{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":6,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":6,"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","author_layer_release":"2026-06-26"},"query_hash":"26bf4d3a9568","filters":{"venue":"Journal of Computing Data and Exploration"}},"results":[{"id":"W4414398320","doi":"10.33137/codex.v1i1.45420","title":"Multiscale Regression for Chronic Kidney Disease via Age-Curvature and Electrolytes","year":2025,"lang":"en","type":"article","venue":"Journal of Computing Data and Exploration","topic":"Liver Disease Diagnosis and Treatment","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Kidney disease; Logistic regression; Regression; Linear regression; Regression analysis; Nonlinear regression; Comorbidity; Disease","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.02960394360927631,"gpt":0.331967669213546,"spread":0.3023637256042697,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001465841,0.0000763396,0.0001667783,0.00006807863,0.0001035809,0.00004746349,0.00005060995,0.00002731596,0.00000147628],"category_scores_gemma":[0.0001337665,0.00005153477,0.000031829,0.00005395858,0.00002002511,0.0002923904,0.0000543766,0.00007233596,2.378649e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003131173,"about_ca_system_score_gemma":0.0001343412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001849149,"about_ca_topic_score_gemma":0.000001346764,"domain_scores_codex":[0.9994816,0.00002179047,0.0001909985,0.0001306152,0.00009276362,0.00008228444],"domain_scores_gemma":[0.9994012,0.00008126615,0.0001288348,0.0001442429,0.00008521476,0.0001592637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005109593,0.002122378,0.1542651,0.003014647,0.001575135,0.0003426367,0.001836192,0.000115506,0.0190425,0.0009405002,0.1706575,0.6409784],"study_design_scores_gemma":[0.02614353,0.00304616,0.5507022,0.01034507,0.005414406,0.000106779,0.0003387297,0.3217531,0.005698288,0.004874828,0.07107884,0.0004980646],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9119821,0.01775615,0.05404839,0.01502731,0.0003857111,0.0006419211,0.0001161361,0.00002253602,0.00001968771],"genre_scores_gemma":[0.9956164,0.0009976085,0.002176003,0.0003986677,0.0003072277,0.000002818049,0.0004678689,0.000005245938,0.00002810712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6404803,"threshold_uncertainty_score":0.2101527,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414398250","doi":"10.33137/codex.v1i1.45640","title":"Goldbach’s Conjecture","year":2025,"lang":"en","type":"article","venue":"Journal of Computing Data and Exploration","topic":"Limits and Structures in Graph Theory","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Goldbach's conjecture; Riemann hypothesis; Conjecture; Number theory; State (computer science)","authors":[{"name":"Mariana Vazquez Coello","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08057890878785307,"gpt":0.3694907822998896,"spread":0.2889118735120366,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006420593,0.00006105401,0.0001494926,0.00009047703,0.0001371831,0.00005192281,0.0002276589,0.00004096112,0.000003509077],"category_scores_gemma":[0.0003230181,0.00004362059,0.00002289935,0.00008693551,0.00002980418,0.0003308679,0.000180212,0.0001444599,2.095961e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007716567,"about_ca_system_score_gemma":0.00002918163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.888996e-7,"about_ca_topic_score_gemma":0.000001117365,"domain_scores_codex":[0.9994034,0.00005731053,0.0002939218,0.00007854233,0.0001014988,0.00006530225],"domain_scores_gemma":[0.9992115,0.0002445458,0.0002212739,0.0002257591,0.0000738388,0.00002309013],"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":[0.00008729605,0.0000582382,0.001280515,0.0001868586,0.0001894191,0.00001568266,0.004728355,0.000124455,0.0003553274,0.8547352,0.06063569,0.07760295],"study_design_scores_gemma":[0.0005411609,0.00006737394,0.0005513517,0.0001957396,0.00008581361,0.00005986865,0.0007346916,0.006098086,0.0002368818,0.9785253,0.01282106,0.00008264655],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6461997,0.000619798,0.3496791,0.001271736,0.001140489,0.00007748754,0.000009482837,0.00002019351,0.0009820168],"genre_scores_gemma":[0.9860722,0.00006400952,0.01345696,0.0001443488,0.0002194229,6.679169e-8,0.000007771163,0.000003835949,0.00003143081],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3398724,"threshold_uncertainty_score":0.1778796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414398164","doi":"10.33137/codex.v1i1.45681","title":"Multi-Modal