.00006385937,0.00005218247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007064657,0.00007364777,0.001564028,8.385007e-7,2.087452e-7,0.000009423263,0.00007049821,0.01903303,0.9367431,0.0358018,0.00016029,0.00647244],"study_design_scores_gemma":[0.0007774297,0.0006392613,0.106381,0.000003968411,0.00000242792,0.0001261249,0.0002991408,0.1425566,0.6076794,0.1092404,0.03206713,0.0002271003],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9948468,0.0001065598,0.00003133167,0.003183039,0.0005843001,0.0001842296,0.00000725198,0.00001699006,0.001039493],"genre_scores_gemma":[0.9973602,0.000004762329,0.00001604469,0.002489384,0.00001777412,0.00002430345,2.240742e-7,0.000003436631,0.00008384429],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3290637,"threshold_uncertainty_score":0.9998631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413401677","doi":"10.1038/s43588-025-00853-2","title":"What’s so hard about RNA-targeting drug discovery?","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"RNA modifications and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Drug discovery; Computational biology; Drug; Computer science; Biology; Pharmacology; Bioinformatics","retraction":null,"screen_n_in":null,"score":{"opus":0.004718065492468867,"gpt":0.2872765304396582,"spread":0.2825584649471893,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002916221,0.00007882425,0.0000580316,0.00006340233,0.0003846086,0.0003899255,0.0003534415,0.00007243468,0.000007216062],"category_scores_gemma":[0.0001429124,0.00007031072,0.00004288128,0.0004008853,0.0002835229,0.00004632478,0.0001065737,0.0001401208,0.000005455298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003612122,"about_ca_system_score_gemma":0.0005296186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009155023,"about_ca_topic_score_gemma":0.000008253428,"domain_scores_codex":[0.9990662,0.00001656502,0.0001212411,0.0003754176,0.0002540203,0.0001665603],"domain_scores_gemma":[0.9994791,0.00002301945,0.00004993254,0.0001599789,0.0002473101,0.00004072515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000602011,0.0001454203,0.004636909,0.00003802502,0.0000515636,0.000002288803,0.0002332917,0.07359699,0.7265547,0.09186852,0.04377525,0.05903683],"study_design_scores_gemma":[0.001261764,0.0001024954,0.2855208,0.0002514399,0.00003563927,0.00001014724,0.000639913,0.02058507,0.2360567,0.02308156,0.4315012,0.0009532098],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9367617,0.011095,0.042377,0.004644113,0.00229457,0.0001806761,0.00001697102,0.00002144471,0.002608462],"genre_scores_gemma":[0.9917767,0.00009539445,0.003581414,0.001763424,0.0001339373,0.00001070992,0.00006019172,0.000003791037,0.002574455],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.490498,"threshold_uncertainty_score":0.376006,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408673029","doi":"10.1038/s43588-025-00774-0","title":"Quantifying associations between socio-spatial factors and cognitive development in the ABCD cohort","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Birth, Development, and Health","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"National Institute on Drug Abuse; National Institute of Mental Health; National Institute on Aging","keywords":"Cohort; Geography; Cognition; Psychology; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04359931459905438,"gpt":0.3806459830872018,"spread":0.3370466684881474,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001119126,0.00008825043,0.0001558479,0.0002055767,0.0006049732,0.0000513129,0.0001152842,0.0001087574,0.000004770512],"category_scores_gemma":[0.0005843178,0.00006090727,0.00001734048,0.0007695928,0.0001966285,0.00008765973,0.0000454187,0.00046121,0.000002814083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002254014,"about_ca_system_score_gemma":0.001800053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006561029,"about_ca_topic_score_gemma":0.000170106,"domain_scores_codex":[0.9986532,0.00004157646,0.0002167464,0.00025902,0.0006228319,0.0002066729],"domain_scores_gemma":[0.9987916,0.0007633007,0.00007195411,0.00004354809,0.0002698939,0.00005968063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000003745247,0.00002695653,0.9740325,0.00001308789,0