{"meta":{"query_hash":"ba4c3db01bc1","filters":{"venue":"The Journal of Machine Learning for Biomedical Imaging"},"cohort_total":33,"direct_labels_cover":0,"predictions_cover":33,"exported":33,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/ba4c3db01bc1","api":"https://metacan.xera.ac/api/v1/cohort?venue=The+Journal+of+Machine+Learning+for+Biomedical+Imaging"},"results":[{"id":"W2954679106","doi":"10.59275/j.melba.2021-gfgg","title":"PathologyGAN: Learning deep representations of cancer tissue","year":2021,"lang":"en","type":"preprint","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; University of Glasgow","keywords":"Artificial intelligence; Cancer; Computer science; Breast cancer; Colorectal cancer; Deep learning; Feature (linguistics); Feature vector; Pattern recognition (psychology); Stromal cell; Machine learning; Medicine; Pathology; Internal medicine","score_opus":0.014307464974859305,"score_gpt":0.33815447274286375,"score_spread":0.32384700776800446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954679106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01843929,0.010146979,0.9594012,0.009404274,0.0022814337,0.00018975484,0.000003684572,0.000059445014,0.00007393053],"genre_scores_gemma":[0.9401147,0.0015942479,0.0569635,0.0001874375,0.0008472603,0.000021811627,0.000019859006,0.000046652032,0.00020453805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99689347,0.00079756544,0.00094264414,0.0003279496,0.00071170676,0.00032665202],"domain_scores_gemma":[0.99596876,0.0009067448,0.0019384314,0.0004371221,0.0006180759,0.00013084467],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0028175975,0.00023775424,0.0005568969,0.00035473472,0.0003062861,0.0001301567,0.0014472598,0.00014743724,0.00005619454],"category_scores_gemma":[0.0013442031,0.0001786095,0.0002699672,0.00044470982,0.00030091056,0.0002480181,0.0011768751,0.002745102,0.0000011562862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012445837,0.00012943713,0.00710723,0.00047408105,0.00041515706,0.00011304101,0.008751136,0.18050405,0.020693123,0.00013939488,0.00051067263,0.7810382],"study_design_scores_gemma":[0.0012362858,0.00047998814,0.002895739,0.0010731502,0.00043578472,0.00096584857,0.0008754188,0.963227,0.0070314365,0.0026930762,0.018659458,0.0004268228],"about_ca_topic_score_codex":0.0004405843,"about_ca_topic_score_gemma":0.000022977449,"teacher_disagreement_score":0.9216754,"about_ca_system_score_codex":0.0001618547,"about_ca_system_score_gemma":0.0003977673,"threshold_uncertainty_score":0.9995556},"labels":[],"label_agreement":null},{"id":"W2972185346","doi":"10.59275/j.melba.2023-5g54","title":"Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey","year":2023,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada","keywords":"Artificial intelligence; Computer science; Pooling; Deep learning; Pattern recognition (psychology); Pixel; Classifier (UML); Grading (engineering); Computer vision; Machine learning","score_opus":0.03556278911581747,"score_gpt":0.36143888786230915,"score_spread":0.3258760987464917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972185346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040519168,0.0008277859,0.9893259,0.0050792075,0.00044896489,0.00019357282,7.2457175e-7,0.00006091482,0.000011060083],"genre_scores_gemma":[0.8598207,0.00039510464,0.13918327,0.0002541117,0.00018252379,0.000025792498,0.000025458556,0.000037032347,0.000075961056],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974545,0.0013318284,0.0005177754,0.0002005908,0.00021376481,0.00028151684],"domain_scores_gemma":[0.99617314,0.0029586256,0.00044162903,0.00013210128,0.00021308905,0.000081435246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010548067,0.00012017946,0.0002507897,0.00047792975,0.00030224316,0.00007075253,0.00044307124,0.00006172396,0.0000032469052],"category_scores_gemma":[0.0037672974,0.00009086243,0.000064735876,0.00085092,0.00015847688,0.00025344646,0.000119967845,0.0005325216,0.0000013876053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021931926,0.000032892505,0.020814808,0.00009302149,0.000033849054,0.0000036882204,0.002104809,0.013029853,0.0158267,0.00018359757,0.00047138764,0.94718605],"study_design_scores_gemma":[0.00084641064,0.00021377981,0.014488664,0.0000424032,0.000019893212,0.000086766995,0.00017429052,0.97169924,0.0001432246,0.0014779029,0.010712665,0.0000947382],"about_ca_topic_score_codex":0.000095936455,"about_ca_topic_score_gemma":0.000015107934,"teacher_disagreement_score":0.9586694,"about_ca_system_score_codex":0.00013132008,"about_ca_system_score_gemma":0.00007395902,"threshold_uncertainty_score":0.4510079},"labels":[],"label_agreement":null},{"id":"W2972672210","doi":"10.59275/j.melba.2021-1a1f","title":"PILOT: Physics-Informed Learned Optimized Trajectories for Accelerated MRI","year":2021,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Pipeline (software); Data acquisition; Real-time MRI; Magnetic resonance imaging; Artificial intelligence; Segmentation; Artificial neural network; Iterative reconstruction; Computer vision; Set (abstract data type); Deep learning","score_opus":0.04342063471811727,"score_gpt":0.3749468683684789,"score_spread":0.33152623365036166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972672210","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033735933,0.00074783474,0.97368866,0.021303263,0.00014977477,0.0004398978,0.000013202022,0.00008292987,0.00020083642],"genre_scores_gemma":[0.49274722,0.0011112535,0.50075746,0.001555478,0.0014260085,0.000076115706,0.00027682667,0.00010134009,0.0019482905],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987382,0.00005632697,0.0005126852,0.00012730787,0.00027730063,0.0002881474],"domain_scores_gemma":[0.9978925,0.00084166235,0.0004010656,0.00016866498,0.00053515786,0.00016096591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075948174,0.00015542113,0.00040354583,0.00007278675,0.0003104735,0.000035763547,0.00017554313,0.000034157172,0.000054332126],"category_scores_gemma":[0.0012995744,0.000099357676,0.00022982717,0.00031081372,0.00017541414,0.00013225878,0.000047840203,0.00058915955,0.0000014166025],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012024206,0.0019426644,0.0014999553,0.0008679179,0.00076067896,0.000098143144,0.0023978695,0.012595145,0.37308228,0.0043103267,0.033695936,0.55672485],"study_design_scores_gemma":[0.02162697,0.0031017852,0.00049055874,0.0008372071,0.0013043032,0.002067657,0.0014027639,0.3245122,0.06655718,0.011346593,0.5661921,0.0005606709],"about_ca_topic_score_codex":0.0000095613,"about_ca_topic_score_gemma":8.386242e-7,"teacher_disagreement_score":0.5561642,"about_ca_system_score_codex":0.00007478872,"about_ca_system_score_gemma":0.00031274898,"threshold_uncertainty_score":0.40516883},"labels":[],"label_agreement":null},{"id":"W3003953721","doi":"10.59275/j.melba.2021-8678","title":"A Heteroscedastic Uncertainty Model for Decoupling Sources of MRI Image Quality","year":2021,"lang":"en","type":"preprint","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; National Institute on Aging; National Institute for Health and Care Research; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Nvidia; F. Hoffmann-La Roche; Alzheimer's Society; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Computer science; Artificial intelligence; Probabilistic logic; Segmentation; Data mining; Machine learning; Heteroscedasticity; Uncertainty quantification; Robustness (evolution); Image quality; Noise (video); Quality (philosophy); Pattern recognition (psychology); Image (mathematics)","score_opus":0.02763975736512384,"score_gpt":0.3395162783419846,"score_spread":0.31187652097686075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003953721","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03811066,0.0014562254,0.95457286,0.004203389,0.0011178104,0.00042476732,0.000023690487,0.000076898345,0.000013724461],"genre_scores_gemma":[0.65700585,0.000076498036,0.34218112,0.00015644272,0.0004294853,0.000013923082,0.00003484571,0.000058671772,0.00004317655],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99496955,0.0007546973,0.0019348664,0.0005557297,0.0011206385,0.0006645288],"domain_scores_gemma":[0.9904662,0.0040079816,0.0035002728,0.0007394996,0.0010336442,0.00025240774],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.009861782,0.00050596625,0.0012644661,0.00041306834,0.0004987174,0.00032907093,0.003090968,0.00021865318,0.000009348427],"category_scores_gemma":[0.005727358,0.00036980913,0.0009103561,0.00033052405,0.0004817003,0.00041170628,0.0022527967,0.0028766422,4.3656237e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002215425,0.00010843486,0.0006433186,0.00077156455,0.00026740192,0.000011811836,0.0030458395,0.978115,0.0023837998,0.00029402334,0.00006899701,0.014068247],"study_design_scores_gemma":[0.0014136999,0.00014509069,0.00010878663,0.0007948451,0.00030001104,0.00012278985,0.00032122707,0.99163544,0.00024788536,0.004342117,0.00020345315,0.00036465356],"about_ca_topic_score_codex":0.00013419804,"about_ca_topic_score_gemma":0.000007096745,"teacher_disagreement_score":0.6188952,"about_ca_system_score_codex":0.00018149501,"about_ca_system_score_gemma":0.000711335,"threshold_uncertainty_score":0.99987537},"labels":[],"label_agreement":null},{"id":"W3005163827","doi":"10.59275/j.melba.2021-2dcc","title":"The Alzheimer's Disease Prediction Of Longitudinal Evolution (TADPOLE) Challenge: Results after 1 Year Follow-up","year":2021,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"EPSRC Centre for Doctoral Training in Medical Imaging; National Institutes of Health; Medical