Deep Learning for Retinal Analysis","year":2025,"lang":"en","type":"article","venue":"Journal of Computing Data and Exploration","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Deep learning; Retinal; Scalability; Deep neural networks; Pattern recognition (psychology)","authors":[{"name":"Saadullah Shahzad","is_ca":true},{"name":"Inaam Azeezur-Rahman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05460751979904619,"gpt":0.3728975629768393,"spread":0.3182900431777931,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009008045,0.00006899549,0.0003063997,0.0003803911,0.0001393352,0.00007473799,0.00009910917,0.00002875087,0.000002211566],"category_scores_gemma":[0.0005128769,0.00005556856,0.0001087578,0.000439978,0.00002415122,0.0002742963,0.00005308453,0.0001708334,5.095918e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001681766,"about_ca_system_score_gemma":0.00003981613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006631871,"about_ca_topic_score_gemma":0.000003223396,"domain_scores_codex":[0.9992008,0.00005135744,0.0003817318,0.0001398196,0.0001338026,0.00009254152],"domain_scores_gemma":[0.9991044,0.0001196639,0.0002810338,0.0001569413,0.0002877828,0.00005016672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00144191,0.0005288989,0.4670483,0.0006084087,0.006796299,0.00007467715,0.003906697,0.04610444,0.01661695,0.0002454554,0.004819172,0.4518088],"study_design_scores_gemma":[0.0008831858,0.0001332431,0.01752812,0.0001497503,0.002692099,0.00002390409,0.001042134,0.9746975,0.000136775,0.00005973532,0.002599838,0.00005375353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2017883,0.0004422507,0.7960993,0.001526994,0.00006130193,0.00004078142,0.000001412911,0.00000904427,0.00003056983],"genre_scores_gemma":[0.9420685,0.0001065195,0.05726971,0.0001030291,0.0001771079,2.878856e-7,0.0001447636,0.000004078381,0.0001260305],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.928593,"threshold_uncertainty_score":0.226602,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414398246","doi":"10.33137/codex.v1i1.45881","title":"Student-Faculty Co-Creation of Open Educational Resources for Learning Applied Statistics with Open Source Software Tools","year":2025,"lang":"en","type":"article","venue":"Journal of Computing Data and Exploration","topic":"Open Education and E-Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"University of Toronto Mississauga; University of Toronto; World Health Organization","keywords":"Process (computing); Context (archaeology); Open educational resources; Open source; Open source software; Software; Statistics education; Open-source software development","authors":[{"name":"Nurlana Alili","is_ca":true},{"name":"Xi Su","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07388444604717574,"gpt":0.4081068845539801,"spread":0.3342224385068043,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001426945,0.00009679644,0.0002406882,0.0001365133,0.000408658,0.001920144,0.001865669,0.0000303353,0.000005712191],"category_scores_gemma":[0.0004351814,0.00008287137,0.00001289412,0.0002518903,0.00003462545,0.002674868,0.0009014226,0.0001674633,0.000001233002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003374989,"about_ca_system_score_gemma":0.0004075129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002005795,"about_ca_topic_score_gemma":0.000007908922,"domain_scores_codex":[0.9988199,0.0001092003,0.0004782816,0.000230892,0.000250872,0.0001108459],"domain_scores_gemma":[0.9979232,0.0005208447,0.0008040115,0.0002490464,0.0004498992,0.0000530099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006477717,0.0007683077,0.04690111,0.0003161124,0.0003902496,0.000001303363,0.04526038,0.06849164,0.0007194936,0.1166725,0.05563158,0.6641996],"study_design_scores_gemma":[0.01233052,0.002621633,0.1816491,0.002473102,0.000429406,0.00008691628,0.1083836,0.3080404,0.001493043,0.01538215,0.3658005,0.00130956],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03011926,0.0000253305,0.9672216,0.001110274,0.0001339032,0.0003793407,0.00001826863,0.00001110347,0.0009809487],"genre_scores_gemma":[0.6069192,0.00001623066,0.3919699,0.0001277373,0.0001043456,0.000006933081,0.000485623,0.000007983243,0.0003619992],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.66289,"threshold_uncertainty_score":0.9991159,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414398162","doi":"10.33137/codex.v1i1.45679","title":"Building