{"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"},"query_hash":"efbcabf34d13","filters":{"venue":"Applied Bioinformatics"}},"results":[{"id":"W2027769711","doi":"10.2165/00822942-200403010-00002","title":"Purine loading, stem-loops and Chargaff's second parity rule","year":2004,"lang":"en","type":"review","venue":"Applied Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Purine; Gene; Purine metabolism; RNA; DNA; Base pair; Biology; Genetics; Nucleotide; Chemistry; Computational biology; Biochemistry; Enzyme","retraction":null,"screen_n_in":null,"score":{"opus":0.01833603275092779,"gpt":0.2533041528796697,"spread":0.2349681201287419,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003307218,0.0005689628,0.001008248,0.00009265032,0.0001379585,0.0001050411,0.000387371,0.0007382314,0.00008821634],"category_scores_gemma":[0.00001358052,0.0004698148,0.0002335069,0.0001071543,0.00009339478,0.000007151529,0.0003213407,0.0002491607,0.0001944131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003648589,"about_ca_system_score_gemma":0.0002173566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002358868,"about_ca_topic_score_gemma":0.000003205344,"domain_scores_codex":[0.9982366,0.00002868802,0.0007543492,0.0003674474,0.0001930664,0.0004198647],"domain_scores_gemma":[0.9986171,0.00002210152,0.0005041221,0.0006443181,0.00003215856,0.0001801606],"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":[0.000008547128,0.00003558214,3.865388e-7,0.01948471,0.000197705,0.000002305349,0.00005165199,1.873616e-7,0.0005101998,0.00115355,0.0005789866,0.9779762],"study_design_scores_gemma":[0.0002895691,0.00008653045,3.565229e-7,0.001237468,0.00021694,0.00007952198,0.00004056126,0.000001851857,0.008185734,0.0002212862,0.9890336,0.0006065198],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001349684,0.9871666,0.0008961593,0.00000818567,0.0001549075,0.001213618,0.000197916,0.0000405027,0.01018707],"genre_scores_gemma":[0.00006536652,0.9921788,0.00522633,0.0001142068,0.0001970294,0.0001832189,0.0005032133,0.00006748827,0.00146434],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9884547,"threshold_uncertainty_score":0.9997754,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2084557687","doi":"10.2165/00822942-200504010-00001","title":"Spot Detection and Image Segmentation in DNA??Microarray Data","year":2005,"lang":"en","type":"review","venue":"Applied Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor; IBM (Canada)","funders":"","keywords":"DNA microarray; Cluster analysis; Segmentation; Histogram; Computer science; Data mining; Gene chip analysis; Euclidean distance; Artificial intelligence; Microarray analysis techniques; Pattern recognition (psychology); Image (mathematics); Biology; Gene; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.03628206879582436,"gpt":0.3202165621431473,"spread":0.2839344933473229,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002253105,0.0002475383,0.0003496494,0.0001373055,0.00004909508,0.00006145974,0.000309448,0.0003135452,0.000009429062],"category_scores_gemma":[0.00001496232,0.0002160321,0.00004590238,0.0001614939,0.00004688281,0.00001420805,0.0002410172,0.0001507554,0.00003816542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004098924,"about_ca_system_score_gemma":0.00009605577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001813369,"about_ca_topic_score_gemma":0.00002028711,"domain_scores_codex":[0.9988361,0.00002461057,0.0005409014,0.0003142029,0.0001133617,0.0001708162],"domain_scores_gemma":[0.9988947,0.000008797369,0.0003273365,0.0006964938,0.00001803223,0.00005462866],"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":[0.000006523267,0.0000149378,3.217245e-7,0.001248846,0.00001702259,1.235744e-7,0.00003466721,4.586225e-7,0.01073103,0.000006955264,0.0008154599,0.9871237],"study_design_scores_gemma":[0.0002673926,0.0000198554,0.000004428887,0.0002688847,0.00007750736,0.00001350925,0.0001167372,0.0001082783,0.003677142,0.000005124097,0.9951825,0.0002586808],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001225507,0.9887251,0.006174134,0.0000162447,0.0001530603,0.001071395,0.0001265896,0.00002378045,0.003587109],"genre_scores_gemma":[0.0002193129,0.9900764,0.006438895,0.00007239759,0.0001671659,0.00009238524,0.002815003,0.00002642626,0.00009204326],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.994367,"threshold_uncertainty_score":0.8809534,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2078059232","doi":"10.2165/00822942-200403040-00003","title":"Genomic