{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":7,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":7,"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":"73d85cae4c8a","filters":{"venue":"The Open Bioinformatics Journal"}},"results":[{"id":"W2159289309","doi":"10.2174/1875036200802010037","title":"Sequence-Only Based Prediction of β -Turn Location and Type Using Collocation of Amino Acid Pairs","year":2008,"lang":"en","type":"article","venue":"The Open Bioinformatics Journal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Sequence (biology); BETA (programming language); Turn (biochemistry); Type (biology); Computer science; Collocation (remote sensing); Threading (protein sequence); Algorithm; Amino acid; Peptide sequence; Protein sequencing; Protein structure prediction; Artificial intelligence; Pattern recognition (psychology); Mathematics; Protein structure; Machine learning; Chemistry; Biology; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.04552403034645246,"gpt":0.2922865010885254,"spread":0.246762470742073,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007606205,0.0001060971,0.0001509494,0.0000679028,0.0002229562,0.00004212837,0.0003449944,0.00009050099,0.00001216504],"category_scores_gemma":[0.0002327054,0.00007664999,0.00003495948,0.0001948847,0.0001990798,0.00004970521,0.00012537,0.000148664,0.000001424663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002351295,"about_ca_system_score_gemma":0.0004226875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002013535,"about_ca_topic_score_gemma":0.00000359583,"domain_scores_codex":[0.998951,0.00006775979,0.0005878421,0.00005515258,0.000217484,0.0001207707],"domain_scores_gemma":[0.9985234,0.00001901465,0.0007414688,0.0002523717,0.0004123562,0.00005140232],"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":[0.001781659,0.0004589138,0.1575537,0.001811106,0.000755964,0.00000493374,0.01596022,0.09379302,0.6665422,0.001065876,0.007306139,0.05296621],"study_design_scores_gemma":[0.002006768,0.001376026,0.02509,0.0003338683,0.0001222506,0.00194593,0.001532531,0.8190864,0.146173,0.00009074655,0.001950403,0.0002920833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9436572,0.0001215226,0.05410935,0.00009410425,0.0001430028,0.0003425181,0.00002336267,0.000004690809,0.001504275],"genre_scores_gemma":[0.9647004,0.0002202457,0.03480898,0.0001004506,0.00004744502,0.000001288691,0.00005831234,0.000008871005,0.00005400772],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7252933,"threshold_uncertainty_score":0.3125696,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2913430916","doi":"10.2174/1875036201912010030","title":"A Simple Genetic Algorithm for Optimizing Multiple Sequence Alignment on the Spread of the SARS Epidemic","year":2019,"lang":"en","type":"article","venue":"The Open Bioinformatics Journal","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Direktorat Riset dan Pengabdian Masyarakat","keywords":"Phylogenetic tree; Phylogenetic network; Mutation; Multiple sequence alignment; Tree (set theory); Sequence (biology); Algorithm; Computer science; Sequence alignment; Biology; Genetics; Mathematics; Gene; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.02758131972788786,"gpt":0.2994065380552482,"spread":0.2718252183273603,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001821922,0.0002170297,0.000233905,0.0000302772,0.000455869,0.0001976208,0.002196292,0.0001003179,0.00004080846],"category_scores_gemma":[0.0004011369,0.0001008866,0.0002115072,0.0001113171,0.0001492564,0.00002517987,0.0007179835,0.0003709081,0.00002739798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000433082,"about_ca_system_score_gemma":0.0001532188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002161764,"about_ca_topic_score_gemma":0.000004016507,"domain_scores_codex":[0.9982669,0.0001551456,0.0007615658,0.0001120318,0.0003435106,0.00036085],"domain_scores_gemma":[0.9977651,0.0002551334,0.0008858075,0.0008966184,0.0001341768,0.00006320191],"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":[0.001072024,0.0005047457,0.01439137,0.0007361125,0.002275669,0.00000443771,0.0138041,0.376017,0.1585909,0.004371305,0.1178754,0.310357],"study_design_scores_gemma":[0.001681997,0.0007332587,0.00104934,0.0001921507,0.00007776687,0.0003561306,0.001677103,0.9161945,0.04258357,0.0008443668,0.03424967,0.0003601708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7511026,0.000231474,0.2224615,0.004801227,0.001404082,0.007248616,0.0003048014,0.00002139309,0.01242432],"genre_scores_gemma":[0.7010416,0.0003558127,0.2907669,0.006142331,0.0003068319,0.00009239516,0.00006183298,0.00007100229,0.001161328],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5401775,"threshold_uncertainty_score":0.4114037,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162193618","doi":"10.2174/1875036200802010080","title":"Modeling Cooperative Gene Regulation Using Fast Orthogonal Search","year":2008,"lang":"en","type":"article","venue":"The Open Bioinformatics Journal","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Lawrence Berkeley National Laboratory","keywords":"Motif (music); Saccharomyces cerevisiae; Computer science; Computational biology; Transcription factor; Gene; Gene regulatory network; Biology; Gene