Research Council; Medical Delta; Direktoratet for internasjonalisering og kvalitetsutvikling i høgare utdanning; National Research Foundation Singapore; National Institute of Neurological Disorders and Stroke; National Institute for Health and Care Research; Alzheimer's Society; European Federation of Pharmaceutical Industries and Associations; National Research Foundation; Engineering and Physical Sciences Research Council; UK Research and Innovation; National Institute on Aging; Alzheimer's Association; National Institute of Biomedical Imaging and Bioengineering; Portland State University; University College London Hospitals NHS Foundation Trust; U.S. Department of Defense; European Commission; Alzheimer's Disease Neuroimaging Initiative; National Science Foundation","keywords":"Disease; Machine learning; Multivariate statistics; Artificial intelligence; Support vector machine; Medicine; Computer science; Physical medicine and rehabilitation; Internal medicine","score_opus":0.019024320391026656,"score_gpt":0.31339161860627607,"score_spread":0.29436729821524943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005163827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8023222,0.04731554,0.043147232,0.10288276,0.001815006,0.0010138901,0.00015153314,0.000063977124,0.001287867],"genre_scores_gemma":[0.9979885,0.0006947886,0.00017578065,0.00006501183,0.00047116802,0.000007837152,0.00004239616,0.00001846697,0.00053600786],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99780095,0.0003259057,0.00054665713,0.0001367689,0.0008895313,0.00030020002],"domain_scores_gemma":[0.99816495,0.00046872732,0.00030586647,0.00017904985,0.0006390432,0.00024233892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026883106,0.0001181195,0.0002177825,0.0001229324,0.00025961842,0.000031161493,0.00015267165,0.000032778127,0.00006988651],"category_scores_gemma":[0.0018853637,0.00006460266,0.00024007316,0.00023070257,0.0003264866,0.000109767156,0.0001007779,0.0006037925,0.0000047430035],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05472308,0.0017366692,0.66490453,0.0004860972,0.0027799043,0.00075568364,0.001629886,0.00006927717,0.008397558,0.0003919046,0.009331861,0.25479355],"study_design_scores_gemma":[0.01471018,0.002092492,0.90484196,0.0010407383,0.0026854342,0.00057298824,0.001463103,0.023128195,0.00096127595,0.0010892262,0.047241814,0.00017257257],"about_ca_topic_score_codex":0.000015426915,"about_ca_topic_score_gemma":0.0000029208352,"teacher_disagreement_score":0.254621,"about_ca_system_score_codex":0.00005718269,"about_ca_system_score_gemma":0.0002802954,"threshold_uncertainty_score":0.26344198},"labels":[],"label_agreement":null},{"id":"W3036790661","doi":"10.59275/j.melba.2020-48g7","title":"COVID-19 Image Data Collection: Prospective Predictions are the Future","year":2020,"lang":"en","type":"preprint","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":118,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; Université de Montréal","funders":"Compute Canada; Canadian Institute for Advanced Research","keywords":"Metadata; Coronavirus disease 2019 (COVID-19); Data collection; Computer science; Resource (disambiguation); Data science; Code (set theory); Intensive care unit; Medicine; Medical physics; Medical emergency; Information retrieval; Artificial intelligence; Intensive care medicine; World Wide Web; Disease; Pathology","score_opus":0.03905790863781753,"score_gpt":0.36977021492440615,"score_spread":0.3307123062865886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036790661","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006230681,0.0056238826,0.15662017,0.83290166,0.0023623058,0.0013669264,0.0002634614,0.00018932315,0.00004918189],"genre_scores_gemma":[0.6872095,0.00953888,0.032904524,0.2113638,0.053642754,0.00030648417,0.0027531283,0.0007582913,0.0015226547],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959441,0.00071710994,0.0010415806,0.0005832785,0.0012700747,0.00044389977],"domain_scores_gemma":[0.9930391,0.0025658275,0.0018163553,0.0011234606,0.0006204338,0.0008348483],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004512691,0.00045757438,0.0009080207,0.00037742205,0.0012163577,0.00020252494,0.0017159458,0.0002216547,0.00017311482],"category_scores_gemma":[0.017482536,0.0002569855,0.0004460812,0.0007705056,0.0008339927,0.00017404876,0.0018410855,0.006010998,0.000008304047],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025597105,0.00062142726,0.01668695,0.0022033183,0.0018722763,0.00044009264,0.004844059,0.0024927058,0.00061130105,0.000040428622,0.96003747,0.007590245],"study_design_scores_gemma":[0.003483721,0.00047990595,0.005006555,0.0009974821,0.0028486059,0.0024514918,0.0020679089,0.20433488,0.00002819263,0.0013043969,0.7766981,0.00029871694],"about_ca_topic_score_codex":0.0002509303,"about_ca_topic_score_gemma":0.000023118919,"teacher_disagreement_score":0.68658644,"about_ca_system_score_codex":0.00092894613,"about_ca_system_score_gemma":0.003226576,"threshold_uncertainty_score":0.99998826},"labels":[],"label_agreement":null},{"id":"W3124703593","doi":"10.59275/j.melba.2021-3581","title":"FlowReg: Fast Deformable Unsupervised Medical Image Registration using Optical Flow","year":2021,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research; York University; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; Alzheimer's Disease Neuroimaging Initiative; U.S. Department of Defense","keywords":"Artificial intelligence; Computer science; Image registration; Pixel; Computer vision; Neuroimaging; Affine transformation; Similarity (geometry); Optical flow; Pattern recognition (psychology); Deep learning; Image (mathematics); Mathematics","score_opus":0.014996950758150045,"score_gpt":0.30271601383979846,"score_spread":0.2877190630816484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124703593","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002192823,0.0005351202,0.9809822,0.01540259,0.0004471046,0.00012267174,0.0000020165485,0.00010373113,0.00021173136],"genre_scores_gemma":[0.0882025,0.00015006794,0.9087496,0.0020640553,0.00060792593,0.0000042570264,0.00003027774,0.00003588993,0.00015544923],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99620306,0.00048243455,0.00096375815,0.000237371,0.0016583365,0.0004550209],"domain_scores_gemma":[0.9974476,0.0007265291,0.0004604829,0.00033932214,0.0005534877,0.0004725896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048240996,0.00020297643,0.00035812243,0.00018953525,0.00037514349,0.00025641287,0.0011738138,0.0000984534,0.00020376247],"category_scores_gemma":[0.004325868,0.0001368691,0.0002062395,0.00056501187,0.00040712085,0.00092422735,0.0003446637,0.0010762914,0.000007028061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011600627,0.00035927127,0.00025831943,0.00018654502,0.00012499995,0.00074512174,0.0012472346,0.00075974636,0.11180194,0.00079750875,0.004149055,0.87945426],"study_design_scores_gemma":[0.0012898673,0.0001433996,0.000049330305,0.00019588604,0.00006426318,0.00311714,0.00018051469,0.9650901,0.026303109,0.00083711604,0.0025606926,0.00016860948],"about_ca_topic_score_codex":0.00002239384,"about_ca_topic_score_gemma":0.00000216523,"teacher_disagreement_score":0.9643303,"about_ca_system_score_codex":0.00011196425,"about_ca_system_score_gemma":0.00063565286,"threshold_uncertainty_score":0.558136},"labels":[],"label_agreement":null},{"id":"W3156072047","doi":"10.59275/j.melba.2021-df47","title":"Adversarial Robust Training of Deep Learning MRI Reconstruction Models","year":2021,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; National Institute of Arthritis and Musculoskeletal and Skin Diseases; University of California, San Francisco; York University","keywords":"Computer science; Artificial intelligence; Iterative reconstruction; Deep learning; Generalization; Machine learning; Workflow; Set (abstract data type); Fidelity; 3D reconstruction; Code (set theory); Pattern recognition (psychology); Computer vision; Mathematics","score_opus":0.013024758096579403,"score_gpt":0.23465879115824492,"score_spread":0.22163403306166551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156072047","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027447812,0.0035279936,0.96659386,0.00062076683,0.0009553058,0.00006944958,0.0000028089987,0.0000854007,0.00069661974],"genre_scores_gemma":[0.9625588,0.0004967222,0.03622645,0.000039363942,0.0005563212,0.000001678244,0.000013474813,0.000055154174,0.000052038104],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982752,0.00018092468,0.00069934945,0.00012265408,0.00036234118,0.0003595159],"domain_scores_gemma":[0.99866396,0.0005104619,0.0003616732,0.00011499037,0.00022002566,0.00012891163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013798428,0.00018894799,0.00040220833,0.00018990708,0.00024283491,0.000031978823,0.00023551665,0.00006133567,0.00006632713],"category_scores_gemma":[0.0005941556,0.00015117125,0.00021030309,0.00031592508,0.00018379584,0.00044766965,0.000052785148,0.0012239434,0.000001166388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006729867,0.000014462479,0.00021701476,0.00006743881,0.00009600516,0.000016057013,0.0016742243,0.73399895,0.010881313,0.000069547634,0.000024472882,0.2528732],"study_design_scores_gemma":[0.0012721533,0.00007179569,0.00004356822,0.00024005337,0.00014202786,0.0012329718,0.0033966736,0.9861519,0.0016914277,0.0015189659,0.004070223,0.0001682477],"about_ca_topic_score_codex":0.000006240089,"about_ca_topic_score_gemma":0.0000016898889,"teacher_disagreement_score":0.935111,"about_ca_system_score_codex":0.000068614514,"about_ca_system_score_gemma":0.00006091647,"threshold_uncertainty_score":0.6164584},"labels":[],"label_agreement":null},{"id":"W3157026294","doi":"10.59275/j.melba.2021-a6fd","title":"Recalibration