{"meta":{"query_hash":"da1b422238c4","filters":{"venue":"Medical Image Analysis"},"cohort_total":366,"direct_labels_cover":0,"predictions_cover":366,"exported":366,"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/da1b422238c4","api":"https://metacan.xera.ac/api/v1/cohort?venue=Medical+Image+Analysis"},"results":[{"id":"W1038736503","doi":"10.1016/j.media.2015.07.003","title":"Multi-scale deep networks and regression forests for direct bi-ventricular volume estimation","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiovascular Function and Risk Factors","field":"Medicine","cited_by":115,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; St Joseph's Health Care; CARE Canada; Western University","funders":"Government of Ontario","keywords":"Computer science; Artificial intelligence; Ground truth; Segmentation; Volume (thermodynamics); Regression; Estimation; Scale (ratio); Deep learning; Machine learning; Random forest; Pattern recognition (psychology); Statistics; Mathematics; Engineering","score_opus":0.013897888690403945,"score_gpt":0.2905070853804426,"score_spread":0.2766091966900387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1038736503","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":[0.052226048,0.0016416397,0.94463325,0.00087624067,0.00016489308,0.00028309447,0.0000040241043,0.00008330431,0.00008751113],"genre_scores_gemma":[0.97001183,0.00031069532,0.026165051,0.00052222086,0.0004241858,0.00006459873,0.00072438706,0.000035436846,0.0017416221],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983714,0.000091679,0.0002911455,0.0003372296,0.000675281,0.00023327048],"domain_scores_gemma":[0.99858135,0.000073724485,0.000078641184,0.00030741992,0.00028802612,0.0006708581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088203436,0.00015400801,0.00057353,0.0002747395,0.00008911195,0.000035291974,0.000058733487,0.00019376774,0.00018567262],"category_scores_gemma":[0.0016902518,0.00010270066,0.0006101471,0.00077679753,0.00011002743,0.00009475298,0.000045739238,0.00016479005,0.000016424878],"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":[0.0003361083,0.00048626965,0.7766924,0.0001146057,0.005012693,0.0004887145,0.00029654073,0.0073737185,0.00005791033,0.0000019390316,0.027277412,0.18186171],"study_design_scores_gemma":[0.0020785718,0.00006970113,0.09508465,0.000037578728,0.0041902885,0.0000441628,0.00008994012,0.89264745,0.00006363225,0.0000048235397,0.0055736294,0.00011555128],"about_ca_topic_score_codex":0.00013604344,"about_ca_topic_score_gemma":0.00022176313,"teacher_disagreement_score":0.9184682,"about_ca_system_score_codex":0.00006271153,"about_ca_system_score_gemma":0.000051293006,"threshold_uncertainty_score":0.41880113},"labels":[],"label_agreement":null},{"id":"W1627283626","doi":"10.1016/j.media.2015.06.005","title":"Analytic signal phase-based myocardial motion estimation in tagged MRI sequences by a bilinear model and motion compensation","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Nautical Research Society","funders":"Agence Nationale de la Recherche","keywords":"Motion estimation; Bilinear interpolation; Motion field; Estimator; Computer vision; Artificial intelligence; Computer science; Motion compensation; Optical flow; Trajectory; Mathematics; Algorithm; Quarter-pixel motion; Image (mathematics); Physics","score_opus":0.02226197642583755,"score_gpt":0.32333633498314773,"score_spread":0.3010743585573102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1627283626","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":[0.026410878,0.000067572604,0.9707774,0.0024725888,0.000029934206,0.00010460522,0.0000048990987,0.0000780532,0.000054099655],"genre_scores_gemma":[0.8724042,0.000010614804,0.12695843,0.0004644117,0.00001957311,0.000008359473,0.00011330583,0.0000053094795,0.000015778214],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777013,0.0002151461,0.0004181436,0.00047114864,0.00090708217,0.00021836252],"domain_scores_gemma":[0.99905574,0.00009599291,0.00014048614,0.00024871418,0.0001670107,0.00029206433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012367917,0.00014739463,0.00032694542,0.0005352614,0.000076515054,0.00016251844,0.000262699,0.00007507337,0.000032627086],"category_scores_gemma":[0.00045544762,0.00013135516,0.00010128707,0.0016709608,0.00013090576,0.0010349072,0.00006411529,0.00018245431,0.0000111861555],"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":[0.000046324232,0.0005416496,0.003404579,0.000023020828,0.00016730888,0.000053336877,0.00074134587,0.5602428,0.0053740465,0.00033948603,0.00073592865,0.4283302],"study_design_scores_gemma":[0.0013581673,0.0000478726,0.00025677547,0.000015469059,0.000117039584,0.0000020180762,0.000038178823,0.99624056,0.00076752383,0.0010030379,0.000015820187,0.0001375615],"about_ca_topic_score_codex":0.00011964321,"about_ca_topic_score_gemma":0.000028640174,"teacher_disagreement_score":0.84599334,"about_ca_system_score_codex":0.00011217106,"about_ca_system_score_gemma":0.00012999616,"threshold_uncertainty_score":0.5356508},"labels":[],"label_agreement":null},{"id":"W1884191083","doi":"10.1016/j.media.2016.05.004","title":"Brain tumor segmentation with Deep Neural Networks","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":3245,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Université de Montréal; Université de Sherbrooke","funders":"","keywords":"Computer science; Convolutional neural network; Exploit; Artificial intelligence; Segmentation; Deep learning; Set (abstract data type); Deep neural networks; Pattern recognition (psychology); Layer (electronics); Machine learning; Architecture; Artificial neural network","score_opus":0.013204008021251752,"score_gpt":0.2671777228647449,"score_spread":0.2539737148434931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1884191083","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":[0.15130453,0.000009087407,0.8325507,0.015153047,0.000077387085,0.000098144505,0.0000024611466,0.00014225791,0.0006623492],"genre_scores_gemma":[0.9927716,0.000007858063,0.00023173403,0.0060569937,0.000102615624,0.000030544164,0.00000480726,0.000012171668,0.000781674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982326,0.0002476258,0.00023159724,0.0004084073,0.00064303505,0.00023673891],"domain_scores_gemma":[0.99892426,0.00042438915,0.00011717463,0.0002645475,0.000042917272,0.00022671405],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030202625,0.00011453672,0.00017246573,0.00017957488,0.00012888612,0.00006121757,0.00020611713,0.000042606975,0.0029561499],"category_scores_gemma":[0.0011362062,0.00006546754,0.000113897186,0.0013893028,0.00025706,0.0002458902,0.000028090097,0.00012561794,0.0000920373],"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":[0.00020264371,0.00029280008,0.008634997,0.000012712808,0.00025480872,0.000514108,0.00023465481,0.0005291236,0.4716101,0.00048885995,0.0026139196,0.51461124],"study_design_scores_gemma":[0.0013059049,0.00013195479,0.013703912,0.0000135752225,0.00040523484,0.00008861911,0.00014738092,0.90403485,0.07895698,0.000079299265,0.0008163942,0.00031590945],"about_ca_topic_score_codex":0.000016146032,"about_ca_topic_score_gemma":0.0001207087,"teacher_disagreement_score":0.90350574,"about_ca_system_score_codex":0.00004451404,"about_ca_system_score_gemma":0.000017595876,"threshold_uncertainty_score":0.99795526},"labels":[],"label_agreement":null},{"id":"W1901606657","doi":"10.1016/j.media.2015.06.009","title":"Abdominal multi-organ segmentation from CT images using conditional shape–location and unsupervised intensity priors","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":156,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; Ministry of Education, Culture, Sports, Science and Technology; Japan Society for the Promotion of Science; Ontario Council on Graduate Studies, Council of Ontario Universities","keywords":"Prior probability; Segmentation; Artificial intelligence; Pattern recognition (psychology); Computer science; Image segmentation; Computer vision; Bayesian probability","score_opus":0.021190394260791008,"score_gpt":0.2817087070582469,"score_spread":0.2605183127974559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1901606657","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":[0.472364,0.00020727166,0.52714807,0.00008712122,0.000044163913,0.00004274739,0.0000148620065,0.000073298965,0.000018468141],"genre_scores_gemma":[0.950803,0.000039213453,0.04847467,0.00017987234,0.00010375226,0.0000054753637,0.0003652094,0.0000178192,0.000010983071],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882996,0.0000455649,0.0002789684,0.00023740054,0.0004217521,0.00018635094],"domain_scores_gemma":[0.9992978,0.00006688117,0.000045786037,0.00013890561,0.00017602624,0.0002745806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024057068,0.00015777283,0.0002877754,0.00018059416,0.000088420114,0.00005904251,0.00009736047,0.000045141693,0.00038194947],"category_scores_gemma":[0.0002656168,0.00015558195,0.00007130394,0.0005222601,0.00015712387,0.00047257938,0.000042751723,0.00018978267,0.000021830552],"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":[0.00023721706,0.0006713498,0.235475,0.00028370597,0.007586901,0.0012368197,0.008689699,0.093125425,0.47602707,0.000049188933,0.0019283887,0.17468922],"study_design_scores_gemma":[0.00084233354,0.000007094783,0.02082445,0.000023905468,0.0007274886,0.000014848271,0.0011996237,0.96394485,0.012052965,0.00014683316,0.000021738468,0.00019387671],"about_ca_topic_score_codex":0.00022329442,"about_ca_topic_score_gemma":0.000049558403,"teacher_disagreement_score":0.8708194,"about_ca_system_score_codex":0.00009985031,"about_ca_system_score_gemma":0.0000392737,"threshold_uncertainty_score":0.6344448},"labels":[],"label_agreement":null},{"id":"W1906917243","doi":"10.1016/j.media.2015.10.006","title":"Population-based prediction of subject-specific prostate deformation for MR-to-ultrasound image registration","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":47,"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":"Medical Research Council; University College London Hospitals NHS Foundation Trust; Wellcome Trust; Royal Academy of Engineering; Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research; National Institute for Health and Care Research; NIHR Biomedical Research Centre, Royal Marsden NHS Foundation Trust/Institute of Cancer Research; Cancer Research UK","keywords":"Artificial intelligence; Image registration; Percentile; Computer science; Population; Computer vision; Medical imaging; Prostate; Landmark; Magnetic resonance imaging; Ultrasound; Statistical model; Pattern recognition (psychology); Image (mathematics); Mathematics; Statistics; Medicine; Radiology","score_opus":0.014404910519597457,"score_gpt":0.25170295380671487,"score_spread":0.2372980432871174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1906917243","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":[0.20460758,0.0000826898,0.79373145,0.00052806345,0.00011417592,0.00021386669,0.00010436337,0.00019700058,0.00042078737],"genre_scores_gemma":[0.98295575,0.000029823495,0.01465182,0.00010073026,0.00016386773,0.00006829167,0.001907748,0.000024670353,0.00009730139],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976872,0.00006935417,0.0007489142,0.00025328808,0.0009729094,0.00026829078],"domain_scores_gemma":[0.99851906,0.00019785194,0.00012644628,0.00033621097,0.0003645204,0.0004559091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012309492,0.00017591163,0.00044389485,0.000559504,0.00006375515,0.00007426835,0.0001743131,0.00011284743,0.00019271222],"category_scores_gemma":[0.0014741768,0.00015767789,0.00028266254,0.001645418,0.00007170042,0.00031818138,0.000010951337,0.0001510707,0.000027095708],"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":[0.00033416657,0.0011650525,0.27967376,0.0017223583,0.0070028165,0.00006666979,0.0052916855,0.32335517,0.08839588,0.00039666065,0.18041955,0.11217622],"study_design_scores_gemma":[0.00081362046,0.000053684955,0.012068699,0.00005147752,0.0009556796,0.0000020378725,0.00021730231,0.9789568,0.004935454,0.00017056408,0.0015643206,0.00021034834],"about_ca_topic_score_codex":0.00019937192,"about_ca_topic_score_gemma":0.00006679059,"teacher_disagreement_score":0.7790797,"about_ca_system_score_codex":0.0001293749,"about_ca_system_score_gemma":0.00006471325,"threshold_uncertainty_score":0.6429918},"labels":[],"label_agreement":null},{"id":"W1967113208","doi":"10.1016/j.media.2010.04.006","title":"Wavelet-based estimation of the hemodynamic responses in diffuse optical imaging","year":2010,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Optical Imaging and Spectroscopy Techniques","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Wavelet; Diffuse optical imaging; Estimator; Computer science; Artificial intelligence; SIGNAL (programming language); Noise (video); Finger tapping; Contrast (vision); Functional near-infrared spectroscopy; Computer vision; Pattern recognition (psychology); Mathematics; Image (mathematics); Neuroscience; Iterative reconstruction; Statistics; Cognition; Psychology; Medicine","score_opus":0.004223334705785716,"score_gpt":0.3080096687362906,"score_spread":0.30378633403050487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967113208","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":[0.8905002,0.000018642297,0.09358928,0.014474092,0.000041576015,0.00013733542,0.000003712672,0.000082839106,0.0011523337],"genre_scores_gemma":[0.93765813,0.0000047002113,0.061369047,0.0007905439,0.000028190127,0.000012755687,0.000015242107,0.000013871721,0.00010752044],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814963,0.00009553743,0.0004537766,0.00027298185,0.0007609321,0.0002671299],"domain_scores_gemma":[0.99866253,0.0003578381,0.00007888972,0.0006022751,0.000101360005,0.00019711725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084798475,0.00014103102,0.00046353048,0.0004263191,0.000045365952,0.000025596266,0.00022887517,0.00010759211,0.00038753476],"category_scores_gemma":[0.0046225777,0.000090798996,0.0003149874,0.0012582013,0.0006596774,0.00007145124,0.000065821056,0.00075274875,0.0000069231946],"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":[0.000603183,0.004648738,0.31849474,0.0002627791,0.0005887013,0.00074021384,0.00023155671,0.000033077493,0.56511486,0.0022990508,0.00068306405,0.10630002],"study_design_scores_gemma":[0.0010052199,0.000033454107,0.13890104,0.00008536357,0.00076475734,0.000018996969,0.000019472272,0.80394834,0.054793242,0.00029497017,0.000027036573,0.000108116335],"about_ca_topic_score_codex":0.00016442839,"about_ca_topic_score_gemma":0.00010348871,"teacher_disagreement_score":0.80391526,"about_ca_system_score_codex":0.000047923528,"about_ca_system_score_gemma":0.00018790542,"threshold_uncertainty_score":0.5533991},"labels":[],"label_agreement":null},{"id":"W1967118256","doi":"10.1016/j.media.2008.07.002","title":"Fusion of optical imaging and MRI for the evaluation and adjustment of macroscopic models of cardiac electrophysiology: A feasibility study","year":2008,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health; University of Alabama; Ontario Innovation Trust","keywords":"Cardiac electrophysiology; Optical mapping; Work (physics); Experimental data; Electrophysiology; Diffuse optical imaging; Contrast (vision); Fusion; Conductivity; Biological system; Physics; Computer science; Artificial intelligence; Mathematics; Statistics; Iterative reconstruction; Neuroscience; Cardiology; Medicine; Thermodynamics","score_opus":0.03505340872948261,"score_gpt":0.39176821624191654,"score_spread":0.35671480751243395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967118256","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":[0.7524704,0.0014738915,0.2447829,0.00034461773,0.0000036243457,0.0008911018,0.000009386351,0.0000058793526,0.00001821279],"genre_scores_gemma":[0.98340267,0.0014812335,0.014932758,0.000027647255,0.00001558494,0.00011395651,0.000015848555,0.0000042313386,0.0000060958405],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989964,0.000052071726,0.0003139843,0.00019274307,0.00035611517,0.00008868875],"domain_scores_gemma":[0.9990911,0.00018526328,0.00010942733,0.00027033224,0.00028310774,0.000060790924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005614276,0.0000677683,0.00043054586,0.00006823566,0.000045854667,8.6207245e-7,0.00004960281,0.00003271846,0.000020500664],"category_scores_gemma":[0.00021243241,0.000042698503,0.0001148094,0.00027939814,0.00037507003,0.00003081217,0.00005285377,0.000072302566,3.1172355e-8],"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":[0.00097054936,0.0046177064,0.107760444,0.00045507489,0.0024214971,0.0000055914707,0.0023442863,0.000715462,0.58699644,0.0009122216,0.00032779426,0.29247293],"study_design_scores_gemma":[0.0016850673,0.00084475375,0.42187536,0.000038765415,0.0079293065,0.00000527092,0.00082918495,0.5361002,0.028335303,0.0022566838,0.000008980159,0.00009112044],"about_ca_topic_score_codex":0.00007775014,"about_ca_topic_score_gemma":0.0000061521873,"teacher_disagreement_score":0.55866116,"about_ca_system_score_codex":0.000019190971,"about_ca_system_score_gemma":0.000057067853,"threshold_uncertainty_score":0.17411944},"labels":[],"label_agreement":null},{"id":"W1968301261","doi":"10.1016/j.media.2013.08.006","title":"Denoising and fast diffusion imaging with physically constrained sparse dictionary learning","year":2013,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Artificial intelligence; Computer science; Noise reduction; Dictionary learning; Diffusion MRI; Pattern recognition (psychology); Gaussian; Diffusion; Sparse approximation; Computer vision; Physics","score_opus":0.012633093816359044,"score_gpt":0.29270872219528005,"score_spread":0.280075628378921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968301261","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":[0.4746985,0.00006802258,0.5140331,0.009081554,0.0000053109734,0.00022832555,0.0000017688737,0.00029385238,0.0015895915],"genre_scores_gemma":[0.97449744,0.00009604232,0.023859255,0.0010068796,0.00007565227,0.000045509907,0.000050852806,0.00002161813,0.00034674077],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873924,0.000035546,0.00021723296,0.00036379427,0.0004229248,0.00022128325],"domain_scores_gemma":[0.99914473,0.000101519974,0.000080997415,0.00022914211,0.00013229933,0.00031132775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010550502,0.00014772416,0.00032293034,0.00018375547,0.0001894587,0.00005028088,0.00007172412,0.000036513182,0.0005515422],"category_scores_gemma":[0.00015299057,0.00010856916,0.00009889206,0.00065516966,0.0004108119,0.00017304535,0.000080240636,0.00037399246,0.000021066093],"study_design_candidate":"observational","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":[0.00006610763,0.0006589556,0.46173117,0.00008084335,0.000809291,0.0005772265,0.00031240584,0.000058962833,0.16481507,0.00038319995,0.0012640276,0.36924273],"study_design_scores_gemma":[0.0026065018,0.00029527393,0.42653534,0.0003735696,0.0043281545,0.0007946094,0.0009540326,0.5554624,0.002814468,0.0011000608,0.0040349644,0.0007005887],"about_ca_topic_score_codex":0.00009726838,"about_ca_topic_score_gemma":0.000003343378,"teacher_disagreement_score":0.5554035,"about_ca_system_score_codex":0.00002210364,"about_ca_system_score_gemma":0.000036051923,"threshold_uncertainty_score":0.6039001},"labels":[],"label_agreement":null},{"id":"W1969368707","doi":"10.1016/j.media.2008.12.006","title":"Detection and measurement of coverage loss in interleaved multi-acquisition brain MRIs due to motion-induced inter-slice misalignment","year":2009,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"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; Artificial intelligence; Data set; Motion (physics); Range (aeronautics); Set (abstract data type); Computer vision; Missing data; Pattern recognition (psychology); Algorithm","score_opus":0.017590773498436654,"score_gpt":0.3237284229383808,"score_spread":0.30613764943994415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969368707","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":[0.28668538,0.000023381206,0.7081868,0.0047203647,0.000007801115,0.00027318537,0.0000032896426,0.00003313542,0.0000666915],"genre_scores_gemma":[0.988688,0.000033868066,0.009701884,0.0014360982,0.00003240066,0.00005199666,0.00001832384,0.00000802884,0.000029404691],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985092,0.00005956294,0.00044977592,0.00031144434,0.00050677947,0.00016321865],"domain_scores_gemma":[0.9992089,0.00003718299,0.000098686345,0.00026952045,0.00016006437,0.00022561647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005811189,0.0001283477,0.00040722208,0.0003642986,0.000032340482,0.000010330289,0.00007567234,0.000093919785,0.00013931298],"category_scores_gemma":[0.00033983032,0.00011555614,0.00012609277,0.00082843594,0.000041893007,0.000070406975,0.000034450128,0.00016392197,0.000004612428],"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":[0.00014935696,0.0010571346,0.0016816637,0.000040697276,0.00017360954,0.000100005534,0.0005682202,0.00004582796,0.6766106,0.000029230612,0.0001250298,0.31941864],"study_design_scores_gemma":[0.0044916575,0.0014854063,0.28836882,0.00063499797,0.0014916711,0.00008568092,0.00061126583,0.05433958,0.64659053,0.00058035966,0.0007760622,0.00054399204],"about_ca_topic_score_codex":0.00021006136,"about_ca_topic_score_gemma":0.00028092726,"teacher_disagreement_score":0.70200264,"about_ca_system_score_codex":0.00019103488,"about_ca_system_score_gemma":0.000020552729,"threshold_uncertainty_score":0.47122428},"labels":[],"label_agreement":null},{"id":"W1969392314","doi":"10.1016/s1361-8415(02)00087-7","title":"The development and evaluation of a three-dimensional ultrasound-guided breast biopsy apparatus","year":2002,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Breast Lesions and Carcinomas","field":"Medicine","cited_by":47,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Robarts Clinical Trials; Western University","funders":"","keywords":"Biopsy; Imaging phantom; Breast biopsy; Medicine; USB; Radiology; Ultrasound; Needle biopsy; Mammography; Sampling (signal processing); Chicken breast; 3D ultrasound; Medical physics; Breast cancer; Computer science; Computer vision; Cancer","score_opus":0.036347930551477156,"score_gpt":0.29647933319383124,"score_spread":0.26013140264235407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969392314","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":[0.99365103,0.0015417278,0.0010517512,0.0023011558,0.000026657568,0.00014823729,0.0000044955973,0.000015430518,0.0012594934],"genre_scores_gemma":[0.9978929,0.000025918553,0.0015669642,0.00013175124,0.00005553678,0.000021246704,0.000032852804,0.000007411098,0.00026540025],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9974317,0.00010151005,0.00042043862,0.00023562416,0.0016129323,0.000197808],"domain_scores_gemma":[0.9987418,0.00019057382,0.00009603734,0.00029770052,0.00041834195,0.00025555977],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016111204,0.00011874706,0.00031506494,0.00015389976,0.00016539171,0.000020303985,0.00008984043,0.000084777814,0.0026901688],"category_scores_gemma":[0.00039098042,0.000069785514,0.00014858159,0.0007895893,0.00027916126,0.000040241433,0.000045613466,0.00014458074,0.00003487891],"study_design_candidate":"observational","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":[0.00018803062,0.0015821499,0.27441835,0.00010995605,0.008447522,0.00019626718,0.0012437046,0.000040750205,0.014353434,0.0002638913,0.015708882,0.68344706],"study_design_scores_gemma":[0.0013725057,0.000026446973,0.89982796,0.00004849568,0.0038256454,0.0010328608,0.00011868877,0.092747,0.00048634512,0.000057886453,0.00033535803,0.00012082285],"about_ca_topic_score_codex":0.000081659484,"about_ca_topic_score_gemma":0.00014827518,"teacher_disagreement_score":0.68332624,"about_ca_system_score_codex":0.0000472244,"about_ca_system_score_gemma":0.00014894441,"threshold_uncertainty_score":0.9982215},"labels":[],"label_agreement":null},{"id":"W1969422115","doi":"10.1016/j.media.2008.07.003","title":"3D estimation of soft biological tissue deformation from radio-frequency ultrasound volume acquisitions","year":2008,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Ultrasound Imaging and Elastography","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Hôpital Notre-Dame","funders":"","keywords":"Elastography; Imaging phantom; 3D ultrasound; Ultrasound; Deformation (meteorology); Ultrasonic sensor; Ultrasound elastography; Computer science; Similarity (geometry); Biomedical engineering; Orientation (vector space); Acoustics; Mathematics; Algorithm; Materials science; Artificial intelligence; Physics; Geometry; Optics; Medicine","score_opus":0.01020306237214801,"score_gpt":0.2630836163661459,"score_spread":0.2528805539939979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969422115","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":[0.57293886,0.00030856396,0.42520398,0.00056589354,0.00004334021,0.000085861335,0.000050839637,0.00008702577,0.0007156597],"genre_scores_gemma":[0.93652374,0.00023639027,0.060843945,0.00035745045,0.00013382998,0.000013813122,0.001773616,0.000011098351,0.00010612416],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99798363,0.00010788458,0.00060588215,0.0003014412,0.00073659874,0.0002645719],"domain_scores_gemma":[0.9986077,0.0003191313,0.00017055761,0.00038805045,0.00019907457,0.00031547056],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031827894,0.00017822145,0.00059453986,0.00047637668,0.00018521513,0.000017823708,0.0001529771,0.00018468432,0.0054742806],"category_scores_gemma":[0.0016765273,0.00013866069,0.0003654239,0.0015835754,0.0006527175,0.00025354107,0.000020841633,0.00026444803,0.00018192065],"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":[0.00016059523,0.0019788006,0.84002566,0.00012024555,0.005894998,0.00027169372,0.0034838256,0.0006847688,0.10509992,0.000060019367,0.006991026,0.035228457],"study_design_scores_gemma":[0.0025732599,0.0006171281,0.90344,0.00017770573,0.0075311447,0.0010136983,0.0004786676,0.07542424,0.0047856937,0.0012290695,0.0020534254,0.0006759467],"about_ca_topic_score_codex":0.0007764978,"about_ca_topic_score_gemma":0.000011498895,"teacher_disagreement_score":0.36436003,"about_ca_system_score_codex":0.000047529615,"about_ca_system_score_gemma":0.000093537914,"threshold_uncertainty_score":0.9954349},"labels":[],"label_agreement":null},{"id":"W1971405799","doi":"10.1016/j.media.2010.07.001","title":"Multiple q-shell diffusion propagator imaging","year":2010,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":169,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Association France Parkinson","keywords":"Diffusion MRI; Propagator; Computer science; Diffusion; Laplace transform; Fourier transform; SIGNAL (programming language); Diffusion equation; Algorithm; Artificial intelligence; Physics; Computer vision; Mathematical analysis; Mathematics","score_opus":0.01894291456037772,"score_gpt":0.3416434039444404,"score_spread":0.3227004893840627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971405799","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":[0.55100864,0.000061916,0.4227734,0.020261941,0.00008896166,0.00046146818,0.000013657005,0.0007629416,0.0045671035],"genre_scores_gemma":[0.95167655,0.00004442142,0.045132652,0.0020924166,0.00019879239,0.000056242636,0.000075390024,0.00002609,0.0006974613],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984994,0.000020262676,0.00028870668,0.00039958803,0.0005340825,0.0002579843],"domain_scores_gemma":[0.99863386,0.00009602837,0.00007448857,0.000643662,0.00012782235,0.00042411155],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023564401,0.00014384346,0.00032759682,0.00024258246,0.00012032273,0.000026793261,0.00019324606,0.000069945345,0.0017207053],"category_scores_gemma":[0.0009867597,0.000110823355,0.00026917682,0.0009236287,0.00023623138,0.00009042416,0.000114882125,0.0006041123,0.00009110149],"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":[0.00002989981,0.0006289234,0.3552921,0.00003588832,0.00019638575,0.00038285277,0.00004913628,6.7282764e-7,0.56754637,0.00022918859,0.005626551,0.069982044],"study_design_scores_gemma":[0.0032950945,0.00010505638,0.2246842,0.000106515006,0.005301327,0.0004360357,0.00011271447,0.44359902,0.10103973,0.0015590806,0.21882313,0.0009381081],"about_ca_topic_score_codex":0.000067607354,"about_ca_topic_score_gemma":0.00003232197,"teacher_disagreement_score":0.4665066,"about_ca_system_score_codex":0.00001633017,"about_ca_system_score_gemma":0.00005601537,"threshold_uncertainty_score":0.9991919},"labels":[],"label_agreement":null},{"id":"W1985161468","doi":"10.1016/j.media.2011.05.010","title":"An integrated approach to segmentation and nonrigid registration for application in image-guided pelvic radiotherapy","year":2011,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health","keywords":"Segmentation; Computer science; Artificial intelligence; Computer vision; Image registration; Image segmentation; Radiation treatment planning; Radiation therapy; Medicine; Image (mathematics); Radiology","score_opus":0.016001706040179614,"score_gpt":0.32771335626662274,"score_spread":0.3117116502264431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985161468","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":[0.028688509,0.000023213239,0.96988153,0.00011237254,0.0000066427747,0.0005619334,0.000014486066,0.000055157212,0.0006561621],"genre_scores_gemma":[0.31697482,0.000018766443,0.68173593,0.0001787462,0.0000679794,0.0004898547,0.000463104,0.000020375024,0.000050395076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988583,0.00007012472,0.00032781772,0.00038135867,0.00019290877,0.00016953824],"domain_scores_gemma":[0.9993486,0.000027240043,0.00011260803,0.00027305284,0.00009365766,0.00014486405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004148854,0.00014257095,0.0002693352,0.00026263716,0.00005133182,0.000042226584,0.00015919829,0.000057287838,0.0002013571],"category_scores_gemma":[0.000016434977,0.00012706709,0.00008200222,0.0007135578,0.00007481603,0.0003183826,0.000007531116,0.000100728386,8.003428e-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":[0.00031387087,0.002177017,0.095966384,0.00006520813,0.0014214254,0.0000038957805,0.006879515,0.0002227768,0.24502115,0.005678978,0.0013806002,0.6408692],"study_design_scores_gemma":[0.0032973285,0.0004825848,0.019821158,0.000029911058,0.0007456989,0.0000035884882,0.0018998669,0.89936066,0.06606585,0.0045697284,0.002734122,0.0009895144],"about_ca_topic_score_codex":0.0012442484,"about_ca_topic_score_gemma":0.000059854305,"teacher_disagreement_score":0.89913785,"about_ca_system_score_codex":0.00005629889,"about_ca_system_score_gemma":0.00003294262,"threshold_uncertainty_score":0.5181646},"labels":[],"label_agreement":null},{"id":"W1987164933","doi":"10.1016/j.media.2006.01.002","title":"Methods for segmenting curved needles in ultrasound images","year":2006,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Image and Object Detection Techniques","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hough transform; Computer vision; Artificial intelligence; Segmentation; Curvature; Ultrasound; Computer science; Transformation (genetics); Image (mathematics); Mathematics; Radiology; Medicine; Geometry","score_opus":0.007393570306163159,"score_gpt":0.3360884202962845,"score_spread":0.32869484999012133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987164933","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":[0.0009968652,0.00026360387,0.99580467,0.00050771364,0.00006279913,0.00013755973,0.0000022031768,0.00028205547,0.0019425562],"genre_scores_gemma":[0.13656166,0.00003527747,0.86214304,0.0004575592,0.00012783175,0.00008781662,0.000018886833,0.000012071186,0.0005558827],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980004,0.00028402623,0.0004910338,0.00046081367,0.0003724196,0.00039131538],"domain_scores_gemma":[0.9983987,0.0008127905,0.0001193557,0.00044159207,0.0001324256,0.00009508728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025479547,0.00016091323,0.0003938458,0.0007283754,0.0001242788,0.00026886573,0.0006935971,0.000107456945,0.00014171432],"category_scores_gemma":[0.0010700243,0.00014264925,0.00035591586,0.0024463749,0.000094405375,0.00054590654,0.00013035315,0.00019074709,0.0000089395535],"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":[0.000014048136,0.00046836826,0.0066449638,0.00007472623,0.0005706414,0.00013682291,0.00047209434,0.000048475515,0.12080763,0.0007126988,0.008357092,0.8616924],"study_design_scores_gemma":[0.00060073065,0.000055441324,0.0077146674,0.000023598463,0.0003148723,0.000017851487,0.00011968863,0.0768262,0.9012386,0.010243334,0.0024022732,0.00044272284],"about_ca_topic_score_codex":0.0010089538,"about_ca_topic_score_gemma":0.00015684195,"teacher_disagreement_score":0.8612497,"about_ca_system_score_codex":0.000055343127,"about_ca_system_score_gemma":0.00004872231,"threshold_uncertainty_score":0.58170676},"labels":[],"label_agreement":null},{"id":"W1989986853","doi":"10.1016/j.media.2012.11.007","title":"Regional heart motion abnormality detection: An information theoretic approach","year":2013,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CARE Canada; McGill University; London Health Sciences Centre; St Joseph's Health Care; University of Alberta","funders":"","keywords":"Abnormality; Artificial intelligence; Computer science; Motion (physics); Computer vision; Pattern recognition (psychology); Medicine","score_opus":0.008462233525864483,"score_gpt":0.24652221636517618,"score_spread":0.2380599828393117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989986853","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":[0.010219525,0.0000067190076,0.9850606,0.0020388903,0.000020267635,0.00016218417,9.2124986e-7,0.00036197924,0.0021289305],"genre_scores_gemma":[0.94022906,0.000010904673,0.058060367,0.0013520736,0.000065046755,0.00018780527,0.000040271585,0.000003422112,0.000051065243],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848825,0.00012315376,0.0003479786,0.00026293573,0.0005903354,0.00018736774],"domain_scores_gemma":[0.99876106,0.00003181094,0.00010600105,0.0006185492,0.00023132247,0.0002512656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000586244,0.000108332984,0.00017161282,0.0002812861,0.0002286326,0.00028481154,0.00052732055,0.000115370574,0.00063064945],"category_scores_gemma":[0.000056587618,0.0000912422,0.0001807244,0.0016409167,0.00013322251,0.0024240962,0.000097558805,0.00019327203,0.00023334073],"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":[0.000010461087,0.00094417384,0.0027100097,0.00006978837,0.000553886,0.000004554587,0.0012502299,0.00038352588,0.0012506958,0.10004853,0.0067337356,0.8860404],"study_design_scores_gemma":[0.00011084877,0.000047137764,0.022436345,0.0000019298627,0.00008759176,0.00003952864,0.00008268538,0.96687376,0.0013496301,0.006254827,0.002539018,0.00017669881],"about_ca_topic_score_codex":0.00041718653,"about_ca_topic_score_gemma":0.000010814946,"teacher_disagreement_score":0.9664902,"about_ca_system_score_codex":0.000039790433,"about_ca_system_score_gemma":0.000029117267,"threshold_uncertainty_score":0.6905169},"labels":[],"label_agreement":null},{"id":"W1990369221","doi":"10.1016/j.media.2004.11.002","title":"Modelling liver tissue properties using a non-linear visco-elastic model for surgery simulation","year":2004,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Elasticity and Material Modeling","field":"Engineering","cited_by":147,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Linear elasticity; Computation; Elasticity (physics); Computer science; Liver tissue; Linear model; Perforation; Soft tissue; Simulation; Biomedical engineering; Materials science; Algorithm; Surgery; Finite element method; Structural engineering; Engineering; Composite material; Machine learning","score_opus":0.05522292957347681,"score_gpt":0.2745313301477562,"score_spread":0.21930840057427942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990369221","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":[0.3009081,0.000074761716,0.6987325,0.00001879695,0.00006974097,0.00009509648,0.0000063389093,0.00008632132,0.00000833871],"genre_scores_gemma":[0.95951194,0.00004832723,0.040091705,0.00003963686,0.00020372911,0.000017249517,0.000028174194,0.000038566413,0.000020686708],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869496,0.000013450464,0.00041191216,0.0002240727,0.00034173368,0.00031385064],"domain_scores_gemma":[0.9994161,0.00012847564,0.000039123846,0.00015024179,0.00011248737,0.000153541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027733564,0.00017813045,0.00041835033,0.00027005855,0.0001140428,0.000054398424,0.000102408245,0.00014026868,0.00004816207],"category_scores_gemma":[0.00019647814,0.00016172328,0.00019641618,0.00035525483,0.00004975469,0.0002840307,0.000029565961,0.00012457183,0.000015111557],"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":[0.000015435871,0.00002712985,0.0000025497156,0.00016918311,0.00022632146,0.00001030814,0.0003052115,0.9901574,0.00884525,0.000006957779,0.0000026360415,0.00023160482],"study_design_scores_gemma":[0.00018741273,0.0000073011665,5.466451e-7,0.00011828487,0.00082138815,0.0000011720829,0.000014008413,0.992025,0.0064751487,0.00014514125,0.00000686831,0.00019772568],"about_ca_topic_score_codex":0.0001862637,"about_ca_topic_score_gemma":0.00003198926,"teacher_disagreement_score":0.6586408,"about_ca_system_score_codex":0.0000795851,"about_ca_system_score_gemma":0.00006923939,"threshold_uncertainty_score":0.6594884},"labels":[],"label_agreement":null},{"id":"W1991042152","doi":"10.1016/s1361-8415(02)00090-7","title":"Irregularity index: A new border irregularity measure for cutaneous melanocytic lesions","year":2002,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":97,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Hospital and Health Sciences Centre; University of British Columbia; BC Cancer Agency; Simon Fraser University","funders":"","keywords":"Lesion; Index (typography); Measure (data warehouse); Pattern recognition (psychology); Computer science; Artificial intelligence; Texture (cosmology); Medicine; Mathematics; Pathology; Data mining; Image (mathematics)","score_opus":0.023035226442801503,"score_gpt":0.29739657225210875,"score_spread":0.27436134580930727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991042152","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":[0.054499228,0.0019178485,0.8681233,0.052014153,0.00066660286,0.0022881941,0.000051237817,0.0008822703,0.01955718],"genre_scores_gemma":[0.9402675,0.00014824864,0.0046822587,0.003103918,0.0005693704,0.000067269066,0.000097159085,0.000053193355,0.051011078],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967166,0.000099052646,0.00057375804,0.00066035014,0.0013964303,0.000553797],"domain_scores_gemma":[0.99760205,0.0001694482,0.00012793137,0.0008047683,0.0002501935,0.0010455835],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004470933,0.00031289697,0.00086212554,0.0005738742,0.00024335163,0.00008050429,0.000264107,0.00032225018,0.018260991],"category_scores_gemma":[0.0014938441,0.00026686734,0.00088217505,0.0015456128,0.0001802806,0.00008123534,0.000112376634,0.00046984124,0.00022028998],"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":[0.0009935315,0.0032755772,0.009859869,0.0005277453,0.016887601,0.0073876926,0.0009123066,0.00010215124,0.0018697693,0.0006725081,0.25431675,0.7031945],"study_design_scores_gemma":[0.0097270915,0.0009828873,0.011256924,0.00021501344,0.030245492,0.0034274382,0.0005259934,0.4335624,0.00091261556,0.0011780465,0.50653243,0.0014336852],"about_ca_topic_score_codex":0.00053204014,"about_ca_topic_score_gemma":0.0011693737,"teacher_disagreement_score":0.8857683,"about_ca_system_score_codex":0.00018925188,"about_ca_system_score_gemma":0.00013407276,"threshold_uncertainty_score":0.99997836},"labels":[],"label_agreement":null},{"id":"W1992845372","doi":"10.1016/j.media.2013.04.008","title":"The impact of registration accuracy on imaging validation study design: A novel statistical power calculation","year":2013,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lawson Health Research Institute; Western University","funders":"","keywords":"Statistical power; Context (archaeology); Modalities; Computer science; Image registration; Medical imaging; Statistical model; Statistical hypothesis testing; Monte Carlo method; Power (physics); Artificial intelligence; Medical physics; Statistics; Mathematics; Image (mathematics); Medicine","score_opus":0.017757023342676096,"score_gpt":0.3701413791481233,"score_spread":0.3523843558054472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992845372","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":[0.36799327,0.00002546755,0.6271374,0.0037497906,0.000039024904,0.0005237609,0.0000031583656,0.00003394502,0.00049417606],"genre_scores_gemma":[0.99527276,0.000013711617,0.0041313,0.00022496011,0.00008273026,0.000038208116,0.0000857937,0.000018930165,0.00013161369],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971512,0.00028883145,0.00067692023,0.00032916115,0.0012676523,0.00028622852],"domain_scores_gemma":[0.997094,0.0014852536,0.00028423755,0.0004692961,0.00033939598,0.00032782913],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019274531,0.00018275426,0.00044626,0.00025811567,0.00017765134,0.00013333918,0.00017908067,0.000061524996,0.0010128049],"category_scores_gemma":[0.010435475,0.00010575255,0.00028796418,0.0008043432,0.00024938054,0.0001891325,0.00003906219,0.00046073284,0.000037704416],"study_design_candidate":"observational","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":[0.00094602327,0.007512708,0.5827408,0.00008183209,0.011038128,0.00040433215,0.0025598211,0.010418605,0.0468063,0.0008706482,0.045747988,0.29087284],"study_design_scores_gemma":[0.0011280756,0.0003544899,0.39755514,0.000030135041,0.00095570553,0.000015526166,0.00019836135,0.59933674,0.00016279888,0.0001321782,0.000027083557,0.00010373666],"about_ca_topic_score_codex":0.0016788665,"about_ca_topic_score_gemma":0.00000484931,"teacher_disagreement_score":0.6272795,"about_ca_system_score_codex":0.00011374163,"about_ca_system_score_gemma":0.00019081053,"threshold_uncertainty_score":0.9999004},"labels":[],"label_agreement":null},{"id":"W1993062536","doi":"10.1016/j.media.2011.07.006","title":"Multi-modal registration of speckle-tracked freehand 3D ultrasound to CT in the lumbar spine","year":2011,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Artificial intelligence; Computer vision; Computer science; Modal; 3D ultrasound; Lumbar spine; Ultrasound; Radiology; Medicine; Surgery; Materials science","score_opus":0.017139208940812937,"score_gpt":0.2627789060975648,"score_spread":0.24563969715675188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993062536","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":[0.7088612,0.0002567767,0.28585744,0.0005710839,0.000076574666,0.0001393213,0.00001269997,0.000084096115,0.004140856],"genre_scores_gemma":[0.98668015,0.000105618754,0.012544678,0.0002674626,0.00009337165,0.000015393001,0.000047024587,0.000014136958,0.00023215597],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978539,0.00011267484,0.0006265215,0.00026438799,0.00084121025,0.0003013282],"domain_scores_gemma":[0.9990265,0.000091607464,0.0000657513,0.00049613084,0.00006157183,0.00025843596],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012097489,0.00017672697,0.0004860522,0.00039062096,0.000038479375,0.000031990843,0.00047550074,0.0000661246,0.0022143144],"category_scores_gemma":[0.0012273598,0.00012648008,0.00026573744,0.0019996408,0.00019224765,0.00011243598,0.000024569317,0.00033097755,0.00006287971],"study_design_candidate":"observational","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":[0.00008440749,0.0071208845,0.37112755,0.0015328749,0.020763002,0.0071571223,0.038372703,0.014035331,0.29680887,0.00059579225,0.053566217,0.18883525],"study_design_scores_gemma":[0.0017269708,0.00011008617,0.39763355,0.00018831824,0.0045015835,0.00004572642,0.0016170556,0.5805403,0.011171464,0.00016339512,0.0014537661,0.00084780203],"about_ca_topic_score_codex":0.00095334713,"about_ca_topic_score_gemma":0.0013114446,"teacher_disagreement_score":0.56650496,"about_ca_system_score_codex":0.000028628061,"about_ca_system_score_gemma":0.000021806653,"threshold_uncertainty_score":0.9986978},"labels":[],"label_agreement":null},{"id":"W1995083187","doi":"10.1016/j.media.2008.04.002","title":"Area-preserving flattening maps of 3D ultrasound carotid arteries images","year":2008,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thrombosis and Atherosclerosis Research Institute; Western University; Robarts Clinical Trials","funders":"Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Flattening; Computer vision; Artificial intelligence; Carotid arteries; Ultrasound; Computer science; Anatomy; Radiology; Medicine; Surgery; Physics","score_opus":0.0155384322519146,"score_gpt":0.2721831698747432,"score_spread":0.25664473762282863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995083187","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":[0.010861117,0.00012083516,0.9855629,0.0007936458,0.00006872956,0.00010830377,0.000013717582,0.00030459545,0.0021661527],"genre_scores_gemma":[0.36797103,0.00038816655,0.62923956,0.0012198953,0.00011615816,0.0000456728,0.00009781042,0.000023217572,0.0008984862],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99624705,0.00023692234,0.0007692538,0.0005590598,0.0017676033,0.0004201192],"domain_scores_gemma":[0.9974518,0.00058279786,0.0002683022,0.0009851669,0.00030454874,0.00040741774],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008874317,0.00023148628,0.00064467243,0.00056002394,0.0001895329,0.00010184716,0.001633513,0.00012316446,0.0022999644],"category_scores_gemma":[0.001745748,0.00019951446,0.00031584303,0.0021549757,0.0007168648,0.0009867585,0.00037051804,0.00032507876,0.00003678153],"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":[0.00004046408,0.0013860659,0.2333604,0.000495958,0.005855411,0.004008095,0.014902854,0.00011391512,0.4032928,0.00045567917,0.23316331,0.10292505],"study_design_scores_gemma":[0.0015167113,0.00027332405,0.044907235,0.00028056058,0.0013239264,0.0004933642,0.0006855055,0.043802477,0.9028224,0.0013037625,0.001167992,0.0014227878],"about_ca_topic_score_codex":0.0003016266,"about_ca_topic_score_gemma":0.000027762497,"teacher_disagreement_score":0.49952954,"about_ca_system_score_codex":0.0000385946,"about_ca_system_score_gemma":0.00014519891,"threshold_uncertainty_score":0.99861205},"labels":[],"label_agreement":null},{"id":"W1996595747","doi":"10.1016/j.media.2010.12.003","title":"Evaluating intensity normalization on MRIs of human brain with multiple sclerosis","year":2010,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":178,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University Health Centre; McGill University; NeuroRx Research (Canada)","funders":"","keywords":"Artificial intelligence; Computer science; Segmentation; Normalization (sociology); Pattern recognition (psychology); Bayesian probability; Voxel; Computer vision","score_opus":0.04306000652787775,"score_gpt":0.35168841171107285,"score_spread":0.3086284051831951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996595747","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":[0.21611398,0.0000025039149,0.782203,0.0011598082,0.0000363387,0.00010572862,0.0000018770884,0.00014262267,0.00023412936],"genre_scores_gemma":[0.7854133,0.0000030612973,0.21280742,0.0016164164,0.000041307296,0.000017438733,0.000032803964,0.000008598955,0.000059602964],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99699473,0.00017881018,0.0004890453,0.00043643537,0.0016732335,0.00022774091],"domain_scores_gemma":[0.99787617,0.00036871218,0.00026837442,0.0007281877,0.00048160547,0.00027694376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018948644,0.00014993199,0.0003830196,0.00043475121,0.00013757756,0.00008445158,0.0007992762,0.00011021259,0.0008655478],"category_scores_gemma":[0.0031127285,0.00011446024,0.00014903123,0.0018300958,0.00032286512,0.00039998954,0.00020306928,0.00038807065,0.000017004782],"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":[0.000036391517,0.00066464866,0.03552946,0.00005424882,0.0007016203,0.00005905701,0.0013212416,0.000054958884,0.7398499,0.0006838215,0.003769066,0.21727557],"study_design_scores_gemma":[0.0009948574,0.0005307461,0.050164696,0.00009743339,0.0003629905,0.0000056148874,0.0000702946,0.43904027,0.50819504,0.00020935298,0.000019980518,0.0003087119],"about_ca_topic_score_codex":0.00038332795,"about_ca_topic_score_gemma":0.0003589897,"teacher_disagreement_score":0.5693956,"about_ca_system_score_codex":0.000023371607,"about_ca_system_score_gemma":0.00006992091,"threshold_uncertainty_score":0.94771415},"labels":[],"label_agreement":null},{"id":"W1996757269","doi":"10.1016/s1361-8415(01)00049-4","title":"A computational model of postoperative knee kinematics","year":2001,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Total Knee Arthroplasty Outcomes","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Kinematics; Knee Joint; Computer science; Total knee replacement; Prosthesis; Surgical planning; Joint (building); Orthodontics; Medicine; Surgery; Artificial intelligence; Engineering; Physics","score_opus":0.01508868387873902,"score_gpt":0.3006531355982514,"score_spread":0.2855644517195124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996757269","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":[0.5835992,0.00005137419,0.40490544,0.007673963,0.000018299876,0.000116505464,0.0000134124175,0.000040353996,0.0035814291],"genre_scores_gemma":[0.92469215,0.000017646633,0.07179716,0.0018910747,0.000021643706,0.000005621209,0.00007709309,0.000012075851,0.0014855547],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981947,0.000031347987,0.00045870565,0.00019084227,0.00094883714,0.0001755774],"domain_scores_gemma":[0.9989832,0.00016395444,0.000091740934,0.00023132605,0.0002699461,0.0002598113],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022019514,0.0001240518,0.00059006055,0.00031565488,0.000038217728,0.000009471132,0.00007953719,0.0000772113,0.0031918727],"category_scores_gemma":[0.0007896056,0.00009484033,0.0003288972,0.0009512732,0.0002404787,0.00008616434,0.000054793894,0.00016365449,0.00007905711],"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":[0.0009021453,0.0053820955,0.51500106,0.00048463946,0.023840206,0.002753332,0.007544212,0.3760351,0.01022791,0.0066690235,0.017050808,0.034109496],"study_design_scores_gemma":[0.0011561512,0.00010178099,0.0137701025,0.0000308294,0.0013859995,0.000050790335,0.000145977,0.982741,0.0001299301,0.0003021393,0.000091904534,0.00009336916],"about_ca_topic_score_codex":0.000040981897,"about_ca_topic_score_gemma":0.00003388357,"teacher_disagreement_score":0.6067059,"about_ca_system_score_codex":0.000028942211,"about_ca_system_score_gemma":0.00015190282,"threshold_uncertainty_score":0.99771935},"labels":[],"label_agreement":null},{"id":"W1997823434","doi":"10.1016/s1361-8415(02)00133-0","title":"Robust registration for computer-integrated orthopedic surgery: Laboratory validation and clinical experience","year":2003,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":91,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Outlier; Artificial intelligence; Computer science; Computer vision; Orthopedic surgery; Spurious relationship; Image registration; Process (computing); Image (mathematics); Medicine; Surgery; Machine learning","score_opus":0.02871522958399645,"score_gpt":0.27951944716133803,"score_spread":0.25080421757734156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997823434","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":[0.17795418,0.00006433787,0.82152396,0.00008343444,0.00015560287,0.00007612541,0.000007826265,0.00008319558,0.000051337625],"genre_scores_gemma":[0.9742258,0.00040846426,0.02460488,0.00019096656,0.00015332342,0.000017573308,0.00033462755,0.000023628738,0.000040692386],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986847,0.00013908382,0.0004998417,0.00023394475,0.00028338438,0.00015904347],"domain_scores_gemma":[0.9990459,0.00034722307,0.00006358981,0.00017448807,0.00018302308,0.00018575879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000931765,0.00011679066,0.0003122585,0.00015649383,0.00006703388,0.00007450102,0.00005406358,0.00013946451,0.00013897852],"category_scores_gemma":[0.00101934,0.00010681079,0.00013449875,0.00082684105,0.000097200675,0.0001332637,0.0000053007125,0.000113550625,0.000003467627],"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":[0.00006047025,0.00055565767,0.3065415,0.00042062634,0.0030957998,0.00014089195,0.0005938522,0.5660938,0.00076410087,0.0015687399,0.03961871,0.080545865],"study_design_scores_gemma":[0.00019889281,0.000019484816,0.001917524,0.000014962143,0.0002988923,0.0000013049549,0.000046542205,0.9948421,0.00041216702,0.000009867309,0.0021033802,0.00013485584],"about_ca_topic_score_codex":0.000017304274,"about_ca_topic_score_gemma":0.00004905149,"teacher_disagreement_score":0.79691905,"about_ca_system_score_codex":0.00002444351,"about_ca_system_score_gemma":0.000059555892,"threshold_uncertainty_score":0.43556175},"labels":[],"label_agreement":null},{"id":"W2000714473","doi":"10.1016/j.media.2012.04.008","title":"Surface-based multi-template automated hippocampal segmentation: Application to temporal lobe epilepsy","year":2012,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"Canadian Institutes of Health Research","keywords":"Epilepsy; Temporal lobe; Segmentation; Artificial intelligence; Hippocampal formation; Computer science; Pattern recognition (psychology); Surface (topology); Computer vision; Neuroscience; Psychology; Mathematics","score_opus":0.018889320166164552,"score_gpt":0.3355391048080844,"score_spread":0.31664978464191984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000714473","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":[0.012537478,0.00005602076,0.9825048,0.0024255903,0.0001381535,0.00046455814,0.0000102218555,0.0017681542,0.00009506515],"genre_scores_gemma":[0.4214274,0.000004978207,0.5746041,0.003494605,0.000081678045,0.000108468004,0.00017629839,0.000015811183,0.00008668967],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958236,0.0003999651,0.0007926428,0.0006374328,0.0016976871,0.0006486709],"domain_scores_gemma":[0.9970669,0.00022703853,0.0002477831,0.0009123496,0.00024379852,0.0013021444],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001990165,0.00028845778,0.0004902153,0.00048323045,0.00017503646,0.00019840282,0.001161965,0.00017994377,0.0012713725],"category_scores_gemma":[0.00046263065,0.00025984662,0.00025972558,0.0036141847,0.00015879,0.000952476,0.00025429617,0.00026509608,0.0008053412],"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":[0.00008700893,0.0047515463,0.4071015,0.00025946513,0.0026078713,0.0003173152,0.004298133,0.0017609372,0.12142933,0.00046372638,0.07958089,0.37734225],"study_design_scores_gemma":[0.0008543869,0.00006887605,0.016292516,0.000024305691,0.00031552455,0.000007038761,0.0000688754,0.90035784,0.08088289,0.000028758417,0.00062499853,0.0004740103],"about_ca_topic_score_codex":0.00032196107,"about_ca_topic_score_gemma":0.00004132718,"teacher_disagreement_score":0.8985969,"about_ca_system_score_codex":0.00017263852,"about_ca_system_score_gemma":0.00015192378,"threshold_uncertainty_score":0.9999854},"labels":[],"label_agreement":null},{"id":"W2001484348","doi":"10.1016/j.media.2004.06.014","title":"Validation of dynamic heart models obtained using non-linear registration for virtual reality training, planning, and guidance of minimally invasive cardiac surgeries","year":2004,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":94,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Robarts Clinical Trials","funders":"","keywords":"Virtual reality; Training (meteorology); Computer science; Artificial intelligence; Image registration; Computer vision; Minimally invasive procedures; Medicine; Surgery; Image (mathematics); Geography","score_opus":0.06121609951463408,"score_gpt":0.36113409017281217,"score_spread":0.2999179906581781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001484348","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":[0.7734461,0.000081515944,0.22565281,0.00036412838,0.000022857977,0.00017140352,0.000031723277,0.000014164615,0.0002153253],"genre_scores_gemma":[0.99002206,0.000017091126,0.009500203,0.00009074809,0.00004647106,0.000008407497,0.0002774183,0.0000117335885,0.000025854686],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823135,0.00007183354,0.00069624453,0.00027236316,0.00055722543,0.0001709788],"domain_scores_gemma":[0.998557,0.0004372793,0.00029501788,0.00018817678,0.00034545464,0.00017712072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001144047,0.00013017251,0.00075281935,0.00021275075,0.000059640934,0.000010289189,0.000050182975,0.00012934828,0.000039621154],"category_scores_gemma":[0.0017660366,0.000116849405,0.0003066442,0.00054796494,0.00028540927,0.00016059414,0.000018464852,0.00009874917,1.8614064e-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":[0.0069573,0.0019455949,0.15745072,0.0027276785,0.014666705,0.00028328164,0.039008103,0.47908342,0.2709224,0.003270862,0.00019635132,0.023487583],"study_design_scores_gemma":[0.00517976,0.00047099206,0.036399182,0.00050698436,0.0029797407,0.000008897551,0.0025448436,0.92745215,0.02334449,0.00078222534,0.000055831995,0.00027493114],"about_ca_topic_score_codex":0.00020863269,"about_ca_topic_score_gemma":0.00002342575,"teacher_disagreement_score":0.4483687,"about_ca_system_score_codex":0.000044810895,"about_ca_system_score_gemma":0.00033712576,"threshold_uncertainty_score":0.47649804},"labels":[],"label_agreement":null},{"id":"W2003074994","doi":"10.1016/j.media.2007.08.003","title":"Validation of a new surgical procedure for percutaneous scaphoid fixation using intra-operative ultrasound","year":2007,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Orthopedic Surgery and Rehabilitation","field":"Medicine","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kingston General Hospital; Queen's University","funders":"","keywords":"Percutaneous; Medicine; Fixation (population genetics); Fluoroscopy; Ultrasound; Scaphoid fracture; Radiology; Wrist","score_opus":0.015285398822714959,"score_gpt":0.33574210147062916,"score_spread":0.3204567026479142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003074994","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":[0.8908689,0.000112599,0.107642934,0.00063922047,0.0000638568,0.00033812813,0.0000074589507,0.00002733184,0.0002995864],"genre_scores_gemma":[0.9881079,0.000037149508,0.010503137,0.00013763884,0.00037283395,0.0000048472784,0.0002705816,0.0000136745375,0.00055222533],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980731,0.00007019003,0.00062019896,0.00029209946,0.0007172622,0.00022712849],"domain_scores_gemma":[0.99785334,0.0010917508,0.00016726954,0.00017018495,0.00039908956,0.00031835286],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001537483,0.00013567256,0.00049596175,0.0003965344,0.0000820446,0.000015841857,0.000052958407,0.00019449074,0.0012193554],"category_scores_gemma":[0.0040532756,0.00010368514,0.00039048144,0.0012178869,0.00017509302,0.00013958308,0.000010307327,0.00015930033,0.0000040761447],"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":[0.0025089695,0.001681553,0.13805719,0.00079907425,0.0043285037,0.0006842884,0.008879549,0.000643419,0.74530673,0.00014279422,0.0012200018,0.09574794],"study_design_scores_gemma":[0.009192737,0.002588643,0.037819073,0.000945393,0.026532428,0.004854713,0.009912896,0.09811139,0.8024238,0.0006889309,0.0054952856,0.0014347201],"about_ca_topic_score_codex":0.00010942978,"about_ca_topic_score_gemma":0.000037977235,"teacher_disagreement_score":0.100238115,"about_ca_system_score_codex":0.00007540227,"about_ca_system_score_gemma":0.00035010072,"threshold_uncertainty_score":0.9996937},"labels":[],"label_agreement":null},{"id":"W2003863798","doi":"10.1016/j.media.2010.05.010","title":"Non-local MRI upsampling","year":2010,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":274,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"","keywords":"Upsampling; Interpolation (computer graphics); Artificial intelligence; Computer science; Computer vision; Bicubic interpolation; Image scaling; Constraint (computer-aided design); Coherence (philosophical gambling strategy); Nearest-neighbor interpolation; Image (mathematics); Mathematics; Algorithm; Multivariate interpolation; Image processing; Bilinear interpolation; Statistics","score_opus":0.005285407020192026,"score_gpt":0.2967542073361372,"score_spread":0.2914688003159452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003863798","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":[0.0008661858,0.000031611744,0.993889,0.0030611544,0.000121475976,0.00004609759,6.7555436e-7,0.0005498181,0.0014340017],"genre_scores_gemma":[0.18595304,0.000014347884,0.81285053,0.0009180659,0.00010398106,0.000015432472,0.000004823892,0.000010301972,0.000129477],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978719,0.000025871597,0.00032897826,0.0005590096,0.0008307881,0.00038348848],"domain_scores_gemma":[0.9983027,0.00011798648,0.00010303452,0.0009366393,0.0001880155,0.00035163693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007620334,0.00016738578,0.00033220323,0.00036265235,0.00015713234,0.00021820354,0.0017663507,0.00014385323,0.00039603515],"category_scores_gemma":[0.00054198544,0.00014270154,0.00021835449,0.002070073,0.00032682094,0.0007682737,0.00054557767,0.0006722446,0.000104693245],"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":[0.000013579314,0.0007092946,0.006775966,0.00008994345,0.0012949961,0.0013546861,0.0012078828,0.00030277204,0.06470112,0.010039628,0.010808019,0.9027021],"study_design_scores_gemma":[0.00011298964,0.0000144648375,0.00038331116,0.000009897393,0.00011787122,0.000017691227,0.0000108200675,0.9834045,0.0072071925,0.0061600967,0.002350816,0.0002103496],"about_ca_topic_score_codex":0.000054066673,"about_ca_topic_score_gemma":0.00006119747,"teacher_disagreement_score":0.9831017,"about_ca_system_score_codex":0.000020599755,"about_ca_system_score_gemma":0.000112935086,"threshold_uncertainty_score":0.58191997},"labels":[],"label_agreement":null},{"id":"W2004369235","doi":"10.1016/j.media.2008.09.001","title":"Depth potential function for folding pattern representation, registration and analysis","year":2008,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":123,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada","keywords":"Surface (topology); Curvature; Projection (relational algebra); Mathematics; Geometry; Representation (politics); Scalar (mathematics); Plane (geometry); Function (biology); Invariant (physics); Algorithm; Artificial intelligence; Computer science","score_opus":0.0154725849044681,"score_gpt":0.25613802021610516,"score_spread":0.24066543531163706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004369235","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":[0.18115602,0.00019920999,0.8180568,0.00019945619,0.000038356386,0.000048815193,0.000009228305,0.00013087502,0.00016122422],"genre_scores_gemma":[0.9966347,0.0003101604,0.0020844664,0.000090201385,0.0001654565,0.000025345344,0.00046328068,0.000016964133,0.00020938557],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847883,0.00004185751,0.00042784458,0.0003437561,0.0004913487,0.00021634345],"domain_scores_gemma":[0.99928904,0.00007177132,0.0000684402,0.00026339677,0.00012949249,0.00017785042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033228242,0.00015039633,0.0004305364,0.00067973376,0.00019697772,0.000062861625,0.00010042667,0.000112251975,0.00027521115],"category_scores_gemma":[0.00016170701,0.00014392937,0.0005428226,0.0019947584,0.00006434187,0.0001931707,0.00001783173,0.000117531745,0.0000065018326],"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":[0.00004514382,0.00013967867,0.19435164,0.00012502761,0.0453611,0.00015989711,0.0007701897,0.6237125,0.0028304183,0.000019654963,0.005743184,0.12674159],"study_design_scores_gemma":[0.00024213594,0.0000128493275,0.019766882,0.0000035696294,0.011979523,0.000004170513,0.00007136824,0.96747816,0.00018778363,0.00005523763,0.000046470104,0.00015184561],"about_ca_topic_score_codex":0.00021483234,"about_ca_topic_score_gemma":0.00040913286,"teacher_disagreement_score":0.8159723,"about_ca_system_score_codex":0.000027071408,"about_ca_system_score_gemma":0.000014439831,"threshold_uncertainty_score":0.58692694},"labels":[],"label_agreement":null},{"id":"W2007421864","doi":"10.1016/j.media.2009.09.005","title":"A nonlinear identification method to study effective connectivity in functional MRI","year":2009,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University","funders":"Canadian Institutes of Health Research; Institut National de la Santé et de la Recherche Médicale","keywords":"Identification (biology); Artificial intelligence; Computer science; Nonlinear system; Machine learning; Pattern recognition (psychology); Biology","score_opus":0.022841829544684056,"score_gpt":0.3477557489552384,"score_spread":0.32491391941055436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007421864","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":[0.55744153,0.0000120434215,0.42281872,0.018352237,0.00012958916,0.00072382856,0.000012874188,0.00010234592,0.00040683796],"genre_scores_gemma":[0.99139935,0.0000029138553,0.0023034709,0.0058390633,0.00014902042,0.00017007154,0.000006563854,0.0000101978685,0.00011932772],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9954217,0.0013406631,0.00044771266,0.0011134855,0.0013470718,0.00032937783],"domain_scores_gemma":[0.9917716,0.007319534,0.00010655756,0.00042473193,0.0001532875,0.00022432188],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003070942,0.00021839257,0.00054488605,0.00086736126,0.00021489785,0.00007781843,0.00028283815,0.00008136847,0.0005582373],"category_scores_gemma":[0.03649417,0.00019811498,0.00024030496,0.0047718766,0.00008573322,0.00028853485,0.00012827954,0.00037930862,0.00020948873],"study_design_candidate":"observational","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":[0.0015996066,0.023335151,0.13473894,0.000036932004,0.0026873464,0.0016645258,0.008570548,0.006750311,0.4184607,0.0009900234,0.0066228737,0.39454305],"study_design_scores_gemma":[0.0013269166,0.00059093506,0.9017813,0.00000988433,0.00059332483,0.000013229621,0.0005870404,0.044519465,0.048666045,0.0011635439,0.00037947297,0.00036880604],"about_ca_topic_score_codex":0.00016281602,"about_ca_topic_score_gemma":0.00050625036,"teacher_disagreement_score":0.7670424,"about_ca_system_score_codex":0.00016894491,"about_ca_system_score_gemma":0.000053749616,"threshold_uncertainty_score":0.9716219},"labels":[],"label_agreement":null},{"id":"W2007981068","doi":"10.1016/j.media.2004.06.016","title":"Brain morphometry using 3D moment invariants","year":2004,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":86,"is_retracted":false,"has_abstract":false,"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":"Invariant (physics); Artificial intelligence; Principal component analysis; Pattern recognition (psychology); Computer science; Moment (physics); Scale (ratio); Mathematics; Computer vision; Physics; Cartography; Geography","score_opus":0.04630396967636442,"score_gpt":0.3427405736488299,"score_spread":0.2964366039724655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007981068","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":[0.16872211,0.000038514245,0.82646453,0.003128929,0.00004882685,0.000081616425,0.0000123440805,0.00006491551,0.001438206],"genre_scores_gemma":[0.6363301,0.00001729867,0.36033913,0.0026195648,0.00018114381,0.000011531189,0.000036070905,0.000022947414,0.00044216804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977606,0.00011574002,0.00051633816,0.00035917314,0.00090183836,0.0003463454],"domain_scores_gemma":[0.99863803,0.00035225393,0.00014709223,0.0004505498,0.00008063256,0.00033141582],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010946555,0.0001765339,0.0005080139,0.0004708124,0.00013930937,0.00006712559,0.0003088243,0.00017784843,0.009627367],"category_scores_gemma":[0.0026502996,0.00013430303,0.00031347427,0.002661097,0.00011308587,0.0001250827,0.00015683989,0.00027428457,0.000119677934],"study_design_candidate":"theoretical_or_conceptual","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":[0.00022144725,0.027107151,0.07588999,0.0010219369,0.048132814,0.0176354,0.0031129518,0.0063146055,0.0740444,0.5347637,0.13595222,0.07580342],"study_design_scores_gemma":[0.01998981,0.00079407817,0.062601745,0.00072500214,0.02963457,0.00051458104,0.0020574883,0.42423204,0.014275192,0.4197711,0.01940748,0.0059969095],"about_ca_topic_score_codex":0.00032906918,"about_ca_topic_score_gemma":0.00003649761,"teacher_disagreement_score":0.46760803,"about_ca_system_score_codex":0.00012345762,"about_ca_system_score_gemma":0.00008757996,"threshold_uncertainty_score":0.991278},"labels":[],"label_agreement":null},{"id":"W2009911194","doi":"10.1016/j.media.2014.07.003","title":"Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: the VESSEL12 study","year":2014,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":158,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Heart, Lung, and Blood Institute","keywords":"Segmentation; Computer science; Automation; Artificial intelligence; Computed tomography; Algorithm; Data mining; Machine learning; Radiology; Medicine; Engineering","score_opus":0.012072452417376455,"score_gpt":0.32582657637598206,"score_spread":0.3137541239586056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009911194","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":[0.74316144,0.00011975133,0.24964423,0.005779485,0.00015792793,0.0007961295,0.0000031047773,0.00010095178,0.00023698516],"genre_scores_gemma":[0.9957392,0.0000066000307,0.0032511612,0.00074951496,0.00010497501,0.0000499596,0.000048713493,0.000016459,0.0000334172],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767774,0.00036037745,0.00058211095,0.0002883411,0.0008318069,0.00025962671],"domain_scores_gemma":[0.9985811,0.0005035009,0.0001979801,0.00042773545,0.0001366139,0.00015306644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021777898,0.00015056899,0.0006124961,0.00033192252,0.00014611604,0.00003778344,0.0003824384,0.0000639024,0.0000545619],"category_scores_gemma":[0.0010914662,0.000083745275,0.00031856247,0.002145392,0.00028578803,0.000053835418,0.000095249816,0.00041964298,0.0000010166945],"study_design_candidate":"observational","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":[0.000054621745,0.00095368776,0.9749787,0.00012454591,0.0019846736,0.000013412949,0.0019397856,0.002605286,0.00085400476,0.000041371724,0.0034730781,0.012976859],"study_design_scores_gemma":[0.00152763,0.00005789203,0.3228437,0.00006080501,0.0013335724,0.0000030167384,0.00047260438,0.6734378,0.000111414076,0.000013958354,0.00007880112,0.000058847858],"about_ca_topic_score_codex":0.00062793755,"about_ca_topic_score_gemma":0.00008328503,"teacher_disagreement_score":0.67083246,"about_ca_system_score_codex":0.00003950367,"about_ca_system_score_gemma":0.000063841035,"threshold_uncertainty_score":0.34150332},"labels":[],"label_agreement":null},{"id":"W2010139045","doi":"10.1016/j.media.2006.09.001","title":"3D prostate model formation from non-parallel 2D ultrasound biopsy images","year":2006,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Robarts Clinical Trials; Western University","funders":"Canadian Institutes of Health Research; Prostate Cancer Foundation","keywords":"Biopsy; 3D ultrasound; Prostate biopsy; Prostate cancer; Prostate; Ultrasound; Radiology; Medicine; Gold standard (test); Computer science; Cancer; Internal medicine","score_opus":0.006800600494576521,"score_gpt":0.2638776791929591,"score_spread":0.2570770786983826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010139045","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":[0.004473694,0.00009037352,0.99142885,0.0013318053,0.000050332506,0.00020823104,0.00003710876,0.00045827444,0.001921314],"genre_scores_gemma":[0.11890415,0.00012381523,0.8777218,0.0013892815,0.00012584277,0.000082612874,0.0005038432,0.000017887009,0.0011308005],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99626446,0.00013933014,0.00080651115,0.00064564974,0.0016773045,0.00046675315],"domain_scores_gemma":[0.998076,0.0002451689,0.0002666834,0.0008235938,0.00023127222,0.00035723276],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007570112,0.00027036443,0.00047143246,0.00047028618,0.0001657213,0.00043730627,0.0012029674,0.00015663488,0.00095919723],"category_scores_gemma":[0.00037654984,0.00022887294,0.00028560768,0.0017135674,0.00026344584,0.0018744619,0.000250026,0.0003093907,0.0002057584],"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":[0.00007838844,0.002542622,0.005567618,0.00019206991,0.0025482082,0.0016703283,0.0041720597,0.009150767,0.31472245,0.001211404,0.3092454,0.34889868],"study_design_scores_gemma":[0.00048726884,0.000021486201,0.0014223332,0.000021844242,0.00030262058,0.0000115607645,0.000029779547,0.9574968,0.036151923,0.0036603925,0.00008109686,0.00031285197],"about_ca_topic_score_codex":0.0010847114,"about_ca_topic_score_gemma":0.00006555163,"teacher_disagreement_score":0.9483461,"about_ca_system_score_codex":0.000086960354,"about_ca_system_score_gemma":0.00010477333,"threshold_uncertainty_score":0.99995404},"labels":[],"label_agreement":null},{"id":"W2012048142","doi":"10.1016/j.media.2014.10.005","title":"Quantification of local changes in myocardial motion by diffeomorphic registration via currents: Application to paced hypertrophic obstructive cardiomyopathy in 2D echocardiographic sequences","year":2014,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiomyopathy and Myosin Studies","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Heart Institute; Université de Montréal","funders":"Seventh Framework Programme; Centro para el Desarrollo Tecnológico Industrial","keywords":"Normalization (sociology); Hypertrophic cardiomyopathy; Artificial intelligence; Ventricular outflow tract; Cardiology; Pattern recognition (psychology); Computer science; Medicine; Internal medicine; Computer vision","score_opus":0.009045251812629227,"score_gpt":0.2643767267392591,"score_spread":0.2553314749266299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012048142","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":[0.53007746,0.00041024617,0.46724224,0.0015930932,0.000092139,0.00042228858,0.000022065118,0.000031520525,0.000108961],"genre_scores_gemma":[0.998108,0.0005908796,0.00028834274,0.00015799946,0.00018463827,0.00026395483,0.0003806826,0.00001760096,0.000007857597],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99675024,0.00043851783,0.00070744246,0.0006824456,0.0010927896,0.00032857232],"domain_scores_gemma":[0.99856275,0.00014801754,0.00023725822,0.0005468043,0.00028267366,0.0002225058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016005202,0.0002631026,0.0011943219,0.0012276659,0.00006330921,0.000019571205,0.00015857533,0.00022859164,0.000015182933],"category_scores_gemma":[0.00061944383,0.00023834336,0.0004350086,0.003774001,0.00039424576,0.00012823375,0.00005533655,0.00031925587,0.000008913455],"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":[0.0005763923,0.0006511713,0.52643937,0.0003526103,0.002005484,0.00007154912,0.0012479658,0.0015791322,0.11752862,0.00016507097,0.0003563706,0.34902626],"study_design_scores_gemma":[0.0024303559,0.0003768489,0.94431984,0.00024376684,0.003131483,0.000032816,0.0013811946,0.038883064,0.00792555,0.0003826945,0.00040449065,0.00048790523],"about_ca_topic_score_codex":0.001853671,"about_ca_topic_score_gemma":0.0010652659,"teacher_disagreement_score":0.4680306,"about_ca_system_score_codex":0.00016928175,"about_ca_system_score_gemma":0.00004620989,"threshold_uncertainty_score":0.971936},"labels":[],"label_agreement":null},{"id":"W2013160622","doi":"10.1016/j.media.2013.03.009","title":"Tractometer: Towards validation of tractography pipelines","year":2013,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":236,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Tractography; Computer science; Artificial intelligence; Seeding; Pattern recognition (psychology); Computer vision; Mathematics; Diffusion MRI; Engineering; Magnetic resonance imaging","score_opus":0.04430028071975608,"score_gpt":0.3782283427137563,"score_spread":0.33392806199400027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013160622","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":[0.5676335,0.000082703096,0.4217497,0.008003238,0.00001484765,0.0002840244,0.000009957248,0.00017417036,0.0020478433],"genre_scores_gemma":[0.96484166,0.00015495888,0.034038648,0.00058151555,0.00005709708,0.00006138909,0.000089170346,0.000012250186,0.00016330059],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99869597,0.000026916905,0.00039439366,0.00022579618,0.00051125424,0.00014565827],"domain_scores_gemma":[0.9989781,0.000068248264,0.00012074843,0.00037990787,0.00024992783,0.00020307442],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017694487,0.00010442169,0.0003765496,0.00045679178,0.000028751223,0.000014365214,0.0001307727,0.00007100028,0.0027279195],"category_scores_gemma":[0.00034838569,0.00007989846,0.00037709024,0.0016977988,0.00014987316,0.00014001716,0.00002742389,0.00017488266,0.000029224275],"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":[0.000049457147,0.002442563,0.12154736,0.00024029338,0.0021861065,0.000073192576,0.00026946227,0.00001439045,0.2814159,0.00026651038,0.014260258,0.5772345],"study_design_scores_gemma":[0.0016016376,0.00033749102,0.47920343,0.00011856545,0.0062377597,0.00006589269,0.00017807036,0.019640377,0.47438848,0.0036198432,0.014055159,0.0005532997],"about_ca_topic_score_codex":0.00017975902,"about_ca_topic_score_gemma":0.0000016620709,"teacher_disagreement_score":0.5766812,"about_ca_system_score_codex":0.000009040467,"about_ca_system_score_gemma":0.000031334825,"threshold_uncertainty_score":0.9981837},"labels":[],"label_agreement":null},{"id":"W2014373879","doi":"10.1016/s1361-8415(02)00083-x","title":"Deformable organisms for automatic medical image analysis","year":2002,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":76,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Toronto; Toronto Metropolitan University","funders":"National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Stiftelsen för Strategisk Forskning","keywords":"Artificial intelligence; Computer science; Computer vision; Segmentation; Corpus callosum; Process (computing); Perception; Sagittal plane; Pattern recognition (psychology); Anatomy; Biology; Neuroscience","score_opus":0.0057308416164632,"score_gpt":0.27071737069590973,"score_spread":0.26498652907944653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014373879","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":[0.1123731,0.00087935984,0.8783061,0.0021962046,0.00003428012,0.00036931664,0.000034266603,0.00025107662,0.0055563],"genre_scores_gemma":[0.9506576,0.0012747371,0.035553176,0.003483089,0.000510962,0.00022165621,0.0018416415,0.00010214144,0.006354971],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99546444,0.0002039693,0.0010193697,0.0009916673,0.0015548879,0.0007656438],"domain_scores_gemma":[0.99701256,0.00012171035,0.00028447833,0.0013766205,0.00041629918,0.0007883098],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016333458,0.00043132436,0.0011214024,0.0008900759,0.00023104901,0.00015756389,0.0010936202,0.0005668549,0.02213976],"category_scores_gemma":[0.0028789698,0.00037175964,0.001987575,0.0037523995,0.00043415042,0.00003451222,0.00037276943,0.00030994826,0.00018119488],"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":[0.000117868185,0.0037415866,0.023731686,0.00043507395,0.12181064,0.0010571114,0.0005665826,0.00015515342,0.27488285,0.0001044841,0.45388597,0.119510986],"study_design_scores_gemma":[0.0014236014,0.00028647034,0.0011498315,0.00002362408,0.03331521,0.000041720737,0.00015027841,0.7939046,0.14246258,0.00013089203,0.026020199,0.0010909965],"about_ca_topic_score_codex":0.00016782417,"about_ca_topic_score_gemma":0.00066176715,"teacher_disagreement_score":0.84275293,"about_ca_system_score_codex":0.000055656266,"about_ca_system_score_gemma":0.00010628421,"threshold_uncertainty_score":0.99987346},"labels":[],"label_agreement":null},{"id":"W2014940628","doi":"10.1016/j.media.2011.04.003","title":"New methods for MRI denoising based on sparseness and self-similarity","year":2011,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":280,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"Canadian Institutes of Health Research","keywords":"Thresholding; Artificial intelligence; Noise reduction; Pattern recognition (psychology); Similarity (geometry); Image denoising; Computer science; Exploit; Filter (signal processing); Discrete cosine transform; USable; Invariant (physics); Mathematics; Computer vision; Image (mathematics)","score_opus":0.03962570295564427,"score_gpt":0.35447629242740264,"score_spread":0.31485058947175837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014940628","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":[0.00033520028,0.00018047432,0.9966855,0.001105064,0.00014178596,0.00012689257,0.0000010994141,0.00017031717,0.001253642],"genre_scores_gemma":[0.006853841,0.000025775951,0.9904429,0.0023899884,0.000102261394,0.000010895611,0.0000042866054,0.000014418676,0.00015566443],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972583,0.0007305224,0.0003742469,0.0006870329,0.00053648814,0.00041342113],"domain_scores_gemma":[0.9973703,0.0011043533,0.000111271154,0.0007428352,0.00015154458,0.0005196861],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034215972,0.00022745683,0.00054274034,0.00046308176,0.00021072912,0.00022033577,0.00083614996,0.00016181942,0.00024835137],"category_scores_gemma":[0.00080440723,0.00018906129,0.00033278405,0.0014584283,0.00008509503,0.00035268808,0.00018512904,0.00023640932,0.000008800708],"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":[0.0000930171,0.00044208972,0.00123895,0.000068878224,0.00093986705,0.00023491762,0.0011655143,0.00005577374,0.0016429147,0.002446533,0.002052934,0.9896186],"study_design_scores_gemma":[0.0011672182,0.00015852148,0.0034701405,0.000027483502,0.001066929,0.000009859083,0.000014278451,0.96102816,0.021498183,0.0069871624,0.0041962876,0.00037578816],"about_ca_topic_score_codex":0.00023844601,"about_ca_topic_score_gemma":0.000018262972,"teacher_disagreement_score":0.98924285,"about_ca_system_score_codex":0.000032513643,"about_ca_system_score_gemma":0.00020234394,"threshold_uncertainty_score":0.77096957},"labels":[],"label_agreement":null},{"id":"W2016296285","doi":"10.1016/j.media.2015.03.001","title":"Skin lesion tracking using structured graphical models","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Vancouver Coastal Health Research Institute; University of British Columbia; Simon Fraser University; Vancouver Coastal Health","funders":"CIHR Skin Research Training Centre; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canadian Dermatology Foundation","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Computer vision; Matching (statistics); Set (abstract data