{"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":"7c3cc6ee32a6","filters":{"venue":"IEEE Transactions on Biometrics Behavior and Identity Science"}},"results":[{"id":"W3175579268","doi":"10.1109/tbiom.2021.3065914","title":"An Efficient Convolutional Neural Network for Fingerprint Pore Detection","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Biometrics Behavior and Identity Science","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fingerprint (computing); Computer science; Convolutional neural network; Artificial intelligence; Centroid; Pattern recognition (psychology); Scheme (mathematics); Artificial neural network; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03557229552737199,"gpt":0.3122987586349795,"spread":0.2767264631076075,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001146009,0.0001503128,0.0001527064,0.00193874,0.00138565,0.001124582,0.0007278976,0.00009561655,0.00001609442],"category_scores_gemma":[0.00006381473,0.0001617731,0.0001114059,0.01528038,0.0003380046,0.001310846,0.00001485105,0.0001849747,0.000009251496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001809672,"about_ca_system_score_gemma":0.0002151454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000628035,"about_ca_topic_score_gemma":0.00006425631,"domain_scores_codex":[0.9975453,0.00005664171,0.0003113648,0.0008177928,0.0008496154,0.0004193004],"domain_scores_gemma":[0.9982131,0.0001118944,0.0001031272,0.0005545956,0.00072787,0.0002894518],"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":[0.00004351513,0.004255706,0.002025751,0.00007089904,0.00003159262,0.00004265012,0.000606031,0.01751088,0.1781141,0.01979335,0.000122439,0.7773831],"study_design_scores_gemma":[0.001008607,0.0004454311,0.1754246,0.0000149171,0.00008430929,0.0001998643,0.0001262266,0.6841564,0.1361826,0.0007368653,0.000911196,0.000709022],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.309023,0.00008432993,0.6881996,0.00008937002,0.002272773,0.0001989057,0.00003922327,0.00008551504,0.000007261408],"genre_scores_gemma":[0.9822124,0.00003785528,0.01745434,0.0001096192,0.00004324113,0.00005878481,0.000006555959,0.000006391945,0.00007081795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7766741,"threshold_uncertainty_score":0.9999144,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2981302199","doi":"10.1109/tbiom.2019.2947264","title":"Video Face Clustering With Self-Supervised Representation Learning","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Biometrics Behavior and Identity Science","topic":"Face recognition and analysis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Cluster analysis; Artificial intelligence; Computer science; Face (sociological concept); Self representation; Representation (politics); Pattern recognition (psychology); Machine learning; Art; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.0240441834061977,"gpt":0.2894166536235818,"spread":0.2653724702173841,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000477191,0.0001321137,0.0001511801,0.002218614,0.0005481948,0.0009231546,0.0005343812,0.00004660664,0.00004119179],"category_scores_gemma":[0.00001295152,0.000120466,0.00006447535,0.01072617,0.0001195786,0.003176502,0.00001334788,0.000203171,0.0001166945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008990008,"about_ca_system_score_gemma":0.00006560713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001283873,"about_ca_topic_score_gemma":0.00003455486,"domain_scores_codex":[0.9980533,0.00004244441,0.0001873853,0.0006130032,0.0008287105,0.0002752072],"domain_scores_gemma":[0.9991452,0.00006382825,0.00007343099,0.0003426841,0.0002065947,0.0001683269],"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":[0.00004157092,0.001624227,0.07029575,0.0001215819,0.00009336814,0.00005860967,0.004043879,0.02230188,0.2389038,0.0003683368,0.00001944137,0.6621275],"study_design_scores_gemma":[0.002084652,0.0009556549,0.06639813,0.00008153843,0.0002031142,0.0001463021,0.001565641,0.8214163,0.105939,0.00004582933,0.0001405075,0.001023345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4339967,0.00001024594,0.5654038,0.00005434218,0.0002116052,0.0001293801,0.000001840699,0.0001086382,0.00008342854],"genre_scores_gemma":[0.9860131,0.0001099802,0.01339346,0.00005278613,0.000005063381,0.00001679838,7.69809e-7,0.000006329956,0.0004016987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7991144,"threshold_uncertainty_score":0.8902002,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3093251642","doi":"10.1109/tbiom.2020.3031470","title":"View-Invariant Gait Recognition With Attentive Recurrent Learning of Partial Representations","year":2020,"lang":"en","type":"preprint","venue":"IEEE Transactions on Biometrics Behavior and Identity Science","topic":"Gait Recognition and Analysis","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Mitacs","keywords":"Computer science; Gait; Robustness (evolution); Artificial intelligence; Convolutional neural network; Deep learning; Pattern recognition (psychology); Machine learning; Computer vision; Physical medicine and