of Aleatoric and EpistemicRegression Uncertainty in Medical Imaging","year":2021,"lang":"en","type":"preprint","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"European Regional Development Fund; European Commission","keywords":"Uncertainty quantification; Computer science; Regression; Inference; Calibration; Bayesian probability; Dropout (neural networks); Machine learning; Sensitivity analysis; Predictive inference; Artificial intelligence; Monte Carlo method; Bayesian inference; Econometrics; Statistics; Uncertainty analysis; Mathematics; Frequentist inference","score_opus":0.009173376499591528,"score_gpt":0.2787949627953283,"score_spread":0.26962158629573674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157026294","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034927223,0.010278289,0.9320402,0.021869835,0.0006696995,0.00014033473,0.0000025408415,0.000022401997,0.00004947114],"genre_scores_gemma":[0.9851345,0.0012841539,0.013131462,0.0002147055,0.00018932567,0.0000030722422,0.000013715112,0.000016205995,0.000012891185],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99713284,0.000484787,0.0010062491,0.00027734233,0.0008239878,0.00027477168],"domain_scores_gemma":[0.9973793,0.00074685045,0.0011651383,0.00026568078,0.00025079542,0.00019225065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003646031,0.00021869491,0.0005375674,0.0003314682,0.000115023766,0.00015911878,0.0011857728,0.00012864333,0.000018501327],"category_scores_gemma":[0.0015440944,0.00013926263,0.00013335444,0.000383417,0.0002587557,0.00031101616,0.0010666215,0.0016842444,1.7024291e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001586232,0.00022964364,0.02715387,0.001755206,0.00009248446,0.00034133805,0.0039453385,0.0022238765,0.0026960804,0.0015554334,0.00046053817,0.95938754],"study_design_scores_gemma":[0.0008618381,0.000067340174,0.0018674572,0.0040017483,0.000044790955,0.0009885037,0.00022321944,0.9846851,0.00023111225,0.0060552955,0.0007793911,0.00019417673],"about_ca_topic_score_codex":0.00012529585,"about_ca_topic_score_gemma":0.0000055536884,"teacher_disagreement_score":0.9824613,"about_ca_system_score_codex":0.00006683463,"about_ca_system_score_gemma":0.00061058253,"threshold_uncertainty_score":0.73172975},"labels":[],"label_agreement":null},{"id":"W4283735188","doi":"10.59275/j.melba.2022-7175","title":"A Differentially Private Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observations","year":2022,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Agence Nationale de la Recherche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Computer science; Differential privacy; Probabilistic logic; Realization (probability); Bayesian probability; Latent variable; Data mining; Code (set theory); Federated learning; Machine learning; Artificial intelligence; Statistics","score_opus":0.05570277757738716,"score_gpt":0.33660631870905666,"score_spread":0.2809035411316695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283735188","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04131713,0.00039965034,0.93017757,0.02678032,0.00037159104,0.00053887384,0.00032476455,0.000089870606,2.4746865e-7],"genre_scores_gemma":[0.66672575,0.00002740158,0.3328217,0.00021285404,0.000047905043,0.00004362895,0.00010054125,0.000018603421,0.0000016041787],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970907,0.0007160901,0.0008833448,0.0002838524,0.000594532,0.00043149188],"domain_scores_gemma":[0.993478,0.0031564073,0.0008977251,0.0021424142,0.00024535198,0.00008007163],"candidate_categories":["metaresearch","sts","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.007148353,0.00018708853,0.00035817697,0.000080577345,0.0013910484,0.00016125244,0.013432771,0.00005113321,0.000008466913],"category_scores_gemma":[0.054061674,0.00011258721,0.00017003558,0.00053068687,0.00032160137,0.00025838558,0.020003857,0.0012162434,2.1492059e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00134835,0.0026079118,0.0044987253,0.0016101905,0.0013888999,0.00005283511,0.0049229185,0.68699205,0.013304237,0.011020507,0.00810096,0.2641524],"study_design_scores_gemma":[0.00056048133,0.00016062323,0.00008320783,0.00008004119,0.000054989534,0.000115651696,0.000051380972,0.8898809,0.00008587835,0.107136324,0.0016829227,0.00010762379],"about_ca_topic_score_codex":0.000042035823,"about_ca_topic_score_gemma":0.000003128807,"teacher_disagreement_score":0.62540865,"about_ca_system_score_codex":0.00013482069,"about_ca_system_score_gemma":0.00015161665,"threshold_uncertainty_score":0.999909},"labels":[],"label_agreement":null},{"id":"W4362458848","doi":"10.59275/j.melba.2022-354b","title":"QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation – Analysis of Ranking Scores and Benchmarking Results","year":2022,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"National Institutes of Health; National Cancer Institute; Instituto Tecnológico de Costa Rica; Natural Sciences and Engineering Research Council of Canada; National Institute of Neurological Disorders and Stroke; Canadian Institute for Advanced Research","keywords":"Benchmarking; Segmentation; Computer science; Benchmark (surveying); Artificial intelligence; Machine learning; Task (project management); Ranking (information retrieval); Reliability (semiconductor); Data mining","score_opus":0.01864686215268765,"score_gpt":0.32309564876986147,"score_spread":0.30444878661717384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362458848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9580169,0.0023657694,0.006875873,0.031894714,0.00035027898,0.00037285083,0.000024329738,0.000025281379,0.000074008385],"genre_scores_gemma":[0.99618423,0.00027308642,0.0017556528,0.00133473,0.00024947576,0.000008127273,0.00013071905,0.000037588925,0.000026396245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99621254,0.00081842847,0.0012530406,0.00030842703,0.0010065136,0.00040106356],"domain_scores_gemma":[0.99577296,0.002545381,0.0011724345,0.00019626749,0.00011872284,0.00019424432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008495643,0.00024063404,0.0008211284,0.0012244545,0.00044098857,0.000042625405,0.00030181892,0.00003847337,0.00006551982],"category_scores_gemma":[0.003202766,0.00017448104,0.00028112595,0.0012487671,0.00028351755,0.00012174218,0.00017785268,0.0018355193,2.1845372e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013175489,0.0014800989,0.16897699,0.0008844918,0.003101543,0.00086255866,0.022291502,0.34172866,0.060879316,0.00035924008,0.0029632885,0.38329685],"study_design_scores_gemma":[0.006483148,0.0016076561,0.017544419,0.0006471961,0.0011021966,0.00044012192,0.002340989,0.9661822,0.00010696178,0.00014424234,0.0031842592,0.00021661306],"about_ca_topic_score_codex":0.00040065593,"about_ca_topic_score_gemma":0.000025198411,"teacher_disagreement_score":0.62445354,"about_ca_system_score_codex":0.00018702346,"about_ca_system_score_gemma":0.00013159527,"threshold_uncertainty_score":0.79745203},"labels":[],"label_agreement":null},{"id":"W4376880401","doi":"10.59275/j.melba.2023-7e96","title":"Multi-Scale Feature Fusion using Parallel-Attention Block for COVID-19 Chest X-ray Diagnosis","year":2023,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Robustness (evolution); Coronavirus disease 2019 (COVID-19); Fuse (electrical); Artificial intelligence; Feature (linguistics); Generalization; Data mining; Pattern recognition (psychology); Medicine; Mathematics; Pathology; Infectious disease (medical specialty); Disease","score_opus":0.04386742789201088,"score_gpt":0.37216416311223943,"score_spread":0.32829673522022856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376880401","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1984397,0.0019400056,0.3535276,0.44306332,0.0011829954,0.001494776,0.00005080842,0.00029576904,0.0000050143194],"genre_scores_gemma":[0.7604133,0.0021014956,0.1928658,0.03735729,0.004300467,0.00017586026,0.00049688667,0.00039994187,0.0018889465],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974216,0.00027202573,0.00070271775,0.0002991365,0.00072556396,0.0005789479],"domain_scores_gemma":[0.9953631,0.0028142591,0.0006999597,0.0002570634,0.00031263268,0.0005529806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043024155,0.00028996964,0.0005929629,0.00063105195,0.00075168855,0.00006974973,0.00034401525,0.00014691577,0.000044002314],"category_scores_gemma":[0.006638421,0.00019638447,0.0004951592,0.0007657535,0.00027469403,0.00014697212,0.00015405349,0.0009579767,0.000009015962],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004780165,0.0022681803,0.23779117,0.0045149466,0.0010398686,0.0004753287,0.0052077435,0.061762594,0.29569995,0.000012859565,0.264774,0.121673174],"study_design_scores_gemma":[0.008181299,0.00057830027,0.015881324,0.0008771331,0.001014313,0.00056872924,0.00057472556,0.5802435,0.00025477118,0.000067565474,0.39149004,0.00026828374],"about_ca_topic_score_codex":0.00013279215,"about_ca_topic_score_gemma":0.00001078606,"teacher_disagreement_score":0.56197363,"about_ca_system_score_codex":0.00032690755,"about_ca_system_score_gemma":0.00035663843,"threshold_uncertainty_score":0.8008326},"labels":[],"label_agreement":null},{"id":"W4377002285","doi":"10.59275/j.melba.2022-db5c","title":"Label fusion and training methods for reliable representation of inter-rater uncertainty","year":2023,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Craig H. Neilsen Foundation; Canada First Research