an Emphatic AI Coach & Agent","year":2025,"lang":"en","type":"article","venue":"Journal of Computing Data and Exploration","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Pipeline (software); Ask price; Conversation; Applications of artificial intelligence; Chatbot","authors":[{"name":"Dev Vora","is_ca":true},{"name":"Dev Shah","is_ca":true},{"name":"Tanish Roy","is_ca":true},{"name":"Mehtab Cheema","is_ca":true},{"name":"Saadullah Shahzad","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07640635246494491,"gpt":0.3777183333456353,"spread":0.3013119808806904,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001121408,0.00006465872,0.0001129081,0.0001429499,0.00009906819,0.0003737152,0.0006627895,0.00002780171,5.786839e-7],"category_scores_gemma":[0.0002152776,0.0000571314,0.00001455536,0.0002012414,0.000008785708,0.003110952,0.0002941886,0.0001351468,6.751994e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001577063,"about_ca_system_score_gemma":0.00004899898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005792549,"about_ca_topic_score_gemma":0.000001454691,"domain_scores_codex":[0.999303,0.00006981286,0.0002696496,0.0001340914,0.0001409097,0.00008253527],"domain_scores_gemma":[0.9991013,0.0001734268,0.0001948598,0.0003894177,0.00009798237,0.00004299103],"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":[0.00003509326,0.0002116118,0.001961338,0.0001562682,0.0001212533,0.00003342569,0.003601467,0.01746034,0.002707936,0.07634747,0.02578237,0.8715814],"study_design_scores_gemma":[0.0002922581,0.0001513151,0.0008869668,0.0002603609,0.0000347525,0.0001001643,0.00006163598,0.8879797,0.0004130049,0.01775776,0.09190615,0.0001558637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02764221,0.0002496405,0.970025,0.001481547,0.000478708,0.00003583049,9.671724e-7,0.00007140971,0.00001465078],"genre_scores_gemma":[0.4980497,0.00006898757,0.5015548,0.0002152466,0.00009739873,2.064611e-7,0.000007689316,0.000002466741,0.000003417303],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8714256,"threshold_uncertainty_score":0.3603744,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414398266","doi":"10.33137/codex.v1i1.45680","title":"Predicting Protein Functions: A Deep Learning Approach to Unraveling Biological Complexity","year":2025,"lang":"en","type":"article","venue":"Journal of Computing Data and Exploration","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Deep learning; Protein sequencing; Field (mathematics); Sequence (biology); Feature (linguistics); Annotation; Biological data; Genomics","authors":[{"name":"Uyiosa Iyekekpolor","is_ca":true},{"name":"A. Shahul Hameed","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1447900144032077,"gpt":0.3506819999506972,"spread":0.2058919855474894,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002480333,0.0001147449,0.0002219099,0.000277263,0.0003425254,0.0003592638,0.0007364674,0.00004541648,4.980424e-7],"category_scores_gemma":[0.001080305,0.00009914643,0.00003549476,0.0006210876,0.00003632299,0.001336771,0.0009315835,0.0003234291,0.000001938801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004349397,"about_ca_system_score_gemma":0.0001023372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000654003,"about_ca_topic_score_gemma":0.000001257382,"domain_scores_codex":[0.9982887,0.0004121607,0.0005488292,0.0003247537,0.0002651007,0.000160459],"domain_scores_gemma":[0.9987256,0.0003382168,0.0003201012,0.000282366,0.0002550003,0.00007870166],"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":[0.00007685901,0.0002001427,0.003246765,0.00007526106,0.00008990205,0.000005554139,0.003342279,0.6702771,0.001240796,0.04218109,0.0002615094,0.2790027],"study_design_scores_gemma":[0.0002472943,0.0001153187,0.003296048,0.0001400844,0.000009354586,0.00003168245,0.0005995761,0.9858895,0.00006077554,0.008686607,0.0008298773,0.00009391631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1814966,0.0001308365,0.8170342,0.0006785901,0.0002602141,0.0001445036,0.000001668191,0.00004547129,0.0002078667],"genre_scores_gemma":[0.6182526,0.000006211607,0.3814693,0.00009519704,0.0001432732,0.000001488399,0.00002221301,0.000002873937,0.000006795188],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.436756,"threshold_uncertainty_score":0.4043074,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}