expression; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.04184068761405676,"gpt":0.2821583290921968,"spread":0.2403176414781401,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006024635,0.000137313,0.0001351634,0.00003815603,0.0009185935,0.0002332622,0.0006036548,0.00008082409,0.00003554224],"category_scores_gemma":[0.00002225027,0.00009625642,0.00007021299,0.00009150241,0.00008641116,0.00003215484,0.0004048951,0.0002108045,0.00001245119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003924072,"about_ca_system_score_gemma":0.0003350198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001245857,"about_ca_topic_score_gemma":0.000007727573,"domain_scores_codex":[0.998968,0.00006171872,0.0004142085,0.00009618909,0.0002143408,0.0002455525],"domain_scores_gemma":[0.9992451,0.000006111962,0.0001373495,0.0002685661,0.0002499843,0.00009286268],"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":[0.00009167837,0.00003728462,0.0002166075,0.000008633969,0.0001110281,0.00000524297,0.001519782,0.8939167,0.102066,0.0002627033,0.0003117086,0.001452616],"study_design_scores_gemma":[0.000498647,0.00009520902,0.0001434984,0.00001427246,0.00001416359,0.002051901,0.0005963979,0.9881515,0.007958773,0.0001141126,0.0002033129,0.0001582496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8396695,0.00007193952,0.1583192,0.00007355298,0.00009080705,0.0001883283,0.00001331339,0.000002588986,0.001570821],"genre_scores_gemma":[0.9573104,0.0003100572,0.04155969,0.0001983691,0.000223291,0.000002210934,0.00007038055,0.00001894894,0.0003066957],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1176409,"threshold_uncertainty_score":0.7065172,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3206292757","doi":"10.2174/1875036202114010063","title":"Unsupervised Clustering in Epidemiological Factor Analysis","year":2021,"lang":"en","type":"article","venue":"The Open Bioinformatics Journal","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Solana Networks (Canada)","funders":"","keywords":"Epidemiology; Principal component analysis; Epidemiological method; Dimensionality reduction; Cluster analysis; Computer science; Artificial intelligence; Statistics; Data mining; Machine learning; Medicine; Mathematics; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.4015662938541903,"gpt":0.4662462768483867,"spread":0.06467998299419642,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005458052,0.0002531334,0.001091602,0.0001378481,0.0004448415,0.0003343247,0.001288238,0.0001337785,0.001287829],"category_scores_gemma":[0.01384856,0.0001307039,0.0003936983,0.001085663,0.0001158826,0.0003750911,0.001606374,0.0007895107,0.00004877744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002007238,"about_ca_system_score_gemma":0.0001033582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000422665,"about_ca_topic_score_gemma":0.0003397855,"domain_scores_codex":[0.9965618,0.0008085155,0.001595329,0.0001797682,0.0003128429,0.0005418026],"domain_scores_gemma":[0.9925665,0.006053001,0.0005392474,0.0005270477,0.0001566907,0.0001575273],"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":[0.000820532,0.00184136,0.6342199,0.0009517093,0.01277663,0.001149403,0.03840943,0.04077605,0.0004363451,0.07899431,0.03706054,0.1525637],"study_design_scores_gemma":[0.002934746,0.0002251294,0.3074178,0.0002932738,0.001007027,0.0004985273,0.007987604,0.3425413,0.0001229344,0.326161,0.009703436,0.001107225],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5613493,0.0009946865,0.3650123,0.03720694,0.0006194926,0.001564579,0.00008776462,0.0001472068,0.03301777],"genre_scores_gemma":[0.8084751,0.001194009,0.1817103,0.007737538,0.0001913141,0.00003313834,0.000009554154,0.00002472531,0.0006242953],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3268022,"threshold_uncertainty_score":0.9996251,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402458231","doi":"10.2174/0118750362298089240820111544","title":"Detection of Dementia: Using Electroencephalography and Machine Learning","year":2024,"lang":"en","type":"article","venue":"The Open Bioinformatics Journal","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Electroencephalography; Dementia; Support vector machine; Computer science; Artificial intelligence; Random forest; Decision tree; Machine learning; Feature selection; Logistic regression; Spike (software development); Pattern recognition (psychology); Psychology; Medicine; Psychiatry","retraction":null,"screen_n_in":null,"score":{"opus":0.03861501887869004,"gpt":0.2879062247833128,"spread":0.2492912059046228,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005981359,0.00007405667,0.00009314579,0.0001209862,0.0003379335,0.0007515171,0.0003573781,0.00001955238,0.00001822745],"category_scores_gemma":[0.00005233354,0.0000432464,0.00004095987,0.0002489874,0.00008278139,0.0006815591,0.0001844374,0.0003538026,0.000002997745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001003317,"about_ca_system_score_gemma":0.0000232445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001072911,"about_ca_topic_score_gemma":0.000002822709,"domain_scores_codex":[0.999292,0.00007770661,0.000270982,0.00006121993,0.0001533707,0.0001447137],"domain_scores_gemma":[0.9996148,0.0001257414,0.0001368729,0.00006666