type); Mathematics","score_opus":0.06139986517366262,"score_gpt":0.3265433110588494,"score_spread":0.26514344588518673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016296285","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":[0.065882824,0.00012411966,0.9326181,0.0007542121,0.00021205861,0.000045618268,8.618326e-7,0.00013401276,0.00022821379],"genre_scores_gemma":[0.92551273,0.000012886295,0.07394324,0.00032405512,0.00017403792,0.0000032097619,0.0000035688374,0.000009097823,0.000017172848],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99725807,0.00018030497,0.0003323865,0.00049447163,0.0014391006,0.00029566803],"domain_scores_gemma":[0.99861246,0.00006176299,0.00010719152,0.0005666855,0.00020577286,0.00044611946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008726734,0.00014496877,0.00031505869,0.00045938473,0.00011068693,0.00017728854,0.00078613084,0.00016441163,0.000078084064],"category_scores_gemma":[0.00023161963,0.00012356385,0.00025009186,0.0028718037,0.00012040579,0.00090064993,0.0002443977,0.00030822234,0.000009467884],"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":[0.00007934545,0.00036923002,0.0052207042,0.000056995497,0.0026536696,0.0009792583,0.00543889,0.10934304,0.0077797445,0.0074137026,0.003469661,0.8571958],"study_design_scores_gemma":[0.0002453937,0.000021783253,0.0004708254,0.000009217161,0.00022491149,0.000021258184,0.000039288287,0.9858566,0.0016845677,0.011179962,0.000098885015,0.00014733362],"about_ca_topic_score_codex":0.00036198986,"about_ca_topic_score_gemma":0.00015061762,"teacher_disagreement_score":0.87651354,"about_ca_system_score_codex":0.00013854104,"about_ca_system_score_gemma":0.00016445074,"threshold_uncertainty_score":0.5038788},"labels":[],"label_agreement":null},{"id":"W2017456026","doi":"10.1016/j.media.2010.10.002","title":"Semi-automatic segmentation for prostate interventions","year":2010,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia; University of British Columbia Hospital","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Segmentation; Contouring; Artificial intelligence; Computer science; Initialization; Computer vision; Prostate; Prostate brachytherapy; Prostate gland; Brachytherapy; Image segmentation; Pattern recognition (psychology); Medicine; Radiology; Radiation therapy","score_opus":0.013718249757867933,"score_gpt":0.34870626617178313,"score_spread":0.3349880164139152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017456026","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":[0.0033676366,0.000021251995,0.9930681,0.002274397,0.00018973152,0.00039426034,0.000009258934,0.00045446513,0.00022091386],"genre_scores_gemma":[0.101109,0.000022118069,0.89572424,0.0016103067,0.0001005984,0.0004680501,0.00015563179,0.0000151322765,0.0007949065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977949,0.0000927851,0.0006001687,0.00041289514,0.0008169012,0.00028230334],"domain_scores_gemma":[0.99840385,0.00027697498,0.00019305735,0.0005579821,0.00022178864,0.00034637417],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013158843,0.0001419486,0.00029397896,0.00044066206,0.00013516119,0.00024391494,0.0008571431,0.00010043038,0.002067114],"category_scores_gemma":[0.0014892624,0.00012121115,0.00047688096,0.0013513971,0.00016453049,0.0006746991,0.000173838,0.00027410884,0.00007121656],"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":[0.0000032495004,0.00042301544,0.0008497301,0.00021363226,0.0007969653,0.000041559953,0.00070952845,0.0000025253644,0.038038764,0.0011870196,0.014820696,0.9429133],"study_design_scores_gemma":[0.0012903023,0.00019165162,0.0023307174,0.00010240452,0.0012609953,0.00002061181,0.00015725484,0.85622835,0.13099173,0.0058785984,0.001025218,0.00052215223],"about_ca_topic_score_codex":0.000038999628,"about_ca_topic_score_gemma":0.000115860246,"teacher_disagreement_score":0.94239116,"about_ca_system_score_codex":0.000027796932,"about_ca_system_score_gemma":0.000084400104,"threshold_uncertainty_score":0.99884516},"labels":[],"label_agreement":null},{"id":"W2018427609","doi":"10.1016/j.media.2008.04.003","title":"Towards a validation of atlas warping techniques","year":2008,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Neurological disorders and treatments","field":"Medicine","cited_by":96,"is_retracted":false,"has_abstract":false,"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":"Image warping; Pallidotomy; Atlas (anatomy); Brain atlas; Deep brain stimulation; Thalamotomy; Computer science; Magnetic resonance imaging; Artificial intelligence; Brain mapping; Medicine; Radiology; Anatomy; Parkinson's disease; Pathology","score_opus":0.021996961059738394,"score_gpt":0.3125067473191224,"score_spread":0.290509786259384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018427609","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":[0.96979797,0.00013610204,0.018233534,0.004429654,0.000009337458,0.00011946951,0.0000034293823,0.000079077276,0.0071914354],"genre_scores_gemma":[0.995575,0.00027477025,0.0026866626,0.0010423989,0.000029956489,0.000012864568,0.00005371478,0.0000063243483,0.0003183157],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988501,0.000043455813,0.0002317007,0.00019234432,0.0005493729,0.00013303173],"domain_scores_gemma":[0.9994583,0.000038785565,0.0000662741,0.00018766942,0.00009535907,0.0001535937],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013100791,0.00008980363,0.0004034031,0.00019306458,0.00004238033,0.0000032170904,0.00006962336,0.00008696811,0.0015370441],"category_scores_gemma":[0.0003426989,0.000060611925,0.00029781516,0.0007602461,0.00016562387,0.000044550645,0.0000364289,0.00011301703,0.000021002455],"study_design_candidate":"observational","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":[0.0005901811,0.0065253745,0.6799777,0.00029002497,0.010989729,0.0085659595,0.0009279034,0.000006751376,0.043562,0.00018229605,0.024618505,0.22376357],"study_design_scores_gemma":[0.0052579115,0.002582032,0.40261596,0.00015026175,0.015867155,0.00015954979,0.00015147493,0.0048662396,0.56040514,0.0017839276,0.0054857437,0.00067458453],"about_ca_topic_score_codex":0.0001352912,"about_ca_topic_score_gemma":0.0000038051678,"teacher_disagreement_score":0.51684314,"about_ca_system_score_codex":0.000013289481,"about_ca_system_score_gemma":0.000046721998,"threshold_uncertainty_score":0.9993757},"labels":[],"label_agreement":null},{"id":"W2018861380","doi":"10.1016/j.media.2010.07.011","title":"Intra-operative 3D guidance and edema detection in prostate brachytherapy using a non-isocentric C-arm","year":2010,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"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","keywords":"Brachytherapy; Prostate brachytherapy; Medicine; Prostate cancer; Radiation treatment planning; Nuclear medicine; Prostate; Dosimetry; Radiology; Biomedical engineering; Radiation therapy; Cancer","score_opus":0.007717011027891792,"score_gpt":0.30838901095483867,"score_spread":0.3006719999269469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018861380","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":[0.9907216,0.00075496716,0.0061684414,0.001669744,0.00008600985,0.00038967095,0.000008062142,0.000020386977,0.000181162],"genre_scores_gemma":[0.994962,0.0010353021,0.0028282672,0.0008569117,0.0001324959,0.00008146786,0.000021274825,0.000016893167,0.000065409746],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984434,0.000056982983,0.0003716552,0.00041877702,0.00040674125,0.00030239034],"domain_scores_gemma":[0.9991719,0.00007690502,0.00009357487,0.00023018233,0.00012475322,0.00030264427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041901754,0.00018336037,0.00051609916,0.00035281357,0.000085734835,0.000047663936,0.00005601339,0.00010457527,0.00062820164],"category_scores_gemma":[0.00026408912,0.000138514,0.00012175372,0.0012919572,0.00018039961,0.00015154034,0.000033627362,0.00037963418,0.000008743853],"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":[0.00036096256,0.0015133789,0.59846085,0.00012383611,0.0021221887,0.001673384,0.002095511,0.000040988274,0.054827247,0.000011592356,0.00010638011,0.3386637],"study_design_scores_gemma":[0.011004961,0.0010777947,0.5258257,0.00034684947,0.0040333834,0.00022685014,0.0003948883,0.35568455,0.09913641,0.0001538117,0.0014473685,0.0006674287],"about_ca_topic_score_codex":0.00067663897,"about_ca_topic_score_gemma":0.00145301,"teacher_disagreement_score":0.35564357,"about_ca_system_score_codex":0.00012496623,"about_ca_system_score_gemma":0.00013731008,"threshold_uncertainty_score":0.6878367},"labels":[],"label_agreement":null},{"id":"W2021204548","doi":"10.1016/j.media.2012.09.004","title":"Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging","year":2012,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":361,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"","keywords":"Segmentation; Magnetic resonance imaging; Multiple sclerosis; Computer science; Artificial intelligence; Lesion; Image segmentation; Pattern recognition (psychology); Medicine; Radiology; Pathology","score_opus":0.13020247935303603,"score_gpt":0.4478487463707702,"score_spread":0.3176462670177342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021204548","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000053250124,0.99302346,0.004451665,0.0006411886,0.00006530002,0.0011782531,0.0001807366,0.000028888642,0.00042521377],"genre_scores_gemma":[0.00002762937,0.9636894,0.034281824,0.0005744564,0.0001008918,0.00035872243,0.0005867062,0.000053237396,0.00032713078],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.992822,0.0017030587,0.0022977157,0.00059650734,0.0020830056,0.00049770216],"domain_scores_gemma":[0.99514174,0.0019289688,0.0010072737,0.0009440706,0.00054697064,0.0004309988],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003620278,0.0004969876,0.004500386,0.0010826483,0.0000857246,0.000014230664,0.0004084533,0.00018920591,0.020085797],"category_scores_gemma":[0.004261789,0.000354218,0.0023663277,0.0025225924,0.00062150235,0.00010872492,0.00028948116,0.00062958343,0.00018317951],"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":[0.0000066690736,0.00034916573,0.0030588433,0.13069358,0.0011829293,0.0000060704006,0.00002819902,5.982118e-8,0.000024092491,0.0000010556245,0.0047555147,0.8598938],"study_design_scores_gemma":[0.0015975492,0.00015412513,0.049606245,0.5634264,0.064788096,0.000024413983,0.00006643233,0.0028032225,0.00006105946,0.0000030215742,0.31682703,0.00064244046],"about_ca_topic_score_codex":0.000066806184,"about_ca_topic_score_gemma":0.00000732392,"teacher_disagreement_score":0.8592514,"about_ca_system_score_codex":0.00018267907,"about_ca_system_score_gemma":0.00029335645,"threshold_uncertainty_score":0.999891},"labels":[],"label_agreement":null},{"id":"W2022237952","doi":"10.1016/j.media.2014.06.003","title":"Multi-shell diffusion signal recovery from sparse measurements","year":2014,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Center for Research Resources; National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; Vedecká Grantová Agentúra MŠVVaŠ SR a SAV; Academy of Finland","keywords":"Algorithm; SIGNAL (programming language); Diffusion; Computer science; Range (aeronautics); Mathematics; Mathematical optimization; Physics","score_opus":0.08600627826693114,"score_gpt":0.35698312701008417,"score_spread":0.27097684874315303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022237952","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":[0.09048844,0.00006340701,0.90526736,0.002575752,0.000027873346,0.00016188377,0.0000137710185,0.00021678528,0.0011847395],"genre_scores_gemma":[0.8207242,0.00015961056,0.17329389,0.0042133606,0.0002625056,0.000047125428,0.0003023561,0.000034558463,0.00096237246],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810565,0.00008196532,0.00034684865,0.00045754688,0.0007756705,0.00023229817],"domain_scores_gemma":[0.9987069,0.00012578416,0.000101398946,0.000578084,0.00011545956,0.00037237286],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035944566,0.00016002932,0.00043342606,0.00019308738,0.0000913471,0.000022263204,0.00019374462,0.00009761743,0.0024926811],"category_scores_gemma":[0.00057524815,0.00012944154,0.00031014794,0.00064060075,0.00011816803,0.00007673289,0.00009601643,0.00028565034,0.00015446778],"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":[0.00019343245,0.00272014,0.19963294,0.00005120737,0.0020789606,0.00019171939,0.00011021751,0.000053167474,0.53967506,0.000031721753,0.014476351,0.2407851],"study_design_scores_gemma":[0.0060714055,0.0004201558,0.2647662,0.0003183022,0.012149483,0.000028459068,0.00006203706,0.5850134,0.06367485,0.002342124,0.06409203,0.0010615772],"about_ca_topic_score_codex":0.00022849064,"about_ca_topic_score_gemma":0.000039581715,"teacher_disagreement_score":0.73197347,"about_ca_system_score_codex":0.000043905882,"about_ca_system_score_gemma":0.000032463326,"threshold_uncertainty_score":0.99841917},"labels":[],"label_agreement":null},{"id":"W2022848122","doi":"10.1016/j.media.2004.06.011","title":"Accurate assessment of patellar tracking using fiducial and intensity-based fluoroscopic techniques","year":2004,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Lower Extremity Biomechanics and Pathologies","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Fiducial marker; Translation (biology); Kinematics; Orientation (vector space); Fluoroscopy; Rotation (mathematics); Tracking (education); Computer vision; Patella; Cadaver; Artificial intelligence; Intensity (physics); Match moving; Computer science; Medicine; Anatomy; Motion (physics); Mathematics; Radiology; Physics; Geometry; Optics","score_opus":0.019423565391080734,"score_gpt":0.30225480110535924,"score_spread":0.2828312357142785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022848122","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":[0.41375488,0.00010825757,0.58565605,0.00008315391,0.000046235742,0.000054898752,0.000031229065,0.00013077588,0.00013449659],"genre_scores_gemma":[0.9537398,0.000099558005,0.046013534,0.00006436504,0.000029238681,0.0000031268003,0.00003798765,0.000011302596,0.0000010641264],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990719,0.000023392295,0.00027305065,0.00017341311,0.00028926818,0.00016899922],"domain_scores_gemma":[0.9995742,0.00004481033,0.000048505062,0.00017575141,0.00007124222,0.00008551533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034323943,0.00012425159,0.00036586673,0.0002520063,0.0000421339,0.000037663012,0.000119311015,0.00012405244,0.00021525365],"category_scores_gemma":[0.0001017957,0.000108700864,0.00012040891,0.0005156656,0.00008930119,0.0000817019,0.00004659595,0.00016990706,7.1609674e-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":[0.000022795022,0.00039296946,0.014084617,0.00084012316,0.002451687,0.0010796952,0.0006514203,0.01563782,0.87393785,0.00021263202,0.00021727575,0.09047114],"study_design_scores_gemma":[0.0005151877,0.00007149282,0.0050877593,0.00023012437,0.0012537533,0.000011674298,0.00012907761,0.6101652,0.38131392,0.0005894526,0.00020581527,0.00042655272],"about_ca_topic_score_codex":0.00006188976,"about_ca_topic_score_gemma":0.00003330692,"teacher_disagreement_score":0.59452736,"about_ca_system_score_codex":0.000050227893,"about_ca_system_score_gemma":0.00005078027,"threshold_uncertainty_score":0.44326928},"labels":[],"label_agreement":null},{"id":"W2023743679","doi":"10.1016/j.media.2008.10.004","title":"Phase unwrapping of MR images using ΦUN – A fast and robust region growing algorithm","year":2008,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced X-ray Imaging Techniques","field":"Physics and Astronomy","cited_by":92,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Friedrich-Schiller-Universität Jena","keywords":"Algorithm; Computer science; Phase unwrapping; Artificial intelligence; Signal-to-noise ratio (imaging); Image resolution; Noise (video); Phase (matter); Imaging phantom; Computer vision; Image (mathematics); Physics; Optics; Interferometry","score_opus":0.022163233765784555,"score_gpt":0.30973673754343667,"score_spread":0.2875735037776521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023743679","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":[0.11696929,0.00013150791,0.8822605,0.0001816011,0.000013817597,0.00006676817,0.000012851224,0.000065235385,0.00029845815],"genre_scores_gemma":[0.7141212,0.000047310074,0.28546503,0.00007130226,0.00016308321,0.0000075799835,0.00003684514,0.000021991018,0.00006564179],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849856,0.0000720671,0.00039732092,0.00035076385,0.0004028845,0.0002784235],"domain_scores_gemma":[0.9991146,0.000081768434,0.00019542783,0.0003011013,0.00012634596,0.00018078888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022604356,0.00018913313,0.00051081664,0.00032558473,0.00017346797,0.000024687397,0.0001870466,0.00004687122,0.00017607586],"category_scores_gemma":[0.000056893015,0.00017754524,0.00024623855,0.00089237787,0.000435193,0.00048267122,0.00013121207,0.00023332621,0.0000013079016],"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":[0.000039205443,0.0017653735,0.06277366,0.00009690531,0.0041114637,0.0008747203,0.001355804,0.0008305487,0.050849244,0.00037087506,0.0014615476,0.87547064],"study_design_scores_gemma":[0.0035407355,0.00014237122,0.0010073299,0.00031636204,0.0033111088,0.00008697992,0.0012211043,0.88396305,0.10254458,0.0024077257,0.0004658895,0.0009927884],"about_ca_topic_score_codex":0.00045625662,"about_ca_topic_score_gemma":0.0000010931711,"teacher_disagreement_score":0.88313246,"about_ca_system_score_codex":0.000021927004,"about_ca_system_score_gemma":0.000052236705,"threshold_uncertainty_score":0.7240085},"labels":[],"label_agreement":null},{"id":"W2025476726","doi":"10.1016/j.media.2007.06.008","title":"Clinical validation of vessel-based registration for correction of brain-shift","year":2007,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Intracranial Aneurysms: Treatment and Complications","field":"Medicine","cited_by":79,"is_retracted":false,"has_abstract":false,"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":"Norges Forskningsråd","keywords":"Artificial intelligence; Computer science; Computer vision; Image registration; Spline (mechanical); Thin plate spline; Tracking (education); Pattern recognition (psychology); Image (mathematics)","score_opus":0.02600084122234758,"score_gpt":0.3658752603438896,"score_spread":0.33987441912154204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025476726","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":[0.40875062,0.00001593046,0.58647275,0.0033332172,0.00009182288,0.0002172062,0.000005888708,0.000021887512,0.0010906646],"genre_scores_gemma":[0.9946159,0.0000070536444,0.0041568675,0.0002941975,0.0001616788,0.000013742994,0.0004601076,0.0000068996605,0.00028353857],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984725,0.000052379553,0.0007499609,0.00019390066,0.00041301566,0.00011822593],"domain_scores_gemma":[0.9981859,0.00077608007,0.0003013541,0.00025629386,0.00035628484,0.00012411337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012426955,0.00008074115,0.00039266044,0.00022870544,0.0000436562,0.0000061325586,0.00006945622,0.00012635026,0.00029165912],"category_scores_gemma":[0.0015195124,0.00006720627,0.00042588488,0.0007235606,0.00016621425,0.000057867142,0.000006134393,0.00009956084,0.0000047678045],"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":[0.0049326653,0.011438958,0.5646943,0.00079060695,0.0067234915,0.000108671025,0.0006628118,0.00023314275,0.053754386,0.0030176507,0.020033022,0.3336103],"study_design_scores_gemma":[0.0062813084,0.0023044078,0.69470453,0.00016063628,0.013658695,0.0000141078635,0.00027006466,0.08360488,0.19486266,0.00066136493,0.0031750288,0.00030232422],"about_ca_topic_score_codex":0.00008741648,"about_ca_topic_score_gemma":0.00006626675,"teacher_disagreement_score":0.58586526,"about_ca_system_score_codex":0.000022971511,"about_ca_system_score_gemma":0.00011950682,"threshold_uncertainty_score":0.31934628},"labels":[],"label_agreement":null},{"id":"W2026595385","doi":"10.1016/j.media.2007.12.002","title":"Multimodal image registration using floating regressors in the joint intensity scatter plot","year":2008,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada","keywords":"Image registration; Computer science; Artificial intelligence; Histogram; Robustness (evolution); Curse of dimensionality; Computer vision; Pattern recognition (psychology); Image (mathematics)","score_opus":0.04663912200230379,"score_gpt":0.319221277277396,"score_spread":0.2725821552750922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026595385","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":[0.09346531,0.000025080863,0.90088177,0.0049676057,0.000052175696,0.00015939126,0.0000011280124,0.00014955203,0.0002980109],"genre_scores_gemma":[0.6033285,0.00002874295,0.39195624,0.0044984375,0.00009560678,0.000013674823,0.000018355337,0.000010026649,0.00005038209],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961294,0.0004973086,0.0007504596,0.0005527383,0.0016912551,0.000378858],"domain_scores_gemma":[0.9982291,0.00022036007,0.0002647408,0.00083994155,0.00023485618,0.00021098585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023571216,0.00019779448,0.0004267126,0.0004602578,0.0002534084,0.0001781653,0.0011183157,0.00011901721,0.00027748971],"category_scores_gemma":[0.0022342573,0.0001400818,0.0002513813,0.0022189436,0.0005613681,0.00090380374,0.00026543852,0.0005501527,0.000034564095],"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":[0.00014495762,0.0049262093,0.09074339,0.00039608692,0.0030217322,0.029662246,0.07600166,0.00062100147,0.37078705,0.0010536261,0.0785287,0.34411335],"study_design_scores_gemma":[0.0005091833,0.000043034404,0.020009369,0.00007095972,0.00018311157,0.0001872057,0.00041249712,0.9423944,0.035598762,0.00023534603,0.000032385407,0.0003237494],"about_ca_topic_score_codex":0.0013282815,"about_ca_topic_score_gemma":0.000092926435,"teacher_disagreement_score":0.9417734,"about_ca_system_score_codex":0.00010152356,"about_ca_system_score_gemma":0.00012224852,"threshold_uncertainty_score":0.571237},"labels":[],"label_agreement":null},{"id":"W2029098063","doi":"10.1016/j.media.2007.12.003","title":"Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI","year":2008,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":360,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Segmentation; Active appearance model; Artificial intelligence; Computer science; Gauss; Pattern recognition (psychology); Statistical model; Computer vision; Image (mathematics)","score_opus":0.02068048989772678,"score_gpt":0.30107647428998674,"score_spread":0.28039598439225993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029098063","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":[0.03515038,0.00083786616,0.9634792,0.00022020708,0.000015170597,0.00014432479,0.000059224138,0.0000368748,0.000056710505],"genre_scores_gemma":[0.48296246,0.0007272988,0.5159617,0.00021885625,0.000014597946,0.000030405085,0.000034259254,0.0000069433972,0.000043457727],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976905,0.00013514284,0.0005887828,0.00045764842,0.0009007444,0.00022717804],"domain_scores_gemma":[0.99860436,0.00027413492,0.00018091581,0.0003991322,0.00023984151,0.00030161097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087440736,0.00013407345,0.00084487564,0.00060707034,0.000073165305,0.000023538882,0.00034758574,0.00008082969,0.000103140505],"category_scores_gemma":[0.0003619972,0.000113657705,0.00024931275,0.0021886204,0.0006326818,0.0001276276,0.00018727142,0.000087134984,4.4169346e-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":[0.0003174279,0.0040195044,0.05966026,0.0024734098,0.07786955,0.00040620347,0.017059365,0.06997238,0.061038118,0.049859155,0.019651208,0.63767344],"study_design_scores_gemma":[0.00018597698,0.00004955878,0.0029043846,0.000011556544,0.00196992,0.0000015049362,0.000020146894,0.98992246,0.0045453925,0.000268042,0.000014684889,0.00010634284],"about_ca_topic_score_codex":0.00018382544,"about_ca_topic_score_gemma":0.000008089553,"teacher_disagreement_score":0.9199501,"about_ca_system_score_codex":0.000013914936,"about_ca_system_score_gemma":0.00006548678,"threshold_uncertainty_score":0.46348265},"labels":[],"label_agreement":null},{"id":"W2029665903","doi":"10.1016/j.media.2011.01.005","title":"Extracting skeletal muscle fiber fields from noisy diffusion tensor data","year":2011,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Vedecká Grantová Agentúra MŠVVaŠ SR a SAV; Canada Research Chairs","keywords":"Smoothing; Diffusion MRI; Noise (video); Tensor (intrinsic definition); Noise reduction; Artificial intelligence; Pattern recognition (psychology); Mathematics; Fiber; Synthetic data; SIGNAL (programming language); Computer science; Algorithm; Computer vision; Geometry","score_opus":0.1199979832209549,"score_gpt":0.37935965336528793,"score_spread":0.25936167014433303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029665903","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":[0.38293886,0.00020432606,0.5955779,0.0067895157,0.000054138924,0.00031684665,0.00012534366,0.00054945325,0.013443631],"genre_scores_gemma":[0.88411784,0.00016569396,0.11139059,0.0018670246,0.00027742036,0.000023518685,0.00074700697,0.000029297722,0.001381579],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984352,0.000033686,0.00032283802,0.0005335751,0.00045287146,0.0002218565],"domain_scores_gemma":[0.99807554,0.00015090367,0.000099880766,0.0013306888,0.000068747184,0.00027424048],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020473823,0.0001373666,0.0003405049,0.0001272695,0.000097822456,0.000015736983,0.00041370586,0.00011370004,0.011532795],"category_scores_gemma":[0.0006775911,0.000108843,0.00017435948,0.0005479286,0.0001243307,0.00016896428,0.00034149,0.00041883232,0.00014142568],"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":[0.00007714307,0.0025370924,0.062174987,0.00006500159,0.0017174954,0.0019008443,0.00071251247,0.0000016027478,0.019906549,0.000097125456,0.033637878,0.87717175],"study_design_scores_gemma":[0.0022752099,0.00022181132,0.6173186,0.00022673847,0.012561139,0.00009565859,0.00041594208,0.14549552,0.0058771814,0.002114331,0.21233514,0.0010627562],"about_ca_topic_score_codex":0.0007747508,"about_ca_topic_score_gemma":0.0000467189,"teacher_disagreement_score":0.876109,"about_ca_system_score_codex":0.000014522503,"about_ca_system_score_gemma":0.000030700758,"threshold_uncertainty_score":0.9893708},"labels":[],"label_agreement":null},{"id":"W2031113857","doi":"10.1016/j.media.2011.03.004","title":"Evaluation of visualization of the prostate gland in vibro-elastography images","year":2011,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Medical Research and Materiel Command; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Prostate gland; Elastography; Visualization; Prostate; Artificial intelligence; Computer vision; Computer science; Medicine; Radiology; Ultrasound; Internal medicine","score_opus":0.02393714517619314,"score_gpt":0.3213250073869932,"score_spread":0.29738786221080005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031113857","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":[0.03498323,0.000113991206,0.963362,0.00012317747,0.000040621377,0.00023902513,0.0000027697874,0.00003524956,0.0010999637],"genre_scores_gemma":[0.9595424,0.00006643551,0.040192667,0.00012839645,0.000008061035,0.00003367513,0.000007547135,0.000005168662,0.000015648327],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9960604,0.00069209357,0.00059240544,0.00024746594,0.00226609,0.00014160309],"domain_scores_gemma":[0.99843407,0.00008298435,0.00031756598,0.0004875925,0.00059334346,0.000084419786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003887696,0.00009333652,0.00026672598,0.00055718515,0.000026115173,0.000016566646,0.0007325998,0.000064289175,0.0005785928],"category_scores_gemma":[0.0013583904,0.000063397245,0.00018060277,0.0037153119,0.00030887965,0.00036865775,0.00018028174,0.00010251786,0.000002102509],"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":[0.00003245704,0.0015935086,0.27778727,0.00017012293,0.001295045,0.000019804744,0.01032928,0.000053441727,0.04101192,0.0009812763,0.0012791788,0.6654467],"study_design_scores_gemma":[0.0010597603,0.00010317624,0.25667614,0.00011980481,0.0011420596,0.0000020830346,0.00013861721,0.17435366,0.5621234,0.004086711,0.000009416433,0.00018517554],"about_ca_topic_score_codex":0.00035203865,"about_ca_topic_score_gemma":0.00009689626,"teacher_disagreement_score":0.9245592,"about_ca_system_score_codex":0.000023062628,"about_ca_system_score_gemma":0.00014559393,"threshold_uncertainty_score":0.6335186},"labels":[],"label_agreement":null},{"id":"W2031752028","doi":"10.1016/j.media.2014.12.007","title":"Elastic registration of prostate MR images based on estimation of deformation states","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University Health Network; Ontario Institute for Cancer Research; London Health Sciences Centre; McMaster University; Robarts Clinical Trials; Western University","funders":"Canadian Institutes of Health Research; Ontario Institute for Cancer Research","keywords":"Image registration; Artificial intelligence; Magnetic resonance imaging; Computer vision; Computer science; Metric (unit); Voxel; Position (finance); Scanner; Mathematics; Medicine; Image (mathematics); Radiology","score_opus":0.012774714612642086,"score_gpt":0.29812930048999836,"score_spread":0.2853545858773563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031752028","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":[0.007270987,0.000015981652,0.99079686,0.0011137427,0.00003481593,0.00015393349,0.0000092323935,0.00010679361,0.0004976297],"genre_scores_gemma":[0.7401074,0.000013059242,0.2593338,0.0002923473,0.000011634964,0.000021041553,0.00016630965,0.0000056939475,0.0000486751],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968595,0.00021178822,0.0007770696,0.00024560216,0.0017475103,0.00015854587],"domain_scores_gemma":[0.998044,0.00025040377,0.00051588815,0.0004693437,0.000481643,0.00023871378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017257193,0.00012476726,0.00032841304,0.0005455233,0.000029719076,0.000054936365,0.00045304096,0.0000705053,0.0001055513],"category_scores_gemma":[0.0026530293,0.00010120217,0.00012425898,0.001531122,0.00021951327,0.00075007905,0.000059536476,0.00012326227,0.000014386744],"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":[0.00028639578,0.0026129647,0.0060239485,0.0010267505,0.001108505,0.000113637776,0.0058618947,0.122032456,0.012293947,0.0023587095,0.029815169,0.8164656],"study_design_scores_gemma":[0.00037061618,0.00020238888,0.0006390058,0.000052431467,0.00013440268,0.0000010049471,0.00005508665,0.8869649,0.11055725,0.000931621,0.0000070863994,0.000084198306],"about_ca_topic_score_codex":0.00013147497,"about_ca_topic_score_gemma":0.000008396715,"teacher_disagreement_score":0.8163814,"about_ca_system_score_codex":0.00005767161,"about_ca_system_score_gemma":0.00021729678,"threshold_uncertainty_score":0.41269046},"labels":[],"label_agreement":null},{"id":"W2045105614","doi":"10.1016/j.media.2010.03.001","title":"Robust Rician noise estimation for MR images","year":2010,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":237,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Robustness (evolution); Computer science; Artificial intelligence; Estimator; Gaussian noise; Noise (video); Rician fading; Ghosting; Wavelet; Noise reduction; Pattern recognition (psychology); Computer vision; Mathematics; Algorithm; Statistics; Image (mathematics); Fading","score_opus":0.01805896654669985,"score_gpt":0.3059172455766335,"score_spread":0.28785827902993366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045105614","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":[0.0030447855,0.000042649568,0.99084395,0.0041750027,0.0003017181,0.00011828992,0.0000051946895,0.00016192583,0.0013064768],"genre_scores_gemma":[0.09665399,0.000007659811,0.900902,0.0012644229,0.00024075538,0.00003284183,0.000030463852,0.000013286885,0.0008546305],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978508,0.00013802784,0.00038326482,0.00051103416,0.0007355973,0.00038127942],"domain_scores_gemma":[0.9980203,0.00052801816,0.00012195549,0.00074447575,0.0002725667,0.00031269633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002072856,0.00017483921,0.00038300257,0.00043062,0.00022677939,0.0003854502,0.001104288,0.00014827908,0.00038645286],"category_scores_gemma":[0.0025309077,0.00014548884,0.00039276874,0.0016385952,0.00015422069,0.0006904716,0.00016757424,0.00034633087,0.00008279414],"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":[0.000029898838,0.00038213067,0.0007484479,0.00006354103,0.00085086393,0.00025676,0.0004888788,0.0010368979,0.06397067,0.0039968593,0.018547857,0.9096272],"study_design_scores_gemma":[0.00052354444,0.00003463066,0.0017515651,0.0000074989775,0.0004603852,0.000012032951,0.000008253012,0.9776875,0.014768391,0.0029038235,0.0016097515,0.00023265877],"about_ca_topic_score_codex":0.000093440314,"about_ca_topic_score_gemma":0.000051650386,"teacher_disagreement_score":0.9766506,"about_ca_system_score_codex":0.00001706614,"about_ca_system_score_gemma":0.00010446671,"threshold_uncertainty_score":0.5932863},"labels":[],"label_agreement":null},{"id":"W2045999511","doi":"10.1016/j.media.2007.10.006","title":"Performance evaluation of a medical robotic 3D-ultrasound imaging system","year":2007,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Peripheral Artery Disease Management","field":"Medicine","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Montreal Clinical Research Institute; Université de Montréal","funders":"","keywords":"Imaging phantom; Scanner; Computer science; Repeatability; Computer vision; Artificial intelligence; Stenosis; Ground truth; Robot; Biomedical engineering; Medicine; Nuclear medicine; Radiology; Mathematics","score_opus":0.015040411005570417,"score_gpt":0.3230855610905272,"score_spread":0.3080451500849568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045999511","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":[0.9194101,0.00045877893,0.06767285,0.0014829033,0.00011922677,0.00033716683,0.0000020718892,0.00010135182,0.010415565],"genre_scores_gemma":[0.9979289,0.000040659106,0.00092890864,0.00064733805,0.0002155717,0.000019733656,0.00008176334,0.000016473226,0.00012060878],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9917742,0.00016438321,0.00079355115,0.00037966348,0.0064898375,0.0003983903],"domain_scores_gemma":[0.99802244,0.00015034054,0.00016693359,0.00051523634,0.0004401605,0.00070488086],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0077937325,0.00018307341,0.0006264202,0.0005195501,0.00007058702,0.000023430506,0.00028837292,0.00010309337,0.0068996353],"category_scores_gemma":[0.0013023163,0.00014577943,0.00033244584,0.0014807694,0.00024948642,0.0001463326,0.000102432554,0.00024068501,0.00009136215],"study_design_candidate":"observational","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":[0.000243317,0.0012854881,0.53170687,0.0014095538,0.006249665,0.0012511654,0.00077757594,0.000716487,0.0013546478,0.00007969392,0.0024302045,0.45249537],"study_design_scores_gemma":[0.001332441,0.00003574185,0.29679593,0.0002728938,0.008669937,0.000063674735,0.0005784628,0.69179434,0.00020111962,0.0000018726623,0.00012783364,0.00012575739],"about_ca_topic_score_codex":0.00016570106,"about_ca_topic_score_gemma":0.0000765993,"teacher_disagreement_score":0.6910778,"about_ca_system_score_codex":0.00030059915,"about_ca_system_score_gemma":0.00027750805,"threshold_uncertainty_score":0.9940082},"labels":[],"label_agreement":null},{"id":"W2046296065","doi":"10.1016/j.media.2012.06.006","title":"Intervertebral disc segmentation in MR images using anisotropic oriented flux","year":2012,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":67,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St Joseph's Health Care; London Health Sciences Centre; Western University; CARE Canada","funders":"","keywords":"Segmentation; Sagittal plane; Artificial intelligence; Intervertebral disc; Computer vision; Computer science; Tracking (education); Image segmentation; Level set (data structures); Active contour model; Pattern recognition (psychology); Anatomy; Medicine","score_opus":0.009771000929835016,"score_gpt":0.27683422184961465,"score_spread":0.26706322091977963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046296065","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":[0.51012546,0.0005048362,0.4881355,0.00023226469,0.00016966612,0.000046822806,0.000007253173,0.00014303597,0.00063519325],"genre_scores_gemma":[0.99091256,0.000059162296,0.008270425,0.00016717041,0.00021212877,0.0000100022835,0.00014533078,0.000024307228,0.0001989237],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979541,0.000121983445,0.00050679146,0.00022219251,0.0006693452,0.0005256187],"domain_scores_gemma":[0.99916124,0.00006009295,0.000047374127,0.0002538206,0.000038011614,0.0004394612],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005069987,0.00020184882,0.00047305602,0.00058275036,0.000052560325,0.000049394013,0.0001950717,0.00009831516,0.005766588],"category_scores_gemma":[0.00029826292,0.00017258413,0.0002938539,0.0019978054,0.000120961544,0.00048565186,0.00006418511,0.00032344347,0.0001101303],"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":[0.000008326311,0.0007398078,0.8626964,0.00028188035,0.004788257,0.0002952917,0.0021070933,0.0045879576,0.04460775,0.000070818685,0.008027719,0.07178871],"study_design_scores_gemma":[0.0006803764,0.000009015708,0.023638323,0.0000728781,0.0018590762,0.000007835605,0.0005768166,0.9644496,0.007954047,0.000022654693,0.00036249997,0.00036691414],"about_ca_topic_score_codex":0.0002899946,"about_ca_topic_score_gemma":0.00004558482,"teacher_disagreement_score":0.9598616,"about_ca_system_score_codex":0.00013480936,"about_ca_system_score_gemma":0.000017474269,"threshold_uncertainty_score":0.9951423},"labels":[],"label_agreement":null},{"id":"W2050978844","doi":"10.1016/j.media.2010.04.007","title":"High-throughput detection of prostate cancer in histological sections using probabilistic pairwise Markov models","year":2010,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":123,"is_retracted":false,"has_abstract":false,"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; American Cancer Society","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Markov chain; Pixel; Pairwise comparison; Markov model; Probabilistic logic; Markov random field; Markov process; Prior probability; Segmentation; Image segmentation; Bayesian probability; Machine learning; Mathematics","score_opus":0.01819696402735157,"score_gpt":0.3014415382075682,"score_spread":0.28324457418021665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050978844","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":[0.9906296,0.0004240137,0.006920497,0.0012559931,0.00017585403,0.00040364597,0.0000433861,0.000039500297,0.00010749196],"genre_scores_gemma":[0.9965256,0.00045322857,0.0024713504,0.00013116263,0.000087996625,0.00020586312,0.00003306252,0.00001472669,0.00007703579],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820954,0.000075597985,0.00051715295,0.0004140589,0.0005042817,0.00027940108],"domain_scores_gemma":[0.9989894,0.00009960793,0.00014987797,0.0003185535,0.0001988828,0.00024365708],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036808182,0.0001700966,0.0006442488,0.0003397124,0.00006162476,0.000012170704,0.00007646207,0.0001689186,0.0009964013],"category_scores_gemma":[0.00036800874,0.000126987,0.00025309413,0.001263856,0.00029350954,0.00012403933,0.000046251927,0.00042172446,0.0000027585697],"study_design_candidate":"observational","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":[0.0015886534,0.009539846,0.5899922,0.0011544286,0.008169443,0.0022549287,0.00224477,0.024988253,0.114178136,0.0005118715,0.00041337102,0.24496408],"study_design_scores_gemma":[0.006417333,0.00078427687,0.19358812,0.00039295902,0.012833688,0.000091701484,0.00020456844,0.7488137,0.033025227,0.0028664733,0.00034877978,0.0006331553],"about_ca_topic_score_codex":0.006246711,"about_ca_topic_score_gemma":0.00858908,"teacher_disagreement_score":0.72382545,"about_ca_system_score_codex":0.0003223407,"about_ca_system_score_gemma":0.0002595139,"threshold_uncertainty_score":0.99991685},"labels":[],"label_agreement":null},{"id":"W2051558301","doi":"10.1016/j.media.2010.07.008","title":"Biomechanically constrained groupwise ultrasound to CT registration of the lumbar spine","year":2010,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":75,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kingston General Hospital; National Research Council Canada; University of British Columbia; Queen's University","funders":"Canadian Institutes of Health Research","keywords":"Imaging phantom; Image registration; Artificial intelligence; Curvature; Computer science; Displacement (psychology); Medicine; Metric (unit); Volume (thermodynamics); Computer vision; Cadaver; Similarity (geometry); Radiology; Mathematics; Image (mathematics); Anatomy","score_opus":0.0035896634749833325,"score_gpt":0.229809595028521,"score_spread":0.22621993155353767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051558301","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":[0.70875716,0.000050270082,0.28311554,0.0041515757,0.00033135555,0.00013322713,0.00002359365,0.00019256123,0.003244704],"genre_scores_gemma":[0.9952606,0.000033634464,0.0037378424,0.0004434691,0.00014506903,0.0000099638655,0.000032974123,0.000016510556,0.00031991265],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978599,0.000057497615,0.0005878384,0.0002604016,0.00095741224,0.0002769736],"domain_scores_gemma":[0.9986223,0.000102924154,0.00007896907,0.0006362395,0.00010705713,0.0004525277],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00088923087,0.00017058766,0.00045005596,0.00025203233,0.000065724525,0.000044916444,0.0005289178,0.00008712926,0.0024910371],"category_scores_gemma":[0.0028366053,0.000117978205,0.00044558584,0.0024040819,0.0003228894,0.0000746834,0.000050630802,0.00046318705,0.000039434082],"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":[0.0000021808005,0.00016305417,0.002596348,0.000085541,0.0020860287,0.000076074546,0.00012587896,0.00039282185,0.9561144,0.00059442566,0.0062436904,0.031519517],"study_design_scores_gemma":[0.0019484655,0.00011319833,0.037152678,0.00023396163,0.010808138,0.00015140217,0.0003698812,0.7900925,0.14189634,0.0013230565,0.014344332,0.001566051],"about_ca_topic_score_codex":0.00015746198,"about_ca_topic_score_gemma":0.00043698883,"teacher_disagreement_score":0.8142181,"about_ca_system_score_codex":0.00001642935,"about_ca_system_score_gemma":0.00005023499,"threshold_uncertainty_score":0.99842083},"labels":[],"label_agreement":null},{"id":"W2054940523","doi":"10.1016/j.media.2015.04.013","title":"Multiscale properties of weighted total variation flow with applications to denoising and registration","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto; Fields Institute for Research in Mathematical Sciences","funders":"Canadian Institutes of Health Research","keywords":"Total variation denoising; Noise reduction; Regularization (linguistics); Mathematics; Algorithm; Scale (ratio); Flow (mathematics); Noise (video); Image (mathematics); Pattern recognition (psychology); Artificial intelligence; Computer science; Geometry","score_opus":0.01850511152056049,"score_gpt":0.2748066895848789,"score_spread":0.2563015780643184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054940523","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":[0.012250629,0.00005387732,0.9855348,0.0016792486,0.0000105206245,0.00023184682,0.0000015709569,0.000104155806,0.00013334103],"genre_scores_gemma":[0.38019466,0.0000059934223,0.6193431,0.00023551841,0.000030989064,0.000073878844,0.000011891608,0.000004693988,0.00009927746],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982816,0.00009386145,0.00032369196,0.00030191403,0.0008726043,0.00012635515],"domain_scores_gemma":[0.99881685,0.00004046199,0.00011884505,0.00034615133,0.00032697173,0.0003507103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061352184,0.000091896545,0.0002143762,0.0002469316,0.000053552012,0.00009731388,0.00026966733,0.000054940934,0.000027970034],"category_scores_gemma":[0.0003236904,0.000067585905,0.000036909772,0.0013359634,0.00013417448,0.00045829956,0.000104090985,0.0000845951,0.0000071438144],"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":[0.00010266008,0.0009509904,0.0036983865,0.0002055505,0.0013277796,0.00007578052,0.014000804,0.0003980994,0.15127032,0.0020719625,0.002911602,0.82298607],"study_design_scores_gemma":[0.00086115603,0.0002609552,0.004810895,0.00009614735,0.00051580457,0.00002988626,0.00027269602,0.84555185,0.1466544,0.00047417273,0.00012988986,0.00034212536],"about_ca_topic_score_codex":0.00020721811,"about_ca_topic_score_gemma":0.00006111296,"teacher_disagreement_score":0.84515375,"about_ca_system_score_codex":0.000034918812,"about_ca_system_score_gemma":0.00011165269,"threshold_uncertainty_score":0.27560732},"labels":[],"label_agreement":null},{"id":"W2055260435","doi":"10.1016/j.media.2012.05.005","title":"Mammography segmentation with maximum likelihood active contours","year":2012,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Carleton University","funders":"","keywords":"Segmentation; Active contour model; Artificial intelligence; Level set (data structures); Pattern recognition (psychology); Computer science; Image segmentation; Mammography; Computer vision; Point distribution model; Divergence (linguistics); Digital mammography; Scale-space segmentation; Mathematics; Medicine","score_opus":0.006622734472672239,"score_gpt":0.2728543265296406,"score_spread":0.26623159205696834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055260435","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":[0.005034526,0.000115175295,0.99102014,0.0015350508,0.00008189882,0.00018899224,0.0000045377014,0.00035906117,0.0016606125],"genre_scores_gemma":[0.3535653,0.000098012366,0.6413029,0.0044327057,0.00021684877,0.00014766683,0.000098865625,0.000023855047,0.00011384321],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99670434,0.000232952,0.00037285656,0.00041880656,0.0016858192,0.000585199],"domain_scores_gemma":[0.9980249,0.00017061699,0.00019021942,0.00056606403,0.00018253743,0.0008656886],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008947229,0.00021491462,0.00037253276,0.00059682585,0.00011796636,0.00014786354,0.00077855156,0.00011096738,0.0015203911],"category_scores_gemma":[0.00019977287,0.00016087433,0.00023033361,0.0028550832,0.00025458608,0.0016486199,0.00016778744,0.0002845068,0.00009542705],"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":[0.000032705844,0.000757124,0.02981672,0.000028749868,0.002394105,0.00014512813,0.0022106362,0.0000010937998,0.0038392504,0.0003712812,0.006543277,0.9538599],"study_design_scores_gemma":[0.007511981,0.0012970082,0.16609147,0.00024484567,0.008345397,0.00020186583,0.004537989,0.033684123,0.7655545,0.0055575157,0.0032882772,0.0036850285],"about_ca_topic_score_codex":0.00012558958,"about_ca_topic_score_gemma":0.000042381096,"teacher_disagreement_score":0.9501749,"about_ca_system_score_codex":0.000068532056,"about_ca_system_score_gemma":0.000082472856,"threshold_uncertainty_score":0.99939233},"labels":[],"label_agreement":null},{"id":"W2056387355","doi":"10.1016/j.media.2011.05.017","title":"Brachytherapy seed reconstruction with joint-encoded C-arm single-axis rotation and motion compensation","year":2011,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia; Queen's University","funders":"National Cancer Institute","keywords":"Computer vision; Artificial intelligence; Fiducial marker; Fluoroscopy; Motion compensation; Computer science; Rotation (mathematics); Brachytherapy; Tracking (education); Prostate brachytherapy; Projection (relational algebra); Match moving; Mathematics; Motion (physics); Medicine; Algorithm; Radiation therapy; Radiology","score_opus":0.015524478349288343,"score_gpt":0.247808702962002,"score_spread":0.23228422461271364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056387355","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":[0.27681282,0.000019828205,0.7217469,0.00009846559,0.000017103572,0.0001145723,0.000003347156,0.000072267896,0.0011146887],"genre_scores_gemma":[0.89292824,0.000019898684,0.10672626,0.00007287,0.00008814469,0.00002655358,0.000071169496,0.000015959586,0.000050924915],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998933,0.00008994066,0.00026942624,0.00028424,0.0002739961,0.00014939709],"domain_scores_gemma":[0.99936724,0.00002906943,0.00018979776,0.00018513804,0.000118871765,0.00010989379],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021535154,0.00014262843,0.00027565914,0.00021612771,0.00009989785,0.0000363415,0.00006368188,0.000056161483,0.0022996285],"category_scores_gemma":[0.000013596942,0.000116980795,0.00009171273,0.00052142044,0.00017514433,0.00041264232,0.000010489082,0.00014544874,0.000002654945],"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":[0.00010634114,0.00042003382,0.2932764,0.000013199778,0.0015007164,0.000007655734,0.001497528,0.000028242044,0.027353426,0.0010259107,0.00002266176,0.6747479],"study_design_scores_gemma":[0.006682312,0.0018226926,0.34445906,0.00024236347,0.003893936,0.00008046523,0.0028723518,0.27621162,0.33398414,0.027226478,0.00042605877,0.002098519],"about_ca_topic_score_codex":0.00040611217,"about_ca_topic_score_gemma":0.000045387605,"teacher_disagreement_score":0.6726494,"about_ca_system_score_codex":0.00003582793,"about_ca_system_score_gemma":0.000017816528,"threshold_uncertainty_score":0.9986124},"labels":[],"label_agreement":null},{"id":"W2057441779","doi":"10.1016/j.media.2014.10.004","title":"Right ventricle segmentation from cardiac MRI: A collation study","year":2014,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":242,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; CARE Canada","funders":"Medical Research Council; National Science Council; Ministerio de Ciencia e Innovación; British Heart Foundation; Engineering and Physical Sciences Research Council; Comunidad de Madrid","keywords":"Hausdorff distance; Segmentation; Computer science; Artificial intelligence; Tracing; Metric (unit); Pattern recognition (psychology); Computer vision; Ventricle; Medicine","score_opus":0.005184458891641832,"score_gpt":0.33445430141747684,"score_spread":0.329269842525835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057441779","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":[0.9921397,0.0002635947,0.00543326,0.0003429684,0.000090878275,0.000366754,0.000035428046,0.00005225822,0.0012751651],"genre_scores_gemma":[0.99815977,0.000037619342,0.0003266437,0.00021202887,0.00026409436,0.00004471332,0.00078759016,0.000011838883,0.00015570318],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981651,0.0001817782,0.00026244475,0.0003222448,0.0009055677,0.00016288934],"domain_scores_gemma":[0.9990149,0.000117207455,0.000071587965,0.00033982968,0.00010731779,0.00034914876],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00026200255,0.0001251551,0.00048498486,0.00018148047,0.00008210539,0.00003628726,0.00005249178,0.00005611253,0.0027690853],"category_scores_gemma":[0.00020909529,0.000098367535,0.0010445417,0.00085581164,0.00003507929,0.0000733126,0.000032591906,0.00007823001,0.00020048946],"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":[0.000061091785,0.00076915836,0.9791433,0.000004002635,0.009038249,0.00005045549,0.0001428275,0.0000069001067,0.00015577728,0.0000041102808,0.00078657985,0.009837528],"study_design_scores_gemma":[0.0021849833,0.00013946833,0.9649914,0.0000092537275,0.025623687,3.33456e-7,0.00040049033,0.0055898926,0.00031701731,0.00004776209,0.00059782836,0.00009786756],"about_ca_topic_score_codex":0.0008333034,"about_ca_topic_score_gemma":0.0000313906,"teacher_disagreement_score":0.016585438,"about_ca_system_score_codex":0.00008664466,"about_ca_system_score_gemma":0.000043702672,"threshold_uncertainty_score":0.99814254},"labels":[],"label_agreement":null},{"id":"W2060830357","doi":"10.1016/j.media.2011.10.001","title":"Tumor invasion margin on the Riemannian space of brain fibers","year":2011,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"","keywords":"Geodesic; Glioma; Margin (machine learning); Diffusion MRI; Magnetic resonance imaging; Fiber tract; Lesion; Brain tumor; Infiltration (HVAC); Computer science; Medicine; Mathematics; Pathology; Radiology; Mathematical analysis; Physics; Cancer research","score_opus":0.07676911403623363,"score_gpt":0.3431612832338788,"score_spread":0.2663921691976452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060830357","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":[0.5488384,0.00010379298,0.22568454,0.17880367,0.000040332063,0.00094603,0.000028096749,0.0003863201,0.04516882],"genre_scores_gemma":[0.97568136,0.000041758394,0.01621716,0.0068510454,0.00004192521,0.000040186347,0.000017860217,0.000018178465,0.0010905074],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99887234,0.000056301953,0.00023953522,0.00023713543,0.0004411292,0.00015358614],"domain_scores_gemma":[0.99883366,0.00021337968,0.00010501842,0.0006175912,0.000065838234,0.00016450018],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038107755,0.00010324829,0.0002838016,0.00016574166,0.000059347756,0.0000046202126,0.00020576672,0.0000384503,0.0022105873],"category_scores_gemma":[0.0008294351,0.00006271633,0.00022684534,0.0009222735,0.00027747423,0.00003263641,0.000064789245,0.00025051075,0.000038244718],"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":[0.0011713195,0.0067782803,0.110115506,0.0005516649,0.005479281,0.0031818943,0.005528027,0.000018854444,0.11989139,0.07372029,0.5820141,0.09154944],"study_design_scores_gemma":[0.0035996914,0.0017810172,0.2708242,0.0010127712,0.009852976,0.00022080881,0.0018004936,0.030676018,0.5332184,0.020983428,0.12471298,0.0013172474],"about_ca_topic_score_codex":0.00010784767,"about_ca_topic_score_gemma":0.000012167523,"teacher_disagreement_score":0.45730108,"about_ca_system_score_codex":0.000016597669,"about_ca_system_score_gemma":0.000036249778,"threshold_uncertainty_score":0.9987015},"labels":[],"label_agreement":null},{"id":"W2062366581","doi":"10.1016/j.media.2010.08.006","title":"Learning to estimate out-of-plane motion in ultrasound imagery of real tissue","year":2010,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Ultrasound Imaging and Elastography","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; McGill University","funders":"","keywords":"Decorrelation; Speckle pattern; Artificial intelligence; Computer vision; Computer science; Position (finance); Transducer; Process (computing); Heuristic; Acoustics; Physics","score_opus":0.006265516535536988,"score_gpt":0.30774618299346,"score_spread":0.30148066645792304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062366581","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":[0.9734794,0.00002362542,0.022485636,0.0005808809,0.00012504685,0.00009874929,0.0000071115987,0.000046257654,0.0031532773],"genre_scores_gemma":[0.9826701,0.000047077156,0.016651165,0.00007925918,0.000090626345,0.000006227113,0.00013224831,0.000016649028,0.00030660335],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99808043,0.000077268036,0.00056557887,0.0003012963,0.0006873842,0.00028805033],"domain_scores_gemma":[0.99867,0.0003621911,0.00013983679,0.00033167118,0.00016712389,0.00032917838],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009357318,0.00015124744,0.0006810307,0.00092197256,0.000033909917,0.000014967718,0.00013946429,0.00012910397,0.0011570076],"category_scores_gemma":[0.0031114004,0.00012985688,0.0002259288,0.0016561265,0.00026869876,0.000088623565,0.00003044551,0.00061635755,0.000039887625],"study_design_candidate":"observational","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":[0.000054034484,0.00025255763,0.4474979,0.00007674877,0.00032904334,0.00005358386,0.0009313197,0.000047075202,0.5374774,0.0000057752354,0.00014421815,0.013130369],"study_design_scores_gemma":[0.0018204573,0.0005629997,0.9253554,0.0002659372,0.0035417608,0.00012101744,0.0008215138,0.0031750463,0.061248396,0.000088743,0.0025598938,0.00043887118],"about_ca_topic_score_codex":0.0012092275,"about_ca_topic_score_gemma":0.000539247,"teacher_disagreement_score":0.47785744,"about_ca_system_score_codex":0.00001399888,"about_ca_system_score_gemma":0.00005816632,"threshold_uncertainty_score":0.9997561},"labels":[],"label_agreement":null},{"id":"W2063727717","doi":"10.1016/j.media.2012.01.002","title":"A CANDLE for a deeper in vivo insight","year":2012,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Fluorescence Microscopy Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":72,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"Canadian Institutes of Health Research; Deutscher Akademischer Austauschdienst; McGill University","keywords":"Candle; Smoothing; Filter (signal processing); Artificial intelligence; Noise reduction; Computer vision; Computer science; Noise (video); Optics; Materials science; Pattern recognition (psychology); Physics; Chemistry; Image (mathematics)","score_opus":0.006283904015054822,"score_gpt":0.3113302873830297,"score_spread":0.3050463833679749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063727717","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":[0.19363779,0.0010893346,0.8041994,0.00022512463,0.000036573663,0.00016897665,0.000019134977,0.000020441137,0.0006032544],"genre_scores_gemma":[0.9082339,0.00022733839,0.089375265,0.0010728794,0.0002626861,0.0001576636,0.0001125402,0.000023098864,0.00053466833],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99910694,0.000032989792,0.0001812044,0.00020940794,0.00016432191,0.00030514275],"domain_scores_gemma":[0.99950105,0.000016047996,0.0000358636,0.00023569893,0.00005396507,0.00015739589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030877412,0.00010012928,0.00018918116,0.00011598831,0.000029796369,0.000008803181,0.00015990745,0.00016392843,0.0002688546],"category_scores_gemma":[0.00043064624,0.00008591915,0.0001505643,0.00033904376,0.000095738484,0.000007923047,0.00007273578,0.00008505367,0.0000035874214],"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":[0.000040587092,0.00016961432,0.040969264,0.000012247884,0.00020022655,0.000005263602,0.000115216484,0.0000024990854,0.9511823,0.000036992915,0.004176855,0.0030889506],"study_design_scores_gemma":[0.00035431396,0.00005841653,0.0011327228,0.000009099972,0.00018453527,0.0000032054515,0.000042182342,0.0003882847,0.94013596,0.00007007844,0.057436798,0.00018443316],"about_ca_topic_score_codex":0.000080561804,"about_ca_topic_score_gemma":0.00041288426,"teacher_disagreement_score":0.7148241,"about_ca_system_score_codex":0.000019810252,"about_ca_system_score_gemma":0.0000417972,"threshold_uncertainty_score":0.3503681},"labels":[],"label_agreement":null},{"id":"W2068854578","doi":"10.1016/j.media.2011.01.006","title":"Automatic inference of articulated spine models in CT images using high-order Markov Random Fields","year":2011,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine","funders":"Institut national de recherche en informatique et en automatique (INRIA)","keywords":"Markov random field; Context (archaeology); Computer science; Artificial intelligence; Markov chain; Transformation (genetics); Inference; Pattern recognition (psychology); Mathematics; Algorithm; Machine learning; Image (mathematics); Image segmentation","score_opus":0.01518001686626846,"score_gpt":0.2554743617237202,"score_spread":0.2402943448574517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068854578","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":[0.50934625,0.00020231954,0.4895218,0.000076032564,0.00003553598,0.00004633859,0.0000029238438,0.00009756257,0.0006712215],"genre_scores_gemma":[0.9737741,0.00014796061,0.025884334,0.00007936811,0.000024710447,0.000008145463,0.000021840935,0.000018695837,0.000040882067],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783427,0.0001207921,0.00079991395,0.00025722035,0.0006260055,0.0003617761],"domain_scores_gemma":[0.9990259,0.00013032196,0.00008504098,0.00038870188,0.00010581701,0.0002642435],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006631006,0.0002151169,0.00086116657,0.00063056464,0.000028203258,0.000022245868,0.0002844804,0.00009899969,0.0047825556],"category_scores_gemma":[0.00073167664,0.00017679112,0.0002718774,0.0024596679,0.00018459426,0.00022837886,0.000063091196,0.00034330413,0.000012185165],"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":[0.00007242057,0.0029471018,0.07883257,0.0028145127,0.028521612,0.0057931594,0.0063286237,0.3877863,0.041877963,0.00040277067,0.0021345427,0.44248843],"study_design_scores_gemma":[0.00078705756,0.0000073157394,0.0031977282,0.00011046762,0.0013397835,0.0000031840327,0.000043519874,0.99044895,0.0033608847,0.0005098513,0.000002022916,0.00018920828],"about_ca_topic_score_codex":0.0018746655,"about_ca_topic_score_gemma":0.000108420834,"teacher_disagreement_score":0.6026627,"about_ca_system_score_codex":0.000030847994,"about_ca_system_score_gemma":0.00004417274,"threshold_uncertainty_score":0.9961272},"labels":[],"label_agreement":null},{"id":"W2070074822","doi":"10.1016/j.media.2011.08.002","title":"A constrained independent component analysis technique for artery–vein separation of two-photon laser scanning microscopy images of the cerebral microvasculature","year":2011,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Independent component analysis; Cerebral blood flow; Biomedical engineering; Artificial intelligence; Hemodynamics; Computer science; Pattern recognition (psychology); Medicine; Cardiology","score_opus":0.012446014937098532,"score_gpt":0.29709385187753873,"score_spread":0.2846478369404402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070074822","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":[0.106764205,0.000035796318,0.8918235,0.00038195873,0.000030369418,0.00048369716,0.00003392975,0.00007039728,0.00037616136],"genre_scores_gemma":[0.8245085,0.0000049831533,0.17500924,0.00026497754,0.000013013494,0.000083391584,0.0000422859,0.00000897597,0.00006467664],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9972345,0.00036448461,0.00082939747,0.00049539993,0.000808753,0.00026741924],"domain_scores_gemma":[0.9977177,0.0001332205,0.0006037664,0.0009802511,0.00043694762,0.00012814048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001760706,0.00022210149,0.0007424184,0.0008086581,0.000103641556,0.0000682278,0.0011618886,0.00019480953,0.00017751135],"category_scores_gemma":[0.00015796663,0.00016386545,0.0011540722,0.0031469087,0.0003742019,0.00032073556,0.0002565464,0.00028202552,0.0000012523692],"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":[0.00009556653,0.0011528132,0.038870852,0.00014406569,0.012748616,0.000022581296,0.005885058,0.0004230846,0.93307006,0.0044157933,0.0014940744,0.0016774363],"study_design_scores_gemma":[0.000496428,0.000065366985,0.009647637,0.00003381455,0.002213854,0.0000063997436,0.00006523424,0.042310443,0.944144,0.0007964485,0.00003518055,0.00018518249],"about_ca_topic_score_codex":0.00047391545,"about_ca_topic_score_gemma":0.00027427127,"teacher_disagreement_score":0.71774423,"about_ca_system_score_codex":0.000041956522,"about_ca_system_score_gemma":0.00016913208,"threshold_uncertainty_score":0.6682239},"labels":[],"label_agreement":null},{"id":"W2075139145","doi":"10.1016/j.media.2015.01.002","title":"Observation-driven adaptive differential evolution and its application to accurate and smooth bronchoscope three-dimensional motion tracking","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Japan Society for the Promotion of Science","keywords":"Computer vision; Tracking (education); Artificial intelligence; Computer science; Smoothness; Differential evolution; Mathematics","score_opus":0.02228749615254581,"score_gpt":0.24809980814439847,"score_spread":0.22581231199185267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075139145","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":[0.34978566,0.00010564991,0.64965165,0.00023167959,0.000037432175,0.00010948485,0.000005551175,0.000051408606,0.000021499567],"genre_scores_gemma":[0.9975064,0.000016173975,0.0021416673,0.000065549604,0.00009202193,0.000016809905,0.00013333977,0.000015339063,0.000012747294],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889845,0.000038504342,0.00024413824,0.00024209564,0.00042468053,0.00015210846],"domain_scores_gemma":[0.9993256,0.000042411153,0.00004097419,0.00011418306,0.00018753103,0.00028935287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016464075,0.00012892147,0.00021155443,0.00018641773,0.000067587614,0.00005165576,0.00006321838,0.00010177389,0.00004502817],"category_scores_gemma":[0.0001572716,0.000121623765,0.000040845447,0.0005759294,0.000031269705,0.00022346823,0.00003329945,0.00010902694,0.000013518565],"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":[0.00004248843,0.000080996615,0.012615758,0.000049334183,0.00047955933,0.000008645096,0.0003265861,0.93572885,0.011925073,0.00084659865,0.00044998527,0.037446138],"study_design_scores_gemma":[0.00027123548,0.000025697223,0.063938715,0.000016337062,0.00026080455,8.5490075e-7,0.00002073778,0.93483645,0.00035037674,0.00012795924,0.000029817003,0.00012100111],"about_ca_topic_score_codex":0.00013096255,"about_ca_topic_score_gemma":0.00034127862,"teacher_disagreement_score":0.6477207,"about_ca_system_score_codex":0.00008788892,"about_ca_system_score_gemma":0.000020395393,"threshold_uncertainty_score":0.4959673},"labels":[],"label_agreement":null},{"id":"W2082304695","doi":"10.1016/j.media.2013.05.002","title":"Left ventricle segmentation in MRI via convex relaxed distribution matching","year":2013,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CARE Canada; Robarts Clinical Trials; Western University","funders":"","keywords":"Segmentation; Algorithm; Computer science; Regular polygon; Mathematics; Matching (statistics); Artificial intelligence; Pattern recognition (psychology); Mathematical optimization; Geometry","score_opus":0.00498603816576751,"score_gpt":0.26662508064793256,"score_spread":0.261639042482165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082304695","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":[0.022915184,0.000057751073,0.9733745,0.002962775,0.000061892344,0.00024536197,0.0000028008758,0.00023114,0.00014858415],"genre_scores_gemma":[0.85058945,0.0000889713,0.1469896,0.0017540187,0.000057677924,0.000091635105,0.0002776366,0.000012140717,0.00013886142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99713784,0.00027515722,0.0006180762,0.00046087414,0.0011507601,0.00035729687],"domain_scores_gemma":[0.9987253,0.00019445075,0.0001629622,0.00044376086,0.00013528405,0.00033826564],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00092978554,0.0001550923,0.0003297645,0.00034214067,0.00009568726,0.00022268179,0.00070602214,0.0001200377,0.0035169998],"category_scores_gemma":[0.00038032344,0.00014021175,0.00015524517,0.0018364836,0.00013184406,0.0012906196,0.00021848583,0.00030765214,0.0003961198],"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":[0.000011337469,0.0010182612,0.03536415,0.00008573523,0.00077651616,0.00048513766,0.003703581,0.00010139823,0.07468843,0.0010171155,0.01972951,0.8630188],"study_design_scores_gemma":[0.0013674053,0.00009074061,0.063054405,0.00007043987,0.00029252123,0.000028487679,0.0004631495,0.8102377,0.11305661,0.01049564,0.00021170659,0.0006312103],"about_ca_topic_score_codex":0.00094659586,"about_ca_topic_score_gemma":0.00005617064,"teacher_disagreement_score":0.8623876,"about_ca_system_score_codex":0.00016883315,"about_ca_system_score_gemma":0.00005542373,"threshold_uncertainty_score":0.9973939},"labels":[],"label_agreement":null},{"id":"W2082544654","doi":"10.1016/j.media.2007.06.001","title":"A protocol for evaluation of similarity measures for non-rigid registration","year":2007,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"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; McGill University; Vanderbilt University","keywords":"Similarity (geometry); Artificial intelligence; Similarity measure; Mutual information; Image registration; Range (aeronautics); Protocol (science); Maxima and minima; Pattern recognition (psychology); Measure (data warehouse); Computer science; Computer vision; Mathematics; Position (finance); Task (project management); Image (mathematics); Data mining; Medicine","score_opus":0.07331654037583747,"score_gpt":0.4519022011277982,"score_spread":0.37858566075196076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082544654","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":[0.00009780087,0.0000021246433,0.9514142,0.00076326466,0.000026216425,0.047155455,0.000005077924,0.00008013798,0.0004556947],"genre_scores_gemma":[0.02722165,9.79977e-7,0.82124585,0.00071108574,0.0001467262,0.15051183,0.000060759805,0.000011996597,0.00008913062],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961935,0.0001346517,0.00075621187,0.0003975922,0.002263279,0.00025471838],"domain_scores_gemma":[0.9968358,0.0004970025,0.0003701956,0.00049983547,0.0015834688,0.00021366937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013222912,0.00012627932,0.00032795154,0.0003445325,0.00008870536,0.000067795816,0.0006273019,0.00013524335,0.00016484165],"category_scores_gemma":[0.0058367117,0.00010566655,0.0003076312,0.0010527648,0.00014469441,0.0004089883,0.00005667921,0.00010138673,0.0000015525322],"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":[0.00015584502,0.00073470233,0.0006369773,0.00035427636,0.00075891346,0.0000065309728,0.0005324952,0.000021318527,0.014791921,0.0011858381,0.021731952,0.9590892],"study_design_scores_gemma":[0.0031486205,0.00026019558,0.0016800549,0.000050927018,0.00081289373,0.0000014816051,0.00004267973,0.6824836,0.30340436,0.006639437,0.0012649547,0.00021079562],"about_ca_topic_score_codex":0.000048545524,"about_ca_topic_score_gemma":0.00014095039,"teacher_disagreement_score":0.95887846,"about_ca_system_score_codex":0.000083195264,"about_ca_system_score_gemma":0.000328034,"threshold_uncertainty_score":0.6987511},"labels":[],"label_agreement":null},{"id":"W2083886415","doi":"10.1016/j.media.2013.12.003","title":"Self-similarity weighted mutual information: A new nonrigid image registration metric","year":2013,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Image registration; Mutual information; Artificial intelligence; Similarity measure; Mathematics; Affine transformation; Stochastic gradient descent; Similarity (geometry); Pattern recognition (psychology); Metric (unit); Gradient descent; Computer vision; Computer science; Image (mathematics); Geometry","score_opus":0.0070905747271410155,"score_gpt":0.26632723646321915,"score_spread":0.2592366617360781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083886415","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":[0.00039690133,0.000046629513,0.9827133,0.008532376,0.00009653382,0.00034644373,0.000003320832,0.00084005453,0.0070244567],"genre_scores_gemma":[0.012181365,0.00012590837,0.98069906,0.005777212,0.0001921629,0.00008410974,0.00017514304,0.000011066313,0.00075397035],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954831,0.0002512208,0.0010001013,0.000478726,0.0023299071,0.00045692245],"domain_scores_gemma":[0.9968281,0.00026492984,0.00036696417,0.00098913,0.0005761798,0.00097473845],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011352681,0.0002671621,0.00048505256,0.0010970286,0.000164319,0.0009784923,0.0015281554,0.00022636155,0.0071093854],"category_scores_gemma":[0.001605783,0.00022557213,0.00031982714,0.0058832187,0.0001746444,0.0061086393,0.00034014424,0.0004587572,0.0016485748],"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":[0.000008361393,0.00052131846,0.00087451475,0.00011271922,0.0015414185,0.00016875028,0.0019689219,0.0000015951331,0.0009399342,0.0022064864,0.50512296,0.48653302],"study_design_scores_gemma":[0.0017661552,0.0002245908,0.0070471726,0.00003695146,0.0010854868,0.00005258229,0.00018951722,0.9446153,0.021889288,0.004352232,0.017702077,0.0010386654],"about_ca_topic_score_codex":0.0009043822,"about_ca_topic_score_gemma":0.00004097361,"teacher_disagreement_score":0.9446137,"about_ca_system_score_codex":0.00012962837,"about_ca_system_score_gemma":0.0004130459,"threshold_uncertainty_score":0.99912876},"labels":[],"label_agreement":null},{"id":"W2087829477","doi":"10.1016/j.media.2009.10.007","title":"An automatic geometrical and statistical method to detect acoustic shadows in intraoperative ultrasound brain images","year":2009,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"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":"Artificial intelligence; Computer science; Robustness (evolution); Computer vision; Segmentation; Ultrasound; Acoustic shadow; 3D ultrasound; Statistical model; Acoustic impedance; Pattern recognition (psychology); Acoustics; Ultrasonic sensor","score_opus":0.00835886815253391,"score_gpt":0.3524337114892521,"score_spread":0.34407484333671823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087829477","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":[0.0043294057,0.000056999077,0.99036026,0.004519586,0.000021189053,0.0002928167,0.0000134003085,0.0002976575,0.00010868733],"genre_scores_gemma":[0.24216555,0.000020597603,0.7506686,0.0070153372,0.000037959577,0.00003489571,0.00002102886,0.000009022951,0.000027048394],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99520993,0.0010751385,0.00078950176,0.00093873584,0.0014166778,0.00057001575],"domain_scores_gemma":[0.9951492,0.0027910129,0.00009510334,0.000630321,0.00014326787,0.0011911034],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0032000742,0.00028958954,0.00074618426,0.0015912692,0.00010542495,0.00047748288,0.0010389169,0.0001638601,0.0011322041],"category_scores_gemma":[0.0095477,0.00024229503,0.000101832185,0.0054141567,0.00021882735,0.0007967598,0.00015828041,0.00051036844,0.00003690704],"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":[0.000007824106,0.00026384555,0.0003427594,0.000017071305,0.00013549463,0.0006226535,0.00082660385,0.000063343505,0.029757403,0.0002511103,0.0027241353,0.96498775],"study_design_scores_gemma":[0.00094590744,0.0011234344,0.07839705,0.0000594493,0.000423027,0.000107296684,0.00022731686,0.8853024,0.027101757,0.005491506,0.000038313014,0.000782504],"about_ca_topic_score_codex":0.000171955,"about_ca_topic_score_gemma":0.000087055545,"teacher_disagreement_score":0.96420527,"about_ca_system_score_codex":0.00011916678,"about_ca_system_score_gemma":0.0001277888,"threshold_uncertainty_score":0.9997809},"labels":[],"label_agreement":null},{"id":"W2099275521","doi":"10.1016/j.media.2008.02.003","title":"A geometric flow for segmenting vasculature in proton-density weighted MRI","year":2008,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Segmentation; Magnetic resonance imaging; Computer vision; Pattern recognition (psychology); Radiology; Medicine","score_opus":0.013182058574639463,"score_gpt":0.3154482726148905,"score_spread":0.30226621404025106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099275521","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":[0.06478257,0.00022135979,0.9311484,0.0022524307,0.000009051963,0.0010936025,0.00000839406,0.00012260229,0.00036158503],"genre_scores_gemma":[0.29561135,0.0009014296,0.699492,0.0012093155,0.00024294073,0.00110347,0.00038995306,0.000034762437,0.0010148062],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984749,0.000022125314,0.00035182128,0.00036349648,0.00050079264,0.00028689424],"domain_scores_gemma":[0.9990405,0.000099145,0.0000787664,0.00037308858,0.00018324405,0.0002252514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037704755,0.00013248839,0.0005017757,0.00065393676,0.000119343276,0.000008317023,0.00011359038,0.0001593986,0.00032437083],"category_scores_gemma":[0.00048314442,0.00010595314,0.00038885852,0.0038224792,0.000108808395,0.00007555522,0.000053349715,0.0003054509,0.00001060623],"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":[0.0007840387,0.008408065,0.66345924,0.001390693,0.0059290044,0.00396824,0.0016335094,0.0005060558,0.017682351,0.0008246341,0.04376242,0.25165176],"study_design_scores_gemma":[0.0064318217,0.0002972384,0.115576275,0.00023725706,0.0050647706,0.00025236956,0.00014756767,0.80973476,0.024011308,0.0017615829,0.035635862,0.00084917137],"about_ca_topic_score_codex":0.000056884088,"about_ca_topic_score_gemma":0.000027982436,"teacher_disagreement_score":0.8092287,"about_ca_system_score_codex":0.00006992905,"about_ca_system_score_gemma":0.00007271973,"threshold_uncertainty_score":0.43206438},"labels":[],"label_agreement":null},{"id":"W2103187823","doi":"10.1016/j.media.2015.04.008","title":"Pico Lantern: Surface reconstruction and augmented reality in laparoscopic surgery using a pick-up laser projector","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Augmented Reality Applications","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research","keywords":"Computer vision; Artificial intelligence; Augmented reality; Computer science; Projector; Surface reconstruction; Biomedical engineering; Medicine; Computer graphics (images); Surface (topology); Mathematics","score_opus":0.05706451839276741,"score_gpt":0.324873144666533,"score_spread":0.26780862627376556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103187823","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":[0.6212941,0.000047409452,0.37650332,0.0017575247,0.00009879711,0.00011682965,0.000008588622,0.000074206175,0.000099262215],"genre_scores_gemma":[0.991794,0.000055656852,0.007661254,0.00024206679,0.000049714065,0.000017962346,0.000039910232,0.000008073569,0.0001313743],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778813,0.00033037146,0.00048826003,0.000511133,0.0006016197,0.0002804623],"domain_scores_gemma":[0.9986671,0.0001898888,0.00016021605,0.00054036535,0.00012228651,0.0003201094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014879191,0.00014129137,0.00043540107,0.000318737,0.00006787851,0.000120134355,0.00033671132,0.000112100395,0.00005081322],"category_scores_gemma":[0.00045708657,0.00012793514,0.000101496116,0.0021261454,0.00018039817,0.00043497115,0.00022912072,0.00021048494,0.000012991252],"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":[0.000084813066,0.0010835157,0.9132784,0.00019945497,0.0019306167,0.000356814,0.0041638734,0.0014639845,0.0026084553,0.00061000104,0.0081226565,0.066097386],"study_design_scores_gemma":[0.0007824799,0.000017171367,0.02329584,0.00007883395,0.00027316404,0.00005605921,0.00023602709,0.9728718,0.001398915,0.00038322885,0.0003296783,0.00027683793],"about_ca_topic_score_codex":0.004534377,"about_ca_topic_score_gemma":0.001985934,"teacher_disagreement_score":0.9714078,"about_ca_system_score_codex":0.00015417502,"about_ca_system_score_gemma":0.000268771,"threshold_uncertainty_score":0.6854651},"labels":[],"label_agreement":null},{"id":"W2106033751","doi":"10.1016/j.media.2013.12.002","title":"Evaluation of prostate segmentation algorithms for MRI: The PROMISE12 challenge","year":2013,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":820,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute; KWF Kankerbestrijding; National Institutes of Health; National Science Foundation","keywords":"Artificial intelligence; Segmentation; Computer science; Algorithm; Computer vision; Prostate; Pattern recognition (psychology); Medicine","score_opus":0.03657965750292922,"score_gpt":0.3547086912706948,"score_spread":0.3181290337677656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106033751","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":[0.001550177,0.00015240813,0.9877267,0.00855152,0.000061166975,0.0015051253,0.000004540532,0.000095710784,0.00035266374],"genre_scores_gemma":[0.18018322,0.00029809674,0.812542,0.0017107532,0.00018474051,0.004515063,0.00014772004,0.000026389192,0.0003919874],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99567354,0.00045061536,0.0005555052,0.00036847408,0.0027150633,0.00023680922],"domain_scores_gemma":[0.9973446,0.000293991,0.00027373113,0.0005536917,0.0013592794,0.0001747046],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005184345,0.0001302823,0.0002695637,0.00022323063,0.00010396221,0.00012269632,0.000812546,0.000074143514,0.0012905238],"category_scores_gemma":[0.0013197721,0.00008410465,0.0002076533,0.0010652986,0.00019561358,0.0007082358,0.00013515132,0.00012498305,0.000032857948],"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":[0.0000020021416,0.00016598284,0.00007275564,0.000029898018,0.000523212,0.0000012270241,0.0011543231,0.000019126168,0.0021344975,0.00014473786,0.0045494833,0.9912028],"study_design_scores_gemma":[0.00074880396,0.00010605013,0.00078758324,0.000017237317,0.0009898231,0.0000011865905,0.00022574014,0.95205534,0.03980379,0.005059289,0.00007665533,0.00012852123],"about_ca_topic_score_codex":0.00013486753,"about_ca_topic_score_gemma":0.0000201749,"teacher_disagreement_score":0.9910742,"about_ca_system_score_codex":0.00007019517,"about_ca_system_score_gemma":0.00019057232,"threshold_uncertainty_score":0.9996224},"labels":[],"label_agreement":null},{"id":"W2109185541","doi":"10.1016/j.media.2006.06.008","title":"Intra-subject elastic registration of 3D ultrasound images","year":2006,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Voxel; Artificial intelligence; Computer vision; 3D ultrasound; Image registration; Process (computing); Ultrasound; Speckle pattern; Image (mathematics); Radiology; Medicine","score_opus":0.006560609823574037,"score_gpt":0.2707165386954212,"score_spread":0.2641559288718472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109185541","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":[0.0026067581,0.00010729905,0.9914423,0.0007878555,0.00005885399,0.00009816659,0.00000564927,0.00023344383,0.004659642],"genre_scores_gemma":[0.5960137,0.000068582034,0.40233728,0.0005588098,0.00015404177,0.000025949763,0.00008961879,0.0000124351745,0.000739529],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9966976,0.00021072889,0.0007917824,0.0004553237,0.0015560945,0.00028848008],"domain_scores_gemma":[0.9980068,0.0005890627,0.00030954625,0.000660108,0.00023513133,0.00019930956],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011457341,0.00017172284,0.0004176429,0.00043300155,0.000071899965,0.000139282,0.00090976787,0.00011862304,0.0012626888],"category_scores_gemma":[0.0018283917,0.00014731825,0.00021933006,0.0022339763,0.00041291377,0.0005946544,0.000106837935,0.00022375044,0.000041131443],"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":[0.00003808843,0.0022136827,0.01512404,0.0003435887,0.0022827012,0.0009942062,0.0007101663,0.0002058641,0.541667,0.007989342,0.14026296,0.2881684],"study_design_scores_gemma":[0.0011923704,0.00027416623,0.037081443,0.00011434686,0.0015987429,0.000079216356,0.000084522915,0.06030051,0.8903494,0.007647916,0.00040501275,0.0008723376],"about_ca_topic_score_codex":0.0006695145,"about_ca_topic_score_gemma":0.00010293513,"teacher_disagreement_score":0.593407,"about_ca_system_score_codex":0.000046139518,"about_ca_system_score_gemma":0.00012847308,"threshold_uncertainty_score":0.9996503},"labels":[],"label_agreement":null},{"id":"W2109762309","doi":"10.1016/j.media.2014.11.009","title":"Non-invasive evaluation of breast cancer response to chemotherapy using quantitative ultrasonic backscatter parameters","year":2014,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Ultrasound Imaging and Elastography","field":"Medicine","cited_by":134,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto","funders":"National Institute of Biomedical Imaging and Bioengineering; Ontario Ministry of Research and Innovation; Canadian Institutes of Health Research; Research and Innovation Foundation","keywords":"Medicine; Ultrasound; Chemotherapy; Breast cancer; Backscatter (email); Radiology; Cancer; Nuclear medicine; Internal