rehabilitation","retraction":null,"screen_n_in":null,"score":{"opus":0.05659673704040318,"gpt":0.3067739856656211,"spread":0.250177248625218,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003564441,0.00024399,0.0003454711,0.00244965,0.0003145904,0.0003054463,0.0002658143,0.0001259447,0.0001059181],"category_scores_gemma":[0.00004056383,0.0002457993,0.0001628796,0.005667684,0.0003570944,0.0005405836,0.00001337537,0.0006884323,0.00003081402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001113302,"about_ca_system_score_gemma":0.00008585829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001578591,"about_ca_topic_score_gemma":0.00004879625,"domain_scores_codex":[0.9979132,0.0000536049,0.0004354756,0.0005855227,0.0007642366,0.0002479219],"domain_scores_gemma":[0.9989265,0.00005792786,0.0001639518,0.0002322755,0.0003990374,0.0002203748],"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":[0.000166463,0.002743509,0.007388667,0.001790239,0.0008143726,0.0001053974,0.003719824,0.06636782,0.1514404,0.00008531494,0.0001565851,0.7652214],"study_design_scores_gemma":[0.003987127,0.002234993,0.134178,0.002192991,0.008449361,0.0001163387,0.004137696,0.3119932,0.5269086,0.0008594597,0.0003704927,0.004571852],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4606205,0.00008143338,0.53771,0.00003869054,0.0006513942,0.0003242309,0.0002909568,0.0001337024,0.0001491876],"genre_scores_gemma":[0.9970042,0.001252925,0.001503921,0.000009359134,0.00002641278,0.0001020199,0.0000498406,0.00002080695,0.00003051801],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7606495,"threshold_uncertainty_score":0.9999994,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401717952","doi":"10.1109/tbiom.2024.3446846","title":"A Data Perspective on Ethical Challenges in Voice Biometrics Research","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Biometrics Behavior and Identity Science","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; University of Toronto","funders":"Mozilla Foundation","keywords":"Biometrics; Perspective (graphical); Psychology; Engineering ethics; Computer science; Engineering; Computer security; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.2563719231205265,"gpt":0.4530711126378877,"spread":0.1966991895173612,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["bibliometrics","scholarly_communication"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.006676671,0.000181022,0.0001738906,0.01749537,0.0007263882,0.001785467,0.00225026,0.0002419956,0.000008791505],"category_scores_gemma":[0.0004108816,0.0001721266,0.00005330516,0.05003539,0.0006706863,0.00271658,0.0000733432,0.001594758,0.0001817636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006188215,"about_ca_system_score_gemma":0.0003379264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005914535,"about_ca_topic_score_gemma":0.000355527,"domain_scores_codex":[0.9951928,0.0001841156,0.0002740084,0.001562012,0.002175162,0.0006118561],"domain_scores_gemma":[0.9974676,0.0006719261,0.00003059494,0.001147758,0.000410428,0.0002717014],"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":[0.00002956463,0.001581828,0.00009008424,0.00009578043,0.00001871251,0.0003478887,0.002155711,0.00004947979,0.02042177,0.05387728,0.0001983292,0.9211336],"study_design_scores_gemma":[0.00655031,0.01955825,0.1691836,0.002611154,0.0004766187,0.001900941,0.01856587,0.3557035,0.3217633,0.04884017,0.04631627,0.008529995],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2407488,0.003717914,0.7409015,0.006436539,0.005447746,0.0008280494,0.0001752241,0.0005126652,0.001231501],"genre_scores_gemma":[0.993978,0.003697995,0.002072772,0.00005250618,0.00003824676,0.00003472972,9.505924e-7,0.00001142461,0.0001133948],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9126036,"threshold_uncertainty_score":0.9992508,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2920716353","doi":"10.1109/tbiom.2019.2900745","title":"Editorial Introducing the IEEE Transactions on Biometrics, Behavior, and Identity Science","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Biometrics Behavior and Identity Science","topic":"User Authentication and Security Systems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Biometrics; Identity (music); Computer science; Internet privacy; Computer security; Art; Aesthetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02442832272514045,"gpt":0.305647274019266,"spread":0.2812189512941256,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","bibliometrics","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00407215,0.0003704338,0.0003629358,0.007576675,0.002821484,0.004000781,0.002889647,0.0001839933,0.0000394664],"category_scores_gemma":[0.00009670218,0.0003187616,0.0001622408,0.0310788,0.001845411,0.007371054,0.00002680865,0.0006876458,0.0001669381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004039933,"about_ca_system_score_gemma":0.0004096098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00075828,"about_ca_topic_score_gemma":0.0001446201,"domain_scores_codex":[0.9933524,0.0001174631,0.0006400806,0.001618488,0.003459579,0.0008119493],"domain_scores_gemma":[0.9966642,0.0002851345,0.0002468636,0.001472533,0.0008030038,0.0005283233],"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":[0.0001179593,0.00