959,0.00002019344,0.00003575418],"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":[0.0000501076,0.00002493728,0.0004005546,0.0001257125,0.0001090906,0.00001452295,0.005658513,0.001313704,0.8539829,0.00104314,0.00009307803,0.1371838],"study_design_scores_gemma":[0.0001757152,0.0002376242,0.00007504976,0.0001383987,0.00004604681,0.002059601,0.0003001537,0.6524563,0.3408071,0.001441868,0.002174335,0.00008774392],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9143448,0.001091617,0.08172297,0.0002382442,0.000403255,0.000178966,0.000002975287,0.00002743839,0.001989738],"genre_scores_gemma":[0.9971975,0.0003001912,0.002323368,0.0001099752,0.00003555109,5.86655e-7,1.58621e-7,0.00000563921,0.00002704377],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6511427,"threshold_uncertainty_score":0.7246897,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061284677","doi":"10.2174/1875036201004010041","title":"Differences in Promoters of Orthologous Genes","year":2010,"lang":"en","type":"article","venue":"The Open Bioinformatics Journal","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Biotechnology Research Institute","funders":"Directorate for Biological Sciences; University of Ottawa","keywords":"Gene; Biology; Zebrafish; Orthologous Gene; Genome; Genetics; Promoter; Human genome; Phylogenetic tree; Model organism; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.02240162046769039,"gpt":0.2833074828353821,"spread":0.2609058623676917,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004735663,0.00006229511,0.00008865142,0.00004000766,0.00007414578,0.00007218333,0.000616178,0.00005991463,0.0000394996],"category_scores_gemma":[0.00003938283,0.00003576672,0.0000321323,0.00007096688,0.00007911061,0.00001102654,0.0001498867,0.0001649346,0.000003049132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002907918,"about_ca_system_score_gemma":0.00008828202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005252123,"about_ca_topic_score_gemma":0.0000341506,"domain_scores_codex":[0.9994385,0.00003282765,0.0002778561,0.00005159236,0.00009657181,0.0001026956],"domain_scores_gemma":[0.9994608,0.000005774152,0.0002187885,0.000224368,0.00005299368,0.00003726747],"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":[0.00009711672,0.00007116237,0.01974709,0.00001667298,0.00002617875,0.00000102558,0.0009818084,0.00001556483,0.9127294,0.0003007689,0.001924614,0.06408856],"study_design_scores_gemma":[0.002652854,0.000705636,0.1480401,0.000107571,0.00003357106,0.0007266598,0.005027388,0.002260814,0.7865507,0.001489664,0.05189627,0.000508752],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944152,0.00007678603,0.000752557,0.0003702261,0.0002240281,0.0001506377,0.00000236666,0.000001198878,0.00400703],"genre_scores_gemma":[0.996257,0.0002242197,0.00310181,0.0001069165,0.00005484142,0.00000658776,0.000004376402,0.000004000414,0.0002402499],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.128293,"threshold_uncertainty_score":0.1458524,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2129324791","doi":"10.2174/1875036201408010016","title":"Predicting Neutropenia Risk in Breast Cancer Patients from Pre-Chemotherapy Characteristics","year":2014,"lang":"en","type":"article","venue":"The Open Bioinformatics Journal","topic":"Neutropenia and Cancer Infections","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":"Kingston General Hospital; Queen's University","funders":"","keywords":"Febrile neutropenia; Medicine; Odds ratio; Neutropenia; Breast cancer; Internal medicine; Chemotherapy; Cancer; Surgery; Oncology","retraction":null,"screen_n_in":null,"score":{"opus":0.009756043574750862,"gpt":0.2715187704383582,"spread":0.2617627268636074,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000603067,0.0001781107,0.000352904,0.00007936292,0.0003731259,0.0003847085,0.0004977382,0.00006729804,0.0006124323],"category_scores_gemma":[0.00004852348,0.0001097709,0.00007825433,0.0001917544,0.00006039049,0.0005340566,0.0001563351,0.0007537527,0.00004860927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001624199,"about_ca_system_score_gemma":0.0001535927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009957363,"about_ca_topic_score_gemma":0.0001207899,"domain_scores_codex":[0.9985029,0.0001032057,0.0006868964,0.0001058594,0.0003022686,0.0002988871],"domain_scores_gemma":[0.9986572,0.00008640545,0.0005950736,0.0003210886,0.0001698649,0.0001703946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004957806,0.0001386167,0.9367175,0.0000157799,0.00009761826,0.000001427023,0.001862299,0.00004726415,0.00007500225,0.00001918824,0.001718244,0.05881131],"study_design_scores_gemma":[0.004174157,0.0001789823,0.9804561,0.000289783,0.0001256078,0.0001181402,0.0001422198,0.008133871,0.00008939046,0.0001428092,0.006004738,0.0001442006],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920468,0.00001985806,0.0003345349,0.001520594,0.0005422494,0.0006014883,0.0001487995,0.00001759569,0.004768086],"genre_scores_gemma":[0.9952325,0.0009224769,0.0009021919,0.002071329,0.0005982388,0.00003049533,0.00002608694,0.00002966057,0.0001870065],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05866711,"threshold_uncertainty_score":0.6705705,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}