medicine","score_opus":0.02130449228885332,"score_gpt":0.35133687314363643,"score_spread":0.3300323808547831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109762309","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":[0.9184468,0.000060219725,0.075401984,0.005667465,0.00005501034,0.00021149067,0.000021101807,0.000019755458,0.00011617337],"genre_scores_gemma":[0.9768715,0.000039825423,0.0201039,0.0028158175,0.00006362454,0.000020386498,0.000023905463,0.000022705595,0.00003832],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99711907,0.00039405926,0.0004076097,0.00039189076,0.0013896866,0.00029769636],"domain_scores_gemma":[0.99769145,0.00065782305,0.0001551706,0.00040717667,0.0007279413,0.00036045187],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027058444,0.00018626482,0.0006147579,0.0007237123,0.00006165635,0.000023335715,0.00013952565,0.00008972409,0.001763628],"category_scores_gemma":[0.0019339999,0.00014962819,0.00043465543,0.0020934418,0.00027908894,0.00009848947,0.0000169392,0.00019006828,0.000030242398],"study_design_candidate":"observational","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":[0.002681222,0.00057912536,0.27449656,0.00010966868,0.0072151814,0.000008426343,0.0041626287,0.0019050712,0.6870437,0.0000025021727,0.001008339,0.020787584],"study_design_scores_gemma":[0.0050478093,0.0005327432,0.78921527,0.0006651634,0.017155405,0.00008048799,0.0014988892,0.15663779,0.028343303,0.00005926255,0.00023975605,0.0005241352],"about_ca_topic_score_codex":0.0009968692,"about_ca_topic_score_gemma":0.0000972748,"teacher_disagreement_score":0.6587004,"about_ca_system_score_codex":0.00012038096,"about_ca_system_score_gemma":0.00033468666,"threshold_uncertainty_score":0.9991489},"labels":[],"label_agreement":null},{"id":"W2111627180","doi":"10.1016/j.media.2009.01.004","title":"Directional functions for orientation distribution estimation","year":2009,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Center for Research Resources; National Institute of General Medical Sciences; National Institute of Mental Health","keywords":"Spherical harmonics; Orientation (vector space); Interpolation (computer graphics); Spherical coordinate system; Computer science; Unit sphere; Tractography; Geodesic; Algorithm; Diffusion MRI; Artificial intelligence; Mathematics; Computer vision; Mathematical analysis; Geometry; Image (mathematics)","score_opus":0.03070482850914545,"score_gpt":0.3971433175471677,"score_spread":0.36643848903802223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111627180","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":[0.006793665,0.000016394439,0.9803461,0.011834591,0.000025524101,0.00024097362,0.000053638993,0.00022188041,0.00046725513],"genre_scores_gemma":[0.9032915,0.000029836961,0.08878592,0.0013148823,0.0001819562,0.00016030794,0.005293769,0.000008826432,0.00093298143],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990873,0.000012757345,0.00022145867,0.00023704984,0.0003148306,0.00012661553],"domain_scores_gemma":[0.9993493,0.000070053684,0.00006376034,0.00019097528,0.00018527824,0.0001406575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015923577,0.00007882801,0.00017425625,0.00012477158,0.00015535273,0.000017509376,0.000044273493,0.000053723008,0.0002459835],"category_scores_gemma":[0.0005626415,0.000070322225,0.00020319286,0.0009427979,0.0000511582,0.00011174156,0.000006781728,0.00010527919,0.000015747843],"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":[0.0003701963,0.0023031572,0.011874453,0.000070186914,0.0010355491,0.000033697306,0.00009416044,0.00090818765,0.016294105,0.015430977,0.097095564,0.85448974],"study_design_scores_gemma":[0.0018723585,0.0005037973,0.18429676,0.000048531885,0.005976167,0.00007377211,0.000054319993,0.7229784,0.007883253,0.013216169,0.06272858,0.0003678643],"about_ca_topic_score_codex":0.000007462496,"about_ca_topic_score_gemma":0.0000022288925,"teacher_disagreement_score":0.89649785,"about_ca_system_score_codex":0.00006600474,"about_ca_system_score_gemma":0.000040245213,"threshold_uncertainty_score":0.28676572},"labels":[],"label_agreement":null},{"id":"W2112571055","doi":"10.1016/j.media.2015.04.001","title":"Globally optimal co-segmentation of three-dimensional pulmonary 1H and hyperpolarized 3He MRI with spatial consistence prior","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Atomic and Subatomic Physics Research","field":"Physics and Astronomy","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Canadian Institutes of Health Research","keywords":"Segmentation; Convex optimization; Robustness (evolution); Image segmentation; Computer science; Algorithm; Artificial intelligence; Regular polygon; Mathematical optimization; Pattern recognition (psychology); Mathematics","score_opus":0.014910975680764152,"score_gpt":0.2915944086527316,"score_spread":0.27668343297196746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112571055","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":[0.6198666,0.000064469205,0.3773783,0.00039875592,0.000014987331,0.00014887915,0.00006083485,0.000012695308,0.0020544524],"genre_scores_gemma":[0.99437535,0.0000027091542,0.005161998,0.000057288067,0.00008247386,0.000012196746,0.00018389049,0.000010114304,0.00011400496],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795604,0.000096959164,0.00031098715,0.00031230898,0.0010793847,0.00024431862],"domain_scores_gemma":[0.9989148,0.00012186689,0.0001314558,0.000214049,0.00024234163,0.00037552576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048107814,0.00015338713,0.0004406413,0.000100559635,0.00008156475,0.000040875817,0.00020402526,0.00005028064,0.0007632935],"category_scores_gemma":[0.00003218854,0.000115220915,0.00012928068,0.00042596672,0.00050635333,0.0001700199,0.00012089405,0.00019630192,0.000019947156],"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":[0.0010149614,0.0009757285,0.817703,0.000040955638,0.0050117206,0.00017495961,0.00047529515,0.00042974917,0.008704765,0.0010747584,0.0014259882,0.16296813],"study_design_scores_gemma":[0.003086607,0.00011109146,0.014599341,0.000040947387,0.0013863458,0.000012215901,0.0009954218,0.97424257,0.0038644567,0.0011364634,0.00014480478,0.00037972326],"about_ca_topic_score_codex":0.0020601917,"about_ca_topic_score_gemma":0.00005326583,"teacher_disagreement_score":0.9738128,"about_ca_system_score_codex":0.000038210128,"about_ca_system_score_gemma":0.0005901975,"threshold_uncertainty_score":0.8357528},"labels":[],"label_agreement":null},{"id":"W2118740630","doi":"10.1016/j.media.2008.02.002","title":"Regions, systems, and the brain: Hierarchical measures of functional integration in fMRI","year":2008,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":78,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Functional integration; Computer science; Information flow; Mutual information; Information integration; Artificial intelligence; Functional connectivity; Neuroscience; Measure (data warehouse); Resting state fMRI; Cognitive science; Machine learning; Psychology; Data mining; Mathematics","score_opus":0.05515823734104367,"score_gpt":0.274552352493841,"score_spread":0.21939411515279736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118740630","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":[0.4696374,0.0017072973,0.21650435,0.30774358,0.00040867637,0.000582273,0.000019273619,0.000105241634,0.0032919173],"genre_scores_gemma":[0.9966563,0.00027482948,0.0000435143,0.0025879582,0.00008325752,0.000037865415,0.0000043654336,0.0000051838774,0.0003067466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973138,0.0007720133,0.00035901307,0.00034787197,0.0010592766,0.0001480362],"domain_scores_gemma":[0.98946667,0.010052525,0.000094823255,0.00021625569,0.000091654685,0.00007804704],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012873498,0.000108117485,0.00038560692,0.00032169904,0.0001924342,0.000019096507,0.00014936244,0.00006553059,0.000077411256],"category_scores_gemma":[0.046259034,0.000066152534,0.00015047273,0.0013135202,0.0015805648,0.0001282907,0.000087384884,0.00030378357,0.000006667303],"study_design_candidate":"observational","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":[0.0068671275,0.0029072496,0.1641976,0.0002954695,0.0042181755,0.0017593552,0.01738756,0.0044219457,0.070692234,0.37599233,0.31668028,0.03458068],"study_design_scores_gemma":[0.014001279,0.0005041435,0.43648654,0.0003155605,0.0018330383,0.0011224089,0.0037528914,0.5025963,0.010609223,0.014954133,0.0125766555,0.0012478305],"about_ca_topic_score_codex":0.00028138875,"about_ca_topic_score_gemma":0.0003710228,"teacher_disagreement_score":0.5270189,"about_ca_system_score_codex":0.000030422903,"about_ca_system_score_gemma":0.00007095461,"threshold_uncertainty_score":0.9617747},"labels":[],"label_agreement":null},{"id":"W2118891573","doi":"10.1016/s1361-8415(00)00008-6","title":"T-snakes: Topology adaptive snakes","year":2000,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":413,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Topology (electrical circuits); Computer science; Artificial intelligence; Mathematics; Combinatorics","score_opus":0.0049221644127234645,"score_gpt":0.2713293990795815,"score_spread":0.266407234666858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118891573","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":[0.73129857,0.0022008433,0.1331824,0.002489623,0.000041353273,0.0003040686,0.000023350052,0.0002426918,0.13021712],"genre_scores_gemma":[0.97727746,0.0012031051,0.0045968737,0.0025337792,0.00036865758,0.00004183679,0.00042427942,0.00003167405,0.013522315],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99785846,0.00019455978,0.00041576507,0.00065947557,0.00047018318,0.0004015336],"domain_scores_gemma":[0.9986744,0.000034766123,0.00007954506,0.0007947583,0.00013476875,0.0002817671],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00045941316,0.00023830931,0.00047394037,0.00022537296,0.00010038616,0.000040387018,0.00051240757,0.00030558518,0.019648114],"category_scores_gemma":[0.00029696187,0.00020842037,0.0006302285,0.00087813055,0.0004393115,0.000009977587,0.000107436645,0.00021042356,0.00023557148],"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":[0.0005487401,0.0016832895,0.019010844,0.00004020334,0.01969182,0.0015324268,0.0003513683,0.00014696678,0.2795483,0.00024018636,0.26525205,0.4119538],"study_design_scores_gemma":[0.001774194,0.0011186608,0.0073884195,0.000031438776,0.008944613,0.00012403677,0.0005535565,0.01479223,0.4575751,0.00064194243,0.50507116,0.0019846228],"about_ca_topic_score_codex":0.0003016647,"about_ca_topic_score_gemma":0.0005879514,"teacher_disagreement_score":0.40996918,"about_ca_system_score_codex":0.00001829977,"about_ca_system_score_gemma":0.000073938136,"threshold_uncertainty_score":0.9812481},"labels":[],"label_agreement":null},{"id":"W2122126162","doi":"10.1016/j.media.2011.05.009","title":"Max-flow segmentation of the left ventricle by recovering subject-specific distributions via a bound of the Bhattacharyya measure","year":2011,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CARE Canada; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bhattacharyya distance; Segmentation; Metric (unit); Measure (data warehouse); Active contour model; Kernel density estimation; Algorithm; Mathematics; Similarity measure; Computer science; Flow (mathematics); Artificial intelligence; Active shape model; Kernel (algebra); Similarity (geometry); Image segmentation; Mathematical optimization; Image (mathematics); Data mining; Geometry","score_opus":0.014707241027463076,"score_gpt":0.250092132108051,"score_spread":0.2353848910805879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122126162","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":[0.016090669,0.00019061781,0.9823595,0.0006523383,0.00013111642,0.00020101751,0.000038251794,0.0000449876,0.00029147565],"genre_scores_gemma":[0.9508714,0.000090079564,0.048498314,0.00032263546,0.000025641883,0.000024300492,0.00004478508,0.000010617721,0.00011222584],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9971167,0.00037048687,0.00059467286,0.00031451805,0.0013724826,0.00023114815],"domain_scores_gemma":[0.99829787,0.00012635173,0.00036658096,0.0008594092,0.0002041699,0.00014559996],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00095827965,0.00013723466,0.0002964936,0.00012083593,0.00016712883,0.00004579586,0.0014793227,0.00008648929,0.0015865118],"category_scores_gemma":[0.00042651856,0.0000859481,0.00038042982,0.0020213323,0.00043657934,0.00037069336,0.0003650682,0.00024635505,0.000007245846],"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":[0.00003852507,0.0020243844,0.059217606,0.00015925585,0.0023033647,0.000041802257,0.007176028,0.000016292366,0.42924318,0.00054752966,0.03842894,0.4608031],"study_design_scores_gemma":[0.00042802095,0.000050230934,0.035675786,0.00006860707,0.0004485684,0.00001083619,0.00011581403,0.016682424,0.94537604,0.00075991463,0.00019405165,0.00018969105],"about_ca_topic_score_codex":0.00024608284,"about_ca_topic_score_gemma":0.000045546938,"teacher_disagreement_score":0.9347807,"about_ca_system_score_codex":0.00008315241,"about_ca_system_score_gemma":0.0000931681,"threshold_uncertainty_score":0.99932617},"labels":[],"label_agreement":null},{"id":"W2125700054","doi":"10.1016/j.media.2012.06.001","title":"Ultrasound–fluoroscopy registration for prostate brachytherapy dosimetry","year":2012,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Cancer Institute; Cancer Care Ontario","keywords":"Image registration; Fluoroscopy; Prostate brachytherapy; Brachytherapy; Imaging phantom; Ultrasound; Fiducial marker; Medicine; Dosimetry; Prostate; Artificial intelligence; Computer vision; Computer science; Nuclear medicine; Radiology; Radiation therapy; Image (mathematics); Cancer","score_opus":0.006868823869743458,"score_gpt":0.319200043771111,"score_spread":0.31233121990136753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125700054","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":[0.03144549,0.0002931404,0.96674716,0.0002596053,0.000055748496,0.00025698513,0.00003967381,0.000100477286,0.0008017095],"genre_scores_gemma":[0.88225263,0.00006847073,0.11487639,0.00044148846,0.0008573857,0.00019521074,0.00033678766,0.00003506487,0.00093658397],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986845,0.00005506114,0.00030532153,0.00023303265,0.00034496648,0.00037711265],"domain_scores_gemma":[0.99903923,0.00020272477,0.00015144047,0.0003166357,0.00006654718,0.00022343235],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005000967,0.00016354842,0.0003136352,0.00013102306,0.00011720799,0.000050555962,0.0001707425,0.00006479297,0.0026791058],"category_scores_gemma":[0.0000649524,0.00013789932,0.00031082737,0.0006041228,0.000115374925,0.00040565128,0.000010918461,0.00015065446,0.0000069664907],"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":[0.000121072044,0.0010309396,0.68344474,0.00003877522,0.0044218763,0.0000026904395,0.0011250094,0.00001914735,0.09348483,0.006166547,0.017514972,0.1926294],"study_design_scores_gemma":[0.0044742716,0.00054399663,0.03871299,0.000077977485,0.0046548764,0.000012648681,0.00053188537,0.016619798,0.76240873,0.012857482,0.15668075,0.0024246143],"about_ca_topic_score_codex":0.00011891545,"about_ca_topic_score_gemma":0.0000039519537,"teacher_disagreement_score":0.8518708,"about_ca_system_score_codex":0.000032750053,"about_ca_system_score_gemma":0.000034663946,"threshold_uncertainty_score":0.9982326},"labels":[],"label_agreement":null},{"id":"W2126675188","doi":"10.1016/j.media.2008.06.002","title":"Robotic assistance for ultrasound-guided prostate brachytherapy","year":2008,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":126,"is_retracted":false,"has_abstract":false,"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; Engineering Research Centers","keywords":"Brachytherapy; Prostate brachytherapy; Prostate; Ultrasound; Artificial intelligence; Computer science; Medical physics; Medicine; Computer vision; Radiology; Radiation therapy; Internal medicine","score_opus":0.012192385800863625,"score_gpt":0.30938550927034125,"score_spread":0.2971931234694776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126675188","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":[0.02069587,0.00020104785,0.97724336,0.0005370202,0.000035877845,0.00026991984,0.000025958874,0.00013278257,0.0008581341],"genre_scores_gemma":[0.7623112,0.00026634644,0.23106527,0.0008955102,0.00051366875,0.00032966866,0.00024615857,0.000065359476,0.0043067797],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983918,0.00005558905,0.0003800158,0.00038840575,0.00042055748,0.0003636127],"domain_scores_gemma":[0.9988747,0.00024330849,0.00014830731,0.0003995523,0.00013753379,0.00019658986],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00025106885,0.00020041554,0.0004911313,0.00014240699,0.00021236448,0.000030959636,0.00027065503,0.000057009063,0.0024277004],"category_scores_gemma":[0.00007223566,0.00016982788,0.00045850995,0.0007731835,0.00024378044,0.00020013849,0.000014572712,0.0001755676,0.000007283787],"study_design_candidate":"observational","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":[0.00021688301,0.0017859136,0.7698149,0.00007777717,0.014013117,0.00017161136,0.001918318,0.0017742782,0.035676755,0.006032439,0.090345316,0.078172706],"study_design_scores_gemma":[0.02274721,0.0016182939,0.14472961,0.00033356657,0.010902926,0.0002969792,0.00085127994,0.27989703,0.19997382,0.060238443,0.26914948,0.009261349],"about_ca_topic_score_codex":0.000087736735,"about_ca_topic_score_gemma":0.000008192814,"teacher_disagreement_score":0.74617815,"about_ca_system_score_codex":0.000040553623,"about_ca_system_score_gemma":0.00007979946,"threshold_uncertainty_score":0.9984842},"labels":[],"label_agreement":null},{"id":"W2127412835","doi":"10.1016/j.media.2014.02.009","title":"Dual optimization based prostate zonal segmentation in 3D MR images","year":2014,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Canadian Institutes of Health Research","keywords":"Prostate; Segmentation; Consistency (knowledge bases); Computer science; Artificial intelligence; Prostate gland; Image segmentation; Relaxation (psychology); Algorithm; Pattern recognition (psychology); Mathematics; Medicine","score_opus":0.006099888535110403,"score_gpt":0.2740379779660794,"score_spread":0.26793808943096903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127412835","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":[0.0007397684,0.000018896942,0.9950391,0.0029646344,0.00006298937,0.00019729536,0.000004142053,0.0002720568,0.00070110173],"genre_scores_gemma":[0.077582516,0.000032959684,0.91827035,0.0035383406,0.00007648865,0.00009547274,0.00021494324,0.000015048035,0.00017390547],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963808,0.00050305884,0.0006491647,0.00059002714,0.0015169634,0.00035998406],"domain_scores_gemma":[0.9985044,0.00030553882,0.00019197764,0.0004906149,0.0001828385,0.00032463766],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019137901,0.00019654984,0.00036730358,0.0007976204,0.00008549285,0.00023555793,0.0005959815,0.00011368763,0.001694189],"category_scores_gemma":[0.0012026551,0.00017657263,0.00014854461,0.0025179535,0.00019139863,0.00090759003,0.00016116971,0.00026395798,0.00005182799],"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":[0.00006262857,0.0016277668,0.02416587,0.00019060085,0.00069368194,0.0006405374,0.0014871045,0.07191706,0.014271711,0.00049818994,0.012246386,0.87219846],"study_design_scores_gemma":[0.00070465275,0.00005930031,0.0016601466,0.000023976683,0.00010317053,0.000002687849,0.000020853067,0.9794311,0.017631173,0.000112699876,0.000053134583,0.00019711566],"about_ca_topic_score_codex":0.000121582925,"about_ca_topic_score_gemma":0.00003822545,"teacher_disagreement_score":0.90751404,"about_ca_system_score_codex":0.000091321825,"about_ca_system_score_gemma":0.00012982715,"threshold_uncertainty_score":0.9992184},"labels":[],"label_agreement":null},{"id":"W2127556538","doi":"10.1016/j.media.2012.07.001","title":"Tongue contour tracking in dynamic ultrasound via higher-order MRFs and efficient fusion moves","year":2012,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Traditional Chinese Medicine Studies","field":"Medicine","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Computer vision; Markov random field; Regularization (linguistics); Hidden Markov model; Energy minimization; Tracking (education); Image segmentation; Pattern recognition (psychology)","score_opus":0.009603979836587473,"score_gpt":0.30489716795757427,"score_spread":0.2952931881209868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127556538","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":[0.9814876,0.003753515,0.007318467,0.005345216,0.0001876392,0.00019478406,0.000009593419,0.00006145994,0.0016417393],"genre_scores_gemma":[0.99705803,0.0002458246,0.00083818694,0.0009928748,0.0003965227,0.000020881489,0.00011187935,0.000021372667,0.00031442606],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975123,0.000102389,0.00049575703,0.00035165699,0.0010733629,0.00046452554],"domain_scores_gemma":[0.9984782,0.0005520037,0.0000877101,0.00024668942,0.000137838,0.00049755967],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008372267,0.0002485956,0.00078004686,0.0005227208,0.00009934499,0.000017219914,0.00009286273,0.00012503448,0.0017634637],"category_scores_gemma":[0.0014630569,0.0001774994,0.00017772098,0.0013966634,0.00038608396,0.00011780675,0.000061144456,0.00043757368,0.000027502918],"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":[0.00019685211,0.0027230834,0.943328,0.0003389721,0.0031101003,0.00077590335,0.003914121,0.00007427445,0.023366973,0.00022680331,0.001252199,0.020692682],"study_design_scores_gemma":[0.001620944,0.00005999749,0.98757756,0.00011594545,0.0015667144,0.000085925414,0.00036110886,0.007911617,0.00011065563,0.00006174606,0.00034213794,0.00018563072],"about_ca_topic_score_codex":0.0003912324,"about_ca_topic_score_gemma":0.00036539888,"teacher_disagreement_score":0.04424954,"about_ca_system_score_codex":0.000109053886,"about_ca_system_score_gemma":0.000044715525,"threshold_uncertainty_score":0.9991491},"labels":[],"label_agreement":null},{"id":"W2132017284","doi":"10.1016/j.media.2010.02.003","title":"A fast and robust patient specific Finite Element mesh registration technique: Application to 60 clinical cases","year":2010,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":68,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mesh generation; Finite element method; Computer science; Representation (politics); Computation; Algorithm; Process (computing); Computer vision; Artificial intelligence","score_opus":0.014806047416593082,"score_gpt":0.2783070879995928,"score_spread":0.2635010405829997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132017284","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":[0.079836,0.00005852817,0.91878885,0.0005575939,0.000046550333,0.0001557609,0.000013860567,0.00015561127,0.00038725053],"genre_scores_gemma":[0.97516215,0.00022781511,0.02396922,0.00016672413,0.00018239857,0.0001086823,0.00011466872,0.000018465562,0.0000498552],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820673,0.000047098794,0.00066054316,0.0003789642,0.0004933326,0.00021333729],"domain_scores_gemma":[0.9988906,0.00014637453,0.00006759911,0.00044077504,0.00010190572,0.00035276447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007734573,0.00016314063,0.00036166774,0.00029450448,0.00007915009,0.0000788419,0.00015520767,0.00015685336,0.00041903887],"category_scores_gemma":[0.00034209943,0.00014571626,0.00020872393,0.0008898372,0.00007720423,0.000075820506,0.000048294347,0.00038312492,0.00004395591],"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":[0.000031918153,0.00044575508,0.00827353,0.00008275626,0.0018673817,0.00028124324,0.0004489194,0.16039138,0.013221352,0.00010537868,0.012974664,0.8018757],"study_design_scores_gemma":[0.00012361203,0.000047719128,0.0007540291,0.000012790194,0.0005900931,0.000006688343,0.00008897156,0.994081,0.0009534241,0.000030864136,0.0030939267,0.00021686763],"about_ca_topic_score_codex":0.00008383104,"about_ca_topic_score_gemma":0.0005333095,"teacher_disagreement_score":0.8953262,"about_ca_system_score_codex":0.000022858647,"about_ca_system_score_gemma":0.000017095006,"threshold_uncertainty_score":0.59421366},"labels":[],"label_agreement":null},{"id":"W2132322720","doi":"10.1016/s1361-8415(03)00037-9","title":"A fully automatic and robust brain MRI tissue classification method","year":2003,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":336,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Parametric statistics; Classifier (UML); Data set; Set (abstract data type); Magnetic resonance imaging; Mathematics; Statistics; Medicine","score_opus":0.01855722862763469,"score_gpt":0.3401510110432345,"score_spread":0.32159378241559977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132322720","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":[0.00023915927,0.00012025692,0.9875069,0.010014971,0.000043268767,0.00015479741,0.0000011833697,0.0003617809,0.0015576573],"genre_scores_gemma":[0.0063737365,0.00005887064,0.9892604,0.00352294,0.000028514205,0.000051765328,0.000014087315,0.000010519718,0.0006792076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966839,0.0007893838,0.0005276833,0.0005960699,0.0011003952,0.00030257434],"domain_scores_gemma":[0.997906,0.00061509863,0.00016603236,0.0006806951,0.00013165695,0.000500511],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002850471,0.00017492715,0.00039956707,0.00044639647,0.00012046903,0.00024593654,0.0006474261,0.00013873575,0.0019377952],"category_scores_gemma":[0.0032053336,0.0001488885,0.00011524649,0.0021754778,0.00019323509,0.0005202226,0.00013292755,0.00024836077,0.000071623675],"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":[0.000001357883,0.00021034511,0.00046869545,0.00006572242,0.0005132916,0.00017794527,0.00070455467,0.000013143892,0.0090042865,0.00701326,0.025059042,0.95676833],"study_design_scores_gemma":[0.0004562471,0.000075076285,0.0024188822,0.00002923261,0.0004415053,0.00006009806,0.00013618096,0.96878934,0.021883013,0.002372942,0.0029836632,0.00035383663],"about_ca_topic_score_codex":0.00005179056,"about_ca_topic_score_gemma":0.000021697044,"teacher_disagreement_score":0.96877617,"about_ca_system_score_codex":0.000048660106,"about_ca_system_score_gemma":0.00011974026,"threshold_uncertainty_score":0.99897456},"labels":[],"label_agreement":null},{"id":"W2134834581","doi":"10.1016/s1361-8415(00)00014-1","title":"An algorithmic overview of surface registration techniques for medical imaging","year":2000,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":411,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Computer science; Rigid transformation; Robustness (evolution); Image registration; Representation (politics); Artificial intelligence; Modalities; Transformation (genetics); Surface (topology); Similarity (geometry); Exploit; Similarity measure; Matching (statistics); Point set registration; Computer vision; Theoretical computer science; Point (geometry); Mathematics; Image (mathematics); Geometry","score_opus":0.01076959209935504,"score_gpt":0.3015921323986959,"score_spread":0.2908225402993409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134834581","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":[0.033265032,0.0014181612,0.9632478,0.0007081867,0.000020849047,0.00008731087,0.000023992354,0.0003414058,0.0008873094],"genre_scores_gemma":[0.9769732,0.0020439306,0.020257374,0.00016225158,0.00014977965,0.000017770726,0.0001985153,0.00003181555,0.0001653881],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800813,0.00006134029,0.0005826818,0.0002661475,0.00083501893,0.00024665738],"domain_scores_gemma":[0.9991005,0.000086478576,0.000050143135,0.00038116932,0.00010793674,0.0002737781],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010710938,0.00016209578,0.0005021388,0.00018269173,0.000053397056,0.000036892037,0.00033955293,0.00013775844,0.004223445],"category_scores_gemma":[0.00015147429,0.00014663364,0.00039223715,0.00087961816,0.00010020524,0.00018629084,0.000010667019,0.00018027356,0.000011078712],"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":[0.000013084318,0.00020951395,0.00096178893,0.0003148477,0.001647069,0.000060234634,0.0001950027,0.023090567,0.0024626972,0.000037206468,0.0032538972,0.96775407],"study_design_scores_gemma":[0.00013969456,0.000013480068,0.00006675186,0.00005914619,0.00089508446,0.000003401509,0.000030034045,0.995624,0.002126081,0.00012022119,0.00076633936,0.0001557549],"about_ca_topic_score_codex":0.00023828016,"about_ca_topic_score_gemma":0.000085084,"teacher_disagreement_score":0.97253346,"about_ca_system_score_codex":0.000029302488,"about_ca_system_score_gemma":0.00004899081,"threshold_uncertainty_score":0.9966868},"labels":[],"label_agreement":null},{"id":"W2135407363","doi":"10.1016/j.media.2011.11.007","title":"Construction of 3D MR image-based computer models of pathologic hearts, augmented with histology and optical fluorescence imaging to characterize action potential propagation","year":2011,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Sunnybrook Health Science Centre; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Artificial intelligence; Computer vision; Histology; Action (physics); Computer science; Image (mathematics); Fluorescence; Optical imaging; Pattern recognition (psychology); Biomedical engineering; Optics; Physics; Medicine; Pathology","score_opus":0.021161846180739845,"score_gpt":0.2794185111249943,"score_spread":0.2582566649442544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135407363","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":[0.22455953,0.00000842678,0.774301,0.00079778704,0.000009933605,0.00022162219,0.000006873771,0.00003953744,0.000055314293],"genre_scores_gemma":[0.55298924,0.00001493904,0.44678727,0.00011328054,0.000015837742,0.000023335582,0.00004691776,0.000005415864,0.0000037537413],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889815,0.000042381853,0.0003520392,0.00027970286,0.00028805024,0.0001396633],"domain_scores_gemma":[0.99915916,0.000021275153,0.00016949505,0.00022084247,0.00027819572,0.0001510629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017732852,0.0001093659,0.0003941259,0.0002478477,0.000039465707,0.0000046789505,0.000057501344,0.000066096494,0.00013575963],"category_scores_gemma":[0.000041828072,0.00008402868,0.00007254932,0.00042829983,0.0005342285,0.00012291547,0.000035711877,0.00013445203,0.0000010160887],"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":[0.0011702483,0.0010474618,0.007805693,0.00023343365,0.0002695659,0.00027057083,0.00028521375,0.00018017771,0.77683586,0.0008640608,0.00008304329,0.21095467],"study_design_scores_gemma":[0.0017040736,0.0008093476,0.039229263,0.00018957778,0.0023796996,0.0003608616,0.00012458659,0.7814045,0.17315893,0.00035902727,0.00002592638,0.0002542381],"about_ca_topic_score_codex":0.000059658385,"about_ca_topic_score_gemma":0.000004658745,"teacher_disagreement_score":0.7812243,"about_ca_system_score_codex":0.000030755487,"about_ca_system_score_gemma":0.000052479383,"threshold_uncertainty_score":0.342659},"labels":[],"label_agreement":null},{"id":"W2149314739","doi":"10.1016/j.media.2006.06.009","title":"3D curve inference for diffusion MRI regularization and fibre tractography☆","year":2006,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"","keywords":"Tractography; Regularization (linguistics); Diffusion MRI; Inference; Artificial intelligence; Computer science; Mathematics; Pattern recognition (psychology); Magnetic resonance imaging; Medicine; Radiology","score_opus":0.019148141866167187,"score_gpt":0.3437552625796552,"score_spread":0.324607120713488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149314739","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":[0.03584045,0.000097905286,0.95826185,0.004895807,0.000006619108,0.00025440648,0.000016388407,0.00013139042,0.00049520854],"genre_scores_gemma":[0.875179,0.00032837057,0.12197487,0.0007405258,0.00013870095,0.0001102177,0.0006094702,0.000020588492,0.0008982404],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99904054,0.00001750873,0.00023576687,0.00028971772,0.00026984533,0.00014663076],"domain_scores_gemma":[0.9993047,0.00012886745,0.00007503729,0.00025689867,0.000110202105,0.0001242798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000136272,0.000101976286,0.00025462234,0.00021300839,0.00009694041,0.000023085391,0.00006611558,0.00007885619,0.00011286941],"category_scores_gemma":[0.00022540115,0.000083169165,0.00014757227,0.0007940628,0.00013995603,0.00007870367,0.0000334864,0.0001230022,0.0000014401666],"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":[0.0002538866,0.0024832375,0.5430996,0.00053313695,0.0010239185,0.00014516531,0.00020464872,0.00008926561,0.13374206,0.014565481,0.022881314,0.28097832],"study_design_scores_gemma":[0.00288384,0.00035595434,0.51853704,0.00019221618,0.005965773,0.000052012485,0.00005230208,0.3808227,0.010679129,0.026578112,0.053223845,0.0006570852],"about_ca_topic_score_codex":0.00006142188,"about_ca_topic_score_gemma":0.000016545308,"teacher_disagreement_score":0.83933854,"about_ca_system_score_codex":0.0000112009175,"about_ca_system_score_gemma":0.000023110131,"threshold_uncertainty_score":0.339154},"labels":[],"label_agreement":null},{"id":"W2150903265","doi":"10.1016/j.media.2013.05.008","title":"Medical image processing on the GPU – Past, present and future","year":2013,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":405,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Vetenskapsrådet","keywords":"Computer science; Image processing; Graphics processing unit; Medical imaging; Artificial intelligence; Computer vision; Histogram; General-purpose computing on graphics processing units; Interpolation (computer graphics); Graphics; Computer graphics; Image registration; Computer graphics (images); Image (mathematics); Parallel computing","score_opus":0.03209868690587763,"score_gpt":0.38649137733420813,"score_spread":0.3543926904283305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150903265","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006002646,0.82016164,0.007655297,0.1667378,0.00005644267,0.0013624715,0.000022209531,0.00025809437,0.0037400653],"genre_scores_gemma":[0.000007772175,0.98328155,0.0047071674,0.0038339288,0.005459144,0.0009496653,0.00036341752,0.00008386511,0.001313506],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937102,0.0003877532,0.0012174194,0.0009950493,0.0030744276,0.0006151573],"domain_scores_gemma":[0.9956487,0.0007579516,0.00043005575,0.0013007548,0.00024280639,0.0016197441],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017661161,0.00066759315,0.0027610774,0.0004668447,0.00027561383,0.00019711406,0.0008903358,0.0008700231,0.013891196],"category_scores_gemma":[0.00093618577,0.0003299824,0.0011388512,0.002030048,0.0011749151,0.00009530483,0.00042466674,0.0025598102,0.0003035779],"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":[0.0000022128183,0.00019430125,0.0000038945045,0.0027312408,0.0008384433,0.00021077428,0.000020803664,1.8302553e-9,7.3315596e-7,0.00009593969,0.19445519,0.8014465],"study_design_scores_gemma":[0.00020166312,0.00004774392,0.000010444416,0.004995549,0.010564164,0.0001975089,0.000041441996,0.002495453,0.0000024521648,0.000058555288,0.9810753,0.00030974764],"about_ca_topic_score_codex":0.00006614589,"about_ca_topic_score_gemma":0.000002522216,"teacher_disagreement_score":0.80113673,"about_ca_system_score_codex":0.00008595035,"about_ca_system_score_gemma":0.0006669224,"threshold_uncertainty_score":0.99991524},"labels":[],"label_agreement":null},{"id":"W2154537621","doi":"10.1016/j.media.2009.10.002","title":"CPOL: Complex phase order likelihood as a similarity measure for MR–CT registration","year":2009,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Similarity measure; Similarity (geometry); Artificial intelligence; Measure (data warehouse); Image registration; Pattern recognition (psychology); Fiducial marker; Computer science; Computer vision; Mutual information; Noise (video); Phase (matter); Mathematics; Image (mathematics); Data mining; Physics","score_opus":0.028935580101750315,"score_gpt":0.3702821879122302,"score_spread":0.34134660781047993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154537621","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":[0.0007147395,0.00006259866,0.9775931,0.019237095,0.000050009756,0.00037129823,0.00001179661,0.00047667156,0.0014826823],"genre_scores_gemma":[0.29283005,0.000051157334,0.6854076,0.02069677,0.0002454433,0.00009588463,0.0003424498,0.000017990777,0.0003126862],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996102,0.00023023676,0.0006987868,0.000708857,0.0017824254,0.00047772317],"domain_scores_gemma":[0.99745756,0.0002355706,0.00024216689,0.0008661849,0.0005545357,0.0006440072],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018338125,0.000245766,0.0005245142,0.0003631519,0.0002116661,0.00030831393,0.0011995493,0.00011629812,0.0012633242],"category_scores_gemma":[0.0034454092,0.0002151734,0.00037799572,0.002320952,0.00018130186,0.00071047986,0.00009609289,0.00030878084,0.000047121546],"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":[0.000038050563,0.0014652204,0.00008633489,0.00003201018,0.0005520648,0.00031696807,0.0003225931,0.0000035406977,0.013588559,0.0017007675,0.08084557,0.9010483],"study_design_scores_gemma":[0.0070159175,0.0016773706,0.0014828931,0.00009717685,0.0021657315,0.00009880111,0.00014462833,0.8651804,0.077000186,0.028897913,0.014880775,0.0013582542],"about_ca_topic_score_codex":0.00012734203,"about_ca_topic_score_gemma":0.00009179829,"teacher_disagreement_score":0.8996901,"about_ca_system_score_codex":0.00007252604,"about_ca_system_score_gemma":0.00029600805,"threshold_uncertainty_score":0.99964964},"labels":[],"label_agreement":null},{"id":"W2158649156","doi":"10.1016/j.media.2004.06.009","title":"Tuning and comparing spatial normalization methods","year":2004,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":221,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"","keywords":"Normalization (sociology); Spatial normalization; Computer science; Artificial intelligence; Image registration; Algorithm; Range (aeronautics); Process (computing); Computer vision; Pattern recognition (psychology); Image (mathematics); Voxel","score_opus":0.017013804513317972,"score_gpt":0.3596544167055799,"score_spread":0.34264061219226194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158649156","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":[0.001901331,0.00007964429,0.995826,0.0011643918,0.000049851787,0.00006240285,2.4286882e-7,0.00026134972,0.0006547512],"genre_scores_gemma":[0.20088038,0.000055221848,0.79793775,0.0010231526,0.000046174715,0.000009834174,0.00001403267,0.0000056828035,0.000027786687],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981279,0.00021266403,0.00036875982,0.0003603374,0.00070985535,0.00022048496],"domain_scores_gemma":[0.9990189,0.000106570675,0.000104456165,0.00033518692,0.00009442331,0.00034048196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013208109,0.00011845558,0.00030965975,0.00035772388,0.00011895704,0.00019005917,0.0005123242,0.00007624339,0.0002561587],"category_scores_gemma":[0.0008187642,0.00010480159,0.00009455473,0.001344722,0.00016753946,0.00058275135,0.00033323202,0.00018850622,0.000013764151],"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":[0.0000048649567,0.00017552999,0.010412726,0.0000478784,0.000632988,0.00021891815,0.0019508282,0.00019266893,0.00890336,0.00369737,0.00028697465,0.9734759],"study_design_scores_gemma":[0.0007235616,0.000047302034,0.0058726906,0.000043372118,0.00035853023,0.000023454082,0.000056391953,0.9461278,0.043861266,0.0024556175,0.00014532967,0.00028470924],"about_ca_topic_score_codex":0.0006681653,"about_ca_topic_score_gemma":0.00009688716,"teacher_disagreement_score":0.9731912,"about_ca_system_score_codex":0.000044778793,"about_ca_system_score_gemma":0.0000643148,"threshold_uncertainty_score":0.4273685},"labels":[],"label_agreement":null},{"id":"W2158727422","doi":"10.1016/j.media.2007.06.002","title":"Activation detection in diffuse optical imaging by means of the general linear model","year":2007,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Optical Imaging and Spectroscopy Techniques","field":"Medicine","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université de Montréal; Polytechnique Montréal; Institut Universitaire de Gériatrie de Montréal","funders":"Canada Research Chairs; Institut National de la Santé et de la Recherche Médicale","keywords":"Computer science; General linear model; Functional magnetic resonance imaging; Artificial intelligence; Diffuse optical imaging; Communication noise; Computer vision; Noise (video); Functional imaging; Basis (linear algebra); Pattern recognition (psychology); Linear model; Image (mathematics); Iterative reconstruction; Machine learning; Mathematics; Neuroscience","score_opus":0.007082030066336433,"score_gpt":0.31845821717452094,"score_spread":0.3113761871081845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158727422","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":[0.44735944,0.000018339497,0.54923767,0.002156774,0.000011906772,0.000075559714,0.000001358655,0.000044165594,0.0010947987],"genre_scores_gemma":[0.9785186,0.00002354357,0.02033542,0.0007845432,0.00006530082,0.00000559077,0.000013398679,0.000014345559,0.00023925495],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820745,0.000045398538,0.00045837814,0.0002527536,0.0007474176,0.0002885866],"domain_scores_gemma":[0.99920285,0.00009892913,0.00007602317,0.00032503487,0.00011072561,0.00018646357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087251974,0.00012662874,0.0003681672,0.00029720887,0.0000454299,0.000012360159,0.0001410163,0.00010643314,0.0000736007],"category_scores_gemma":[0.0009753729,0.00008532059,0.0002556113,0.0012001629,0.00026934323,0.000102274746,0.00005653566,0.00047772515,0.000001947202],"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":[0.00014669998,0.0012108056,0.038096223,0.000039080616,0.00028652835,0.000041161267,0.00017175003,0.00008134835,0.93289286,0.00017106827,0.00048139287,0.026381081],"study_design_scores_gemma":[0.00050053373,0.000021257356,0.0068096644,0.00003080767,0.0003942366,0.0000043336586,0.000028855638,0.5814979,0.41050997,0.000106448664,0.00002972686,0.00006624214],"about_ca_topic_score_codex":0.0002614182,"about_ca_topic_score_gemma":0.000081645616,"teacher_disagreement_score":0.58141655,"about_ca_system_score_codex":0.000115536015,"about_ca_system_score_gemma":0.0000515013,"threshold_uncertainty_score":0.34792727},"labels":[],"label_agreement":null},{"id":"W2160389475","doi":"10.1016/j.media.2015.04.010","title":"Automatic segmentation of occluded vasculature via pulsatile motion analysis in endoscopic robot-assisted partial nephrectomy video","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Computer vision; Segmentation; Artificial intelligence; Computer science; Pulsatile flow; Nephrectomy; Magnification; Medicine; Kidney; Internal medicine","score_opus":0.016997941704835536,"score_gpt":0.3174904747514418,"score_spread":0.3004925330466063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160389475","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":[0.8561824,0.00034189704,0.14137672,0.0013305258,0.00005631322,0.00028746368,0.000010297972,0.00009239968,0.00032198188],"genre_scores_gemma":[0.9912682,0.00003173787,0.007125572,0.00027812715,0.00007609147,0.00010651684,0.00088941614,0.000020253614,0.00020403981],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995282,0.0005937589,0.0011373106,0.00056562386,0.0020306702,0.00039065804],"domain_scores_gemma":[0.99792325,0.0001555029,0.0004212017,0.00065193884,0.00032375153,0.0005243566],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016548792,0.00027796312,0.0015406202,0.0023392292,0.00007033977,0.000048018912,0.00023010939,0.00016714731,0.006209286],"category_scores_gemma":[0.0011443598,0.00023481654,0.0011760447,0.01040763,0.00018069103,0.00024589204,0.00008607117,0.00044647657,0.000024631072],"study_design_candidate":"observational","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":[0.00013023506,0.0013314494,0.8935308,0.00018087165,0.019724563,0.00044314,0.0011053067,0.0053161895,0.008828039,0.0000043596274,0.00048998214,0.068915054],"study_design_scores_gemma":[0.0020357547,0.00009033669,0.33108857,0.000041486408,0.031079933,0.000011652703,0.0005294832,0.6329439,0.0019258574,0.000024540923,0.00005823395,0.0001702166],"about_ca_topic_score_codex":0.0021837957,"about_ca_topic_score_gemma":0.00038436634,"teacher_disagreement_score":0.62762773,"about_ca_system_score_codex":0.00026084718,"about_ca_system_score_gemma":0.00017872876,"threshold_uncertainty_score":0.9946992},"labels":[],"label_agreement":null},{"id":"W2160744602","doi":"10.1016/j.media.2004.06.026","title":"Flux driven automatic centerline extraction","year":2004,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":185,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada","keywords":"Skeletonization; Distance transform; Computer science; Boundary (topology); Artificial intelligence; Key (lock); Function (biology); Algorithm; Computer vision; Mathematics; Image (mathematics); Mathematical analysis","score_opus":0.00872080128720197,"score_gpt":0.3128668158849142,"score_spread":0.30414601459771223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160744602","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":[0.0035766917,0.000032701584,0.9895444,0.0051335213,0.000108809436,0.000107116386,0.00000135913,0.0006942457,0.00080116757],"genre_scores_gemma":[0.23456116,0.00005263226,0.76117563,0.0034680986,0.00013399169,0.000041084564,0.00007015403,0.000013784647,0.00048346174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720466,0.00012217353,0.0005223609,0.00044883895,0.0013899686,0.00031201332],"domain_scores_gemma":[0.9985215,0.00010573284,0.00015074162,0.00063897646,0.0001220994,0.0004609622],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00062333,0.00015905507,0.00033435653,0.00045808815,0.000101106154,0.00017342833,0.0009765759,0.000110567795,0.0031551637],"category_scores_gemma":[0.0006876292,0.00013468775,0.0002658493,0.0019414317,0.00015369324,0.000820782,0.00019851656,0.0002812977,0.0004118337],"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":[0.00000457058,0.0012216201,0.0010025082,0.00007566772,0.0014471479,0.001478068,0.001145029,0.0001579171,0.018690133,0.0019021695,0.010532832,0.9623423],"study_design_scores_gemma":[0.0023030778,0.0002264338,0.008465043,0.00016197994,0.001192748,0.000119585085,0.00014113256,0.860925,0.1193229,0.0049775555,0.0013325564,0.0008319687],"about_ca_topic_score_codex":0.00011579062,"about_ca_topic_score_gemma":0.000042890624,"teacher_disagreement_score":0.96151036,"about_ca_system_score_codex":0.00012451458,"about_ca_system_score_gemma":0.00012522428,"threshold_uncertainty_score":0.99775606},"labels":[],"label_agreement":null},{"id":"W2163009740","doi":"10.1016/j.media.2014.11.003","title":"Subject-specific finite-element modeling of normal aortic valve biomechanics from 3D+t TEE images","year":2014,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cardiac cycle; Aortic valve; Finite element method; Biomechanics; Biomedical engineering; Tearing; Computer science; Mathematics; Medicine; Structural engineering; Anatomy; Surgery; Cardiology; Mechanical engineering; Engineering","score_opus":0.011956026934218758,"score_gpt":0.30368267789873205,"score_spread":0.2917266509645133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163009740","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":[0.6294753,0.0014467343,0.36670843,0.00037419714,0.0001314727,0.00022295803,0.00022585364,0.000072047515,0.00134299],"genre_scores_gemma":[0.99486756,0.0005767491,0.0030748446,0.00028183506,0.00023999164,0.00002249712,0.000843593,0.00002810663,0.00006480291],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971188,0.00010964881,0.00066791725,0.00048584802,0.0012394856,0.0003783431],"domain_scores_gemma":[0.9981802,0.00022440444,0.00014885949,0.00068009243,0.00024060946,0.0005258505],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00042352756,0.0002526131,0.000916821,0.00041350833,0.00007190146,0.00003111205,0.00016570487,0.00012216507,0.0036406089],"category_scores_gemma":[0.0004537219,0.00020266125,0.0025944952,0.0009443846,0.00009640928,0.00008678716,0.00011777256,0.0001818391,0.00011471761],"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":[0.0012493407,0.007901772,0.47159067,0.00056757004,0.120362096,0.000556046,0.0010341537,0.0037009774,0.015769614,0.00016246007,0.004081787,0.3730235],"study_design_scores_gemma":[0.003083284,0.00024170824,0.021733183,0.000108825654,0.02767012,0.0000020122277,0.00026763338,0.9432677,0.002759737,0.00023544699,0.0003025572,0.0003277975],"about_ca_topic_score_codex":0.00079865585,"about_ca_topic_score_gemma":0.00001201612,"teacher_disagreement_score":0.93956673,"about_ca_system_score_codex":0.00006914998,"about_ca_system_score_gemma":0.00008316561,"threshold_uncertainty_score":0.9972702},"labels":[],"label_agreement":null},{"id":"W2163397436","doi":"10.1016/j.media.2011.02.002","title":"Recent advances in diffusion MRI modeling: Angular and radial reconstruction","year":2011,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":104,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Diffusion MRI; Diffusion; Artificial intelligence; Bridge (graph theory); Sampling (signal processing); SIGNAL (programming language); Diffusion imaging; Emphasis (telecommunications); Magnetic resonance imaging; Computer vision; Machine learning; Physics","score_opus":0.07453154444029955,"score_gpt":0.39947682010072955,"score_spread":0.32494527566042997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163397436","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017783534,0.9168292,0.08184118,0.0002603411,0.000039586797,0.00041504396,0.00000958126,0.000089789144,0.00049747544],"genre_scores_gemma":[0.000007277109,0.987476,0.011874658,0.00010549313,0.00013080894,0.00012289522,0.00018187163,0.000032427502,0.00006859795],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980034,0.000099837074,0.000713412,0.0006367953,0.00031003347,0.00023648309],"domain_scores_gemma":[0.99889374,0.00006261908,0.00020401366,0.00048316916,0.0000712248,0.00028521256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030575533,0.0002893916,0.0016177479,0.0007043547,0.00005815921,0.000014918632,0.00015154331,0.00027241258,0.00045813542],"category_scores_gemma":[0.00028927688,0.0002207067,0.00040274352,0.0013950107,0.00017750252,0.00012341117,0.00010194598,0.00066137925,0.000008766554],"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":[0.000006041128,0.00007661056,0.00005811694,0.0007253652,0.00010851216,0.000052187155,0.000010730227,8.595562e-7,5.745606e-7,0.00003225277,0.000041750394,0.998887],"study_design_scores_gemma":[0.0002310351,0.000029274112,0.000005991686,0.0023752442,0.0046203844,0.00018333181,0.00000905094,0.015433076,9.365258e-7,0.0004010102,0.9765002,0.00021047352],"about_ca_topic_score_codex":0.000023846478,"about_ca_topic_score_gemma":0.000024122844,"teacher_disagreement_score":0.99867654,"about_ca_system_score_codex":0.00008225021,"about_ca_system_score_gemma":0.00011430618,"threshold_uncertainty_score":0.90001583},"labels":[],"label_agreement":null},{"id":"W2163695678","doi":"10.1016/j.media.2007.04.002","title":"Validation of vessel-based registration for correction of brain shift","year":2007,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"","keywords":"Imaging phantom; Image registration; Iterative closest point; Computer science; Artificial intelligence; Computer vision; Point set registration; Displacement (psychology); Outlier; Deformation (meteorology); Matching (statistics); Point (geometry); Mathematics; Nuclear medicine; Geology; Image (mathematics); Point cloud; Medicine; Geometry; Statistics","score_opus":0.0460120816706241,"score_gpt":0.40532354460114456,"score_spread":0.35931146293052046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163695678","genre_codex":"methods","genre_gemma":"review","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":[6.213336e-7,0.13365261,0.8652651,0.00018090893,0.00017406174,0.0004791346,0.0000153719,0.00008862661,0.0001435666],"genre_scores_gemma":[0.00009950364,0.6697749,0.3269977,0.00041318836,0.00021851338,0.00025851536,0.0018686951,0.000044879613,0.00032412083],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.995792,0.00038567072,0.0016832403,0.0005255163,0.0013964829,0.00021713984],"domain_scores_gemma":[0.99517256,0.0019074571,0.0015661838,0.0007676268,0.00039258093,0.00019359692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035270755,0.00025848183,0.0015871704,0.0012286863,0.000044798813,0.00005254226,0.0009864505,0.00040406332,0.0002229727],"category_scores_gemma":[0.003943198,0.00022029497,0.0010536518,0.00316065,0.00023831714,0.00028949272,0.00007381865,0.00026903595,0.000004638981],"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":[0.0000028549027,0.000113589704,0.0000019821628,0.003385831,0.00034970653,0.000004771956,0.000032902626,0.0000031420261,0.00002005675,0.000080174716,0.0037508723,0.99225414],"study_design_scores_gemma":[0.0021539186,0.0012552427,0.000040037907,0.020605374,0.026163053,0.000018268336,0.000058174875,0.20273994,0.0986974,0.0010885014,0.6449225,0.0022575846],"about_ca_topic_score_codex":0.000070273134,"about_ca_topic_score_gemma":0.000010869538,"teacher_disagreement_score":0.98999655,"about_ca_system_score_codex":0.00008870281,"about_ca_system_score_gemma":0.0005895625,"threshold_uncertainty_score":0.8983368},"labels":[],"label_agreement":null},{"id":"W2164382630","doi":"10.1016/j.media.2015.08.004","title":"Joint segmentation of lumen and outer wall from femoral artery MR images: Towards 3D imaging measurements of peripheral arterial disease","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Peripheral Artery Disease Management","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; University of Toronto; Western University; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Segmentation; Lumen (anatomy); Algorithm; Artificial intelligence; Computer science; Computer vision; Medicine; Surgery","score_opus":0.036423634535153224,"score_gpt":0.2933001013930873,"score_spread":0.2568764668579341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164382630","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":[0.9786767,0.0003161172,0.016342962,0.0033711481,0.0001398681,0.00035170966,0.00009305116,0.000046798617,0.0006616424],"genre_scores_gemma":[0.9912131,0.000019876186,0.006599429,0.0012863392,0.00019608691,0.000032534783,0.00045849607,0.000023414952,0.00017075836],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99656045,0.00018819653,0.0007966682,0.000477811,0.0016778453,0.00029904747],"domain_scores_gemma":[0.99803907,0.00001544287,0.0002458717,0.000467483,0.0003019201,0.0009302187],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00058259733,0.00026087186,0.0008192094,0.0002883291,0.000034714358,0.000054379354,0.00015223125,0.000049393766,0.002016973],"category_scores_gemma":[0.00024789062,0.000217892,0.00032945437,0.00037014828,0.00031553602,0.00032807104,0.00016581718,0.00011992152,0.000012020008],"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":[0.0024789535,0.0023369526,0.80736727,0.0005552611,0.008633926,0.0013308465,0.0044780127,0.00005661477,0.085237674,0.0000020592088,0.009744212,0.07777821],"study_design_scores_gemma":[0.012102749,0.00029453967,0.89495176,0.0003496692,0.01623028,0.000010270309,0.0018494707,0.066924706,0.0062503507,0.0001785318,0.0002350503,0.0006225938],"about_ca_topic_score_codex":0.000897535,"about_ca_topic_score_gemma":0.000038218855,"teacher_disagreement_score":0.08758451,"about_ca_system_score_codex":0.00014993714,"about_ca_system_score_gemma":0.00018924523,"threshold_uncertainty_score":0.99889535},"labels":[],"label_agreement":null},{"id":"W2167908150","doi":"10.1016/j.media.2012.07.002","title":"Symmetric positive semi-definite Cartesian Tensor fiber orientation distributions (CT-FOD)","year":2012,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute on Aging; National Center for Research Resources; McGill University; Johns Hopkins University","keywords":"Tensor (intrinsic definition); Diffusion MRI; Cartesian coordinate system; Mathematics; Tensor field; Cartesian tensor; Mathematical analysis; Orientation (vector space); Convolution (computer science); Artificial intelligence; Geometry; Computer science; Tensor density; Magnetic resonance imaging; Exact solutions in general relativity; Artificial neural network","score_opus":0.029280580250433053,"score_gpt":0.35686157417974923,"score_spread":0.32758099392931617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167908150","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":[0.1338401,0.00056519336,0.830072,0.015348608,0.00007598068,0.00066745444,0.00036392265,0.0006233675,0.018443372],"genre_scores_gemma":[0.9809087,0.0001013192,0.014946348,0.0012222606,0.00020643331,0.000095554584,0.0011859189,0.000022886348,0.001310598],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983249,0.000060622482,0.00034162952,0.0003192238,0.0005614759,0.00039215304],"domain_scores_gemma":[0.9984876,0.00020334424,0.00010697875,0.00045862328,0.0001959537,0.00054749486],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002641244,0.00016430348,0.0003687653,0.0004125216,0.00017234529,0.00002302371,0.00011546112,0.00005937154,0.0012638844],"category_scores_gemma":[0.00080402545,0.00013816936,0.00030483934,0.0033293688,0.00017655533,0.00015455103,0.000061700484,0.00032396385,0.00023929635],"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":[0.0001370743,0.0054302798,0.68282247,0.00017505563,0.0049286145,0.00090052345,0.00075443106,0.0000189788,0.009289758,0.022366172,0.043055046,0.23012161],"study_design_scores_gemma":[0.0021975003,0.00025547566,0.83659744,0.00014908281,0.018954353,0.0006406564,0.00036123107,0.012162097,0.019325541,0.0012153214,0.10705783,0.0010834573],"about_ca_topic_score_codex":0.00009037536,"about_ca_topic_score_gemma":0.0000042849542,"teacher_disagreement_score":0.8470686,"about_ca_system_score_codex":0.00010347465,"about_ca_system_score_gemma":0.000045321023,"threshold_uncertainty_score":0.9996491},"labels":[],"label_agreement":null},{"id":"W2168389179","doi":"10.1016/j.media.2009.10.003","title":"A filtered approach to neural tractography using the Watson directional function","year":2009,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Center for Research Resources; National Institute of Mental Health; Fogarty International Center; National Institutes of Health","keywords":"Tractography; Computer science; Diffusion MRI; Noise (video); Fiber; Artificial intelligence; Kalman filter; SIGNAL (programming language); Noise reduction; Algorithm; Mathematics; Computer vision","score_opus":0.072124928754897,"score_gpt":0.37745874984233835,"score_spread":0.30533382108744134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168389179","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":[0.06577556,0.000053371397,0.920331,0.011491376,0.00002122606,0.0002476178,0.000004751482,0.0001920843,0.00188299],"genre_scores_gemma":[0.94949347,0.000014838574,0.043168426,0.0068732705,0.00020140251,0.000034386616,0.000060931045,0.000010489634,0.00014281749],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870527,0.000042079773,0.00022872619,0.0003189453,0.0005068207,0.0001981337],"domain_scores_gemma":[0.99921453,0.000045539164,0.000052777912,0.00037553758,0.00008491724,0.00022667817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020235419,0.00012002363,0.00024573551,0.00027523987,0.00016802941,0.000030472305,0.00013151397,0.000052547657,0.00017096342],"category_scores_gemma":[0.00013227647,0.00007751039,0.0003258815,0.00208674,0.00008015209,0.00007489305,0.000023644221,0.00029085597,0.0000044921944],"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":[0.001044438,0.006996253,0.03562695,0.00008606718,0.0037693311,0.00020686976,0.0009527945,0.003462776,0.2996705,0.0025128392,0.047341645,0.59832954],"study_design_scores_gemma":[0.001251548,0.0005369382,0.32480177,0.000053706168,0.008565912,0.00034671818,0.00023764896,0.6248523,0.004758628,0.0017166787,0.03225326,0.0006248566],"about_ca_topic_score_codex":0.00003586964,"about_ca_topic_score_gemma":0.0000020686828,"teacher_disagreement_score":0.8837179,"about_ca_system_score_codex":0.000025655356,"about_ca_system_score_gemma":0.000021091202,"threshold_uncertainty_score":0.3160782},"labels":[],"label_agreement":null},{"id":"W2170179519","doi":"10.1016/j.media.2011.03.003","title":"Unsupervised dealiasing and denoising of color-Doppler data","year":2011,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiovascular Function and Risk Factors","field":"Medicine","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; Université de Montréal","funders":"Canadian Institutes of Health Research; Jewish General Hospital","keywords":"Computer science; Artificial intelligence; Computer vision; Doppler effect; Segmentation; Smoothing; Noise (video); Scanner; Algorithm; Pattern recognition (psychology); Image (mathematics)","score_opus":0.07115705155525058,"score_gpt":0.30896473304708905,"score_spread":0.23780768149183845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170179519","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":[0.956041,0.0006995325,0.040957633,0.0003384501,0.00006492443,0.00010493179,0.00001765207,0.000044672088,0.0017312436],"genre_scores_gemma":[0.9954673,0.00039784517,0.00341436,0.00033588166,0.0000692182,0.0000012315858,0.00015626042,0.000012235734,0.00014567134],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985623,0.000080045575,0.00030428488,0.00030030633,0.0005999826,0.00015312045],"domain_scores_gemma":[0.9987745,0.000058293346,0.000057184996,0.00069758395,0.00010804128,0.00030434722],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00073258113,0.00010170703,0.0005327018,0.0002635718,0.000047389636,0.0000103334405,0.00013796947,0.00009684628,0.0029706736],"category_scores_gemma":[0.0006277842,0.000074407326,0.00026509,0.0007308226,0.00023622248,0.00009949035,0.00015441087,0.00015233787,0.000014069416],"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":[0.00023411121,0.00038042042,0.92763674,0.000170293,0.012989694,0.0006134844,0.0013038911,0.0000015129144,0.0044736234,0.00003537142,0.0033458543,0.04881498],"study_design_scores_gemma":[0.0028647243,0.00012886903,0.9405983,0.000117706826,0.025168128,0.00026068615,0.0013404331,0.01706755,0.005832192,0.000023080387,0.0062995157,0.0002988336],"about_ca_topic_score_codex":0.0011095806,"about_ca_topic_score_gemma":0.00013682724,"teacher_disagreement_score":0.048516147,"about_ca_system_score_codex":0.000016182374,"about_ca_system_score_gemma":0.000081445054,"threshold_uncertainty_score":0.9979407},"labels":[],"label_agreement":null},{"id":"W2171349848","doi":"10.1016/j.media.2004.03.001","title":"Adaptive registration using local information measures","year":2004,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Cancer Institute; National Institutes of Health","keywords":"Computer science; Mutual information; Artificial intelligence; Entropy (arrow of time); Grid; Computer vision; Degrees of freedom (physics and chemistry); Operator (biology); Mathematics","score_opus":0.019746192222127413,"score_gpt":0.29483334089881746,"score_spread":0.27508714867669004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171349848","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":[0.00034505076,0.000027242872,0.9969818,0.0013763937,0.000051545005,0.000101140344,0.0000019630058,0.00026564588,0.00084923854],"genre_scores_gemma":[0.42158645,0.000024473795,0.57595885,0.0022997165,0.00005396219,0.0000143214,0.000038341273,0.000004814853,0.000019065217],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972416,0.00010911939,0.00051222084,0.00024777104,0.0016582051,0.00023108916],"domain_scores_gemma":[0.9987469,0.000051145817,0.000196612,0.0004223136,0.0002796746,0.0003034005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009281972,0.00013197775,0.00023903183,0.0004303162,0.000117527605,0.00020836444,0.0006344136,0.00011630683,0.00020250506],"category_scores_gemma":[0.0006849759,0.000114885726,0.00016647877,0.0018540192,0.00024583787,0.0024673755,0.00012507445,0.00021665977,0.00007649319],"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":[0.000015049743,0.00019698149,0.0001319177,0.000023080062,0.0006928174,0.00016896611,0.0015193358,0.0025654198,0.0022927895,0.0075040204,0.0014733718,0.98341626],"study_design_scores_gemma":[0.0012032962,0.00016183002,0.00078575267,0.00007789954,0.0006330034,0.000049552073,0.0005011419,0.9117711,0.07641132,0.0073669013,0.00049240974,0.00054578984],"about_ca_topic_score_codex":0.00066877436,"about_ca_topic_score_gemma":0.00007591531,"teacher_disagreement_score":0.98287046,"about_ca_system_score_codex":0.00018580003,"about_ca_system_score_gemma":0.00028541646,"threshold_uncertainty_score":0.4684904},"labels":[],"label_agreement":null},{"id":"W2175900216","doi":"10.1016/j.media.2015.10.012","title":"Sparse Reconstruction Challenge for diffusion MRI: Validation on a physical phantom to determine which acquisition scheme and analysis method to use?","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":90,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"National Cancer Institute; National Institute of Biomedical Imaging and Bioengineering; National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; National Institutes of Health","keywords":"Computer science; Imaging phantom; Diffusion MRI; Artificial intelligence; Set (abstract data type); Data set; Iterative reconstruction; Neuroimaging; Pattern recognition (psychology); Protocol (science); Data mining; Machine learning; Medical physics; Magnetic resonance imaging; Nuclear medicine; Medicine; Radiology","score_opus":0.10680281640726129,"score_gpt":0.42206878803914777,"score_spread":0.31526597163188647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2175900216","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":[0.32221928,0.0000058984438,0.6687893,0.008342382,0.000013030387,0.00043644675,0.000026593356,0.00010167896,0.00006535399],"genre_scores_gemma":[0.5740762,0.000036461486,0.42376256,0.0012295034,0.00019756224,0.0002689073,0.0002777956,0.000024144523,0.00012688222],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802685,0.00009539791,0.0003529748,0.0006851916,0.00059199135,0.00024757354],"domain_scores_gemma":[0.9979675,0.00024909782,0.00011148639,0.00049344316,0.00045082867,0.00072766125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005739021,0.00020097129,0.00063943316,0.00089367287,0.0000997185,0.00005327125,0.00010461234,0.00009602678,0.00006131171],"category_scores_gemma":[0.0009047346,0.00017183764,0.00026084477,0.0029391781,0.0000444214,0.00017776803,0.00008710661,0.00016706705,0.000014435551],"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":[0.0022513485,0.0036013944,0.041209817,0.00018742308,0.0060344506,0.00010182049,0.0020263202,0.0009840211,0.17088953,0.0013775728,0.0043611387,0.76697516],"study_design_scores_gemma":[0.0022821387,0.0014218893,0.020517835,0.00014115647,0.015103999,0.000049082242,0.00018128182,0.91915005,0.03371868,0.0016021922,0.005229607,0.00060210726],"about_ca_topic_score_codex":0.000057659476,"about_ca_topic_score_gemma":0.000034293582,"teacher_disagreement_score":0.918166,"about_ca_system_score_codex":0.00009225272,"about_ca_system_score_gemma":0.000037510832,"threshold_uncertainty_score":0.70073354},"labels":[],"label_agreement":null},{"id":"W2191021609","doi":"10.1016/j.media.2015.08.006","title":"Probabilistic non-linear registration with spatially adaptive regularisation","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":44,"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; University of California, San Diego; Genentech; National Institutes of Health; IXICO; Servier; Eisai; National Institute on Aging; National Institute for Health and Care Research; Seventh Framework Programme; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; University College London Hospitals NHS Foundation Trust; Alzheimer's Disease Neuroimaging Initiative; Eli Lilly and Company; U.S. Department of Defense; Medical Research Council; Meso Scale Diagnostics; Synarc; University of Southern California; University College London; Medpace; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; F. Hoffmann-La Roche; Alzheimer's Drug Discovery Foundation; Foundation for the National Institutes of Health","keywords":"Computer science; Transformation (genetics); Constraint (computer-aided design); Probabilistic logic; Bayesian probability; Inference; Artificial intelligence; Bayesian inference; Image registration; Pattern recognition (psychology); Mathematics; Image (mathematics)","score_opus":0.023972822733220846,"score_gpt":0.2925563478936194,"score_spread":0.2685835251603986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2191021609","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":[0.0013778708,0.000013210213,0.9936564,0.0024715587,0.000042660788,0.00024081137,0.0000014357421,0.00026078633,0.001935254],"genre_scores_gemma":[0.25425088,0.0000072116163,0.7439831,0.0009845784,0.00013188682,0.00007124676,0.00008036369,0.000012694413,0.0004780777],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965528,0.00021260507,0.00046078063,0.0005227537,0.0020059857,0.0002450528],"domain_scores_gemma":[0.997808,0.000113287526,0.00023873757,0.0006876135,0.0005992317,0.00055314676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015098181,0.00016952418,0.0003251969,0.00028734896,0.000070728725,0.0001415626,0.0007101093,0.00011626275,0.00016584614],"category_scores_gemma":[0.0014713663,0.00012827136,0.00010161723,0.0018982996,0.0002809632,0.00079436356,0.00012554844,0.00023264985,0.00006058517],"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":[0.0006196807,0.0035157942,0.0078409,0.00026678614,0.006193644,0.0039212722,0.014614471,0.0060161063,0.0052034906,0.020205496,0.08051499,0.8510874],"study_design_scores_gemma":[0.0007243522,0.00039634554,0.0011007743,0.000036260117,0.00041636772,0.000016705539,0.00010093771,0.9886816,0.006202537,0.0019291822,0.0001238247,0.00027106877],"about_ca_topic_score_codex":0.00039205333,"about_ca_topic_score_gemma":0.0002660361,"teacher_disagreement_score":0.98266554,"about_ca_system_score_codex":0.00012090328,"about_ca_system_score_gemma":0.00050483935,"threshold_uncertainty_score":0.52307546},"labels":[],"label_agreement":null},{"id":"W2222869326","doi":"10.1016/j.media.2015.10.011","title":"Strengths and weaknesses of state of the art fiber tractography pipelines – A comprehensive in-vivo and phantom evaluation study using Tractometer","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":74,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"National Institute of Mental Health; Deutsche Forschungsgemeinschaft","keywords":"Tractography; Metric (unit); Imaging phantom; Computer science; Consistency (knowledge bases); Artificial intelligence; Machine learning; Data mining; Diffusion MRI; Magnetic resonance imaging; Engineering; Medicine; Nuclear medicine; Radiology","score_opus":0.0852731398949972,"score_gpt":0.4298637285706721,"score_spread":0.34459058867567494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2222869326","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":[0.9958,0.00024612053,0.0031301845,0.00036929862,0.000006920985,0.00036905025,0.0000116921165,0.000010681387,0.000056026965],"genre_scores_gemma":[0.99674183,0.00010908898,0.003021753,0.0000656675,0.000010478733,0.000015491167,0.000004586363,0.000007024459,0.000024052708],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99869126,0.000107450316,0.00035078096,0.00019570936,0.00056660676,0.00008820912],"domain_scores_gemma":[0.9989288,0.00024601028,0.0001587675,0.00023785607,0.00033152965,0.000097026954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003916479,0.000092179085,0.00037340462,0.0002940606,0.000020060077,0.00000705835,0.00006225934,0.000026450456,0.000054617736],"category_scores_gemma":[0.0005491016,0.00006056178,0.00007951073,0.0011238385,0.00023959797,0.00007687042,0.000051462695,0.00012124522,1.4276472e-7],"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":[0.00029339312,0.00375003,0.75980914,0.00024871997,0.0016268961,0.00005430455,0.0038067074,0.00029168584,0.08371328,0.0000064543,0.0006714133,0.14572796],"study_design_scores_gemma":[0.007877582,0.0006452349,0.7544301,0.0004009869,0.013929143,0.00008478909,0.0038481625,0.17936678,0.03537626,0.0013784738,0.0022049085,0.00045756943],"about_ca_topic_score_codex":0.00011152607,"about_ca_topic_score_gemma":0.00006243259,"teacher_disagreement_score":0.17907509,"about_ca_system_score_codex":0.000009499494,"about_ca_system_score_gemma":0.0000523053,"threshold_uncertainty_score":0.24696375},"labels":[],"label_agreement":null},{"id":"W2254473384","doi":"10.1016/j.media.2016.01.004","title":"Evaluation of state-of-the-art segmentation algorithms for left ventricle infarct from late Gadolinium enhancement MR images","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":116,"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":"Engineering and Physical Sciences Research Council; King's College London; Ministerio de Economía y Competitividad; National Institute for Health and Care Research; Wellcome Trust","keywords":"Thresholding; Benchmarking; Segmentation; Ground truth; Computer science; Artificial intelligence; Magnetic resonance imaging; Ventricle; Benchmark (surveying); Steady-state free precession imaging; Algorithm; Medicine; Pattern recognition (psychology); Radiology; Image (mathematics); Cardiology","score_opus":0.02727050351282946,"score_gpt":0.38037277047506146,"score_spread":0.353102266962232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2254473384","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":[0.1258796,0.00011465389,0.87043905,0.0027489774,0.000029367717,0.0005721412,0.000103098864,0.000018216775,0.000094867195],"genre_scores_gemma":[0.9098942,0.0004242587,0.08804975,0.0002600222,0.000077890196,0.00022773954,0.00018625963,0.000017298975,0.0008625413],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980414,0.000073584895,0.00047804444,0.0002169481,0.0010519248,0.00013808563],"domain_scores_gemma":[0.99847203,0.00017399025,0.00027557998,0.00035041876,0.000637378,0.000090627225],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009525549,0.00009170217,0.00030512805,0.00011187339,0.000039787545,0.000004102725,0.00011973355,0.000045127857,0.0011111709],"category_scores_gemma":[0.00051716174,0.000054596316,0.0002469469,0.0003953423,0.00014374309,0.00008301264,0.000045539196,0.000056891535,0.000008618571],"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":[0.000066876986,0.00041611472,0.004332123,0.000030104813,0.00072470226,0.000001108667,0.00014730774,0.000071010254,0.41433924,0.000010626986,0.0024158023,0.577445],"study_design_scores_gemma":[0.0017749213,0.00011276134,0.012051291,0.00010662029,0.0043570977,5.158168e-7,0.000032072352,0.028049484,0.9496094,0.0027216463,0.0010927868,0.000091411835],"about_ca_topic_score_codex":0.00006204945,"about_ca_topic_score_gemma":0.000018714662,"teacher_disagreement_score":0.78401464,"about_ca_system_score_codex":0.00008743926,"about_ca_system_score_gemma":0.00011932645,"threshold_uncertainty_score":0.99980193},"labels":[],"label_agreement":null},{"id":"W2255928173","doi":"10.1016/j.media.2016.01.006","title":"Geometrical deployment for braided stent","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Intracranial Aneurysms: Treatment and Complications","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Western Hospital; University Health Network","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Software deployment; Stent; Computer science; Position (finance); RADIUS; Biomedical engineering; Simulation; Radiology; Engineering; Medicine; Software engineering","score_opus":0.020466744944273637,"score_gpt":0.3041720158400374,"score_spread":0.28370527089576375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2255928173","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":[0.28212327,0.00022832847,0.6183031,0.09578878,0.000094968884,0.00073129695,0.000049601866,0.00021146119,0.0024691897],"genre_scores_gemma":[0.9865922,0.00008907799,0.0041214144,0.001909657,0.00027665382,0.0002005163,0.00007741182,0.000018064795,0.0067150183],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984275,0.000028545628,0.00032865282,0.00032338873,0.00060386845,0.000288059],"domain_scores_gemma":[0.9986545,0.00034734074,0.000056297158,0.0003478053,0.00019007314,0.00040398544],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022163121,0.00012992145,0.00040156074,0.00037734513,0.000086878325,0.000016316835,0.00013034827,0.000084484156,0.0035792098],"category_scores_gemma":[0.00079611194,0.00007049056,0.000529314,0.0010688106,0.00010543375,0.00005376736,0.00003746203,0.00006797367,0.00024824153],"study_design_candidate":"observational","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":[0.0008118792,0.005019573,0.115530394,0.0001078434,0.013381946,0.00075638486,0.00014210083,0.0000013308124,0.029670585,0.004594154,0.044802338,0.78518146],"study_design_scores_gemma":[0.032222856,0.0042165285,0.67831415,0.00031522062,0.062217303,0.00046578803,0.00021950324,0.019646468,0.031863615,0.004854624,0.1638895,0.0017744727],"about_ca_topic_score_codex":0.000036056048,"about_ca_topic_score_gemma":0.000021789981,"teacher_disagreement_score":0.783407,"about_ca_system_score_codex":0.00008411726,"about_ca_system_score_gemma":0.00006887909,"threshold_uncertainty_score":0.9973317},"labels":[],"label_agreement":null},{"id":"W2284206694","doi":"10.1016/j.media.2016.01.002","title":"The application of a new sampling theorem for non-bandlimited signals on the sphere: Improving the recovery of crossing fibers for low b-value acquisitions","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"National Institute of Mental Health; NIH Blueprint for Neuroscience Research; McDonnell Center for Systems Neuroscience; Washington University in St. Louis","keywords":"Deconvolution; Bandlimiting; Sampling (signal processing); Mathematics; Algorithm; Convolution (computer science); Kernel (algebra); Nonuniform sampling; Computer science; Mathematical analysis; Fourier transform; Artificial intelligence; Computer vision; Discrete mathematics; Artificial neural network","score_opus":0.038154558591240596,"score_gpt":0.36350859537872743,"score_spread":0.3253540367874868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2284206694","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":[0.021766348,0.00006004883,0.95439214,0.022583995,0.00001312686,0.0010271528,0.00005617983,0.000033908786,0.000067132605],"genre_scores_gemma":[0.9607711,0.000094788025,0.036149792,0.0017744424,0.00020661889,0.00058464386,0.000035384095,0.000032696487,0.00035053006],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986862,0.00004293729,0.00046363278,0.00026480693,0.0003314679,0.0002109356],"domain_scores_gemma":[0.9940516,0.004551613,0.000353474,0.0007207791,0.00023624486,0.000086293534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010212504,0.00012274593,0.00030082752,0.00006559465,0.00046296025,0.000036989695,0.0003232405,0.000062381056,0.000043274067],"category_scores_gemma":[0.0020370898,0.00005012915,0.0004577596,0.00061103073,0.0005308779,0.00005090407,0.000044062523,0.00011522839,0.0000011596705],"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":[0.0005332922,0.00022978331,0.0002953919,0.000118884745,0.0009126409,6.126217e-7,0.0002485304,0.00023871369,0.42256376,0.009077343,0.0042364555,0.5615446],"study_design_scores_gemma":[0.004012251,0.0009207069,0.0034519676,0.0011335433,0.007882067,0.000012215367,0.00090933417,0.30472824,0.5510997,0.10664139,0.018647103,0.000561436],"about_ca_topic_score_codex":0.000054870976,"about_ca_topic_score_gemma":0.000011492864,"teacher_disagreement_score":0.9390048,"about_ca_system_score_codex":0.000037529993,"about_ca_system_score_gemma":0.00016243187,"threshold_uncertainty_score":0.35607627},"labels":[],"label_agreement":null},{"id":"W2297040190","doi":"10.1016/j.media.2016.03.004","title":"X-ray and magnetic resonance imaging fusion for cardiac resynchronization therapy","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiac pacing and defibrillation studies","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"Sunnybrook Research Institute","keywords":"Cardiac resynchronization therapy; Coronary sinus; Fluoroscopy; Medicine; Ventricle; Magnetic resonance imaging; Heart failure; Cardiology; Cardiac magnetic resonance; Coronary Vein; Internal medicine; Radiology; Ejection fraction","score_opus":0.009565483470173436,"score_gpt":0.28736634963190233,"score_spread":0.2778008661617289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2297040190","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":[0.48716936,0.14481902,0.32836172,0.023245564,0.00040429525,0.0010174443,0.00011132588,0.00034589696,0.014525383],"genre_scores_gemma":[0.98696625,0.008619682,0.0016485888,0.0005738521,0.00037702272,0.000030100458,0.000025816202,0.000018029363,0.0017406276],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987878,0.00005723852,0.00023491516,0.0002991492,0.00043507697,0.00018577857],"domain_scores_gemma":[0.99903625,0.0003192177,0.000047602578,0.00022822352,0.00021232148,0.0001563665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046569225,0.00011086487,0.0004935105,0.00019229695,0.00011580627,0.000020922342,0.000016752963,0.000050992472,0.00013009366],"category_scores_gemma":[0.00091220683,0.00006685155,0.0002618556,0.00048771902,0.00017335077,0.00006704527,0.000034302815,0.000042710533,0.000011483324],"study_design_candidate":"observational","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":[0.00013830315,0.000025429434,0.23363456,0.000020772972,0.0003591992,0.000011898564,0.00018646437,6.180274e-7,0.008007794,0.000029202909,0.010674219,0.7469115],"study_design_scores_gemma":[0.0041517834,0.00019004945,0.6354519,0.00020974728,0.0023443191,0.00002599422,0.00018819088,0.0032409898,0.0012884483,0.00012440092,0.35246313,0.00032102523],"about_ca_topic_score_codex":0.000030369407,"about_ca_topic_score_gemma":0.0000037204059,"teacher_disagreement_score":0.7465905,"about_ca_system_score_codex":0.000032464355,"about_ca_system_score_gemma":0.000041287207,"threshold_uncertainty_score":0.2726127},"labels":[],"label_agreement":null},{"id":"W2298552625","doi":"10.1016/j.media.2016.02.010","title":"Non Local Spatial and Angular Matching: Enabling higher spatial resolution diffusion MRI datasets through adaptive denoising","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":82,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Noise reduction; Noise (video); Computer science; Artificial intelligence; Rician fading; Spatial analysis; Pattern recognition (psychology); Gaussian noise; Noise measurement; Algorithm; Computer