.00001762336,0.000001255643,0.0019857,0.000005987924,0.00001065538,0.0209762,0.00005104747,0.002875244],"study_design_scores_gemma":[0.0003517872,0.00001236721,0.9935836,0.00007510112,0.00001763661,0.000001174264,0.0003339621,0.000208907,0.0000845964,0.005196057,0.00007143565,0.00006337131],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9896439,0.0001363049,0.004896966,0.003280851,0.0001336719,0.0003850345,0.00001283582,0.00001812359,0.001492346],"genre_scores_gemma":[0.9949824,0.00004923325,0.002860864,0.001956508,0.00003505186,0.00000910068,0.00009953054,0.000002529398,0.000004798907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01955111,"threshold_uncertainty_score":0.4653026,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416850705","doi":"10.1038/s43588-025-00923-5","title":"Identifying variants of molecules through database search of mass spectra","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Microbial Natural Products and Biosynthesis","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Centre of Excellence for Child and Youth Mental Health","funders":"National Institute of General Medical Sciences; U.S. Department of Health and Human Services; U.S. Department of Energy; National Institutes of Health; National Science Foundation","keywords":"PubChem; Identification (biology); Molecule; Mass spectrometry; Mass spectrum; Streptomyces; Database search engine","retraction":null,"screen_n_in":null,"score":{"opus":0.02321265847175873,"gpt":0.344988771703539,"spread":0.3217761132317802,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004465974,0.00006508791,0.0001513138,0.0001722479,0.0000808902,0.00001461533,0.0002250437,0.0000596052,0.0000468093],"category_scores_gemma":[0.0005204782,0.00004917083,0.00003958614,0.00128756,0.0003719977,0.0001528587,0.00008502474,0.0002413556,0.000002122742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003759586,"about_ca_system_score_gemma":0.0004221339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003123512,"about_ca_topic_score_gemma":0.000001296983,"domain_scores_codex":[0.9988536,0.00001910665,0.0001905048,0.000267053,0.0005337694,0.0001359411],"domain_scores_gemma":[0.9991106,0.0001285103,0.00006326691,0.00015882,0.0005072383,0.00003154201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004752209,0.00006257523,0.0004386864,0.0001645846,0.00001768024,0.000005616945,0.00006290162,0.000314502,0.952229,0.04517549,0.0002889418,0.001192489],"study_design_scores_gemma":[0.0003250199,0.00003782282,0.06525146,0.0003537438,0.00003095271,0.00001218229,0.00004646378,0.002841913,0.9226426,0.008268802,0.0001199598,0.00006909664],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.921913,0.002379719,0.06204928,0.006576145,0.0006295285,0.0004952651,0.0001150283,0.00003117049,0.005810903],"genre_scores_gemma":[0.9015169,0.00001742557,0.09807429,0.0002769448,0.00002982123,1.125853e-7,0.00001421957,0.000002151513,0.00006815894],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06481277,"threshold_uncertainty_score":0.2005128,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414249370","doi":"10.1038/s43588-025-00861-2","title":"On the compatibility of generative AI and generative linguistics","year":2025,"lang":"en","type":"review","venue":"Nature Computational Science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; HEC Montréal","funders":"","keywords":"Generative grammar; Cognitive linguistics; Applied linguistics; Computational linguistics; Language and Communication Technologies; Theoretical linguistics; Quantitative linguistics; Compatibility (geochemistry)","retraction":null,"screen_n_in":null,"score":{"opus":0.02464684558482763,"gpt":0.3833029036527605,"spread":0.3586560580679329,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001046426,0.0003025305,0.0006329192,0.0003202306,0.0004413009,0.0002781454,0.002118538,0.0002531092,0.000002291999],"category_scores_gemma":[0.005667737,0.0001760794,0.0001111413,0.002045117,0.0008260997,0.000130786,0.0007307693,0.001162016,0.00000146874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001532731,"about_ca_system_score_gemma":0.001752517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003912954,"about_ca_topic_score_gemma":0.000002229923,"domain_scores_codex