{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001803219,0.0007537435,0.0008511405,0.0009231595,0.0002899172,0.0008099508,0.0007462096,0.0005581338,0.001682412],"category_scores_gemma":[0.006762788,0.0002840564,0.001320754,0.0008946174,0.0005171325,0.0009680322,0.00121968,0.001164399,0.0005635029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005268912,"about_ca_system_score_gemma":0.0009339374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008554181,"about_ca_topic_score_gemma":0.007236332,"domain_scores_codex":[0.9994112,0.0002267931,0.00002587487,0.0001565433,0.0001167499,0.00006288886],"domain_scores_gemma":[0.9982212,0.0009016039,0.0003628095,0.0002240704,0.0001929577,0.00009723429],"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":[0.000264822,0.000144364,0.05174021,0.0001910726,0.0003934664,0.000302752,0.0001710283,0.7372397,0.007086969,0.04412769,0.004582752,0.1537552],"study_design_scores_gemma":[0.000005675869,0.00003612542,0.003886981,0.000009338893,0.00001863435,0.00003715689,0.00001177975,0.9869847,0.0002606704,0.007868101,0.0008667868,0.00001394602],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.123005,0.001636938,0.8707411,0.001147844,0.000128043,0.00005224647,0.0007991248,0.00107209,0.001417584],"genre_scores_gemma":[0.8841776,0.001098266,0.1105502,0.0001873686,0.0001942379,0.00008063336,0.0008695888,0.0001598082,0.002682169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008554181,"threshold_uncertainty_score":0.01700878,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002764097,0.0005373048,0.0008243619,0.001781616,0.003043227,0.003144048,0.001050929,0.002296784,0.009884185],"category_scores_gemma":[0.01305582,0.0003933987,0.0008559794,0.001333908,0.007311383,0.01019369,0.004001046,0.002711596,0.002594939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002564018,"about_ca_system_score_gemma":0.001444935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001989064,"about_ca_topic_score_gemma":0.001076584,"domain_scores_codex":[0.997905,0.0004449768,0.0001148621,0.0005505548,0.000615417,0.0003691592],"domain_scores_gemma":[0.995975,0.001826537,0.0002546371,0.0008208607,0.0007738815,0.0003491274],"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":[0.000008305549,0.000002612655,0.000135588,0.00001104732,0.00000172303,0.00001568339,0.00009055075,0.0003068105,0.00006078953,0.9948965,0.002326112,0.002144316],"study_design_scores_gemma":[0.000004005599,0.000005067668,0.00007225343,0.00001799239,0.000001908898,0.0000321981,0.00004042442,0.001049315,0.0001401045,0.9860216,0.01261083,0.000004318477],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1118635,0.007623158,0.1481273,0.04399627,0.002719235,0.0001069919,0.0008101111,0.0005187535,0.6842348],"genre_scores_gemma":[0.912355,0.003841075,0.02441526,0.005622592,0.001491485,0.000159182,0.0003384773,0.0001554086,0.05162149],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009884185,"threshold_uncertainty_score":0.03306586,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005607671,0.000610636,0.0003689472,0.0007990847,0.000269074,0.0008245203,0.000923346,0.0007029179,0.002699933],"category_scores_gemma":[0.001597004,0.0002725306,0.0006280635,0.0005982527,0.0003306599,0.0007770538,0.001141484,0.001015615,0.0006759629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007975089,"about_ca_system_score_gemma":0.0007208061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005412334,"about_ca_topic_score_gemma":0.008359556,"domain_scores_codex":[0.9997415,0.00004788178,0.00001473099,0.00008659263,0.0000703483,0.00003896701],"domain_scores_gemma":[0.999607,0.0001434481,0.00005105604,0.00007116227,0.00009790282,0.00002947593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002612948,0.0002506835,0.003301059,0.0001782775,0.000181006,0.0002267421,0.0001042432,0.2560934,0.02980346,0.01226539,0.01450773,0.6828268],"study_design_scores_gemma":[0.000003439397,0.00001516973,0.000321159,0.000007348177,0.0000100948,0.00002714721,0.000007181558,0.9878201,0.003939054,0.006740852,0.001102409,0.000005945652],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01773989,0.0008806597,0.9753925,0.0004650205,0.00005535824,0.00003918343,0.000397839,0.003548608,0.001480817],"genre_scores_gemma":[0.640963,0.0007368737,0.3505448,0.0005897834,0.0001038778,0.0001168172,0.001229011,0.0002540071,0.005461752],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005412334,"threshold_uncertainty_score":0.01076168,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.02274903,0.001181389,0.001023676,0.003402983,0.002752929,0.00989861,0.003441504,0.002171692,0.02466699],"category_scores_gemma":[0.09283005,0.0007975648,0.001539494,0.003001309,0.002576858,0.007271763,0.0152655,0.003402411,0.01282274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001467272,"about_ca_system_score_gemma":0.00739817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003924136,"about_ca_topic_score_gemma":0.001509347,"domain_scores_codex":[0.9786118,0.01166711,0.001257937,0.002402146,0.004974029,0.001087081],"domain_scores_gemma":[0.8802648,0.06818881,0.005454812,0.01863578,0.01324652,0.01420929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.000224355,0.001493007,0.00926047,0.0007782482,0.0000750395,0.001314183,0.05089786,0.00184004,0.010573,0.02915816,0.0408689,0.8535167],"study_design_scores_gemma":[0.0002228707,0.001114028,0.007690632,0.0009773141,0.0001184169,0.002516352,0.02150697,0.01006892,0.02846931,0.09980255,0.8271858,0.0003269253],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09723151,0.0008025207,0.8090308,0.006889183,0.001345866,0.001835623,0.0006989712,0.009382557,0.07278302],"genre_scores_gemma":[0.2636765,0.0006791514,0.6533841,0.001560864,0.0007733326,0.00184623,0.001258543,0.004107652,0.0727137],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9965585,"threshold_uncertainty_score":0.1203098,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00399115,0.001165143,0.000619013,0.000690501,0.001346581,0.003113877,0.002625009,0.002361393,0.008802343],"category_scores_gemma":[0.01269496,0.0008119974,0.0007187181,0.0003223326,0.001547396,0.005568914,0.004110402,0.003907207,0.005498706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001022314,"about_ca_system_score_gemma":0.002285246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003580789,"about_ca_topic_score_gemma":0.004994778,"domain_scores_codex":[0.9964552,0.00165547,0.000152724,0.0010968,0.0005014025,0.0001383951],"domain_scores_gemma":[0.9931838,0.003151797,0.0002311691,0.001792197,0.001238849,0.0004021531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001515032,0.003066036,0.03485499,0.001529586,0.0003277726,0.001022628,0.01362928,0.1540487,0.06939434,0.09301636,0.06735503,0.5602403],"study_design_scores_gemma":[0.0001065469,0.000481734,0.001507836,0.000121908,0.00007713266,0.0003109899,0.002124371,0.8461605,0.03276083,0.02306988,0.09318101,0.00009730778],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1096649,0.0003216069,0.8427629,0.002456077,0.0003702012,0.0009649509,0.001487866,0.02076188,0.02120954],"genre_scores_gemma":[0.3560911,0.0001647659,0.6183469,0.001015278,0.00005436779,0.0008770566,0.00402965,0.001108788,0.01831203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008802343,"threshold_uncertainty_score":0.02944678,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006013603,0.0006530449,0.0005108349,0.0009115434,0.0002990194,0.0008610151,0.001005034,0.0007807174,0.001136162],"category_scores_gemma":[0.001428446,0.0003262926,0.0007302974,0.0006485432,0.0006916324,0.00155737,0.0009791837,0.001713649,0.0003075134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009882395,"about_ca_system_score_gemma":0.0009195704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003533379,"about_ca_topic_score_gemma":0.00530266,"domain_scores_codex":[0.9998267,0.00004205897,0.000009633774,0.00004961088,0.00004854069,0.0000234575],"domain_scores_gemma":[0.999589,0.0002077758,0.00004445295,0.00005683082,0.00006815603,0.00003376334],"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":[0.0001529319,0.0002950985,0.005240217,0.0002006978,0.0001524496,0.0001524569,0.0001797612,0.5233296,0.02220479,0.0518042,0.005503135,0.3907846],"study_design_scores_gemma":[0.000002943876,0.00001609285,0.0001787118,0.000008402805,0.00000708448,0.00001299094,0.00000923838,0.9779163,0.001297039,0.01984526,0.0007017249,0.000004176982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0408644,0.001058609,0.9536008,0.001367055,0.00006315659,0.00003673248,0.0003650078,0.0007411158,0.001902986],"genre_scores_gemma":[0.6022662,0.002227944,0.3887365,0.0005654988,0.0001071439,0.000113654,0.001206153,0.0001264225,0.004650589],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003533379,"threshold_uncertainty_score":0.00717026,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}