Excellence Fund; Nvidia","keywords":"Segmentation; Artificial intelligence; Computer science; Ground truth; Machine learning; Task (project management); Pattern recognition (psychology)","score_opus":0.032162855398389124,"score_gpt":0.365834025024052,"score_spread":0.33367116962566284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377002285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07213165,0.0010245971,0.9223544,0.0038722556,0.00036178506,0.00011154045,0.000005345275,0.00007986374,0.00005855196],"genre_scores_gemma":[0.9303108,0.00058395404,0.0682943,0.00012877084,0.00032415532,0.000008154031,0.00004482636,0.000049097336,0.00025593725],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998875,0.00014032946,0.00049329764,0.00008814868,0.0001789569,0.00022423262],"domain_scores_gemma":[0.99824214,0.0012662035,0.0001891448,0.00008786358,0.00010929037,0.00010538183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037338275,0.000105075495,0.00031952126,0.00026006595,0.00011728703,0.000024481953,0.00015961453,0.000034644545,0.000016795102],"category_scores_gemma":[0.0015796839,0.00006696787,0.00011048224,0.00039462926,0.00013610061,0.000093851406,0.000044853037,0.0003392487,6.719109e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077503486,0.000018045766,0.0009422691,0.0002512965,0.00017511008,0.0000032694193,0.0024622881,0.012547393,0.08038973,0.000022664102,0.0027796817,0.9003307],"study_design_scores_gemma":[0.0008884206,0.00008500248,0.000094945746,0.00019074256,0.00015718957,0.000034504916,0.00081265083,0.98124075,0.0012586068,0.0010509645,0.014111368,0.00007483627],"about_ca_topic_score_codex":0.000031003514,"about_ca_topic_score_gemma":4.2332448e-7,"teacher_disagreement_score":0.9686934,"about_ca_system_score_codex":0.000018861796,"about_ca_system_score_gemma":0.00001766976,"threshold_uncertainty_score":0.27308705},"labels":[],"label_agreement":null},{"id":"W4377004088","doi":"10.59275/j.melba.2022-2d93","title":"Rethinking Generalization: The Impact of Annotation Style on Medical Image Segmentation","year":2022,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NeuroRx Research (Canada); McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Genentech; MedDay Pharmaceuticals; Royal Academy of Engineering; International Progressive MS Alliance; Compute Canada; Western Canada Research Grid; Canadian Institute for Advanced Research; Teva Pharmaceutical Industries; Biogen","keywords":"Annotation; Computer science; Context (archaeology); Segmentation; Generalization; Artificial intelligence; Machine learning; Style (visual arts); Ground truth; Automatic image annotation; Image (mathematics); Natural language processing; Image retrieval; Information retrieval; Mathematics; Geography","score_opus":0.013424928776439223,"score_gpt":0.33384529284453457,"score_spread":0.3204203640680953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377004088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7485507,0.0014445983,0.18443535,0.063624,0.00081049645,0.0006674146,0.000017890672,0.000058639584,0.00039090347],"genre_scores_gemma":[0.99475497,0.00012839958,0.0027819902,0.0014718222,0.00059154833,0.000010167501,0.00009895772,0.00004563849,0.00011649313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99618953,0.00082636427,0.00083121407,0.00015012208,0.0017109764,0.0002918118],"domain_scores_gemma":[0.99718904,0.0011787725,0.00095686544,0.0002049443,0.00026576148,0.00020458893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007355106,0.00018219333,0.00039086255,0.00029549567,0.00071834476,0.000036567093,0.00045546453,0.00004273121,0.00054564414],"category_scores_gemma":[0.0034293523,0.000095912634,0.0003541499,0.0005020382,0.00038312864,0.00011299658,0.00013734555,0.0019058317,0.0000014259085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007996956,0.0022193512,0.06173733,0.00054988806,0.0021167141,0.00046290117,0.033700194,0.14210358,0.1403581,0.0013800958,0.053284854,0.55409],"study_design_scores_gemma":[0.0048272144,0.0023940755,0.0063949716,0.00025875669,0.0003599918,0.0026482644,0.0010760345,0.9730359,0.00046620113,0.0011630222,0.007201214,0.0001743977],"about_ca_topic_score_codex":0.00015443403,"about_ca_topic_score_gemma":5.09462e-7,"teacher_disagreement_score":0.83093226,"about_ca_system_score_codex":0.00021679742,"about_ca_system_score_gemma":0.00034251984,"threshold_uncertainty_score":0.82799965},"labels":[],"label_agreement":null},{"id":"W4377004358","doi":"10.59275/j.melba.2022-a1cc","title":"Image quality assessment by overlapping task-specific and task-agnostic measures: application to prostate multiparametric MR images for cancer segmentation","year":2022,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; CRIS Cancer Foundation; University of Manchester; National Cancer Institute; University College London; National Institutes of Health; Wellcome / EPSRC Centre for Interventional and Surgical Sciences; Engineering and Physical Sciences Research Council; Prostate Cancer Foundation; University of Cambridge; Cancer Research UK; Knight Cancer Institute, Oregon Health and Science University; Oregon Health and Science University","keywords":"Task (project management); Computer science; Image quality; Quality (philosophy); Artificial intelligence; Segmentation; Image (mathematics)","score_opus":0.016699404896214097,"score_gpt":0.3522393019801811,"score_spread":0.33553989708396703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377004358","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10092634,0.004659513,0.8616635,0.030495225,0.00038370874,0.001662496,0.00013344146,0.000052988642,0.00002275045],"genre_scores_gemma":[0.9403094,0.000926034,0.05525534,0.0021724424,0.00045244227,0.00035066466,0.00026116066,0.000089762434,0.00018274187],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99678355,0.00047780827,0.0009116972,0.00034447166,0.0010259005,0.000456593],"domain_scores_gemma":[0.99669707,0.0015890588,0.0008348412,0.00019576824,0.00032191206,0.00036136134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006535632,0.00025280667,0.0005515207,0.0004226456,0.0008499187,0.00010220631,0.00028811817,0.000036150785,0.000032123222],"category_scores_gemma":[0.0022395928,0.00018709438,0.00017329626,0.0005567205,0.00022226582,0.00016392366,0.00016128071,0.0012404151,8.2869576e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001172044,0.00035587157,0.014454657,0.00037363876,0.00023453761,0.000011551929,0.0016213144,0.0041221487,0.58338666,0.000037488728,0.016670994,0.3775591],"study_design_scores_gemma":[0.009867566,0.0015564375,0.011311098,0.00030086635,0.0006869336,0.00051920896,0.0020560827,0.56795335,0.0009301468,0.00031920066,0.40397516,0.0005239626],"about_ca_topic_score_codex":0.00024728756,"about_ca_topic_score_gemma":9.942406e-7,"teacher_disagreement_score":0.83938307,"about_ca_system_score_codex":0.0004053439,"about_ca_system_score_gemma":0.0001666227,"threshold_uncertainty_score":0.76294875},"labels":[],"label_agreement":null},{"id":"W4386246031","doi":"10.59275/j.melba.2023-553a","title":"Weakly Supervised Intracranial Hemorrhage Segmentation using Head-Wise Gradient-Infused Self-Attention Maps from a Swin Transformer in Categorical Learning","year":2023,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Intracerebral and Subarachnoid Hemorrhage Research","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Segmentation; Artificial intelligence; Computer science; Deep learning; Categorical variable; Pattern recognition (psychology); Binary classification; Code (set theory); Machine learning","score_opus":0.019897732439585203,"score_gpt":0.31058978279320626,"score_spread":0.29069205035362106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386246031","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95192486,0.00037916037,0.039173715,0.007580855,0.00030652102,0.00048896205,0.000009184798,0.00010761673,0.000029149287],"genre_scores_gemma":[0.9869846,0.00014947748,0.011597921,0.00014679992,0.0006719668,0.000009236535,0.00024860792,0.00006457198,0.00012682639],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965562,0.0005197962,0.000963989,0.00025470043,0.0009845458,0.0007207347],"domain_scores_gemma":[0.998487,0.00058112916,0.00028774538,0.0001316262,0.00020213725,0.0003103947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003365948,0.0002671612,0.00056969345,0.0007572509,0.00040503393,0.00007264091,0.00025342836,0.00012926164,0.00013965307],"category_scores_gemma":[0.00063703157,0.00018361805,0.00029296576,0.0010203364,0.00014564276,0.0003134005,0.00004895523,0.0020763008,0.00002865811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033957565,0.00064380455,0.081846856,0.00056833506,0.0002229474,0.001898861,0.0054109585,0.0015500713,0.5336555,0.000018438488,0.00014013296,0.37064832],"study_design_scores_gemma":[0.006572607,0.0005501282,0.008714723,0.0001995495,0.0003001126,0.0011319035,0.0020431136,0.97890985,0.0008720905,0.0003056114,0.00019869351,0.00020161024],"about_ca_topic_score_codex":0.0006130896,"about_ca_topic_score_gemma":0.00001795802,"teacher_disagreement_score":0.9773598,"about_ca_system_score_codex":0.0003449901,"about_ca_system_score_gemma":0.00021126536,"threshold_uncertainty_score":0.90206087},"labels":[],"label_agreement":null},{"id":"W4388585137","doi":"10.59275/j.melba.2023-3d9d","title":"Towards Early Prediction of Human iPSC Reprogramming Success","year":2023,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Pluripotent Stem Cells Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Induced pluripotent stem cell; Reprogramming; Computer science; Artificial