":[0.9975289,0.0002356418,0.0003748134,0.0007842074,0.0008621825,0.0002143028],"domain_scores_gemma":[0.994753,0.002928482,0.0004024339,0.000513214,0.001337579,0.00006530996],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[6.920901e-7,0.00002011221,6.225245e-7,0.0006309887,0.00001032146,0.000001858347,0.00006625635,0.00009763833,7.574965e-7,0.7794797,0.0006576032,0.2190334],"study_design_scores_gemma":[0.0001141934,0.000154014,0.00001614611,0.00892576,0.00009220816,0.0000163251,0.000003785707,0.06478085,0.0003468268,0.8645957,0.06027398,0.0006802815],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.000001159539,0.7331946,0.2651888,0.0005171592,0.000349211,0.0004090933,0.0000318194,0.00006617049,0.000242031],"genre_scores_gemma":[0.003382884,0.283535,0.7102697,0.002501767,0.0001774982,0.00004569492,0.00002945695,0.00001178994,0.000046196],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.4496596,"threshold_uncertainty_score":0.718031,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3181323861","doi":"10.1038/s43588-021-00104-0","title":"Rapid protein model refinement by deep learning","year":2021,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Pontifical Institute of Mediaeval Studies; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Graph; Artificial neural network; Refining (metallurgy); Machine learning; Theoretical computer science; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.004223012420562871,"gpt":0.2483147148313146,"spread":0.2440917024107518,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001701186,0.00008107887,0.00005650587,0.00002317269,0.000206131,0.00004425438,0.0001888963,0.0001138766,0.00001362784],"category_scores_gemma":[0.0002207465,0.00007611899,0.00003068589,0.0002329527,0.0001180956,0.000006454313,0.000135898,0.000213658,0.000002450376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002306456,"about_ca_system_score_gemma":0.0002744364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.416692e-7,"about_ca_topic_score_gemma":0.000003420762,"domain_scores_codex":[0.9990192,0.00002078547,0.00009442468,0.0003534528,0.0003418184,0.0001703315],"domain_scores_gemma":[0.9994903,0.000007017018,0.00004441278,0.0001177692,0.0002766771,0.00006378946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001148231,0.0000220325,0.00006806474,0.000005646853,0.000006769064,0.000002621246,0.00001750778,0.1524916,0.8279095,0.004951743,0.0003964369,0.0141166],"study_design_scores_gemma":[0.0005470108,0.0001417627,0.001171113,0.00001695445,0.00000720043,0.00004075194,0.00002773712,0.5461127,0.4097331,0.01394616,0.02786303,0.0003924719],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5942554,0.004674759,0.3956335,0.001215594,0.0001498515,0.0002091381,0.00001872751,0.00002810239,0.003814935],"genre_scores_gemma":[0.9521011,0.00001548111,0.04648987,0.0007563916,0.00005350593,0.000008549357,0.000191359,0.000005465141,0.0003782971],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4181763,"threshold_uncertainty_score":0.3104042,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4417454615","doi":"10.1038/s43588-025-00928-0","title":"AI-guided molecular design with recipes included","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Generative Design; Generative grammar; Set (abstract data type)","retraction":null,"screen_n_in":null,"score":{"opus":0.007382473306322654,"gpt":0.3193867711825728,"spread":0.3120042978762502,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00256406,0.000199916,0.0002047463,0.0003246121,0.0007097936,0.0005135989,0.001377672,0.0001135313,0.000195707],"category_scores_gemma":[0.001226474,0.0001518663,0.00002890621,0.002123404,0.001071955,0.0005538739,0.0003186327,0.0003636226,0.00009204953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001617808,"about_ca_system_score_gemma":0.00111431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002818553,"about_ca_topic_score_gemma":0.000003102836,"domain_scores_codex":[0.9969016,0.0001977282,0.0002898644,0.000796489,0.001347883,0.0004663867],"domain_scores_gemma":[0.9982926,0.0004144399,0.0001439514,0.0003449453,0.0006832322,0.0001208099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003443804,0.00002772593,0.0003362162,0.00001137072,0.000002191408,0.00001268759