vision; Mathematics; Statistics","score_opus":0.029768578420550303,"score_gpt":0.3345688220668706,"score_spread":0.3048002436463203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2298552625","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":[0.038562447,0.00013262266,0.95467556,0.0060771387,0.000028625725,0.00019683459,0.00005942595,0.00013053838,0.0001368304],"genre_scores_gemma":[0.9720399,0.00038779085,0.025942193,0.0008719285,0.00029672164,0.000023708066,0.00027082863,0.000028032295,0.00013890705],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980815,0.000057520574,0.0003580455,0.0005737226,0.00062494143,0.00030427836],"domain_scores_gemma":[0.99890804,0.000119856064,0.00012543709,0.0005064473,0.00007862969,0.00026157216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025733918,0.0001953707,0.00041825426,0.00017325404,0.00018672376,0.000026163745,0.00013669662,0.00012853161,0.00046118448],"category_scores_gemma":[0.00012588366,0.00013112245,0.00014213246,0.00046707946,0.00036243632,0.00022112092,0.00022089624,0.00025324296,0.000017882097],"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":[0.0011075214,0.0014574942,0.019036882,0.00017875477,0.0016895212,0.0020315053,0.00072569144,0.000055093835,0.3113664,0.0013573173,0.01217444,0.6488194],"study_design_scores_gemma":[0.019413082,0.0021334342,0.23089385,0.0035557442,0.023501985,0.0006370422,0.00080993935,0.38984546,0.15379141,0.028349353,0.1432526,0.003816118],"about_ca_topic_score_codex":0.0016874439,"about_ca_topic_score_gemma":0.00013761983,"teacher_disagreement_score":0.93347746,"about_ca_system_score_codex":0.00008372081,"about_ca_system_score_gemma":0.00004252993,"threshold_uncertainty_score":0.5347018},"labels":[],"label_agreement":null},{"id":"W2423172756","doi":"10.1016/j.media.2016.06.004","title":"Image-guided interventions and computer-integrated therapy: Quo vadis?","year":2016,"lang":"en","type":"editorial","venue":"Medical Image Analysis","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Canada Foundation for Innovation; Harvard University; Heart and Stroke Foundation of Canada; Natural Sciences and Engineering Research Council of Canada; Mayo Clinic","keywords":"Status quo; Psychological intervention; Implementation; Computer science; Visualization; Data science; Medicine; Artificial intelligence; Political science","score_opus":0.02901492476713416,"score_gpt":0.3715704268395559,"score_spread":0.3425555020724217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2423172756","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047577275,0.004413183,0.35646728,0.009237243,0.60644835,0.0013898106,0.0008085542,0.0012146388,0.015263173],"genre_scores_gemma":[0.013803019,0.003947059,0.0066469004,0.0013993898,0.957103,0.000085230145,0.007097974,0.00018475205,0.009732683],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99586254,0.00028692698,0.0009974347,0.0007543014,0.0016839708,0.0004148114],"domain_scores_gemma":[0.99606466,0.0016067002,0.00029147285,0.00051614724,0.0007165466,0.0008044861],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001103149,0.00043503448,0.0015225979,0.00072099746,0.00012676376,0.00014452593,0.000252751,0.00085241394,0.016628629],"category_scores_gemma":[0.0030949833,0.00027551173,0.0014322547,0.0010827625,0.00047048114,0.00012331808,0.00012822918,0.00105859,0.00016580541],"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":[0.00013494905,0.00032333145,0.00049791543,0.00015557617,0.0065632546,0.0006318381,0.00007596863,3.6297072e-7,0.00001779961,0.000012122988,0.89040595,0.10118095],"study_design_scores_gemma":[0.007494328,0.0002210338,0.0010170998,0.0010238361,0.005135321,0.000011341988,0.00003537395,0.015886076,0.000013736007,0.000049985716,0.9686839,0.00042796374],"about_ca_topic_score_codex":0.00021318984,"about_ca_topic_score_gemma":0.00006827621,"teacher_disagreement_score":0.3506546,"about_ca_system_score_codex":0.00009812568,"about_ca_system_score_gemma":0.00029545385,"threshold_uncertainty_score":0.9999697},"labels":[],"label_agreement":null},{"id":"W2429271550","doi":"10.1016/j.media.2016.06.011","title":"Open-source platforms for navigated image-guided interventions","year":2016,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":176,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Key (lock); Field (mathematics); Navigation system; Software; Data science; Software engineering; Human–computer interaction; Artificial intelligence; Computer security","score_opus":0.14718353703732354,"score_gpt":0.48497841305535794,"score_spread":0.3377948760180344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2429271550","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007334378,0.8491046,0.14056447,0.0006365616,0.00014642163,0.0016537342,0.0001544672,0.0002115734,0.0075208633],"genre_scores_gemma":[0.000059305392,0.9800517,0.0026526575,0.0005254524,0.00043334157,0.00039495854,0.003376361,0.00011033455,0.012395896],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959844,0.00011412109,0.0017650775,0.00077366305,0.00085052726,0.0005122179],"domain_scores_gemma":[0.99631906,0.001172108,0.0005653462,0.00071689533,0.00035246354,0.0008741241],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016879827,0.000483927,0.0037115088,0.00068112387,0.00016965916,0.00017670398,0.00077866577,0.0005484237,0.027360987],"category_scores_gemma":[0.0037560484,0.000278129,0.0050079143,0.0019594263,0.0002634698,0.00021504954,0.00040436274,0.00057805283,0.00072369265],"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":[0.000025070327,0.000203889,0.00000993634,0.0053475145,0.0064057177,0.00013658337,0.000016052321,1.833712e-7,2.3826517e-7,0.00006665822,0.0026001823,0.98518795],"study_design_scores_gemma":[0.0030294242,0.000071270624,0.000007393644,0.024007041,0.022985134,0.00004812556,0.00001944396,0.0010400085,0.0000010918722,0.00007267267,0.94838315,0.0003352146],"about_ca_topic_score_codex":0.000048682643,"about_ca_topic_score_gemma":0.000017645956,"teacher_disagreement_score":0.98485273,"about_ca_system_score_codex":0.00015074047,"about_ca_system_score_gemma":0.00035489292,"threshold_uncertainty_score":0.9999671},"labels":[],"label_agreement":null},{"id":"W2461431685","doi":"10.1016/j.media.2016.06.035","title":"Increasing the impact of medical image computing using community-based open-access hackathons: The NA-MIC and 3D Slicer experience","year":2016,"lang":"en","type":"editorial","venue":"Medical Image Analysis","topic":"Biomedical and Engineering Education","field":"Engineering","cited_by":100,"is_retracted":false,"has_abstract":false,"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; National Institute on Aging; National Cancer Institute; National Institutes of Health; University of Toronto; National Heart, Lung, and Blood Institute; Cancer Care Ontario","keywords":"Variety (cybernetics); Computer science; Software; Portfolio; Data science; Open source software; World Wide Web; Engineering management; Engineering; Artificial intelligence; Business","score_opus":0.02545183757932712,"score_gpt":0.3936397144089996,"score_spread":0.36818787682967247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2461431685","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":[0.32814032,0.002385381,0.48745748,0.0031110188,0.17665608,0.00087610213,0.0003753093,0.000502061,0.00049624307],"genre_scores_gemma":[0.80475956,0.001087188,0.0038056634,0.00036621856,0.18890268,0.00008506644,0.0007262753,0.00023195578,0.00003540444],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99518853,0.0006886758,0.0008835445,0.0003754275,0.0023109026,0.00055291405],"domain_scores_gemma":[0.99297374,0.004979217,0.00025528067,0.0010370637,0.00024428155,0.00051041675],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0054172273,0.00048564002,0.0010019463,0.00036129367,0.0004656287,0.0006674984,0.004052081,0.00083739473,0.00087767123],"category_scores_gemma":[0.005865968,0.0002515535,0.00038308944,0.001604673,0.0013121744,0.00041789157,0.0013630312,0.0024587468,0.000005890642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013746691,0.0007325188,0.0017606829,0.0031483427,0.0090473,0.00015425698,0.008161176,0.0036182164,0.005319575,0.0000104625415,0.9082135,0.059696496],"study_design_scores_gemma":[0.00095122063,0.00004856558,0.0013340157,0.0017847624,0.0016495109,0.000025032314,0.0004055946,0.97395873,0.00017450663,0.000030497662,0.018913887,0.0007236768],"about_ca_topic_score_codex":0.015158032,"about_ca_topic_score_gemma":0.00016190115,"teacher_disagreement_score":0.9703405,"about_ca_system_score_codex":0.0002378649,"about_ca_system_score_gemma":0.00067131565,"threshold_uncertainty_score":0.9999937},"labels":[],"label_agreement":null},{"id":"W2466670129","doi":"10.1016/j.media.2016.06.038","title":"Automatic segmentation approach to extracting neonatal cerebral ventricles from 3D ultrasound images","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Fetal and Pediatric Neurological Disorders","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Western University","funders":"Canadian Institutes of Health Research; Academic Medical Organization of Southwestern Ontario","keywords":"Initialization; Segmentation; Artificial intelligence; 3D ultrasound; Computer science; Cerebral ventricle; Medicine; Pattern recognition (psychology); Ultrasound; Computer vision; Radiology; Anatomy","score_opus":0.010865785127341222,"score_gpt":0.26689803274165386,"score_spread":0.25603224761431265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2466670129","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":[0.8746283,0.00023605462,0.119154565,0.003703299,0.000066100474,0.00023358225,0.000062444684,0.00015420884,0.0017614599],"genre_scores_gemma":[0.9807412,0.00007193843,0.016424404,0.0018850436,0.00029154497,0.00003090742,0.00016955874,0.000017023658,0.0003683558],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9976925,0.00012437774,0.00042855978,0.00049276755,0.000912169,0.00034962248],"domain_scores_gemma":[0.99825084,0.000793645,0.00010421888,0.00027226843,0.00006306393,0.0005159872],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002963301,0.00019198177,0.00047253518,0.00026123086,0.00008553811,0.00004260962,0.0001775423,0.000118950826,0.008983673],"category_scores_gemma":[0.00220268,0.00011261055,0.00030727318,0.0010595281,0.00013059741,0.00018622095,0.000069435686,0.0001966962,0.00033398042],"study_design_candidate":"observational","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":[0.00024115009,0.0012199746,0.23973137,0.000111507055,0.0023000224,0.00060322945,0.00061202026,0.000014736888,0.049162548,0.00001430629,0.008338627,0.6976505],"study_design_scores_gemma":[0.006322916,0.0006006561,0.95309,0.00011022273,0.010581363,0.00015175527,0.0011708303,0.012671865,0.01197416,0.0006654431,0.0016414566,0.0010193255],"about_ca_topic_score_codex":0.00021191426,"about_ca_topic_score_gemma":0.000010215075,"teacher_disagreement_score":0.71335864,"about_ca_system_score_codex":0.000041605002,"about_ca_system_score_gemma":0.000045295947,"threshold_uncertainty_score":0.99192226},"labels":[],"label_agreement":null},{"id":"W2479734208","doi":"10.1016/j.media.2016.07.012","title":"Learning in data-limited multimodal scenarios: Scandent decision forests and tree-based features","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute on Aging; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Decision tree; Computer science; Artificial intelligence; Classifier (UML); Feature (linguistics); Machine learning; Decision tree learning; Random forest; Pattern recognition (psychology); Tree (set theory); Incremental decision tree; Data mining; Mathematics","score_opus":0.018317545149545804,"score_gpt":0.30574153267386384,"score_spread":0.287423987524318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2479734208","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":[0.19457772,0.00015725863,0.7999866,0.004979629,0.000049378697,0.0000835729,0.0000028590653,0.00008889999,0.00007410094],"genre_scores_gemma":[0.977597,0.00008997161,0.021693159,0.00037155245,0.000045238656,0.000009540263,0.000018525774,0.000009393843,0.00016561437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705344,0.0002410239,0.0004378155,0.00082761835,0.000994705,0.00044538695],"domain_scores_gemma":[0.9972625,0.0011671152,0.0001049736,0.0010050472,0.00011797133,0.00034243453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012884219,0.00018063332,0.0003692851,0.0007076164,0.00014089103,0.00022841801,0.001488274,0.00013397729,0.00019023952],"category_scores_gemma":[0.0041248747,0.00011815647,0.000103582235,0.0018959299,0.00021513281,0.0008499605,0.00072133495,0.00026675448,0.00005475915],"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":[0.000042293763,0.00015115603,0.11096695,0.000007405479,0.00011917446,0.00046064268,0.00026387148,0.00087583455,0.00086858263,0.00015337722,0.00048663554,0.8856041],"study_design_scores_gemma":[0.0004919068,0.000057221427,0.07074289,0.000098057724,0.00009184899,0.000003952148,0.00006343342,0.9250309,0.0022916093,0.00041277788,0.00050823943,0.00020716117],"about_ca_topic_score_codex":0.0008935195,"about_ca_topic_score_gemma":0.017435288,"teacher_disagreement_score":0.92415506,"about_ca_system_score_codex":0.00007380889,"about_ca_system_score_gemma":0.00013107977,"threshold_uncertainty_score":0.97293},"labels":[],"label_agreement":null},{"id":"W2484736472","doi":"10.1016/j.media.2016.07.009","title":"ISLES 2015 - A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":531,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Université de Sherbrooke","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute on Aging; National Cancer Institute; Northeastern University; National Institute for Health and Care Research","keywords":"Segmentation; Benchmarking; Computer science; Artificial intelligence; Stroke (engine); Multispectral image; Benchmark (surveying); Magnetic resonance imaging; Lesion; Medicine; Pattern recognition (psychology); Machine learning; Radiology; Pathology; Cartography; Geography","score_opus":0.027593968755972878,"score_gpt":0.3462863085249213,"score_spread":0.31869233976894845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2484736472","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":[0.38109413,0.0003865813,0.5856303,0.027688028,0.0001555629,0.000991437,0.00015699695,0.00010804835,0.0037889092],"genre_scores_gemma":[0.9555487,0.00032219617,0.037070025,0.0009768265,0.0006024701,0.00033826995,0.00220365,0.000034762914,0.0029031017],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9964902,0.00010984696,0.00056287507,0.00062506757,0.0018030881,0.0004089644],"domain_scores_gemma":[0.9981435,0.00035707888,0.00021543838,0.00052135065,0.00038215113,0.0003804578],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001205714,0.00023285199,0.00051901623,0.00044502656,0.00008627283,0.000046358095,0.00022374559,0.00017522606,0.008741614],"category_scores_gemma":[0.0019111127,0.00015643206,0.00045469857,0.0005545886,0.00014607649,0.0003148583,0.00010653254,0.000139612,0.000107532964],"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":[0.00020656052,0.0003630299,0.026214432,0.000037199574,0.004820996,0.000034605833,0.00018245498,0.0000021165995,0.35340714,0.000011297546,0.41042408,0.20429608],"study_design_scores_gemma":[0.038577426,0.0008453264,0.08793711,0.000590168,0.059806935,0.000025669422,0.002303605,0.3071328,0.36596644,0.00025775903,0.13489029,0.0016664723],"about_ca_topic_score_codex":0.00015594617,"about_ca_topic_score_gemma":0.00012379585,"teacher_disagreement_score":0.57445455,"about_ca_system_score_codex":0.00037696198,"about_ca_system_score_gemma":0.00016914896,"threshold_uncertainty_score":0.99216455},"labels":[],"label_agreement":null},{"id":"W2508153689","doi":"10.1016/j.media.2016.09.001","title":"Conformal invariants for multiply connected surfaces: Application to landmark curve-based brain morphometry analysis","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":false,"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; U.S. Department of Defense; National Institute on Aging; National Institutes of Health; National Science Foundation","keywords":"Brain morphometry; Landmark; Invariant (physics); Conformal map; Neuroimaging; Computation; Mathematics; Artificial intelligence; Shape analysis (program analysis); Pattern recognition (psychology); Surface (topology); Geometry; Computer science; Algorithm; Neuroscience; Magnetic resonance imaging; Psychology; Medicine","score_opus":0.03491847557675011,"score_gpt":0.37055534472712737,"score_spread":0.33563686915037727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2508153689","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":[0.06294575,0.000016843645,0.91107464,0.024589477,0.000010963549,0.00074412726,0.00021779678,0.00026278972,0.00013760549],"genre_scores_gemma":[0.9218044,0.000017510074,0.07023414,0.0062453635,0.00007135484,0.00049167924,0.00063731923,0.000029740406,0.00046844475],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977363,0.00006406009,0.0005751403,0.00063086057,0.0005985401,0.00039510755],"domain_scores_gemma":[0.99697506,0.0010239558,0.0001847906,0.0008396506,0.00039404674,0.00058249],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007413275,0.00022487565,0.00075337425,0.001009742,0.00012285376,0.00003123422,0.00030221065,0.00013836502,0.00073692965],"category_scores_gemma":[0.002687167,0.00015468306,0.00055296766,0.004753823,0.00015096938,0.00011810279,0.00006620366,0.00014291759,0.00005662263],"study_design_candidate":"observational","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":[0.0015647023,0.0021684265,0.55677086,0.00027003407,0.014865126,0.00012383267,0.00018151292,0.0010395198,0.24661702,0.0014000437,0.036100604,0.13889834],"study_design_scores_gemma":[0.007562759,0.00045073865,0.21497719,0.00012767746,0.018858405,0.0000122648635,0.00007232304,0.6581739,0.032516934,0.00038856734,0.06586293,0.0009962975],"about_ca_topic_score_codex":0.00016906523,"about_ca_topic_score_gemma":0.00014769823,"teacher_disagreement_score":0.8588587,"about_ca_system_score_codex":0.00008082159,"about_ca_system_score_gemma":0.00011227907,"threshold_uncertainty_score":0.8068863},"labels":[],"label_agreement":null},{"id":"W2513067461","doi":"10.1016/j.media.2016.08.007","title":"Brain shift in neuronavigation of brain tumors: A review","year":2016,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Glioma Diagnosis and Treatment","field":"Medicine","cited_by":318,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill Genome Centre","funders":"Canadian Institutes of Health Research; Canadian HIV Trials Network, Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Fondation Brain Canada","keywords":"Neuronavigation; Paradigm shift; Computer science; Field (mathematics); Compensation (psychology); Brain activity and meditation; Medical physics; Artificial intelligence; Neuroscience; Medicine; Electroencephalography; Psychology; Magnetic resonance imaging; Radiology","score_opus":0.024902599760763068,"score_gpt":0.3796284851693184,"score_spread":0.3547258854085553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2513067461","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025173522,0.98271793,0.00014045535,0.015910681,0.000024893157,0.0008246995,0.000054913315,0.000022597787,0.0002786717],"genre_scores_gemma":[0.00007858621,0.99644053,0.000082962506,0.0022071372,0.000106782805,0.0002498926,0.00067946664,0.00003944516,0.00011517549],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957099,0.00057522906,0.0016575482,0.000617072,0.0011120294,0.00032823207],"domain_scores_gemma":[0.9969167,0.0012108287,0.00061213406,0.00078992266,0.000089019086,0.00038137793],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013871068,0.0004247808,0.004749847,0.0008959706,0.000019009074,0.000011314108,0.00026992988,0.00026938616,0.0038802633],"category_scores_gemma":[0.004254292,0.00024847302,0.00209377,0.0028870732,0.00016644681,0.00006323827,0.00009929875,0.00039714,0.00020908525],"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":[0.0000034003372,0.0004536336,0.000251488,0.0338773,0.001759052,0.0015862884,0.000012875061,1.2269637e-8,7.920488e-7,0.000025562214,0.0071564564,0.95487314],"study_design_scores_gemma":[0.0008092279,0.00011046827,0.00058689225,0.24326958,0.01861944,0.000064497195,0.000002294204,0.000013262197,0.0000025451716,0.000029715115,0.73625183,0.00024024381],"about_ca_topic_score_codex":0.00014118964,"about_ca_topic_score_gemma":0.00007033631,"teacher_disagreement_score":0.9546329,"about_ca_system_score_codex":0.00014778593,"about_ca_system_score_gemma":0.000433296,"threshold_uncertainty_score":0.9999967},"labels":[],"label_agreement":null},{"id":"W2513411538","doi":"10.1016/j.media.2016.08.005","title":"Evaluation and comparison of 3D intervertebral disc localization and segmentation methods for 3D T2 MR data: A grand challenge","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":75,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Segmentation; Hausdorff distance; Artificial intelligence; Computer science; Data set; Ground truth; Magnetic resonance imaging; Pattern recognition (psychology); Intervertebral disc; Computer vision; Medicine; Anatomy; Radiology","score_opus":0.05513416208565318,"score_gpt":0.41719475857006677,"score_spread":0.3620605964844136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2513411538","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":[0.0069673224,0.0021867894,0.9898759,0.00065589487,0.00004681577,0.0001288584,0.000028560013,0.000039690087,0.00007016983],"genre_scores_gemma":[0.90000224,0.0010983972,0.09822472,0.00005574131,0.0000925454,0.000044395823,0.00042479511,0.000021288357,0.000035865734],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982706,0.00025404195,0.00047334368,0.0003010471,0.0005457528,0.00015524022],"domain_scores_gemma":[0.99898595,0.00033326342,0.00008871921,0.00027731172,0.00014626392,0.00016850249],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025214825,0.0001300263,0.00047517728,0.00024061407,0.00005129938,0.000032406737,0.00014075468,0.00008122171,0.0004132191],"category_scores_gemma":[0.0013889387,0.00008784955,0.0000749751,0.00039266306,0.00017686222,0.00029977487,0.00007405816,0.0000722575,0.0000013465003],"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":[0.0000045317915,0.000052135954,0.0029626149,0.00013167475,0.001208911,5.650311e-7,0.00035887017,0.00013061371,0.0011984912,0.0000064857454,0.00054464757,0.99340045],"study_design_scores_gemma":[0.0008908628,0.000026020667,0.0003831035,0.0000730355,0.004304744,6.011511e-7,0.00013315657,0.9927114,0.00083086395,0.00014668175,0.0003890782,0.00011040747],"about_ca_topic_score_codex":0.00003816788,"about_ca_topic_score_gemma":0.00008530647,"teacher_disagreement_score":0.99329007,"about_ca_system_score_codex":0.000028876877,"about_ca_system_score_gemma":0.000017449946,"threshold_uncertainty_score":0.45244592},"labels":[],"label_agreement":null},{"id":"W2521652955","doi":"10.1016/j.media.2016.08.012","title":"Atlas-based shape analysis and classification of retinal optical coherence tomography images using the functional shape (fshape) framework","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research","keywords":"Optical coherence tomography; Glaucoma; Artificial intelligence; Computer science; Nerve fiber layer; Pattern recognition (psychology); Retinal; Linear discriminant analysis; Population; Computer vision; Optics; Ophthalmology; Physics; Medicine","score_opus":0.02320369450665437,"score_gpt":0.30954422201178283,"score_spread":0.28634052750512845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521652955","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":[0.55525625,0.0003064899,0.43500665,0.00896627,0.000021699092,0.00010371399,0.000024140412,0.000048044312,0.000266776],"genre_scores_gemma":[0.98170257,0.00010594921,0.017164351,0.0005808661,0.00017049872,0.000018004019,0.000077793964,0.000021307893,0.0001586462],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.995869,0.00028392076,0.0008846888,0.00076575635,0.0017665111,0.00043016762],"domain_scores_gemma":[0.996356,0.0013245629,0.0003910359,0.00077369006,0.0006620217,0.00049269694],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014020123,0.00032269885,0.0010890076,0.0012869696,0.00021834743,0.000084889296,0.00030576525,0.00023607345,0.0060064113],"category_scores_gemma":[0.0022089907,0.00017590249,0.0013364198,0.006538342,0.0016746911,0.00016018667,0.00009518158,0.00045797852,0.0000200896],"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":[0.00027420363,0.00034603578,0.90713805,0.00007321067,0.009552844,0.00008298526,0.000044382825,0.000029415185,0.053026643,0.00015078379,0.00031509926,0.028966345],"study_design_scores_gemma":[0.0005854681,0.00009506817,0.6360817,0.00020371309,0.03440151,0.0000194083,0.0001247952,0.32545665,0.0025873675,0.00013614236,0.000073658564,0.00023448371],"about_ca_topic_score_codex":0.00011712262,"about_ca_topic_score_gemma":0.000023046334,"teacher_disagreement_score":0.42644635,"about_ca_system_score_codex":0.000056541172,"about_ca_system_score_gemma":0.0001802269,"threshold_uncertainty_score":0.99490225},"labels":[],"label_agreement":null},{"id":"W2542242623","doi":"10.1016/j.media.2016.10.009","title":"Unsupervised boundary delineation of spinal neural foramina using a multi-feature and adaptive spectral segmentation","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Segmentation; Feature (linguistics); Computer science; Boundary (topology); Artificial neural network; Computer vision; Mathematics","score_opus":0.016609550336393875,"score_gpt":0.27929440416018625,"score_spread":0.26268485382379236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2542242623","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":[0.44190618,0.00047888941,0.5571376,0.00033910052,0.000028210297,0.00003728491,0.000011146104,0.000046168745,0.00001538734],"genre_scores_gemma":[0.97371054,0.00012873021,0.02586944,0.00006410468,0.00010217947,0.0000039402066,0.000030330102,0.00001608692,0.00007463485],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985981,0.000069555485,0.0003417545,0.00023332609,0.0005228757,0.0002344092],"domain_scores_gemma":[0.99937236,0.000063597625,0.00006154689,0.00016201391,0.00009917227,0.00024131719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029220106,0.00016460493,0.0003952617,0.00032823705,0.000058928246,0.000031948246,0.00011040839,0.0000992856,0.00030666386],"category_scores_gemma":[0.00022051713,0.0001133395,0.0002056644,0.0007936585,0.00023277239,0.00024269824,0.00002921606,0.00015522486,0.0000036770873],"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":[0.000086576605,0.00024116314,0.05551391,0.00028326834,0.00528925,0.00023159698,0.0007612346,0.0026840526,0.28768453,0.00002509547,0.0004884776,0.6467109],"study_design_scores_gemma":[0.00070072064,0.000031208776,0.007076787,0.00007460658,0.0015191229,0.000007798052,0.00016860322,0.98498243,0.0052484865,0.000016217966,0.000024257468,0.00014975466],"about_ca_topic_score_codex":0.00010506722,"about_ca_topic_score_gemma":0.000040435778,"teacher_disagreement_score":0.9822984,"about_ca_system_score_codex":0.000055796103,"about_ca_system_score_gemma":0.000029588082,"threshold_uncertainty_score":0.46218506},"labels":[],"label_agreement":null},{"id":"W2558764425","doi":"10.1016/j.media.2016.11.008","title":"Direct and simultaneous estimation of cardiac four chamber volumes by multioutput sparse regression","year":2016,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; St Joseph's Health Care; Western University","funders":"National Natural Science Foundation of China; Government of Ontario","keywords":"Discriminative model; Volume (thermodynamics); Artificial intelligence; Computer science; Pattern recognition (psychology); Mathematics; Computer vision","score_opus":0.008844177531851929,"score_gpt":0.27735978089106406,"score_spread":0.26851560335921215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2558764425","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":[0.011453066,0.0002777503,0.98634887,0.0012731344,0.000055435445,0.00011622295,0.000016149872,0.0001746698,0.0002847041],"genre_scores_gemma":[0.8454661,0.0006160936,0.15199555,0.00030177773,0.000039687566,0.000022953795,0.000019837882,0.000012053062,0.0015259531],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759114,0.00019624528,0.00045545577,0.00045393943,0.0010730685,0.00023015097],"domain_scores_gemma":[0.99795115,0.0008379425,0.00021284758,0.0005013898,0.0001604051,0.00033627366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080414803,0.00016260534,0.00047219047,0.00024448673,0.000062929685,0.000053521573,0.00034307514,0.00010009332,0.0003148324],"category_scores_gemma":[0.0029670827,0.00009988521,0.00016888895,0.0007328902,0.00031417998,0.0004656484,0.00022704959,0.00009067839,0.000023141094],"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":[0.000004876887,0.00006283106,0.0007109588,0.00001889592,0.00023626698,0.000050093255,0.0001546013,0.000004443197,0.016596667,0.00001279714,0.007906402,0.97424114],"study_design_scores_gemma":[0.0006247308,0.00009761158,0.00119198,0.00022134346,0.0005669803,0.000010697437,0.000027594993,0.6771624,0.31851834,0.000189014,0.0009931512,0.0003961244],"about_ca_topic_score_codex":0.00015274575,"about_ca_topic_score_gemma":0.000008309325,"teacher_disagreement_score":0.97384506,"about_ca_system_score_codex":0.000035741636,"about_ca_system_score_gemma":0.00004234376,"threshold_uncertainty_score":0.40732008},"labels":[],"label_agreement":null},{"id":"W2571012593","doi":"10.1016/j.media.2017.01.004","title":"Robust estimation of carotid artery wall motion using the elasticity-based state-space approach","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiovascular Health and Disease Prevention","field":"Medicine","cited_by":87,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Initialization; Common carotid artery; Elasticity (physics); Carotid arteries; Mathematics; Ultrasound; Measure (data warehouse); Artificial intelligence; Computer science; Medicine; Surgery; Radiology; Physics; Data mining","score_opus":0.031407864564820386,"score_gpt":0.30930143244943076,"score_spread":0.2778935678846104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2571012593","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":[0.33293158,0.00007461799,0.66577154,0.0007680352,0.000021701757,0.00019604606,0.0000053390468,0.00001621095,0.00021494972],"genre_scores_gemma":[0.98988295,0.000017739176,0.009608614,0.00019621765,0.00007775591,0.000014245149,0.00015302116,0.000010313705,0.000039137933],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980584,0.00018062812,0.00034925083,0.00024945833,0.00095663755,0.00020561962],"domain_scores_gemma":[0.99851316,0.000062311825,0.00024611407,0.0006848956,0.00018609439,0.00030742568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011254563,0.00011617797,0.000448468,0.0001908743,0.00025871058,0.00004960436,0.00015046688,0.00008202598,0.00020173019],"category_scores_gemma":[0.0013823467,0.000080708574,0.00066427124,0.0003023125,0.00022551461,0.00012733623,0.000040395284,0.00018876235,0.000005984762],"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":[0.0011797848,0.003174645,0.28753704,0.004321188,0.013253129,0.00025698935,0.00087321637,0.6119753,0.005758329,0.000079193385,0.0010070471,0.07058411],"study_design_scores_gemma":[0.0009527227,0.000014132717,0.17714328,0.000051085008,0.004914092,0.000007799783,0.00003209089,0.81641626,0.0003792608,0.000021945018,0.0000063796465,0.000060971608],"about_ca_topic_score_codex":0.00062835764,"about_ca_topic_score_gemma":0.00003824973,"teacher_disagreement_score":0.65695137,"about_ca_system_score_codex":0.00006535353,"about_ca_system_score_gemma":0.00019674172,"threshold_uncertainty_score":0.32912},"labels":[],"label_agreement":null},{"id":"W2580480204","doi":"10.1016/j.media.2017.01.009","title":"A deep learning approach for the analysis of masses in mammograms with minimal user intervention","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":342,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Segmentation; Computer science; Deep learning; Pattern recognition (psychology); Classifier (UML); Mammography; Bayesian probability; Visualization; Test set; Machine learning; Breast cancer","score_opus":0.015229905149617709,"score_gpt":0.2996650691174222,"score_spread":0.2844351639678045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2580480204","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":[0.030088583,0.00012770329,0.96894246,0.00049419614,0.00002806774,0.00011563235,8.6709775e-7,0.00002463617,0.00017787512],"genre_scores_gemma":[0.94865525,0.000026200265,0.05104491,0.000029454297,0.000025631449,0.00008480731,0.000011726134,0.0000060485827,0.00011596881],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983015,0.00012562232,0.000347569,0.00039198936,0.000620665,0.00021266426],"domain_scores_gemma":[0.9983851,0.00023935325,0.00037873856,0.0008012974,0.00013553324,0.000060010436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013832393,0.00011184327,0.00041535666,0.00055425137,0.00022158248,0.00024678325,0.0012449963,0.00007220101,0.000091421105],"category_scores_gemma":[0.0005245175,0.00007164352,0.00050611794,0.00215417,0.00023104943,0.00042074762,0.00022233395,0.0002079539,8.86334e-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":[0.000113195674,0.00035482924,0.2773192,0.000075824464,0.013057338,0.00002414859,0.0010306275,0.031781513,0.0000806455,0.0001955004,0.00003838651,0.6759288],"study_design_scores_gemma":[0.00032273628,0.00006774389,0.110815614,0.00001056731,0.003110214,9.609045e-7,0.00018691589,0.88510156,0.00013526966,0.000017384196,0.00015092694,0.00008012694],"about_ca_topic_score_codex":0.0010119533,"about_ca_topic_score_gemma":0.0024381378,"teacher_disagreement_score":0.91856664,"about_ca_system_score_codex":0.000046264813,"about_ca_system_score_gemma":0.000026106452,"threshold_uncertainty_score":0.29215378},"labels":[],"label_agreement":null},{"id":"W2589644515","doi":"10.1016/j.media.2017.11.005","title":"Learning normalized inputs for iterative estimation in medical image segmentation","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":229,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Computer science; Pipeline (software); Segmentation; Convolutional neural network; Artificial intelligence; Benchmark (surveying); Deep learning; Residual; Image segmentation; Pattern recognition (psychology); Computer vision; Algorithm","score_opus":0.00796106501721744,"score_gpt":0.3132501830028003,"score_spread":0.30528911798558284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589644515","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":[0.09953765,0.00007797196,0.8950861,0.0032058835,0.000117393254,0.00014445027,0.000008789583,0.00017669321,0.0016450778],"genre_scores_gemma":[0.9811086,0.00017666745,0.017350864,0.0003516992,0.00016530864,0.000104780054,0.00038145386,0.00003206052,0.00032858245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973022,0.00013309417,0.0006428875,0.00034779153,0.0011663884,0.00040769044],"domain_scores_gemma":[0.99860513,0.00030401887,0.00014607323,0.00037478533,0.00012001348,0.00044998154],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016157241,0.0002260321,0.0006245942,0.00049408723,0.000295987,0.00029388923,0.00047726743,0.00019707729,0.0023118553],"category_scores_gemma":[0.006033029,0.00020084053,0.0003308536,0.0005573875,0.00025036052,0.0006131686,0.000079888036,0.0005318856,0.00006422897],"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":[0.00008047334,0.0005998332,0.0773045,0.00089943095,0.007785271,0.0014279457,0.0057300227,0.031792898,0.01404973,0.00012818404,0.008825431,0.8513763],"study_design_scores_gemma":[0.0011768513,0.000016691725,0.002810479,0.000091005466,0.00066214154,0.0000032930768,0.000096472555,0.9925235,0.0019944399,0.000092204136,0.00031611367,0.00021684053],"about_ca_topic_score_codex":0.00017869001,"about_ca_topic_score_gemma":0.0001935958,"teacher_disagreement_score":0.96073055,"about_ca_system_score_codex":0.0000854138,"about_ca_system_score_gemma":0.00006053718,"threshold_uncertainty_score":0.9986002},"labels":[],"label_agreement":null},{"id":"W2589663521","doi":"10.1016/j.media.2017.02.007","title":"Longitudinal segmentation of age-related white matter hyperintensities","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":49,"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; Genentech; National Institutes of Health; Takeda Pharmaceutical Company; IXICO; H. Lundbeck A/S; Wolfson Foundation; National Institute on Aging; National Institute for Health and Care Research; Seventh Framework Programme; Northern California Institute for Research and Education; DoD Alzheimer's Disease Neuroimaging Initiative; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; National Institute on Handicapped Research; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Roche; Merck; Alzheimer's Drug Discovery Foundation; AbbVie; Fujirebio Europe; Alzheimer's Association; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative; Medical Research Council; Johnson and Johnson; Meso Scale Diagnostics","keywords":"Hyperintensity; Segmentation; Lesion; Robustness (evolution); Computer science; Artificial intelligence; Longitudinal data; Longitudinal study; Pattern recognition (psychology); Medicine; Magnetic resonance imaging; Data mining; Radiology; Pathology","score_opus":0.016349241689653973,"score_gpt":0.3072204340925042,"score_spread":0.29087119240285025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589663521","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":[0.020201733,0.000026337895,0.9717162,0.0038913663,0.00011672389,0.00009178098,0.0000031750394,0.000113422306,0.0038392611],"genre_scores_gemma":[0.8330726,0.000040215,0.16380307,0.0010188586,0.00004099136,0.00002054675,0.0000312319,0.000010950436,0.0019615516],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975848,0.00011528733,0.00056836894,0.0004006463,0.0010900504,0.00024082027],"domain_scores_gemma":[0.9979313,0.00007317149,0.00039594393,0.001124091,0.00023928199,0.00023622779],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00074177905,0.0001520996,0.00043453733,0.00033598015,0.00019979246,0.00030103308,0.0014304838,0.0001023304,0.004302425],"category_scores_gemma":[0.0004884034,0.00012849539,0.00026792314,0.0004404817,0.0006949129,0.0009175306,0.00045923027,0.00020118833,0.00015455516],"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":[0.00003464821,0.0007127801,0.7086186,0.00023748048,0.00485872,0.0025916798,0.0042197164,0.000027284847,0.026037633,0.0012941904,0.03876963,0.21259768],"study_design_scores_gemma":[0.001163996,0.00012544259,0.8485288,0.00012538464,0.0012005977,0.000054179254,0.00029204608,0.059823014,0.08630972,0.0016901722,0.00008638678,0.000600251],"about_ca_topic_score_codex":0.0002448498,"about_ca_topic_score_gemma":0.000036225192,"teacher_disagreement_score":0.81287086,"about_ca_system_score_codex":0.000031766267,"about_ca_system_score_gemma":0.00004736334,"threshold_uncertainty_score":0.9966078},"labels":[],"label_agreement":null},{"id":"W2592617572","doi":"10.1016/j.media.2017.03.001","title":"Population model of bladder motion and deformation based on dominant eigenmodes and mixed-effects models in prostate cancer radiotherapy","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institut National Du Cancer; Institute of Cancer Research; Departamento Administrativo de Ciencia, Tecnología e Innovación (COLCIENCIAS)","keywords":"Principal component analysis; Voxel; Population; Computer science; Mathematics; Prostate cancer; Artificial intelligence; Statistics; Pattern recognition (psychology); Medicine; Cancer; Internal medicine","score_opus":0.008159641242234032,"score_gpt":0.29719497717197674,"score_spread":0.28903533592974273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592617572","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":[0.4006787,0.00007493833,0.59894377,0.00011229914,0.000005704054,0.00012986637,0.000010738852,0.0000066339326,0.000037373855],"genre_scores_gemma":[0.97908014,0.00019025002,0.02053084,0.000044512348,0.0000191669,0.0000836762,0.000028098575,0.000010881452,0.000012415513],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991797,0.00004820375,0.00022329579,0.00019448118,0.00022912005,0.000125167],"domain_scores_gemma":[0.99943376,0.00003587289,0.00019729449,0.00023203962,0.000037207254,0.00006381052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024958738,0.000117460186,0.00030625451,0.00019531457,0.000098219134,0.000037992442,0.00008185802,0.000043162017,0.000040885498],"category_scores_gemma":[0.000016116623,0.00009357047,0.000064906664,0.00010208843,0.00009964911,0.00042868796,0.000015255621,0.00009217479,4.2710816e-8],"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":[0.00013458327,0.00022730534,0.25952014,0.00008618235,0.0004417841,0.0000026477162,0.00062486687,0.21580666,0.0067687677,0.0013267573,0.00001450314,0.5150458],"study_design_scores_gemma":[0.00064931903,0.00002470498,0.020222561,0.000041152245,0.00010847452,6.570249e-8,0.00000942702,0.96986496,0.006053678,0.0029322936,0.0000010301732,0.00009230082],"about_ca_topic_score_codex":0.0014649592,"about_ca_topic_score_gemma":0.000068959554,"teacher_disagreement_score":0.7540583,"about_ca_system_score_codex":0.000035762863,"about_ca_system_score_gemma":0.000015089612,"threshold_uncertainty_score":0.38156927},"labels":[],"label_agreement":null},{"id":"W2612377680","doi":"10.1016/j.media.2017.04.008","title":"A structured latent model for ovarian carcinoma subtyping from histopathology slides","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Subtyping; Computer science; Discriminative model; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Feature vector; Histopathology; Machine learning; Pathology; Medicine","score_opus":0.025349649899223437,"score_gpt":0.29035625491355294,"score_spread":0.2650066050143295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612377680","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":[0.062121805,0.00008651273,0.9338486,0.0033352505,0.0003150627,0.000087719694,0.000014221706,0.000073924886,0.0001169107],"genre_scores_gemma":[0.8799938,0.00000852259,0.119195215,0.00041113136,0.0001738456,0.00003226249,0.000013058845,0.000008698624,0.00016344523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983593,0.000060409664,0.00028527624,0.0005838092,0.00042132623,0.0002898341],"domain_scores_gemma":[0.99806285,0.000091562215,0.00023155523,0.0012972091,0.00012549279,0.00019134258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004373124,0.00013929504,0.0003666365,0.000182073,0.000445455,0.00023809649,0.0014947538,0.00015007108,0.00010585914],"category_scores_gemma":[0.0005582748,0.00012440646,0.00028274438,0.00020418588,0.00016145967,0.000408502,0.00035206223,0.00017841537,0.0000089378045],"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":[0.00026129483,0.00028512426,0.17847763,0.00011709478,0.0030990574,0.0012118757,0.008224704,0.0074879746,0.027749445,0.008624752,0.007060622,0.75740045],"study_design_scores_gemma":[0.00035257186,0.000017556076,0.060594454,0.000004872985,0.0003354112,0.0000040884856,0.0000049211435,0.929603,0.0008250804,0.008010904,0.00011563074,0.00013152148],"about_ca_topic_score_codex":0.0011999471,"about_ca_topic_score_gemma":0.0010952501,"teacher_disagreement_score":0.922115,"about_ca_system_score_codex":0.0001254923,"about_ca_system_score_gemma":0.00012667371,"threshold_uncertainty_score":0.5073148},"labels":[],"label_agreement":null},{"id":"W2727053570","doi":"10.1016/j.media.2017.06.009","title":"Modelling and extraction of pulsatile radial distension and compression motion for automatic vessel segmentation from video","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Pulsatile flow; Computer vision; Segmentation; Computer science; Artificial intelligence; Motion estimation; Orientation (vector space); Optical flow; Motion (physics); Computation; Mathematics; Image (mathematics); Algorithm","score_opus":0.023570089986048075,"score_gpt":0.3294118092825127,"score_spread":0.3058417192964646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727053570","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":[0.09484768,0.00007830449,0.904152,0.0005758422,0.00006827232,0.0001945142,0.000011174852,0.000054396914,0.000017857074],"genre_scores_gemma":[0.694068,0.0001290678,0.30554315,0.00008438424,0.00003374561,0.000037761594,0.00008496957,0.0000055086684,0.000013380067],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839944,0.000118374184,0.00038872112,0.00035417188,0.0006165872,0.00012269494],"domain_scores_gemma":[0.998595,0.0003308247,0.00040925032,0.00041112356,0.00009103575,0.00016279367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065041916,0.00010438638,0.0002917526,0.00017462688,0.00037287368,0.00019077581,0.00031821482,0.00007178413,0.0001799661],"category_scores_gemma":[0.00045968202,0.00009225634,0.000079542115,0.00013560442,0.00017413244,0.0010041135,0.00020010362,0.000109101646,6.3054e-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":[0.000026957396,0.00018819663,0.002294827,0.00009055124,0.00028997994,0.000014816852,0.0010050628,0.0003843825,0.056434985,0.00008846642,0.00059655757,0.9385852],"study_design_scores_gemma":[0.0004906727,0.00003941951,0.004638965,0.000036447625,0.00026455912,0.0000019792558,0.0000604824,0.965147,0.028111344,0.0011118313,0.000011317194,0.00008595881],"about_ca_topic_score_codex":0.00057074934,"about_ca_topic_score_gemma":0.000010827613,"teacher_disagreement_score":0.9647626,"about_ca_system_score_codex":0.00002681863,"about_ca_system_score_gemma":0.00002079555,"threshold_uncertainty_score":0.37621045},"labels":[],"label_agreement":null},{"id":"W2738318712","doi":"10.1016/j.media.2017.07.004","title":"Designing image segmentation studies: Statistical power, sample size and reference standard quality","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":35,"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; Canadian Institutes of Health Research; Medical Research Council; Radboud Universiteit; Cancer Research UK","keywords":"Resampling; Sample size determination; Segmentation; Computer science; Reference data; Statistics; Range (aeronautics); Standard deviation; Matching (statistics); Sample (material); Statistical power; Data set; Artificial intelligence; Mathematics; Data mining","score_opus":0.03164478710718117,"score_gpt":0.3839955934075969,"score_spread":0.35235080630041576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738318712","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":[0.045949128,0.00042100914,0.95219433,0.00027035933,0.00006363987,0.00007035604,0.000118617754,0.0001272389,0.00078531523],"genre_scores_gemma":[0.7904884,0.00066491537,0.20860575,0.00010687949,0.000041281604,0.000015223028,0.000027632357,0.000018429486,0.000031495292],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998321,0.00009343915,0.0003989882,0.00030529403,0.0005713094,0.00030999747],"domain_scores_gemma":[0.99771225,0.001403288,0.00009874004,0.00041515823,0.00012831116,0.00024224326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086307275,0.00018553718,0.0005017503,0.00007413166,0.00038715778,0.00019081637,0.00022187666,0.00006295886,0.0007762732],"category_scores_gemma":[0.007929001,0.00016698011,0.00007166871,0.0001589019,0.00041837525,0.0005093584,0.00010920178,0.00027325324,0.000013440856],"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":[0.0006486004,0.00046815025,0.10826486,0.0025308698,0.024189366,0.002137094,0.017384943,0.0023799331,0.2358944,0.0041911425,0.009528115,0.59238255],"study_design_scores_gemma":[0.017714974,0.0009583502,0.43669593,0.0012371632,0.017962629,0.000069532434,0.061571043,0.2537286,0.11586502,0.07710745,0.00850751,0.00858177],"about_ca_topic_score_codex":0.00010067915,"about_ca_topic_score_gemma":0.00010122882,"teacher_disagreement_score":0.74453926,"about_ca_system_score_codex":0.00007714628,"about_ca_system_score_gemma":0.000024440062,"threshold_uncertainty_score":0.94923276},"labels":[],"label_agreement":null},{"id":"W2741247953","doi":"10.1016/j.media.2017.07.006","title":"Ensemble of expert deep neural networks for spatio-temporal denoising of contrast-enhanced MRI sequences","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"FP7 Ideas: European Research Council; Israel Science Foundation; United States-Israel Binational Science Foundation","keywords":"Computer science; Artificial intelligence; Voxel; Pattern recognition (psychology); Dynamic contrast-enhanced MRI; Artificial neural network; Diffusion MRI; Classifier (UML); Noise reduction; Noise (video); Deep learning; Contrast (vision); Magnetic resonance imaging; Image (mathematics)","score_opus":0.023359598990500108,"score_gpt":0.32877905013837194,"score_spread":0.30541945114787183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2741247953","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":[0.02789131,0.0004279969,0.9702504,0.000835515,0.00020145025,0.00013673668,0.0000022964757,0.000030332323,0.00022392465],"genre_scores_gemma":[0.8233924,0.000032312648,0.1761504,0.00021593113,0.00012612576,0.000012610293,0.000010338582,0.000008163868,0.00005170427],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975695,0.00023773637,0.00066311285,0.00043833576,0.00071888964,0.00037242196],"domain_scores_gemma":[0.99723077,0.0005521003,0.00062479754,0.0009614101,0.00043620644,0.0001947243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016816985,0.00018020505,0.00076669356,0.00021214658,0.00025243015,0.00022387727,0.0016480864,0.00013060456,0.000081901926],"category_scores_gemma":[0.0013855352,0.00014858952,0.000482782,0.00046309832,0.00044279313,0.00070600514,0.00023154063,0.00015347067,0.0000010498617],"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":[0.00031953826,0.00046101888,0.0072813714,0.00016320933,0.0024663492,0.00025692343,0.0034537893,0.0072708195,0.090743884,0.0011308106,0.00081717735,0.8856351],"study_design_scores_gemma":[0.00069158734,0.000099917794,0.0010267574,0.00003273559,0.00025471844,0.000003540256,0.000039451177,0.91667694,0.080211714,0.00075510744,0.000043580592,0.00016393997],"about_ca_topic_score_codex":0.00067586993,"about_ca_topic_score_gemma":0.00028202322,"teacher_disagreement_score":0.9094061,"about_ca_system_score_codex":0.000019024625,"about_ca_system_score_gemma":0.000077440476,"threshold_uncertainty_score":0.60593045},"labels":[],"label_agreement":null},{"id":"W2757633676","doi":"10.1016/j.media.2017.09.005","title":"Full left ventricle quantification via deep multitask relationships learning","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":161,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Softmax function; Multi-task learning; Artificial intelligence; Deep learning; Computer science; Pattern recognition (psychology); Classifier (UML); Convolutional neural network; Ventricle; Machine learning; Task (project management); Cardiology; Medicine","score_opus":0.023500276494085866,"score_gpt":0.32301923516133463,"score_spread":0.29951895866724876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2757633676","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":[0.36329332,0.00086641836,0.61685383,0.011840776,0.00028722722,0.00021467335,0.0000063832426,0.00022610514,0.0064112823],"genre_scores_gemma":[0.99579686,0.00008255114,0.0026965681,0.0001710654,0.00024121482,0.000006205356,0.0001846028,0.000016623108,0.00080431585],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982912,0.00013767034,0.00032462683,0.00031419974,0.0006889049,0.00024339223],"domain_scores_gemma":[0.9980194,0.00044530266,0.000190433,0.0007589257,0.00022657374,0.00035935364],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010612477,0.0001221205,0.00038275166,0.00026297153,0.0006676643,0.00013673025,0.00017727872,0.00012550592,0.00096824125],"category_scores_gemma":[0.019056052,0.00011041259,0.0003791849,0.00029190833,0.0002262777,0.00016765595,0.00007400298,0.0005714475,0.00061578857],"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":[0.00004455298,0.00018816745,0.9746234,0.000028216213,0.00082719827,0.00028444198,0.00024425302,0.00014369882,0.0012776128,0.00003586107,0.0012319032,0.021070708],"study_design_scores_gemma":[0.0008844348,0.000043780645,0.8136407,0.000039456234,0.004158282,0.000046255514,0.00016809242,0.17746991,0.00066978025,0.00005722202,0.0026597136,0.00016234038],"about_ca_topic_score_codex":0.00026081307,"about_ca_topic_score_gemma":0.00010858656,"teacher_disagreement_score":0.6325035,"about_ca_system_score_codex":0.000051832885,"about_ca_system_score_gemma":0.000060001566,"threshold_uncertainty_score":0.999945},"labels":[],"label_agreement":null},{"id":"W2770706469","doi":"10.1016/j.media.2017.11.007","title":"The semiotics of medical image Segmentation","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Robarts Clinical Trials","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Semiotics; Computer science; Sign (mathematics); Segmentation; Interpretation (philosophy); Metaphor; Symbol (formal); Semiosis; Perspective (graphical); Artificial intelligence; Image (mathematics); Image segmentation; Interface (matter); Natural language processing; Human–computer interaction; Linguistics; Mathematics","score_opus":0.012701397737422833,"score_gpt":0.3466525148679864,"score_spread":0.3339511171305636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770706469","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":[0.71123624,0.0025183514,0.23589721,0.04412917,0.00058232294,0.00019863497,0.00004338834,0.00005256893,0.00534211],"genre_scores_gemma":[0.9909533,0.002296155,0.004742283,0.00053852354,0.0003838851,0.000010949637,0.000113306276,0.000013715681,0.00094784476],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979023,0.00011554459,0.00036175843,0.0002644567,0.0011108586,0.00024507786],"domain_scores_gemma":[0.99850434,0.000114905255,0.00022667774,0.00078458263,0.00012065169,0.00024882233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015179808,0.00011826893,0.0002621071,0.000045158973,0.00035781352,0.0000870683,0.0011131903,0.0003123264,0.0003850813],"category_scores_gemma":[0.007192629,0.00007355914,0.00026288372,0.00013098869,0.001539022,0.000004903342,0.0003940682,0.00019294849,0.000014627372],"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":[0.00016431109,0.0004833318,0.046220668,0.00010557584,0.0056747333,0.00025260646,0.00026636425,0.000003608913,0.112621084,0.00028358208,0.07593047,0.75799364],"study_design_scores_gemma":[0.007296131,0.0013204084,0.16966534,0.00028418872,0.006477387,0.000117567986,0.0037946072,0.04782306,0.51373196,0.0013229593,0.24629992,0.0018664667],"about_ca_topic_score_codex":0.00014062667,"about_ca_topic_score_gemma":0.00032773483,"teacher_disagreement_score":0.7561272,"about_ca_system_score_codex":0.0000072515227,"about_ca_system_score_gemma":0.0001377829,"threshold_uncertainty_score":0.86107683},"labels":[],"label_agreement":null},{"id":"W2773397026","doi":"10.1016/j.media.2017.12.001","title":"Automatic spinal cord localization, robust to MRI contrasts using global curve optimization","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Polytechnique Montréal","funders":"National Institute of Neurological Disorders and Stroke; National Eye Institute; Fonds de recherche du Québec – Nature et technologies; Fondation Aix-Marseille Universite; Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Centre National de la Recherche Scientifique; National Multiple Sclerosis Society; Canada Foundation for Innovation; Canadian HIV Trials Network, Canadian Institutes of Health Research; Agence Nationale de la Recherche; Natural Sciences and Engineering Research Council of Canada","keywords":"Spinal cord; Feature (linguistics); Artificial intelligence; Computer science; Pattern recognition (psychology); Diffusion MRI; Computer vision; Magnetic resonance imaging; Medicine; Radiology","score_opus":0.01740338147861816,"score_gpt":0.3089809144577952,"score_spread":0.29157753297917705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773397026","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":[0.019821608,0.000108058484,0.97767675,0.0010392554,0.00018740084,0.00008662971,0.0000151592985,0.0002673866,0.00079776684],"genre_scores_gemma":[0.943295,0.00007322105,0.055543013,0.00060524454,0.00029160295,0.000011500516,0.000085498046,0.000032119104,0.000062813044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975541,0.00007778065,0.0005689052,0.00037440204,0.0009832409,0.0004415386],"domain_scores_gemma":[0.9981654,0.00003547181,0.00012608609,0.0007090624,0.00020649297,0.00075747],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005850713,0.0002501633,0.00062641,0.00025440287,0.000385376,0.0003918065,0.0006119537,0.00014247489,0.0026576037],"category_scores_gemma":[0.0016533221,0.00023015593,0.00028609586,0.0011835136,0.00021227106,0.00031706452,0.00010831366,0.00018870574,0.00008575074],"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":[0.000006333591,0.00005356777,0.014177316,0.00006444001,0.0013488084,0.00012445905,0.00002716481,0.940628,0.000025484476,0.000015449634,0.0029213799,0.040607605],"study_design_scores_gemma":[0.0002850866,0.000018849722,0.0025958451,0.00010005927,0.0017786358,0.00000751194,0.000030554205,0.99466795,0.0000427384,0.000022843093,0.00019725233,0.00025266057],"about_ca_topic_score_codex":0.00042975607,"about_ca_topic_score_gemma":0.00012926212,"teacher_disagreement_score":0.92347336,"about_ca_system_score_codex":0.00015287797,"about_ca_system_score_gemma":0.00006370274,"threshold_uncertainty_score":0.9982541},"labels":[],"label_agreement":null},{"id":"W2773727367","doi":"10.1016/j.media.2017.12.007","title":"The first MICCAI challenge on PET tumor segmentation","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":140,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Cancer Institute; Agence Nationale de la Recherche","keywords":"Computer science; Segmentation; Artificial intelligence; Convolutional neural network; Pipeline (software); Deep learning; Imaging phantom; Benchmark (surveying); Machine learning; Pattern recognition (psychology); Medicine; Nuclear medicine","score_opus":0.02087583818442917,"score_gpt":0.35591176630178334,"score_spread":0.33503592811735416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773727367","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":[0.12224555,0.00019597312,0.024818206,0.8199481,0.00015996136,0.0007871184,0.000018819317,0.0003572848,0.03146903],"genre_scores_gemma":[0.98546624,0.00078920985,0.005057668,0.005636425,0.00039185595,0.0002018896,0.00006631856,0.000022228189,0.0023681526],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99825364,0.000029553205,0.00030394612,0.00030495206,0.000853761,0.00025416937],"domain_scores_gemma":[0.99802494,0.00017638148,0.00017167597,0.0011776874,0.00010048021,0.00034884573],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00066186313,0.00013240249,0.00029852,0.00009357197,0.0009564138,0.00013977283,0.00049694785,0.000044615652,0.0011526404],"category_scores_gemma":[0.0014129899,0.00007895662,0.0002688454,0.00019502976,0.000500544,0.00007090846,0.00011239402,0.00034711245,0.0001946549],"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":[0.00034162943,0.004065123,0.029338375,0.00029627612,0.005899316,0.00368319,0.00069440645,0.00000257897,0.0033298326,0.010119518,0.68591136,0.2563184],"study_design_scores_gemma":[0.004570279,0.0008755523,0.075926654,0.00057409535,0.009106786,0.00022771471,0.00059536257,0.1349132,0.0089262435,0.002729928,0.76061934,0.00093484705],"about_ca_topic_score_codex":0.00018472623,"about_ca_topic_score_gemma":0.00017033415,"teacher_disagreement_score":0.8632207,"about_ca_system_score_codex":0.00004610572,"about_ca_system_score_gemma":0.000056902572,"threshold_uncertainty_score":0.99976045},"labels":[],"label_agreement":null},{"id":"W2775432161","doi":"10.1016/j.media.2017.12.003","title":"Multi-hypothesis tracking of the tongue surface in ultrasound video recordings of normal and impaired speech","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Centre for Research on Brain Language and Music; École de Technologie Supérieure","funders":"","keywords":"Tongue; Computer science; Artificial intelligence; Robustness (evolution); Computer vision; Pattern recognition (psychology); Set (abstract data type); Speech recognition","score_opus":0.01999198382214388,"score_gpt":0.276528776163784,"score_spread":0.2565367923416401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775432161","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":[0.9569906,0.0001281671,0.04158659,0.0010176119,0.000043659125,0.0000481128,0.0000022816864,0.000012253384,0.00017075115],"genre_scores_gemma":[0.93803716,0.000048202277,0.061751153,0.00007926619,0.000016830983,8.770281e-7,2.8608852e-7,0.000004647672,0.00006156972],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984626,0.00008461244,0.00040139246,0.00029682077,0.00052613707,0.00022844328],"domain_scores_gemma":[0.9983636,0.00034996937,0.00037958712,0.00069312035,0.00010640947,0.00010732884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011620513,0.00011277233,0.00041448043,0.00012986736,0.00016869264,0.0001631106,0.0013200268,0.000079826474,0.000062572726],"category_scores_gemma":[0.0031885367,0.00007879252,0.00019042553,0.0006710612,0.00035453818,0.00060544343,0.00030692955,0.00017042157,0.0000012566138],"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":[0.000008173781,0.00013261876,0.7343006,0.000055187214,0.00023267865,0.000057095,0.0009675398,0.000021621265,0.11126214,0.0000032407593,0.0000467512,0.1529123],"study_design_scores_gemma":[0.00040993054,0.000013706526,0.61543655,0.00009888591,0.00014861453,0.000013899694,0.00009049842,0.019150505,0.36441252,0.000102172504,0.000008172879,0.00011456304],"about_ca_topic_score_codex":0.0012204209,"about_ca_topic_score_gemma":0.0010345174,"teacher_disagreement_score":0.25315037,"about_ca_system_score_codex":0.000017101,"about_ca_system_score_gemma":0.000076360855,"threshold_uncertainty_score":0.38172066},"labels":[],"label_agreement":null},{"id":"W2775469102","doi":"10.1016/j.media.2018.12.007","title":"Learning to detect chest radiographs containing pulmonary lesions using visual attention networks","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":131,"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":"Guy's and St Thomas' NHS Foundation Trust; National Medical Research Council; Medical Research Council; Centro de Investigación Biomédica en Red de Salud Mental; University College London; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Cancer Research UK; King's College London; King's University College; King's College Hospital NHS Foundation Trust","keywords":"Softmax function; Artificial intelligence; Radiography; Computer science; Convolutional neural network; Deep learning; Bounding overwatch; Pattern recognition (psychology); Chest radiograph; Nodule (geology); Radiology; Medicine","score_opus":0.017178629149785983,"score_gpt":0.33547331330847213,"score_spread":0.31829468415868617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775469102","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":[0.8376007,0.00025817254,0.15562603,0.005749913,0.0001381647,0.00031726088,0.000001098557,0.00018412141,0.00012452068],"genre_scores_gemma":[0.9875542,0.000094144416,0.0033661334,0.008239152,0.0003212749,0.000019251072,0.00009285208,0.000049428858,0.00026356702],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99688697,0.00025483436,0.0005589613,0.0006843617,0.0010414431,0.0005734103],"domain_scores_gemma":[0.9978971,0.00060563517,0.00015602112,0.00041898532,0.00019030331,0.000731979],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012721223,0.0002645801,0.0008426104,0.0012275276,0.00022199999,0.00007845804,0.00018734229,0.0002432044,0.0017413474],"category_scores_gemma":[0.0015490402,0.00024571124,0.0007407244,0.003870555,0.000115319555,0.00014836375,0.0001752456,0.00074524916,0.0001380794],"study_design_candidate":"observational","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":[0.00031705285,0.00044298326,0.778053,0.00016154912,0.0033189596,0.0015210129,0.00037232394,0.022488462,0.031000119,0.0000033889924,0.0009638798,0.16135728],"study_design_scores_gemma":[0.00082058244,0.0003689812,0.14858773,0.00042021758,0.004243428,0.00005321774,0.00043987972,0.8410237,0.00019635359,0.0000032026587,0.0035219756,0.0003207291],"about_ca_topic_score_codex":0.00075694546,"about_ca_topic_score_gemma":0.000058946993,"teacher_disagreement_score":0.81853527,"about_ca_system_score_codex":0.0002160308,"about_ca_system_score_gemma":0.00016044047,"threshold_uncertainty_score":0.9999995},"labels":[],"label_agreement":null},{"id":"W2776074204","doi":"10.1016/j.media.2017.12.006","title":"Fast elastic registration of soft tissues under large deformations","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Iterative closest point; Supine position; Computer science; Artificial intelligence; Focus (optics); Position (finance); Computer vision; Image registration; Segmentation; Medicine; Image (mathematics); Surgery; Point cloud","score_opus":0.015268306260974413,"score_gpt":0.33222229964755084,"score_spread":0.3169539933865764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2776074204","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":[0.00091681496,0.000032298925,0.99291307,0.003051985,0.00006169577,0.00007622402,0.000006791623,0.00012745986,0.002813667],"genre_scores_gemma":[0.8423963,0.00005030822,0.15577157,0.0007221002,0.00007238461,0.000021973594,0.000055951954,0.000007888222,0.0009014793],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997713,0.000091259106,0.0005327467,0.0002723653,0.0011605521,0.00023002754],"domain_scores_gemma":[0.99786896,0.00013354392,0.00044122708,0.0010887785,0.00022452242,0.00024299849],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009549281,0.00011476278,0.00030154118,0.00025999267,0.00030837802,0.00027744996,0.0014086025,0.00009524708,0.0010038487],"category_scores_gemma":[0.0019149806,0.000095813084,0.00017670981,0.00046401608,0.00031257732,0.0012583038,0.00030411914,0.0001658551,0.000071487964],"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":[0.000026268921,0.0024528913,0.018485203,0.00042734444,0.004423626,0.00044347043,0.005361471,0.00030730604,0.010965745,0.06624937,0.05256363,0.8382937],"study_design_scores_gemma":[0.0010882952,0.00013742252,0.025010908,0.00012701815,0.0010413572,0.000018637373,0.00037126688,0.9226884,0.040263113,0.007775109,0.000942374,0.0005360945],"about_ca_topic_score_codex":0.00020860024,"about_ca_topic_score_gemma":0.00023981504,"teacher_disagreement_score":0.9223811,"about_ca_system_score_codex":0.000029020126,"about_ca_system_score_gemma":0.00010257042,"threshold_uncertainty_score":0.99990934},"labels":[],"label_agreement":null},{"id":"W2783775739","doi":"10.1016/j.media.2018.09.002","title":"Joint registration and synthesis using a probabilistic model for alignment of MRI and histological sections","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":38,"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 on Aging; Engineering and Physical Sciences Research Council; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, San Diego; National Institutes of Health; Genentech; National Institute of Neurological Disorders and Stroke; IXICO; Servier; Eisai; DoD Alzheimer's Disease Neuroimaging Initiative; Pfizer; Biogen; BioClinica; National Institute of Mental Health; Neurosciences Research Foundation; National Center for Research Resources; F. Hoffmann-La Roche; University of Southern California; Wellcome Trust; National Institute of Diabetes and Digestive and Kidney Diseases; Synarc; Medpace; European Research Council; Northern California Institute for Research and Education; Massachusetts General Hospital; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Novartis Pharmaceuticals Corporation; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Artificial intelligence; Image registration; Computer science; Probabilistic logic; Computer vision; Rigid transformation; Robustness (evolution); Mutual information; Pattern recognition (psychology); Metric (unit); Inference; Affine transformation; Bayesian inference; Real-time MRI; Bayesian probability; Image (mathematics); Magnetic resonance imaging; Mathematics","score_opus":0.04816367954821354,"score_gpt":0.3234920483452383,"score_spread":0.27532836879702477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783775739","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":[0.011338588,0.000038858718,0.98710287,0.0011796459,0.000017349303,0.00018424338,0.0000048406228,0.00005749889,0.00007611708],"genre_scores_gemma":[0.40835628,0.00002761127,0.5912814,0.00021644324,0.000026093967,0.000047471574,0.0000025985523,0.0000033879635,0.0000386871],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985542,0.00008830945,0.00040262184,0.00036219714,0.00044592467,0.00014672961],"domain_scores_gemma":[0.9990189,0.00018444886,0.00016086425,0.0002667342,0.00017956187,0.00018946124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008583143,0.00009582009,0.00029451126,0.00019236145,0.0001148801,0.000053155913,0.00017947925,0.00008127541,0.000053450065],"category_scores_gemma":[0.0017587756,0.000077152916,0.00008588875,0.0004220397,0.0006118488,0.00019953592,0.00011998654,0.00006433065,4.469036e-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":[0.0002056513,0.0043495307,0.0025825999,0.0018943681,0.0058063706,0.00015949474,0.0126018645,0.0012514793,0.25387087,0.04694279,0.017026372,0.65330863],"study_design_scores_gemma":[0.00012637228,0.00007458223,0.00016578249,0.000022095277,0.0003890656,0.000009801151,0.00002499703,0.9828198,0.012983058,0.0032962514,0.000007959025,0.00008025944],"about_ca_topic_score_codex":0.000089791814,"about_ca_topic_score_gemma":0.00004492567,"teacher_disagreement_score":0.9815683,"about_ca_system_score_codex":0.000048068046,"about_ca_system_score_gemma":0.00007593886,"threshold_uncertainty_score":0.31462047},"labels":[],"label_agreement":null},{"id":"W2790348354","doi":"10.1016/j.media.2018.03.001","title":"Rapid fully automatic segmentation of subcortical brain structures by shape-constrained surface adaptation","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research; European Commission","keywords":"Segmentation; Artificial intelligence; Adaptation (eye); Computer science; Computer vision; Surface (topology); Pattern recognition (psychology); Brain morphometry; Neuroscience; Mathematics; Psychology; Geometry; Magnetic resonance imaging; Medicine","score_opus":0.012098587567837887,"score_gpt":0.2926726285358938,"score_spread":0.28057404096805594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790348354","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":[0.05565547,0.00007548107,0.9407386,0.002713066,0.00007761084,0.00019877916,0.00001274622,0.0002893768,0.0002388543],"genre_scores_gemma":[0.5520454,0.000028415778,0.44570243,0.0019345316,0.00006268285,0.000013854615,0.00011533694,0.000012591494,0.000084734485],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959719,0.0004241347,0.0009196461,0.0005390149,0.0017926125,0.0003526918],"domain_scores_gemma":[0.99781436,0.0005169261,0.0003439903,0.0005548545,0.00036411523,0.00040578248],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012504867,0.0002186893,0.0004963006,0.00031661493,0.00011026646,0.00012994824,0.0009087409,0.00015806724,0.006909135],"category_scores_gemma":[0.0016780033,0.00018884914,0.00022540113,0.002056629,0.00083205453,0.000663831,0.00016549166,0.00020552891,0.0000462064],"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":[0.000016479398,0.00025100057,0.00050160085,0.00007099822,0.0008682862,0.000043995613,0.0016985958,0.000009591903,0.11733787,0.00067428994,0.024601793,0.8539255],"study_design_scores_gemma":[0.0006220159,0.00023986094,0.0014428579,0.000022932498,0.00032424048,0.000008280705,0.0002265729,0.83856744,0.15753616,0.0007192859,0.000056406,0.00023391886],"about_ca_topic_score_codex":0.00012679519,"about_ca_topic_score_gemma":0.000028920665,"teacher_disagreement_score":0.8536916,"about_ca_system_score_codex":0.000058488098,"about_ca_system_score_gemma":0.00019020094,"threshold_uncertainty_score":0.9939987},"labels":[],"label_agreement":null},{"id":"W2791687065","doi":"10.1016/j.media.2018.03.004","title":"Riemannian metric optimization on surfaces (RMOS) for intrinsic brain mapping in the Laplace–Beltrami embedding space","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":false,"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; National Institute of Mental Health; Canadian Institutes of Health Research; Foundation of the American Society of Neuroradiology; National Institutes of Health; BioClinica; National Eye Institute; National Institute on Aging; Alzheimer's Association; AbbVie; Biogen; American Society of Neuroradiology; Northern California Institute for Research and Education; Alzheimer's Drug Discovery Foundation; U.S. Department of Defense","keywords":"Embedding; Mathematics; Surface (topology); Riemannian geometry; Metric (unit); Polygon mesh; Artificial intelligence; Mathematical analysis; Topology (electrical circuits); Computer science; Algorithm; Geometry; Combinatorics","score_opus":0.04481816951865586,"score_gpt":0.39064356498760916,"score_spread":0.3458253954689533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791687065","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":[0.029464848,0.000046320667,0.92806625,0.04079919,0.00002068398,0.000501301,0.000007019113,0.00011532663,0.0009790343],"genre_scores_gemma":[0.8735954,0.00008656274,0.11900537,0.006399411,0.0002470413,0.0001388042,0.00009977508,0.00002786607,0.0003997606],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984362,0.0000919804,0.00032210982,0.00038322745,0.0004916364,0.0002748175],"domain_scores_gemma":[0.99844813,0.0007316454,0.000110629946,0.00045832962,0.00013159338,0.00011965613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009907931,0.00014684266,0.0003460532,0.00063625124,0.00018654551,0.000044314176,0.00024186492,0.00008219315,0.0001919019],"category_scores_gemma":[0.0022900852,0.00010355937,0.00017623347,0.0037099712,0.00019086515,0.00008540247,0.0000405819,0.00027312967,0.000012743237],"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":[0.00167313,0.009503272,0.13222064,0.001480782,0.007102303,0.001509689,0.016666116,0.08589549,0.028837796,0.032306124,0.30182648,0.38097817],"study_design_scores_gemma":[0.0012598844,0.00030438456,0.009269896,0.00014143609,0.0008850341,0.000022910886,0.0006600511,0.96275324,0.0015118124,0.0007747775,0.022134796,0.00028179423],"about_ca_topic_score_codex":0.000052331827,"about_ca_topic_score_gemma":0.000029521709,"teacher_disagreement_score":0.87685776,"about_ca_system_score_codex":0.000057277608,"about_ca_system_score_gemma":0.000040498384,"threshold_uncertainty_score":0.42230284},"labels":[],"label_agreement":null},{"id":"W2793804994","doi":"10.1016/j.media.2018.02.002","title":"Multiscale deep neural network based analysis of FDG-PET images for the early diagnosis of Alzheimer’s disease","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":203,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Pacific Alzheimer Research Foundation; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; Eisai; U.S. Department of Defense; Eli Lilly and Company; Lundbeckfonden; Michael Smith Health Research BC; AbbVie; Fondation Brain Canada; DoD Alzheimer's Disease Neuroimaging Initiative; Natural Sciences and Engineering Research Council of Canada; Pfizer; BioClinica; Biogen; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; F. Hoffmann-La Roche; Roche; Merck; Alzheimer's Drug Discovery Foundation; Takeda Pharmaceutical Company; Fujirebio Europe; Alzheimer's Association; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics","keywords":"Dementia; Prodromal Stage; Positron emission tomography; Neuroimaging; Disease; Cognition; Psychology; Medicine; Cognitive impairment; Alzheimer's disease; Neuroscience; Pathology","score_opus":0.020387958468980453,"score_gpt":0.34946875540623984,"score_spread":0.3290807969372594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793804994","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":[0.8501457,0.001791349,0.14109127,0.005440086,0.00007285296,0.00090336567,0.00021965832,0.00003743933,0.00029830198],"genre_scores_gemma":[0.99655664,0.00011507712,0.0016771649,0.0007716707,0.00024007105,0.0002427008,0.00024840835,0.000019581894,0.00012867211],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9966567,0.00023900141,0.00068951,0.00043171362,0.0014754771,0.000507577],"domain_scores_gemma":[0.9963088,0.0012983764,0.00023917307,0.00065978046,0.0009370694,0.0005568244],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001321888,0.00021399799,0.0009769719,0.0006731075,0.0001589206,0.00003270712,0.00034770212,0.000059526137,0.006761436],"category_scores_gemma":[0.0016567011,0.00013512246,0.0016433295,0.0041580577,0.001140963,0.000098068085,0.0001204283,0.00017894909,0.00001087368],"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":[0.0004907454,0.0006823079,0.94960225,0.00005393823,0.023233512,0.00007895025,0.00006211246,0.00014541051,0.00015755148,0.000004977003,0.0022515797,0.023236647],"study_design_scores_gemma":[0.00089447654,0.00026819497,0.61957586,0.000022783366,0.072725356,3.457722e-7,0.00005118949,0.30445895,0.001779495,0.000010697685,0.00012822244,0.00008443406],"about_ca_topic_score_codex":0.000486078,"about_ca_topic_score_gemma":0.00023302744,"teacher_disagreement_score":0.33002642,"about_ca_system_score_codex":0.000017168513,"about_ca_system_score_gemma":0.00011217887,"threshold_uncertainty_score":0.9941465},"labels":[],"label_agreement":null},{"id":"W2799738340","doi":"10.1016/j.media.2019.02.009","title":"Constrained-CNN losses for weakly supervised segmentation","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":282,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Kahnawake Education Center","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Leverage (statistics); Computer science; Segmentation; Iterated function; Mathematical optimization; Differentiable function; Artificial intelligence; Dual (grammatical number); Pixel; Machine learning; Mathematics","score_opus":0.011301270334979404,"score_gpt":0.29366071320176274,"score_spread":0.28235944286678333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799738340","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":[0.01911923,0.000040067433,0.9748856,0.004698119,0.000058050493,0.00029589748,0.000007144426,0.00012233858,0.0007735765],"genre_scores_gemma":[0.7087473,0.000053472035,0.28799394,0.0021746291,0.000118398246,0.00014613186,0.00011545665,0.000012007006,0.00063863286],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985665,0.00004173299,0.0002776969,0.000422414,0.00044954888,0.00024208437],"domain_scores_gemma":[0.99867564,0.00041158154,0.000085852924,0.00052381336,0.0001273703,0.00017574953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024266695,0.00011272532,0.00024526045,0.0001536091,0.00008571257,0.000095251584,0.0006477513,0.000055927165,0.0005673956],"category_scores_gemma":[0.00014077467,0.00009848409,0.00020381801,0.0014250894,0.00008720926,0.0004222263,0.00010554189,0.000096449825,0.00021149944],"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":[0.00004624775,0.00071386324,0.019543186,0.00016641094,0.002471037,0.000067333065,0.000680828,0.0044521727,0.09364945,0.08169131,0.011488763,0.7850294],"study_design_scores_gemma":[0.0006435411,0.00005836511,0.0014455513,0.0000100065745,0.00028829082,0.000004990115,0.000059225444,0.98479533,0.0056707864,0.0027709794,0.0040119784,0.00024093821],"about_ca_topic_score_codex":0.000009539893,"about_ca_topic_score_gemma":0.000009577391,"teacher_disagreement_score":0.98034316,"about_ca_system_score_codex":0.000025376805,"about_ca_system_score_gemma":0.00005594831,"threshold_uncertainty_score":0.6212584},"labels":[],"label_agreement":null},{"id":"W2803806607","doi":"10.1016/j.media.2018.05.007","title":"Quantifying the uncertainty in model parameters using Gaussian process-based Markov chain Monte Carlo in cardiac electrophysiology","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiac electrophysiology and arrhythmias","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Pioneer Hi-Bred; National Heart, Lung, and Blood Institute; Foundation for the National Institutes of Health; National Institutes of Health; National Science Foundation","keywords":"Markov chain Monte Carlo; Surrogate model; Posterior probability; Computer science; Sampling (signal processing); Importance sampling; Bayesian inference; Gaussian process; Inference; Mathematical optimization; Algorithm; Approximate inference; Monte Carlo method; Bayesian probability; Gaussian; Mathematics; Artificial intelligence; Machine learning; Statistics","score_opus":0.02091680177372739,"score_gpt":0.3267277054927146,"score_spread":0.3058109037189872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803806607","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":[0.9931398,0.0002968058,0.003406357,0.0026240703,0.000057876372,0.00030115424,0.000006244755,0.000034043478,0.00013363121],"genre_scores_gemma":[0.99689806,0.00007375201,0.0007585987,0.0019129685,0.00021062444,0.000058308597,0.000029157423,0.000025095513,0.000033447635],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970126,0.00054278574,0.0005470503,0.00062193745,0.00050744525,0.00076817465],"domain_scores_gemma":[0.9987306,0.00026570645,0.00012360302,0.00054691563,0.00012986126,0.00020333297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010477504,0.00028067298,0.0011527496,0.00061441533,0.0001415943,0.000017460785,0.00021272423,0.00027803043,0.00009455688],"category_scores_gemma":[0.0007205387,0.00019108932,0.00059612776,0.0025531002,0.00075786514,0.00007460038,0.00005131616,0.00084850605,0.000009625094],"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":[0.006445729,0.0010073018,0.15032914,0.00044623172,0.0070908573,0.0045430185,0.0035037075,0.6257618,0.182547,0.00014593822,0.00057468604,0.017604541],"study_design_scores_gemma":[0.0008632727,0.0001741288,0.014803337,0.00007524892,0.0009711641,0.000012618179,0.00017779761,0.9812789,0.0013203017,0.000110690155,0.0000059911918,0.00020657635],"about_ca_topic_score_codex":0.0016458255,"about_ca_topic_score_gemma":0.0014838141,"teacher_disagreement_score":0.35551703,"about_ca_system_score_codex":0.00020266575,"about_ca_system_score_gemma":0.00051090587,"threshold_uncertainty_score":0.77923965},"labels":[],"label_agreement":null},{"id":"W2803866553","doi":"10.1016/j.media.2018.05.006","title":"Superpixel and multi-atlas based fusion entropic model for the segmentation of X-ray images","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal","funders":"","keywords":"Artificial intelligence; Segmentation; Computer science; Atlas (anatomy); Pattern recognition (psychology); Computer vision; Pruning; Image segmentation; Medicine","score_opus":0.011840635446570899,"score_gpt":0.2703603444348402,"score_spread":0.2585197089882693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803866553","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":[0.048096236,0.00036800592,0.95036507,0.00092270086,0.000041525876,0.000090366004,0.000021671045,0.000056132107,0.00003830924],"genre_scores_gemma":[0.9646813,0.00021521347,0.034425743,0.00026359392,0.00011096739,0.000027673808,0.000053009135,0.000015840165,0.00020662525],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998764,0.00004097811,0.00033009076,0.00020092425,0.00045629608,0.00020773645],"domain_scores_gemma":[0.9991138,0.00029573592,0.00004375645,0.00024686632,0.00013076935,0.00016908302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046479213,0.00013342155,0.0003199794,0.00019841657,0.000109401306,0.000034540277,0.00018187865,0.00006808029,0.0005061354],"category_scores_gemma":[0.00044784433,0.00008636205,0.00022392397,0.0005507823,0.00035073617,0.000085686115,0.0000313947,0.0001162189,0.0000068587074],"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":[0.000069521106,0.00080007914,0.043267224,0.0010823167,0.011669772,0.000032724958,0.0039564758,0.14997742,0.34992263,0.00005766175,0.027221594,0.41194257],"study_design_scores_gemma":[0.00054782344,0.000013122866,0.001036135,0.000017603208,0.0017761328,2.6137286e-7,0.00011015178,0.9897492,0.0065485896,0.000014982751,0.00009292629,0.00009305782],"about_ca_topic_score_codex":0.00007395295,"about_ca_topic_score_gemma":0.000051150928,"teacher_disagreement_score":0.9165851,"about_ca_system_score_codex":0.000016559861,"about_ca_system_score_gemma":0.000024418665,"threshold_uncertainty_score":0.55418277},"labels":[],"label_agreement":null},{"id":"W2803954248","doi":"10.1016/j.media.2018.05.005","title":"Automated