intelligence; Source code; Segmentation; Regenerative medicine; Computational biology; Machine learning; Biology; Stem cell; Embryonic stem cell; Cell; Cell biology; Operating system; Genetics","score_opus":0.01815780357043608,"score_gpt":0.3210128194884764,"score_spread":0.3028550159180403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388585137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9887137,0.00062050106,0.008845561,0.0013325475,0.00018232959,0.00014244541,0.000011338794,0.000019335785,0.00013226304],"genre_scores_gemma":[0.9986411,0.00016738573,0.00031338504,0.000022274415,0.00039000122,0.0000034683421,0.00007275737,0.000025296877,0.00036434783],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984369,0.00020586175,0.00045222306,0.0001365308,0.00047813504,0.00029031892],"domain_scores_gemma":[0.9990916,0.0000768173,0.00033490304,0.00017508212,0.00021228705,0.000109287226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031794328,0.00010360115,0.00018274927,0.00019155203,0.00019412498,0.000025530313,0.00041864603,0.00006141413,0.0000112488915],"category_scores_gemma":[0.0006289852,0.000070658454,0.00015762079,0.00028733697,0.0002357484,0.000010489278,0.00019157577,0.00037312476,0.000002300419],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022983614,0.0000642045,0.031391013,0.00010645846,0.00012819053,0.000013729487,0.00023120003,0.00027709478,0.92400324,0.000011449177,0.0013197516,0.04222381],"study_design_scores_gemma":[0.011758169,0.010459163,0.21557695,0.0010248085,0.0006459801,0.0012226768,0.0015498667,0.10372487,0.4449616,0.0012266417,0.20691776,0.00093150005],"about_ca_topic_score_codex":0.000091312024,"about_ca_topic_score_gemma":0.0000017580644,"teacher_disagreement_score":0.47904164,"about_ca_system_score_codex":0.000016138503,"about_ca_system_score_gemma":0.000061991814,"threshold_uncertainty_score":0.2881368},"labels":[],"label_agreement":null},{"id":"W4389481639","doi":"10.59275/j.melba.2023-g3f8","title":"Shape-aware Segmentation of the Placenta in BOLD Fetal MRI Time Series","year":2023,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Pregnancy and preeclampsia studies","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; Boston Children's Hospital; National Institutes of Health; National Science Foundation","keywords":"Segmentation; Placenta; Artificial intelligence; Fetus; Pattern recognition (psychology); Hyperoxia; Computer science; Medicine; Pregnancy; Biology; Internal medicine","score_opus":0.012202823395899884,"score_gpt":0.2869925574705007,"score_spread":0.2747897340746008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389481639","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9050076,0.004337803,0.002686543,0.08582391,0.00073365925,0.00073945214,0.000030530722,0.00007621304,0.00056431064],"genre_scores_gemma":[0.9980996,0.00038981385,0.0003998012,0.00023478972,0.0001563832,0.0000037031523,0.000018540988,0.000017807959,0.00067951065],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99875736,0.0001775649,0.00041368217,0.00007264778,0.00038160963,0.00019711505],"domain_scores_gemma":[0.9991003,0.00038391142,0.00030291325,0.00009988745,0.00006276327,0.000050178223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001465632,0.00010164044,0.00026953063,0.00014513725,0.00015648485,0.000008392329,0.00018657182,0.00003057287,0.000055665074],"category_scores_gemma":[0.00046079332,0.000052624353,0.00013310238,0.00037381102,0.00023551521,0.00010521447,0.00011957078,0.0004930731,0.0000054396105],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004650074,0.00044489346,0.71755415,0.0013521885,0.000869468,0.00016377654,0.017288534,0.0018439622,0.08374228,0.00009119049,0.021707095,0.15029237],"study_design_scores_gemma":[0.0203315,0.0024098956,0.46415663,0.0089426255,0.0014908949,0.0028514692,0.011026438,0.43017328,0.01661613,0.002236002,0.03912071,0.0006444088],"about_ca_topic_score_codex":0.000021568672,"about_ca_topic_score_gemma":0.0000036656172,"teacher_disagreement_score":0.42832932,"about_ca_system_score_codex":0.000037623704,"about_ca_system_score_gemma":0.000060500282,"threshold_uncertainty_score":0.21459588},"labels":[],"label_agreement":null},{"id":"W4390873488","doi":"10.59275/j.melba.2024-b87a","title":"Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET","year":2024,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; F. Hoffmann-La Roche; Agence Nationale de la Recherche; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; Grand Équipement National De Calcul Intensif; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Alzheimer's Association","keywords":"Autoencoder; Artificial intelligence; Computer science; Generative model; Anomaly detection; Deep learning; Pattern recognition (psychology); Ground truth; Anomaly (physics); Image (mathematics); Generative grammar; Computer vision","score_opus":0.016223693342653178,"score_gpt":0.29138998094582963,"score_spread":0.27516628760317646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390873488","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012488444,0.0004949546,0.9777557,0.008322995,0.00035849496,0.00052414945,0.0000039311335,0.000027674861,0.000023644161],"genre_scores_gemma":[0.7832595,0.000017713392,0.21616165,0.00014634292,0.0003550623,0.00003253474,0.000004159449,0.000014885792,0.000008134419],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981212,0.00047762034,0.0004386978,0.00021060322,0.00055929675,0.00019257172],"domain_scores_gemma":[0.9979711,0.0005806987,0.00035361046,0.00014378653,0.0008566767,0.00009411866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062662284,0.00012901147,0.00020436014,0.00026423452,0.00024870178,0.000108664,0.00029132765,0.000025404968,0.0000040136474],"category_scores_gemma":[0.00051450374,0.00008211661,0.00010102219,0.00044301053,0.00009359051,0.00062911026,0.000042605538,0.00024825925,8.1407063e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017329153,0.000024966528,0.000009621927,0.000037296126,0.000075672455,8.053549e-7,0.0007390209,0.13178155,0.0727033,0.00018707076,0.0001193962,0.794148],"study_design_scores_gemma":[0.0006084536,0.00063829386,0.000044336502,0.00008159562,0.00016235124,0.00026789843,0.00012562635,0.9878122,0.0052517746,0.004303466,0.00061162043,0.000092363836],"about_ca_topic_score_codex":0.000039421906,"about_ca_topic_score_gemma":0.000018164086,"teacher_disagreement_score":0.85603064,"about_ca_system_score_codex":0.00013064551,"about_ca_system_score_gemma":0.00018378222,"threshold_uncertainty_score":0.33486181},"labels":[],"label_agreement":null},{"id":"W4393905672","doi":"10.59275/j.melba.2024-267f","title":"Disentangling Hippocampal Shape Variations: A Study of Neurological Disorders Using Mesh Variational Autoencoder with Contrastive Learning","year":2024,"lang":"en","type":"preprint","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University; University of Alberta","funders":"Canadian Institutes of Health Research; Women and Children's Health Research Institute; Canada Research Chairs; Children's Health Research Institute","keywords":"Autoencoder; Hippocampal formation; Neuroscience; Psychology; Graph; Artificial intelligence; Pattern recognition (psychology); Medicine; Computer science; Deep learning; Theoretical computer science","score_opus":0.03634657959718149,"score_gpt":0.3565907821513885,"score_spread":0.32024420255420705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393905672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29964045,0.00073712977,0.6908331,0.0069732955,0.00025680897,0.0013403934,0.00002688823,0.00015380498,0.00003811158],"genre_scores_gemma":[0.9544595,0.00009595575,0.044718154,0.00015062146,0.0003845046,0.000036671074,0.0000493931,0.000082346945,0.000022856446],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971056,0.00038249049,0.0009996537,0.00038648746,0.00080042356,0.00032532646],"domain_scores_gemma":[0.9967642,0.0011692977,0.0012697615,0.00023716058,0.0003945318,0.00016506978],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0015113096,0.00035704943,0.00075010676,0.00040438276,0.00033044338,0.000058794332,0.00035651255,0.000106025545,0.00003248669],"category_scores_gemma":[0.0010828619,0.00022121058,0.00025815258,0.00040149284,0.00032033536,0.00007217776,0.00047986954,0.0035897198,5.617638e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007967994,0.0065814494,0.3193867,0.0018935715,0.0038132155,0.00043751847,0.011802328,0.55255973,0.0038363927,0.0022347374,0.00030233606,0.089184046],"study_design_scores_gemma":[0.001969551,0.0017679501,0.0044382634,0.00068369514,0.0019197667,0.000526752,0.000569636,0.98062545,0.000007673991,0.0068234485,0.00046384239,0.00020394799],"about_ca_topic_score_codex":0.000039409897,"about_ca_topic_score_gemma":0.0000019451907,"teacher_disagreement_score":0.6548191,"about_ca_system_score_codex":0.00009609218,"about_ca_system_score_gemma":0.00033031567,"threshold_uncertainty_score":0.998709},"labels":[],"label_agreement":null},{"id":"W4395067675","doi":"10.59275/j.melba.2024-4dg2","title":"A voxel-level approach to brain age prediction: A method to assess regional brain aging","year":2024,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hotchkiss Brain Institute; Ontario Brain Institute; University of Calgary","funders":"","keywords":"Brain aging; Voxel; Aging brain; Computer science; Psychology; Artificial