,0.00007948309,0.478783,0.4833167,0.03624607,0.0008547395,0.0002954217],"study_design_scores_gemma":[0.0008654311,0.0001997951,0.02690101,0.0002078902,0.00001871891,0.00008532105,0.00003042094,0.2263152,0.6436004,0.09914122,0.001981947,0.0006526575],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3228688,0.0001034221,0.6678249,0.00546909,0.0007880347,0.0003267599,0.000005124524,0.0002023404,0.002411506],"genre_scores_gemma":[0.7494409,5.270415e-7,0.246611,0.00380934,0.00002737861,0.00001634419,0.000002940677,0.000006755593,0.00008483908],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4265721,"threshold_uncertainty_score":0.619293,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416466606","doi":"10.1038/s43588-025-00913-7","title":"Viability of using LLMs as models of human language processing","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Human language; Language model; Language technology; Universal Networking Language; On Language; Computational linguistics; Work (physics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02732870010255197,"gpt":0.3824924493057228,"spread":0.3551637492031708,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004129779,0.0000791971,0.0001423032,0.0001944816,0.0002098038,0.0000184754,0.0004511205,0.00007939043,0.000009930211],"category_scores_gemma":[0.0007864116,0.00006646609,0.0000410667,0.001068359,0.001012106,0.000233504,0.0001273754,0.0002128162,5.088988e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003010537,"about_ca_system_score_gemma":0.0003931704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000331261,"about_ca_topic_score_gemma":0.000002477729,"domain_scores_codex":[0.9988076,0.00005632134,0.0002325247,0.0003684283,0.0003808081,0.0001543008],"domain_scores_gemma":[0.999192,0.0002618323,0.0001496502,0.0001450431,0.0002214876,0.00003001133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000008229247,0.00006229111,0.0002940641,0.00004227023,7.771218e-7,0.000009893079,0.0006341716,0.013166,0.9722014,0.01218145,0.000002468537,0.00139699],"study_design_scores_gemma":[0.0002023883,0.00004241335,0.001427439,0.00007731348,0.000007727959,0.00003618575,0.0001294849,0.07236552,0.8701373,0.05547202,0.00000393533,0.00009823638],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953163,0.0001649288,0.00207064,0.0001001456,0.000116685,0.0001214364,0.000008448987,0.00002299437,0.002078387],"genre_scores_gemma":[0.9966521,3.581777e-7,0.002707345,0.0005971919,0.00001471962,8.048228e-7,0.000001393316,0.000002669497,0.00002347037],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1020641,"threshold_uncertainty_score":0.3729146,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388694106","doi":"10.1038/s43588-023-00553-9","title":"Accurately predicting molecular spectra with deep learning","year":2023,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Quantum chemistry; Spectral line; Identification (biology); Computer science; Chemistry; Computational chemistry; Biological system; Molecule; Physics; Organic chemistry; Quantum mechanics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01621159098828589,"gpt":0.3282560073648352,"spread":0.3120444163765493,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001477229,0.0001923081,0.0001529616,0.0005242542,0.0006363504,0.0005514711,0.001510567,0.000082017,0.00000758699],"category_scores_gemma":[0.0006413192,0.0001680334,0.0000540235,0.006417837,0.0002813106,0.001359584,0.0004992814,0.0006931011,0.00008856598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000135999,"about_ca_system_score_gemma":0.000568918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004338813,"about_ca_topic_score_gemma":0.000002035333,"domain_scores_codex":[0.9964259,0.0001312964,0.0002310357,0.0008319381,0.0018518,0.0005280027],"domain_scores_gemma":[0.9978334,0.001063509,0.0001422533,0.0002728601,0.00050717,0.0001807612],"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":[0.000004755032,0.00001362295,0.0009694679,0.000005202381,0.000007442855,0.00006247396,0.000308496,0.8724751,0.0006007459,0.1076091,0.00001671578,0.01792688],"study_design_scores_gemma":[0.0001979935,0.00008873909,0.05911462,0.00002142808,0.000003165366,0.00007615114,0.0000429042,0.9065902,0.0009549566,0.03239471,0.0002969122,0.0002182509],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.265811,0.00009517105,0.7306732,0.000873941,0.0003085581,0.0001717734,0.000001279976,0.0005647086,0.001500362],"genre_scores_gemma":[0.7829765,0.000002291627,0.2165881,0.0003188683,0.00005687483,0.00001533684,0.00001122251,0.00001058381,0.00002020831],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5171655,"threshold_uncertainty_score":0.6852201,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3185878616","doi":"10.1038/s43588-021-00103-1","title":"A