comprehensive Adolescent Idiopathic Scoliosis assessment using MVC-Net","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Scoliosis diagnosis and treatment","field":"Medicine","cited_by":156,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"Government of Ontario","keywords":"Idiopathic scoliosis; Scoliosis; Computer science; Net (polyhedron); Artificial intelligence; Medicine; Physical medicine and rehabilitation; Machine learning; Medical physics; Mathematics; Surgery","score_opus":0.03776483629591423,"score_gpt":0.3889479305121381,"score_spread":0.3511830942162239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803954248","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":[0.98705834,0.0017325701,0.0061064158,0.003020475,0.00028045024,0.0005284633,0.000012322781,0.0004913529,0.0007696011],"genre_scores_gemma":[0.9914061,0.00024056731,0.0032297606,0.0043610088,0.0006163068,0.000046675308,0.000040495084,0.000035726127,0.000023397935],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99623173,0.00023634796,0.0007140626,0.0006666198,0.0015848458,0.00056640647],"domain_scores_gemma":[0.9974159,0.000051812414,0.00020587767,0.00070081215,0.0008186621,0.0008069079],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047998677,0.00034736126,0.0011351295,0.0006935775,0.00023838991,0.000089906636,0.0002047804,0.00022205945,0.0018263094],"category_scores_gemma":[0.0003422159,0.00026818507,0.00063776836,0.0024413406,0.00045323544,0.00011491958,0.00016067,0.00032762648,0.00022113297],"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":[0.00019604502,0.0046798917,0.9467132,0.00040551147,0.015654936,0.0027760328,0.00036106314,0.000028207292,0.009922179,0.000069097405,0.012755957,0.0064378893],"study_design_scores_gemma":[0.00261973,0.00051415607,0.7568313,0.0012624352,0.012661001,0.00006914485,0.00020267132,0.22023757,0.0045031114,0.000010542778,0.00074414205,0.0003442043],"about_ca_topic_score_codex":0.0005227112,"about_ca_topic_score_gemma":0.00010188124,"teacher_disagreement_score":0.22020936,"about_ca_system_score_codex":0.00040447104,"about_ca_system_score_gemma":0.00039140106,"threshold_uncertainty_score":0.99997705},"labels":[],"label_agreement":null},{"id":"W2806788401","doi":"10.1016/j.media.2018.05.010","title":"A deep learning approach for real time prostate segmentation in freehand ultrasound guided biopsy","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Segmentation; Sørensen–Dice coefficient; Prostate biopsy; Deep learning; Convolutional neural network; Hausdorff distance; Ultrasound; Pattern recognition (psychology); Computer vision; Image segmentation; Prostate; Radiology; Medicine; Cancer","score_opus":0.012907864425345618,"score_gpt":0.30040093726861444,"score_spread":0.2874930728432688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806788401","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":[0.023001745,0.000018948549,0.9754201,0.00037631215,0.000014911385,0.00029265392,0.0000017391382,0.000111647496,0.000761947],"genre_scores_gemma":[0.21481967,0.000055614408,0.78358024,0.00021586336,0.00017921216,0.00028065403,0.00020288963,0.000015681802,0.00065019075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983132,0.000099720724,0.00035419513,0.0005135145,0.00040523734,0.00031416392],"domain_scores_gemma":[0.99894994,0.00026258308,0.00013375877,0.0003631082,0.0001359453,0.00015468715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054407644,0.00012413542,0.00024290633,0.00024255332,0.00017415638,0.0000982695,0.0005184821,0.00006548913,0.00008805086],"category_scores_gemma":[0.0003519768,0.00011060286,0.00010893413,0.0023668855,0.00017640127,0.00034544538,0.000106753265,0.00013815565,0.000040887888],"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":[0.00019605829,0.001992801,0.05373443,0.00016997347,0.0025730168,0.00016861048,0.012977527,0.05576872,0.36529052,0.0047520017,0.009879477,0.49249685],"study_design_scores_gemma":[0.00040621066,0.000048777885,0.0016005534,0.0000041148396,0.00010485915,0.000011114344,0.0000319639,0.9952989,0.0015282322,0.0006990407,0.00012643624,0.00013979175],"about_ca_topic_score_codex":0.000059505783,"about_ca_topic_score_gemma":0.000045285607,"teacher_disagreement_score":0.9395302,"about_ca_system_score_codex":0.00005631808,"about_ca_system_score_gemma":0.000031414984,"threshold_uncertainty_score":0.45102537},"labels":[],"label_agreement":null},{"id":"W2810924486","doi":"10.1016/j.media.2018.07.001","title":"Synthesizing retinal and neuronal images with generative adversarial nets","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":214,"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":"Chinese Government Scholarship; China Scholarship Council; Government of Jiangxi Province","keywords":"Computer science; Artificial intelligence; Annotation; Set (abstract data type); Generative grammar; Image (mathematics); Pattern recognition (psychology); Computer vision","score_opus":0.007527008097328543,"score_gpt":0.2789910835645772,"score_spread":0.27146407546724866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810924486","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":[0.8664334,0.0003571291,0.09935425,0.022953007,0.00006807947,0.00016315772,0.000013081176,0.00015517282,0.010502713],"genre_scores_gemma":[0.9806896,0.000099310535,0.01485429,0.0022466956,0.0008310125,0.000007784129,0.000041252006,0.000025570374,0.0012044861],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99751985,0.00016410704,0.0003438257,0.00059114024,0.0010042931,0.00037675956],"domain_scores_gemma":[0.9985039,0.00017084801,0.0001188968,0.00034486083,0.00032801088,0.0005334881],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00056799164,0.00024515268,0.0006882161,0.00039984635,0.00022338379,0.00009788508,0.00013434351,0.00008900345,0.0020474317],"category_scores_gemma":[0.00084819086,0.00016647845,0.0002582573,0.001208471,0.0011493502,0.00015432182,0.00008352619,0.0003441422,0.0000532244],"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":[0.0039858557,0.0014115158,0.67461133,0.00029098775,0.030371517,0.009852442,0.0028751022,0.000033266188,0.09119135,0.0002408398,0.03184532,0.1532905],"study_design_scores_gemma":[0.011009389,0.004857241,0.44303045,0.0010775595,0.09240039,0.0022178001,0.0027922627,0.32717404,0.0916795,0.0002736388,0.020785628,0.002702103],"about_ca_topic_score_codex":0.0002497398,"about_ca_topic_score_gemma":0.000057167083,"teacher_disagreement_score":0.32714078,"about_ca_system_score_codex":0.000028989889,"about_ca_system_score_gemma":0.00012844807,"threshold_uncertainty_score":0.9988648},"labels":[],"label_agreement":null},{"id":"W2888400665","doi":"10.1016/j.media.2018.08.004","title":"Algorithms for left atrial wall segmentation and thickness – Evaluation on an open-source CT and MRI image database","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Centre For Medical Engineering, King’s College London; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Canadian Institutes of Health Research; King's College London; British Heart Foundation; Wellcome Trust","keywords":"Segmentation; Algorithm; Artificial intelligence; Cardiac imaging; Computer science; Magnetic resonance imaging; Modality (human–computer interaction); Limiting; Atrial fibrillation; Left atrium; Database; Medical imaging; Medicine; Radiology","score_opus":0.030757148990069972,"score_gpt":0.3879660480808898,"score_spread":0.3572088990908198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888400665","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":[0.49086827,0.0005789053,0.49482378,0.010174878,0.00035495867,0.0018755685,0.00020653068,0.000115541814,0.0010015615],"genre_scores_gemma":[0.86699384,0.0005781751,0.112478495,0.008333888,0.003704092,0.000109655026,0.0068780575,0.000109856745,0.00081394817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978236,0.0002242074,0.00031302153,0.00053322216,0.00087791984,0.00022806147],"domain_scores_gemma":[0.99811274,0.0005483724,0.000099509176,0.00040469016,0.00042617336,0.00040852168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002825343,0.0001697896,0.00046288173,0.00024252477,0.00019831922,0.00020623239,0.00011978788,0.000054065007,0.0005091729],"category_scores_gemma":[0.0034715282,0.00014022185,0.00012968642,0.0003158664,0.00033419125,0.00035197503,0.00012633168,0.00016113301,0.000016429933],"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":[0.0029232006,0.0016606698,0.08862677,0.00046923273,0.006534267,0.0005111375,0.0041599837,0.000049682443,0.018582856,0.000099587356,0.04975169,0.8266309],"study_design_scores_gemma":[0.01872979,0.0016739919,0.041293,0.00023383881,0.029180158,0.00023758497,0.0012434769,0.89366335,0.0055955625,0.0002479031,0.0072534974,0.00064785586],"about_ca_topic_score_codex":0.0005639596,"about_ca_topic_score_gemma":0.00015283175,"teacher_disagreement_score":0.89361364,"about_ca_system_score_codex":0.000052483363,"about_ca_system_score_gemma":0.000138877,"threshold_uncertainty_score":0.5718081},"labels":[],"label_agreement":null},{"id":"W2888443510","doi":"10.1016/j.media.2018.08.005","title":"Spine-GAN: Semantic segmentation of multiple spinal structures","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":215,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Segmentation; Computer science; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Concatenation (mathematics); Computer vision; Mathematics","score_opus":0.0074848948427753085,"score_gpt":0.27293141559568,"score_spread":0.2654465207529047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888443510","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":[0.4736246,0.0003186875,0.5240651,0.00034660785,0.00015287008,0.00005241117,0.0000072867183,0.00017081019,0.0012616308],"genre_scores_gemma":[0.994487,0.00007160411,0.00482116,0.00015091273,0.00030451978,0.0000042614724,0.000051927076,0.000016650476,0.000091976624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981835,0.000050147217,0.00046839923,0.00022681421,0.000806484,0.00026466436],"domain_scores_gemma":[0.99919164,0.00004370778,0.000066171866,0.00030134263,0.00012645774,0.00027070052],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032892104,0.00016216589,0.00046280306,0.0003962535,0.000056885958,0.00002851942,0.00024734045,0.00009116081,0.0032583412],"category_scores_gemma":[0.0005087292,0.00013278167,0.00029305948,0.0016168349,0.00033408968,0.0001046053,0.000030330131,0.00018263393,0.000064535765],"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":[0.00004812781,0.0005075666,0.1954446,0.001372695,0.022723366,0.00044158773,0.0020622967,0.0054631107,0.28657568,0.0002170637,0.021186633,0.46395728],"study_design_scores_gemma":[0.00050263916,0.000049909126,0.020516118,0.000055824596,0.0024868925,0.00000555293,0.00015920421,0.9219974,0.05333039,0.0001496981,0.0004928932,0.0002534305],"about_ca_topic_score_codex":0.00016724935,"about_ca_topic_score_gemma":0.00009518809,"teacher_disagreement_score":0.9165343,"about_ca_system_score_codex":0.0000239781,"about_ca_system_score_gemma":0.000021850987,"threshold_uncertainty_score":0.9976528},"labels":[],"label_agreement":null},{"id":"W2889609823","doi":"10.1016/j.media.2018.09.001","title":"Direct delineation of myocardial infarction without contrast agents using a joint motion feature learning architecture","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":127,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Computer vision; Feature (linguistics); Pixel; Pattern recognition (psychology); Region of interest; Discriminative model; Feature extraction; Optical flow; Kinematics; Image (mathematics); Physics","score_opus":0.02144859605931108,"score_gpt":0.333218146903022,"score_spread":0.3117695508437109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889609823","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":[0.27313533,0.000027805916,0.7216582,0.004088968,0.000039980205,0.00021989757,0.000005656379,0.0001259146,0.00069827837],"genre_scores_gemma":[0.95843077,0.00004762811,0.039770506,0.00070120965,0.0005991578,0.000018044531,0.00015915616,0.000019172705,0.0002543709],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979967,0.0001469765,0.00043019562,0.0003316037,0.0008677097,0.00022683098],"domain_scores_gemma":[0.9986854,0.000052297702,0.0002169004,0.0003049661,0.0004314864,0.000308937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007373748,0.00015849095,0.00057266327,0.00039054052,0.00013396522,0.00002140133,0.00009419565,0.00019189135,0.00079461036],"category_scores_gemma":[0.0017604935,0.00012459472,0.0003430064,0.0011834543,0.0003684968,0.00006590612,0.00005453473,0.00047271562,0.000010626516],"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":[0.00041299104,0.0011015278,0.19970742,0.00032611753,0.006513577,0.000078401565,0.0014382609,0.0004838091,0.5569834,0.00007297349,0.014245101,0.21863641],"study_design_scores_gemma":[0.0016293913,0.00029942644,0.052699883,0.00035020747,0.007683589,0.00009065512,0.00012591123,0.8933626,0.033565264,0.00008311688,0.009790415,0.00031956538],"about_ca_topic_score_codex":0.00030120582,"about_ca_topic_score_gemma":0.000021374417,"teacher_disagreement_score":0.8928788,"about_ca_system_score_codex":0.000066681496,"about_ca_system_score_gemma":0.00008641282,"threshold_uncertainty_score":0.8700426},"labels":[],"label_agreement":null},{"id":"W2890139949","doi":"10.1016/j.media.2019.101552","title":"Generative adversarial network in medical imaging: A review","year":2019,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":1852,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Philips (Canada); University of Saskatchewan","funders":"","keywords":"Adversarial system; Computer science; Discriminator; Artificial intelligence; Generative grammar; Consistency (knowledge bases); Machine learning; Image translation; Segmentation; Domain (mathematical analysis); Image (mathematics); Translation (biology); Adaptation (eye); Medical imaging; Deep learning; Mathematics","score_opus":0.02797709482192573,"score_gpt":0.36800618248329203,"score_spread":0.3400290876613663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890139949","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.538938e-9,0.6523762,0.34369504,0.0019003688,0.0007967545,0.0003939196,0.0000035249388,0.00007762618,0.00075656106],"genre_scores_gemma":[3.9361643e-7,0.98970515,0.00470129,0.003613498,0.0014432351,0.0001888014,0.000098987526,0.000035106255,0.00021355346],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913112,0.0015971193,0.0017491216,0.0014770558,0.003118228,0.00074729556],"domain_scores_gemma":[0.9961624,0.00074673764,0.0006832541,0.0016599699,0.00015120384,0.00059641514],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004195503,0.00061191735,0.004240989,0.0007069933,0.000083435385,0.00014548318,0.0033563587,0.000570989,0.0032509097],"category_scores_gemma":[0.0018185297,0.0004730886,0.0018966753,0.008316054,0.00021241728,0.00042218296,0.0011237294,0.0017648537,0.000617102],"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":[8.244154e-7,0.000034373286,0.000006664361,0.0050234837,0.00080977095,0.00053035334,0.000015115462,0.0000042982742,3.9976573e-9,0.000082863044,0.024344208,0.96914804],"study_design_scores_gemma":[0.00020485788,0.0000141584815,0.000001718492,0.023526844,0.004485098,0.000071857925,0.0000011024828,0.05479938,5.0260947e-8,0.00006791797,0.9163786,0.00044838764],"about_ca_topic_score_codex":0.00016497457,"about_ca_topic_score_gemma":0.00021059571,"teacher_disagreement_score":0.96869963,"about_ca_system_score_codex":0.00051635195,"about_ca_system_score_gemma":0.0023134262,"threshold_uncertainty_score":0.9997721},"labels":[],"label_agreement":null},{"id":"W2892938835","doi":"10.1016/j.media.2018.09.005","title":"Automatic grading of prostate cancer in digitized histopathology images: Learning from multiple experts","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":177,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; Richmond Hospital; Vancouver General Hospital; BC Cancer Agency; University of British Columbia","funders":"Canadian Institutes of Health Research; Prostate Cancer Canada","keywords":"Grading (engineering); Histopathology; Artificial intelligence; Prostate cancer; Computer science; Computer vision; Prostate; Pattern recognition (psychology); Medicine; Medical physics; Cancer; Pathology; Internal medicine; Biology","score_opus":0.010282521718145456,"score_gpt":0.2790481769492846,"score_spread":0.2687656552311391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892938835","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":[0.57407963,0.00024093581,0.42449048,0.0006080413,0.00019617802,0.000078091914,0.0000031161737,0.00014213042,0.00016139053],"genre_scores_gemma":[0.98735905,0.000078259705,0.012138971,0.00014749417,0.00009886085,0.000051448595,0.0000054917673,0.000010114406,0.00011031121],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793553,0.000253992,0.00049161137,0.00048030066,0.0005461574,0.000292386],"domain_scores_gemma":[0.99882025,0.00031452652,0.00022422287,0.0004054414,0.00011099547,0.00012459052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005227965,0.00013469355,0.00046711272,0.00045647696,0.000078510275,0.000050498114,0.0005539363,0.000089256435,0.0007168854],"category_scores_gemma":[0.00082784327,0.00012171533,0.00014542624,0.0014263034,0.00032138047,0.00040461565,0.00021073449,0.00020448906,0.000015389063],"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":[0.000040056202,0.00019569091,0.26089963,0.00005305672,0.00044065824,0.00037378585,0.014187894,0.00035633106,0.033561256,0.000020145684,0.00085567066,0.6890158],"study_design_scores_gemma":[0.00067361526,0.00006506781,0.031332236,0.00007365064,0.00012712028,0.000003431756,0.00014919392,0.94927645,0.017472776,0.00038299925,0.00027005485,0.00017342],"about_ca_topic_score_codex":0.003235901,"about_ca_topic_score_gemma":0.0013242096,"teacher_disagreement_score":0.94892013,"about_ca_system_score_codex":0.000183668,"about_ca_system_score_gemma":0.00010420291,"threshold_uncertainty_score":0.7849392},"labels":[],"label_agreement":null},{"id":"W2894870703","doi":"10.1016/j.media.2018.09.006","title":"A hybrid camera- and ultrasound-based approach for needle localization and tracking using a 3D motorized curvilinear ultrasound probe","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Soft Robotics and Applications","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Ultrasound; 3D ultrasound; Computer vision; Artificial intelligence; Computer science; Tracking (education); Kalman filter; Biomedical engineering; Medicine; Radiology","score_opus":0.01376895410654164,"score_gpt":0.2618212940485883,"score_spread":0.24805233994204665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894870703","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":[0.08683653,0.00015263911,0.91252863,0.000030633964,0.00002220276,0.00024619445,0.000022916185,0.00010252766,0.000057719768],"genre_scores_gemma":[0.85183245,0.00004166724,0.14754477,0.00011174402,0.0002059995,0.00005373858,0.0001695378,0.000030654766,0.000009444538],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989427,0.000024177061,0.00027490372,0.00028592962,0.00024047299,0.00023184299],"domain_scores_gemma":[0.9991806,0.0002613656,0.000045533736,0.00019432147,0.00013005086,0.00018809197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030596435,0.00015751104,0.00029960132,0.00016791365,0.00018767758,0.000120501456,0.00009218862,0.00007887809,0.00006424861],"category_scores_gemma":[0.00041895386,0.00014842446,0.00008513625,0.0005876097,0.0002209839,0.000101561454,0.000013543975,0.000105073545,0.0000011939003],"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":[0.00017713252,0.0015598346,0.07884842,0.0025331012,0.008287429,0.000031730964,0.0045916843,0.4213182,0.4382455,0.0008833809,0.002496363,0.04102723],"study_design_scores_gemma":[0.00045374717,0.00001874741,0.00022264625,0.000013103794,0.0007639703,0.00000990195,0.000061258164,0.9952686,0.0025444478,0.000072144576,0.000402041,0.00016939285],"about_ca_topic_score_codex":0.00009002047,"about_ca_topic_score_gemma":0.00001479096,"teacher_disagreement_score":0.7649959,"about_ca_system_score_codex":0.00003133264,"about_ca_system_score_gemma":0.000027945402,"threshold_uncertainty_score":0.6052574},"labels":[],"label_agreement":null},{"id":"W2898898617","doi":"10.1016/j.media.2018.10.011","title":"A graph-based lesion characterization and deep embedding approach for improved computer-aided diagnosis of nonmass breast MRI lesions","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"MRI in cancer diagnosis","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"National Institute for Materials Science; Canadian Cancer Society; Ontario Institute for Cancer Research","keywords":"Artificial intelligence; Embedding; Computer-aided diagnosis; Graph; Breast MRI; Pattern recognition (psychology); Computer-aided; Computer science; Lesion; Computer vision; Medicine; Theoretical computer science; Breast cancer; Pathology; Mammography; Internal medicine","score_opus":0.01694372814630471,"score_gpt":0.3100155083522342,"score_spread":0.2930717802059295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898898617","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":[0.12213224,0.0000688539,0.87260467,0.0043810103,0.000064764696,0.0005482972,0.000113552465,0.000056517503,0.000030112798],"genre_scores_gemma":[0.8453637,0.0006831495,0.14975607,0.0016051659,0.0006692589,0.00043544744,0.0014028604,0.000051646046,0.0000327361],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781793,0.00010166141,0.0006135767,0.00059313496,0.000538045,0.00033563678],"domain_scores_gemma":[0.9979313,0.00041576347,0.00028146856,0.0004630649,0.0004835761,0.00042482384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064438215,0.00023707523,0.0008481625,0.0006473986,0.00015525261,0.000038004448,0.00017711076,0.00021314737,0.0005303445],"category_scores_gemma":[0.00026727957,0.00019915322,0.00041239025,0.0014480642,0.00045162367,0.00013716727,0.000087995926,0.00016370339,0.0000024612254],"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":[0.0012018554,0.0044469046,0.36155224,0.0021855067,0.006167752,0.000048209098,0.0010878291,0.00012360705,0.07399852,0.000058432546,0.0048451265,0.54428405],"study_design_scores_gemma":[0.0024138954,0.00043762685,0.058780298,0.00021400386,0.004147804,0.000012670046,0.000058302667,0.9228301,0.01041069,0.000011557299,0.00045409787,0.00022897711],"about_ca_topic_score_codex":0.00014885023,"about_ca_topic_score_gemma":0.00005283679,"teacher_disagreement_score":0.9227065,"about_ca_system_score_codex":0.00006226581,"about_ca_system_score_gemma":0.00011511382,"threshold_uncertainty_score":0.81212324},"labels":[],"label_agreement":null},{"id":"W2901235535","doi":"10.1016/j.media.2018.11.008","title":"CATARACTS: Challenge on automatic tool annotation for cataRACT surgery","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":128,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"D-Wave Systems (Canada)","funders":"European Regional Development Fund; Centro de Matemática Universidade do Porto; Fundação para a Ciência e a Tecnologia","keywords":"Workflow; Annotation; Context (archaeology); Computer science; Cataracts; Cataract surgery; Artificial intelligence; Medicine; Surgery","score_opus":0.04315227666897925,"score_gpt":0.35849689856686356,"score_spread":0.3153446218978843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901235535","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":[0.9564248,0.00007877258,0.025558932,0.009857946,0.00020772334,0.00037733908,0.000022291926,0.00024500917,0.007227226],"genre_scores_gemma":[0.995037,0.000025818077,0.0006928369,0.0028435637,0.00055874937,0.00003079144,0.00052115467,0.000015861036,0.0002742167],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821264,0.00006171672,0.0004592785,0.00030884476,0.000687303,0.00027024702],"domain_scores_gemma":[0.9977103,0.0013610666,0.00011381063,0.00028924565,0.00023838486,0.00028720874],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009147189,0.00013860481,0.0005211503,0.0003783,0.00011722228,0.000028856617,0.00006999364,0.000121570854,0.00493086],"category_scores_gemma":[0.003772055,0.000105552725,0.00043654902,0.0008146797,0.00013922092,0.00011298906,0.000013565205,0.00014560591,0.00029569783],"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":[0.00056807906,0.0015461773,0.012255319,0.00022694479,0.0033228144,0.00036893142,0.0010803738,0.000014549696,0.00008392089,0.00036174027,0.006303855,0.9738673],"study_design_scores_gemma":[0.00571124,0.0010166041,0.15595758,0.0003542848,0.0056926943,0.000020360021,0.0004194519,0.7545089,0.0008899729,0.00035421946,0.07441122,0.00066343177],"about_ca_topic_score_codex":0.00004690291,"about_ca_topic_score_gemma":0.000040090697,"teacher_disagreement_score":0.97320384,"about_ca_system_score_codex":0.00004427995,"about_ca_system_score_gemma":0.000108644585,"threshold_uncertainty_score":0.9959788},"labels":[],"label_agreement":null},{"id":"W2901481277","doi":"10.1016/j.media.2020.101751","title":"Graph refinement based airway extraction using mean-field networks and graph neural networks","year":2020,"lang":"en","type":"preprint","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Danmarks Frie Forskningsfond; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Computer science; Graph; Artificial neural network; Inference; Algorithm; Artificial intelligence; Pattern recognition (psychology); Theoretical computer science","score_opus":0.023797524028233572,"score_gpt":0.30691302252036046,"score_spread":0.28311549849212686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901481277","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":[0.0015364229,0.0010832102,0.9857303,0.010512194,0.00039434197,0.00035977372,0.0000044138824,0.00029118,0.000088174165],"genre_scores_gemma":[0.8748075,0.0010102678,0.11631346,0.006592356,0.0008518578,0.00015232466,0.00020163642,0.000050597395,0.000020007508],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99533325,0.0003166136,0.0009214519,0.001666013,0.0011172062,0.0006454373],"domain_scores_gemma":[0.99635357,0.00062323926,0.0005895724,0.0015005834,0.00018597701,0.00074704515],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061549264,0.0005558904,0.000923128,0.00053680106,0.0003541034,0.0003749355,0.0015052641,0.0005360987,0.0001580308],"category_scores_gemma":[0.00019096614,0.00052763504,0.0006905147,0.0035947459,0.00020323799,0.00035350304,0.0016478982,0.002075431,0.0000030279652],"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":[0.000020958918,0.00010291362,0.0005754852,0.00003780652,0.00067620043,0.00016268696,0.00004071357,0.944272,0.00010395698,0.000323984,0.0015363344,0.052146956],"study_design_scores_gemma":[0.00024008265,0.00004289176,0.0003802336,0.000050403985,0.0011096029,0.00000857302,0.000008088818,0.9961543,0.00008221608,0.0012431451,0.00021325109,0.00046721142],"about_ca_topic_score_codex":0.00024874476,"about_ca_topic_score_gemma":0.00022571134,"teacher_disagreement_score":0.87327105,"about_ca_system_score_codex":0.00008016422,"about_ca_system_score_gemma":0.00008767551,"threshold_uncertainty_score":0.99971753},"labels":[],"label_agreement":null},{"id":"W2909627766","doi":"10.1016/j.media.2019.01.004","title":"Training recurrent neural networks robust to incomplete data: Application to Alzheimer’s disease progression modeling","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":139,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research; U.S. Department of Defense","keywords":"Computer science; Artificial intelligence; Artificial neural network; Machine learning; Training (meteorology); Disease; Training set; Recurrent neural network; Medicine; Pathology","score_opus":0.08360766209578195,"score_gpt":0.3858014648162579,"score_spread":0.3021938027204759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909627766","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":[0.011014792,0.00026510906,0.9739771,0.013760829,0.00020979824,0.00050622015,0.000007885678,0.00020050486,0.00005774838],"genre_scores_gemma":[0.91898406,0.000007753626,0.07795199,0.0023773757,0.000286226,0.00008103242,0.00028420473,0.000017616801,0.000009726431],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99628234,0.00029862096,0.00052310916,0.0011785931,0.0011952497,0.000522091],"domain_scores_gemma":[0.99628085,0.00014482255,0.00012027836,0.0020244787,0.00015557055,0.0012739818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014020242,0.00020765311,0.00041062897,0.00035862988,0.00016918422,0.0002069274,0.0024596374,0.0000763121,0.000098537676],"category_scores_gemma":[0.0005348211,0.00017919547,0.00012684775,0.002406698,0.000022799964,0.00044083333,0.0016482476,0.00049487123,0.00011094849],"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":[0.000011456592,0.000030459789,0.0057187607,0.000012767812,0.0000736731,0.000015070494,0.0002638485,0.5632065,0.0000029529583,0.00006784675,0.0001819148,0.43041477],"study_design_scores_gemma":[0.00010173285,0.000042502525,0.002494399,0.00005463228,0.00019687411,0.0000014540112,0.000023356892,0.9961965,3.9911734e-7,0.000020066427,0.000663025,0.0002050331],"about_ca_topic_score_codex":0.00023095141,"about_ca_topic_score_gemma":0.00009650122,"teacher_disagreement_score":0.9079693,"about_ca_system_score_codex":0.000048306112,"about_ca_system_score_gemma":0.00010862712,"threshold_uncertainty_score":0.7307379},"labels":[],"label_agreement":null},{"id":"W2910002198","doi":"10.1016/j.media.2019.01.005","title":"Recurrent inference machines for reconstructing heterogeneous MRI data","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":85,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Artificial intelligence; Computer science; Inference; Overfitting; Deep learning; Iterative reconstruction; Process (computing); Imaging phantom; SIGNAL (programming language); Inverse problem; Compressed sensing; Pattern recognition (psychology); Benchmark (surveying); Machine learning; Real-time MRI; Magnetic resonance imaging; Artificial neural network; Mathematics; Radiology; Medicine","score_opus":0.03739816782364099,"score_gpt":0.4081645798559363,"score_spread":0.3707664120322953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910002198","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":[0.032615718,0.00021261537,0.96254116,0.0028056286,0.00005369794,0.0004779189,0.00011485535,0.00013273019,0.0010456829],"genre_scores_gemma":[0.47310552,0.00051148224,0.52177393,0.0011588847,0.00030955832,0.00014329531,0.0021233289,0.000034787,0.0008391822],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986933,0.000017519991,0.0003310762,0.00045653974,0.00029560697,0.00020594388],"domain_scores_gemma":[0.9983784,0.00020153755,0.000107148524,0.0009943801,0.0001160158,0.00020254756],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031387468,0.00011854864,0.0003981029,0.00013396499,0.000059387028,0.000018981798,0.0003322327,0.00008061216,0.0015686594],"category_scores_gemma":[0.0006367087,0.000093039554,0.00017408853,0.000506527,0.00007707978,0.00009485228,0.0001865211,0.000182268,0.000043086802],"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":[0.00011739588,0.00041205523,0.054803412,0.00022418832,0.0011236593,0.000047034737,0.00007418503,0.00011839635,0.0036388305,0.0008238704,0.004277519,0.93433946],"study_design_scores_gemma":[0.0009261442,0.00018458806,0.0006535813,0.00012594965,0.0025575382,0.000079771366,0.000060545357,0.9558616,0.0025239843,0.0017721555,0.0349444,0.000309692],"about_ca_topic_score_codex":0.000032237396,"about_ca_topic_score_gemma":0.00003793147,"teacher_disagreement_score":0.95574325,"about_ca_system_score_codex":0.00002399875,"about_ca_system_score_gemma":0.00006476363,"threshold_uncertainty_score":0.99934405},"labels":[],"label_agreement":null},{"id":"W2910094941","doi":"10.1016/j.media.2022.102680","title":"The Liver Tumor Segmentation Benchmark (LiTS)","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1164,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"National Cancer Institute; National Institutes of Health; Fonds de Recherche du Québec - Santé; Fondation de l'Association des radiologistes du Québec; International Graduate School of Science and Engineering; Universität Zürich; Deutsche Forschungsgemeinschaft","keywords":"Benchmark (surveying); Segmentation; Computer science; Artificial intelligence; Medical physics; Medicine; Pattern recognition (psychology); Cartography","score_opus":0.007724142912540659,"score_gpt":0.2656009642944292,"score_spread":0.25787682138188855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910094941","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":[0.0033326293,0.00042217888,0.9870038,0.008218525,0.00008523368,0.00012536584,0.0000035241276,0.00009734214,0.00071141764],"genre_scores_gemma":[0.9018634,0.00043205102,0.08322024,0.010097031,0.00029107835,0.00095393014,0.00011257655,0.000022274484,0.0030074164],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811983,0.00019290509,0.00022884492,0.00032169413,0.0009128981,0.00022379936],"domain_scores_gemma":[0.9987161,0.0004054899,0.00010131131,0.00059441035,0.000048415895,0.00013425502],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005617029,0.00007964259,0.00012117124,0.00009148031,0.0009141251,0.000094440475,0.0012538373,0.0000115741805,0.0010107311],"category_scores_gemma":[0.00012026652,0.00005859865,0.00014346541,0.002639343,0.00009728655,0.00021002852,0.0006511899,0.00023805976,0.000060766375],"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":[0.000017393011,0.00039862035,0.0019816433,0.000008671672,0.0010952831,0.00050541625,0.0011981385,0.0092160525,0.0014138841,0.045800272,0.06759614,0.8707685],"study_design_scores_gemma":[0.00016220893,0.000030027644,0.0021739262,0.0000010138788,0.00019666702,0.000020954545,0.00014506202,0.94519377,0.00031377206,0.00284923,0.048756614,0.0001567828],"about_ca_topic_score_codex":0.00003417503,"about_ca_topic_score_gemma":0.00004581247,"teacher_disagreement_score":0.9359777,"about_ca_system_score_codex":0.000065360226,"about_ca_system_score_gemma":0.000045466968,"threshold_uncertainty_score":0.9999025},"labels":[],"label_agreement":null},{"id":"W2912696013","doi":"10.1016/j.media.2005.09.002","title":"United Snakes","year":2005,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"Turun Yliopisto","keywords":"Computer science; Artificial intelligence; Robustness (evolution); Segmentation; Computer vision; Image segmentation; Pattern recognition (psychology); Biology","score_opus":0.010482848239352076,"score_gpt":0.3051294323258833,"score_spread":0.2946465840865312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912696013","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":[0.0010862215,0.000063620166,0.98204553,0.012840524,0.00003588022,0.00005792881,0.0000013083671,0.00054106844,0.0033279385],"genre_scores_gemma":[0.107773125,0.00012403392,0.86957246,0.020066733,0.00027193423,0.000035028886,0.00007042454,0.000013851376,0.0020724148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974465,0.00015909132,0.00040697126,0.00039403222,0.0012911233,0.00030231022],"domain_scores_gemma":[0.99843067,0.00017525406,0.000088618435,0.0006663175,0.00014729239,0.00049183686],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00082703104,0.00013540857,0.00027477054,0.0007705534,0.00008504134,0.0001598743,0.0012820651,0.0000980287,0.0051257005],"category_scores_gemma":[0.00084150664,0.000110081935,0.00021397429,0.0038948648,0.00018119825,0.00064393145,0.00024951162,0.00024244693,0.00045060457],"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":[0.000002561711,0.0003028958,0.00086989097,0.000011110476,0.0007108242,0.0002269671,0.00047502836,0.000019820403,0.0017325934,0.002546798,0.055117447,0.93798405],"study_design_scores_gemma":[0.0007774418,0.000077090626,0.0022515068,0.000028346489,0.0006550457,0.000027135125,0.00007340756,0.87470526,0.068011,0.0008226946,0.05194847,0.00062259403],"about_ca_topic_score_codex":0.00007223414,"about_ca_topic_score_gemma":0.000038879625,"teacher_disagreement_score":0.9373615,"about_ca_system_score_codex":0.000045849014,"about_ca_system_score_gemma":0.000067295616,"threshold_uncertainty_score":0.99578375},"labels":[],"label_agreement":null},{"id":"W2913510405","doi":"10.1016/j.media.2019.01.013","title":"Weakly supervised mitosis detection in breast histopathology images using concentric loss","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":165,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network","funders":"National Science Foundation of Sri Lanka; National Natural Science Foundation of China","keywords":"Histopathology; Concentric; Artificial intelligence; Pattern recognition (psychology); Mathematics; Computer vision; Computer science; Medicine; Pathology; Geometry","score_opus":0.006263077141884169,"score_gpt":0.2467378444246055,"score_spread":0.24047476728272132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913510405","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":[0.43387732,0.00013899141,0.56438345,0.00091301656,0.0003560812,0.00008726415,0.00000243992,0.00008305985,0.00015836617],"genre_scores_gemma":[0.9917947,0.000061027175,0.0075609107,0.00037558266,0.00010533874,0.000011582956,0.0000035501353,0.000011778084,0.00007550117],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974316,0.00031073167,0.00044061075,0.000680641,0.00072002923,0.00041642162],"domain_scores_gemma":[0.99877334,0.0001317588,0.00013654145,0.00064571324,0.00013138885,0.0001812733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069814123,0.00017916187,0.0004551699,0.0006697836,0.00007696652,0.0000917824,0.00072432484,0.00017901354,0.00064585306],"category_scores_gemma":[0.00011785402,0.0001737124,0.0002432212,0.003940582,0.00014715668,0.0006324168,0.00023555296,0.0003456446,0.0001369069],"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":[0.00008690777,0.00041021543,0.43224734,0.00010714205,0.0005081025,0.001147412,0.0010048838,0.0011961731,0.2169334,0.00008478644,0.0002629126,0.3460107],"study_design_scores_gemma":[0.0008313375,0.00005618789,0.09784705,0.000027692493,0.0003045065,0.00024641768,0.000051943764,0.88513625,0.014760848,0.0001434862,0.00024518793,0.00034911252],"about_ca_topic_score_codex":0.0011333437,"about_ca_topic_score_gemma":0.00020441707,"teacher_disagreement_score":0.88394004,"about_ca_system_score_codex":0.0004481769,"about_ca_system_score_gemma":0.000119301396,"threshold_uncertainty_score":0.7083786},"labels":[],"label_agreement":null},{"id":"W2917393555","doi":"10.1016/j.media.2019.02.011","title":"Deep-learning based multiclass retinal fluid segmentation and detection in optical coherence tomography images using a fully convolutional neural network","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":160,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Fondation pour la Recherche sur Alzheimer; Genome British Columbia; Simon Fraser University; Michael Smith Health Research BC; Canadian Institutes of Health Research; Alzheimer Society; Natural Sciences and Engineering Research Council of Canada; Fondation Brain Canada","keywords":"Optical coherence tomography; Artificial intelligence; Computer science; Convolutional neural network; Segmentation; Retinal; Pattern recognition (psychology); Computer vision; Cut; Retina; Pixel; Image segmentation; Ophthalmology; Medicine; Optics; Physics","score_opus":0.007756989084423179,"score_gpt":0.2748887174620818,"score_spread":0.26713172837765864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2917393555","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":[0.8229982,0.00029664484,0.17571975,0.00062791415,0.000037845493,0.00015123615,0.0000011095926,0.00004976581,0.00011749643],"genre_scores_gemma":[0.9840202,0.000027706394,0.015299016,0.00034756836,0.00012312373,0.000011955779,0.00007435455,0.00001670442,0.00007940182],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973518,0.00030008287,0.00051565806,0.000529384,0.0008828038,0.00042023597],"domain_scores_gemma":[0.9988341,0.0002947666,0.00014152574,0.00019898439,0.00020608141,0.00032457447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009642023,0.00021603414,0.0006000248,0.0006131512,0.00012550825,0.00008451418,0.000089176305,0.00012966467,0.0008414329],"category_scores_gemma":[0.0005528582,0.00019178295,0.00033183122,0.0021925154,0.00030044588,0.00018647977,0.000050947092,0.0005624504,0.000018545521],"study_design_candidate":"observational","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":[0.00030662373,0.00015476909,0.9010406,0.00009854491,0.0006218084,0.00025577127,0.00007793517,0.020092662,0.06319029,0.0000029733467,0.00001692424,0.0141410595],"study_design_scores_gemma":[0.0011620608,0.00012254839,0.18598993,0.00009548943,0.0016392819,0.00004377592,0.0002051358,0.8090285,0.0015378373,0.00000815834,0.0000111934,0.00015605496],"about_ca_topic_score_codex":0.00030475523,"about_ca_topic_score_gemma":0.000059280876,"teacher_disagreement_score":0.78893584,"about_ca_system_score_codex":0.00009180622,"about_ca_system_score_gemma":0.000067825684,"threshold_uncertainty_score":0.92131},"labels":[],"label_agreement":null},{"id":"W2927384312","doi":"10.1016/j.media.2019.03.012","title":"Graph Convolutions on Spectral Embeddings for Cortical Surface Parcellation","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Surface (topology); Computer science; Graph; Artificial intelligence; Euclidean geometry; Surface reconstruction; Pattern recognition (psychology); Algorithm; Theoretical computer science; Mathematics; Geometry","score_opus":0.021703436753890352,"score_gpt":0.29752471837269956,"score_spread":0.2758212816188092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2927384312","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":[0.92814696,0.000015169827,0.049892113,0.018137448,0.00028240037,0.0003248807,0.00003864591,0.000121424695,0.0030409666],"genre_scores_gemma":[0.9949784,0.000015135031,0.00061508856,0.003158334,0.00009398154,0.000015641852,0.000012249017,0.000012312763,0.0010988266],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979058,0.0001409402,0.00025159508,0.00058466697,0.00079037296,0.00032666302],"domain_scores_gemma":[0.9919423,0.007464648,0.00007080814,0.00027240926,0.0000827925,0.0001670648],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00049074966,0.00014213027,0.00032854808,0.00018813135,0.0002186437,0.000044166245,0.00017754584,0.00007968292,0.0018236816],"category_scores_gemma":[0.013289032,0.0001227715,0.00037231093,0.0011155463,0.00025877223,0.00012534329,0.000052882904,0.00024099185,0.0004419809],"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":[0.0009804581,0.0021650326,0.14098902,0.00016893189,0.0029055623,0.0001382088,0.0011928139,0.011602185,0.6890087,0.055218536,0.093909256,0.0017212722],"study_design_scores_gemma":[0.0031616476,0.0010514717,0.092017345,0.000052764022,0.0022751577,0.000015014019,0.00048179444,0.7691202,0.11196865,0.0071154824,0.011652868,0.0010875807],"about_ca_topic_score_codex":0.000027788397,"about_ca_topic_score_gemma":0.000031582742,"teacher_disagreement_score":0.75751805,"about_ca_system_score_codex":0.00006248987,"about_ca_system_score_gemma":0.00004450926,"threshold_uncertainty_score":0.99908876},"labels":[],"label_agreement":null},{"id":"W2941681265","doi":"10.1016/j.media.2019.04.012","title":"Direct automated quantitative measurement of spine by cascade amplifier regression network with manifold regularization","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Science and Technology Planning Project of Guangdong Province; China Scholarship Council; National Natural Science Foundation of China","keywords":"Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Computer science; Discriminative model; Embedding; Regularization (linguistics); Cascade; Mathematics; Overfitting; Regression; Nonlinear dimensionality reduction; Curse of dimensionality; Dimensionality reduction; Artificial neural network; Statistics; Engineering","score_opus":0.007527160090647314,"score_gpt":0.24274834865850764,"score_spread":0.23522118856786034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941681265","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":[0.092790864,0.0032711625,0.893731,0.00088150543,0.00018292572,0.00029293864,0.000023393248,0.0011143921,0.0077118315],"genre_scores_gemma":[0.99266726,0.00024235855,0.0057401196,0.00011432527,0.00005786424,0.000012216369,0.00023362318,0.000039367387,0.000892897],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971028,0.0001290254,0.0004957333,0.00032969099,0.0016175042,0.00032525236],"domain_scores_gemma":[0.9988739,0.00006440984,0.0001322255,0.00039429736,0.00027245298,0.00026272575],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009429602,0.00022287075,0.0007165482,0.00023399173,0.00004596876,0.0000322824,0.00023095551,0.00012755896,0.0011045411],"category_scores_gemma":[0.00032176677,0.00015319348,0.0001905471,0.0021220571,0.000087564185,0.0001262246,0.000037053374,0.00021922044,0.00004117752],"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":[0.00015298363,0.0011002293,0.08325728,0.0019490648,0.048407786,0.00044982188,0.0013215803,0.22508074,0.27155346,0.0007097202,0.34048027,0.025537055],"study_design_scores_gemma":[0.0004935419,0.000047278107,0.0022883585,0.00035760613,0.0020685378,0.0000019867714,0.000051435607,0.9825538,0.0102643855,0.000011830679,0.0016036516,0.00025760132],"about_ca_topic_score_codex":0.00013788724,"about_ca_topic_score_gemma":0.000041460455,"teacher_disagreement_score":0.89987636,"about_ca_system_score_codex":0.00006494039,"about_ca_system_score_gemma":0.00003891385,"threshold_uncertainty_score":0.9998086},"labels":[],"label_agreement":null},{"id":"W2950994280","doi":"10.1016/j.media.2019.101557","title":"Exploring uncertainty measures in deep networks for Multiple sclerosis lesion detection and segmentation","year":2019,"lang":"en","type":"preprint","venue":"Medical Image Analysis","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dropout (neural networks); Segmentation; Voxel; Artificial intelligence; Computer science; Context (archaeology); Sigmoid function; Image segmentation; Pattern recognition (psychology); Deep learning; Machine learning; Lesion; Monte Carlo method; Artificial neural network; Medicine; Mathematics; Statistics; Pathology","score_opus":0.059854850753197124,"score_gpt":0.29529285201127436,"score_spread":0.23543800125807723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950994280","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":[0.3873441,0.00078245695,0.6113824,0.000049136786,0.000037482,0.0003523241,0.000003988786,0.000023986235,0.000024129915],"genre_scores_gemma":[0.9879213,0.006645195,0.003605317,0.000110143876,0.0001686325,0.00048415523,0.0009966879,0.000033673066,0.000034899436],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770224,0.00019745248,0.0005244479,0.000884277,0.0004011703,0.00029039462],"domain_scores_gemma":[0.9988058,0.000088493194,0.00023045439,0.0005583857,0.00018244839,0.0001343809],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010797442,0.00029356897,0.000571752,0.0004453177,0.00007414066,0.00009561887,0.00025494664,0.00046798444,0.000021946164],"category_scores_gemma":[0.0007982393,0.00028803802,0.00047631018,0.00042273762,0.00009584609,0.000014558383,0.00046718438,0.00035982789,0.0000011320104],"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":[0.0003247221,0.00022055578,0.0307875,0.00022286749,0.0028228033,0.000010789051,0.0001751651,0.0649519,0.52810025,6.1562815e-7,0.00022848247,0.37215436],"study_design_scores_gemma":[0.000896825,0.00010649659,0.012277925,0.00012063241,0.0021611124,0.0000012856207,0.00021222021,0.8067649,0.17657465,0.000031561573,0.0003260308,0.000526356],"about_ca_topic_score_codex":0.00088273827,"about_ca_topic_score_gemma":0.0070782453,"teacher_disagreement_score":0.741813,"about_ca_system_score_codex":0.000081255006,"about_ca_system_score_gemma":0.00004668042,"threshold_uncertainty_score":0.9999572},"labels":[],"label_agreement":null},{"id":"W2951135390","doi":"10.1016/j.media.2019.06.002","title":"A methodology for generating four-dimensional arterial spin labeling MR angiography virtual phantoms","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Fundação Amazônia Paraense de Amparo à Pesquisa; Canada Research Chairs; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Alberta Innovates - Health Solutions; Fundação de Amparo à Pesquisa do Estado de São Paulo; Natural Sciences and Engineering Research Council of Canada; Hotchkiss Brain Institute, University of Calgary","keywords":"Computer science; Arterial spin labeling; Artificial intelligence; Magnetic resonance angiography; Ground truth; Scanner; Computer vision; Noise (video); Blood flow; Image processing; Medical imaging; Modality (human–computer interaction); Volume (thermodynamics); Magnetic resonance imaging; Image (mathematics); Radiology; Physics; Medicine","score_opus":0.04414022967995426,"score_gpt":0.38645552914150777,"score_spread":0.3423152994615535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951135390","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":[0.21187897,0.0001277836,0.78563213,0.001708349,0.00007097766,0.00036574446,0.000021525124,0.00010429445,0.00009022721],"genre_scores_gemma":[0.20463301,0.000029063889,0.79149747,0.002372265,0.00056431943,0.00017352565,0.00032059464,0.000027746415,0.00038203024],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983153,0.000077095654,0.00043079388,0.00043961615,0.0004195508,0.00031766974],"domain_scores_gemma":[0.99871093,0.00038055796,0.00012545672,0.00034844578,0.0001848917,0.00024968942],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007768132,0.00016243014,0.00061040936,0.00037039828,0.00010169697,0.000017768942,0.00012854669,0.00016491934,0.0013172727],"category_scores_gemma":[0.0004677799,0.00013189125,0.00077146397,0.0009669219,0.000112447044,0.000069023525,0.00006293847,0.00019282925,0.000028988408],"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":[0.00030667926,0.00037876324,0.0022405437,0.000051158044,0.0021398757,0.00007297188,0.00012459619,0.00056867773,0.9270245,0.0018890148,0.003603919,0.06159932],"study_design_scores_gemma":[0.008400257,0.0015623794,0.0016868485,0.00020384157,0.012699558,0.00018877875,0.00041516364,0.86906505,0.08028942,0.003018531,0.021359602,0.0011105576],"about_ca_topic_score_codex":0.000035610596,"about_ca_topic_score_gemma":0.000016428476,"teacher_disagreement_score":0.86849636,"about_ca_system_score_codex":0.000023872883,"about_ca_system_score_gemma":0.0000680369,"threshold_uncertainty_score":0.99959564},"labels":[],"label_agreement":null},{"id":"W2953031404","doi":"10.1016/j.media.2019.06.010","title":"XQ-SR: Joint x-q space super-resolution with application to infant diffusion MRI","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"NIH Blueprint for Neuroscience Research; National Institute of Biomedical Imaging and Bioengineering; National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; National Institute on Aging; National Institutes of Health","keywords":"Diffusion MRI; Resolution (logic); Computer science; Image resolution; Focus (optics); Artificial intelligence; SIGNAL (programming language); Pattern recognition (psychology); Domain (mathematical analysis); Joint (building); Mathematics; Magnetic resonance imaging; Physics; Optics; Mathematical analysis; Medicine","score_opus":0.014259364138998113,"score_gpt":0.31385705844009204,"score_spread":0.29959769430109395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953031404","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":[0.20581351,0.0000312405,0.7678797,0.024121922,0.000010420617,0.0006438616,0.00000641263,0.00022479761,0.0012680915],"genre_scores_gemma":[0.94470686,0.0001256334,0.050842803,0.0026877103,0.00009683606,0.00019361901,0.00016424336,0.00003106317,0.001151253],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812645,0.000029786812,0.0003019419,0.00054038217,0.0007327164,0.00026874949],"domain_scores_gemma":[0.99846995,0.00004315573,0.000084552004,0.00083736744,0.00016162175,0.0004033748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023880268,0.00016914499,0.0004299619,0.00033917362,0.00007889891,0.000020926476,0.0001519345,0.000084625644,0.0006222449],"category_scores_gemma":[0.00012240701,0.00012398123,0.00016831922,0.0016141376,0.00008969244,0.00008900057,0.000111086425,0.0002764608,0.00028723208],"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":[0.0006430201,0.0022802958,0.250247,0.00030021623,0.0013627891,0.00023553951,0.00067009294,0.001055635,0.64900106,0.00480333,0.023750754,0.06565023],"study_design_scores_gemma":[0.0037820921,0.0012376116,0.29436207,0.00041948076,0.0051574525,0.00019957384,0.00028984767,0.39630118,0.036368974,0.0007378271,0.25990838,0.0012355003],"about_ca_topic_score_codex":0.00020358368,"about_ca_topic_score_gemma":0.00005110065,"teacher_disagreement_score":0.73889333,"about_ca_system_score_codex":0.00008068686,"about_ca_system_score_gemma":0.000055426008,"threshold_uncertainty_score":0.6813145},"labels":[],"label_agreement":null},{"id":"W2955932350","doi":"10.1016/j.media.2020.101758","title":"Automated characterization of noise distributions in diffusion MRI data","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":29,"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":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Noise (video); Scanner; Computer science; Imaging phantom; Artificial intelligence; Noise reduction; Algorithm; Sensitivity (control systems); Pattern recognition (psychology); Physics; Optics","score_opus":0.05534162756861639,"score_gpt":0.3762756233350233,"score_spread":0.3209339957664069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955932350","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":[0.24474996,0.000012959977,0.7251977,0.029155742,0.0000055774976,0.00018106222,0.00029213433,0.00031197668,0.00009288543],"genre_scores_gemma":[0.98542434,0.00019898587,0.0074469806,0.0008233521,0.000038116217,0.000013849724,0.006026796,0.000009013706,0.000018562814],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989335,0.00002965799,0.0003387673,0.0002888539,0.00029974116,0.00010948443],"domain_scores_gemma":[0.9991163,0.0000328435,0.000091788366,0.0005119539,0.00006429985,0.000182802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000119234304,0.00007491807,0.0003026967,0.00011974136,0.000027112817,0.000006320927,0.0002274854,0.00004990086,0.00033576426],"category_scores_gemma":[0.000563625,0.00006428144,0.000070806636,0.0018268226,0.000090716894,0.000100451995,0.00019047441,0.00015707758,0.0000094246225],"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":[0.000069484835,0.0009679006,0.10293876,0.00012666619,0.0002686381,0.00016558524,0.00014258883,0.000008924214,0.8809283,0.00020758522,0.0031218047,0.011053783],"study_design_scores_gemma":[0.00044227316,0.00003219699,0.18050632,0.000040713217,0.000705141,0.0000038435464,0.000011457482,0.8079899,0.006845023,0.000022579414,0.0033189321,0.000081641076],"about_ca_topic_score_codex":0.00003170965,"about_ca_topic_score_gemma":0.000004666507,"teacher_disagreement_score":0.8740833,"about_ca_system_score_codex":0.00001544549,"about_ca_system_score_gemma":0.000042665382,"threshold_uncertainty_score":0.36763832},"labels":[],"label_agreement":null},{"id":"W2959828872","doi":"10.1016/j.media.2019.07.005","title":"Accurate and robust deep learning-based segmentation of the prostate clinical target volume in ultrasound images","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":124,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Canadian Institutes of Health Research; Prostate Cancer Canada","keywords":"Artificial intelligence; Segmentation; Computer science; Convolutional neural network; Hausdorff distance; Deep learning; Pattern recognition (psychology); Image segmentation; Computer vision","score_opus":0.006231307933401923,"score_gpt":0.2571856918820442,"score_spread":0.2509543839486423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2959828872","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":[0.85754055,0.0004727995,0.14035407,0.0008663237,0.00011736967,0.00016303977,0.000010042496,0.00008444742,0.000391346],"genre_scores_gemma":[0.99698985,0.0002483965,0.0020500515,0.00017289589,0.000036248122,0.000008987644,0.00005682877,0.000017785984,0.0004189386],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99788123,0.00029631215,0.00067209284,0.00028450266,0.0006066474,0.00025921455],"domain_scores_gemma":[0.9989269,0.00042445902,0.000119005344,0.00027512416,0.00006793547,0.00018660484],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013310285,0.00015911169,0.00054016034,0.00023140568,0.000039754104,0.000047601614,0.00022795562,0.00010895684,0.001602101],"category_scores_gemma":[0.001293634,0.00011185896,0.0002842977,0.0013353064,0.00027842628,0.00013634848,0.00004389018,0.0005532184,0.000033922977],"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":[0.0000048192364,0.000061859704,0.8130545,0.000090335896,0.0004730138,0.000012969469,0.00012682592,0.18069243,0.001156648,6.3659814e-7,0.0003362173,0.0039897542],"study_design_scores_gemma":[0.0005661594,0.000015320304,0.12254842,0.000040637435,0.0005107755,0.000001043537,0.00018012126,0.87500024,0.0008615543,0.000012834621,0.00013280525,0.00013009777],"about_ca_topic_score_codex":0.00010736622,"about_ca_topic_score_gemma":0.000053056905,"teacher_disagreement_score":0.6943078,"about_ca_system_score_codex":0.000026429521,"about_ca_system_score_gemma":0.000035466994,"threshold_uncertainty_score":0.99931055},"labels":[],"label_agreement":null},{"id":"W2963190374","doi":"10.1016/j.media.2019.101534","title":"Learning the implicit strain reconstruction in ultrasound elastography using privileged information","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Ultrasound Imaging and Elastography","field":"Medicine","cited_by":74,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Process (computing); Artificial neural network; Artificial intelligence; Deep learning; Causality (physics); Elastography; Machine learning; Data mining; Ultrasound","score_opus":0.004420114574558858,"score_gpt":0.2471541416463416,"score_spread":0.24273402707178277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963190374","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":[0.9734373,0.000051225135,0.023204943,0.0004981943,0.00011005762,0.00021507758,0.0000057238217,0.000070761525,0.0024067017],"genre_scores_gemma":[0.9962242,0.00005627048,0.0029230444,0.0005394678,0.0000755292,0.000008525284,0.00011221957,0.000011544583,0.000049148483],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980326,0.00016021155,0.00052153034,0.00023689642,0.00069803157,0.00035072863],"domain_scores_gemma":[0.99892896,0.00029384618,0.00016670549,0.00031597214,0.00012005521,0.00017445123],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010542702,0.0001709679,0.0004200327,0.0010957799,0.00012846415,0.000094751704,0.00014070392,0.00012971174,0.0012937986],"category_scores_gemma":[0.0007624549,0.000120742254,0.00042251608,0.0034472223,0.00022100513,0.00051154627,0.000025488376,0.00078621705,0.00007546123],"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":[0.00004288,0.0000611636,0.9521819,0.00004144633,0.0007734902,0.0000042823713,0.0009201289,0.0004476366,0.023166353,0.000011794399,0.00003177727,0.022317149],"study_design_scores_gemma":[0.002958513,0.0002813005,0.92645967,0.00030611161,0.0032240818,0.00096832,0.009365696,0.05014989,0.00044190724,0.00016975329,0.0051304046,0.00054432056],"about_ca_topic_score_codex":0.00040745968,"about_ca_topic_score_gemma":0.000060305716,"teacher_disagreement_score":0.049702253,"about_ca_system_score_codex":0.00005650164,"about_ca_system_score_gemma":0.000090729154,"threshold_uncertainty_score":0.9996191},"labels":[],"label_agreement":null},{"id":"W2963666472","doi":"10.1016/j.media.2019.101533","title":"Automatic spondylolisthesis grading from MRIs across modalities using faster adversarial recognition network","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Discriminator; Computer science; Artificial intelligence; Pattern recognition (psychology); Spondylolisthesis; Grading (engineering); Bounding overwatch; Machine learning; Lumbar; Radiology; Detector; Medicine","score_opus":0.013419027629881397,"score_gpt":0.25469032976568107,"score_spread":0.24127130213579967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963666472","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":[0.88241965,0.0002679381,0.11556833,0.00020073728,0.00040460643,0.00007631166,0.000064029446,0.00036461005,0.0006338032],"genre_scores_gemma":[0.98962873,0.00007938076,0.008357697,0.00038039757,0.00093462714,0.000010402702,0.0003450689,0.000053315125,0.000210352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99696916,0.00018230041,0.00068735203,0.00044134332,0.0010302084,0.00068962417],"domain_scores_gemma":[0.99852484,0.0003958537,0.00010353738,0.00047632278,0.00007498252,0.0004244327],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008397532,0.0003132878,0.0009028092,0.00025976924,0.00013957646,0.00019552658,0.0003440661,0.00022703894,0.01622175],"category_scores_gemma":[0.0003259302,0.000284814,0.00064118364,0.0016179022,0.00014013198,0.00037125702,0.00008673625,0.00042664612,0.0005286904],"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":[0.00006226685,0.00038708022,0.20146443,0.0008969584,0.039672144,0.0010185413,0.008081973,0.12767187,0.0066770655,0.00002797823,0.011708257,0.60233146],"study_design_scores_gemma":[0.00045161342,0.0000055134055,0.0017664687,0.00014463246,0.0025759484,0.0000033959516,0.0005241514,0.9931872,0.00025849626,0.00036918654,0.000354513,0.00035889412],"about_ca_topic_score_codex":0.0010567175,"about_ca_topic_score_gemma":0.00007864381,"teacher_disagreement_score":0.86551535,"about_ca_system_score_codex":0.00011503746,"about_ca_system_score_gemma":0.00003217815,"threshold_uncertainty_score":0.9999604},"labels":[],"label_agreement":null},{"id":"W2966434031","doi":"10.1016/j.media.2020.101851","title":"Boundary loss for highly unbalanced segmentation","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":459,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Boundary (topology); Computer science; Artificial intelligence; Computer vision; Mathematical optimization; Mathematics; Mathematical analysis","score_opus":0.030341759310164765,"score_gpt":0.3062704956848611,"score_spread":0.27592873637469634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966434031","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":[0.11435278,0.00001929646,0.83399487,0.04989741,0.00014691424,0.00024349995,0.000034603374,0.0002335828,0.0010770422],"genre_scores_gemma":[0.98545945,0.000023386796,0.00089784083,0.013029093,0.00016344915,0.000052899024,0.000040722723,0.000009844254,0.0003233088],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99863553,0.00009643711,0.00024022182,0.00037360314,0.00049391587,0.00016029892],"domain_scores_gemma":[0.9992869,0.00018964664,0.000092190516,0.00014282187,0.00004686193,0.00024156086],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018456817,0.00008511109,0.00017763754,0.000089373396,0.00015330927,0.00008418899,0.00019593313,0.00005206124,0.0010692137],"category_scores_gemma":[0.0020263677,0.00007577014,0.00018205287,0.0012838852,0.00015413662,0.00015931306,0.000023753675,0.00011463488,0.00014029791],"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":[0.00009967343,0.00010375178,0.0006206273,0.000041225852,0.00012600329,0.00004259856,0.00042507463,0.000029999579,0.9554171,0.0005354736,0.0065274825,0.036031015],"study_design_scores_gemma":[0.0013843367,0.00013492988,0.0036091688,0.0000057998095,0.00060870027,0.0000071646255,0.00023515167,0.29618376,0.67114204,0.00044624234,0.025962202,0.00028047568],"about_ca_topic_score_codex":0.0000056317567,"about_ca_topic_score_gemma":0.0000059621275,"teacher_disagreement_score":0.8711067,"about_ca_system_score_codex":0.000029780558,"about_ca_system_score_gemma":0.00005015378,"threshold_uncertainty_score":0.99984396},"labels":[],"label_agreement":null},{"id":"W2968439290","doi":"10.1016/j.media.2019.101542","title":"Accurate automated Cobb angles estimation using multi-view extrapolation net","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Scoliosis diagnosis and treatment","field":"Medicine","cited_by":95,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Extrapolation; CobB; Net (polyhedron); Artificial intelligence; Estimation; Computer science; Mathematics; Computer vision; Algorithm; Mathematical optimization; Pattern recognition (psychology); Statistics; Geometry; Engineering; Biology","score_opus":0.038072274048796734,"score_gpt":0.3853353582943171,"score_spread":0.3472630842455203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968439290","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":[0.96122736,0.0009476131,0.035460785,0.001356256,0.00008093845,0.0004241419,0.000009672435,0.00027638458,0.0002168367],"genre_scores_gemma":[0.9847548,0.0001735559,0.014046181,0.0005366914,0.000048324197,0.000021923091,0.00031097943,0.000017701446,0.00008984017],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983264,0.00009646824,0.00043324818,0.00033753028,0.0005650129,0.00024133475],"domain_scores_gemma":[0.9989772,0.00011746641,0.00015111962,0.00034160953,0.00014461405,0.00026802227],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00034703707,0.00017736004,0.0005667161,0.00035910596,0.00006639133,0.000057484885,0.000081007514,0.00013426911,0.0033284714],"category_scores_gemma":[0.00034330148,0.0001338626,0.00029794854,0.0013164305,0.000057015375,0.00020492657,0.00003288886,0.00012445953,0.00030958568],"study_design_candidate":"observational","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":[0.00011224643,0.0023421177,0.9259869,0.00037310782,0.008687856,0.00045115087,0.00052998884,0.003623524,0.0071096052,0.00007782944,0.0018159196,0.048889767],"study_design_scores_gemma":[0.0011697683,0.000051893294,0.23831578,0.00013937523,0.0030517897,0.000012194264,0.000029963901,0.75634986,0.00067999604,0.000004488778,0.000095271156,0.00009963335],"about_ca_topic_score_codex":0.000367312,"about_ca_topic_score_gemma":0.00005954095,"teacher_disagreement_score":0.7527263,"about_ca_system_score_codex":0.00012060248,"about_ca_system_score_gemma":0.00009914656,"threshold_uncertainty_score":0.9975826},"labels":[],"label_agreement":null},{"id":"W2972635947","doi":"10.1016/j.media.2019.101554","title":"PV-LVNet: Direct left ventricle multitype indices estimation from 2D echocardiograms of paired apical views with deep neural networks","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiovascular Function and Risk Factors","field":"Medicine","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Science and Technology Planning Project of Guangdong Province; China Scholarship Council; National Natural Science Foundation of China","keywords":"Ventricle; Resampling; Artificial intelligence; Segmentation; Image quality; Consistency (knowledge bases); Computer science; Pattern recognition (psychology); Image segmentation; Mathematics; Artificial neural network; Computer vision; Image (mathematics); Medicine; Cardiology","score_opus":0.007737155493168633,"score_gpt":0.24722477783468197,"score_spread":0.23948762234151333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972635947","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":[0.80664176,0.0012073747,0.19087489,0.00022740304,0.00019833955,0.00032220356,0.000008181511,0.000093826,0.00042605127],"genre_scores_gemma":[0.99726653,0.00020845869,0.001572692,0.0002528061,0.00017276201,0.000006182415,0.0004009853,0.00002218781,0.000097368174],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974277,0.00022803058,0.00046613233,0.00042654667,0.0011817137,0.000269846],"domain_scores_gemma":[0.9985721,0.00019018525,0.00017378517,0.0005733882,0.00013402381,0.00035652608],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005358649,0.00020741903,0.0010711389,0.00030353127,0.000046793306,0.000030968684,0.00013626038,0.00021023586,0.0026622906],"category_scores_gemma":[0.00030625446,0.00013760796,0.0010402647,0.0012879788,0.00016625911,0.0001231775,0.000051223527,0.0003527101,0.00007386358],"study_design_candidate":"observational","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":[0.00026836983,0.00023084215,0.89329684,0.00003879815,0.0061834333,0.0001335067,0.0002088347,0.012842977,0.00012516252,5.5957094e-7,0.00021018852,0.086460486],"study_design_scores_gemma":[0.0014032223,0.00012834919,0.37820414,0.000038836966,0.004932574,0.00001228482,0.00009226457,0.6141319,0.00023041104,0.000001435077,0.0006937631,0.00013075754],"about_ca_topic_score_codex":0.0009768334,"about_ca_topic_score_gemma":0.00026454157,"teacher_disagreement_score":0.601289,"about_ca_system_score_codex":0.000049050268,"about_ca_system_score_gemma":0.00004189708,"threshold_uncertainty_score":0.9982494},"labels":[],"label_agreement":null},{"id":"W2974263843","doi":"10.1016/j.media.2019.101560","title":"Special issue on MICCAI 2018","year":2019,"lang":"en","type":"editorial","venue":"Medical Image Analysis","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Engineering and Physical Sciences Research Council","keywords":"Systems biology; Computer science; Gene regulatory network; Synthetic biology; Modelling biological systems; Computational biology; Key (lock); Data science; Artificial intelligence; Biology; Gene","score_opus":0.0033260884908028147,"score_gpt":0.2558565078153947,"score_spread":0.2525304193245919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974263843","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011749457,0.0011609093,0.0014607945,0.0007431767,0.97145045,0.000309077,0.0003530948,0.00004991274,0.023297658],"genre_scores_gemma":[0.00017374492,0.0011181541,0.00017966943,0.00038398313,0.94157755,0.00001786877,0.007244802,0.00008944594,0.04921476],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944219,0.00030990856,0.00071495445,0.0014497914,0.0024598637,0.0006435831],"domain_scores_gemma":[0.99681866,0.00016824917,0.00036928218,0.001816734,0.0003500834,0.00047697415],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008538217,0.0006320604,0.0013090724,0.00050270616,0.000108731576,0.00010149257,0.0011598244,0.0023455399,0.009870115],"category_scores_gemma":[0.0017213589,0.00057165936,0.0017555869,0.0010262459,0.0002739292,0.00000417517,0.00039356083,0.00088690856,0.0021168469],"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":[0.000057780726,0.00011595225,0.00007624775,0.00003203447,0.006032575,0.00005579478,0.000008438195,0.00011829671,0.00043475206,5.276659e-7,0.9899284,0.0031391713],"study_design_scores_gemma":[0.00045157745,0.0001823609,0.000028045884,0.000029974542,0.00488435,9.704954e-7,0.000012219999,0.00039634373,0.0010407763,0.0000041726735,0.9923919,0.00057731906],"about_ca_topic_score_codex":0.00008663189,"about_ca_topic_score_gemma":0.00038001157,"teacher_disagreement_score":0.029872863,"about_ca_system_score_codex":0.00009330911,"about_ca_system_score_gemma":0.0005878274,"threshold_uncertainty_score":0.9996735},"labels":[],"label_agreement":null},{"id":"W2975180264","doi":"10.1016/j.media.2021.101996","title":"Multi-scale fully convolutional neural networks for histopathology image segmentation: From nuclear aberrations to the global tissue architecture","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Olympus","keywords":"Convolutional neural network; Artificial intelligence; Segmentation; Computer science; Pattern recognition (psychology); Scale (ratio); Histopathology; Image segmentation; Image (mathematics); Computer vision; Architecture; Pathology; Cartography; Medicine; Geography","score_opus":0.00989152442796864,"score_gpt":0.28675368304538734,"score_spread":0.2768621586174187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975180264","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":[0.0028864706,0.00021199184,0.961089,0.034787863,0.00060407177,0.00017630462,0.00006849968,0.0000948513,0.00008095775],"genre_scores_gemma":[0.16919623,0.00001654714,0.8188562,0.010071841,0.0010234329,0.0001563378,0.00029461892,0.000017979157,0.00036681656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794465,0.00030552116,0.00033051692,0.0006006903,0.00052021677,0.0002983858],"domain_scores_gemma":[0.99858737,0.00023149037,0.00009587428,0.0005849956,0.00027011716,0.00023013203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036795813,0.00015079975,0.00026447332,0.000071247436,0.00036935465,0.0001876396,0.00070867874,0.00011687185,0.0007389437],"category_scores_gemma":[0.00033114673,0.00012453085,0.0002299606,0.0014438144,0.0001445301,0.00020663401,0.00029241497,0.00024190532,0.000046474936],"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":[0.00030466318,0.0012393289,0.008394262,0.000049870607,0.0026741163,0.0012439535,0.008800188,0.17333779,0.041427318,0.002333329,0.14052315,0.619672],"study_design_scores_gemma":[0.0003796519,0.000048347847,0.012869955,0.0000038353583,0.0003292808,0.000043566077,0.00009483048,0.975547,0.00019605324,0.00033213492,0.01000017,0.00015513839],"about_ca_topic_score_codex":0.00020810693,"about_ca_topic_score_gemma":0.003605209,"teacher_disagreement_score":0.80220926,"about_ca_system_score_codex":0.00020978539,"about_ca_system_score_gemma":0.000120151184,"threshold_uncertainty_score":0.80909157},"labels":[],"label_agreement":null},{"id":"W2977457995","doi":"10.1016/j.media.2019.101568","title":"Segmentation and quantification of infarction without contrast agents via spatiotemporal generative adversarial learning","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":71,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Western University","keywords":"Artificial intelligence; Computer science; Segmentation; Pattern recognition (psychology); Discriminator; Encoder; Generator (circuit theory); Centroid; Contrast (vision); Feature (linguistics); Power (physics)","score_opus":0.008969040013805935,"score_gpt":0.3076035449077018,"score_spread":0.29863450489389587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977457995","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":[0.6496129,0.00005924918,0.348339,0.0014155863,0.0000913229,0.00018554651,0.000001607543,0.000024982151,0.00026981038],"genre_scores_gemma":[0.9937786,0.00009070695,0.00482224,0.00036210977,0.00012278023,0.0000066355424,0.00029413486,0.000013450829,0.000509333],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982617,0.00017518531,0.0004278276,0.00029900693,0.0006830102,0.00015329057],"domain_scores_gemma":[0.9991493,0.00008412681,0.00025029664,0.00015606458,0.00015401216,0.00020616857],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007782631,0.00012268109,0.00046096116,0.0002940273,0.00006726745,0.000025136636,0.000057679263,0.000102111146,0.0012117189],"category_scores_gemma":[0.00069156324,0.000103826664,0.00013309564,0.0004750632,0.00016684581,0.00014661887,0.000030876232,0.00037274839,0.000020657037],"study_design_candidate":"observational","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":[0.00017204089,0.0001377869,0.82943213,0.000112043024,0.0017537898,0.000011117142,0.00072213187,0.00085836183,0.10922062,0.000048634556,0.00011006834,0.05742126],"study_design_scores_gemma":[0.0020479457,0.00014955428,0.16635124,0.000050545514,0.0018181397,0.000012552517,0.0002454051,0.82505447,0.0036709832,0.000020740812,0.00046684692,0.00011157113],"about_ca_topic_score_codex":0.0005269399,"about_ca_topic_score_gemma":0.000015046445,"teacher_disagreement_score":0.8241961,"about_ca_system_score_codex":0.000033688153,"about_ca_system_score_gemma":0.00006456335,"threshold_uncertainty_score":0.9997013},"labels":[],"label_agreement":null},{"id":"W2979808779","doi":"10.1016/j.media.2019.101587","title":"‘Squeeze & excite’ guided few-shot segmentation of volumetric images","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":166,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Bayerisches Staatsministerium für Bildung und Kultus, Wissenschaft und Kunst; Nvidia","keywords":"Artificial intelligence; Segmentation; Computer vision; Shot (pellet); Computer science; Image segmentation; Pattern recognition (psychology); Chemistry","score_opus":0.02131291264568962,"score_gpt":0.32293430772163023,"score_spread":0.3016213950759406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979808779","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":[0.055939782,0.00013385942,0.94071263,0.0013959787,0.00007197394,0.00017950841,0.0000048621646,0.000102734884,0.0014586492],"genre_scores_gemma":[0.7573558,0.00015683919,0.23882477,0.0008209337,0.00009420799,0.00004516517,0.000085208805,0.000015827247,0.0026012678],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975795,0.00011163835,0.0005333631,0.0005181447,0.0009789874,0.00027836388],"domain_scores_gemma":[0.99798566,0.00032359755,0.00025743016,0.0010021123,0.00022568386,0.0002055018],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044429037,0.0001501142,0.000395899,0.0005887245,0.00006443942,0.00006270446,0.001057788,0.000076489676,0.0012666469],"category_scores_gemma":[0.00034147233,0.00013404131,0.00026206105,0.006355573,0.0001117646,0.00053116964,0.0002913912,0.0001739631,0.00042266838],"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":[0.000040878967,0.0015598263,0.1664033,0.00025111734,0.0036650384,0.00010540655,0.0012573393,0.012910619,0.2499251,0.0075898278,0.08040439,0.47588715],"study_design_scores_gemma":[0.0025300728,0.00018891608,0.09153708,0.000068297166,0.0016984969,0.000038586983,0.000102838974,0.8280067,0.052123584,0.0060344324,0.016274879,0.0013961325],"about_ca_topic_score_codex":0.000080913014,"about_ca_topic_score_gemma":0.0000312041,"teacher_disagreement_score":0.8150961,"about_ca_system_score_codex":0.000049340997,"about_ca_system_score_gemma":0.00005150311,"threshold_uncertainty_score":0.9996463},"labels":[],"label_agreement":null},{"id":"W2979992932","doi":"10.1016/j.media.2020.101796","title":"BIAS: Transparent reporting of biomedical image analysis challenges","year":2020,"lang":"en","type":"preprint","venue":"Medical Image Analysis","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Toronto; Sunnybrook Health Science Centre","funders":"National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; Ministerstvo Školství, Mládeže a Tělovýchovy; Canadian Cancer Society; NIH Clinical Center; European Research Council; National Institutes of Health; National Science Foundation","keywords":"Interpretability; Checklist; Benchmarking; Computer science; Data science; Transparency (behavior); Set (abstract data type); Quality (philosophy); Artificial intelligence; Psychology; Business; Computer security","score_opus":0.4378958910839068,"score_gpt":0.501754488514744,"score_spread":0.06385859743083722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979992932","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":[0.45694745,0.009381246,0.34528998,0.18264505,0.0010525915,0.0011916815,0.0001967002,0.00042593738,0.002869393],"genre_scores_gemma":[0.9826076,0.0065054335,0.0069884346,0.00070470106,0.0010396622,0.00008618801,0.0019262421,0.000045286524,0.000096419586],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9892111,0.000386195,0.005742522,0.0013637696,0.0027096511,0.00058675505],"domain_scores_gemma":[0.9923801,0.00057444506,0.003237912,0.0013762285,0.0009994345,0.0014318988],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039152117,0.0004958931,0.0036465111,0.0020015629,0.00009735737,0.000049130846,0.00053391047,0.0009323441,0.004827206],"category_scores_gemma":[0.016340453,0.00041484673,0.0030734173,0.004450732,0.00066985184,0.00008039374,0.0003066613,0.0017254151,0.000063761094],"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":[0.0006527992,0.005751997,0.14376456,0.014571678,0.14157419,0.0057645505,0.03342771,0.00039199667,0.004246058,0.00012613687,0.0067174505,0.64301085],"study_design_scores_gemma":[0.0005987045,0.0012787736,0.1399884,0.0032243605,0.38130856,0.00009977859,0.024556752,0.40844297,0.028847601,0.0041238475,0.004816917,0.0027133361],"about_ca_topic_score_codex":0.0039252527,"about_ca_topic_score_gemma":0.0008866859,"teacher_disagreement_score":0.64029753,"about_ca_system_score_codex":0.00018070893,"about_ca_system_score_gemma":0.001374555,"threshold_uncertainty_score":0.99983037},"labels":[],"label_agreement":null},{"id":"W2981744453","doi":"10.1016/j.media.2019.101591","title":"Commensal correlation network between segmentation and direct area estimation for bi-ventricle quantification","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Benchmark (surveying); Segmentation; Computer science; Artificial intelligence; Inference; Differentiable function; Cardiac magnetic resonance imaging; Ventricle; Pattern recognition (psychology); Convergence (economics); Estimation; Algorithm; Magnetic resonance imaging; Mathematics; Medicine; Radiology; Cardiology","score_opus":0.020180454323840285,"score_gpt":0.3508524836921112,"score_spread":0.3306720293682709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981744453","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":[0.098609045,0.0000885949,0.898334,0.0019362879,0.000020033389,0.00065190066,0.00001647747,0.000094006245,0.00024965368],"genre_scores_gemma":[0.88071877,0.00008492876,0.116583124,0.0002704094,0.00009464673,0.00012374813,0.0017847924,0.000013437684,0.00032613298],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895793,0.000029394194,0.00031609682,0.00026247563,0.0002825295,0.00015155654],"domain_scores_gemma":[0.99909055,0.00028766092,0.00015066729,0.00022422966,0.00011428452,0.00013259269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041089338,0.00009630919,0.00030015683,0.00013735384,0.00010111436,0.000023444432,0.000047713827,0.000095692216,0.00024401587],"category_scores_gemma":[0.00017553817,0.00008527659,0.00011016029,0.00074305094,0.00004780579,0.0001297656,0.000019770454,0.00009910948,0.000027560773],"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":[0.00019511634,0.00041594447,0.71774673,0.00021199595,0.0010040493,0.0000052436326,0.00030280172,0.009561699,0.007314677,0.0016345548,0.014358672,0.24724849],"study_design_scores_gemma":[0.0008828771,0.00012130499,0.07182917,0.000049253984,0.0020721185,0.000002774283,0.000057019082,0.92008996,0.0017686208,0.00090400124,0.002085197,0.00013771415],"about_ca_topic_score_codex":0.000024679424,"about_ca_topic_score_gemma":0.0000034523678,"teacher_disagreement_score":0.91052824,"about_ca_system_score_codex":0.000049019767,"about_ca_system_score_gemma":0.000022887005,"threshold_uncertainty_score":0.34774783},"labels":[],"label_agreement":null},{"id":"W2982287615","doi":"10.1016/j.media.2019.101593","title":"Multi-indices quantification of optic nerve head in fundus image via multitask collaborative learning","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Multi-task learning; Artificial intelligence; Feature (linguistics); Fundus (uterus); Task (project management); Pattern recognition (psychology); Representation (politics); Feature learning; Ensemble learning; Segmentation; Machine