intelligence; Neuroscience; Cognition","score_opus":0.10091776870353689,"score_gpt":0.3692185245557048,"score_spread":0.26830075585216795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395067675","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024850063,0.0002984795,0.7251122,0.2705115,0.0007207461,0.00028935264,0.000029752291,0.00011559588,0.00043733363],"genre_scores_gemma":[0.743803,0.000030916573,0.15694302,0.08738341,0.0050277784,0.00010483329,0.000022551902,0.00021877003,0.006465722],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996357,0.0009987145,0.0005824143,0.00047554146,0.0010934583,0.00049282174],"domain_scores_gemma":[0.9782468,0.020920806,0.0001814717,0.00019146546,0.00013206499,0.0003273963],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0077065295,0.00026500665,0.0003842584,0.00066795584,0.00060954737,0.00023702804,0.0006241471,0.00005025982,0.0000214481],"category_scores_gemma":[0.025679896,0.00017948891,0.00025109798,0.0011945775,0.00020732758,0.00030699468,0.00032040878,0.0011836769,0.000018136876],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007081318,0.00033240917,0.00036928663,0.00036664712,0.00028047326,0.0002698354,0.008411454,0.014429895,0.38087106,0.0050033806,0.42450753,0.1644499],"study_design_scores_gemma":[0.00083838066,0.00055179856,0.0009947913,0.00046282145,0.000102603706,0.003396595,0.00056120683,0.20366377,0.0018161346,0.00225615,0.78504527,0.00031046337],"about_ca_topic_score_codex":0.00003162721,"about_ca_topic_score_gemma":0.0000019954587,"teacher_disagreement_score":0.741318,"about_ca_system_score_codex":0.00018245087,"about_ca_system_score_gemma":0.0001590516,"threshold_uncertainty_score":0.9825272},"labels":[],"label_agreement":null},{"id":"W4400121095","doi":"10.59275/j.melba.2024-151b","title":"Impact of Initialization on Intra-subject Pediatric Brain MR Image Registration: A Comparative Analysis between SyN ANTs and Deep Learning-Based Approaches","year":2024,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Polytechnique Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"","keywords":"Initialization; Image registration; Artificial intelligence; Computer science; Subject (documents); Subject matter; Computer vision; Deep learning; Image (mathematics); Medical physics; Psychology; Medicine; Library science; Curriculum","score_opus":0.03619910164753889,"score_gpt":0.3430835035040612,"score_spread":0.3068844018565223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400121095","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07390275,0.0008678368,0.92171276,0.0032177207,0.000036064288,0.00015869756,0.0000061040196,0.00005211174,0.000045954173],"genre_scores_gemma":[0.9895644,0.000050973093,0.010048039,0.000042151856,0.00023166637,0.0000044949393,0.000036773716,0.000012179416,0.000009311977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981479,0.0004542578,0.0005562108,0.00022299853,0.0004055627,0.00021307265],"domain_scores_gemma":[0.99650437,0.0024841628,0.0005916346,0.00016876582,0.00012732457,0.00012376827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016075269,0.00017147067,0.00037164235,0.00057412306,0.00024020397,0.0001402419,0.00041897665,0.00003947229,0.000006020286],"category_scores_gemma":[0.00044530007,0.000111995985,0.00021261262,0.0018711542,0.00020884114,0.00035721168,0.00005456295,0.00065178063,0.0000011084693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047568954,0.00040742682,0.099346526,0.00039951995,0.001975313,0.000056837787,0.0066873655,0.6642432,0.0037065495,0.003227077,0.0007803085,0.21869417],"study_design_scores_gemma":[0.00039973675,0.0005486896,0.015382705,0.00004819522,0.0003808247,0.00003866846,0.000045568195,0.98199975,0.00013214152,0.00066487415,0.00024079929,0.00011806711],"about_ca_topic_score_codex":0.000013852279,"about_ca_topic_score_gemma":0.0000016448661,"teacher_disagreement_score":0.91566163,"about_ca_system_score_codex":0.00006149748,"about_ca_system_score_gemma":0.00010100358,"threshold_uncertainty_score":0.45670637},"labels":[],"label_agreement":null},{"id":"W4400480052","doi":"10.59275/j.melba.2024-3d4e","title":"Automatic rating of incomplete hippocampal inversions evaluated across multiple cohorts","year":2024,"lang":"en","type":"preprint","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Toronto","funders":"National Institute of Child Health and Human Development; National Health and Medical Research Council; Medical Research Council; Fédération pour la Recherche sur le Cerveau; Centre Hospitalier Universitaire Vaudois; Université de Lausanne; Hôpitaux Universitaires de Genève; Fondation pour la Recherche Médicale; National Natural Science Foundation of China; Mission Interministérielle de Lutte Contre les Drogues et les Conduites Addictives; Science Foundation Ireland; École Polytechnique Fédérale de Lausanne; Agence Nationale de la Recherche; European Commission; Institut national de recherche en informatique et en automatique (INRIA); Deutsche Forschungsgemeinschaft; Université de Genève; King's College London; Bundesministerium für Bildung und Forschung; National Institute for Health and Care Research; National Institutes of Health; Fondation de l'Avenir pour la Recherche Médicale Appliquée; Institut National de la Santé et de la Recherche Médicale; University of Oxford","keywords":"Artificial intelligence; Machine learning; Population; Regression; Cohort; Generalization; Computer science; Psychology; Medicine; Pathology; Mathematics","score_opus":0.044710661650761055,"score_gpt":0.3432172790349323,"score_spread":0.2985066173841713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400480052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96135753,0.0012518356,0.0085854195,0.025001546,0.0028586255,0.0006187049,0.00013369514,0.00013129332,0.000061371924],"genre_scores_gemma":[0.99741536,0.00005216071,0.0013390714,0.0006430431,0.00041689907,0.000013200643,0.000014175124,0.000057444497,0.000048634203],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958175,0.0010298456,0.001113969,0.00037532454,0.0012224449,0.0004409315],"domain_scores_gemma":[0.97838897,0.019455824,0.0014101985,0.00028242695,0.00031398848,0.00014858117],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00601693,0.0003401269,0.0007724451,0.00033049274,0.0006349665,0.0000999423,0.00076240255,0.0001078713,0.000053980377],"category_scores_gemma":[0.060654223,0.00022516437,0.0004333049,0.00044372876,0.00082749175,0.00009703994,0.0021025098,0.0027991517,0.000009748034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001960142,0.0010875838,0.027059162,0.008785707,0.0022226009,0.00045643756,0.03615317,0.10258713,0.5592791,0.0003086014,0.030467818,0.22963256],"study_design_scores_gemma":[0.0011552031,0.00024815573,0.0009294696,0.0015654087,0.00032966072,0.00041223242,0.0007610642,0.9832288,0.0029017024,0.006247495,0.0019746698,0.0002461478],"about_ca_topic_score_codex":0.00012737345,"about_ca_topic_score_gemma":0.000007955327,"teacher_disagreement_score":0.88064164,"about_ca_system_score_codex":0.00017898054,"about_ca_system_score_gemma":0.0003082223,"threshold_uncertainty_score":0.9995014},"labels":[],"label_agreement":null},{"id":"W4406412026","doi":"10.59275/j.melba.2024-24gc","title":"Finding Reproducible and Prognostic Radiomic Features in Variable Slice Thickness Contrast Enhanced CT of Colorectal Liver Metastases","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; National Institutes of Health","keywords":"Reproducibility; Medicine; Radiology; Thresholding; Feature (linguistics); Artificial intelligence; Nuclear medicine; Computer science; Mathematics; Statistics; Image (mathematics)","score_opus":0.007204905557761505,"score_gpt":0.28794906708576895,"score_spread":0.28074416152800746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406412026","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9152972,0.010212732,0.06582785,0.007239146,0.00044600313,0.0005955911,0.000008305343,0.000032773023,0.00034038143],"genre_scores_gemma":[0.98785454,0.00042571555,0.0108352285,0.00044663963,0.00014013177,0.000007770461,0.000017855575,0.000028218483,0.00024392465],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977161,0.00039236477,0.00081684615,0.00027131508,0.0004186754,0.0003846513],"domain_scores_gemma":[0.9965355,0.0023625721,0.0005507876,0.00018553965,0.00020858871,0.00015703718],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005757206,0.00021857493,0.0007774492,0.0005731766,0.00022424839,0.000032899643,0.00026634822,0.0000519127,0.00003050342],"category_scores_gemma":[0.0090590315,0.00014308156,0.00013635056,0.0006357897,0.0005871045,0.00013066441,0.00011486873,0.0014753548,3.9040307e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0067049195,0.0012982503,0.23734994,0.0036471717,0.0015637759,0.0006882088,0.0048027486,0.0036139677,0.57322747,0.0019003291,0.0042925533,0.16091067],"study_design_scores_gemma":[0.042107247,0.003320006,0.2565179,0.014677446,0.0057684868,0.023694847,0.0031832492,0.5692147,0.04923361,0.0029009671,0.028122343,0.001259215],"about_ca_topic_score_codex":0.00026085967,"about_ca_topic_score_gemma":0.0000033747203,"teacher_disagreement_score":0.56560075,"about_ca_system_score_codex":0.00007624274,"about_ca_system_score_gemma":0.0003091069,"threshold_uncertainty_score":0.9992881},"labels":[],"label_agreement":null},{"id":"W4408171770","doi":"10.59275/j.melba.2025-bea1","title":"Analysis of the BraTS 2023 Intracranial Meningioma Segmentation Challenge","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Meningioma and schwannoma management","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Toronto; McGill University; University of Ottawa; Montreal Neurological Institute and