versatile model for single-cell data analysis","year":2021,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Inference; Computer science; Visualization; Cluster analysis; Gene regulatory network; Data visualization; Data mining; Data science; Artificial intelligence; Gene; Biology; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.036703688733312,"gpt":0.3007246107746592,"spread":0.2640209220413473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002138218,0.00007764495,0.00008763118,0.0000577848,0.0001615239,0.00006532142,0.0004695696,0.0001029216,0.000006470384],"category_scores_gemma":[0.0002237846,0.000077204,0.00006854352,0.0005760527,0.0001166974,0.00001207707,0.0001458718,0.00008427471,0.000001192997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001784659,"about_ca_system_score_gemma":0.0004296146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002523859,"about_ca_topic_score_gemma":0.00003656168,"domain_scores_codex":[0.9989227,0.00001123063,0.0001100024,0.0005321756,0.0002590411,0.0001648726],"domain_scores_gemma":[0.9991004,0.00004019778,0.00004048686,0.0003471351,0.000406177,0.00006555974],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002555323,0.0001369332,0.0006997477,0.000009066181,0.00004867563,0.000001346981,0.00003988054,0.3543694,0.6426237,0.000519426,0.0006949559,0.0008313535],"study_design_scores_gemma":[0.0002952705,0.00003190525,0.0005118208,0.000002015414,0.00006952749,0.000003102187,0.00001044208,0.9352604,0.0614983,0.0007978452,0.001397621,0.0001217845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1679282,0.0005289689,0.8299949,0.0003008458,0.0001812927,0.00008722661,0.0002629716,0.0000101814,0.0007054812],"genre_scores_gemma":[0.9123305,0.000004679076,0.08545987,0.0005803694,0.00007428729,0.000002502437,0.001401744,0.000005438651,0.0001405979],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.744535,"threshold_uncertainty_score":0.3148288,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414162661","doi":"10.1038/s43588-025-00864-z","title":"Applying weighted Cox regression to genome-wide association studies of time-to-event phenotypes","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Biobank; Minor allele frequency; Proportional hazards model; Genetic association; Type I and type II errors; Regression; Phenotype; Null hypothesis; Allele; Regression analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.008313976985895824,"gpt":0.3189564122537243,"spread":0.3106424352678285,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008788222,0.00008708281,0.0001580438,0.0001380749,0.0001979506,0.00001148086,0.0002306034,0.0001323915,0.000007929372],"category_scores_gemma":[0.0043734,0.00007446586,0.0000411658,0.0006365658,0.00006079427,0.000003879021,0.0001985409,0.00009201004,0.00002263587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001407639,"about_ca_system_score_gemma":0.0002113185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003274955,"about_ca_topic_score_gemma":0.000004588838,"domain_scores_codex":[0.9989311,0.00006222259,0.0002237823,0.0003153708,0.0002771365,0.0001904054],"domain_scores_gemma":[0.9986016,0.0003706482,0.000141574,0.0001200149,0.0007082722,0.00005791675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000139055,0.0001962703,0.2071311,0.00005574317,0.0003322528,9.565732e-7,0.0005478648,0.2887145,0.3806386,0.001695666,0.1018214,0.01872667],"study_design_scores_gemma":[0.0004734995,0.0002433204,0.907226,0.0001011409,0.00003826259,8.483416e-7,0.0001491404,0.004892762,0.01660131,0.008211116,0.06174384,0.0003188061],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9580221,0.001130309,0.03165629,0.007361347,0.0003119577,0.0004802582,0.00001987239,0.00001266017,0.001005191],"genre_scores_gemma":[0.9752578,0.00001903637,0.01968366,0.003732231,0.00005609345,0.00004030206,0.00003990493,0.000003707537,0.001167336],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7000948,"threshold_uncertainty_score":0.5235684,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414777573","doi":"10.1038/s43588-025-00880-z","title":"Proteoform