Conflict Settled in Favour of the Species Rather Than the Gene at Extreme GC Percentage Values","year":2004,"lang":"en","type":"article","venue":"Applied Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Merck Canada Inc. (Canada); Queen's University; University of British Columbia","funders":"","keywords":"Genome; GC-content; Biology; Genetics; Gene; Codon usage bias; Phylogenetic tree","retraction":null,"screen_n_in":null,"score":{"opus":0.01785389388283213,"gpt":0.2090485774648516,"spread":0.1911946835820194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000177983,0.000177802,0.0001749935,0.00002408162,0.000143104,0.00001663378,0.0003939378,0.00008981412,0.00001149419],"category_scores_gemma":[0.000008554626,0.0001047042,0.0001080645,0.00007506831,0.0002313899,9.62308e-7,0.0004019642,0.00007871697,0.00001712838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004081062,"about_ca_system_score_gemma":0.00005243205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002101414,"about_ca_topic_score_gemma":0.0001084588,"domain_scores_codex":[0.9991206,0.00001608002,0.0003557726,0.0001330922,0.0001374106,0.000237043],"domain_scores_gemma":[0.9992797,0.00001190074,0.0001640807,0.0004891093,0.00002620296,0.00002899403],"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":[0.00003408791,0.000042385,0.007598384,0.00002535596,0.00008165977,2.833049e-7,0.002831727,0.0009931624,0.9870163,0.0008783764,0.0002690992,0.0002292412],"study_design_scores_gemma":[0.002038579,0.0001137971,0.2775005,0.00001909256,0.00006174028,0.00001554035,0.005211179,0.0001492952,0.6873701,0.0006881814,0.02640864,0.0004234463],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9927754,0.000468551,0.00009950905,0.0001855231,0.0001004987,0.0004112594,0.00005302291,0.000002878826,0.005903387],"genre_scores_gemma":[0.9976889,0.0004664478,0.0008914723,0.0004199299,0.00007036787,0.00001988825,0.00002296146,0.00001614272,0.0004038624],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2996462,"threshold_uncertainty_score":0.4269711,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2032021641","doi":"10.2165/00822942-200504020-00011","title":"CESE","year":2005,"lang":"it","type":"article","venue":"Applied Bioinformatics","topic":"Cardiac electrophysiology and arrhythmias","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Environmental science","retraction":null,"screen_n_in":null,"score":{"opus":0.007811367973232826,"gpt":0.2333325068026826,"spread":0.2255211388294498,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002333963,0.0003451768,0.0005693419,0.0001334974,0.0001875851,0.0000382378,0.0001569251,0.0003625083,0.0007253908],"category_scores_gemma":[0.00003350851,0.0002989981,0.0002232126,0.0003049429,0.000210355,0.0001590323,0.0001129283,0.0006144751,0.01454879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001261022,"about_ca_system_score_gemma":0.0001865981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000241474,"about_ca_topic_score_gemma":0.000001126002,"domain_scores_codex":[0.9980664,0.0000149737,0.0006907624,0.0001961213,0.0003140561,0.0007177183],"domain_scores_gemma":[0.9987737,0.00009886156,0.0002219622,0.000589355,0.00005957918,0.0002565665],"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":[0.001187092,0.0006588256,0.0002039082,0.001172508,0.001404406,0.0001377622,0.01299512,0.001783606,0.009625979,0.05567833,0.1643512,0.7508012],"study_design_scores_gemma":[0.009562809,0.001147842,0.003317188,0.0003740044,0.001682264,0.0009750615,0.004767063,0.05463993,0.03980406,0.001117153,0.8804715,0.002141113],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2724158,0.001577078,0.00120332,0.004461466,0.0009594358,0.001524494,0.00006875949,0.0003588792,0.7174308],"genre_scores_gemma":[0.9783661,0.0008197752,0.008796523,0.00586383,0.002604034,0.000026638,0.0001227439,0.00003659915,0.00336377],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7486601,"threshold_uncertainty_score":0.9999462,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W973763935","doi":"10.2165/00822942-200504020-00005","title":"Amino