Hospital","funders":"","keywords":"Meningioma; Medicine; Radiology","score_opus":0.011677306087870763,"score_gpt":0.3034014316426765,"score_spread":0.29172412555480576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408171770","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8858108,0.0015940195,0.072180815,0.03812278,0.00063491374,0.00041027786,0.0000063720627,0.00001961311,0.0012204136],"genre_scores_gemma":[0.9977266,0.000031503856,0.0012842153,0.00018935709,0.00013836412,0.0000031237291,0.000014063084,0.0000091948605,0.0006035826],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982852,0.00022814379,0.0006556799,0.00010758274,0.0005279246,0.00019549785],"domain_scores_gemma":[0.9986388,0.00038158256,0.0005432689,0.00018900727,0.00017442596,0.00007290843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022474357,0.0001230407,0.00041251152,0.00059273036,0.00020771998,0.000020719674,0.0002910785,0.000037190366,0.00008991465],"category_scores_gemma":[0.0005485884,0.00006483349,0.00038244826,0.0011585085,0.00017090328,0.00006699328,0.00010873303,0.00042045594,9.1707955e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0057557053,0.0015473848,0.17248839,0.0013690697,0.025137816,0.00054543256,0.008379703,0.006349354,0.1463559,0.002570324,0.010850254,0.6186507],"study_design_scores_gemma":[0.010279906,0.0015023794,0.16911365,0.0012656271,0.028915947,0.00075199717,0.0038177497,0.7576847,0.0034145063,0.001493323,0.021380678,0.00037953185],"about_ca_topic_score_codex":0.000046077326,"about_ca_topic_score_gemma":0.0000035536955,"teacher_disagreement_score":0.7513354,"about_ca_system_score_codex":0.00006107383,"about_ca_system_score_gemma":0.00007546814,"threshold_uncertainty_score":0.2643833},"labels":[],"label_agreement":null},{"id":"W4409687339","doi":"10.59275/j.melba.2025-c1d9","title":"GeoLS: an Intensity-based, Geodesic Soft Labeling for Image Segmentation","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Digital Image Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer vision; Segmentation; Artificial intelligence; Intensity (physics); Geodesic; Computer science; Image segmentation; Image (mathematics); Mathematics; Physics; Geometry; Optics","score_opus":0.012982768790405311,"score_gpt":0.3178742906932374,"score_spread":0.3048915219028321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409687339","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022253706,0.00053984526,0.9860309,0.010476743,0.00026905516,0.000215157,0.0000027609742,0.00018072878,0.000059455087],"genre_scores_gemma":[0.2627817,0.0000121943995,0.73464656,0.0022836355,0.0001254275,0.000012395775,0.000017472625,0.000022926144,0.000097704295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985505,0.000118772296,0.0005076391,0.00019019369,0.00032423617,0.00030867648],"domain_scores_gemma":[0.99794775,0.00068623846,0.00044067873,0.00022188445,0.00060327904,0.000100183344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032306497,0.0001599277,0.00025024195,0.0003569004,0.0003574322,0.0004563604,0.0011033041,0.00003690429,0.0000020579919],"category_scores_gemma":[0.0013826705,0.00011211855,0.00013105899,0.00037782083,0.00021908992,0.0012863349,0.00017735237,0.00042459613,0.0000010241645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002708567,0.00022140692,0.0005423191,0.00026056985,0.00007014731,0.000016053262,0.00047826054,0.0007645815,0.05172096,0.00086952455,0.003289079,0.94149625],"study_design_scores_gemma":[0.0010413763,0.00031897932,0.000043290533,0.00032044674,0.000074106305,0.00009406867,0.00008054056,0.95514727,0.015424857,0.01981831,0.0074862945,0.00015045796],"about_ca_topic_score_codex":0.000016670945,"about_ca_topic_score_gemma":7.1315225e-7,"teacher_disagreement_score":0.9543827,"about_ca_system_score_codex":0.000075556345,"about_ca_system_score_gemma":0.00018748049,"threshold_uncertainty_score":0.45720616},"labels":[],"label_agreement":null},{"id":"W4411667236","doi":"10.59275/j.melba.2025-9bd3","title":"The Brain Tumor Segmentation (BraTS-METS) Challenge 2023: Brain Metastasis Segmentation on Pre-treatment MRI","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Hospital for Sick Children; SickKids Foundation; Montreal Neurological Institute and Hospital; University of Toronto; Windsor Regional Hospital; University of Calgary; McGill University; Centre Hospitalier de l’Université de Montréal; Queen's University","funders":"National Cancer Institute; National Institutes of Health; Children's Hospital of Philadelphia; Yale University","keywords":"Segmentation; Brain metastasis; Medicine; Magnetic resonance imaging; Internal medicine; Metastasis; Artificial intelligence; Computer science; Radiology; Cancer","score_opus":0.010862005629949899,"score_gpt":0.32969527209675975,"score_spread":0.3188332664668099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411667236","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10182033,0.008060335,0.20878668,0.67633575,0.0018674578,0.0017855996,0.000021305828,0.00012450517,0.0011980138],"genre_scores_gemma":[0.9454589,0.0033750958,0.01621143,0.021537773,0.002016695,0.00013180755,0.00025153355,0.00017717638,0.010839613],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967125,0.0007504969,0.00093252934,0.00027297554,0.0008326257,0.0004988455],"domain_scores_gemma":[0.994681,0.0038644471,0.0007083669,0.00029756277,0.00020007369,0.0002485419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050252085,0.00032728215,0.0005338574,0.0003986081,0.0009096945,0.00013415342,0.00037858626,0.00005638964,0.000067894354],"category_scores_gemma":[0.0033661716,0.00017127715,0.00035429187,0.0004588287,0.00038782076,0.00014647488,0.00008172213,0.0011602226,0.000008580247],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024622446,0.0006734748,0.00271515,0.0002279958,0.0012943939,0.00010375802,0.0019017493,0.0023743138,0.0235697,0.0007959164,0.038307145,0.9255742],"study_design_scores_gemma":[0.016173916,0.0050715315,0.003936211,0.0013963671,0.0020129129,0.0009960756,0.0035922334,0.364539,0.0049083335,0.002256654,0.594613,0.0005037655],"about_ca_topic_score_codex":0.00011758434,"about_ca_topic_score_gemma":0.000008861673,"teacher_disagreement_score":0.9250704,"about_ca_system_score_codex":0.0003730901,"about_ca_system_score_gemma":0.0002591552,"threshold_uncertainty_score":0.6996727},"labels":[],"label_agreement":null},{"id":"W4411696885","doi":"10.59275/j.melba.2025-f6fg","title":"BraTS-PEDs: Results of the Multi-Consortium International Pediatric Brain Tumor Segmentation Challenge 2023","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Medicine","score_opus":0.012051860635160963,"score_gpt":0.3193921706241968,"score_spread":0.30734030998903583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411696885","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3587144,0.00639838,0.15265097,0.47276273,0.0059644696,0.0012705614,0.00005184696,0.00009504835,0.0020916073],"genre_scores_gemma":[0.98727185,0.00043619025,0.0060687857,0.0028052973,0.0009404466,0.0000067171636,0.000036634352,0.00003628379,0.0023977729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997333,0.00035122252,0.0011012736,0.00018817189,0.0007314901,0.00029484273],"domain_scores_gemma":[0.99696773,0.0012954456,0.0010237243,0.00023701672,0.00033464597,0.00014145694],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0041352455,0.00019212245,0.0004115013,0.0004232266,0.00025245477,0.000035204062,0.0005926751,0.000055571894,0.000041481584],"category_scores_gemma":[0.008598542,0.000107922475,0.00030836632,0.00050847494,0.00035805858,0.000115062154,0.00017951072,0.0013749142,0.0000023575458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008990658,0.0034372758,0.28966853,0.0022518924,0.0024654781,0.00025941513,0.009244634,0.006394657,0.085742764,0.0010638696,0.12994,0.46054083],"study_design_scores_gemma":[0.032342575,0.00095464726,0.056540474,0.0018539059,0.0018590846,0.0012552524,0.00225061,0.7034034,0.002189512,0.00090843806,0.1959622,0.00047990718],"about_ca_topic_score_codex":0.00009029241,"about_ca_topic_score_gemma":0.00000358156,"teacher_disagreement_score":0.6970087,"about_ca_system_score_codex":0.000102999045,"about_ca_system_score_gemma":0.0002859637,"threshold_uncertainty_score":0.99975246},"labels":[],"label_agreement":null},{"id":"W4416054896","doi":"10.59275/j.melba.2025-d1g3","title":"Investigating Demographic Bias in Brain MRI Segmentation: A Comparative Study of Deep-Learning and Non-Deep-Learning Methods","year":2025,"lang":"en","type":"preprint","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; McDonnell Center for Systems Neuroscience; National Institutes of Health","keywords":"Segmentation; Metric (unit); Scale-space segmentation; Pattern recognition (psychology); Image segmentation; Field (mathematics)","score_opus":0.03975856399701808,"score_gpt":0.39768339274451264,"score_spread":0.35792482874749454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416054896","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10941187,0.002318716,0.8838187,0.003305891,0.00022033509,0.00081471045,0.0000012073177,0.00005956954,0.0000489981],"genre_scores_gemma":[0.6607477,0.00022326484,0.33865842,0.0001406148,0.000115658884,0.000045505512,0.000011960413,0.000023666704,0.000033160777],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99341667,0.0033693684,0.0015767027,0.0005306837,0.00066174095,0.0004448112],"domain_scores_gemma":[0.9891569,0.0073724934,0.0026076408,0.00032346224,0.0003342431,0.00020524526],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0077475654,0.00042040384,0.000993389,0.0009899376,0.00057658367,0.00015474329,0.0013384763,0.00012078409,0.0000038949415],"category_scores_gemma":[0.0020365845,0.00032863114,0.00018600043,0.0015840747,0.00040705304,0.00030381628,0.0016681799,0.0043448987,3.180447e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009756805,0.00038629764,0.08879781,0.00043403608,0.0004067424,0.000018598626,0.042512897,0.45747533,0.0037781629,0.00023449009,0.000045611156,0.40581244],"study_design_scores_gemma":[0.0016920317,0.0004947281,0.005409052,0.0006955546,0.00014439155,0.00007327692,0.0046546455,0.98228264,0.00014237338,0.0035140256,0.00060931174,0.00028795938],"about_ca_topic_score_codex":0.00008132483,"about_ca_topic_score_gemma":0.000024797368,"teacher_disagreement_score":0.5513359,"about_ca_system_score_codex":0.000096338124,"about_ca_system_score_gemma":0.00012368264,"threshold_uncertainty_score":0.99991655},"labels":[],"label_agreement":null},{"id":"W4417539435","doi":"10.59275/j.melba.2025-6838","title":"Exploring