search from protein database with top-down mass spectra","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Bioinformatics Solutions (Canada)","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Deconvolution; Pipeline (software); Identification (biology); Graph; Basis (linear algebra); Search algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.006857039943264111,"gpt":0.3020115019358871,"spread":0.295154461992623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001715236,0.0001158578,0.00009065864,0.00008259397,0.0003584806,0.00009455022,0.0005654888,0.00009066236,0.0001330744],"category_scores_gemma":[0.00005981289,0.00009508074,0.00002133837,0.0008141014,0.0002215394,0.0002352259,0.0001256189,0.0005859591,0.000009196852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002664874,"about_ca_system_score_gemma":0.0004974719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005578245,"about_ca_topic_score_gemma":0.000007825148,"domain_scores_codex":[0.9986226,0.000004657185,0.0001351602,0.0004833368,0.000506593,0.0002476398],"domain_scores_gemma":[0.9992392,0.00007453133,0.00005377324,0.0003166539,0.0002414732,0.00007434063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006554802,0.00009098178,0.001602264,0.00004976849,0.00001251963,0.000007224503,0.00004296922,0.004195482,0.8026556,0.1851722,0.0001520023,0.005953408],"study_design_scores_gemma":[0.0002702405,0.00001413144,0.0006123536,0.0001371891,0.000004852862,0.000002894887,0.00002446772,0.01357355,0.8681682,0.1148912,0.002123502,0.0001774702],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2625386,0.00008354418,0.7218292,0.003133367,0.00001946777,0.000616262,0.000168912,0.0001843651,0.01142623],"genre_scores_gemma":[0.5673742,0.000001214917,0.4318853,0.0001314943,0.00003637717,0.0001292892,0.00007782203,0.000004769042,0.0003594763],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3048356,"threshold_uncertainty_score":0.387728,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220825386","doi":"10.1038/s43588-022-00219-y","title":"Bridge over troubled transcripts","year":2022,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Bridge (graph theory); Transcriptome; Computational biology; RNA; Biology; Genetics; Gene; Gene expression; Anatomy","retraction":null,"screen_n_in":null,"score":{"opus":0.01038962341712222,"gpt":0.2671934954825503,"spread":0.2568038720654281,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002602302,0.00008298577,0.00006406291,0.00005880555,0.0004621628,0.00003684251,0.0003819706,0.00005452349,0.00006280047],"category_scores_gemma":[0.00003393896,0.0000844364,0.000058422,0.0003559619,0.0001535219,0.00000722811,0.00007583072,0.0002414228,0.000002187924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003856133,"about_ca_system_score_gemma":0.0002470285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001367653,"about_ca_topic_score_gemma":0.000007642663,"domain_scores_codex":[0.9988469,0.00002889403,0.0001052403,0.0003414946,0.000486514,0.0001909922],"domain_scores_gemma":[0.999678,0.00001405452,0.000032699,0.0001188459,0.00008854997,0.0000679045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001365987,0.0001687099,0.005924852,0.000006038536,0.00001475501,0.000006286348,0.0001331331,0.04394823,0.9391139,0.005300429,0.002685497,0.00256162],"study_design_scores_gemma":[0.003859429,0.00100125,0.6882473,0.00001010501,0.00003059969,0.0001753003,0.00006079119,0.03227044,0.07816628,0.006242354,0.1888816,0.001054547],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9898842,0.0003783984,0.007459648,0.0003990291,0.0007057256,0.0001054942,0.00004032548,0.00001625858,0.0010109],"genre_scores_gemma":[0.9966632,0.000003125629,0.001222873,0.001767203,0.0001176876,0.000009804276,0.00009811441,0.000007807023,0.0001102507],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8609475,"threshold_uncertainty_score":0.3554629,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416592793","doi":"10.1038/s43588-025-00937-z","title":"Publisher