learning","score_opus":0.014979672065277522,"score_gpt":0.33932552860065307,"score_spread":0.32434585653537557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982287615","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":[0.96984977,0.00058255583,0.026864516,0.0016298454,0.000039741924,0.00024508205,0.0000084964295,0.000053493754,0.0007265061],"genre_scores_gemma":[0.98293763,0.000096755415,0.015007871,0.00007775736,0.000042941938,0.000015493042,0.0002345483,0.000023515538,0.0015634923],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99686474,0.00035554802,0.0008568772,0.0005748422,0.000988399,0.00035961496],"domain_scores_gemma":[0.9980198,0.00029992094,0.00038789646,0.00048558207,0.0005193023,0.000287477],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013240835,0.00023708021,0.0011171765,0.0010964486,0.000061564184,0.000048883772,0.00021880376,0.00014393902,0.0014012015],"category_scores_gemma":[0.0015718179,0.00019527222,0.00045910972,0.0043111555,0.0002943356,0.0002491494,0.00006418043,0.0006525191,0.00029494535],"study_design_candidate":"observational","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":[0.00020152549,0.001117674,0.69631964,0.00033425138,0.0029112957,0.00068911334,0.0012917469,0.0008173217,0.282522,0.00000873097,0.00010058941,0.013686092],"study_design_scores_gemma":[0.0027595083,0.00024621704,0.22311926,0.00032079636,0.0042796917,0.000019029638,0.0025005862,0.75457114,0.011636666,0.000007685605,0.00019412978,0.00034529303],"about_ca_topic_score_codex":0.0016491084,"about_ca_topic_score_gemma":0.00028165933,"teacher_disagreement_score":0.75375384,"about_ca_system_score_codex":0.00008204605,"about_ca_system_score_gemma":0.0001593552,"threshold_uncertainty_score":0.99951166},"labels":[],"label_agreement":null},{"id":"W2982313557","doi":"10.1016/j.media.2019.101588","title":"A partial augmented reality system with live ultrasound and registered preoperative MRI for guiding robot-assisted radical prostatectomy","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Hospital and Health Sciences Centre; University of British Columbia","funders":"Canadian Institutes of Health Research; University of British Columbia","keywords":"Magnetic resonance imaging; Artificial intelligence; Sagittal plane; Computer science; Computer vision; Ultrasound; Augmented reality; Medicine; Prostatectomy; Image-guided surgery; Image registration; Robot; Prostate; Radiology; Image (mathematics)","score_opus":0.03819850888818283,"score_gpt":0.3235354810076974,"score_spread":0.2853369721195146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982313557","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":[0.8359826,0.00012790339,0.15634994,0.0020943575,0.00006140937,0.0017940644,0.000036108413,0.0002245396,0.003329058],"genre_scores_gemma":[0.99640465,0.000012550646,0.0023575127,0.00031915796,0.00009722048,0.00009099882,0.00026299412,0.00002128465,0.0004336373],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99754155,0.00020204978,0.0005502989,0.0005914971,0.0007678406,0.00034675293],"domain_scores_gemma":[0.99805975,0.00063103787,0.00017275405,0.00033748383,0.00025858326,0.0005403917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009391902,0.00021793088,0.00083354197,0.00016037736,0.0001339958,0.000083000916,0.000082646206,0.00015204313,0.0007076365],"category_scores_gemma":[0.00085392786,0.00014421505,0.00023263664,0.0007035564,0.0002235062,0.00011812997,0.00003367339,0.00018762932,0.000017146445],"study_design_candidate":"observational","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":[0.026024656,0.0029745966,0.8439004,0.005439637,0.045879155,0.0031390733,0.010899248,0.0014952983,0.007791855,0.0034438432,0.0015398283,0.04747243],"study_design_scores_gemma":[0.04101081,0.0017666802,0.31354347,0.0016363233,0.011192776,0.0003856785,0.007065159,0.61713386,0.0017520264,0.000019126763,0.0036057676,0.0008883451],"about_ca_topic_score_codex":0.00015746357,"about_ca_topic_score_gemma":0.000056205357,"teacher_disagreement_score":0.61563855,"about_ca_system_score_codex":0.000110342655,"about_ca_system_score_gemma":0.00013195028,"threshold_uncertainty_score":0.77481234},"labels":[],"label_agreement":null},{"id":"W3000109616","doi":"10.1016/j.media.2020.101638","title":"Deep Atlas Network for Efficient 3D Left Ventricle Segmentation on Echocardiography","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Key Research and Development Program of China Stem Cell and Translational Research; National Key Research and Development Program of China","keywords":"Segmentation; Artificial intelligence; Deep learning; Computer science; Hausdorff distance; Inference; Atlas (anatomy); Pattern recognition (psychology); Medicine; Anatomy","score_opus":0.011147254427377887,"score_gpt":0.27307106594755104,"score_spread":0.26192381152017313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000109616","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":[0.0020367906,0.00014332235,0.99182945,0.0053023244,0.00005797418,0.00028483718,0.0000034507882,0.00017287958,0.00016897607],"genre_scores_gemma":[0.6493055,0.000090139634,0.34219354,0.0074597048,0.0006699389,0.00014286791,0.00009896837,0.000021352767,0.000017983399],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980758,0.000075728596,0.00030083922,0.00055594766,0.00064631685,0.00034536226],"domain_scores_gemma":[0.9986791,0.00034297263,0.00011195589,0.000418342,0.000082447455,0.00036520595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023424588,0.00014165026,0.00027792665,0.00013458473,0.00020618844,0.000080161226,0.0006718647,0.00005726215,0.00008112158],"category_scores_gemma":[0.00015140117,0.00012688432,0.00040196264,0.0033251285,0.00006225974,0.0001160147,0.00013550301,0.00015355405,0.00007753993],"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":[0.000028537788,0.00015543439,0.0023806745,0.000013061277,0.0007371195,0.00003010091,0.00031901777,0.8755038,0.00034002206,0.0021963373,0.0076757623,0.11062018],"study_design_scores_gemma":[0.000267212,0.00006683234,0.0008878756,0.00000394681,0.00026066406,7.96576e-7,0.000011525777,0.9940306,0.0005707055,0.0004800322,0.0032866222,0.00013319775],"about_ca_topic_score_codex":0.0000031517263,"about_ca_topic_score_gemma":0.0000037754487,"teacher_disagreement_score":0.6496359,"about_ca_system_score_codex":0.000030203408,"about_ca_system_score_gemma":0.000019970046,"threshold_uncertainty_score":0.5174192},"labels":[],"label_agreement":null},{"id":"W3000524228","doi":"10.1016/j.media.2020.101636","title":"Improving cardiac MRI convolutional neural network segmentation on small training datasets and dataset shift: A continuous kernel cut approach","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research; British Heart Foundation; Medical Research Council; National Institute for Health and Care Research","keywords":"Segmentation; Convolutional neural network; Computer science; Artificial intelligence; Pattern recognition (psychology); Deep learning; Kernel (algebra); Market segmentation; Image segmentation; Scale-space segmentation; Machine learning; Mathematics","score_opus":0.01914023953641023,"score_gpt":0.28293529042554033,"score_spread":0.2637950508891301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000524228","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":[0.21046858,0.0015610098,0.73701406,0.044861104,0.0003704427,0.0010563389,0.0035020744,0.00032484496,0.0008415798],"genre_scores_gemma":[0.8799027,0.00016450323,0.032353893,0.026155606,0.0020883891,0.00005047893,0.059174564,0.00006510387,0.00004471323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970945,0.00024446222,0.0005237873,0.00074191164,0.0008993943,0.0004959598],"domain_scores_gemma":[0.9981671,0.0002830682,0.0001784091,0.00032665653,0.00003807357,0.0010067153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011115432,0.00027303197,0.0008517423,0.00014450823,0.0001923666,0.00011051384,0.00021614756,0.00013017122,0.00029107372],"category_scores_gemma":[0.0013927196,0.00022966045,0.00022858374,0.0006954712,0.0003390982,0.0001645117,0.000174732,0.00092439086,0.000016414158],"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":[0.0017802066,0.0012606126,0.1854486,0.0014617585,0.01719297,0.004374256,0.0078949295,0.010828523,0.0046362765,0.0009145208,0.29736468,0.46684265],"study_design_scores_gemma":[0.0018553822,0.00018572003,0.009304385,0.00004845737,0.003329467,0.0000410517,0.00044246885,0.97924787,0.0000228272,0.000019018353,0.00521603,0.00028731377],"about_ca_topic_score_codex":0.0002908823,"about_ca_topic_score_gemma":0.000009709991,"teacher_disagreement_score":0.9684194,"about_ca_system_score_codex":0.00004241976,"about_ca_system_score_gemma":0.000121191166,"threshold_uncertainty_score":0.93652815},"labels":[],"label_agreement":null},{"id":"W3006047402","doi":"10.1016/j.media.2020.101879","title":"Detect and correct bias in multi-site neuroimaging datasets","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":120,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Center for Research Resources; National Institute of General Medical Sciences; National Institute on Drug Abuse; National Institute of Mental Health; Leibniz-Rechenzentrum; Leibniz-Gemeinschaft; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; Servier; U.S. Department of Energy; Eisai; National Institute on Aging; Commonwealth Scientific and Industrial Research Organisation; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; Medpace; Bayerisches Staatsministerium für Bildung und Kultus, Wissenschaft und Kunst; Synarc; 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","keywords":"Neuroimaging; Artificial intelligence; Computer science; Pattern recognition (psychology); Machine learning; Psychology; Neuroscience","score_opus":0.09558029519063245,"score_gpt":0.32719995885862985,"score_spread":0.2316196636679974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006047402","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":[0.8268739,0.00040702417,0.07444241,0.09681006,0.00022191767,0.00029548726,0.0003296069,0.00026640802,0.00035322577],"genre_scores_gemma":[0.9751997,0.00009421043,0.0006100859,0.02398412,0.000049793325,0.000008839144,0.000021635413,0.00001160127,0.00002003787],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978885,0.00031956894,0.00024698616,0.0007223183,0.00056973484,0.0002529105],"domain_scores_gemma":[0.99563086,0.0038230713,0.000059597325,0.00021419348,0.000019379531,0.0002528873],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00042758198,0.00014845314,0.0003543812,0.00024314641,0.000103428254,0.000070268354,0.0002104683,0.00003826538,0.0002641984],"category_scores_gemma":[0.06398691,0.00013094673,0.00010324221,0.001979181,0.00026191788,0.00023344507,0.00034438397,0.00033506413,0.00008796532],"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":[0.00029141002,0.00045470713,0.51987094,0.00018332705,0.0006636649,0.009335887,0.0046171695,0.0005197832,0.3175296,0.000026170967,0.043111008,0.10339633],"study_design_scores_gemma":[0.0019396163,0.00013160011,0.13140881,0.000030751315,0.00066114444,0.000053089567,0.00024686626,0.82806414,0.026576778,0.00004476449,0.0102509335,0.0005914869],"about_ca_topic_score_codex":0.00020518308,"about_ca_topic_score_gemma":0.0005511017,"teacher_disagreement_score":0.8275444,"about_ca_system_score_codex":0.00001828355,"about_ca_system_score_gemma":0.000028261642,"threshold_uncertainty_score":0.94389755},"labels":[],"label_agreement":null},{"id":"W3006062690","doi":"10.1016/j.media.2020.101640","title":"SDAE-GAN: Enable high-dimensional pathological images in liver cancer survival prediction with a policy gradient based data augmentation method","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Feature (linguistics); Computer science; Immunohistochemistry; Pattern recognition (psychology); Artificial intelligence; Stage (stratigraphy); Pathology; Medicine; Biology","score_opus":0.04969742740291736,"score_gpt":0.335134612735509,"score_spread":0.2854371853325916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006062690","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":[0.0091910055,0.000108304324,0.97082895,0.019244349,0.00012373074,0.0001670541,0.00009477514,0.00015630234,0.000085514446],"genre_scores_gemma":[0.80914384,0.00010663305,0.1855109,0.004254009,0.0005120173,0.00010131278,0.0003117367,0.000019389441,0.000040137886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961427,0.0005854215,0.0004255631,0.001060054,0.0014197457,0.00036651056],"domain_scores_gemma":[0.9983916,0.00024370253,0.00016332467,0.0007057901,0.00014311115,0.0003524599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012202811,0.00021160196,0.00043277943,0.00040561383,0.00011526048,0.00012999891,0.0009864927,0.00012070202,0.00057076936],"category_scores_gemma":[0.00046560194,0.00016387866,0.00009704547,0.0037796416,0.00014301621,0.0009106534,0.00039522062,0.000373805,0.000018039616],"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":[0.0014086916,0.0022934445,0.08285283,0.00039519215,0.003574009,0.0058040842,0.0036735442,0.21038815,0.02481025,0.0013707657,0.02430962,0.6391194],"study_design_scores_gemma":[0.0009865502,0.00017672204,0.022560712,0.000022933418,0.0003251782,0.0000076239844,0.000028919228,0.9718389,0.0035166019,0.00009187361,0.00025754422,0.00018644184],"about_ca_topic_score_codex":0.0055138664,"about_ca_topic_score_gemma":0.0010139439,"teacher_disagreement_score":0.79995286,"about_ca_system_score_codex":0.00026936724,"about_ca_system_score_gemma":0.0004392602,"threshold_uncertainty_score":0.8335354},"labels":[],"label_agreement":null},{"id":"W3007894695","doi":"10.1016/j.media.2020.101670","title":"Embedding high-dimensional Bayesian optimization via generative modeling: Parameter personalization of cardiac electrophysiological models","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiac electrophysiology and arrhythmias","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health; National Science Foundation","keywords":"Embedding; Generative model; Computer science; Bayesian optimization; Dimension (graph theory); Parameter space; Dimensionality reduction; Bayesian probability; Artificial intelligence; Space (punctuation); Encoder; Code (set theory); Generative grammar; Range (aeronautics); Algorithm; Pattern recognition (psychology); Machine learning; Mathematics","score_opus":0.014823666582116634,"score_gpt":0.26777361907298153,"score_spread":0.2529499524908649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007894695","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":[0.23594625,0.00025741712,0.7616957,0.0018303774,0.000026262716,0.00013862243,0.0000105969475,0.000046929188,0.00004784206],"genre_scores_gemma":[0.96443355,0.00017514834,0.032151926,0.002078354,0.00038287125,0.00001916094,0.00071658846,0.0000208018,0.000021620232],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769837,0.000273307,0.00048448535,0.00053343683,0.00069959916,0.00031078342],"domain_scores_gemma":[0.998861,0.00011329621,0.00012835446,0.00021271262,0.00031901128,0.00036558975],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018804749,0.00022811402,0.001022757,0.00016955411,0.00010073582,0.000011194599,0.00009093276,0.00025220442,0.00095130765],"category_scores_gemma":[0.0004306735,0.00017964318,0.0007346308,0.0010682448,0.00016774148,0.00014058818,0.000061392646,0.00036858118,0.0000085666115],"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":[0.0004115417,0.00009275355,0.00004442551,0.000031713516,0.0021347885,0.00007906452,0.00016188872,0.94478905,0.0511295,0.00009341691,0.00019158724,0.00084029284],"study_design_scores_gemma":[0.00038455246,0.0003684823,0.000048220856,0.000014636352,0.0023044422,0.000009143449,0.000023689114,0.9926383,0.0036823668,0.00036007506,0.0000018281406,0.00016426001],"about_ca_topic_score_codex":0.00004092077,"about_ca_topic_score_gemma":6.236546e-7,"teacher_disagreement_score":0.7295438,"about_ca_system_score_codex":0.000047462232,"about_ca_system_score_gemma":0.00013263254,"threshold_uncertainty_score":0.999962},"labels":[],"label_agreement":null},{"id":"W3008167392","doi":"10.1016/j.media.2019.101612","title":"Trophectoderm segmentation in human embryo images via inceptioned U-Net","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Reproductive Biology and Fertility","field":"Medicine","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Hemophilia Society; Pacific Centre for Reproductive Medicine; Simon Fraser University","funders":"","keywords":"Jaccard index; Artificial intelligence; Segmentation; Computer science; Sørensen–Dice coefficient; Pattern recognition (psychology); Convolutional neural network; Dice; Deep learning; Image segmentation; Minimum bounding box; Machine learning; Image (mathematics); Mathematics; Statistics","score_opus":0.017150756764093975,"score_gpt":0.3192022697082575,"score_spread":0.3020515129441635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008167392","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":[0.93395126,0.00017902254,0.05336226,0.011412562,0.000026674692,0.00019833958,0.0000051633397,0.0000640359,0.00080069236],"genre_scores_gemma":[0.99616796,0.000030680865,0.0009142281,0.0022029341,0.00022193111,0.000019693143,0.00026108732,0.000007655117,0.0001738048],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99834394,0.00019957189,0.0003977666,0.0004894437,0.00037797418,0.00019132059],"domain_scores_gemma":[0.999283,0.000040665254,0.00007165639,0.00025927648,0.00008748847,0.0002579075],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00042695986,0.00012644574,0.00047583765,0.00016579461,0.0000643363,0.000010118133,0.00010424106,0.00012835559,0.004581114],"category_scores_gemma":[0.0007172916,0.00010094646,0.00019987496,0.001041923,0.0002745836,0.00010481278,0.000048793157,0.0003148191,0.00008133506],"study_design_candidate":"observational","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":[0.0007113331,0.00033029314,0.2638933,0.00006616589,0.0009409562,0.00033528617,0.00077091507,0.000007891792,0.72211367,0.0000057695347,0.0013412185,0.009483199],"study_design_scores_gemma":[0.001298387,0.00018679225,0.9608718,0.000009924636,0.0009491662,0.0000061672117,0.00021001301,0.0037259941,0.032408908,0.00011662433,0.00008842145,0.00012777785],"about_ca_topic_score_codex":0.00017084433,"about_ca_topic_score_gemma":0.000051030715,"teacher_disagreement_score":0.6969785,"about_ca_system_score_codex":0.00005227799,"about_ca_system_score_gemma":0.00004477791,"threshold_uncertainty_score":0.99632883},"labels":[],"label_agreement":null},{"id":"W3008753367","doi":"10.1016/j.media.2020.101668","title":"Contrast agent-free synthesis and segmentation of ischemic heart disease images using progressive sequential causal GANs","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":85,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Regularization (linguistics); Pixel; Pattern recognition (psychology); Leverage (statistics); Computer vision","score_opus":0.014827723108367795,"score_gpt":0.3162005930765553,"score_spread":0.3013728699681875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008753367","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":[0.87127286,0.001238983,0.09591488,0.03094203,0.000046774276,0.00029112995,0.0000622376,0.00006812285,0.0001629682],"genre_scores_gemma":[0.9835736,0.00009767387,0.013121478,0.002785939,0.00027343503,0.000015271613,0.00007917359,0.000026715597,0.000026697198],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978128,0.00014590069,0.00047342532,0.00040810413,0.00088424375,0.0002755299],"domain_scores_gemma":[0.99824595,0.0001898429,0.00017374479,0.0002705933,0.00012715999,0.0009927227],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038931565,0.0001888793,0.0006758359,0.00017872121,0.000083723906,0.000044457236,0.0001597941,0.000076092234,0.0011429851],"category_scores_gemma":[0.0049720006,0.00015695684,0.000260463,0.00059744244,0.00054400193,0.00013150719,0.00013999673,0.00034637435,0.00000452166],"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":[0.0007960108,0.00058587146,0.25335577,0.0013459368,0.0055872253,0.003184073,0.0012229424,0.00013320184,0.69638443,0.000023335431,0.016832288,0.020548912],"study_design_scores_gemma":[0.0063708387,0.0002799791,0.05453964,0.00078598777,0.035100464,0.0001981503,0.0009813018,0.80797714,0.091905266,0.00007185413,0.0010010626,0.00078832335],"about_ca_topic_score_codex":0.00014226144,"about_ca_topic_score_gemma":0.000001708691,"teacher_disagreement_score":0.8078439,"about_ca_system_score_codex":0.000036452388,"about_ca_system_score_gemma":0.00017815779,"threshold_uncertainty_score":0.9997701},"labels":[],"label_agreement":null},{"id":"W3009496543","doi":"10.1016/j.media.2020.101685","title":"An integrated deep learning framework for joint segmentation of blood pool and myocardium","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Segmentation; Pyramid (geometry); Pooling; Computer science; Artificial intelligence; Deep learning; Pattern recognition (psychology); Feature (linguistics); Task (project management); Image segmentation; Residual; Feature learning; Feature extraction; Computer vision; Engineering; Mathematics","score_opus":0.015040855844964224,"score_gpt":0.2940954518938342,"score_spread":0.27905459604886995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009496543","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":[0.009676892,0.00010684035,0.9866785,0.0032990125,0.000011596974,0.00012696734,0.0000023249636,0.00008632897,0.000011526231],"genre_scores_gemma":[0.5383782,0.000049682458,0.4607187,0.0007342092,0.000050707513,0.0000290687,0.000030361598,0.000005560919,0.00000353042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988286,0.000087348,0.00028019608,0.00035305033,0.00030484385,0.00014594663],"domain_scores_gemma":[0.9990613,0.00020971899,0.00013312079,0.00022986077,0.00011531161,0.00025069728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002027514,0.00009241737,0.00026759392,0.00008476027,0.00008470917,0.000049383863,0.00031554076,0.000063276544,0.0000454767],"category_scores_gemma":[0.0005923388,0.00008065555,0.00011285227,0.0014278298,0.0000793967,0.0002439008,0.000088417124,0.00020659377,0.0000027510546],"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":[0.000039921495,0.00035725397,0.004225766,0.00010167247,0.0023922487,0.000040492094,0.003945833,0.021355284,0.05565566,0.011919606,0.0002534901,0.8997128],"study_design_scores_gemma":[0.00021144436,0.00012760582,0.00058229594,0.0000076909055,0.00054311677,0.0000015965683,0.00014351883,0.9872495,0.009203447,0.0016728807,0.00015995881,0.00009695397],"about_ca_topic_score_codex":0.0000079169795,"about_ca_topic_score_gemma":0.0000041274843,"teacher_disagreement_score":0.9658942,"about_ca_system_score_codex":0.0000066662355,"about_ca_system_score_gemma":0.00001945764,"threshold_uncertainty_score":0.3289038},"labels":[],"label_agreement":null},{"id":"W3016428943","doi":"10.1016/j.media.2021.101988","title":"Magic DIAMOND: Multi-fascicle diffusion compartment imaging with tensor distribution modeling and tensor-valued diffusion encoding","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Philips (Canada); CARE Canada; Université de Sherbrooke","funders":"Université de Sherbrooke","keywords":"Diffusion MRI; Voxel; Tractography; Tensor (intrinsic definition); Computer science; Fascicle; Algorithm; Artificial intelligence; Mathematics; Statistical physics; Physics; Geometry; Geology; Magnetic resonance imaging","score_opus":0.03966792182640934,"score_gpt":0.34059918555620194,"score_spread":0.3009312637297926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016428943","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":[0.43619683,0.00023900048,0.5596755,0.0034841653,0.000009083069,0.00016483034,0.000019518875,0.00014408091,0.000067008055],"genre_scores_gemma":[0.9565727,0.00045632053,0.041277647,0.00082715997,0.000057971516,0.00003659382,0.00053273834,0.000026860233,0.00021201995],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784225,0.00007472805,0.00040253164,0.0006599391,0.00067044253,0.00035011],"domain_scores_gemma":[0.99864805,0.00007109737,0.000103851686,0.0004964858,0.00027312498,0.0004073787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023381693,0.00023206472,0.0005330235,0.00014791726,0.00027156458,0.00006554686,0.00010302332,0.00006037519,0.00018116325],"category_scores_gemma":[0.00029510676,0.00017481192,0.00017794165,0.0009601421,0.00019481328,0.00013784392,0.00019513149,0.0003462816,0.000008158474],"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":[0.00025766465,0.0032199305,0.69859374,0.000257283,0.0009261071,0.002954797,0.000525648,0.00081620406,0.24935327,0.00048435928,0.0008762555,0.041734748],"study_design_scores_gemma":[0.0013931732,0.00003433046,0.029745506,0.0001367539,0.0015211025,0.00014600612,0.000262089,0.962957,0.0030569695,0.00007952298,0.00045120274,0.00021630678],"about_ca_topic_score_codex":0.0000833887,"about_ca_topic_score_gemma":0.000018139843,"teacher_disagreement_score":0.96214086,"about_ca_system_score_codex":0.00009032093,"about_ca_system_score_gemma":0.000055071618,"threshold_uncertainty_score":0.7128623},"labels":[],"label_agreement":null},{"id":"W3018177167","doi":"10.1016/j.media.2020.101667","title":"Tripartite-GAN: Synthesizing liver contrast-enhanced MRI to improve tumor detection","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":111,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Western University","funders":"Primary Research and Development Plan of Zhejiang Province; Taishan Scholar Project of Shandong Province; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Discriminator; Convolutional neural network; Context (archaeology); Generator (circuit theory); Detector; Materials science; Artificial intelligence; Power (physics)","score_opus":0.007824679294856297,"score_gpt":0.272096335132687,"score_spread":0.2642716558378307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018177167","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":[0.22829929,0.00019581911,0.7413446,0.028058965,0.0001491707,0.00034079433,0.0000052314417,0.00022255824,0.0013836053],"genre_scores_gemma":[0.97288346,0.000063590756,0.004463241,0.02146962,0.00081317016,0.00003993434,0.000017202723,0.000037934416,0.00021184674],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970677,0.00014049925,0.0005826138,0.0006626237,0.0010447897,0.00050178025],"domain_scores_gemma":[0.9974511,0.0002771214,0.00013358553,0.00033192744,0.00016515778,0.0016410751],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007687132,0.00024891863,0.0008752788,0.00029497402,0.000112859816,0.00007767453,0.00023973155,0.000115383875,0.0022622603],"category_scores_gemma":[0.0069976114,0.00020479078,0.00047536538,0.0016337881,0.00015695508,0.00012363636,0.00008196335,0.00079636206,0.0003389165],"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":[0.0006047975,0.00034241402,0.0020062109,0.0002636143,0.002968987,0.0022393137,0.0020258091,0.0003118586,0.66164017,0.000018622924,0.0033381674,0.32424003],"study_design_scores_gemma":[0.0023996597,0.0005045576,0.0035014371,0.00012885155,0.0048381975,0.000047273137,0.00038658094,0.82196283,0.15132791,0.000013087007,0.014435712,0.0004539028],"about_ca_topic_score_codex":0.0002106934,"about_ca_topic_score_gemma":0.000033640827,"teacher_disagreement_score":0.821651,"about_ca_system_score_codex":0.000079500925,"about_ca_system_score_gemma":0.00011096966,"threshold_uncertainty_score":0.99864984},"labels":[],"label_agreement":null},{"id":"W3023773746","doi":"10.1016/j.media.2020.101714","title":"The reliability of a deep learning model in clinical out-of-distribution MRI data: A multicohort study","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"MRI in cancer diagnosis","field":"Medicine","cited_by":171,"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 on Aging; Canadian Institutes of Health Research; National Institutes of Health; IXICO; H. Lundbeck A/S; Servier; Karolinska Institutet; Alzheimerfonden; Swedish Brain Power; Hjärnfonden; Vetenskapsrådet; Eisai; Stiftelsen Olle Engkvist Byggmästare; Genentech; Stiftelsen för Strategisk Forskning; Center for Innovative Medicine; Northern California Institute for Research and Education; Stockholms Läns Landsting; DoD Alzheimer's Disease Neuroimaging Initiative; Pfizer; Biogen; BioClinica; Nvidia; University of Southern California; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Alzheimer's Association; Åke Wiberg Stiftelse","keywords":"Artificial intelligence; Computer science; Reliability (semiconductor); Deep learning; Convolutional neural network; Protocol (science); Machine learning; Neuroradiologist; Neuroimaging; Medical physics; Pattern recognition (psychology); Magnetic resonance imaging; Medicine; Pathology; Radiology","score_opus":0.07275462749978208,"score_gpt":0.42609457491245006,"score_spread":0.353339947412668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023773746","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":[0.78853947,0.0002940293,0.19116192,0.018996287,0.00007581964,0.00069580035,0.00006160379,0.000041527903,0.00013353051],"genre_scores_gemma":[0.9968489,0.0008575664,0.001691557,0.00024257382,0.00009778951,0.000029597371,0.00020836266,0.000010434046,0.0000132621735],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995982,0.00056319765,0.0014594061,0.0005866549,0.001181504,0.00022722782],"domain_scores_gemma":[0.9966168,0.0014372615,0.00029981395,0.0010437608,0.0002789497,0.00032343136],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005142118,0.00013211153,0.00096495025,0.000066424545,0.000048654838,0.000010799933,0.0005306237,0.0001294066,0.00020441352],"category_scores_gemma":[0.019519074,0.00008986767,0.00031650378,0.0012435033,0.00043695915,0.00009387089,0.000412549,0.0007684733,0.0000079881665],"study_design_candidate":"observational","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":[0.00026206195,0.001335287,0.97856516,0.000070757655,0.00096545974,0.00005494041,0.00082844804,0.0023034185,0.000020381663,0.0000021012438,0.0013344951,0.0142574655],"study_design_scores_gemma":[0.0013002503,0.00026534914,0.1328674,0.0000266522,0.0029713989,2.4986093e-7,0.00085827033,0.8611294,0.000035624053,0.000009272422,0.00046900666,0.00006711841],"about_ca_topic_score_codex":0.00039893715,"about_ca_topic_score_gemma":0.00082567014,"teacher_disagreement_score":0.858826,"about_ca_system_score_codex":0.00006477437,"about_ca_system_score_gemma":0.00019970154,"threshold_uncertainty_score":0.9887399},"labels":[],"label_agreement":null},{"id":"W3024398883","doi":"10.1016/j.media.2020.101728","title":"Prediction of inter-fractional radiotherapy dose plans with domain translation in spatiotemporal embeddings","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre de Santé et de Services Sociaux Cavendish; Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Artificial intelligence; Radiation therapy; Translation (biology); Artificial neural network; Machine learning; Pattern recognition (psychology); Medicine; Radiology","score_opus":0.012261696318670202,"score_gpt":0.27999613511641136,"score_spread":0.26773443879774117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024398883","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":[0.07310838,0.00003412327,0.9247201,0.0016060019,0.000009083583,0.00011518069,0.00006413554,0.000041844683,0.00030114996],"genre_scores_gemma":[0.9251513,0.000019843337,0.074229,0.00017890449,0.0001696399,0.000022423083,0.00020150117,0.000015955993,0.000011413462],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988699,0.00006589412,0.00034840792,0.00023339495,0.00035565998,0.0001267589],"domain_scores_gemma":[0.99952185,0.0000693237,0.00014238083,0.000116903786,0.000039651848,0.000109879526],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017054874,0.000121907455,0.0003254176,0.00018184894,0.00002480836,0.000013018272,0.00012008031,0.00005335477,0.0022875592],"category_scores_gemma":[0.000009075282,0.000101105725,0.00013960194,0.00082585367,0.00010484564,0.0002501851,0.0000064871047,0.00021601365,6.9596445e-7],"study_design_candidate":"observational","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":[0.00068629737,0.00052219944,0.8637156,0.000039491508,0.0027209993,0.000029760227,0.0049557295,0.0015987697,0.02062962,0.0005249882,0.00059772155,0.103978805],"study_design_scores_gemma":[0.009664051,0.0012106766,0.058614094,0.00020628073,0.0011113683,0.0000059037834,0.0016612813,0.89097285,0.020008426,0.0020160794,0.0135978395,0.00093114405],"about_ca_topic_score_codex":0.00023287168,"about_ca_topic_score_gemma":0.000035964717,"teacher_disagreement_score":0.8893741,"about_ca_system_score_codex":0.000031569518,"about_ca_system_score_gemma":0.000045757093,"threshold_uncertainty_score":0.9986245},"labels":[],"label_agreement":null},{"id":"W3024581418","doi":"10.1016/j.media.2020.101723","title":"Dynamically constructed network with error correction for accurate ventricle volume estimation","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Volume (thermodynamics); Residual; Algorithm; Ventricle; Constraint (computer-aided design); Artificial intelligence; Mathematics; Medicine","score_opus":0.010639167569552811,"score_gpt":0.28153158846780824,"score_spread":0.27089242089825544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024581418","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":[0.00085139344,0.000017037855,0.98987323,0.008225525,0.0001199641,0.00030131443,0.00000566755,0.000500781,0.00010511119],"genre_scores_gemma":[0.17596136,0.000008242522,0.81734234,0.0061185714,0.00015652795,0.00009464946,0.00018888124,0.000015935397,0.00011349303],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771976,0.00013659433,0.00045801298,0.0005036073,0.0008540692,0.00032796542],"domain_scores_gemma":[0.99835235,0.00024587827,0.00022510195,0.0003066575,0.00036405344,0.00050598854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045888772,0.00016233286,0.00036868238,0.00013156827,0.00014276513,0.00019333008,0.0006234731,0.00010103331,0.0006990213],"category_scores_gemma":[0.001898493,0.00013319033,0.00016255758,0.0027965475,0.00018627507,0.00058474735,0.000121723286,0.00021906134,0.000044360302],"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":[0.00019248256,0.0002488656,0.003498369,0.000115599214,0.0017096953,0.00025901728,0.00071960106,0.008417823,0.0009601797,0.00046774335,0.1296766,0.853734],"study_design_scores_gemma":[0.00040018995,0.00016152086,0.0008369461,0.000019050012,0.0003450521,0.000008837113,0.000030160343,0.99653935,0.0011751376,0.00015011421,0.00017168981,0.00016197236],"about_ca_topic_score_codex":0.000030131301,"about_ca_topic_score_gemma":0.000016647675,"teacher_disagreement_score":0.9881215,"about_ca_system_score_codex":0.000054045042,"about_ca_system_score_gemma":0.00014382895,"threshold_uncertainty_score":0.76537925},"labels":[],"label_agreement":null},{"id":"W3025299467","doi":"10.1016/j.media.2020.101722","title":"Dense biased networks with deep priori anatomy and hard region adaptation: Semi-supervised learning for fine renal artery segmentation","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Renal and Vascular Pathologies","field":"Medicine","cited_by":77,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Jiangsu Provincial Key Research and Development Program; National Natural Science Foundation of China","keywords":"Segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Feature (linguistics); Renal artery; Computer vision; Kidney; Medicine","score_opus":0.02783024500628021,"score_gpt":0.2722791180322217,"score_spread":0.2444488730259415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025299467","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":[0.29731897,0.00043488352,0.6969075,0.0050147446,0.000009799184,0.00022588819,8.9848214e-7,0.00006482968,0.000022485838],"genre_scores_gemma":[0.9757034,0.00031065723,0.021437734,0.0015859867,0.00031006764,0.000058432728,0.00043617474,0.000021450654,0.00013606416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985346,0.00012074221,0.0002956061,0.00038043433,0.00045715895,0.00021143742],"domain_scores_gemma":[0.999098,0.00016553227,0.000102550395,0.0001410941,0.00016380755,0.00032901615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002962381,0.00016067826,0.0004672248,0.00013576838,0.0001146217,0.000046382942,0.000061021332,0.00010751357,0.00012064057],"category_scores_gemma":[0.00063817494,0.0001126992,0.00021302342,0.0007673905,0.00012453714,0.00012193169,0.000027757975,0.00025538035,0.000003479849],"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":[0.0068623913,0.00052294537,0.24657188,0.0010907543,0.013790502,0.008584915,0.010459521,0.042294197,0.016423464,0.000026081107,0.004694117,0.64867926],"study_design_scores_gemma":[0.0034006578,0.00064197846,0.016812602,0.00008756916,0.003582756,0.00010242926,0.0010124957,0.97313863,0.00058120576,0.000005835984,0.0004603452,0.00017351595],"about_ca_topic_score_codex":0.000015052529,"about_ca_topic_score_gemma":0.000041312964,"teacher_disagreement_score":0.9308444,"about_ca_system_score_codex":0.00002007163,"about_ca_system_score_gemma":0.000053278156,"threshold_uncertainty_score":0.459574},"labels":[],"label_agreement":null},{"id":"W3033511611","doi":"10.1016/j.media.2020.101721","title":"MB-FSGAN: Joint segmentation and quantification of kidney tumor on CT by the multi-branch feature sharing generative adversarial network","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Primary Research and Development Plan of Zhejiang Province; Taishan Scholar Project of Shandong Province; National Natural Science Foundation of China","keywords":"Segmentation; Computer science; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology)","score_opus":0.026175718185868488,"score_gpt":0.28758356056552725,"score_spread":0.26140784237965875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033511611","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":[0.0063666673,0.00013520253,0.9568748,0.03625342,0.00006134393,0.00021903335,0.000013061783,0.000050241546,0.00002626286],"genre_scores_gemma":[0.8951125,0.00009934212,0.089945786,0.013984913,0.0004663491,0.000086589265,0.00016614035,0.000017304681,0.0001210689],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836165,0.00012668905,0.0003095193,0.00052496436,0.00049186667,0.00018529256],"domain_scores_gemma":[0.9988337,0.00014586236,0.00022532618,0.00040402208,0.00007548617,0.00031558215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029349595,0.00013909976,0.00026861773,0.00004879204,0.00020546562,0.000079083264,0.00052471453,0.000033960026,0.000039667815],"category_scores_gemma":[0.00035689893,0.00009977781,0.00011424482,0.0013865142,0.00013139175,0.00023083975,0.00015370721,0.00025986062,0.000011840864],"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":[0.00016970816,0.0007367944,0.0077089937,0.00014081279,0.0030780714,0.000098299395,0.0059746257,0.11822854,0.3296234,0.011841065,0.36393702,0.15846266],"study_design_scores_gemma":[0.0003983593,0.00003617537,0.0006052169,0.000012393309,0.00019766972,0.0000025700658,0.00003576044,0.9733418,0.023962712,0.00019470515,0.0010896972,0.00012294634],"about_ca_topic_score_codex":0.000023009467,"about_ca_topic_score_gemma":0.000012076114,"teacher_disagreement_score":0.88874584,"about_ca_system_score_codex":0.000023427852,"about_ca_system_score_gemma":0.000041749456,"threshold_uncertainty_score":0.4068821},"labels":[],"label_agreement":null},{"id":"W3035739940","doi":"10.1016/j.media.2020.101754","title":"Prediction of in-plane organ deformation during free-breathing radiotherapy via discriminative spatial transformer networks","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mitel (Canada); Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Artificial intelligence; Computer science; Ground truth; Segmentation; Discriminative model; Encoder; Computer vision; Pattern recognition (psychology)","score_opus":0.006308130476169781,"score_gpt":0.24193867177710657,"score_spread":0.23563054130093677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035739940","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":[0.096008085,0.000060743343,0.9030465,0.00048284561,0.000016884827,0.00013359619,0.00003367106,0.000048706675,0.00016899938],"genre_scores_gemma":[0.99191505,0.000069400936,0.0074514598,0.00008934625,0.00025956554,0.000018608418,0.00017183844,0.000017800601,0.000006946361],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987206,0.000075439384,0.00044562027,0.0002119894,0.00035188944,0.00019447361],"domain_scores_gemma":[0.99947697,0.00004260307,0.00014259688,0.00016448766,0.00004401716,0.00012934046],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016627261,0.00014822076,0.00039921573,0.00016419546,0.00005349631,0.000014831166,0.00020000493,0.00006849984,0.0015518771],"category_scores_gemma":[0.000018412116,0.00012714446,0.00017873179,0.0007392453,0.000085511296,0.0003468215,0.000014294376,0.00027479327,4.928969e-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":[0.0005223261,0.0007557232,0.43792,0.00021021812,0.005722202,0.000070942224,0.02582359,0.010218124,0.15606159,0.00032480163,0.00021901882,0.36215144],"study_design_scores_gemma":[0.0025456178,0.00018353999,0.03420234,0.00007347323,0.00070011616,0.000002843671,0.00051200384,0.8709694,0.090045035,0.00033268094,0.00009373745,0.00033918148],"about_ca_topic_score_codex":0.0007013324,"about_ca_topic_score_gemma":0.000036084944,"teacher_disagreement_score":0.8959069,"about_ca_system_score_codex":0.000050572475,"about_ca_system_score_gemma":0.000020066107,"threshold_uncertainty_score":0.99936086},"labels":[],"label_agreement":null},{"id":"W3037040939","doi":"10.1016/j.media.2020.101769","title":"The state-of-the-art in ultrasound-guided spine interventions","year":2020,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":47,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University; Montreal Neurological Institute and Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Usability; Workflow; Computer science; Initialization; Robustness (evolution); Visualization; Artificial intelligence; Reliability (semiconductor); Medical physics; Image registration; Radiology; Computer vision; Medicine; Human–computer interaction; Image (mathematics)","score_opus":0.025079506062803607,"score_gpt":0.33708206618333864,"score_spread":0.312002560120535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037040939","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000055588757,0.9717733,0.026474647,0.00059645134,0.0001915534,0.0001731391,0.000029872706,0.00008276536,0.0006726574],"genre_scores_gemma":[0.00008332119,0.9979839,0.0002136346,0.000061645995,0.00010228638,0.000058426827,0.00012242101,0.000043451473,0.00133096],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99612284,0.00039222257,0.0017401287,0.00034755928,0.0010060137,0.00039123106],"domain_scores_gemma":[0.99801004,0.0006015104,0.00025289343,0.00075178174,0.00006351605,0.00032025587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011872097,0.00037292307,0.0022037816,0.00040581467,0.0000847382,0.000083730134,0.0012368072,0.00016121872,0.0008586326],"category_scores_gemma":[0.003249503,0.0002016552,0.0036287252,0.005188259,0.0003718901,0.000056164714,0.00017099835,0.0011789133,0.00014768234],"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":[1.7449624e-7,0.000046292473,0.000033318815,0.0045450972,0.0048748534,0.00008150574,0.000040590392,0.00010794711,0.0000010793441,0.000007283924,0.017578265,0.9726836],"study_design_scores_gemma":[0.00011487779,0.0000047563813,0.000020660633,0.005268396,0.011246994,0.00001831358,0.000013932813,0.016610125,0.0000033713736,0.0000521051,0.96638453,0.0002619446],"about_ca_topic_score_codex":0.0000697231,"about_ca_topic_score_gemma":0.00030491114,"teacher_disagreement_score":0.97242165,"about_ca_system_score_codex":0.000106216525,"about_ca_system_score_gemma":0.0001381722,"threshold_uncertainty_score":0.9401425},"labels":[],"label_agreement":null},{"id":"W3037731665","doi":"10.1016/j.media.2020.101757","title":"Yottixel – An Image Search Engine for Large Archives of Histopathology Whole Slide Images","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":142,"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; Hamilton Health Sciences; Toronto General Hospital; Jacobs (Canada); Northern Digital (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Government of Ontario","keywords":"Computer science; Search engine indexing; Digital pathology; Pixel; Information retrieval; Mosaic; Atlas (anatomy); Search engine; Image retrieval; Artificial intelligence; Computer vision; Image (mathematics); Biology","score_opus":0.015046636709015432,"score_gpt":0.2963813551718508,"score_spread":0.2813347184628354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037731665","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":[0.005392466,0.00017669838,0.98400986,0.009654927,0.000077216566,0.00013262914,0.00005398196,0.00013323875,0.00036895994],"genre_scores_gemma":[0.6767409,0.00006410496,0.32082158,0.0015651438,0.0003596691,0.000055414675,0.000072840914,0.000027337433,0.00029303867],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976258,0.00024337422,0.0004330622,0.00065006013,0.0006242075,0.0004234513],"domain_scores_gemma":[0.9983828,0.000312198,0.00012207245,0.0006219155,0.00014678811,0.00041421686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007698418,0.00016515295,0.00051274884,0.00034962277,0.00010553442,0.00006181462,0.0011824353,0.000087801716,0.00023284588],"category_scores_gemma":[0.00070507976,0.00015268484,0.00035603816,0.0013345766,0.00022910425,0.0004686275,0.00035397868,0.00027748133,0.000024662018],"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":[0.00023264396,0.0010172667,0.0042609023,0.0005717288,0.0012524547,0.00065239595,0.011597867,0.0005515531,0.5126089,0.0018482995,0.010470485,0.4549355],"study_design_scores_gemma":[0.0008043276,0.00038952174,0.00319775,0.000010820227,0.00034751708,0.000009664359,0.00014840357,0.9412728,0.04809556,0.0005291622,0.00495751,0.00023694447],"about_ca_topic_score_codex":0.00005744,"about_ca_topic_score_gemma":0.00003693903,"teacher_disagreement_score":0.9407213,"about_ca_system_score_codex":0.00003229098,"about_ca_system_score_gemma":0.00012853584,"threshold_uncertainty_score":0.62263066},"labels":[],"label_agreement":null},{"id":"W3041342951","doi":"10.1016/j.media.2020.101783","title":"Holistic multitask regression network for multiapplication shape regression segmentation","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Artificial intelligence; Computer science; Regression; Segmentation; Multi-task learning; Pattern recognition (psychology); Regression analysis; Machine learning; Task (project management); Mathematics; Statistics","score_opus":0.025699172228552274,"score_gpt":0.3124252000212351,"score_spread":0.2867260277926828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041342951","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":[0.021591835,0.00069178286,0.97329897,0.003425016,0.00011310912,0.00022288441,0.000028315057,0.00044893837,0.00017918262],"genre_scores_gemma":[0.9473923,0.0004361916,0.047732905,0.0016971548,0.0011294712,0.00016050521,0.0012720929,0.000057197383,0.00012221931],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792236,0.000071878916,0.0005140066,0.00041917252,0.00071153766,0.00036103182],"domain_scores_gemma":[0.9986648,0.000247872,0.00009971923,0.00027210964,0.00010581254,0.0006097089],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00041818924,0.00023459735,0.0005145166,0.00014224423,0.00014572489,0.00006384768,0.00027815314,0.00015692522,0.0012596672],"category_scores_gemma":[0.00093700964,0.00017836585,0.00037680703,0.0014964037,0.00008709978,0.0001512466,0.000046808833,0.0002737906,0.00009326016],"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":[0.000056562996,0.00017532447,0.008621836,0.0006369108,0.003406353,0.000078863726,0.00086371106,0.0409132,0.032580778,0.000051956387,0.16446014,0.74815434],"study_design_scores_gemma":[0.0005115853,0.0000134792745,0.00051368476,0.000066588,0.0015435246,6.872715e-7,0.000104497914,0.9920797,0.0015262592,0.00004967347,0.003384754,0.00020558294],"about_ca_topic_score_codex":0.000023783969,"about_ca_topic_score_gemma":0.00000787427,"teacher_disagreement_score":0.9511665,"about_ca_system_score_codex":0.000046009558,"about_ca_system_score_gemma":0.000020296675,"threshold_uncertainty_score":0.99965334},"labels":[],"label_agreement":null},{"id":"W3041500444","doi":"10.1016/j.media.2020.101770","title":"Supervised learning with cyclegan for low-dose FDG PET image denoising","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":194,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Siemens (Canada); University Health Network","funders":"National University Cancer Institute, Singapore","keywords":"Artificial intelligence; Noise reduction; Image denoising; Computer science; Pattern recognition (psychology); Computer vision; Supervised learning; Artificial neural network","score_opus":0.015696871443824582,"score_gpt":0.3122459519873317,"score_spread":0.2965490805435071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041500444","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":[0.19663544,0.00005161424,0.7156268,0.08556194,0.000010909316,0.0005432566,0.0000130515255,0.0005097593,0.001047271],"genre_scores_gemma":[0.8072988,0.00007347823,0.18229368,0.00886226,0.0004177228,0.0001516965,0.00040816853,0.000064596294,0.000429582],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751717,0.000069917434,0.00047522134,0.0005868674,0.0009062563,0.00044458927],"domain_scores_gemma":[0.99785906,0.00022123949,0.00011371011,0.00039584475,0.00026043717,0.001149729],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00051596423,0.00023909788,0.00072662695,0.00018306625,0.00019565602,0.00008476505,0.00028334273,0.000090457375,0.0021000342],"category_scores_gemma":[0.0019226437,0.00017807719,0.00039777943,0.0014838334,0.00034236562,0.00013932292,0.00009492382,0.0006290942,0.00006400408],"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":[0.0024806515,0.003467251,0.053899862,0.0035870497,0.012804301,0.008671779,0.004384463,0.00010755369,0.62201524,0.0011352807,0.15982524,0.12762135],"study_design_scores_gemma":[0.005659722,0.0008308559,0.0029891366,0.00038616036,0.010125021,0.00016827729,0.0008695956,0.9282851,0.018452669,0.0001233587,0.031313162,0.00079694367],"about_ca_topic_score_codex":0.00007507787,"about_ca_topic_score_gemma":0.000009929992,"teacher_disagreement_score":0.92817754,"about_ca_system_score_codex":0.000039442566,"about_ca_system_score_gemma":0.00017444715,"threshold_uncertainty_score":0.9988122},"labels":[],"label_agreement":null},{"id":"W3042519501","doi":"10.1016/j.media.2020.101791","title":"Attention convolutional neural network for accurate segmentation and quantification of lesions in ischemic stroke disease","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":126,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Hunan Provincial Science and Technology Department; National Natural Science Foundation of China","keywords":"Hyperintensity; Stroke (engine); Segmentation; Convolutional neural network; Lesion; Magnetic resonance imaging; Artificial intelligence; Ischemic stroke; Medicine; Computer science; Pattern recognition (psychology); Cardiology; Radiology; Ischemia; Pathology","score_opus":0.029334498782924903,"score_gpt":0.31634122606994886,"score_spread":0.287006727287024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042519501","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":[0.703766,0.00030534324,0.2810177,0.014203054,0.000029202936,0.0004386752,0.00007291366,0.000023811941,0.00014334614],"genre_scores_gemma":[0.9931065,0.00009379687,0.004596845,0.0008306022,0.00012278168,0.000055884797,0.0010566551,0.000008443756,0.00012850948],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868345,0.000041545434,0.00041809274,0.00028451785,0.00041566472,0.00015674197],"domain_scores_gemma":[0.99925834,0.00011190836,0.00014581706,0.00013337078,0.00009026504,0.00026028286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026427506,0.00009784024,0.00030099694,0.00012907304,0.00003539425,0.0000103847615,0.00006937624,0.00004937005,0.00019787012],"category_scores_gemma":[0.00048702312,0.00008907844,0.00016695277,0.00058910117,0.00011023273,0.00009954899,0.000052637726,0.00010745389,0.000003600695],"study_design_candidate":"observational","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":[0.0015309405,0.00048342947,0.72744995,0.00085965835,0.0026847525,0.00008580754,0.00026575994,0.0020934897,0.1575259,0.0001714216,0.07910738,0.027741507],"study_design_scores_gemma":[0.0019215897,0.00006511613,0.30034104,0.00005078497,0.0032171044,0.0000012473008,0.00026216326,0.6920954,0.001084506,0.000007844848,0.00084467634,0.000108541644],"about_ca_topic_score_codex":0.000023854313,"about_ca_topic_score_gemma":0.000009845397,"teacher_disagreement_score":0.6900019,"about_ca_system_score_codex":0.00003176079,"about_ca_system_score_gemma":0.00004838887,"threshold_uncertainty_score":0.36325133},"labels":[],"label_agreement":null},{"id":"W3042619146","doi":"10.1016/j.media.2020.101792","title":"Handling confounding variables in statistical shape analysis - application to cardiac remodelling","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiovascular Function and Risk Factors","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Agència de Gestió d'Ajuts Universitaris i de Recerca; Horizon 2020; Instituto de Salud Carlos III; Ministerio de Economía y Competitividad; “la Caixa” Foundation","keywords":"Confounding; Robustness (evolution); Statistics; Medicine; Computer science; Artificial intelligence; Internal medicine; Mathematics; Biology","score_opus":0.014677644115568107,"score_gpt":0.2970592467573982,"score_spread":0.2823816026418301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042619146","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":[0.083916076,0.0001433744,0.91290736,0.00219301,0.000046191162,0.00021031487,0.000019908253,0.000075790645,0.00048798166],"genre_scores_gemma":[0.98781747,0.00016637656,0.00939751,0.0017803751,0.00028248903,0.00002555582,0.00045412625,0.000019457684,0.000056642974],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997223,0.00015715025,0.00057839503,0.0006222033,0.0011027834,0.0003164237],"domain_scores_gemma":[0.99829096,0.00024013469,0.00006504072,0.00036460074,0.00014464739,0.00089463964],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010941726,0.00018306711,0.0011795248,0.0008101975,0.00007908479,0.000058144502,0.00012214237,0.00015268262,0.0019595653],"category_scores_gemma":[0.0014774709,0.00015760568,0.00093752303,0.006177599,0.00006894088,0.000070807124,0.00006349229,0.0003692051,0.00012081106],"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":[0.00042075934,0.00026458653,0.85097945,0.0001854488,0.0414461,0.0005125421,0.0020058046,0.04077974,0.00490127,0.00044924492,0.0009831704,0.0570719],"study_design_scores_gemma":[0.00053801143,0.000036883368,0.04640949,0.000019632549,0.020765472,0.0000021212877,0.0003188942,0.9267359,0.00017191947,0.000011670748,0.0047904286,0.00019962012],"about_ca_topic_score_codex":0.0008174955,"about_ca_topic_score_gemma":0.000100252975,"teacher_disagreement_score":0.9039014,"about_ca_system_score_codex":0.00011056911,"about_ca_system_score_gemma":0.00010828452,"threshold_uncertainty_score":0.9989528},"labels":[],"label_agreement":null},{"id":"W3089090082","doi":"10.1016/j.media.2020.101813","title":"Deep neural network models for computational histopathology: A survey","year":2020,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":727,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"National Cancer Institute; Canadian Cancer Society","keywords":"Artificial intelligence; Artificial neural network; Computer science; Deep learning; Pattern recognition (psychology); Machine learning","score_opus":0.0621987312965477,"score_gpt":0.3509627319969386,"score_spread":0.28876400070039093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089090082","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.6954435e-8,0.46812782,0.5310004,0.0002661695,0.0002693466,0.00019424692,0.000018873887,0.00009284675,0.000030291043],"genre_scores_gemma":[0.000020579522,0.8949793,0.10220981,0.0008832692,0.00077344396,0.0002854836,0.00074353564,0.000045771743,0.00005884251],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99567,0.0009309958,0.0009276632,0.0010856485,0.0009219204,0.00046375723],"domain_scores_gemma":[0.9966986,0.001537223,0.0005034455,0.00063698145,0.00024840032,0.0003753242],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016665603,0.00040267067,0.0022881995,0.0003464367,0.00017900634,0.00015529562,0.0018036413,0.00038474024,0.00009212264],"category_scores_gemma":[0.0005963183,0.00034852893,0.0014366329,0.0037009427,0.00015764502,0.00029301664,0.0004708187,0.0006069004,0.000045273788],"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":[0.0000028591382,0.00001956075,0.000004191076,0.00053246395,0.0006191214,0.00008623459,0.00002438275,0.0312806,2.169676e-9,0.0002138272,0.0030323018,0.96418446],"study_design_scores_gemma":[0.00009106142,0.000034699144,0.000011219009,0.00011389578,0.0019848738,0.000028904271,4.0771948e-7,0.79121536,5.0824567e-9,0.0012692604,0.2050026,0.00024773867],"about_ca_topic_score_codex":0.00006638058,"about_ca_topic_score_gemma":0.00018160562,"teacher_disagreement_score":0.96393675,"about_ca_system_score_codex":0.00026855967,"about_ca_system_score_gemma":0.00048820267,"threshold_uncertainty_score":0.99989665},"labels":[],"label_agreement":null},{"id":"W3089741206","doi":"10.1016/j.media.2021.102191","title":"Realistic image normalization for multi-Domain segmentation","year":2021,"lang":"en","type":"preprint","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Fonds Québécois de la Recherche sur la Nature et les Technologies; Nvidia","keywords":"Normalization (sociology); Computer science; Artificial intelligence; Segmentation; Dice; Pattern recognition (psychology); Adversarial system; Image segmentation; Spatial normalization; Machine learning; Mathematics","score_opus":0.028599127600292113,"score_gpt":0.35044219239771185,"score_spread":0.32184306479741975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089741206","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":[0.00073326373,0.00016399314,0.9955503,0.0024522631,0.00018527948,0.0005445641,0.00005369824,0.00021494583,0.00010170594],"genre_scores_gemma":[0.013935868,0.00024812637,0.9804571,0.00090528873,0.0002229446,0.0007267872,0.0032635902,0.00002825987,0.00021201355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968143,0.00020846979,0.0006965936,0.0010826545,0.00083135004,0.00036663833],"domain_scores_gemma":[0.9974113,0.00027879231,0.00041275824,0.0011040171,0.00050059066,0.00029255406],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005878073,0.00029620828,0.0005803066,0.00033637,0.00020785442,0.00041076538,0.0011874426,0.00025458614,0.00017037637],"category_scores_gemma":[0.0006236382,0.0002984464,0.00051283115,0.0018689013,0.00012440984,0.00043390138,0.0010936789,0.0004055213,0.000017570177],"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":[0.00012425528,0.005767866,0.004679924,0.0037323823,0.019428441,0.0019946941,0.010409837,0.15626438,0.037153132,0.04131208,0.04607143,0.6730616],"study_design_scores_gemma":[0.000344303,0.000010586827,0.00044857178,0.000037860234,0.0007303746,0.0000041789376,0.000053463158,0.9946304,0.0009963481,0.0021416713,0.00028954883,0.00031268824],"about_ca_topic_score_codex":0.00009120664,"about_ca_topic_score_gemma":0.00028342698,"teacher_disagreement_score":0.83836603,"about_ca_system_score_codex":0.00014560856,"about_ca_system_score_gemma":0.0002021177,"threshold_uncertainty_score":0.9999468},"labels":[],"label_agreement":null},{"id":"W3091088513","doi":"10.1016/j.media.2020.101916","title":"Fully automated left atrium segmentation from anatomical cine long-axis MRI sequences using deep convolutional neural network with unscented Kalman filter","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Canadian VIGOUR Centre","funders":"Servier; Mitacs","keywords":"Artificial intelligence; Convolutional neural network; Segmentation; Computer science; Kalman filter; Sørensen–Dice coefficient; Pattern recognition (psychology); Computer vision; Artificial neural network; Image segmentation; Deep learning; Ground truth","score_opus":0.01682712962209134,"score_gpt":0.3152889253414733,"score_spread":0.298461795719382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091088513","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":[0.25657183,0.00019628703,0.73064613,0.011717652,0.000018637098,0.0002936371,0.00003828614,0.0004778573,0.000039714563],"genre_scores_gemma":[0.8745783,0.000061884326,0.11926588,0.00364597,0.00043554435,0.000019686977,0.001940524,0.000026538484,0.000025702344],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770266,0.00008473476,0.00051265646,0.0005511758,0.00078932673,0.00035943574],"domain_scores_gemma":[0.9986587,0.00010038694,0.00018430836,0.00027360773,0.00022479624,0.00055816333],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013765857,0.0002388025,0.00057569036,0.00012042349,0.00015838504,0.000033514134,0.00017860894,0.00014420606,0.0027359214],"category_scores_gemma":[0.00010441139,0.00018472297,0.00022674593,0.0014314264,0.00034778166,0.00017302381,0.00007287519,0.0003581601,0.00002082757],"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":[0.0019736362,0.001102045,0.78217494,0.0001698082,0.0066601215,0.002768704,0.00089570624,0.10831729,0.06876878,0.00024513603,0.01977495,0.0071489043],"study_design_scores_gemma":[0.0010181837,0.00013146647,0.035190225,0.000046317964,0.0023483625,0.00003845103,0.00010235288,0.95935726,0.0013023767,0.000048024816,0.00021267863,0.00020428827],"about_ca_topic_score_codex":0.00026498598,"about_ca_topic_score_gemma":0.00017948578,"teacher_disagreement_score":0.85104,"about_ca_system_score_codex":0.00011267328,"about_ca_system_score_gemma":0.00012605525,"threshold_uncertainty_score":0.99817574},"labels":[],"label_agreement":null},{"id":"W3091878842","doi":"10.1016/j.media.2020.101838","title":"ELNet:Automatic classification and segmentation for esophageal lesions using convolutional neural network","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Esophageal Cancer Research and Treatment","field":"Medicine","cited_by":78,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Jiangsu Provincial Key Research and Development Program; China Scholarship Council; National Natural Science Foundation of China","keywords":"Convolutional neural network; Artificial intelligence; Segmentation; Computer science; Lesion; Pattern recognition (psychology); Esophageal cancer; Deep learning; Image segmentation; Medicine; Pathology; Cancer","score_opus":0.06490156277561017,"score_gpt":0.37936036881238244,"score_spread":0.3144588060367723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091878842","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":[0.73938113,0.0050139087,0.23016506,0.023902576,0.000058064797,0.0011787533,0.00006669396,0.00013214457,0.00010164733],"genre_scores_gemma":[0.9842168,0.00007316449,0.013225496,0.0015868694,0.00036434014,0.00006759492,0.00040629364,0.000012105861,0.00004730751],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984909,0.00007797898,0.00028265564,0.00029203988,0.0006016899,0.00025470706],"domain_scores_gemma":[0.9989654,0.00016720471,0.00007334262,0.000113413575,0.00011207756,0.0005686046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024070776,0.00011445213,0.0003261291,0.000093073475,0.0001716829,0.00003354125,0.000057299025,0.00006339117,0.0007486272],"category_scores_gemma":[0.00034150062,0.00009226212,0.00017392667,0.00065303326,0.00014075312,0.00009641958,0.00003461269,0.00013723903,0.000010467209],"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":[0.0013429071,0.0011098271,0.7291805,0.0012411063,0.012544599,0.0012305462,0.0012535121,0.0020097243,0.0090440465,0.0011190111,0.014604728,0.22531949],"study_design_scores_gemma":[0.001522252,0.00023475174,0.12302569,0.000017009857,0.0020545153,0.00001226842,0.00009179284,0.87272716,0.00015151483,0.000060538925,0.000036443675,0.00006607405],"about_ca_topic_score_codex":0.00005293795,"about_ca_topic_score_gemma":0.000016975227,"teacher_disagreement_score":0.8707174,"about_ca_system_score_codex":0.000092697424,"about_ca_system_score_gemma":0.00015664374,"threshold_uncertainty_score":0.8196942},"labels":[],"label_agreement":null},{"id":"W3092065674","doi":"10.1016/j.media.2020.101826","title":"Automatic vertebrae recognition from arbitrary spine MRI images by a category-Consistent self-calibration detection framework","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Discriminative model; Artificial intelligence; Computer science; Bounding overwatch; Pattern recognition (psychology); Calibration; Computer vision; Mathematics","score_opus":0.006815777504003528,"score_gpt":0.2115675228620812,"score_spread":0.20475174535807766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092065674","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":[0.075642295,0.00085213775,0.9149505,0.006583984,0.00012654511,0.00010621813,0.000058728594,0.0013279103,0.00035168274],"genre_scores_gemma":[0.9665984,0.0006454803,0.027037725,0.003935801,0.0005163494,0.000051189898,0.0011313147,0.000060133378,0.000023606312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973018,0.00017873426,0.00071021065,0.00051133934,0.00093659305,0.00036128153],"domain_scores_gemma":[0.99861145,0.0001839844,0.00010101976,0.0003246939,0.00007025627,0.0007086197],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029357357,0.00031254394,0.00068511453,0.00023898749,0.00010912605,0.00016796944,0.0002688682,0.00027448998,0.005799628],"category_scores_gemma":[0.0008019517,0.00028666426,0.0004741707,0.0019510001,0.00010626973,0.00037064025,0.00004791561,0.0006880908,0.00030721092],"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":[0.000028966635,0.0008971077,0.004235332,0.0011813367,0.030275451,0.0009158029,0.0033790679,0.0014630868,0.07921731,0.000026634836,0.122995555,0.7553843],"study_design_scores_gemma":[0.00030642742,0.000023696271,0.00041075458,0.00005717319,0.0035672453,0.00000226523,0.00012786532,0.9771121,0.016911414,0.0006044537,0.00053053774,0.00034607484],"about_ca_topic_score_codex":0.00022466242,"about_ca_topic_score_gemma":0.000019598954,"teacher_disagreement_score":0.975649,"about_ca_system_score_codex":0.000076275406,"about_ca_system_score_gemma":0.000040220784,"threshold_uncertainty_score":0.9999586},"labels":[],"label_agreement":null},{"id":"W3092480895","doi":"10.1016/j.media.2020.101852","title":"Discriminative and generative models for anatomical shape analysis on point clouds with deep neural networks","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research; Bayerisches Staatsministerium für Wissenschaft, Forschung und Kunst","keywords":"Discriminative model; Artificial intelligence; Generative grammar; Point cloud; Computer science; Artificial neural network; Generative model; Point (geometry); Pattern recognition (psychology); Deep neural networks; Deep learning; Mathematics; Geometry","score_opus":0.014336654568467324,"score_gpt":0.24223078918025806,"score_spread":0.22789413461179073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092480895","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":[0.085622385,0.0003469134,0.9106485,0.0029210057,0.000014463524,0.00011297968,0.000033378117,0.00015596031,0.0001443918],"genre_scores_gemma":[0.9923529,0.0001032222,0.005709678,0.001300001,0.00019496455,0.00004774557,0.0002352524,0.00004223177,0.000014024934],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978221,0.00009601002,0.0004149616,0.0006469906,0.00058238895,0.00043755618],"domain_scores_gemma":[0.99864376,0.00023421277,0.00006848031,0.00026751324,0.00014375556,0.00064225646],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027823265,0.0003648182,0.0010393149,0.00042464727,0.00014225132,0.000120749624,0.00025319657,0.00015853386,0.00025315085],"category_scores_gemma":[0.00013535154,0.00027189215,0.0006622265,0.0027623195,0.00016897768,0.00019215753,0.000060477196,0.00040578507,0.0000028406935],"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":[0.000059456175,0.000035694797,0.00034504427,0.000019287489,0.010128577,0.000042844393,0.00067552325,0.97919416,0.000020830264,0.00008597266,0.00016835117,0.00922427],"study_design_scores_gemma":[0.00047170185,0.00011371057,0.00013196058,0.0000065772665,0.014082202,9.510413e-7,0.00033329762,0.98434174,0.000075236596,0.00009898795,0.000006895412,0.0003367286],"about_ca_topic_score_codex":0.000031629937,"about_ca_topic_score_gemma":0.00019876208,"teacher_disagreement_score":0.9067305,"about_ca_system_score_codex":0.000047047448,"about_ca_system_score_gemma":0.000014420971,"threshold_uncertainty_score":0.9999733},"labels":[],"label_agreement":null},{"id":"W3092490063","doi":"10.1016/j.media.2020.101861","title":"Sequential conditional reinforcement learning for simultaneous vertebral body detection and segmentation with modeling the spine anatomy","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":47,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Minimum bounding box; Pattern recognition (psychology); Reinforcement learning; Context (archaeology); Deep learning; Feature (linguistics); Image segmentation; Artificial neural network; Computer vision; Image (mathematics)","score_opus":0.007901384006566854,"score_gpt":0.24945136659967931,"score_spread":0.24154998259311247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092490063","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":[0.061982,0.00008306307,0.9362802,0.0013628788,0.000017896298,0.000100451485,0.0000025848778,0.00011703403,0.000053894924],"genre_scores_gemma":[0.9977333,0.000055064567,0.0012090465,0.00051294715,0.00017699055,0.000032367094,0.00023103949,0.000015924825,0.000033333177],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987329,0.000039986367,0.000270149,0.0002118438,0.0005443549,0.0002007339],"domain_scores_gemma":[0.99948174,0.00007680378,0.000039826056,0.000079023324,0.00007882025,0.0002438153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002300188,0.00013677818,0.0002450263,0.0000994352,0.00018415866,0.00007618789,0.00009207348,0.000052408235,0.0003389944],"category_scores_gemma":[0.00034208188,0.00009419903,0.00012730328,0.00054366846,0.00008906169,0.00012197726,0.000022530814,0.000258504,0.0000061909886],"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":[0.000009248257,0.000007292184,0.00012281505,0.000050721137,0.0012525405,0.000025316205,0.0001985097,0.9854934,0.004429252,0.000009924056,0.000059994847,0.008340948],"study_design_scores_gemma":[0.0005536949,0.000042146552,0.00001479761,0.000010082717,0.0015076639,0.0000045590846,0.00024581223,0.9959792,0.001309282,0.000016732985,0.00019463759,0.00012142633],"about_ca_topic_score_codex":0.00004288603,"about_ca_topic_score_gemma":0.00002071646,"teacher_disagreement_score":0.93575126,"about_ca_system_score_codex":0.00003243511,"about_ca_system_score_gemma":0.00001927329,"threshold_uncertainty_score":0.3841325},"labels":[],"label_agreement":null},{"id":"W3093149564","doi":"10.1016/j.media.2020.101847","title":"A deep community based approach for large scale content based X-ray image retrieval","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Image retrieval; Deep learning; Artificial intelligence; Scale (ratio); Automatic image annotation; Feature (linguistics); Image (mathematics); Content-based image retrieval; Pattern recognition (psychology); Data mining; Information retrieval; Computer vision","score_opus":0.04811755281095157,"score_gpt":0.2887763633008569,"score_spread":0.2406588104899053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093149564","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":[0.00035308997,0.00005572394,0.9863426,0.011849631,0.000025624673,0.00039307965,0.000041332834,0.00052045885,0.00041844128],"genre_scores_gemma":[0.29866177,0.000008293555,0.68628275,0.014353307,0.00009522402,0.00008705979,0.00040284224,0.00002398983,0.00008478604],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99639314,0.0006819913,0.00061685924,0.00061696826,0.0011777927,0.00051323656],"domain_scores_gemma":[0.9969683,0.0004944403,0.00021736379,0.0010681319,0.0005792648,0.00067248853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024629508,0.00027144304,0.00065096054,0.00025361968,0.00042946692,0.0003018059,0.002064436,0.00019133434,0.00031296525],"category_scores_gemma":[0.0018814936,0.00022659106,0.00074694405,0.0030299441,0.00023149296,0.00041514946,0.0002923147,0.00062993413,0.000031247735],"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":[0.0047496096,0.039925937,0.016243098,0.0064106435,0.012221531,0.00090586214,0.018027252,0.0006558364,0.6670262,0.012653771,0.053212687,0.16796754],"study_design_scores_gemma":[0.001178144,0.00015248562,0.00033062437,0.000009426212,0.00036541856,6.32659e-7,0.00020328187,0.946321,0.049551938,0.00003696034,0.0015834804,0.00026659627],"about_ca_topic_score_codex":0.000042657673,"about_ca_topic_score_gemma":0.000008401463,"teacher_disagreement_score":0.9456652,"about_ca_system_score_codex":0.00006967885,"about_ca_system_score_gemma":0.00020506246,"threshold_uncertainty_score":0.9240115},"labels":[],"label_agreement":null},{"id":"W3094447715","doi":"10.1016/j.media.2020.101872","title":"Unifying neural learning and symbolic reasoning for spinal medical report generation","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Domain (mathematical analysis); Machine learning; Deep learning; Artificial neural network; Segmentation; Graph; Theoretical computer science","score_opus":0.01925856031216853,"score_gpt":0.29782291182126175,"score_spread":0.2785643515090932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094447715","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":[0.20943028,0.0012890323,0.7805294,0.00757494,0.00010237832,0.00008440662,0.0000026461491,0.00043308892,0.0005538743],"genre_scores_gemma":[0.993103,0.00040316582,0.004109965,0.0009860884,0.0010607403,0.000022963586,0.0001849615,0.00003559676,0.00009351911],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974046,0.00009370642,0.0005924551,0.00044529437,0.0010782633,0.0003857346],"domain_scores_gemma":[0.99848735,0.00012521398,0.00007562575,0.00015332206,0.00008861189,0.0010698627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010190833,0.0002128224,0.00059069926,0.00020267013,0.00017808109,0.00011526901,0.00019128327,0.00017399482,0.00077452377],"category_scores_gemma":[0.0057481406,0.0001906495,0.0002994348,0.0010623885,0.00014389533,0.00014758979,0.00007073058,0.00060563436,0.000011041226],"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":[0.000055221615,0.0001779269,0.12668142,0.001397039,0.012491068,0.009138007,0.0020787339,0.021290854,0.016177738,0.00036208218,0.024619339,0.78553057],"study_design_scores_gemma":[0.0003065538,0.000026099298,0.00043549735,0.000036408775,0.0012085257,0.00006583867,0.00010500238,0.9936449,0.00018791384,0.0000060381585,0.0037716741,0.00020555458],"about_ca_topic_score_codex":0.000047423313,"about_ca_topic_score_gemma":0.0000120311315,"teacher_disagreement_score":0.97235405,"about_ca_system_score_codex":0.0000242686,"about_ca_system_score_gemma":0.000053128162,"threshold_uncertainty_score":0.8480492},"labels":[],"label_agreement":null},{"id":"W3095505136","doi":"10.1016/j.media.2020.101887","title":"Bone and joint enhancement filtering: Application to proximal femur segmentation from uncalibrated computed tomography datasets","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Orthopaedic implants and arthroplasty","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hotchkiss Brain Institute; Alberta Bone and Joint Health Institute; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Artificial intelligence; Computer vision; Hausdorff distance; Computer science; Femur; Image segmentation; Pattern recognition (psychology); Mathematics; Medicine","score_opus":0.015063896182320723,"score_gpt":0.26937526624213015,"score_spread":0.2543113700598094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095505136","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":[0.46874905,0.00009689287,0.52094805,0.009360623,0.0000249226,0.00041110176,0.00027856836,0.000078914134,0.000051860483],"genre_scores_gemma":[0.9701977,0.00004119952,0.01551282,0.0071468963,0.0002124258,0.00004204197,0.0068200864,0.000013460732,0.000013410191],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822795,0.00005024065,0.0004402295,0.00047028737,0.00060956023,0.00020170712],"domain_scores_gemma":[0.9989012,0.00003255169,0.00009749669,0.00021542332,0.00004873923,0.00070462195],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016804076,0.00015722067,0.00046156993,0.00018049161,0.00007677866,0.000048764756,0.00005334094,0.00006330869,0.0013743738],"category_scores_gemma":[0.00011376204,0.00012682177,0.000111389454,0.0009893521,0.0000835211,0.00010354986,0.00012237307,0.00014672494,0.000054664382],"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":[0.00080582063,0.0011196218,0.08424666,0.00029143778,0.0045452183,0.00094157463,0.0019170536,0.00003641975,0.54971784,0.000024338895,0.029833438,0.3265206],"study_design_scores_gemma":[0.008116259,0.0015998596,0.34615514,0.00028211984,0.0070858565,0.000057912082,0.00074154785,0.48841995,0.112413384,0.000029121307,0.034062132,0.0010367193],"about_ca_topic_score_codex":0.00012832074,"about_ca_topic_score_gemma":0.000029904459,"teacher_disagreement_score":0.5054352,"about_ca_system_score_codex":0.000014528479,"about_ca_system_score_gemma":0.000037781912,"threshold_uncertainty_score":0.9995385},"labels":[],"label_agreement":null},{"id":"W3095560178","doi":"10.1016/j.media.2021.102306","title":"Surgical data science – from concepts toward clinical translation","year":2021,"lang":"en","type":"preprint","venue":"Medical Image Analysis","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University Health Network; Queen's University","funders":"H2020 European Research Council; National Institute of Biomedical Imaging and Bioengineering; National Institute of Diabetes and Digestive and Kidney Diseases; NIHR Imperial Biomedical Research Centre; Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Science of Learning Institute, Johns Hopkins University; Horizon 2020 Framework Programme; University of Toronto; Ministry of Education, Culture, Sports, Science and Technology; Royal Society; Bundesministerium für Bildung und Forschung; National Institute for Health and Care Research; National Institutes of Health; Agence Nationale de la Recherche; Bundesministerium für Wirtschaft und Energie; Royal Academy of Engineering; Wellcome Trust; Polytechnique Montréal; Deutsche Forschungsgemeinschaft; Deutsches Krebsforschungszentrum; Memorial Sloan-Kettering Cancer Center; Johns Hopkins University; National Cancer Institute; HORIZON EUROPE Framework Programme; U.S. Department of Defense; Wellcome / EPSRC Centre for Interventional and Surgical Sciences; Nationales Centrum für Tumorerkrankungen Heidelberg; Nvidia; Université de Strasbourg; National Institute of Dental and Craniofacial Research; Bundesministerium für Forschung und Technologie","keywords":"Data science; Translational research; Data sharing; Field (mathematics); Translational science; Computer science; Analytics; Medicine; Pathology","score_opus":0.5100521637426162,"score_gpt":0.6062329828184161,"score_spread":0.0961808190757999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095560178","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":[0.888553,0.0044561294,0.06810265,0.033646043,0.00258726,0.000502796,0.00019183158,0.0001437735,0.0018164654],"genre_scores_gemma":[0.97388583,0.0037806525,0.009231141,0.0011698075,0.002662597,0.000018596274,0.009158846,0.000020289523,0.00007224015],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933678,0.00041001226,0.0017058271,0.0017414192,0.002322976,0.0004519647],"domain_scores_gemma":[0.99397993,0.0011726216,0.00031740443,0.0024589193,0.0008884836,0.0011826543],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0046280613,0.0002686154,0.0012899302,0.00039927015,0.0001527315,0.00021273798,0.0011507402,0.00078011036,0.00912662],"category_scores_gemma":[0.0061420705,0.00023286726,0.0006178675,0.0018929946,0.0015249234,0.00034443504,0.0009043036,0.0018570155,0.00012151671],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016646634,0.0010733074,0.11449486,0.00021435795,0.0024937235,0.0015022662,0.0026634051,0.000023669918,0.000105398074,0.000016029813,0.0020658507,0.87518066],"study_design_scores_gemma":[0.00082945323,0.00030325638,0.087223634,0.0017153019,0.03153316,0.000085774474,0.009107077,0.8391566,0.004130459,0.0011221418,0.023117552,0.0016755409],"about_ca_topic_score_codex":0.007373315,"about_ca_topic_score_gemma":0.00077733654,"teacher_disagreement_score":0.8735051,"about_ca_system_score_codex":0.00014073351,"about_ca_system_score_gemma":0.005056888,"threshold_uncertainty_score":0.99923664},"labels":[],"label_agreement":null},{"id":"W3097943992","doi":"10.1016/j.media.2021.102146","title":"Self-paced and self-consistent co-training for semi-supervised image segmentation","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"National Natural Science Foundation of China-Zhejiang Joint Fund for the Integration of Industrialization and Informatization; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Segmentation; Robustness (evolution); Cross entropy; Image segmentation; Machine learning; Pattern recognition (psychology); Entropy (arrow of time); Training set; Deep neural networks; Artificial neural network; Deep learning","score_opus":0.02099580457286689,"score_gpt":0.2998354642452361,"score_spread":0.27883965967236923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097943992","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":[0.015112495,0.00017857652,0.9786273,0.0035986092,0.00007334471,0.00014703428,0.000005257646,0.00028132505,0.001976049],"genre_scores_gemma":[0.17911251,0.00018362787,0.81684923,0.003010694,0.000104555555,0.000058745492,0.00014618477,0.000020098849,0.00051433063],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977861,0.00023325901,0.00039068397,0.00056565896,0.0006894802,0.00033478864],"domain_scores_gemma":[0.99848586,0.0004287145,0.000118534466,0.00035566103,0.00024879686,0.00036241228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009677361,0.00016749009,0.00037564116,0.00022200143,0.0002508923,0.00042160737,0.0002927697,0.00009029755,0.0003624401],"category_scores_gemma":[0.00059055176,0.00016051714,0.00025176743,0.0011148098,0.00006826025,0.00047637473,0.00012648282,0.00017506657,0.000028461842],"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":[0.000109648856,0.0030921085,0.014732017,0.0012950753,0.019985216,0.003180213,0.12812562,0.00056488375,0.11883905,0.012968614,0.013596879,0.68351066],"study_design_scores_gemma":[0.0014767697,0.000044669698,0.0015613068,0.000017530207,0.0007049582,0.000032436063,0.0024231335,0.9836975,0.00298204,0.00017115795,0.006607286,0.00028125025],"about_ca_topic_score_codex":0.000009678991,"about_ca_topic_score_gemma":0.00002137174,"teacher_disagreement_score":0.9831326,"about_ca_system_score_codex":0.000052981322,"about_ca_system_score_gemma":0.000219671,"threshold_uncertainty_score":0.6545699},"labels":[],"label_agreement":null},{"id":"W3098535516","doi":"10.1016/j.media.2021.102038","title":"SoftSeg: Advantages of soft versus binary training for image segmentation","year":2021,"lang":"en","type":"preprint","venue":"Medical Image Analysis","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"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; Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Canada First Research Excellence Fund; Canada Research Chairs; Canada Foundation for Innovation; Nvidia","keywords":"Artificial intelligence; Segmentation; Computer science; Pattern recognition (psychology); Voxel; Preprocessor; Binary classification; Image segmentation; Binary number; Ground truth; Pixel; Mathematics; Support vector