987183,0.01556067,0.0003051518,0.0001245541,0.00003641125,0.02998004,0.0003613358,0.5888243,0.009122221,0.001536238,0.3441593],"study_design_scores_gemma":[0.01015912,0.005953632,0.3184645,0.0004558484,0.001585429,0.0007027952,0.004194065,0.09205782,0.5483815,0.001910634,0.008757045,0.007377658],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5069472,0.00005751267,0.4394882,0.0001696574,0.05244811,0.0006966016,0.00004744793,0.0001217057,0.00002356888],"genre_scores_gemma":[0.9981102,0.0001956363,0.0006590519,0.00009262699,0.000579629,0.00008526622,7.368111e-7,0.00001748794,0.0002593325],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4911631,"threshold_uncertainty_score":0.9999264,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401726091","doi":"10.1109/tbiom.2024.3446964","title":"Large-Scale Fully-Unsupervised Re-Identification","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Biometrics Behavior and Identity Science","topic":"Machine Learning and Data Classification","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":"Artificial Intelligence in Medicine (Canada)","funders":"Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Identification (biology); Scale (ratio); Computer science; Artificial intelligence; Geography; Cartography; Biology; Ecology","retraction":null,"screen_n_in":null,"score":{"opus":0.02969761813694448,"gpt":0.323513884743391,"spread":0.2938162666064465,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001561752,0.0001475849,0.0001176147,0.002928331,0.0008419731,0.00248743,0.001009433,0.00007553378,0.00004026679],"category_scores_gemma":[0.00003842184,0.0001428216,0.00007204837,0.01146922,0.0002257058,0.003824909,0.00001651897,0.0002868018,0.0002277451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001148269,"about_ca_system_score_gemma":0.000120981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007649636,"about_ca_topic_score_gemma":0.00004924471,"domain_scores_codex":[0.9975744,0.00005078471,0.0002985603,0.0008598499,0.0008851761,0.0003311621],"domain_scores_gemma":[0.9987889,0.0000848854,0.00005389575,0.0007121352,0.0001648416,0.0001953539],"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":[0.00000951843,0.001246711,0.002608287,0.0001426849,0.00001603586,0.0000316691,0.003082444,0.0001554035,0.1836248,0.01373018,0.0004969166,0.7948554],"study_design_scores_gemma":[0.0009948208,0.0005584882,0.3321965,0.0001463636,0.0002388689,0.0001438721,0.0009505973,0.5657693,0.0813582,0.001499393,0.01461358,0.001529974],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.151177,0.0001629628,0.8457356,0.000440655,0.001806052,0.0001653114,0.00005077983,0.0003254637,0.0001362343],"genre_scores_gemma":[0.9948553,0.0002514218,0.004144791,0.0000561805,0.00002486879,0.00004122556,0.000006770851,0.000008870392,0.0006105297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8436784,"threshold_uncertainty_score":0.9985481,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405303824","doi":"10.1109/tbiom.2024.3516634","title":"A Deep CNN-Based Feature Extraction and Matching of Pores for Fingerprint Recognition","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Biometrics Behavior and Identity Science","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fingerprint (computing); Pattern recognition (psychology); Artificial intelligence; Matching (statistics); Feature extraction; Computer science; Feature (linguistics); Extraction (chemistry); Mathematics; Chemistry; Chromatography; Statistics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.04040861572360703,"gpt":0.3303098214017909,"spread":0.2899012056781838,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001023256,0.0001191612,0.0001295633,0.004580627,0.0004330031,0.0009787777,0.0003413092,0.00009267442,0.000008180848],"category_scores_gemma":[0.00004950518,0.0001169568,0.0000798402,0.009363505,0.0002616787,0.001789328,0.000007057915,0.0001731352,0.000004799329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008470134,"about_ca_system_score_gemma":0.0001070775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001165833,"about_ca_topic_score_gemma":0.00003242864,"domain_scores_codex":[0.9984642,0.00002446998,0.0002329153,0.0005439783,0.0005357013,0.0001986818],"domain_scores_gemma":[0.9990766,0.000219935,0.00007989032,0.0002403349,0.0002592411,0.0001239984],"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":[0.00001391456,0.0004154539,0.0001545583,0.0002316136,0.00001097037,0.000005453605,0.0005146522,0.00004818656,0.09384731,0.001833269,0.00003451523,0.9028901],"study_design_scores_gemma":[0.001464687,0.0009403115,0.09231745,0.0003329529,0.0003564118,0.0001602819,0.0004594107,0.3682148,0.5251254,0.008037771,0.001339733,0.001250727],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1944084,0.0002973202,0.8036214,0.0002070118,0.001079873,0.000253179,0.00004208009,0.00008126089,0.000009512192],"genre_scores_gemma":[0.9652702,0.0001693017,0.03440876,0.00003318535,0.00001179534,0.00004467769,0.000003231032,0.000005843015,0.00005306091],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9016394,"threshold_uncertainty_score":0.9438375,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}