Correction: On the compatibility of generative AI and generative linguistics","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; HEC Montréal","funders":"","keywords":"Generative grammar; Compatibility (geochemistry); Theoretical linguistics; Generative model","retraction":null,"screen_n_in":null,"score":{"opus":0.01299036692066472,"gpt":0.3446690089765777,"spread":0.331678642055913,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007178935,0.0000552419,0.00006917075,0.00004920957,0.001002197,0.000132533,0.0001906335,0.00006860154,0.00002404624],"category_scores_gemma":[0.004200511,0.00003422976,0.00002018817,0.0008861607,0.001065885,0.0001313795,0.0000405321,0.0002378468,0.000001291474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001108236,"about_ca_system_score_gemma":0.000455927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001956011,"about_ca_topic_score_gemma":0.0004466466,"domain_scores_codex":[0.9990014,0.0001229377,0.00009581722,0.000195996,0.0004744736,0.0001093547],"domain_scores_gemma":[0.9982344,0.0004213611,0.00005918163,0.00007018049,0.001178447,0.00003644539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000009231508,0.00003437551,0.002282833,0.000002438096,0.000006947376,3.024879e-7,0.004333121,0.003995595,0.00008212347,0.9461393,0.0400124,0.00310129],"study_design_scores_gemma":[0.0006138275,0.0001936745,0.3151535,0.0001433352,0.00004207382,0.000001471459,0.009362346,0.1145207,0.002201892,0.5012341,0.05606311,0.0004699284],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5207521,0.00163543,0.03213957,0.1058407,0.02095364,0.001503273,0.00002394339,0.0001530624,0.3169984],"genre_scores_gemma":[0.9952253,0.000003583036,0.001071137,0.002809471,0.0001685617,0.000003629053,0.000004111367,8.901353e-7,0.0007133026],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4744732,"threshold_uncertainty_score":0.7708193,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415208579","doi":"10.1038/s43588-025-00886-7","title":"ECloudGen: leveraging electron clouds as a latent variable to scale up structure-based molecular design","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Click Chemistry and Applications","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Key Research and Development Program of China; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Latent variable; Benchmark (surveying); Chemical space; Latent variable model; Generative grammar; Variable (mathematics); Scale (ratio); Generative model","retraction":null,"screen_n_in":null,"score":{"opus":0.007204081071840983,"gpt":0.2855321472125076,"spread":0.2783280661406666,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002092833,0.0001551814,0.0001187515,0.00007738407,0.0004193934,0.0001283213,0.0005920161,0.0001492173,0.000194321],"category_scores_gemma":[0.0002022324,0.0001592626,0.00004299639,0.001405354,0.0001229601,0.00006544917,0.00009675051,0.0004244029,0.00001443207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002588246,"about_ca_system_score_gemma":0.0009706516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001107425,"about_ca_topic_score_gemma":6.937265e-7,"domain_scores_codex":[0.9983828,0.00001170503,0.0001814283,0.0005613693,0.0005265324,0.0003361851],"domain_scores_gemma":[0.9990357,0.0001993419,0.00005687689,0.0002736023,0.0002911809,0.0001432862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001948577,0.0000294636,0.0000958906,0.00001543475,0.000007794601,0.000001135504,0.00002595301,0.2867077,0.7013027,0.01100046,0.000401913,0.0003921163],"study_design_scores_gemma":[0.0002573566,0.000008268351,0.0003040015,0.00004430315,0.00001593534,0.000006760625,0.000007388519,0.03605944,0.9236457,0.03680294,0.002672187,0.0001756859],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6624569,0.000146657,0.3282538,0.002728118,0.0001537833,0.0001787847,0.00002657262,0.0001190566,0.005936322],"genre_scores_gemma":[0.9571576,3.737562e-7,0.03998883,0.002304773,0.00004905138,0.00002714316,0.00004642849,0.000007674856,0.0004181324],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2947007,"threshold_uncertainty_score":0.6494541,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4417153685","doi":"10.1038/s43588-025-00909-3","title":"Decoding