Fairness and Performance Drivers Across State-of-the-Art Pulmonary Nodule Detection Algorithms","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Lung Cancer Diagnosis and Treatment","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Medical Research Council; Stand Up To Cancer; CRUK Lung Cancer Centre of Excellence; UK Regenerative Medicine Platform; University College London; National Institute for Health and Care Research; Cancer Research UK; LUNGevity Foundation; Wellcome Trust; F. Hoffmann-La Roche; Microsoft Research; University College London Hospitals NHS Foundation Trust; Rosetrees Trust; Roy Castle Lung Cancer Foundation; Gilead Sciences; American Association for Cancer Research; AstraZeneca; GlaxoSmithKline","keywords":"Lung cancer screening; Nodule (geology); Discriminative model; National Lung Screening Trial; Lung cancer; Asymptomatic; Computed tomography; Cancer detection","score_opus":0.017400013039780858,"score_gpt":0.2909937764071602,"score_spread":0.27359376336737934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417539435","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98127633,0.001154723,0.011452624,0.0052950215,0.00056160986,0.00019223179,0.0000036096228,0.000012929303,0.000050933824],"genre_scores_gemma":[0.99814504,0.0010307201,0.00039635025,0.000114014976,0.00009810831,0.000009522493,0.000002397719,0.000012377648,0.00019148435],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990413,0.00006222598,0.0003238086,0.00009859621,0.0002783438,0.00019568639],"domain_scores_gemma":[0.99925107,0.00020793607,0.00023874045,0.00011157447,0.000117301475,0.00007337389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008386704,0.00010846659,0.00023789844,0.000093870345,0.00028185133,0.000016513397,0.00011858766,0.000018492254,0.000004045616],"category_scores_gemma":[0.00014085174,0.000058553545,0.000110539564,0.00023388959,0.00021875053,0.00015564602,0.000088607834,0.00039616445,6.132209e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048197474,0.00012860261,0.15406786,0.00033152616,0.00019730206,0.00001306104,0.0008890523,0.0002675211,0.0034213797,0.0000025895727,0.00008185546,0.8401173],"study_design_scores_gemma":[0.00825535,0.0015552068,0.684148,0.003914193,0.0011728206,0.0012472693,0.001498606,0.20464422,0.059832778,0.00020871477,0.033240408,0.00028240308],"about_ca_topic_score_codex":0.00004518364,"about_ca_topic_score_gemma":0.0000033081244,"teacher_disagreement_score":0.83983487,"about_ca_system_score_codex":0.00012445298,"about_ca_system_score_gemma":0.000058057078,"threshold_uncertainty_score":0.23877442},"labels":[],"label_agreement":null},{"id":"W7124836711","doi":"10.59275/j.melba.2025-f593","title":"SurgiSR4K: A High‑Resolution Endoscopic Video Dataset for Robotic-Assisted Minimally Invasive Procedures","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Usability; CLARITY; Invasive surgery; Visualization; Monocular; Minimally invasive procedures","score_opus":0.02089766755471499,"score_gpt":0.3272262943528538,"score_spread":0.30632862679813877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124836711","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3625271,0.0074018906,0.5027168,0.1202964,0.0024352742,0.0032664558,0.0003179702,0.00022044826,0.0008176962],"genre_scores_gemma":[0.9919661,0.00007213002,0.0051653804,0.0015902952,0.0002971662,0.000012308195,0.00063251954,0.000021833857,0.00024226641],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983391,0.0001560429,0.00066634297,0.00015979634,0.00035832377,0.00032040026],"domain_scores_gemma":[0.9955199,0.0034934087,0.00041109463,0.0001362291,0.00026688995,0.00017248484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017074711,0.00016570087,0.00043663936,0.000305012,0.00030324282,0.000041848998,0.00020417862,0.00006372514,0.00006607809],"category_scores_gemma":[0.007856912,0.00010386597,0.00018361509,0.00032311017,0.00020077638,0.000108538225,0.000059904607,0.00047965575,0.000002118492],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04740634,0.0037848474,0.12850608,0.009246968,0.005731442,0.0005969539,0.0036058088,0.032790743,0.063875385,0.0046376255,0.12054656,0.57927126],"study_design_scores_gemma":[0.06807833,0.002994192,0.08873012,0.0060356883,0.0037686082,0.0010213949,0.0013199217,0.38493302,0.0023955486,0.0027319018,0.43735358,0.0006376964],"about_ca_topic_score_codex":0.000035961883,"about_ca_topic_score_gemma":0.000012547818,"teacher_disagreement_score":0.629439,"about_ca_system_score_codex":0.00008046097,"about_ca_system_score_gemma":0.00044433176,"threshold_uncertainty_score":0.9406025},"labels":[],"label_agreement":null},{"id":"W7124924134","doi":"10.59275/j.melba.2025-fcb7","title":"A schistosomiasis dataset with bright- and darkfield images","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto General Hospital; University Health Network","funders":"Canadian Institutes of Health Research","keywords":"Schistosomiasis; Freshwater mollusc; Helminthiasis; Biomphalaria","score_opus":0.0050626932702191344,"score_gpt":0.2550440449348918,"score_spread":0.24998135166467267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124924134","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012562131,0.0070655346,0.94149417,0.03732202,0.00027920908,0.00019872707,0.00007878975,0.00009334911,0.00090607],"genre_scores_gemma":[0.95448637,0.00009052993,0.042593066,0.0024084935,0.00010632777,0.0000038820185,0.000045299334,0.000019675908,0.00024633808],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99882376,0.00010409038,0.00032180248,0.00017294624,0.00032305572,0.0002543491],"domain_scores_gemma":[0.998605,0.00061445945,0.00025134446,0.000271769,0.00010969705,0.0001477346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089794834,0.0001501892,0.00023610432,0.00026023109,0.0002694675,0.00030636226,0.000907697,0.000018797276,0.0000044829603],"category_scores_gemma":[0.00056383514,0.00008589148,0.00006394657,0.0003359267,0.00036140194,0.00073496345,0.0003185741,0.00038628248,0.0000014452705],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000577738,0.00045507174,0.014713001,0.0002854317,0.00046920747,0.00020702014,0.00054125034,0.00017840562,0.0015706581,0.0073429206,0.10353732,0.87012196],"study_design_scores_gemma":[0.010621772,0.0013429102,0.012765386,0.0017663776,0.0011434433,0.0042584557,0.0005635247,0.19056974,0.0044404645,0.023556478,0.74791956,0.0010518511],"about_ca_topic_score_codex":0.000051989977,"about_ca_topic_score_gemma":9.949324e-7,"teacher_disagreement_score":0.9419243,"about_ca_system_score_codex":0.000021596139,"about_ca_system_score_gemma":0.00013181621,"threshold_uncertainty_score":0.3502553},"labels":[],"label_agreement":null},{"id":"W7124958874","doi":"10.59275/j.melba.2025-5ce1","title":"The Trauma THOMPSON Dataset for Real-World Emergency AI","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"U.S. Army Medical Research and Development Command; National Science Foundation","keywords":"Action (physics); Benchmark (surveying); Object (grammar); Psychological intervention; Emergency response; Foundation (evidence); Visualization","score_opus":0.013844783570730974,"score_gpt":0.3552164647173537,"score_spread":0.3413716811466227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124958874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001141494,0.00075311254,0.8617068,0.13480888,0.00080244953,0.0003818783,0.00005023788,0.000059657643,0.00029550004],"genre_scores_gemma":[0.9284665,0.00047539987,0.065084554,0.0022691728,0.0009663533,0.000101425416,0.00026730995,0.00005911272,0.0023101447],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977961,0.00035082322,0.0007788466,0.0002300579,0.00040961144,0.00043451338],"domain_scores_gemma":[0.9961441,0.0023299132,0.0005930679,0.0005577145,0.00024479104,0.00013042556],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004744148,0.00019201692,0.00026509297,0.00027039956,0.0013687204,0.00017233753,0.0023875243,0.000036764,0.000015985483],"category_scores_gemma":[0.0013762229,0.00010678023,0.00020266541,0.0007473485,0.00019344356,0.00025172916,0.00030574156,0.0009489017,0.000005018431],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024234643,0.00018437424,0.005605468,0.000104503066,0.00021539196,0.0000034043837,0.00061207294,0.0025866844,0.0015357663,0.038225338,0.11912599,0.83155864],"study_design_scores_gemma":[0.00067614263,0.00008598106,0.0042819683,0.00004588225,0.000067681554,0.00002441959,0.000033884593,0.5303665,0.000074126845,0.0076233638,0.45662034,0.00009973384],"about_ca_topic_score_codex":0.00028887164,"about_ca_topic_score_gemma":0.00003681351,"teacher_disagreement_score":0.927325,"about_ca_system_score_codex":0.00006775029,"about_ca_system_score_gemma":0.00012319606,"threshold_uncertainty_score":0.99993134},"labels":[],"label_agreement":null}]}