Acids as Placeholders","year":2005,"lang":"en","type":"article","venue":"Applied Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"ORFS; Amino acid; Biology; Genetic code; Genome; GC-content; Open reading frame; Genetics; Stop codon; Codon usage bias; Nucleic acid; Gene; Protein sequencing; Biochemistry; Peptide sequence","retraction":null,"screen_n_in":null,"score":{"opus":0.008663347992397393,"gpt":0.2199712514495086,"spread":0.2113079034571112,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001639347,0.0001678361,0.0001216569,0.00003860409,0.000089753,0.00003917345,0.0002345352,0.0001852654,0.0001015048],"category_scores_gemma":[0.00002311097,0.0001511006,0.00006410985,0.00006459714,0.0000490969,0.000006596447,0.00009126706,0.00006703665,0.0008036912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001242057,"about_ca_system_score_gemma":0.00004483816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001607495,"about_ca_topic_score_gemma":0.000002675459,"domain_scores_codex":[0.9991499,0.000008215848,0.0002622459,0.0001430443,0.0001656048,0.0002709857],"domain_scores_gemma":[0.9994061,0.000008872292,0.00009365003,0.0003704206,0.00002346643,0.00009747132],"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":[0.0001183959,0.00007062257,0.00006135889,0.00004858582,0.00008184469,9.963823e-7,0.0004306804,0.0001592395,0.7833981,0.01078135,0.009430908,0.1954179],"study_design_scores_gemma":[0.0003693611,0.00009273637,0.0000322778,0.000005029717,0.00001179164,0.00001534881,0.0002643761,0.0001961425,0.7273563,0.0002299675,0.2712015,0.0002252144],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6341822,0.0001993828,0.03190679,0.0005749681,0.0002103788,0.0008001705,0.00002317037,0.000116221,0.3319868],"genre_scores_gemma":[0.952152,0.00009977062,0.04272661,0.002186057,0.0002904522,0.00005090302,0.00009138054,0.00002502917,0.002377833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3296089,"threshold_uncertainty_score":0.9999743,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2087758886","doi":"10.2165/00822942-200504020-00002","title":"A Multiple-Pattern Biosequence Analysis Method for Diverse Source Association Mining","year":2005,"lang":"en","type":"article","venue":"Applied Bioinformatics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Representation (politics); Sequence (biology); Matching (statistics); Task (project management); Data mining; Identification (biology); Computational biology; Association rule learning; Pattern recognition (psychology); Biology; Artificial intelligence; Mathematics; Genetics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01839074371195653,"gpt":0.2717366685490165,"spread":0.25334592483706,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006607753,0.0001507141,0.0002239141,0.0002038261,0.0002479609,0.0002631163,0.000750482,0.00009008508,0.000005619111],"category_scores_gemma":[0.0000762268,0.0001436742,0.0001216908,0.0009018708,0.00001586005,0.0004985969,0.0002206047,0.00008314075,0.000096544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001322578,"about_ca_system_score_gemma":0.0000337507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002620535,"about_ca_topic_score_gemma":0.00003589627,"domain_scores_codex":[0.9987139,0.00001141121,0.0004219696,0.0002383221,0.0002840656,0.0003303919],"domain_scores_gemma":[0.9984499,0.0004495375,0.0003809055,0.0005377884,0.00009027882,0.00009159684],"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":[0.000001357487,0.00003735458,0.0005851659,0.00001475399,0.0001833616,8.41601e-8,0.002365438,0.002404278,0.0001340503,0.002359171,0.00167619,0.9902388],"study_design_scores_gemma":[0.000266775,0.00001361963,0.0002944859,0.000003621284,0.0001311375,0.000001005957,0.0004002758,0.9738513,0.001192063,0.00007481472,0.0235768,0.0001940565],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001595242,0.00000468985,0.9965255,0.0006484349,0.00003968252,0.0002908593,0.00008737368,0.0001935913,0.0006146303],"genre_scores_gemma":[0.05000185,0.000004486661,0.9485509,0.0009586561,0.00007983089,0.0001159024,0.0001172773,0.000007290211,0.0001638473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9900447,"threshold_uncertainty_score":0.5858862,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}