omics via representation learning","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"","keywords":"Autoencoder; Profiling (computer programming); Decoding methods; Representation (politics); Feature learning; Encoding (memory)","retraction":null,"screen_n_in":null,"score":{"opus":0.004835519410217555,"gpt":0.2874860803659123,"spread":0.2826505609556948,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002721238,0.00005561887,0.00004635126,0.00006555615,0.0002493526,0.00005651757,0.0001874143,0.00009759857,0.000003013939],"category_scores_gemma":[0.0001454052,0.0000540426,0.00002692737,0.0003426208,0.0001116766,0.000008251893,0.0001135325,0.0001732399,0.000003920834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002288937,"about_ca_system_score_gemma":0.0001375775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002326807,"about_ca_topic_score_gemma":0.000002686643,"domain_scores_codex":[0.9994105,0.00001139611,0.000115483,0.0001895632,0.0001446794,0.0001284423],"domain_scores_gemma":[0.9996548,0.00002906281,0.00005056972,0.00008838685,0.0001447735,0.00003246693],"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":[0.00004902383,0.00003403428,0.01232988,0.00001826377,0.00003303469,0.000001124196,0.0001320824,0.7011152,0.1186696,0.03545513,0.002760067,0.1294026],"study_design_scores_gemma":[0.0005310328,0.00006866978,0.03503218,0.00002490648,0.00001123236,0.0000167496,0.00008333848,0.8889964,0.02583398,0.03514414,0.01398383,0.0002735191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2709997,0.0003791978,0.7205679,0.0005627701,0.0005140338,0.0001117151,0.000001783374,0.00001643797,0.006846533],"genre_scores_gemma":[0.9833975,0.00001128539,0.01547593,0.0007994395,0.00007342824,0.000002208313,0.00005579,0.000002433849,0.0001819567],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7123979,"threshold_uncertainty_score":0.2203793,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410447861","doi":"10.1038/s43588-025-00806-9","title":"Computational challenges arising in algorithmic fairness and health equity with generative AI","year":2025,"lang":"en","type":"article","venue":"Nature Computational Science","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institute of Neurological Disorders and Stroke; Gordon and Betty Moore Foundation","keywords":"Generative grammar; Equity (law); Health equity; Computer science; Theoretical computer science; Artificial intelligence; Economics; Political science; Health care; Economic growth","retraction":null,"screen_n_in":null,"score":{"opus":0.05781304433646098,"gpt":0.4742315941502994,"spread":0.4164185498138384,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003005351,0.00009844958,0.0001580581,0.0002372027,0.001464052,0.0003457225,0.0002748547,0.0001395795,0.000003629692],"category_scores_gemma":[0.0004035633,0.00008905353,0.00001627816,0.00111028,0.001357968,0.0006426987,0.0001144218,0.0005810286,7.898975e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004463335,"about_ca_system_score_gemma":0.004029969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009275124,"about_ca_topic_score_gemma":0.004555711,"domain_scores_codex":[0.9980261,0.000140938,0.0001695174,0.0003661235,0.000952688,0.0003446677],"domain_scores_gemma":[0.9985759,0.000445404,0.00008372874,0.00005482985,0.0006994458,0.000140722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000586641,0.00004199343,0.001414807,0.0000138349,0.000005656353,0.000002434438,0.01062335,0.02507002,0.000002740907,0.9337444,0.00009611941,0.02897882],"study_design_scores_gemma":[0.0003988929,0.00005758163,0.2252444,0.0001322532,0.000002582331,0.000001575736,0.002627805,0.02506159,0.000006039988,0.745713,0.0005907519,0.0001634779],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.09758145,0.006289077,0.1063076,0.7526064,0.0008572063,0.0009979482,0.00002212199,0.0001341047,0.03520411],"genre_scores_gemma":[0.9775451,0.0001206819,0.01598271,0.006235586,0.00007575309,0.00000444841,0.000004916874,0.000003142597,0.00002760557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8799637,"threshold_uncertainty_score":0.9998359,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}