machine","score_opus":0.04295141484576424,"score_gpt":0.35170314741180464,"score_spread":0.3087517325660404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098535516","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":[0.0085933525,0.0003877187,0.98821247,0.0013335588,0.0005137476,0.0002026702,0.000020433963,0.0001311402,0.0006049356],"genre_scores_gemma":[0.27607518,0.00021549201,0.72153616,0.00047898164,0.00020836561,0.00012235761,0.0009526757,0.00003584693,0.00037491592],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99656343,0.00026528665,0.00076503353,0.0008549187,0.0011786803,0.00037263945],"domain_scores_gemma":[0.99715483,0.0009009348,0.0005317578,0.00074072735,0.00039481878,0.00027694547],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001286059,0.00029122838,0.0008347472,0.00059424504,0.00013613874,0.00031953078,0.0010998924,0.00025774285,0.0006593671],"category_scores_gemma":[0.001860161,0.00029312164,0.000851025,0.0011611312,0.0001887189,0.00046775726,0.0008307184,0.0005455249,0.00001021693],"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":[0.00029981037,0.00082916423,0.00067305326,0.0013999315,0.011229511,0.0010499703,0.028625071,0.018131558,0.020888116,0.0012239165,0.002227303,0.9134226],"study_design_scores_gemma":[0.0016401914,0.00011523376,0.0008775242,0.00014717068,0.0015839175,0.0000044351596,0.0043206797,0.9883269,0.0015595137,0.0003073503,0.00063021784,0.000486874],"about_ca_topic_score_codex":0.000049628336,"about_ca_topic_score_gemma":0.000032755885,"teacher_disagreement_score":0.97019535,"about_ca_system_score_codex":0.00007326889,"about_ca_system_score_gemma":0.00050681323,"threshold_uncertainty_score":0.9999521},"labels":[],"label_agreement":null},{"id":"W3107625569","doi":"10.1016/j.media.2020.101912","title":"Learning to segment images with classification labels","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Cancer Society","keywords":"Computer science; Segmentation; Artificial intelligence; Ground truth; Annotation; Class (philosophy); Task (project management); Pattern recognition (psychology); Image segmentation; Labeled data; Machine learning","score_opus":0.015341976670133681,"score_gpt":0.2692718852778553,"score_spread":0.2539299086077216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107625569","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":[0.008840118,0.00002329205,0.9540822,0.035966113,0.000027653055,0.000071418785,6.296569e-7,0.00021008386,0.0007784931],"genre_scores_gemma":[0.9284187,0.000022077866,0.06730404,0.0038483397,0.00013718149,0.00003339992,0.000006288426,0.000009626745,0.00022035743],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814165,0.00011047806,0.00020028555,0.0004772985,0.0008706614,0.00019962677],"domain_scores_gemma":[0.9990355,0.000064738255,0.000076923374,0.00030558257,0.00011825275,0.00039904608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033020444,0.000104877254,0.00020625126,0.00015053319,0.0001036131,0.00014905522,0.000563387,0.00004493176,0.00030005616],"category_scores_gemma":[0.00029778396,0.00008383366,0.000080857484,0.0028404456,0.000049161867,0.0003058654,0.00016868852,0.00023408102,0.00021474269],"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":[0.000066290915,0.00016249742,0.023711646,0.00006184959,0.0017964663,0.00029099573,0.006902458,0.0075078364,0.026462086,0.00039182222,0.013859446,0.9187866],"study_design_scores_gemma":[0.00039934914,0.00048514464,0.01603515,0.000020763171,0.00043071277,0.00000578009,0.00036769328,0.95983356,0.012184679,0.000039000664,0.009863051,0.00033512147],"about_ca_topic_score_codex":0.000042132135,"about_ca_topic_score_gemma":0.000019204092,"teacher_disagreement_score":0.9523257,"about_ca_system_score_codex":0.000069181915,"about_ca_system_score_gemma":0.00006813659,"threshold_uncertainty_score":0.34186372},"labels":[],"label_agreement":null},{"id":"W3111025719","doi":"10.1016/j.media.2020.101939","title":"Image registration: Maximum likelihood, minimum entropy and deep learning","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; Canadian Institutes of Health Research; National Cancer Institute; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; Ontario Trillium Foundation","keywords":"Mutual information; Pairwise comparison; Artificial intelligence; Image registration; Computer science; Discriminative model; Entropy (arrow of time); Kullback–Leibler divergence; Metric (unit); Pattern recognition (psychology); Maximum likelihood; Iterative method; Principle of maximum entropy; Upper and lower bounds; Mathematics; Algorithm; Image (mathematics); Statistics","score_opus":0.009946999533290153,"score_gpt":0.26882140144290256,"score_spread":0.2588744019096124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111025719","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":[0.000643996,0.00023323922,0.97145694,0.025814453,0.000037466925,0.00011472184,0.000001231732,0.0004674757,0.0012304985],"genre_scores_gemma":[0.1106,0.00072363066,0.8746031,0.013340737,0.00038251403,0.000043755408,0.00007363385,0.000027979615,0.00020467355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966576,0.00028918847,0.00058021815,0.00073161366,0.0013433553,0.00039801942],"domain_scores_gemma":[0.9980039,0.00019353279,0.00020259987,0.0004165605,0.00016878315,0.0010146007],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00073890237,0.00021856994,0.00044731348,0.00020522354,0.0001655656,0.0004289121,0.0008746075,0.0001296516,0.0018923141],"category_scores_gemma":[0.0021354773,0.00019635864,0.00020779086,0.0017434912,0.0004082066,0.00081348256,0.0004146308,0.00050067715,0.00014442763],"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":[0.000032763342,0.00025521088,0.0033866952,0.00017335043,0.0012514183,0.0021500974,0.00391349,0.0000036932106,0.044823367,0.0009446437,0.019745639,0.92331964],"study_design_scores_gemma":[0.001166369,0.0003497464,0.0016125654,0.000034961544,0.0007871262,0.000041336138,0.00048437857,0.9688911,0.018258097,0.0023474563,0.0053279996,0.0006988589],"about_ca_topic_score_codex":0.00004306147,"about_ca_topic_score_gemma":0.0000121166195,"teacher_disagreement_score":0.9688874,"about_ca_system_score_codex":0.000029571414,"about_ca_system_score_gemma":0.00008116009,"threshold_uncertainty_score":0.9990201},"labels":[],"label_agreement":null},{"id":"W3125868735","doi":"10.1016/j.media.2021.101976","title":"Synthesis of gadolinium-enhanced liver tumors on nonenhanced liver MR images using pixel-level graph reinforcement learning","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Pixel; Reinforcement learning; Computer science; Artificial intelligence; Graph; Computer vision; Pattern recognition (psychology); Theoretical computer science","score_opus":0.01843634630885849,"score_gpt":0.30063667401865585,"score_spread":0.28220032770979736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125868735","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":[0.517811,0.0006174409,0.47607952,0.0012780302,0.00012185148,0.00018932192,0.000007209137,0.000101163976,0.0037944785],"genre_scores_gemma":[0.9764043,0.0014107142,0.018731972,0.0012527952,0.00025334652,0.000018413291,0.00008440165,0.000057168705,0.001786878],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953042,0.00032609786,0.0010507316,0.0007689738,0.0019173804,0.00063258054],"domain_scores_gemma":[0.99689317,0.00079743506,0.00044124832,0.0006604405,0.0005332679,0.0006744365],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001317536,0.00039281702,0.0014466265,0.00075617275,0.00021696373,0.00005527368,0.0002933534,0.00021444044,0.004534174],"category_scores_gemma":[0.008361416,0.00033783054,0.00094859314,0.0020428253,0.0005276604,0.0001494317,0.00019776086,0.0012154366,0.000063745974],"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":[0.0008942104,0.0022765817,0.012610751,0.001815472,0.0125945285,0.009165173,0.0019893001,0.018727459,0.76940686,0.00023098361,0.001893563,0.16839515],"study_design_scores_gemma":[0.0022462278,0.00029615045,0.011107308,0.0018122953,0.007828319,0.00015391095,0.00058470794,0.50866336,0.46613526,0.000028124294,0.0004478295,0.0006964967],"about_ca_topic_score_codex":0.0003794677,"about_ca_topic_score_gemma":0.00001424727,"teacher_disagreement_score":0.4899359,"about_ca_system_score_codex":0.00012528052,"about_ca_system_score_gemma":0.00037201447,"threshold_uncertainty_score":0.9999916},"labels":[],"label_agreement":null},{"id":"W3126367900","doi":"10.1016/j.media.2021.101982","title":"OF-UMRN: Uncertainty-guided multitask regression network aided by optical flow for fully automated comprehensive analysis of carotid artery","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiovascular Health and Disease Prevention","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Primary Research and Development Plan of Zhejiang Province; Taishan Scholar Project of Shandong Province; National Natural Science Foundation of China","keywords":"Optical flow; Artificial intelligence; Computer science; Regression; Regression analysis; Carotid arteries; Machine learning; Pattern recognition (psychology); Mathematics; Medicine; Statistics; Cardiology; Image (mathematics)","score_opus":0.016314441597565253,"score_gpt":0.3334473112606048,"score_spread":0.31713286966303955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126367900","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":[0.6956051,0.010636304,0.28683072,0.0041233557,0.00029594338,0.0013100747,0.00053965655,0.00030333747,0.0003555203],"genre_scores_gemma":[0.96320575,0.00059079437,0.02556141,0.0011460623,0.00021536839,0.00008629422,0.008987448,0.00003275826,0.00017408577],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961072,0.0003735378,0.0011877716,0.00056467147,0.0013180946,0.000448721],"domain_scores_gemma":[0.99628466,0.00052073604,0.0002981773,0.0007798313,0.0013417653,0.000774829],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00079674023,0.00024441237,0.002104359,0.0004938654,0.000085331194,0.000015354122,0.00012973869,0.00025861096,0.0009593943],"category_scores_gemma":[0.0019776758,0.00020150558,0.0032527307,0.003923319,0.00021541279,0.00006329783,0.00008856165,0.00020806397,0.0000036737235],"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":[0.005633903,0.0066903783,0.087410636,0.008577687,0.43102083,0.0023606564,0.000819286,0.11912788,0.0788614,0.00017035443,0.20472062,0.054606386],"study_design_scores_gemma":[0.0042869863,0.00008878502,0.043190807,0.0002449654,0.08725776,0.00002074474,0.00021365985,0.861135,0.002708914,0.00002475138,0.0006052222,0.0002224016],"about_ca_topic_score_codex":0.00016688628,"about_ca_topic_score_gemma":0.0001175167,"teacher_disagreement_score":0.74200714,"about_ca_system_score_codex":0.00008221019,"about_ca_system_score_gemma":0.00046094105,"threshold_uncertainty_score":0.99995387},"labels":[],"label_agreement":null},{"id":"W3128158496","doi":"10.1016/j.media.2021.102256","title":"Self-supervised driven consistency training for annotation efficient histopathology image analysis","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Canadian Cancer Society; Compute Canada","keywords":"Consistency (knowledge bases); Benchmark (surveying); Bootstrapping (finance); Annotation; Feature (linguistics); Pattern recognition (psychology); Feature learning; Representation (politics); Transfer of learning","score_opus":0.017349676241491793,"score_gpt":0.28616298130608026,"score_spread":0.26881330506458845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128158496","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":[0.021987954,0.00023211553,0.97288036,0.003387124,0.00025739503,0.00014688507,0.000014998495,0.00025865034,0.0008345001],"genre_scores_gemma":[0.5414662,0.000046432993,0.45694587,0.0009581598,0.0001501845,0.00010997578,0.00013018819,0.000017510603,0.00017551078],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965624,0.00037737927,0.0006717983,0.0010039515,0.0009083592,0.00047606748],"domain_scores_gemma":[0.99738824,0.00046547662,0.00023075264,0.0009137262,0.00070121296,0.00030056445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010968349,0.00022425587,0.0007713737,0.00087623345,0.00029247694,0.00018206977,0.00068373163,0.00017621969,0.00044917158],"category_scores_gemma":[0.0010373819,0.00022464861,0.0009733014,0.006676189,0.00017951815,0.00028501634,0.00020223334,0.00024206005,0.000029699462],"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":[0.00018793036,0.0038623514,0.019044697,0.00082847633,0.047507927,0.007143521,0.061768014,0.034654126,0.073391035,0.0104719065,0.005948152,0.7351919],"study_design_scores_gemma":[0.00054689747,0.00005245281,0.0033687425,0.000006632326,0.005118866,0.000023498882,0.00030210864,0.9881503,0.0011816015,0.00019590829,0.0008030544,0.00024996808],"about_ca_topic_score_codex":0.0000444483,"about_ca_topic_score_gemma":0.00023168224,"teacher_disagreement_score":0.95349616,"about_ca_system_score_codex":0.0002516183,"about_ca_system_score_gemma":0.00043988437,"threshold_uncertainty_score":0.9160905},"labels":[],"label_agreement":null},{"id":"W3129517280","doi":"10.1016/j.media.2021.102005","title":"Weakly-Supervised teacher-Student network for liver tumor segmentation from non-enhanced images","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Contrast (vision); Liver tumor; Minimum bounding box; Pattern recognition (psychology); Image (mathematics); Computer vision; Medicine","score_opus":0.007663096682908042,"score_gpt":0.30743983234332845,"score_spread":0.2997767356604204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129517280","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":[0.4051259,0.00096318446,0.58502746,0.0067205313,0.00025986574,0.00033977735,0.000020156702,0.00010172446,0.0014414295],"genre_scores_gemma":[0.79973453,0.00067550293,0.17980519,0.010338049,0.0026810828,0.00017019799,0.0021987152,0.000084606676,0.004312138],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694407,0.00016322109,0.0006099505,0.00068322656,0.001090215,0.0005093321],"domain_scores_gemma":[0.9980636,0.00039073057,0.00015224305,0.00048332696,0.00029928997,0.0006107634],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00082356273,0.00026446124,0.0008805845,0.00015001181,0.00018994279,0.000114066264,0.0002371068,0.00012929866,0.006819699],"category_scores_gemma":[0.0015863113,0.00022528059,0.0006638914,0.00097487797,0.00017666798,0.00013021674,0.00012875456,0.00058481283,0.00007260839],"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":[0.00055338885,0.0030384609,0.16385593,0.00044716598,0.019469177,0.0061319624,0.0035654388,0.001505278,0.2910387,0.0000414324,0.13730726,0.3730458],"study_design_scores_gemma":[0.0080320975,0.00029004092,0.12603334,0.00044683056,0.016543474,0.000054833818,0.0019731296,0.80776244,0.032530706,0.00022880897,0.00529046,0.0008138547],"about_ca_topic_score_codex":0.00038596883,"about_ca_topic_score_gemma":0.0000820523,"teacher_disagreement_score":0.8062571,"about_ca_system_score_codex":0.00010427663,"about_ca_system_score_gemma":0.00022996914,"threshold_uncertainty_score":0.9940882},"labels":[],"label_agreement":null},{"id":"W3130628855","doi":"10.1016/j.media.2021.101984","title":"EIS-Net: Segmenting early infarct and scoring ASPECTS simultaneously on non-contrast CT of patients with acute ischemic stroke","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Segmentation; Artificial intelligence; Convolutional neural network; Intraclass correlation; Radiology; Computer science; Pattern recognition (psychology)","score_opus":0.003524322564388348,"score_gpt":0.22794550264631425,"score_spread":0.2244211800819259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130628855","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":[0.98403084,0.00008265173,0.004859955,0.00047432515,0.000030851214,0.00023264947,0.000035674857,0.000035060322,0.010217994],"genre_scores_gemma":[0.99488264,0.00006183066,0.002955479,0.00064060907,0.00008511694,0.000011619037,0.0001541902,0.0000323662,0.0011761611],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9970543,0.000040653937,0.00050798076,0.0005858016,0.001391492,0.0004197993],"domain_scores_gemma":[0.9984151,0.00020268597,0.000222346,0.0005163039,0.00028041977,0.00036310422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023833675,0.000275669,0.0008256764,0.0003208567,0.00006675354,0.00004173465,0.00015708429,0.000070549904,0.0006736199],"category_scores_gemma":[0.00053101004,0.000218183,0.00022139189,0.0009214558,0.00019124217,0.00010734799,0.0002195025,0.00039686347,0.000014721479],"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":[0.00057047774,0.0009828572,0.8963991,0.00032152384,0.023252692,0.009696514,0.00053065387,0.00004444602,0.03669925,0.0000056182635,0.0026966801,0.028800193],"study_design_scores_gemma":[0.01853265,0.0016192461,0.69609123,0.0014242379,0.04075928,0.0001731255,0.0010842851,0.02265494,0.21364893,0.0000037669097,0.0027951149,0.0012131836],"about_ca_topic_score_codex":0.00011477972,"about_ca_topic_score_gemma":0.000030248928,"teacher_disagreement_score":0.20030785,"about_ca_system_score_codex":0.000071845665,"about_ca_system_score_gemma":0.00010543519,"threshold_uncertainty_score":0.88972443},"labels":[],"label_agreement":null},{"id":"W3131127151","doi":"10.1016/j.media.2021.102009","title":"Predicting future cognitive decline with hyperbolic stochastic coding","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Division of Information and Intelligent Systems; National Institute of Biomedical Imaging and Bioengineering; National Heart, Lung, and Blood Institute; National Institute on Aging; Canadian Institutes of Health Research","keywords":"Cognition; Coding (social sciences); Computer science; Cognitive decline; Artificial intelligence; Mathematics; Psychology; Statistics; Medicine; Dementia","score_opus":0.008760066034389334,"score_gpt":0.26211837901828505,"score_spread":0.2533583129838957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131127151","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":[0.09764153,0.00031176215,0.8971352,0.0040515815,0.00017195656,0.000089376445,0.000006869307,0.00022458207,0.00036715617],"genre_scores_gemma":[0.94595486,0.000022298545,0.051903646,0.0013180829,0.0006580762,0.000018064604,0.00003831311,0.000014356903,0.00007231708],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99637336,0.00027294908,0.0004454096,0.000923555,0.0014893836,0.0004953578],"domain_scores_gemma":[0.99721783,0.0008521415,0.0001374396,0.00067448034,0.00064017036,0.00047791476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008221352,0.00025074187,0.0006075234,0.0002519651,0.00022024152,0.00028615014,0.00084797584,0.0001269864,0.0005233709],"category_scores_gemma":[0.0017037075,0.00019762931,0.00027501085,0.004094048,0.00021043424,0.00035760595,0.00097142445,0.00049587403,0.00003916967],"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":[0.00009009912,0.0025009967,0.21872,0.00020143275,0.00936394,0.012013847,0.0060707545,0.005194622,0.0006770692,0.0026209743,0.0003332885,0.74221295],"study_design_scores_gemma":[0.00070122874,0.00007719069,0.031441238,0.000057013334,0.0009189283,0.00016365528,0.0004247805,0.96515304,0.00027442374,0.00041000676,0.00007251521,0.00030599613],"about_ca_topic_score_codex":0.00006911539,"about_ca_topic_score_gemma":0.00038800543,"teacher_disagreement_score":0.9599584,"about_ca_system_score_codex":0.000058795806,"about_ca_system_score_gemma":0.00033779268,"threshold_uncertainty_score":0.8059089},"labels":[],"label_agreement":null},{"id":"W3131131418","doi":"10.1016/j.media.2021.102001","title":"Estimating dual-energy CT imaging from single-energy CT data with material decomposition convolutional neural network","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Cancer Institute; National Institutes of Health; National Natural Science Foundation of China; Clinical Special Fund of Jiangsu Province","keywords":"Digital Enhanced Cordless Telecommunications; Artificial intelligence; Convolutional neural network; Energy (signal processing); Computer science; Deep learning; Contrast (vision); Medicine; Pattern recognition (psychology); Computer vision; Mathematics; Statistics; Wireless","score_opus":0.0077171823628405965,"score_gpt":0.24115619580662262,"score_spread":0.233439013443782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131131418","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":[0.047292985,0.0010031634,0.9497815,0.00043687184,0.00050903944,0.00002059269,0.0001523503,0.00031327576,0.00049023307],"genre_scores_gemma":[0.90810996,0.000034724202,0.08244105,0.0005652065,0.0014168929,0.00001079551,0.0073303753,0.000056033386,0.00003495224],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758595,0.00012631874,0.0004961056,0.00058803166,0.00067155506,0.00053201657],"domain_scores_gemma":[0.9986637,0.00020594372,0.000094788054,0.00066872255,0.00009823027,0.00026861372],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019375607,0.00029960266,0.0005127204,0.00011895224,0.00021921551,0.000223571,0.00034884518,0.000033124878,0.0015820195],"category_scores_gemma":[0.00011021365,0.00028715833,0.00013344549,0.0009495479,0.0001310525,0.00075893645,0.00027550844,0.00024185656,0.000008378362],"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":[0.00005874747,0.00020434012,0.005058053,0.000049673643,0.0032270649,0.008937458,0.00005374379,0.8601774,0.015888313,0.00023330645,0.005222581,0.10088934],"study_design_scores_gemma":[0.00040104272,0.0000072937905,0.0004314209,0.00008515534,0.0009560503,0.00021192,0.000049817674,0.9930693,0.002715645,0.00036171902,0.0013669488,0.00034369002],"about_ca_topic_score_codex":0.0004869439,"about_ca_topic_score_gemma":0.0003924337,"teacher_disagreement_score":0.86734045,"about_ca_system_score_codex":0.00008490905,"about_ca_system_score_gemma":0.000059846836,"threshold_uncertainty_score":0.99995804},"labels":[],"label_agreement":null},{"id":"W3135100175","doi":"10.1016/j.media.2021.102026","title":"A structural enriched functional network: An application to predict brain cognitive performance","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":24,"is_retracted":false,"has_abstract":false,"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":"NIH Blueprint for Neuroscience Research; National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; U.S. National Library of Medicine; National Institute on Aging; National Research Foundation of Korea; McDonnell Center for Systems Neuroscience; Directorate for Computer and Information Science and Engineering; National Institutes of Health; National Science Foundation","keywords":"Connectome; Computer science; Artificial intelligence; Functional magnetic resonance imaging; Cognition; Diffusion MRI; Network analysis; Default mode network; Cognitive network; Network model; Consistency (knowledge bases); Resting state fMRI; Machine learning; Network architecture; Functional connectivity; Neuroscience; Cognitive radio; Magnetic resonance imaging; Psychology; Computer network","score_opus":0.022270609101040756,"score_gpt":0.2857288497640012,"score_spread":0.2634582406629604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135100175","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":[0.8199987,0.00005406241,0.16179529,0.01632635,0.00022396403,0.00015571008,0.000035419514,0.00015429794,0.0012562457],"genre_scores_gemma":[0.97751343,0.00001682767,0.00039629557,0.020450234,0.00061975897,0.00011311745,0.00013282777,0.000014841304,0.0007426927],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99689585,0.0003272627,0.00029783862,0.0008896639,0.0011987502,0.00039061884],"domain_scores_gemma":[0.99566555,0.0032771914,0.000081410464,0.00032053023,0.00030308962,0.00035224194],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00055296265,0.00018729798,0.00033888163,0.00017366286,0.00039310456,0.00007651041,0.00020659898,0.00008715944,0.0017039838],"category_scores_gemma":[0.018480707,0.00017169958,0.00018017308,0.0030568668,0.00020729515,0.00036051017,0.00021870082,0.0002832193,0.00015961101],"study_design_candidate":"observational","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":[0.00134304,0.0013691775,0.3048598,0.00019085254,0.0043754857,0.00083475834,0.003189658,0.032065723,0.24313284,0.00282854,0.07103837,0.33477175],"study_design_scores_gemma":[0.0010080327,0.00023050305,0.47912064,0.000027137201,0.0008945178,0.00007998241,0.00041167322,0.5038964,0.010087684,0.00049442006,0.0031985203,0.0005504987],"about_ca_topic_score_codex":0.000025018722,"about_ca_topic_score_gemma":0.00024498277,"teacher_disagreement_score":0.47183067,"about_ca_system_score_codex":0.00006785309,"about_ca_system_score_gemma":0.00015758102,"threshold_uncertainty_score":0.99920857},"labels":[],"label_agreement":null},{"id":"W3135491122","doi":"10.1016/j.media.2021.102003","title":"Identifying associations among genomic, proteomic and imaging biomarkers via adaptive sparse multi-view canonical correlation analysis","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research; China Postdoctoral Science Foundation; Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China; U.S. Department of Defense","keywords":"Robustness (evolution); Neuroimaging; Imaging genetics; Computer science; Canonical correlation; Artificial intelligence; Feature selection; Genomics; Machine learning; Computational biology; Correlation; Genome-wide association study; Pattern recognition (psychology); Data mining; Biology; Mathematics; Genome; Genetics; Gene; Neuroscience; Single-nucleotide polymorphism","score_opus":0.010449435964477269,"score_gpt":0.2623913397837242,"score_spread":0.2519419038192469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135491122","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":[0.27439818,0.0013884093,0.7235316,0.00025492447,0.00005552398,0.00013445433,0.000032489315,0.000012895872,0.00019153027],"genre_scores_gemma":[0.9830468,0.0004406231,0.014559731,0.0003188159,0.00009896707,0.000021797516,0.0012568772,0.000016388181,0.00023995346],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816847,0.00017960019,0.0005593556,0.00046908553,0.00030676334,0.0003167091],"domain_scores_gemma":[0.9988784,0.000039199364,0.00025939793,0.00036681638,0.00018471378,0.00027144022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072465773,0.0001930329,0.0004525241,0.00022417503,0.00020155468,0.00012028138,0.00016627542,0.00021063341,0.00023572455],"category_scores_gemma":[0.00024298785,0.00019114283,0.00047808336,0.0011163236,0.00020066956,0.000020397632,0.00025134606,0.00021793603,0.0000113399665],"study_design_candidate":"observational","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":[0.000054362834,0.00032308203,0.85010713,0.000049213613,0.041165624,0.00018429522,0.0005703177,0.0026044014,0.061982546,0.00004723462,0.0012156008,0.041696213],"study_design_scores_gemma":[0.0006033542,0.000014198116,0.2912121,0.000014299588,0.007279325,0.000010022804,0.0002054384,0.69892657,0.001207853,0.00004390589,0.00016381935,0.0003191267],"about_ca_topic_score_codex":0.00037292205,"about_ca_topic_score_gemma":0.0027039654,"teacher_disagreement_score":0.70897186,"about_ca_system_score_codex":0.000061008544,"about_ca_system_score_gemma":0.00015821012,"threshold_uncertainty_score":0.77945787},"labels":[],"label_agreement":null},{"id":"W3136424010","doi":"10.1016/j.media.2021.102035","title":"Loss odyssey in medical image segmentation","year":2021,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":618,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Segmentation; Computer science; Dice; Artificial intelligence; Function (biology); Hausdorff distance; Loss function; Boundary (topology); Benchmark (surveying); Image segmentation; Mathematics; Geography; Statistics; Cartography","score_opus":0.02602045313479882,"score_gpt":0.3855040646034736,"score_spread":0.35948361146867475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136424010","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.2026273e-7,0.50752246,0.49072316,0.0011356191,0.00007393076,0.0002013767,0.0000067578203,0.00008444151,0.000251488],"genre_scores_gemma":[0.0000045351285,0.9583774,0.039614294,0.0006668722,0.0002562257,0.00029711454,0.0005281306,0.00003271284,0.00022269663],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99340415,0.00074706675,0.0014688679,0.0013636056,0.002411006,0.0006052745],"domain_scores_gemma":[0.9961274,0.0010327204,0.0004495098,0.001519711,0.0001550136,0.000715608],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001236884,0.0004948057,0.002434032,0.00080658303,0.00011177465,0.00021148463,0.002791936,0.000531085,0.002177654],"category_scores_gemma":[0.0012121235,0.00041435362,0.0011206097,0.009672324,0.00028246932,0.00050882954,0.0010628687,0.0012700427,0.00036905622],"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":[2.674819e-7,0.00012800419,0.000007652737,0.0004714188,0.00042798033,0.0017602367,0.000028051387,0.0000044353246,4.9381197e-7,0.0005421234,0.0013563806,0.99527293],"study_design_scores_gemma":[0.00041909318,0.000020778609,0.000017042305,0.003700453,0.0032689702,0.00024769458,0.000018613393,0.04441783,0.000008077558,0.0004435167,0.94644445,0.0009934835],"about_ca_topic_score_codex":0.000044626897,"about_ca_topic_score_gemma":0.0001825909,"teacher_disagreement_score":0.99427944,"about_ca_system_score_codex":0.00023156764,"about_ca_system_score_gemma":0.00080250116,"threshold_uncertainty_score":0.99983084},"labels":[],"label_agreement":null},{"id":"W3138739590","doi":"10.1016/j.media.2021.102040","title":"APRIL: Anatomical prior-guided reinforcement learning for accurate carotid lumen diameter and intima-media thickness measurement","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiovascular Health and Disease Prevention","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Fundamental Research Funds for the Central Universities; Xiamen University; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Artificial intelligence; Reinforcement learning; Variance (accounting); Computer science; Carotid arteries; Lumen (anatomy); Pixel; Computer vision; Stability (learning theory); Machine learning; Pattern recognition (psychology); Medicine; Surgery","score_opus":0.02889763293586841,"score_gpt":0.316519889316278,"score_spread":0.2876222563804096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138739590","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":[0.22907975,0.0029276703,0.76087517,0.005309806,0.00019350938,0.00093348924,0.0000075604,0.00011729824,0.0005557438],"genre_scores_gemma":[0.99168277,0.0005832348,0.005065772,0.0015159734,0.00029586878,0.0001522683,0.00046121035,0.00002678116,0.00021611882],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9965079,0.00025968798,0.00063300837,0.0005459006,0.0016214884,0.00043205373],"domain_scores_gemma":[0.99763316,0.0001668878,0.00011922006,0.00042147693,0.00071504386,0.000944227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021904923,0.0002056604,0.00081651966,0.0002516687,0.00015692222,0.00006701333,0.000084466184,0.0001675675,0.00087304605],"category_scores_gemma":[0.006282162,0.00017824105,0.00090835884,0.00070921145,0.00011354161,0.00011160412,0.00013374448,0.000342479,0.00001708289],"study_design_candidate":"observational","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":[0.004153645,0.0032733523,0.26981115,0.013126708,0.08852623,0.004042274,0.0058103213,0.0026872968,0.037916042,0.0007640229,0.032744896,0.53714406],"study_design_scores_gemma":[0.035847466,0.0003533834,0.49249128,0.0012502887,0.073861316,0.0004747402,0.0021928288,0.355351,0.012317116,0.00064954,0.0233164,0.001894667],"about_ca_topic_score_codex":0.00010446963,"about_ca_topic_score_gemma":0.0000779589,"teacher_disagreement_score":0.76260304,"about_ca_system_score_codex":0.00017628293,"about_ca_system_score_gemma":0.000585888,"threshold_uncertainty_score":0.9559242},"labels":[],"label_agreement":null},{"id":"W3138973186","doi":"10.1016/j.media.2021.102032","title":"Fine-Tuning and training of densenet for histopathology image representation using TCGA diagnostic slides","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":211,"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; McMaster University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario; Ontario Research Foundation","keywords":"Representation (politics); Artificial intelligence; Computer science; Training (meteorology); Image (mathematics); Computer vision; Pattern recognition (psychology); Geography","score_opus":0.038616818534811165,"score_gpt":0.3334691023019692,"score_spread":0.294852283767158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138973186","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":[0.16939162,0.00033855648,0.8293721,0.00065457716,0.000099202916,0.00005796645,0.0000027174522,0.000028369168,0.000054904118],"genre_scores_gemma":[0.74883974,0.00005882743,0.2508065,0.00013510059,0.00008654246,0.000017195107,0.00001237707,0.0000079741285,0.000035730704],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984846,0.0002126831,0.00035844417,0.00042101252,0.00033345137,0.00018981933],"domain_scores_gemma":[0.9975164,0.001658096,0.00016755692,0.0003311851,0.00022329594,0.00010346837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067379506,0.000091994225,0.0003505855,0.0002201322,0.00009916785,0.000057999678,0.00019878458,0.000072376766,0.00007112986],"category_scores_gemma":[0.0061414232,0.00009499403,0.00014182596,0.0010297283,0.00015722564,0.0002837449,0.00015294056,0.000101920195,7.4205417e-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":[0.00005335182,0.00019801252,0.03594834,0.00049816555,0.0010576765,0.0020050462,0.01006636,0.0024740046,0.4242588,0.00074634416,0.0007269772,0.52196693],"study_design_scores_gemma":[0.0005281849,0.000059689828,0.01104992,0.00011768893,0.0008519896,0.00012646479,0.00034508706,0.94747657,0.037826836,0.0013697861,0.000052441817,0.00019533068],"about_ca_topic_score_codex":0.00009722673,"about_ca_topic_score_gemma":0.00020278916,"teacher_disagreement_score":0.94500256,"about_ca_system_score_codex":0.00004713805,"about_ca_system_score_gemma":0.00012590515,"threshold_uncertainty_score":0.7352301},"labels":[],"label_agreement":null},{"id":"W3139837796","doi":"10.1016/j.media.2022.102374","title":"Weakly supervised segmentation with cross-modality equivariant constraints","year":2022,"lang":"en","type":"preprint","venue":"Medical Image Analysis","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Compute Canada","keywords":"Computer science; Segmentation; Modality (human–computer interaction); Modalities; Artificial intelligence; Equivariant map; Machine learning; Constraint (computer-aided design); Exploit; Pattern recognition (psychology); Divergence (linguistics); Pixel; Mathematics","score_opus":0.016168797614745857,"score_gpt":0.34553033631595975,"score_spread":0.3293615387012139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139837796","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":[0.076671116,0.00003655124,0.9119485,0.007991182,0.00011906153,0.000393149,0.00008336013,0.0003726998,0.0023843865],"genre_scores_gemma":[0.82523835,0.000015849855,0.17251067,0.00075773365,0.00008956269,0.0003903887,0.0008007248,0.000024407338,0.00017230067],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99447024,0.00063571474,0.00073503266,0.0014805222,0.002213736,0.0004647615],"domain_scores_gemma":[0.99635834,0.00034013262,0.00043514525,0.0021191062,0.00027240868,0.0004748503],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018582494,0.00039447247,0.00074104214,0.0005004907,0.00040252297,0.0007352938,0.0029249238,0.000243294,0.009329114],"category_scores_gemma":[0.00048516167,0.00034458324,0.00045333005,0.0020056257,0.0005592493,0.00027169293,0.0030204598,0.0017385983,0.0000847293],"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":[0.00015581877,0.0036143526,0.43499428,0.0009088427,0.021112138,0.0025874244,0.008306571,0.15109463,0.0033232318,0.031522688,0.0012227019,0.34115732],"study_design_scores_gemma":[0.00055371237,0.0000433734,0.11549924,0.00002438666,0.0008773951,0.000015050833,0.00006255078,0.8806363,0.00011185055,0.0015511092,0.00012409616,0.0005009636],"about_ca_topic_score_codex":0.0037830765,"about_ca_topic_score_gemma":0.000108450935,"teacher_disagreement_score":0.7485672,"about_ca_system_score_codex":0.00023607186,"about_ca_system_score_gemma":0.00072835805,"threshold_uncertainty_score":0.99990064},"labels":[],"label_agreement":null},{"id":"W3142204669","doi":"10.1016/j.media.2021.102245","title":"A multiparametric volumetric quantitative ultrasound imaging technique for soft tissue characterization","year":2021,"lang":"en","type":"preprint","venue":"Medical Image Analysis","topic":"Ultrasound Imaging and Elastography","field":"Medicine","cited_by":2,"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 British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Regularization (linguistics); Imaging phantom; Computer science; Parametric statistics; Mathematics; Algorithm; Artificial intelligence; Pattern recognition (psychology); Physics; Statistics; Optics","score_opus":0.01379314014657327,"score_gpt":0.3223820486060981,"score_spread":0.3085889084595248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3142204669","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":[0.043648172,0.0016796426,0.9513483,0.0010095609,0.00028753642,0.0013227841,0.00022535863,0.000248056,0.00023059956],"genre_scores_gemma":[0.6771932,0.0010891652,0.30473655,0.0012317601,0.0004976355,0.001161573,0.013212735,0.00015384862,0.0007235271],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99514836,0.0002559178,0.0010838137,0.001412519,0.0014053491,0.0006940216],"domain_scores_gemma":[0.99504757,0.0015674296,0.0005635343,0.00087703584,0.0013131059,0.0006313135],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014604108,0.0006192045,0.0018694925,0.004725772,0.0002055602,0.00038517185,0.00042574105,0.0005496072,0.0010779476],"category_scores_gemma":[0.015959404,0.0005883793,0.0015719531,0.008843971,0.00040861338,0.00022601643,0.000254166,0.0014273389,0.000027487908],"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":[0.0003154673,0.0027262452,0.12883581,0.0030400914,0.018070783,0.00064336555,0.0017906246,0.000068699126,0.7819131,0.000016904482,0.0013552915,0.06122362],"study_design_scores_gemma":[0.012415415,0.0016417622,0.30116212,0.00665612,0.17159913,0.0033967253,0.005158714,0.32461616,0.11999453,0.0008170779,0.043443963,0.009098285],"about_ca_topic_score_codex":0.0005752001,"about_ca_topic_score_gemma":0.000022236236,"teacher_disagreement_score":0.6619186,"about_ca_system_score_codex":0.00019041123,"about_ca_system_score_gemma":0.0005434687,"threshold_uncertainty_score":0.9998352},"labels":[],"label_agreement":null},{"id":"W3149170955","doi":"10.1016/j.media.2021.102055","title":"Meta grayscale adaptive network for 3D integrated renal structures segmentation","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Grayscale; Artificial intelligence; Segmentation; Computer science; Computer vision; Pattern recognition (psychology); Deep learning; Image segmentation; Image (mathematics)","score_opus":0.029290088657429034,"score_gpt":0.303212484430983,"score_spread":0.27392239577355393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3149170955","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":[0.00030780496,0.0005227697,0.9964131,0.0022661686,0.00006942377,0.00015357189,0.00001911757,0.00011143889,0.00013657301],"genre_scores_gemma":[0.014838826,0.00008324734,0.98248076,0.0014664439,0.00021126679,0.00018476247,0.00029643564,0.000010961833,0.00042727712],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807537,0.0001571627,0.00035695414,0.00057149556,0.00052032375,0.00031872417],"domain_scores_gemma":[0.99825996,0.00053050654,0.00013826114,0.0005454659,0.0003112689,0.0002145501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025248522,0.00016541003,0.00042430527,0.00009673828,0.00020519749,0.00010403495,0.0005601727,0.00007890176,0.0004989086],"category_scores_gemma":[0.00021794195,0.00012967657,0.00040866758,0.0031394265,0.000097915596,0.00030609587,0.0001788733,0.0001909394,0.000010495562],"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":[0.00010751248,0.0005471013,0.0007455839,0.00004932573,0.046248607,0.0004689106,0.00090155005,0.11123452,0.008510512,0.096535705,0.093757905,0.64089274],"study_design_scores_gemma":[0.00034633258,0.00003888838,0.00038311016,0.000006757778,0.0049548703,0.000011759429,0.00004333904,0.9552628,0.004914842,0.026697913,0.007088882,0.0002505122],"about_ca_topic_score_codex":0.000023958017,"about_ca_topic_score_gemma":0.00036245718,"teacher_disagreement_score":0.8440283,"about_ca_system_score_codex":0.000047134974,"about_ca_system_score_gemma":0.00013678579,"threshold_uncertainty_score":0.5462699},"labels":[],"label_agreement":null},{"id":"W3152831887","doi":"10.1016/j.media.2021.102059","title":"MGN-Net: A multi-view graph normalizer for integrating heterogeneous biological network populations","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"H2020 Marie Skłodowska-Curie Actions; National Institute on Aging; Canadian Institutes of Health Research","keywords":"Biological network; Computer science; Population; Graph; Normalization (sociology); Artificial intelligence; Theoretical computer science; Machine learning; Computational biology; Biology","score_opus":0.024109946087972005,"score_gpt":0.30125367800228153,"score_spread":0.2771437319143095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152831887","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":[0.040742494,0.0037144285,0.95438826,0.00048243414,0.00016704285,0.00016986184,0.00004999269,0.000021088841,0.0002644199],"genre_scores_gemma":[0.81982464,0.0012632591,0.16817333,0.0045421333,0.0010155906,0.000120533565,0.0043971227,0.000035639154,0.0006277716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998421,0.0001010422,0.0005214009,0.0003678883,0.00018148385,0.00040714708],"domain_scores_gemma":[0.9990327,0.000039618797,0.00012651128,0.00038608132,0.00018516778,0.00022996905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046328636,0.00019301253,0.00038183795,0.00005324023,0.00019203863,0.00006276413,0.0002285613,0.0002984482,0.0003818826],"category_scores_gemma":[0.0003866543,0.00015302176,0.00062652375,0.0005374218,0.000116278396,0.0000050313524,0.0001765027,0.00015673986,0.000009773467],"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":[0.00061172777,0.003208117,0.13473867,0.0006307275,0.033681802,0.00079195236,0.001079225,0.056448232,0.07993732,0.006177059,0.12716152,0.55553365],"study_design_scores_gemma":[0.004351913,0.0006679119,0.006499123,0.0001643219,0.0043908507,0.00026801467,0.00047917283,0.7685872,0.008546693,0.0035534003,0.20020463,0.002286779],"about_ca_topic_score_codex":0.000024016785,"about_ca_topic_score_gemma":0.00073926046,"teacher_disagreement_score":0.7862149,"about_ca_system_score_codex":0.0000102754775,"about_ca_system_score_gemma":0.00007475667,"threshold_uncertainty_score":0.6240046},"labels":[],"label_agreement":null},{"id":"W3157261413","doi":"10.1016/j.media.2021.102093","title":"Track-to-Learn: A general framework for tractography with deep reinforcement learning","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université de Sherbrooke","funders":"","keywords":"Tractography; Reinforcement learning; Artificial intelligence; Computer science; Leverage (statistics); Deep learning; Machine learning; Artificial neural network; Prior probability; Diffusion MRI; Bayesian probability; Magnetic resonance imaging","score_opus":0.02872814233882151,"score_gpt":0.36618501131255343,"score_spread":0.33745686897373195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157261413","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":[0.015056881,0.00008116573,0.97365427,0.010084747,0.000009837242,0.000266697,0.0000018221275,0.00017436115,0.0006702271],"genre_scores_gemma":[0.42556107,0.00013686548,0.5672974,0.0052075665,0.00017761257,0.00025923675,0.00018137244,0.000034653407,0.0011441957],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983939,0.00003165636,0.00029353678,0.00044100577,0.0005351157,0.0003047977],"domain_scores_gemma":[0.99866843,0.00016203223,0.00007714288,0.0004265931,0.00023910133,0.00042669225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018855456,0.00015315005,0.00042026737,0.00024182048,0.00014012799,0.000036118377,0.00011536521,0.00009279147,0.0008859508],"category_scores_gemma":[0.0007312249,0.00012123758,0.00036428717,0.0020203195,0.00008655681,0.00005398693,0.000043273874,0.00046225547,0.000010482581],"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":[0.0021467316,0.0048647267,0.15401341,0.0009762996,0.01782873,0.005428767,0.003279643,0.041134972,0.051580306,0.038942862,0.014623289,0.66518027],"study_design_scores_gemma":[0.00521556,0.0026618887,0.035956953,0.00065737485,0.019247787,0.00045507489,0.0011873336,0.5439157,0.047431946,0.0068212776,0.33462122,0.0018279074],"about_ca_topic_score_codex":0.0000122269785,"about_ca_topic_score_gemma":0.000011847303,"teacher_disagreement_score":0.6633524,"about_ca_system_score_codex":0.000026401338,"about_ca_system_score_gemma":0.00007602268,"threshold_uncertainty_score":0.970054},"labels":[],"label_agreement":null},{"id":"W3164110046","doi":"10.1016/j.media.2021.102106","title":"Conditional generation of medical images via disentangled adversarial inference","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Heart Institute; Université de Montréal","funders":"","keywords":"Inference; Computer science; Latent variable; Artificial intelligence; Regularization (linguistics); Machine learning; Adversarial system; Image (mathematics); Unsupervised learning; Variable (mathematics); Pattern recognition (psychology); Mathematics","score_opus":0.018622804010336474,"score_gpt":0.29449437174993365,"score_spread":0.2758715677395972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164110046","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":[0.002148539,0.00021000167,0.98960245,0.007007162,0.00031598,0.00005276988,0.000020566982,0.00004354275,0.0005989961],"genre_scores_gemma":[0.9665704,0.00017507798,0.03113148,0.0009510092,0.00069146627,0.000012441306,0.0003035643,0.000008138629,0.00015645775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955598,0.0004549062,0.00061640306,0.0005765437,0.002493282,0.00029903505],"domain_scores_gemma":[0.9978969,0.00040957305,0.00018247525,0.000569197,0.00051386043,0.00042800902],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008881918,0.00019117177,0.0005425227,0.0002099678,0.00014062892,0.00014705815,0.0009105556,0.00019386313,0.0077298535],"category_scores_gemma":[0.0021472273,0.00016678903,0.00043268522,0.0017825752,0.0002977963,0.000574695,0.00047233683,0.00024946782,0.0000454907],"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":[0.00009697467,0.0055247983,0.023735018,0.00021345101,0.020369537,0.009044494,0.0022046352,0.021181088,0.18461487,0.050367426,0.10179166,0.580856],"study_design_scores_gemma":[0.0006219537,0.000027574779,0.0018124519,0.00001680509,0.00045015436,0.000013261035,0.000025055908,0.96039736,0.03488422,0.00083538494,0.0006961533,0.00021962168],"about_ca_topic_score_codex":0.00014922819,"about_ca_topic_score_gemma":0.0002078966,"teacher_disagreement_score":0.9644218,"about_ca_system_score_codex":0.000035290337,"about_ca_system_score_gemma":0.00053855503,"threshold_uncertainty_score":0.99317724},"labels":[],"label_agreement":null},{"id":"W3168283161","doi":"10.1016/j.media.2022.102624","title":"Towards annotation-efficient segmentation via image-to-image translation","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Artificial intelligence; Translation (biology); Automatic image annotation; Image (mathematics); Computer vision; Computer science; Annotation; Image translation; Image segmentation; Segmentation; Pattern recognition (psychology); Image processing; Biology","score_opus":0.01095319566051169,"score_gpt":0.26759391648783776,"score_spread":0.2566407208273261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168283161","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":[0.0035961024,0.0000734221,0.98542255,0.008994014,0.00026348897,0.00025591874,0.000021364849,0.00012183659,0.0012512957],"genre_scores_gemma":[0.63824975,0.000012240792,0.35902154,0.0020483418,0.00018135092,0.000148805,0.0001549166,0.00001893477,0.00016413443],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607235,0.00054261624,0.00053112354,0.0007089383,0.0017377196,0.0004072738],"domain_scores_gemma":[0.9985696,0.0001492318,0.00015353375,0.0005429338,0.0002372338,0.00034744453],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013301675,0.00022174152,0.00037707176,0.0005922868,0.000578898,0.00028265515,0.0009027488,0.00004912763,0.003201654],"category_scores_gemma":[0.00020790682,0.00021381995,0.00035845273,0.004119103,0.00009206841,0.0005442842,0.00033467865,0.00026604533,0.00012603436],"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":[0.000050887786,0.0007839343,0.0001783785,0.0000223363,0.0012366263,0.00026673777,0.0063067563,0.16703793,0.08118984,0.00028000228,0.008254673,0.73439187],"study_design_scores_gemma":[0.0003692697,0.00008070353,0.0012508179,0.0000030012204,0.0003159585,0.000005363891,0.00023729283,0.9898847,0.0059809564,0.00016660237,0.0014415107,0.00026387302],"about_ca_topic_score_codex":0.00025377117,"about_ca_topic_score_gemma":0.000043282802,"teacher_disagreement_score":0.8228467,"about_ca_system_score_codex":0.00015039783,"about_ca_system_score_gemma":0.00013145385,"threshold_uncertainty_score":0.9977096},"labels":[],"label_agreement":null},{"id":"W3169635423","doi":"10.1016/j.media.2021.102107","title":"Ultra-short echo-time magnetic resonance imaging lung segmentation with under-Annotations and domain shift","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Atomic and Subatomic Physics Research","field":"Physics and Astronomy","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Segmentation; Artificial intelligence; Computer science; Atlas (anatomy); Magnetic resonance imaging; Cluster analysis; Pattern recognition (psychology); Computer vision; Medicine; Radiology; Anatomy","score_opus":0.005021025350039202,"score_gpt":0.27568338162182165,"score_spread":0.2706623562717825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169635423","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":[0.33333826,0.0007718728,0.65469646,0.0019902284,0.0000132930445,0.00013538686,0.0000543081,0.000033082328,0.008967089],"genre_scores_gemma":[0.9966806,0.000022383634,0.0020011144,0.00019544546,0.00008934757,0.000029983266,0.00030144156,0.000017109032,0.0006625515],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983002,0.00013868457,0.0002503745,0.0004027533,0.0005986656,0.00030932087],"domain_scores_gemma":[0.9991782,0.00016592751,0.000040338033,0.00025935893,0.000114922994,0.00024128803],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00025928926,0.00015269038,0.00030363063,0.000115954506,0.00019523001,0.00013663626,0.00013682172,0.000028401515,0.0029939618],"category_scores_gemma":[0.000016193479,0.00013250746,0.00012354669,0.0009997477,0.00022696625,0.00022278834,0.000055847482,0.00023930018,0.000036780755],"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":[0.000050340335,0.00050949183,0.58693576,0.000036163758,0.0017155737,0.00032400346,0.0025602528,0.00011850037,0.016112618,0.005171867,0.0022550875,0.38421038],"study_design_scores_gemma":[0.0046314197,0.00006028242,0.12758078,0.00019263841,0.004737855,0.000028351844,0.01604811,0.78928113,0.019973036,0.03419964,0.0014937524,0.001772994],"about_ca_topic_score_codex":0.00015184826,"about_ca_topic_score_gemma":0.00002679197,"teacher_disagreement_score":0.78916264,"about_ca_system_score_codex":0.000049547463,"about_ca_system_score_gemma":0.0002727014,"threshold_uncertainty_score":0.9979174},"labels":[],"label_agreement":null},{"id":"W3169902296","doi":"10.1016/j.media.2021.102115","title":"Evaluation and comparison of accurate automated spinal curvature estimation algorithms with spinal anterior-posterior X-Ray images: The AASCE2019 challenge","year":2021,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Scoliosis diagnosis and treatment","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Scoliosis; Cobb angle; Spinal Curvatures; Curvature; Estimation; Artificial intelligence; Computer science; Task (project management); Computer vision; Algorithm; Mathematics; Medicine; Surgery; Engineering; Geometry","score_opus":0.07490463179044513,"score_gpt":0.4557718512083843,"score_spread":0.3808672194179392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169902296","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008478424,0.994952,0.0012915697,0.0013001962,0.00007281814,0.0013464508,0.000047490175,0.00007631146,0.00006528243],"genre_scores_gemma":[0.021037383,0.9750475,0.0023864396,0.0000964045,0.00015159628,0.00040005968,0.00080867956,0.000051377363,0.000020550655],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9943136,0.0008127603,0.0013172013,0.00078532007,0.0024265042,0.00034461464],"domain_scores_gemma":[0.99682254,0.00021139461,0.0010155576,0.00079771876,0.0008473148,0.00030548833],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017933248,0.0006077935,0.0038993012,0.0005296644,0.00014828597,0.00013696408,0.0002547636,0.0004170818,0.0005568416],"category_scores_gemma":[0.00082338566,0.0003232831,0.00087264995,0.0018572732,0.00038604866,0.00015201377,0.00013597534,0.0006345381,0.000017679693],"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":[0.000050614148,0.000723365,0.00027269038,0.0042091706,0.010303058,0.00022489089,0.00012502586,0.000006723717,0.0000016158134,0.0000014825147,0.00029267903,0.98378867],"study_design_scores_gemma":[0.0056493636,0.0053351396,0.02215302,0.13443632,0.5180418,0.00069943484,0.0008662318,0.28564522,0.00004923969,0.0000051905404,0.025755804,0.0013632509],"about_ca_topic_score_codex":0.00010580873,"about_ca_topic_score_gemma":0.000055487675,"teacher_disagreement_score":0.98242545,"about_ca_system_score_codex":0.00020516329,"about_ca_system_score_gemma":0.00080567144,"threshold_uncertainty_score":0.9999219},"labels":[],"label_agreement":null},{"id":"W3171948477","doi":"10.1016/j.media.2021.102123","title":"Tetrahedral spectral feature-Based bayesian manifold learning for grey matter morphometry: Findings from the Alzheimer’s disease neuroimaging initiative","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"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 Institute on Aging; National Institutes of Health; National Natural Science Foundation of China; U.S. Department of Defense","keywords":"Artificial intelligence; Grey matter; Pattern recognition (psychology); Neuroimaging; Computer science; Bayesian probability; Brain morphometry; Machine learning; Mathematics; Magnetic resonance imaging; Psychology; Radiology; Medicine","score_opus":0.01994169279444881,"score_gpt":0.29284541888698273,"score_spread":0.27290372609253394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171948477","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":[0.0016805598,0.00036006604,0.9577883,0.039314788,0.00012736082,0.00022210533,0.000039948533,0.00024286727,0.00022403193],"genre_scores_gemma":[0.6749655,0.000037925995,0.2805564,0.042893972,0.000337405,0.00013080811,0.000745081,0.000049831087,0.00028304814],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99614507,0.0005283105,0.0004627577,0.00091961434,0.0013847233,0.0005595186],"domain_scores_gemma":[0.9967216,0.0014344495,0.00017032522,0.00077640207,0.0002626163,0.0006345651],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007485589,0.00030252553,0.00047726012,0.00031423298,0.0003536742,0.0007237432,0.0012757255,0.00009988679,0.0032283466],"category_scores_gemma":[0.0022463095,0.00023257986,0.00058439,0.002455566,0.00022271264,0.00065920746,0.0003201552,0.00073159224,0.00006826837],"study_design_candidate":"observational","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":[0.00018419565,0.0013726673,0.568334,0.00014937427,0.0077762273,0.010163777,0.0029063774,0.00023118673,0.008471269,0.0016027222,0.3070937,0.0917145],"study_design_scores_gemma":[0.0018638286,0.00009558138,0.20367782,0.00015124439,0.0044287625,0.000017786519,0.0003563457,0.7286627,0.055098362,0.0027441522,0.001885186,0.0010181838],"about_ca_topic_score_codex":0.00009711583,"about_ca_topic_score_gemma":0.0000325102,"teacher_disagreement_score":0.7284316,"about_ca_system_score_codex":0.000061120794,"about_ca_system_score_gemma":0.00029856846,"threshold_uncertainty_score":0.9976828},"labels":[],"label_agreement":null},{"id":"W3172893236","doi":"10.1016/j.media.2021.102126","title":"Filtering in tractography using autoencoders (FINTA)","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"National Institute of Mental Health","keywords":"Tractography; Streamlines, streaklines, and pathlines; Artificial intelligence; Autoencoder; Pattern recognition (psychology); Computer science; Deep learning; Filter (signal processing); Diffusion MRI; Human Connectome Project; Voxel; Computer vision; Physics; Magnetic resonance imaging; Functional connectivity","score_opus":0.08399795419258586,"score_gpt":0.4187703104105577,"score_spread":0.3347723562179718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172893236","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":[0.16882396,0.00013141507,0.825212,0.0042972323,0.000014283368,0.000075026655,0.0000039936986,0.00012210547,0.0013199644],"genre_scores_gemma":[0.7406739,0.00020336434,0.2568757,0.0019669875,0.00005490154,0.000019257322,0.00005822797,0.00001923895,0.00012843669],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883157,0.000032812608,0.00027474668,0.00031422218,0.00034253593,0.00020413252],"domain_scores_gemma":[0.9993006,0.000055669734,0.00004425836,0.0003530782,0.00006548242,0.00018090615],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015440874,0.00009689312,0.00032466202,0.00035070692,0.000042390024,0.000017810631,0.000085867025,0.00006155189,0.0009991055],"category_scores_gemma":[0.00026958712,0.00009168677,0.00026707049,0.002407519,0.000096524556,0.00007251657,0.000057045345,0.00029935056,0.00000519698],"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":[0.000089967085,0.0030264559,0.5652593,0.00031990738,0.002532465,0.01745422,0.00071593927,0.0023924012,0.31903598,0.00087809504,0.0027119857,0.0855833],"study_design_scores_gemma":[0.001631362,0.00005892351,0.12491369,0.0003069348,0.0034389303,0.00046753418,0.0004126025,0.82262206,0.032991204,0.001509544,0.011073087,0.00057409983],"about_ca_topic_score_codex":0.00008175387,"about_ca_topic_score_gemma":0.000049875143,"teacher_disagreement_score":0.8202297,"about_ca_system_score_codex":0.0000353387,"about_ca_system_score_gemma":0.00008093113,"threshold_uncertainty_score":0.9999141},"labels":[],"label_agreement":null},{"id":"W3176861478","doi":"10.1016/j.media.2021.102154","title":"United adversarial learning for liver tumor segmentation and detection of multi-modality non-contrast MRI","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Primary Research and Development Plan of Zhejiang Province; Taishan Scholar Project of Shandong Province; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Modality (human–computer interaction); Artificial intelligence; Feature (linguistics); Feature selection; Segmentation; Feature extraction; Pattern recognition (psychology); Discriminator; Magnetic resonance imaging; Computer vision; Radiology; Medicine","score_opus":0.009171958537115481,"score_gpt":0.2997309343071358,"score_spread":0.2905589757700203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176861478","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":[0.3653848,0.00012745829,0.6327238,0.0014935278,0.00006306882,0.00013724425,0.000003858592,0.000023894137,0.000042353808],"genre_scores_gemma":[0.9842158,0.00014986166,0.014341712,0.0005710762,0.0001753619,0.000016092199,0.00025281883,0.000016105012,0.0002611946],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846035,0.00015263546,0.00039746208,0.00032127887,0.0004652127,0.00020305747],"domain_scores_gemma":[0.99881834,0.000292976,0.00015623002,0.00014882385,0.0003059477,0.000277677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008739857,0.0001252384,0.00049576606,0.00029988794,0.00011498359,0.00002630304,0.000054820728,0.00009086894,0.00028845484],"category_scores_gemma":[0.0035796973,0.00011106338,0.00024656559,0.00084837,0.00018858949,0.000083778636,0.000047098794,0.0004028037,0.0000021580386],"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":[0.0008690803,0.0011892555,0.10575804,0.0012272311,0.006974583,0.0010414151,0.002383485,0.0019119536,0.6168955,0.00003885638,0.00035196214,0.26135865],"study_design_scores_gemma":[0.0036518865,0.00010157488,0.03039565,0.00006129211,0.002969436,0.000042470412,0.00050128426,0.9423726,0.01924764,0.000009792424,0.00053620397,0.00011016249],"about_ca_topic_score_codex":0.0005286698,"about_ca_topic_score_gemma":0.000087351335,"teacher_disagreement_score":0.9404607,"about_ca_system_score_codex":0.000043652388,"about_ca_system_score_gemma":0.000105527666,"threshold_uncertainty_score":0.45290333},"labels":[],"label_agreement":null},{"id":"W3195607837","doi":"10.1016/j.media.2021.102218","title":"Automatic annotation of cervical vertebrae in videofluoroscopy images via deep learning","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Dysphagia Assessment and Management","field":"Health Professions","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; North York General Hospital","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institutes of Health","keywords":"Artificial intelligence; Computer science; Swallowing; Pixel; Gold standard (test); Convolutional neural network; Kinematics; Deep learning; Landmark; Computer vision; Pattern recognition (psychology); Medicine; Radiology","score_opus":0.013095892006795232,"score_gpt":0.393504932193157,"score_spread":0.3804090401863618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195607837","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":[0.5624612,0.00069659157,0.41499084,0.0068792026,0.00034959064,0.00047789738,0.000004906739,0.00020001184,0.013939738],"genre_scores_gemma":[0.9901682,0.00017902273,0.0068930807,0.0009246312,0.00006202012,0.00006679881,0.00016663507,0.000016983957,0.0015225885],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99658865,0.000991532,0.00087023614,0.00032442273,0.00082286604,0.000402282],"domain_scores_gemma":[0.99851954,0.0005595412,0.00023493795,0.00028947627,0.00021485846,0.0001816463],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013162335,0.00013817998,0.00058061135,0.00039959588,0.00016049921,0.000015001555,0.00019504318,0.00015556408,0.02239697],"category_scores_gemma":[0.0012233047,0.0001252604,0.0001885976,0.0020431941,0.000079920814,0.0002077838,0.00022174449,0.00060191326,0.00020862672],"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":[0.00002848389,0.0008323052,0.84530467,0.0012680829,0.0023359505,0.0007068187,0.0037115428,0.00019840857,0.0074997805,0.00050086336,0.0040612696,0.1335518],"study_design_scores_gemma":[0.0015863279,0.000053368945,0.5425023,0.00021326354,0.0016624987,8.052356e-7,0.004421278,0.4464094,0.0011818064,0.00052415626,0.0012022615,0.0002425312],"about_ca_topic_score_codex":0.00040917326,"about_ca_topic_score_gemma":0.0009995155,"teacher_disagreement_score":0.44621098,"about_ca_system_score_codex":0.00010366697,"about_ca_system_score_gemma":0.0001758254,"threshold_uncertainty_score":0.9784967},"labels":[],"label_agreement":null},{"id":"W3199008037","doi":"10.1016/j.media.2021.102233","title":"BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":708,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Neurological Disorders and Stroke; National Institutes of Health","keywords":"Computer science; Functional magnetic resonance imaging; Artificial intelligence; Pooling; Connectome; Neuroimaging; Pattern recognition (psychology); Graph; Human Connectome Project; Machine learning; Psychology; Neuroscience; Functional connectivity; Theoretical computer science","score_opus":0.02012230046150534,"score_gpt":0.2959105910532257,"score_spread":0.2757882905917204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199008037","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":[0.088611774,0.0007127791,0.73727405,0.16831937,0.0007783654,0.00035484353,0.00015463945,0.0003694533,0.0034247353],"genre_scores_gemma":[0.94510937,0.00005397102,0.00293561,0.04787698,0.00053829374,0.00011655596,0.00012003396,0.000034232206,0.0032149353],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958013,0.0005616191,0.00055369583,0.001238818,0.0011232211,0.00072130543],"domain_scores_gemma":[0.98363334,0.014900075,0.00016573709,0.0006977133,0.00026549058,0.00033761782],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012411819,0.00029380867,0.0009827571,0.0006126829,0.00047416432,0.00019893257,0.00048417016,0.00013709263,0.002603463],"category_scores_gemma":[0.056165967,0.0002688113,0.0017720095,0.011148079,0.00037172672,0.00030108928,0.00035265577,0.00035588618,0.00003911988],"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":[0.0005272626,0.0017399434,0.096244104,0.00024095194,0.05586958,0.0027932152,0.0020362907,0.06890212,0.0515641,0.005810818,0.6794989,0.034772728],"study_design_scores_gemma":[0.0014841479,0.00018564527,0.014753527,0.000034888995,0.01983927,0.00004672687,0.00048038168,0.908331,0.013734873,0.0056798,0.034298994,0.0011307757],"about_ca_topic_score_codex":0.00009297395,"about_ca_topic_score_gemma":0.0013231374,"teacher_disagreement_score":0.8564976,"about_ca_system_score_codex":0.00006100631,"about_ca_system_score_gemma":0.00011485884,"threshold_uncertainty_score":0.9999764},"labels":[],"label_agreement":null},{"id":"W3199360076","doi":"10.1016/j.media.2021.102231","title":"Real-time multimodal image registration with partial intraoperative point-set data","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":35,"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; University College London; Wellcome Trust","keywords":"Image registration; Artificial intelligence; Rigid transformation; Computer science; Point set registration; Ground truth; Iterative closest point; Computer vision; Point (geometry); Pattern recognition (psychology); Algorithm; Image (mathematics); Mathematics; Point cloud","score_opus":0.011420725786102707,"score_gpt":0.2592982857670171,"score_spread":0.24787755998091437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199360076","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":[0.037621178,0.000038057897,0.95773345,0.00132304,0.000051428935,0.00008874209,0.00011539337,0.0001953119,0.0028334127],"genre_scores_gemma":[0.91463286,0.00043532116,0.07048574,0.000267705,0.00046606848,0.000014510952,0.012993413,0.00007534645,0.00062905013],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998291,0.000115553274,0.0003626144,0.0003996492,0.00058591465,0.00024523746],"domain_scores_gemma":[0.9987254,0.00006879474,0.000044819735,0.0007514739,0.00018680954,0.00022266149],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003286577,0.00017371422,0.00034954082,0.000104576466,0.00007678769,0.00015370065,0.0002382744,0.00010918697,0.0025424792],"category_scores_gemma":[0.00039566396,0.00014665075,0.00007942964,0.000916533,0.00012415464,0.00037871135,0.00006241096,0.0001959939,0.000093931696],"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":[0.00020109054,0.00087890035,0.0037283036,0.00036379308,0.0118641555,0.008414727,0.002402341,0.60265326,0.26842085,0.0007947109,0.08243144,0.017846396],"study_design_scores_gemma":[0.0003707809,0.00002096033,0.00030262972,0.000018245595,0.0007127887,0.000010523425,0.000111966,0.9895767,0.00834964,0.000009973068,0.00032505763,0.00019072981],"about_ca_topic_score_codex":0.00020228919,"about_ca_topic_score_gemma":0.00042231253,"teacher_disagreement_score":0.8872477,"about_ca_system_score_codex":0.000042843574,"about_ca_system_score_gemma":0.00010157629,"threshold_uncertainty_score":0.99836934},"labels":[],"label_agreement":null},{"id":"W3201974489","doi":"10.1016/j.media.2021.102250","title":"Probabilistic 4D predictive model from in-room surrogates using conditional generative networks for image-guided radiotherapy","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Artificial intelligence; Probabilistic logic; Robustness (evolution); Generative model; Population; Scalability; Machine learning; Pattern recognition (psychology); Computer vision; Generative grammar","score_opus":0.01827540480223388,"score_gpt":0.32744500957929706,"score_spread":0.3091696047770632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201974489","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":[0.03589897,0.0003740077,0.9624353,0.0003048514,0.000033889235,0.00030962267,0.00049370783,0.000056289606,0.00009335519],"genre_scores_gemma":[0.34369147,0.00006163803,0.65225494,0.00043688642,0.00063202943,0.00027025738,0.0024958923,0.000055699173,0.000101215854],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979474,0.0001646869,0.00051565905,0.0006035889,0.00039829907,0.00037037523],"domain_scores_gemma":[0.99858445,0.0004052433,0.00016898563,0.00031884303,0.00034289612,0.00017955659],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002715988,0.00026620776,0.000666663,0.00015454926,0.00015955014,0.000101999474,0.00020991852,0.00011598918,0.0022808225],"category_scores_gemma":[0.00010985826,0.00025077804,0.00041322559,0.0007449167,0.00027561188,0.0002862733,0.000043759137,0.0002857984,4.3706254e-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":[0.00012483506,0.00092662877,0.024623277,0.00002129227,0.007303998,0.00008623797,0.00072839914,0.9346396,0.020808458,0.004458479,0.0015028024,0.004776009],"study_design_scores_gemma":[0.0009309875,0.00002207175,0.00031486605,0.00002340719,0.00050125935,0.0000010858396,0.000069497524,0.9732794,0.004340889,0.020219354,0.00005430291,0.000242891],"about_ca_topic_score_codex":0.00026489285,"about_ca_topic_score_gemma":0.00007036784,"teacher_disagreement_score":0.3101804,"about_ca_system_score_codex":0.00017421137,"about_ca_system_score_gemma":0.0003296746,"threshold_uncertainty_score":0.99999446},"labels":[],"label_agreement":null},{"id":"W3204174615","doi":"10.1016/j.media.2021.102252","title":"Cross-covariance isolate detect: A new change-point method for estimating dynamic functional connectivity","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Covariance; Computer science; Sliding window protocol; Change detection; Dynamic functional connectivity; A priori and a posteriori; Resting state fMRI; Pattern recognition (psychology); Artificial intelligence; Time point; Functional magnetic resonance imaging; Data point; Window (computing); Mathematics; Statistics","score_opus":0.05422623268108318,"score_gpt":0.36570928125433916,"score_spread":0.311483048573256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204174615","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":[0.007863855,0.00016214179,0.96249944,0.02816288,0.00066736416,0.00024363202,0.00006302055,0.00016752993,0.00017013852],"genre_scores_gemma":[0.33200407,0.000052770105,0.63279283,0.028550575,0.0016520369,0.0005705753,0.00006698604,0.000094439994,0.0042157136],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996269,0.0003873979,0.00047700497,0.0013167612,0.0009975194,0.00055229984],"domain_scores_gemma":[0.98454654,0.014041884,0.00021291805,0.00051154854,0.00035949275,0.00032764138],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015379743,0.00029875306,0.0006931071,0.0002613719,0.00057552196,0.00021348597,0.00027680816,0.0001587834,0.0021175665],"category_scores_gemma":[0.10183658,0.0002868947,0.0006553681,0.0023610052,0.00024519896,0.0005551456,0.0003072277,0.00041186129,0.00007316832],"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":[0.0009471792,0.001227753,0.0040470916,0.0005123208,0.005629619,0.0015528717,0.0019907563,0.012407619,0.5160154,0.0024935873,0.0121256085,0.4410502],"study_design_scores_gemma":[0.0010503016,0.000062852625,0.0060196025,0.00003053497,0.00072566775,0.00009937632,0.00004650804,0.96168053,0.022901203,0.0054359776,0.0015829537,0.00036450126],"about_ca_topic_score_codex":0.00022653419,"about_ca_topic_score_gemma":0.0008140421,"teacher_disagreement_score":0.94927293,"about_ca_system_score_codex":0.00016395039,"about_ca_system_score_gemma":0.00034076392,"threshold_uncertainty_score":0.99995834},"labels":[],"label_agreement":null},{"id":"W3206709865","doi":"10.1016/j.media.2021.102260","title":"Population-based 3D respiratory motion modelling from convolutional autoencoders for 2D ultrasound-guided radiotherapy","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Image-guided radiation therapy; Artificial intelligence; Computer science; Computer vision; Population; Modality (human–computer interaction); Medical imaging; 3D ultrasound; Motion (physics); Ultrasound; Radiology; Medicine","score_opus":0.017838422751916605,"score_gpt":0.3104975805297779,"score_spread":0.2926591577778613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206709865","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":[0.017389866,0.00035630952,0.98131007,0.00034454543,0.000058221234,0.00014784536,0.00017070526,0.000113847724,0.000108561166],"genre_scores_gemma":[0.2993762,0.000024358169,0.69537663,0.0014080657,0.0006058969,0.0001211967,0.0028766019,0.000049026574,0.00016206423],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817026,0.00012942491,0.0004549304,0.00047166875,0.00051282835,0.0002609032],"domain_scores_gemma":[0.99861807,0.00046239572,0.00016193526,0.0003641574,0.00022960223,0.0001638322],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003057878,0.00019262283,0.00043615288,0.00016476428,0.00017957001,0.000058773654,0.00017268247,0.000103938444,0.0072353776],"category_scores_gemma":[0.00008070521,0.00019309345,0.0004690906,0.0005910714,0.00008688949,0.00018085199,0.000009608848,0.00017747123,0.0000020248317],"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":[0.00007983411,0.0007203075,0.31418186,0.000029810755,0.006103545,0.000021807291,0.00029000881,0.63082224,0.019355493,0.0024128905,0.0031436412,0.022838578],"study_design_scores_gemma":[0.0008362704,0.000014247908,0.0017607642,0.000015386966,0.0004420802,3.2173784e-7,0.000029419181,0.9886586,0.0035589626,0.0020665647,0.0023746577,0.0002427077],"about_ca_topic_score_codex":0.0010064489,"about_ca_topic_score_gemma":0.000027043863,"teacher_disagreement_score":0.3578364,"about_ca_system_score_codex":0.00014045874,"about_ca_system_score_gemma":0.00019073032,"threshold_uncertainty_score":0.99367213},"labels":[],"label_agreement":null},{"id":"W3210027215","doi":"10.1016/j.media.2021.102295","title":"Diagnosing glaucoma on imbalanced data with self-ensemble dual-curriculum learning","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Science and Technology Project of Nantong City; Fundamental Research Funds for Central Universities of the Central South University; National Key Research and Development Program of China; Natural Science Foundation of Hunan Province; National Natural Science Foundation of China","keywords":"Glaucoma; Artificial intelligence; Computer science; Feature (linguistics); Discriminative model; Weighting; Machine learning; Pattern recognition (psychology); Feature vector; Feature learning; Medicine; Ophthalmology; Radiology","score_opus":0.010087269101009787,"score_gpt":0.2993627430291062,"score_spread":0.28927547392809644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210027215","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":[0.9509219,0.0007627027,0.026265144,0.01399003,0.00005735573,0.00010448131,0.000009865572,0.00035484476,0.0075336853],"genre_scores_gemma":[0.98376507,0.00053338794,0.010349156,0.0018390563,0.00034019345,0.000010282903,0.0011190398,0.0000406172,0.00200322],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962689,0.00027448713,0.0004677094,0.0009440699,0.0015498569,0.0004949528],"domain_scores_gemma":[0.99728984,0.00031656088,0.00016512081,0.0012979936,0.0003663992,0.000564111],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007782415,0.00028209525,0.0009898226,0.00035430022,0.00022228742,0.00015016954,0.00027129764,0.00011504582,0.0014337301],"category_scores_gemma":[0.0023947353,0.00020282244,0.00035621936,0.0032111192,0.00014404538,0.00019301065,0.00023897791,0.0007981686,0.00015605382],"study_design_candidate":"observational","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":[0.00007720108,0.0016535218,0.93846375,0.00014403174,0.009370974,0.020630557,0.00022608637,0.000062339626,0.0026058399,0.00002541636,0.0075134463,0.019226842],"study_design_scores_gemma":[0.005832204,0.00079675706,0.16251709,0.0015186236,0.05529144,0.0015259625,0.0030181033,0.7284073,0.010482341,0.000036158086,0.029100737,0.0014732889],"about_ca_topic_score_codex":0.00025352393,"about_ca_topic_score_gemma":0.000106702086,"teacher_disagreement_score":0.7759467,"about_ca_system_score_codex":0.000068724126,"about_ca_system_score_gemma":0.00024151686,"threshold_uncertainty_score":0.9994791},"labels":[],"label_agreement":null},{"id":"W3213990473","doi":"10.1016/j.media.2023.103058","title":"Acquisition-invariant brain MRI segmentation with informative uncertainties","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"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; National Institute on Aging; National Institute for Health and Care Research; Northern California Institute for Research and Education; BioClinica; Biogen; Pfizer; Novartis Pharmaceuticals Corporation; Wellcome Trust; University of Southern California; Engineering and Physical Sciences Research Council; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; University College London Hospitals NHS Foundation Trust; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Segmentation; Computer science; Task (project management); Artificial intelligence; Context (archaeology); Machine learning; Invariant (physics); Quality (philosophy); Data mining; Mathematics","score_opus":0.00644885826553453,"score_gpt":0.29685513854852047,"score_spread":0.29040628028298593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213990473","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":[0.24368085,0.0000798546,0.63144666,0.11615886,0.00011785897,0.00039164882,0.000015853,0.00056905113,0.007539369],"genre_scores_gemma":[0.9552686,0.00030788372,0.016171675,0.020664828,0.0004638136,0.00008958968,0.0019417071,0.00005261145,0.0050392835],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977127,0.00009855854,0.0003836516,0.00026825457,0.0011943133,0.00034252513],"domain_scores_gemma":[0.99873763,0.00031664345,0.00011735673,0.00026526794,0.00015399262,0.0004091143],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010871955,0.0001671585,0.00046009303,0.00066855486,0.00015736409,0.000072967436,0.00013688783,0.000086988664,0.0022631658],"category_scores_gemma":[0.0009044532,0.00011436141,0.00019769778,0.0027244175,0.00030683205,0.00021727,0.00006322149,0.00041596554,0.0002529173],"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":[0.001379034,0.0011069207,0.2696352,0.0013981843,0.03331619,0.012395584,0.030621773,0.011277475,0.009199643,0.005034866,0.44941133,0.1752238],"study_design_scores_gemma":[0.0035312376,0.00035168967,0.06587263,0.00026243096,0.003490137,0.00013711042,0.004921779,0.91404307,0.00075741956,0.00039711717,0.005816384,0.0004189872],"about_ca_topic_score_codex":0.00021349697,"about_ca_topic_score_gemma":0.000024317787,"teacher_disagreement_score":0.9027656,"about_ca_system_score_codex":0.00006917728,"about_ca_system_score_gemma":0.0001686827,"threshold_uncertainty_score":0.9986489},"labels":[],"label_agreement":null},{"id":"W390146591","doi":"10.1016/j.media.2015.05.005","title":"Hierarchical max-flow segmentation framework for multi-atlas segmentation with Kohonen self-organizing map based Gaussian mixture modeling","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"National Center for Research Resources; National Institute of Mental Health; National Institute on Aging; Canadian Institutes of Health Research","keywords":"Segmentation; Computer science; Scale-space segmentation; Artificial intelligence; Self-organizing map; Image segmentation; Segmentation-based object categorization; Pattern recognition (psychology); Minimum spanning tree-based segmentation; Atlas (anatomy); Mixture model; Computer vision; Artificial neural network","score_opus":0.028928817870087917,"score_gpt":0.3196785556511626,"score_spread":0.29074973778107466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W390146591","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":[0.0010396708,0.00007949373,0.9927869,0.0046422877,0.00014192263,0.00064222893,0.000013649657,0.00061944866,0.000034429704],"genre_scores_gemma":[0.020805918,0.000014339607,0.97521603,0.0029578658,0.00019146709,0.00022566204,0.0004958267,0.00004088632,0.000051979066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952,0.00037985534,0.0007573306,0.000937503,0.0021437637,0.00058158644],"domain_scores_gemma":[0.99714345,0.0003516479,0.00027434982,0.0007156654,0.00050481816,0.0010100702],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015578938,0.00037355226,0.00057174946,0.0006042796,0.00023692445,0.00043152762,0.0010064107,0.0003045254,0.0003330875],"category_scores_gemma":[0.0009363905,0.000302198,0.0002510137,0.0020747331,0.00014808643,0.0009886952,0.0001772619,0.00057313277,0.000041475676],"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":[0.0013550019,0.0117360195,0.021143975,0.0025366296,0.017697735,0.0029606582,0.059326276,0.058722906,0.03925114,0.0057841553,0.05901649,0.720469],"study_design_scores_gemma":[0.0016334791,0.00017130742,0.000045676225,0.00008426271,0.0006150671,0.000006821655,0.00036432993,0.979207,0.016493274,0.0009591815,0.00004378172,0.00037586462],"about_ca_topic_score_codex":0.000074425596,"about_ca_topic_score_gemma":0.000054646764,"teacher_disagreement_score":0.92048407,"about_ca_system_score_codex":0.00026134378,"about_ca_system_score_gemma":0.00043336826,"threshold_uncertainty_score":0.999943},"labels":[],"label_agreement":null},{"id":"W4200066891","doi":"10.1016/j.media.2021.102336","title":"Head and neck tumor segmentation in PET/CT: The HECKTOR challenge","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":203,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Université de Sherbrooke","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Segmentation; Thresholding; Artificial intelligence; Computer science; Sørensen–Dice coefficient; Modality (human–computer interaction); Leverage (statistics); Positron emission tomography; Medicine; Nuclear medicine; Medical physics; Pattern recognition (psychology); Image segmentation; Computer vision; Image (mathematics)","score_opus":0.009524723942521691,"score_gpt":0.3205935885383795,"score_spread":0.3110688645958578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200066891","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":[0.93156624,0.0016856819,0.0022206304,0.062325645,0.00007063656,0.000111464615,0.000001940773,0.000031980544,0.0019857916],"genre_scores_gemma":[0.9880181,0.0009808907,0.003254615,0.0066135055,0.00019489079,0.000020766583,0.00007440078,0.000017983568,0.0008248326],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817896,0.00016513202,0.0003570565,0.00034755023,0.0006884378,0.00026287153],"domain_scores_gemma":[0.99906766,0.0001981572,0.00006453217,0.00028942738,0.00007002192,0.00031019884],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008039452,0.000132149,0.00044039945,0.00017715397,0.000089789995,0.00005205758,0.00010434509,0.000014694182,0.0016453441],"category_scores_gemma":[0.001772995,0.000088381545,0.0001673589,0.00091722835,0.00020924608,0.000073295196,0.00008859398,0.0006014485,0.000021909696],"study_design_candidate":"observational","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":[0.00015382298,0.0019147868,0.614062,0.0005927432,0.0037786853,0.104182556,0.0028010178,0.000068242356,0.005461352,0.00069703226,0.00682184,0.2594659],"study_design_scores_gemma":[0.008366926,0.00024662854,0.45618173,0.0005669863,0.0048511545,0.0049886582,0.004218274,0.49612457,0.001195922,0.0005351261,0.022098256,0.0006257548],"about_ca_topic_score_codex":0.00031580345,"about_ca_topic_score_gemma":0.00028229112,"teacher_disagreement_score":0.49605635,"about_ca_system_score_codex":0.000047460366,"about_ca_system_score_gemma":0.00013180054,"threshold_uncertainty_score":0.9992673},"labels":[],"label_agreement":null},{"id":"W4200557095","doi":"10.1016/j.media.2021.102329","title":"Skin3D: Detection and longitudinal tracking of pigmented skin lesions in 3D total-body textured meshes","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Nvidia","keywords":"Polygon mesh; Artificial intelligence; Computer science; Computer vision; Geodesic; Matching (statistics); Lesion; Pattern recognition (psychology); Skin lesion; Mathematics; Medicine; Pathology; Computer graphics (images); Geometry","score_opus":0.010825215192580057,"score_gpt":0.2798404174109954,"score_spread":0.26901520221841535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200557095","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":[0.9668386,0.00041465822,0.03004406,0.0011580692,0.00007703501,0.00014459425,0.000003326749,0.000040284063,0.0012793437],"genre_scores_gemma":[0.9979525,0.00021678768,0.0006737613,0.00016182766,0.00006283817,0.000011025649,0.000027271413,0.000010772143,0.0008832192],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983273,0.00010156895,0.00043972925,0.00035021486,0.00056729815,0.00021385058],"domain_scores_gemma":[0.99922645,0.00009100891,0.00009047593,0.00025431742,0.00012696773,0.00021080246],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00037334854,0.00013244274,0.00050594244,0.00051231304,0.000057798447,0.000025553973,0.000047847614,0.00010935169,0.0020227025],"category_scores_gemma":[0.00067251513,0.00011682063,0.00021552511,0.0015272708,0.000102445876,0.00006341921,0.000080608515,0.00023929878,0.0000073378433],"study_design_candidate":"observational","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":[0.00045167655,0.002183055,0.06953971,0.000534124,0.0055883424,0.009616127,0.00095214706,0.0001292309,0.16387545,0.000055298788,0.00038551094,0.7466893],"study_design_scores_gemma":[0.0029801042,0.00027793332,0.849289,0.00024345801,0.005354764,0.0009741024,0.0015583695,0.07202777,0.06555935,0.00003670576,0.0013785758,0.0003198464],"about_ca_topic_score_codex":0.00033539833,"about_ca_topic_score_gemma":0.001930027,"teacher_disagreement_score":0.77974933,"about_ca_system_score_codex":0.00006714008,"about_ca_system_score_gemma":0.000054889337,"threshold_uncertainty_score":0.99888957},"labels":[],"label_agreement":null},{"id":"W4205470984","doi":"10.1016/j.media.2021.102347","title":"ProstAttention-Net: A deep attention model for prostate cancer segmentation by aggressiveness in MRI scans","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":96,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Lyon; Université Claude Bernard Lyon 1; Agence Nationale de la Recherche","keywords":"Prostate cancer; Prostate; Prostatectomy; Magnetic resonance imaging; Grading (engineering); Segmentation; Medicine; Receiver operating characteristic; Prostate biopsy; Computer science; Biopsy; Artificial intelligence; Radiology; Cancer; Internal medicine","score_opus":0.010217428877475912,"score_gpt":0.31484505776938976,"score_spread":0.30462762889191386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205470984","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":[0.7995431,0.004393343,0.17456172,0.016964044,0.00015800861,0.0029507577,0.0012923055,0.00007531583,0.00006142379],"genre_scores_gemma":[0.9795241,0.0016399848,0.0013718845,0.001416641,0.000048528575,0.0101570105,0.0042935587,0.00003833691,0.0015099987],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976964,0.00009255083,0.0004767314,0.0005210219,0.0008504804,0.00036280995],"domain_scores_gemma":[0.99915594,0.000049261893,0.00020545746,0.00021727478,0.00015029515,0.00022176625],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00045382566,0.00018495253,0.00047210074,0.00034484357,0.00022056156,0.000033904747,0.00010338146,0.00005555173,0.0011125394],"category_scores_gemma":[0.000056560773,0.00016405496,0.0003105171,0.0011020276,0.00008390061,0.0001424813,0.00006755163,0.0002035051,0.0000032980652],"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":[0.0011673868,0.0037780758,0.8170531,0.000514363,0.004421439,0.0003662423,0.0027520135,0.034897324,0.0065566036,0.00002631962,0.0140593015,0.11440784],"study_design_scores_gemma":[0.006497636,0.00032616063,0.019240942,0.00013073604,0.0035701199,0.000006685596,0.0007727061,0.96699387,0.0014323383,0.00014030702,0.0006212346,0.0002672949],"about_ca_topic_score_codex":0.0007359889,"about_ca_topic_score_gemma":0.0007831019,"teacher_disagreement_score":0.93209654,"about_ca_system_score_codex":0.0006730013,"about_ca_system_score_gemma":0.0002498294,"threshold_uncertainty_score":0.99980056},"labels":[],"label_agreement":null},{"id":"W4221132458","doi":"10.1016/j.media.2022.102432","title":"Mapping heterogenous anisotropic tissue mechanical properties with transverse isotropic nonlinear inversion MR elastography","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Elasticity and Material Modeling","field":"Engineering","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; National Science Foundation","keywords":"Magnetic resonance elastography; Anisotropy; Isotropy; Elastography; Materials science; White matter; Diffusion MRI; Nuclear magnetic resonance; Transverse plane; Nonlinear system; Biomedical engineering; Magnetic resonance imaging; Physics; Optics; Acoustics; Ultrasound; Anatomy; Radiology; Medicine","score_opus":0.008492318509760332,"score_gpt":0.1900310918492953,"score_spread":0.18153877333953497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221132458","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":[0.7027202,0.00013488393,0.2964742,0.00014350898,0.00011757902,0.000101559315,0.000015258194,0.00023358763,0.000059178885],"genre_scores_gemma":[0.9931861,0.00008519379,0.0063152867,0.00016938486,0.00009495773,0.00004172275,0.000048028807,0.000034594224,0.000024729961],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981902,0.00009583757,0.00031762986,0.0002962072,0.0007309008,0.00036919696],"domain_scores_gemma":[0.99944305,0.00002309454,0.00003385205,0.0002393465,0.00004070604,0.00021996282],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015621612,0.00020721977,0.0004094684,0.00040388302,0.00028718708,0.000045756566,0.00029193945,0.00008058322,0.0017514994],"category_scores_gemma":[0.000021581423,0.00017661405,0.0001835309,0.0011165437,0.00008730942,0.00013708812,0.00010540872,0.00038717105,0.000029087325],"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":[0.000304628,0.0006319583,0.00074695196,0.00060806033,0.0060910448,0.0013797843,0.0046094395,0.34336853,0.6304488,0.00008634558,0.00043669372,0.011287747],"study_design_scores_gemma":[0.0011567635,0.00043770112,0.00004822451,0.00006122679,0.0013254394,0.000038803995,0.0013989889,0.95617384,0.032391742,0.000024784944,0.0063728285,0.00056964357],"about_ca_topic_score_codex":0.00017857313,"about_ca_topic_score_gemma":0.00015472974,"teacher_disagreement_score":0.6128053,"about_ca_system_score_codex":0.00007250626,"about_ca_system_score_gemma":0.000031431784,"threshold_uncertainty_score":0.99916106},"labels":[],"label_agreement":null},{"id":"W4223609437","doi":"10.1016/j.media.2022.102456","title":"Reasoning discriminative dictionary-embedded network for fully automatic vertebrae tumor diagnosis","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Discriminative model; Artificial intelligence; Computer science; Feature (linguistics); Pattern recognition (psychology); Smoothing; Computer vision","score_opus":0.006446025547585492,"score_gpt":0.2461280501562718,"score_spread":0.2396820246086863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223609437","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":[0.1060148,0.0022232258,0.88130754,0.004179222,0.0008766017,0.00049735035,0.00024283909,0.0015673215,0.0030911122],"genre_scores_gemma":[0.98182917,0.00010311145,0.013431092,0.0012931259,0.0005628377,0.0015025185,0.00065634475,0.00007831068,0.00054350926],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99680257,0.00021448622,0.00061711826,0.00045646005,0.0012745704,0.00063479657],"domain_scores_gemma":[0.99823475,0.000679971,0.000102264894,0.000407542,0.00008354881,0.000491935],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011866791,0.00028211315,0.00075928087,0.000409272,0.00056986004,0.00007679825,0.00049764046,0.000058258007,0.013816583],"category_scores_gemma":[0.0012496442,0.00026298096,0.00074868236,0.0026717398,0.00015258805,0.0001656224,0.00016871149,0.0005477313,0.00003510344],"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":[0.000026396305,0.0008433061,0.03762614,0.0005178244,0.019873489,0.0009799474,0.0025927988,0.19169043,0.0001637836,0.0005861089,0.53247064,0.21262912],"study_design_scores_gemma":[0.00041550514,0.00003599222,0.0019352057,0.000038900147,0.003605228,0.000010591907,0.0006374742,0.9868734,0.000059212645,0.00031778985,0.0057576764,0.00031303955],"about_ca_topic_score_codex":0.00010705091,"about_ca_topic_score_gemma":0.000036078178,"teacher_disagreement_score":0.8758143,"about_ca_system_score_codex":0.00018339546,"about_ca_system_score_gemma":0.000064717446,"threshold_uncertainty_score":0.99998224},"labels":[],"label_agreement":null},{"id":"W4226378137","doi":"10.1016/j.media.2022.102526","title":"Constrained unsupervised anomaly segmentation","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Anomaly Detection Techniques and 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":"École de Technologie Supérieure","funders":"European Regional Development Fund; Generalitat Valenciana; European Commission","keywords":"Computer science; Segmentation; Anomaly detection; Constraint (computer-aided design); Artificial intelligence; Hyperparameter; Regularization (linguistics); Pattern recognition (psychology); Machine learning; Mathematics","score_opus":0.006985585779932297,"score_gpt":0.2591613300058138,"score_spread":0.2521757442258815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226378137","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":[0.012338574,0.00002390511,0.9813775,0.003921125,0.000028147411,0.00009544043,0.000009416964,0.00028847274,0.0019174265],"genre_scores_gemma":[0.94056404,0.000010971551,0.05696102,0.0016571463,0.000027920267,0.00021403984,0.000054609758,0.0000050398457,0.00050519436],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985488,0.00011110722,0.00024386955,0.0003131477,0.00062726287,0.00015577768],"domain_scores_gemma":[0.9992716,0.000053233674,0.000073515206,0.00040756384,0.000051896674,0.0001422184],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044247176,0.00007906165,0.00015708928,0.00027772124,0.00036280515,0.00007365262,0.00069306954,0.00002804986,0.0046492023],"category_scores_gemma":[0.00003549769,0.000077895784,0.00018783347,0.0025704512,0.00006961974,0.00017391569,0.00029749557,0.00016804978,0.000028636427],"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":[0.000026108433,0.0017331444,0.01387519,0.000032253058,0.0029847855,0.0004973289,0.0023535152,0.0009972366,0.036570493,0.08613047,0.026842164,0.82795733],"study_design_scores_gemma":[0.00063154113,0.00016690232,0.004286754,0.0000019867393,0.00045589753,0.000053061503,0.00048435648,0.96226037,0.007831229,0.0024602101,0.020955898,0.00041177476],"about_ca_topic_score_codex":0.0001281947,"about_ca_topic_score_gemma":0.00001466732,"teacher_disagreement_score":0.9612632,"about_ca_system_score_codex":0.000054410004,"about_ca_system_score_gemma":0.00007358159,"threshold_uncertainty_score":0.9962607},"labels":[],"label_agreement":null},{"id":"W4229333559","doi":"10.1016/j.media.2022.102476","title":"Bridging the gap between constrained spherical deconvolution and diffusional variance decomposition via tensor‐valued diffusion MRI","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Philips (Canada); CARE Canada; Université de Sherbrooke","funders":"","keywords":"Diffusion MRI; Deconvolution; Fractional anisotropy; Computer science; Tensor (intrinsic definition); Anisotropy; Orientation (vector space); Algorithm; Diffusion; White matter; Mathematics; Artificial intelligence; Physics; Magnetic resonance imaging; Geometry; Optics","score_opus":0.02731257130503184,"score_gpt":0.34251903067927053,"score_spread":0.3152064593742387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229333559","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":[0.20063663,0.00008549467,0.78096473,0.01772747,0.00001838005,0.0002495096,0.000030215337,0.00013037551,0.00015721294],"genre_scores_gemma":[0.97252935,0.000065191496,0.02429633,0.0023596785,0.00018227761,0.000108020686,0.00029027465,0.00001839422,0.000150476],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980404,0.00016942115,0.00036824576,0.0004320238,0.0007426591,0.00024727278],"domain_scores_gemma":[0.9989742,0.00022083646,0.00013260687,0.00035721116,0.000069510235,0.00024564262],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046871972,0.0001529024,0.00037769758,0.00012425183,0.0006742145,0.00002646563,0.00017589034,0.000051851373,0.0012584854],"category_scores_gemma":[0.00016396662,0.00011516933,0.00019735543,0.00094450085,0.0003707228,0.00006496926,0.0002868017,0.00052715815,0.00000567977],"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":[0.000580989,0.0028492445,0.3720867,0.00015879767,0.002922822,0.0010182923,0.000746395,0.00045409414,0.27187872,0.0043559577,0.014624504,0.32832348],"study_design_scores_gemma":[0.0016655943,0.00020375279,0.24452,0.00003745437,0.0032143306,0.00045500076,0.00012275997,0.7411597,0.0007313346,0.0028203004,0.004723757,0.0003460808],"about_ca_topic_score_codex":0.00007933303,"about_ca_topic_score_gemma":0.0000034365687,"teacher_disagreement_score":0.7718927,"about_ca_system_score_codex":0.00008835333,"about_ca_system_score_gemma":0.000055155742,"threshold_uncertainty_score":0.9996545},"labels":[],"label_agreement":null},{"id":"W4281765497","doi":"10.1016/j.media.2022.102507","title":"Deep learning models of cognitive processes constrained by human brain connectomes","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institut Universitaire de Gériatrie de Montréal","funders":"","keywords":"Human Connectome Project; Connectome; Computer science; Decoding methods; Cognition; Graph; Artificial intelligence; Neural decoding; Machine learning; Inference; Subnetwork; Neuroscience; Theoretical computer science; Psychology; Functional connectivity; Algorithm","score_opus":0.029169179019087586,"score_gpt":0.29471047534253786,"score_spread":0.26554129632345025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281765497","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":[0.8040093,0.00083979825,0.1562072,0.02659549,0.00011688431,0.00050654827,0.0003118393,0.00036261708,0.011050273],"genre_scores_gemma":[0.9949386,0.000024710285,0.0000351771,0.0041732388,0.000026507138,0.00009754099,0.00006574935,0.000016233516,0.0006222345],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967077,0.00062684575,0.0003694681,0.0006062941,0.0013948106,0.0002949324],"domain_scores_gemma":[0.9837021,0.015589694,0.00022247288,0.00014584484,0.00020042613,0.0001394139],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00079259695,0.00017327498,0.0005172448,0.0003571165,0.0006559061,0.000030478039,0.0003188904,0.000058569847,0.004055193],"category_scores_gemma":[0.062540464,0.00016786628,0.00021334401,0.0026115577,0.0007980269,0.00020307262,0.00034279982,0.00061042875,0.000007730576],"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":[0.00093755,0.00742857,0.033165086,0.0009929603,0.012681757,0.0018861624,0.036138184,0.03556915,0.7740411,0.0074929795,0.055182382,0.03448411],"study_design_scores_gemma":[0.00876823,0.0028301752,0.0019109481,0.00017123736,0.005700207,0.00016525431,0.04995473,0.7254402,0.18544813,0.011999996,0.0050328155,0.002578071],"about_ca_topic_score_codex":0.00011651587,"about_ca_topic_score_gemma":0.00009226304,"teacher_disagreement_score":0.6898711,"about_ca_system_score_codex":0.000046267884,"about_ca_system_score_gemma":0.00011815058,"threshold_uncertainty_score":0.99685526},"labels":[],"label_agreement":null},{"id":"W4283316793","doi":"10.1016/j.media.2022.102520","title":"MVFStain: Multiple virtual functional stain histopathology images generation based on specific domain mapping","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Stain; Staining; Artificial intelligence; Computer science; H&E stain; Pathology; Pattern recognition (psychology); Medicine","score_opus":0.01887046352473579,"score_gpt":0.2305144341979102,"score_spread":0.21164397067317442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283316793","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":[0.012659219,0.00007613448,0.9791698,0.006721579,0.0006957604,0.000115910494,0.00001662704,0.00016989316,0.0003750769],"genre_scores_gemma":[0.9508546,0.000012527902,0.043758012,0.0036318721,0.0006256318,0.00021233431,0.00018963212,0.00002101486,0.0006943644],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996011,0.0007670769,0.00042172772,0.00080250786,0.0016448752,0.00035279646],"domain_scores_gemma":[0.9984723,0.00034982618,0.0001680504,0.00071364484,0.00011496741,0.00018121676],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018228445,0.00018638375,0.0003077962,0.00089636736,0.0006606553,0.00011196779,0.00067716365,0.000075674034,0.0031308269],"category_scores_gemma":[0.0002934958,0.00019238354,0.00027846682,0.0023715952,0.00015210592,0.00026559096,0.00033081634,0.00050240423,0.00004980657],"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":[0.00033655178,0.0018094569,0.0071462756,0.000035744604,0.0008095164,0.003336215,0.0026234654,0.3253776,0.12286087,0.006852138,0.19297525,0.3358369],"study_design_scores_gemma":[0.000709347,0.0001841579,0.0031707047,0.0000023355133,0.000053816828,0.000022924729,0.00027084662,0.96391904,0.000829943,0.00028143259,0.03030817,0.00024729536],"about_ca_topic_score_codex":0.000046410612,"about_ca_topic_score_gemma":0.00003836367,"teacher_disagreement_score":0.9381954,"about_ca_system_score_codex":0.0007818217,"about_ca_system_score_gemma":0.00021124748,"threshold_uncertainty_score":0.99778044},"labels":[],"label_agreement":null},{"id":"W4285602699","doi":"10.1016/j.media.2022.102532","title":"Cardiac MRI segmentation with sparse annotations: Ensembling deep learning uncertainty and shape priors","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; GE Healthcare; National Natural Science Foundation of China; Ontario Research Foundation","keywords":"Artificial intelligence; Prior probability; Segmentation; Computer science; Pattern recognition (psychology); Computer vision; Machine learning; Bayesian probability","score_opus":0.006567144916448316,"score_gpt":0.2791082115076999,"score_spread":0.27254106659125155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285602699","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":[0.9097169,0.0012137443,0.08030285,0.00764321,0.00008237988,0.0002791263,0.0000051309166,0.00013239312,0.000624269],"genre_scores_gemma":[0.9844522,0.000586821,0.011909439,0.0018855776,0.00015783611,0.0000809915,0.00042412273,0.00003598684,0.00046701205],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99724007,0.0003341675,0.00036543098,0.00045938036,0.0012786887,0.0003222597],"domain_scores_gemma":[0.99882096,0.0002828329,0.00015309037,0.00020800823,0.00011256875,0.0004225164],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013764335,0.00018005542,0.0005340747,0.00047721516,0.00053851184,0.00006783676,0.00011336289,0.000051273284,0.0020070595],"category_scores_gemma":[0.0009360243,0.00014817607,0.00018588032,0.0014898092,0.00022500273,0.00011156345,0.00012630982,0.0010262066,0.0000070819133],"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":[0.0003809637,0.00039452547,0.46423838,0.00017794085,0.0056691603,0.0015870086,0.006890787,0.050466258,0.004419563,0.00010237214,0.0010632473,0.4646098],"study_design_scores_gemma":[0.0014249792,0.0002671816,0.018358594,0.000044331646,0.0034523476,0.00009830687,0.00537073,0.96550256,0.000045433797,0.00002027793,0.0051785246,0.0002367455],"about_ca_topic_score_codex":0.00027055191,"about_ca_topic_score_gemma":0.000018113955,"teacher_disagreement_score":0.91503626,"about_ca_system_score_codex":0.00011706833,"about_ca_system_score_gemma":0.00012397478,"threshold_uncertainty_score":0.99890524},"labels":[],"label_agreement":null},{"id":"W4286256866","doi":"10.1016/j.media.2022.102554","title":"Task relevance driven adversarial learning for simultaneous detection, size grading, and quantification of hepatocellular carcinoma via integrating multi-modality MRI","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"China Scholarship Council","keywords":"Computer science; Modality (human–computer interaction); Artificial intelligence; Pattern recognition (psychology); Machine learning","score_opus":0.008804619070751366,"score_gpt":0.2814590973556853,"score_spread":0.27265447828493394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286256866","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":[0.38900223,0.00016602046,0.60894364,0.0014678445,0.00009459709,0.0002552748,0.0000068871173,0.000047973248,0.000015522548],"genre_scores_gemma":[0.98487025,0.00005417228,0.01427556,0.00020442175,0.00014420474,0.00006482204,0.00012902795,0.000031878826,0.0002256461],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99727327,0.00034327747,0.0006950784,0.00056164176,0.00081925665,0.000307485],"domain_scores_gemma":[0.99722856,0.0015308732,0.00038773066,0.0003033765,0.00024600854,0.00030342705],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017580288,0.00019734795,0.0007001719,0.00026957472,0.00048386608,0.000027393584,0.00018765376,0.0000996215,0.00023849816],"category_scores_gemma":[0.015004864,0.00018424196,0.00035149176,0.00089255586,0.00029499395,0.00007484159,0.00012822691,0.0009689351,0.0000012113808],"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":[0.00083683856,0.0008737455,0.46406874,0.0006867037,0.0027497222,0.00050899276,0.0034499913,0.025354385,0.3812259,0.000086590495,0.00020075332,0.119957626],"study_design_scores_gemma":[0.0017125562,0.00023991933,0.003876003,0.000026560443,0.0016282543,0.000050837345,0.0005257485,0.9881822,0.0019726588,0.000057728706,0.0015616682,0.00016585125],"about_ca_topic_score_codex":0.0009434396,"about_ca_topic_score_gemma":0.000049230763,"teacher_disagreement_score":0.9628278,"about_ca_system_score_codex":0.00013073096,"about_ca_system_score_gemma":0.00010615567,"threshold_uncertainty_score":0.99329215},"labels":[],"label_agreement":null},{"id":"W4286592278","doi":"10.1016/j.media.2022.102531","title":"Estimating medical image registration error and confidence: A taxonomy and scoping review","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":false,"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":"Image registration; Computer science; Taxonomy (biology); Field (mathematics); Artificial intelligence; Estimation; Systematic error; Data mining; Machine learning; Data science; Image (mathematics); Statistics; Mathematics","score_opus":0.02076406305091679,"score_gpt":0.35695223752247734,"score_spread":0.3361881744715606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286592278","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":[0.085533,0.06453639,0.6373446,0.20265463,0.00041757277,0.0026788872,0.000018037179,0.00039433505,0.0064225234],"genre_scores_gemma":[0.6470918,0.028904863,0.22862676,0.08922455,0.0017837915,0.0014939714,0.0008349836,0.00018322271,0.0018560609],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959987,0.00033353874,0.0007977807,0.0006000893,0.0019150412,0.00035487927],"domain_scores_gemma":[0.9979668,0.0004205879,0.00026917242,0.00035631112,0.00010081094,0.0008862882],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0041880016,0.00021674452,0.00092856365,0.00026839072,0.0004082608,0.000079330166,0.00020953294,0.000088767934,0.0073324614],"category_scores_gemma":[0.010222549,0.00018754002,0.00019053537,0.0008859837,0.00061996945,0.00016034942,0.00033292908,0.0011716163,0.000006845425],"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":[0.00027530425,0.0012529439,0.07268988,0.039372288,0.0060829767,0.017147169,0.001614795,0.00010976035,0.0023978977,0.0011855813,0.069500506,0.7883709],"study_design_scores_gemma":[0.0022495128,0.00023680659,0.0024031813,0.015743485,0.0048993938,0.0022472464,0.00037716367,0.96717983,0.000023482273,0.00013998823,0.004006168,0.0004937262],"about_ca_topic_score_codex":0.00028739573,"about_ca_topic_score_gemma":0.00002881608,"teacher_disagreement_score":0.9670701,"about_ca_system_score_codex":0.00005759785,"about_ca_system_score_gemma":0.0004797829,"threshold_uncertainty_score":0.99811476},"labels":[],"label_agreement":null},{"id":"W4290859860","doi":"10.1016/j.media.2022.102567","title":"Grayscale self-adjusting network with weak feature enhancement for 3D lumbar anatomy segmentation","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Feature (linguistics); Lumbar; Deep learning; Process (computing); Magnetic resonance imaging; Image segmentation; Pattern recognition (psychology); Computer vision; Anatomy; Medicine; Radiology","score_opus":0.0034965541401365315,"score_gpt":0.23195369293814336,"score_spread":0.22845713879800683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290859860","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":[0.028660778,0.0010498496,0.96588343,0.0018810218,0.0001944779,0.0002753875,0.000026351292,0.0004830116,0.001545672],"genre_scores_gemma":[0.66342765,0.00060717866,0.32627872,0.0021452669,0.0013097832,0.0012118787,0.0017496808,0.00015094972,0.0031189],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974137,0.000103215076,0.00036889996,0.00039607563,0.0011862327,0.00053188397],"domain_scores_gemma":[0.9990512,0.00013885689,0.000087411136,0.00030238953,0.0000776275,0.00034253133],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007687002,0.0002321335,0.000506412,0.00025062915,0.00040290033,0.00006422939,0.00029681783,0.00006647301,0.0027533392],"category_scores_gemma":[0.000098724486,0.00020050637,0.00029982498,0.0023182638,0.000062297026,0.00011482385,0.000085193526,0.0004612576,0.00001126498],"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":[0.000055283937,0.0009041391,0.029030168,0.00107712,0.029560441,0.00047980202,0.002450745,0.26063606,0.0033838723,0.00011651804,0.4275162,0.24478966],"study_design_scores_gemma":[0.00074946665,0.000052595817,0.00032356792,0.000028292608,0.0042766393,0.0000073932656,0.0006084253,0.9639265,0.0002911047,0.000025393992,0.029386083,0.00032456734],"about_ca_topic_score_codex":0.00003597305,"about_ca_topic_score_gemma":0.000064302934,"teacher_disagreement_score":0.7032904,"about_ca_system_score_codex":0.00018590881,"about_ca_system_score_gemma":0.00006465595,"threshold_uncertainty_score":0.9981583},"labels":[],"label_agreement":null},{"id":"W4293581532","doi":"10.1016/j.media.2022.102610","title":"Predicting treatment-specific lesion outcomes in acute ischemic stroke from 4D CT perfusion imaging using spatio-temporal convolutional neural networks","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; Hotchkiss Brain Institute; University of Calgary","funders":"","keywords":"Convolutional neural network; Deconvolution; Artificial intelligence; Computer science; Deep learning; Pattern recognition (psychology); Dice; Perfusion scanning; Sørensen–Dice coefficient; Perfusion; Machine learning; Medicine; Radiology; Segmentation; Mathematics; Statistics; Algorithm; Image segmentation","score_opus":0.018628474170982328,"score_gpt":0.2860544841063169,"score_spread":0.26742600993533455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293581532","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":[0.9649298,0.00074626587,0.031151414,0.001999868,0.00023865704,0.000367275,0.00014481352,0.000111870904,0.0003100126],"genre_scores_gemma":[0.99193025,0.00010637734,0.0036450615,0.000672235,0.00030743773,0.00006504713,0.0026945963,0.000044885102,0.0005341069],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99578416,0.00022683121,0.0008796735,0.00083425996,0.001672678,0.0006024159],"domain_scores_gemma":[0.9985078,0.0002349626,0.00030004611,0.00055568817,0.000071417104,0.00033006337],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005433602,0.00039235048,0.0009925112,0.00071758614,0.00041093025,0.00006783005,0.0003109037,0.00006664268,0.0063788258],"category_scores_gemma":[0.00012480353,0.0003454761,0.0006288724,0.0011902823,0.0002114193,0.00021191919,0.00061629905,0.00073010667,0.0000067501437],"study_design_candidate":"observational","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":[0.0001974811,0.00037525658,0.97860867,0.0000057803945,0.0015786254,0.002314365,0.00016212388,0.0032466715,0.0029801452,0.0000011496845,0.0021705064,0.008359218],"study_design_scores_gemma":[0.0030853054,0.000075999626,0.078200854,0.00002765227,0.0032513568,0.000073152514,0.0008414299,0.91216373,0.0002753643,0.0000013034535,0.0017527892,0.00025105002],"about_ca_topic_score_codex":0.0033287513,"about_ca_topic_score_gemma":0.00014394666,"teacher_disagreement_score":0.90891707,"about_ca_system_score_codex":0.001104992,"about_ca_system_score_gemma":0.00014192551,"threshold_uncertainty_score":0.99989974},"labels":[],"label_agreement":null},{"id":"W4295025017","doi":"10.1016/j.media.2022.102608","title":"Focused Attention in Transformers for interpretable classification of retinal images","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":90,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôpital Maisonneuve-Rosemont; Polytechnique Montréal","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Transformer; Convolutional neural network; Pattern recognition (psychology); Machine learning; Computer vision","score_opus":0.013977527888023797,"score_gpt":0.31444630171166765,"score_spread":0.30046877382364384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295025017","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":[0.6494945,0.00024361184,0.33642933,0.010783089,0.000045334324,0.00033284028,0.000049085676,0.00004300993,0.0025791563],"genre_scores_gemma":[0.9961098,0.000048577633,0.002214147,0.00018957908,0.000030863495,0.00011424709,0.0003249757,0.000014045126,0.0009537524],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978503,0.00015172148,0.0006210682,0.00033337867,0.0008036478,0.00023991047],"domain_scores_gemma":[0.99921626,0.00012717253,0.00016734656,0.000199457,0.00014823723,0.00014152004],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014719706,0.00011977379,0.00060270116,0.00086223794,0.00008885576,0.0000141791315,0.0001419586,0.00004878791,0.0017598578],"category_scores_gemma":[0.00046630768,0.00010736216,0.000701439,0.0020975785,0.00014618073,0.00009732863,0.00003334975,0.00029779764,0.000003372986],"study_design_candidate":"observational","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":[0.0016948344,0.0020556184,0.62168014,0.00060415984,0.0044618687,0.00017308154,0.00086097355,0.00011966333,0.19346932,0.00010050887,0.0043312553,0.17044859],"study_design_scores_gemma":[0.00524167,0.00078005355,0.33131886,0.00017753168,0.014054931,0.000040965933,0.0044349697,0.6348895,0.006245734,0.00020975995,0.0021753884,0.00043069373],"about_ca_topic_score_codex":0.00028945276,"about_ca_topic_score_gemma":0.000038848124,"teacher_disagreement_score":0.6347698,"about_ca_system_score_codex":0.00010625582,"about_ca_system_score_gemma":0.000100089805,"threshold_uncertainty_score":0.99915266},"labels":[],"label_agreement":null},{"id":"W4296199856","doi":"10.1016/j.media.2022.102617","title":"Source-free domain adaptation for image segmentation","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Hôpital Notre-Dame","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Nvidia","keywords":"Artificial intelligence; Computer vision; Computer science; Domain adaptation; Adaptation (eye); Segmentation; Image (mathematics); Domain (mathematical analysis); Image segmentation; Pattern recognition (psychology); Mathematics; Psychology","score_opus":0.013353712860726735,"score_gpt":0.2706699761746786,"score_spread":0.25731626331395185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296199856","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":[0.003339569,0.000050076967,0.9896811,0.005429415,0.00012365301,0.00018156559,0.000010154812,0.0001641279,0.0010203028],"genre_scores_gemma":[0.18549564,0.000013379351,0.80700725,0.003895809,0.0001611542,0.0004027016,0.00033439475,0.000027990429,0.0026616782],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99731296,0.00032514552,0.00037936794,0.00044534367,0.0012473814,0.00028980785],"domain_scores_gemma":[0.9986755,0.00030149738,0.00018481989,0.0005208932,0.00011359363,0.00020367278],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016330568,0.0001281969,0.00024064787,0.00043026314,0.0005529676,0.00020612717,0.0010442082,0.000039061073,0.0016168304],"category_scores_gemma":[0.00058768986,0.00013053048,0.0002970997,0.0018226987,0.00007031001,0.00046559187,0.00041002643,0.00022559208,0.000037742986],"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":[0.00019527055,0.0011534618,0.002215274,0.00010640296,0.00330663,0.00032167486,0.039733253,0.04595586,0.016608369,0.03443814,0.04262247,0.81334317],"study_design_scores_gemma":[0.0010836322,0.000083808096,0.0005711978,0.000002168519,0.00019412264,0.0000085879765,0.0028765327,0.96883976,0.00015274962,0.003291126,0.022701921,0.00019439717],"about_ca_topic_score_codex":0.00006747912,"about_ca_topic_score_gemma":0.000039372793,"teacher_disagreement_score":0.9228839,"about_ca_system_score_codex":0.000104425126,"about_ca_system_score_gemma":0.00010444084,"threshold_uncertainty_score":0.99929583},"labels":[],"label_agreement":null},{"id":"W4296288620","doi":"10.1016/j.media.2022.102611","title":"Anticipation for surgical workflow through instrument interaction and recognized Signals","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Computer science; Anticipation (artificial intelligence); Feature (linguistics); Workflow; Artificial intelligence; Task (project management); Segmentation; Noise (video); Inference; Laptop; Surgical instrument; Machine learning; Human–computer interaction; Computer vision; Pattern recognition (psychology)","score_opus":0.055835172749610903,"score_gpt":0.3775551914670036,"score_spread":0.3217200187173927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296288620","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":[0.95969254,0.00013412557,0.029574579,0.0061752796,0.00014381157,0.0003630861,0.000013987369,0.00008127584,0.0038212948],"genre_scores_gemma":[0.99624944,0.000048453996,0.0018251763,0.0010609466,0.00012097876,0.00009177783,0.0003383006,0.000010118503,0.0002547905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842685,0.0001376986,0.00036657354,0.00027872756,0.0006104203,0.00017970143],"domain_scores_gemma":[0.9989715,0.00055731524,0.00008999977,0.00011444515,0.00007788917,0.00018885444],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007606027,0.00009756516,0.0003930295,0.00017363737,0.00019180446,0.000027442327,0.000045429377,0.00005413911,0.013789878],"category_scores_gemma":[0.00048295595,0.000081621656,0.00025500826,0.000788738,0.00006068874,0.00010189473,0.000058292637,0.00022492728,0.000006673574],"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":[0.0033374934,0.001156353,0.03993121,0.0000881994,0.0041704746,0.0005518253,0.0014446267,0.00074105425,0.0002142718,0.00036103182,0.0008775387,0.9471259],"study_design_scores_gemma":[0.029500777,0.0008647505,0.0144948,0.00008825217,0.007013158,0.0001433022,0.002223621,0.7196424,0.00063938793,0.0012499262,0.22364102,0.00049858337],"about_ca_topic_score_codex":0.000042738877,"about_ca_topic_score_gemma":0.000007796884,"teacher_disagreement_score":0.9466273,"about_ca_system_score_codex":0.000056146022,"about_ca_system_score_gemma":0.00003839419,"threshold_uncertainty_score":0.9871116},"labels":[],"label_agreement":null},{"id":"W4302774145","doi":"10.1016/j.media.2022.102649","title":"Predicting the evolution trajectory of population-driven connectional brain templates using recurrent multigraph neural networks","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research","keywords":"Multigraph; Computer science; Population; Artificial intelligence; Neuroimaging; Normalization (sociology); Graph; Machine learning; Neuroscience; Biology; Theoretical computer science; Medicine","score_opus":0.028425723417708527,"score_gpt":0.2876609425353886,"score_spread":0.25923521911768005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302774145","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":[0.97131795,0.0002147325,0.021951659,0.0055361465,0.0005884503,0.00020730367,0.00005986786,0.000077234676,0.000046669473],"genre_scores_gemma":[0.99853206,0.0000055291052,0.00011606369,0.0010316232,0.00020085392,0.000046423265,0.000033691136,0.000012579603,0.000021185117],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964756,0.0009561453,0.00046592075,0.0004989032,0.0013304796,0.00027298954],"domain_scores_gemma":[0.9913575,0.007926349,0.00028603442,0.0002535526,0.00008717702,0.00008937751],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010357155,0.00015722537,0.000326993,0.00037965682,0.0011190858,0.000026959824,0.00032016495,0.00004883418,0.00063629256],"category_scores_gemma":[0.012572553,0.0001264717,0.00038811643,0.0025633858,0.00033209787,0.00017654058,0.00026958768,0.00052709866,8.8061256e-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":[0.000105083396,0.00027191784,0.32523504,0.00001706411,0.0005943206,0.000024728066,0.0006304694,0.66217345,0.007786539,0.00029910525,0.0012712899,0.0015910028],"study_design_scores_gemma":[0.00023876449,0.000065755594,0.075022504,0.0000064033916,0.0003223416,0.000024361221,0.0006706961,0.9232874,0.000091902475,0.00010208602,0.00005485728,0.00011295998],"about_ca_topic_score_codex":0.0016106393,"about_ca_topic_score_gemma":0.00054147816,"teacher_disagreement_score":0.2611139,"about_ca_system_score_codex":0.00021842762,"about_ca_system_score_gemma":0.00005550842,"threshold_uncertainty_score":0.99574494},"labels":[],"label_agreement":null},{"id":"W4308448228","doi":"10.1016/j.media.2022.102670","title":"Segmentation with mixed supervision: Confidence maximization helps knowledge distillation","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Distillation; Maximization; Artificial intelligence; Segmentation; Machine learning; Mathematics; Mathematical optimization; Chemistry; Chromatography","score_opus":0.008958241496845029,"score_gpt":0.2593132697323961,"score_spread":0.25035502823555106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308448228","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":[0.015336315,0.0001302202,0.9818976,0.0016019472,0.00022517933,0.00012372725,0.000004012265,0.00014902747,0.00053199806],"genre_scores_gemma":[0.98094124,0.000031948286,0.018256178,0.00022777653,0.00007754772,0.00009001894,0.00009237469,0.000009882645,0.00027304568],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975041,0.00031707386,0.00029300692,0.00048083364,0.0012159462,0.00018904172],"domain_scores_gemma":[0.9989586,0.0001284777,0.0001360615,0.00045524279,0.00017863959,0.00014299763],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00070347014,0.00012273614,0.00020706777,0.00034792078,0.00040063867,0.00012827652,0.0005595926,0.00003989204,0.001656116],"category_scores_gemma":[0.00010590068,0.000109643384,0.000097535274,0.0035974253,0.00007560121,0.0005776998,0.00029839962,0.00020043127,0.000034069268],"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":[0.00018797704,0.00083810376,0.027621737,0.00011943213,0.0020471876,0.00033780455,0.0077723972,0.054022368,0.004372633,0.006447685,0.008667822,0.88756484],"study_design_scores_gemma":[0.00044314674,0.00015504012,0.0073619173,0.000008478581,0.00027422016,0.000026531621,0.00029773611,0.987621,0.0016938602,0.0003683492,0.0015480301,0.00020169896],"about_ca_topic_score_codex":0.00012993824,"about_ca_topic_score_gemma":0.00021123301,"teacher_disagreement_score":0.9656049,"about_ca_system_score_codex":0.0002410326,"about_ca_system_score_gemma":0.00014445369,"threshold_uncertainty_score":0.9992565},"labels":[],"label_agreement":null},{"id":"W4308459649","doi":"10.1016/j.media.2022.102681","title":"From sMRI to task-fMRI: A unified geometric deep learning framework for cross-modal brain anatomo-functional mapping","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Science Foundation of Beijing Municipality; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Context (archaeology); Artificial intelligence; Deep learning; Graph; Pattern recognition (psychology); Machine learning; Theoretical computer science; Biology","score_opus":0.031196875085315573,"score_gpt":0.3144274947720919,"score_spread":0.2832306196867763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308459649","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":[0.22243175,0.00009299513,0.7351083,0.04090319,0.0005612694,0.00028471826,0.00012932943,0.00019546458,0.00029295188],"genre_scores_gemma":[0.97124916,0.000008069305,0.005664922,0.020373112,0.0006710479,0.0004634893,0.00013392336,0.000043798667,0.0013924753],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99458414,0.000558562,0.0005358803,0.0013473919,0.0023249476,0.0006490691],"domain_scores_gemma":[0.97341055,0.025345046,0.00020240601,0.00046093256,0.00017947784,0.00040160632],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017482183,0.0002934665,0.00062061386,0.0016521576,0.001562316,0.00020513801,0.0006410555,0.000131546,0.008546567],"category_scores_gemma":[0.129821,0.0003044457,0.0005942583,0.009897556,0.00024112538,0.00023305131,0.00086222833,0.0010709525,0.00013717946],"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":[0.0032247936,0.0039151683,0.18604526,0.00023494558,0.012342485,0.0022487477,0.01098643,0.31269452,0.09895599,0.010331151,0.23702401,0.12199651],"study_design_scores_gemma":[0.004268758,0.001046152,0.13250878,0.00005220854,0.0017793423,0.00005827393,0.006006425,0.52307385,0.0061503365,0.0331821,0.28944713,0.002426656],"about_ca_topic_score_codex":0.0002458054,"about_ca_topic_score_gemma":0.000039015038,"teacher_disagreement_score":0.7488174,"about_ca_system_score_codex":0.0003159601,"about_ca_system_score_gemma":0.00012211938,"threshold_uncertainty_score":0.99994075},"labels":[],"label_agreement":null},{"id":"W4308889883","doi":"10.1016/j.media.2022.102693","title":"SSD-KD: A self-supervised diverse knowledge distillation method for lightweight skin lesion classification using dermoscopic images","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":125,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Coastal Health; BC Research (Canada); Vancouver Coastal Health Research Institute; Spinal Cord Injury BC; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Benchmark (surveying); Artificial intelligence; Machine learning; Convolutional neural network; Container (type theory); Feature (linguistics); Pattern recognition (psychology); Engineering","score_opus":0.037007236712825714,"score_gpt":0.35365210019532106,"score_spread":0.3166448634824953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308889883","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":[0.098586544,0.00025999598,0.89542234,0.0024457164,0.0002997186,0.0008952257,0.000033447122,0.00024088981,0.0018161399],"genre_scores_gemma":[0.8969354,0.00008279636,0.09835255,0.0005903424,0.00038698647,0.00022120964,0.00048767525,0.000046825626,0.002896227],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975966,0.00032244276,0.00047800542,0.000536094,0.00078420056,0.00028265684],"domain_scores_gemma":[0.99875784,0.00020622586,0.00016644617,0.000406857,0.00018707295,0.00027557925],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000915671,0.00019743298,0.00050643476,0.0006765487,0.00052890886,0.000046971996,0.00016464107,0.000090197434,0.0033763929],"category_scores_gemma":[0.00029274408,0.00017732246,0.00044979344,0.0015079703,0.000049583796,0.000090355265,0.00019144511,0.00023945169,0.000026137226],"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":[0.0016708629,0.006202364,0.015466031,0.001652849,0.014815913,0.0011727166,0.0062601147,0.0006718465,0.16600518,0.0010413103,0.038700018,0.7463408],"study_design_scores_gemma":[0.001884745,0.000208621,0.0047774604,0.000021611595,0.0076051312,0.00007790145,0.001403263,0.946542,0.002282391,0.000061937404,0.034883287,0.00025160346],"about_ca_topic_score_codex":0.00012988695,"about_ca_topic_score_gemma":0.000059451853,"teacher_disagreement_score":0.9458702,"about_ca_system_score_codex":0.0004193575,"about_ca_system_score_gemma":0.00013162488,"threshold_uncertainty_score":0.99753463},"labels":[],"label_agreement":null},{"id":"W4309630525","doi":"10.1016/j.media.2022.102684","title":"Guidelines and evaluation of clinical explainable AI in medical image analysis","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":168,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"BC Cancer Foundation","keywords":"Guideline; Computer science; Data mining; Artificial intelligence; Medical physics; Medicine; Pathology","score_opus":0.10646275466905696,"score_gpt":0.4673112791791384,"score_spread":0.3608485245100814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309630525","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":[0.32091933,0.00075789355,0.6552469,0.021261988,0.00021841637,0.00028375073,0.000008958584,0.00008436309,0.0012183613],"genre_scores_gemma":[0.9821557,0.00023055113,0.014419653,0.0026942976,0.00012619405,0.000121504716,0.00005066841,0.000013844238,0.00018763467],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98763376,0.0023496628,0.002491142,0.0010451744,0.005939686,0.0005405658],"domain_scores_gemma":[0.9955252,0.0010238172,0.00046351046,0.0011550032,0.0012601754,0.0005723198],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031864963,0.0002342665,0.0012267776,0.0017993469,0.00024163596,0.00012553169,0.0018501924,0.00018305506,0.007003912],"category_scores_gemma":[0.015116978,0.00021769105,0.0006793704,0.011442973,0.0004437199,0.0007372114,0.00146413,0.000756394,0.000025284053],"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":[0.00013743344,0.003131842,0.18903507,0.00009712,0.009828517,0.002493722,0.003499475,0.020918047,0.00060258195,0.0074073644,0.01603569,0.7468131],"study_design_scores_gemma":[0.00041919044,0.00008315849,0.008704822,0.000010543923,0.0022000936,0.000008409175,0.000725102,0.9841737,0.0003265788,0.0021868076,0.000944874,0.00021667585],"about_ca_topic_score_codex":0.0026045202,"about_ca_topic_score_gemma":0.0022368187,"teacher_disagreement_score":0.9632557,"about_ca_system_score_codex":0.00013195447,"about_ca_system_score_gemma":0.00088047364,"threshold_uncertainty_score":0.9968988},"labels":[],"label_agreement":null},{"id":"W4309763239","doi":"10.1016/j.media.2022.102690","title":"Symmetry-based regularization in deep breast cancer screening","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Regional Development Fund; Fundação para a Ciência e a Tecnologia; Canadian Mennonite University; Nvidia","keywords":"Regularization (linguistics); Computer science; Artificial intelligence; Machine learning; Breast cancer; Generalization; Artificial neural network; Theoretical computer science; Mathematics; Medicine; Cancer","score_opus":0.006943077669812815,"score_gpt":0.2585088927304301,"score_spread":0.25156581506061726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309763239","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":[0.0025523535,0.00011454287,0.98894453,0.007890587,0.00013119893,0.000059906586,0.0000066719413,0.000096383985,0.00020383773],"genre_scores_gemma":[0.9705975,0.00001298667,0.02675932,0.0021786105,0.00009972266,0.00013668221,0.000028155637,0.0000122205165,0.00017476626],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99754155,0.00027054123,0.000282898,0.00044297762,0.00121459,0.00024742502],"domain_scores_gemma":[0.99917364,0.000080651174,0.00010927075,0.00043676794,0.00007000206,0.00012968056],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00089704484,0.000100794714,0.00022001339,0.0007445584,0.00019746872,0.00007591946,0.00075433584,0.000048733204,0.0020704502],"category_scores_gemma":[0.00008858701,0.00010466231,0.00014447005,0.0066941413,0.00005243006,0.000284707,0.0003081738,0.0003295595,0.000005416482],"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":[0.000042871856,0.00025859018,0.06514946,0.000025874037,0.00057544763,0.00031003612,0.00046166262,0.11204834,0.00043767708,0.0010072497,0.0009136977,0.8187691],"study_design_scores_gemma":[0.00031033735,0.000015362586,0.016920509,0.0000070855376,0.00010869631,0.000007013395,0.000034917288,0.9815536,0.00023305761,0.0002736894,0.0004141483,0.000121583114],"about_ca_topic_score_codex":0.00095610425,"about_ca_topic_score_gemma":0.0005205259,"teacher_disagreement_score":0.9680452,"about_ca_system_score_codex":0.00030414193,"about_ca_system_score_gemma":0.00014999836,"threshold_uncertainty_score":0.9988418},"labels":[],"label_agreement":null},{"id":"W4309764145","doi":"10.1016/j.media.2022.102698","title":"Orthogonal latent space learning with feature weighting and graph learning for multimodal Alzheimer’s disease diagnosis","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":62,"is_retracted":false,"has_abstract":false,"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; Department of Science and Technology of Sichuan Province; National Institute on Aging; National Center for Advancing Translational Sciences; Ministry of Science and Technology of the People's Republic of China","keywords":"Discriminative model; Artificial intelligence; Computer science; Feature vector; Feature learning; Weighting; Graph; Pattern recognition (psychology); Machine learning; Probabilistic latent semantic analysis; Theoretical computer science","score_opus":0.011779166621783393,"score_gpt":0.3006232963432875,"score_spread":0.2888441297215041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309764145","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":[0.9741207,0.0018093396,0.011964252,0.01104222,0.000023947157,0.00059051026,0.000018367598,0.00009142996,0.00033923675],"genre_scores_gemma":[0.99486274,0.00024630636,0.0016817248,0.00046250393,0.00010336024,0.0005783799,0.00046287887,0.000031583637,0.0015705123],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969355,0.00029076842,0.00021503799,0.00055233843,0.0015089366,0.00049741013],"domain_scores_gemma":[0.99841076,0.00038299797,0.00010307044,0.00014509482,0.00019837361,0.000759684],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009761374,0.00020457513,0.00044477338,0.0004585198,0.00075114914,0.00006857752,0.000111431335,0.00004965518,0.0027800489],"category_scores_gemma":[0.00063848525,0.00015673805,0.0003342551,0.0011459817,0.00019546167,0.00009813807,0.00022751672,0.0009511562,0.0000046211703],"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":[0.00060778734,0.00032056213,0.9705536,0.00005551873,0.0028020386,0.0007895917,0.00016287854,0.00022343604,0.000087370674,0.000019005236,0.00043258717,0.023945626],"study_design_scores_gemma":[0.004193033,0.0013045961,0.86887205,0.000081109625,0.013821932,0.00004242514,0.0013529004,0.098437354,0.00017605249,0.00002608193,0.011329972,0.00036247153],"about_ca_topic_score_codex":0.000061564955,"about_ca_topic_score_gemma":0.000022650673,"teacher_disagreement_score":0.10168153,"about_ca_system_score_codex":0.000038980314,"about_ca_system_score_gemma":0.00015839064,"threshold_uncertainty_score":0.9981316},"labels":[],"label_agreement":null},{"id":"W4309915768","doi":"10.1016/j.media.2022.102699","title":"Mitosis domain generalization in histopathology images — The MIDOG challenge","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Amazon Web Services; Siemens Healthineers; Nvidia","keywords":"Artificial intelligence; Computer science; Grading (engineering); Limiting; Generalization; Pattern recognition (psychology); Set (abstract data type); Domain (mathematical analysis); Machine learning; Mathematics; Biology","score_opus":0.007711893702026811,"score_gpt":0.2507850560881752,"score_spread":0.24307316238614837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309915768","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":[0.018573213,0.0009481893,0.9437399,0.035113946,0.00037084497,0.000104196886,0.0000035619403,0.00009253272,0.0010536093],"genre_scores_gemma":[0.98440343,0.00027963615,0.011514169,0.0029573068,0.00018495932,0.00027054732,0.000017576733,0.000013420955,0.00035898198],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973788,0.0007587958,0.00031432265,0.0004478654,0.0008464811,0.00025373217],"domain_scores_gemma":[0.99901366,0.00012335757,0.00011137479,0.0006314246,0.000042487212,0.00007772178],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014348128,0.000107905966,0.00023259669,0.00042414875,0.0002842215,0.00005011583,0.0011616687,0.000052306605,0.0009837124],"category_scores_gemma":[0.00013147184,0.00008670972,0.00016741369,0.002839566,0.0001311105,0.00019587477,0.0005876417,0.00034809692,0.000015959105],"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":[0.00010482003,0.0022048727,0.045214698,0.000098496756,0.001591746,0.0044005895,0.030503992,0.022015592,0.018851278,0.02045388,0.0808661,0.7736939],"study_design_scores_gemma":[0.0015578754,0.00036185302,0.049040437,0.000011974692,0.00065705925,0.00015765523,0.00109554,0.84223366,0.0017964508,0.015528003,0.08666648,0.00089299167],"about_ca_topic_score_codex":0.00039815734,"about_ca_topic_score_gemma":0.0004807097,"teacher_disagreement_score":0.9658302,"about_ca_system_score_codex":0.0002766319,"about_ca_system_score_gemma":0.00007293571,"threshold_uncertainty_score":0.99992955},"labels":[],"label_agreement":null},{"id":"W4318773574","doi":"10.1016/j.media.2023.102761","title":"Generative Sampling in Bundle Tractography using Autoencoders (GESTA)","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Compute Canada; McDonnell Center for Systems Neuroscience; Réseau en Bio-Imagerie du Quebec; National Institutes of Health; Université de Sherbrooke","keywords":"Tractography; Streamlines, streaklines, and pathlines; Artificial intelligence; Human Connectome Project; White matter; Pattern recognition (psychology); Diffusion MRI; Computer science; Mathematics; Computer vision; Physics; Neuroscience; Psychology; Magnetic resonance imaging","score_opus":0.1638148958616718,"score_gpt":0.45533188993030915,"score_spread":0.29151699406863735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318773574","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":[0.27437463,0.000045884935,0.7200361,0.0047413968,0.000014689048,0.0001538242,0.000007797874,0.00031657406,0.00030912846],"genre_scores_gemma":[0.7738529,0.00033329122,0.22375514,0.0015417152,0.000111748595,0.000063770545,0.00016127588,0.000035101526,0.00014505853],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998549,0.00003987836,0.00031526585,0.00036245,0.00044424378,0.00028915238],"domain_scores_gemma":[0.999232,0.000120489276,0.00006171454,0.000317756,0.00006079028,0.00020723796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033526638,0.00012481805,0.00036400833,0.00089243054,0.00008674375,0.000021016165,0.00011892671,0.0000759025,0.00026466514],"category_scores_gemma":[0.00031273346,0.00011136678,0.000251769,0.0050740964,0.0001539211,0.000086832944,0.000054888293,0.0003286306,0.000018701385],"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":[0.00014465666,0.0029895043,0.7714041,0.00028048037,0.0031704134,0.0028923815,0.002461497,0.02501825,0.128787,0.0017230863,0.006877275,0.054251388],"study_design_scores_gemma":[0.00064617995,0.00006274988,0.0713459,0.000087236855,0.0011718757,0.000028333705,0.00035053023,0.9196947,0.0020563428,0.0017439938,0.0025354915,0.00027661255],"about_ca_topic_score_codex":0.00017410044,"about_ca_topic_score_gemma":0.00007545807,"teacher_disagreement_score":0.8946765,"about_ca_system_score_codex":0.000045906963,"about_ca_system_score_gemma":0.000067873116,"threshold_uncertainty_score":0.45414057},"labels":[],"label_agreement":null},{"id":"W4328098743","doi":"10.1016/j.media.2023.102795","title":"An ultrasound-exclusive non-invasive computational diagnostic framework for personalized cardiology of aortic valve stenosis","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Stenosis; Medicine; Cardiology; Internal medicine; Aortic valve; Aortic valve stenosis; Radiology; Heart valve; Ultrasound","score_opus":0.013441990357171592,"score_gpt":0.3731156302263428,"score_spread":0.3596736398691712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4328098743","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":[0.8546301,0.00024073356,0.14316626,0.0006741045,0.000108279775,0.00053088245,0.00048938557,0.00007202348,0.000088194414],"genre_scores_gemma":[0.99169856,0.00033139958,0.0036362675,0.0005619888,0.00025767833,0.00020803671,0.0032196285,0.000029124067,0.000057307276],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978033,0.0001252771,0.0004464509,0.00047080204,0.00078925845,0.00036494122],"domain_scores_gemma":[0.9930196,0.005566822,0.00015003831,0.00037198336,0.00036152615,0.0005300274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026484294,0.00021256824,0.0011029614,0.00040485832,0.00011234351,0.000018179162,0.00013780888,0.00018251926,0.0006107717],"category_scores_gemma":[0.005842382,0.0001772798,0.0036162806,0.0014239773,0.00033648068,0.000060493334,0.000043289983,0.00014861776,0.00005199726],"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":[0.00023753976,0.00054004655,0.9524396,0.00022579986,0.04054523,0.0002647273,0.00065308064,0.0012597103,0.00020170292,0.00029719807,0.0012612373,0.0020741194],"study_design_scores_gemma":[0.0023001763,0.00039292919,0.9487964,0.000107698324,0.035065528,0.000009684668,0.0011387811,0.009156664,0.00008655499,0.0027367244,0.000017939761,0.0001909311],"about_ca_topic_score_codex":0.00007125677,"about_ca_topic_score_gemma":0.000002675077,"teacher_disagreement_score":0.13952999,"about_ca_system_score_codex":0.00005729016,"about_ca_system_score_gemma":0.0002610521,"threshold_uncertainty_score":0.7229261},"labels":[],"label_agreement":null},{"id":"W4362560246","doi":"10.1016/j.media.2023.102808","title":"MyoPS: A benchmark of myocardial pathology segmentation combining three-sequence cardiac magnetic resonance images","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Segmentation; Benchmark (surveying); Computer science; Preprocessor; Artificial intelligence; Cardiac magnetic resonance; Myocardial infarction; Magnetic resonance imaging; Image segmentation; Medical physics; Medicine; Pattern recognition (psychology); Radiology; Cardiology","score_opus":0.01768570160716264,"score_gpt":0.3377404210989619,"score_spread":0.32005471949179926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362560246","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":[0.3902226,0.004357787,0.58918786,0.007918507,0.00017392897,0.0012803078,0.00031902478,0.000824794,0.00571517],"genre_scores_gemma":[0.910261,0.0036395616,0.08323734,0.0006795963,0.00020551645,0.0004019201,0.0008636574,0.000040932086,0.00067047635],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982156,0.00007051188,0.00044807565,0.00037406804,0.0006111701,0.00028056416],"domain_scores_gemma":[0.9988751,0.00018610335,0.00012161269,0.0004665864,0.00016845956,0.00018214525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005603704,0.0001421759,0.00060110283,0.0003209968,0.00007776146,0.000009640756,0.00015782594,0.00012152477,0.0004872872],"category_scores_gemma":[0.00035876618,0.0001265184,0.00034735663,0.002336571,0.00038623516,0.000077747805,0.000099532685,0.0002275335,0.000043897413],"study_design_candidate":"observational","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":[0.00014234368,0.00041698696,0.15815125,0.00017979473,0.00070800877,0.0011473985,0.0006624634,0.0001179239,0.2405967,0.0012706183,0.0154415695,0.58116496],"study_design_scores_gemma":[0.004096988,0.0015041841,0.82510376,0.0005089769,0.01235875,0.00010902315,0.0018074464,0.062479574,0.06748956,0.009829028,0.013454313,0.0012584028],"about_ca_topic_score_codex":0.000093878894,"about_ca_topic_score_gemma":0.00001109814,"teacher_disagreement_score":0.6669525,"about_ca_system_score_codex":0.000039931638,"about_ca_system_score_gemma":0.000082341474,"threshold_uncertainty_score":0.5335453},"labels":[],"label_agreement":null},{"id":"W4366831358","doi":"10.1016/j.media.2023.102826","title":"Calibrating segmentation networks with margin-based label smoothing","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; École de Technologie Supérieure","funders":"H2020 Marie Skłodowska-Curie Actions; Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Softmax function; Discriminative model; Computer science; Margin (machine learning); Segmentation; Artificial intelligence; Machine learning; Logit; Artificial neural network; Mathematical optimization; Pattern recognition (psychology); Mathematics","score_opus":0.013038805535436885,"score_gpt":0.28536634430265007,"score_spread":0.27232753876721316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366831358","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":[0.0057939244,0.000025227471,0.9880047,0.0053118127,0.00003042571,0.00010797793,0.000001238848,0.00052949414,0.00019523934],"genre_scores_gemma":[0.5337835,0.000033365544,0.46099284,0.0042782477,0.00019821707,0.00016678633,0.0001924596,0.000031183245,0.00032338646],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981435,0.00009493187,0.0002676683,0.00045059496,0.00069756765,0.00034572004],"domain_scores_gemma":[0.9986781,0.00041341133,0.00011902106,0.0005043957,0.00006845237,0.00021663764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040425485,0.00013361636,0.00021683521,0.00026160103,0.00023458649,0.00015075954,0.00061547506,0.00005916994,0.00009430244],"category_scores_gemma":[0.000096226904,0.00010766898,0.000082596736,0.0067726835,0.00008562837,0.00039730468,0.00014707382,0.0002280925,0.000053372343],"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":[0.000013902697,0.00015164862,0.010896955,0.000026839753,0.00064967206,0.00047457614,0.00032930958,0.7381834,0.0014477277,0.0024621554,0.004717118,0.24064672],"study_design_scores_gemma":[0.0002559761,0.000017180471,0.0010929721,0.000012973488,0.00011511443,0.0000015526282,0.00002095949,0.99769896,0.0003478779,0.0001407217,0.00016436247,0.00013136864],"about_ca_topic_score_codex":0.000029157625,"about_ca_topic_score_gemma":0.000066825305,"teacher_disagreement_score":0.52798957,"about_ca_system_score_codex":0.000033034175,"about_ca_system_score_gemma":0.000059387396,"threshold_uncertainty_score":0.43906134},"labels":[],"label_agreement":null},{"id":"W4367853078","doi":"10.1016/j.media.2023.103073","title":"Automatic motion artefact detection in brain T1-weighted magnetic resonance images from a clinical data warehouse using synthetic data","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":false,"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; Pfizer; Novartis Pharmaceuticals Corporation; Agence Nationale de la Recherche; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Computer science; Artificial intelligence; Computer vision; Motion (physics); Ghosting; Magnetic resonance imaging; Medical imaging; Exploit; Pattern recognition (psychology)","score_opus":0.09274629936307639,"score_gpt":0.43112744423604804,"score_spread":0.33838114487297166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367853078","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":[0.28099006,0.00065863424,0.7115869,0.0049342695,0.000053477965,0.0005105935,0.0004951821,0.00072122447,0.000049649076],"genre_scores_gemma":[0.90826887,0.0013792599,0.084493436,0.000683767,0.00029575953,0.0000605671,0.004604391,0.00006646017,0.0001475192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659425,0.000275181,0.0009436977,0.0011049822,0.0007181657,0.00036373088],"domain_scores_gemma":[0.99546516,0.0008372295,0.00017397336,0.0031611503,0.00007874355,0.00028375172],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001841961,0.00020836639,0.0007040196,0.0005220788,0.00010469723,0.000043726992,0.0008211957,0.00021484,0.0010599103],"category_scores_gemma":[0.004221646,0.00018231563,0.00014691224,0.0032688712,0.00025862726,0.00038846774,0.00069153064,0.00053893536,0.00011718533],"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":[0.000038903803,0.0004729991,0.0070667374,0.000038440357,0.0001544911,0.00046077417,0.000049916627,0.00002495033,0.0036359027,0.0000026193454,0.0037113966,0.9843429],"study_design_scores_gemma":[0.0006121226,0.00004996399,0.06297758,0.00014970233,0.0012827144,0.000014803703,0.000057958187,0.9319756,0.00049041084,0.00032801984,0.0018948707,0.00016622998],"about_ca_topic_score_codex":0.0009074796,"about_ca_topic_score_gemma":0.0006211552,"teacher_disagreement_score":0.98417664,"about_ca_system_score_codex":0.00007827879,"about_ca_system_score_gemma":0.000110097484,"threshold_uncertainty_score":0.99985325},"labels":[],"label_agreement":null},{"id":"W4376866854","doi":"10.1016/j.media.2023.102841","title":"BolT: Fused window transformers for fMRI time series analysis","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":106,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Landmark; Artificial intelligence; Transformer; Cascade; LEAPS; Pattern recognition (psychology); Time series; Regularization (linguistics); Encoder; Window (computing); Machine learning","score_opus":0.020018020582874607,"score_gpt":0.2881298682667515,"score_spread":0.2681118476838769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376866854","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":[0.37785015,0.00014315841,0.323174,0.2842005,0.00065504585,0.0014382753,0.0010385195,0.0023200659,0.00918027],"genre_scores_gemma":[0.98126453,0.00017418829,0.00055246113,0.0060996297,0.00027010098,0.0002730613,0.00023444262,0.000047134876,0.011084421],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99664164,0.00019504764,0.00043223123,0.0008655725,0.0012820952,0.0005834086],"domain_scores_gemma":[0.99373525,0.0054352456,0.00009601178,0.00032238924,0.00012381215,0.0002872702],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010847158,0.00025453168,0.0008178599,0.0013908175,0.00043495043,0.0000942974,0.0003538586,0.00012715116,0.002525076],"category_scores_gemma":[0.016776834,0.00021850402,0.0013039421,0.012102743,0.0004771496,0.00038457368,0.00009134817,0.00020691773,0.00058472226],"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":[0.0017555533,0.0016889051,0.04389308,0.00048881286,0.084848665,0.0016648072,0.0066671283,0.0054488145,0.479964,0.0012746903,0.30205107,0.0702545],"study_design_scores_gemma":[0.004704171,0.00077133137,0.0731343,0.00003810566,0.05652536,0.00002340206,0.002269133,0.6177942,0.1666431,0.002734095,0.072850436,0.0025123635],"about_ca_topic_score_codex":0.000060072758,"about_ca_topic_score_gemma":0.00033024614,"teacher_disagreement_score":0.6123454,"about_ca_system_score_codex":0.00005726379,"about_ca_system_score_gemma":0.00008322431,"threshold_uncertainty_score":0.99838674},"labels":[],"label_agreement":null},{"id":"W4377695098","doi":"10.1016/j.media.2023.102846","title":"Diffusion models in medical imaging: A comprehensive survey","year":2023,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":652,"is_retracted":false,"has_abstract":false,"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; Artificial intelligence; Probabilistic logic; Diffusion map; Noise (video); Noise reduction; Machine learning; Diffusion; Medical imaging; Data science; Image (mathematics); Nonlinear dimensionality reduction","score_opus":0.08373872611063253,"score_gpt":0.387150647904169,"score_spread":0.30341192179353643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377695098","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002155632,0.5724848,0.4262063,0.00035761824,0.00034608634,0.00021586641,0.00001631005,0.00023453822,0.00013631117],"genre_scores_gemma":[0.000027557382,0.9979584,0.0008449522,0.0003807022,0.00020444134,0.00013329496,0.0002245095,0.000057586283,0.0001685632],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9905379,0.0019104423,0.0016019455,0.0015217524,0.003715965,0.0007120034],"domain_scores_gemma":[0.9948472,0.0021744568,0.00047162955,0.001518241,0.0002511939,0.0007373176],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032972132,0.00059133174,0.0032286686,0.0022030526,0.0001080169,0.00022146177,0.003472345,0.0006632756,0.00049406284],"category_scores_gemma":[0.0016599966,0.00047635593,0.0012362617,0.011881974,0.00028662666,0.00045455093,0.0019425671,0.0016315434,0.00040282562],"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":[0.0000014801801,0.00007394154,0.00004538329,0.0011650841,0.0006461053,0.0011850991,0.000055228018,0.000015268402,3.1384605e-8,0.000036838468,0.0018795185,0.994896],"study_design_scores_gemma":[0.00030744937,0.000014582548,0.00021769055,0.004313667,0.0013768175,0.00006437815,0.000009971498,0.8360782,1.16102036e-7,0.0004814734,0.15648751,0.00064814306],"about_ca_topic_score_codex":0.003242386,"about_ca_topic_score_gemma":0.00295645,"teacher_disagreement_score":0.99424785,"about_ca_system_score_codex":0.00043257236,"about_ca_system_score_gemma":0.0012051977,"threshold_uncertainty_score":0.9997688},"labels":[],"label_agreement":null},{"id":"W4380148842","doi":"10.1016/j.media.2023.102863","title":"A survey on deep learning for skin lesion segmentation","year":2023,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":178,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Google; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Canadian Institutes of Health Research; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação para a Ciência e a Tecnologia; Fundação de Amparo à Pesquisa do Estado de São Paulo; BC Cancer Foundation; National Science Foundation","keywords":"Artificial intelligence; Segmentation; Deep learning; Skin lesion; Computer vision; Computer science; Pattern recognition (psychology); Lesion; Medicine; Dermatology; Pathology","score_opus":0.07588093704665991,"score_gpt":0.4023016891922042,"score_spread":0.32642075214554434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380148842","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025863004,0.8924015,0.10235639,0.0002819599,0.0004744297,0.0026917118,0.000052078907,0.00047873915,0.0012373014],"genre_scores_gemma":[0.000020879099,0.9823959,0.00026129262,0.00019141994,0.00028794358,0.00023442478,0.004267846,0.00007287734,0.012267445],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99709845,0.0004093984,0.00071839214,0.0005734476,0.0009110398,0.00028926186],"domain_scores_gemma":[0.9980539,0.0009040405,0.00029991037,0.0003364848,0.000114521165,0.00029113836],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015633561,0.00031474794,0.0018515495,0.001170234,0.00012798724,0.00005264101,0.00014250875,0.00030073003,0.0011295317],"category_scores_gemma":[0.002429773,0.0002371592,0.0014113055,0.002056305,0.0000458552,0.000022425713,0.000074493604,0.00050607976,0.0006686436],"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":[0.000030428377,0.00008773104,0.000011651706,0.0042114165,0.003520106,0.00021950326,0.000019680292,0.000005768927,3.7521878e-7,0.0000019040793,0.0027283125,0.9891631],"study_design_scores_gemma":[0.0005551257,0.00032281686,0.00019532675,0.0026680452,0.024211934,0.00002253292,0.00005724268,0.006376795,0.0000021616638,0.000002955745,0.9652937,0.0002913806],"about_ca_topic_score_codex":0.00020141283,"about_ca_topic_score_gemma":0.0005870186,"teacher_disagreement_score":0.98887175,"about_ca_system_score_codex":0.00021302444,"about_ca_system_score_gemma":0.00009863966,"threshold_uncertainty_score":0.9997836},"labels":[],"label_agreement":null},{"id":"W4380183557","doi":"10.1016/j.media.2023.102865","title":"Towards clinical applicability and computational efficiency in automatic cranial implant design: An overview of the AutoImplant 2021 cranial implant design challenge","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Traumatic Brain Injury and Neurovascular Disturbances","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Sunnybrook Health Science Centre; University of Toronto; Sunnybrook Hospital","funders":"Bundesministerium für Digitalisierung und Wirtschaftsstandort; Steirische Wirtschaftsförderungsgesellschaft; Bundesministerium für Verkehr, Innovation und Technologie; Austrian Science Fund","keywords":"Computer science; Implant; Skull; Medical physics; Artificial intelligence; Medicine; Surgery","score_opus":0.10278458159155032,"score_gpt":0.3880010164852415,"score_spread":0.2852164348936912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380183557","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":[0.8996352,0.00063725235,0.094241776,0.0039164326,0.00023434684,0.0010831677,0.000087944485,0.00010772551,0.000056130884],"genre_scores_gemma":[0.9944466,0.0006546659,0.004151177,0.00045616642,0.00012771791,0.000060547383,0.00007622024,0.000017882214,0.000009050517],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949011,0.0013956722,0.0013086639,0.0006598868,0.0013302917,0.00040439202],"domain_scores_gemma":[0.99706846,0.0016596774,0.00023240293,0.00059943716,0.00009380062,0.00034622478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005349478,0.0002612514,0.0012222286,0.00026208992,0.00013257451,0.000031262563,0.00038563673,0.00021287643,0.0005112749],"category_scores_gemma":[0.0013223588,0.00016690104,0.00051448826,0.0017280797,0.00059843605,0.000091739246,0.00015117621,0.000470444,0.000018130155],"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":[0.0019617684,0.010252199,0.057030685,0.003463317,0.007158067,0.0044877753,0.0061018076,0.0034802598,0.0012785894,0.0012314082,0.005373943,0.8981802],"study_design_scores_gemma":[0.002175228,0.00047150056,0.58366215,0.00017603367,0.0014860833,0.00024560202,0.0001259443,0.41011533,0.00007287237,0.0012062653,0.00006614276,0.00019682493],"about_ca_topic_score_codex":0.00015872957,"about_ca_topic_score_gemma":0.00009095288,"teacher_disagreement_score":0.8979834,"about_ca_system_score_codex":0.000037317914,"about_ca_system_score_gemma":0.00040681462,"threshold_uncertainty_score":0.68060267},"labels":[],"label_agreement":null},{"id":"W4381951399","doi":"10.1016/j.media.2023.102871","title":"Automatic labeling of Parkinson’s Disease gait videos with weak supervision","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"British Columbia Centre of Excellence for Women's Health; Vancouver Coastal Health; University of British Columbia Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gait; Artificial intelligence; Computer science; Physical medicine and rehabilitation; Machine learning; Rating scale; A priori and a posteriori; Parkinson's disease; Estimator; Pattern recognition (psychology); Disease; Medicine; Mathematics; Statistics; Pathology","score_opus":0.011610055587825843,"score_gpt":0.26245370000849594,"score_spread":0.2508436444206701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381951399","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":[0.6241143,0.00006380194,0.37147197,0.0032297191,0.00006369289,0.000098726574,0.000007491878,0.0004320223,0.0005182972],"genre_scores_gemma":[0.99148375,0.00008721272,0.007720033,0.0003521667,0.00005143298,0.000016527387,0.00005251937,0.000007859194,0.000228518],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825495,0.00008501066,0.00029066484,0.00029604824,0.00087455276,0.00019877302],"domain_scores_gemma":[0.9990144,0.00012790546,0.00008345089,0.0003795084,0.00011146166,0.00028329],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046759297,0.000098077784,0.00024833216,0.0004812102,0.00009250401,0.00007634482,0.00039735815,0.00003876559,0.001364493],"category_scores_gemma":[0.00022453492,0.000072615956,0.00016163799,0.0025855377,0.00006187928,0.0003559024,0.00012028803,0.0001056687,0.00030031076],"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":[0.00003680648,0.0007425191,0.037340324,0.0004530715,0.0024403124,0.0013669364,0.0016206559,0.0006003303,0.0028094563,0.0008063987,0.012282548,0.93950063],"study_design_scores_gemma":[0.00029808257,0.000034474957,0.028040064,0.00009595411,0.00045047293,0.0000020189643,0.00007119304,0.968727,0.000571097,0.00042269932,0.0011517731,0.000135158],"about_ca_topic_score_codex":0.00004776405,"about_ca_topic_score_gemma":0.000034905566,"teacher_disagreement_score":0.96812665,"about_ca_system_score_codex":0.000014092433,"about_ca_system_score_gemma":0.00007360264,"threshold_uncertainty_score":0.9995484},"labels":[],"label_agreement":null},{"id":"W4384701644","doi":"10.1016/j.media.2023.102878","title":"Robotic ultrasound imaging: State-of-the-art and future perspectives","year":2023,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Soft Robotics and Applications","field":"Engineering","cited_by":153,"is_retracted":false,"has_abstract":false,"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; Process (computing); Artificial intelligence; Teleoperation; Modalities; Human–computer interaction; Data science; Robot","score_opus":0.01278421280006974,"score_gpt":0.2920633726128263,"score_spread":0.27927915981275653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384701644","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003275702,0.98501617,0.013976932,0.00024176422,0.00010567817,0.00017741787,0.00003310854,0.00012691476,0.0003187157],"genre_scores_gemma":[0.000030678868,0.9986921,0.0004681041,0.000010896949,0.00021149678,0.000043882435,0.00006840134,0.00005402021,0.00042045012],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985976,0.000050197203,0.00045203522,0.00029161153,0.00039756802,0.00021096952],"domain_scores_gemma":[0.99887043,0.00034358003,0.00009698477,0.00047832052,0.00005473696,0.00015592869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021031265,0.00025786128,0.0011067434,0.0002640366,0.00006428286,0.000054652723,0.00036564897,0.00010734872,0.0002135355],"category_scores_gemma":[0.00018037972,0.00017581573,0.00066051737,0.0021352787,0.00020334953,0.000038415033,0.00008072978,0.0004298219,0.00006520824],"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":[3.0376924e-7,0.000067112625,0.00008839423,0.007815962,0.0074633593,0.000033876535,0.00047266117,0.0008320681,0.0000025985387,0.00027424385,0.012083085,0.9708663],"study_design_scores_gemma":[0.000087651366,0.0000036388735,0.00023754814,0.001191057,0.015232924,0.000026337177,0.00024832648,0.013111989,0.0000013747865,0.00021508324,0.96916395,0.00048008843],"about_ca_topic_score_codex":0.000011337974,"about_ca_topic_score_gemma":0.00002829723,"teacher_disagreement_score":0.97038627,"about_ca_system_score_codex":0.000048109043,"about_ca_system_score_gemma":0.00005974743,"threshold_uncertainty_score":0.7169557},"labels":[],"label_agreement":null},{"id":"W4386565864","doi":"10.1016/j.media.2023.102942","title":"Deep learning, data ramping, and uncertainty estimation for detecting artifacts in large, imbalanced databases of MRI images","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University; NeuroRx Research (Canada); Montreal Neurological Institute and Hospital","funders":"","keywords":"Computer science; Artificial intelligence; Artifact (error); Transfer of learning; Neuroimaging; Deep learning; Inference; Machine learning; Data quality; Pattern recognition (psychology); Data mining","score_opus":0.022595957263734208,"score_gpt":0.3643586328800441,"score_spread":0.3417626756163099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386565864","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":[0.33880672,0.00036557735,0.6569595,0.0032468284,0.000055353386,0.00028546154,0.000037608013,0.00013085802,0.00011212517],"genre_scores_gemma":[0.96996635,0.0006318201,0.026286343,0.00031232368,0.00010117884,0.000024226125,0.0024985455,0.000028335444,0.00015089709],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977266,0.00013515593,0.0005781537,0.0005374179,0.00059878716,0.00042383958],"domain_scores_gemma":[0.9979655,0.00093190063,0.00020863947,0.00051913154,0.00010427543,0.00027054347],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031359084,0.00016406024,0.0006826277,0.00063024426,0.000114854636,0.000034321925,0.00023554293,0.00008020211,0.0001922633],"category_scores_gemma":[0.022057282,0.00013926743,0.00012067514,0.0015252101,0.00019705365,0.00020755072,0.00029766062,0.0005147582,0.0000068508293],"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":[0.00028566804,0.00040927756,0.49836504,0.0013702059,0.0019013117,0.0004793132,0.0010718119,0.019645598,0.007568093,0.000067512105,0.0028059292,0.46603024],"study_design_scores_gemma":[0.0014927008,0.000052902986,0.044185653,0.00017628253,0.00080788386,0.000010778714,0.00036053386,0.9513507,0.0003400102,0.000050025672,0.0010498767,0.00012264577],"about_ca_topic_score_codex":0.00041534097,"about_ca_topic_score_gemma":0.00023847309,"teacher_disagreement_score":0.9317051,"about_ca_system_score_codex":0.00002908933,"about_ca_system_score_gemma":0.000078916426,"threshold_uncertainty_score":0.98618037},"labels":[],"label_agreement":null},{"id":"W4386725051","doi":"10.1016/j.media.2023.102958","title":"Active learning for medical image segmentation with stochastic batches","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Hôpital Notre-Dame","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Fonds de recherche du Québec – Nature et technologies; Réseau en Bio-Imagerie du Quebec","keywords":"Computer science; Segmentation; Artificial intelligence; Set (abstract data type); Machine learning; Sampling (signal processing); Baseline (sea); Metric (unit); Active learning (machine learning); Image segmentation; Code (set theory); Data mining; Pattern recognition (psychology); Computer vision","score_opus":0.007167990610211484,"score_gpt":0.29577817084283925,"score_spread":0.28861018023262774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386725051","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":[0.013106182,0.000013626232,0.9789292,0.0071472246,0.00007067867,0.00011443951,0.000002467675,0.00039850734,0.00021763674],"genre_scores_gemma":[0.8671776,0.00004395747,0.1264052,0.0012288974,0.00070535654,0.00026975182,0.00044528348,0.000060015347,0.0036639182],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970281,0.00019541201,0.0002821901,0.00053761265,0.0015422663,0.00041440627],"domain_scores_gemma":[0.9981986,0.00085532217,0.00012297207,0.0002830655,0.0001442855,0.00039573538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013111539,0.0001732857,0.0003616384,0.00042180027,0.00026977167,0.00017212497,0.00066999666,0.0001011045,0.0005681377],"category_scores_gemma":[0.0022815624,0.00012869858,0.00020192625,0.0025773179,0.00015576593,0.00034541733,0.00020242059,0.00047596486,0.00014335144],"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":[0.000078119,0.00025772644,0.0017837826,0.000104323604,0.0028483882,0.00077107374,0.0048923944,0.013935048,0.0007641993,0.00046724666,0.0039040225,0.9701937],"study_design_scores_gemma":[0.00063014036,0.00012326059,0.0015943778,0.000027867896,0.00027497462,0.000009402933,0.00035082444,0.9961903,0.00023518018,0.00015803146,0.00022994183,0.00017570074],"about_ca_topic_score_codex":0.00012666159,"about_ca_topic_score_gemma":0.000050427858,"teacher_disagreement_score":0.9822552,"about_ca_system_score_codex":0.00003474146,"about_ca_system_score_gemma":0.00016959649,"threshold_uncertainty_score":0.6220709},"labels":[],"label_agreement":null},{"id":"W4386826462","doi":"10.1016/j.media.2023.102972","title":"Automatic Head and Neck Tumor segmentation and outcome prediction relying on FDG-PET/CT images: Findings from the second edition of the HECKTOR challenge","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Hasler Stiftung; Siemens Healthineers; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Artificial intelligence; Positron emission tomography; Segmentation; Computer science; Population; Percentile; Medicine; Leverage (statistics); Medical physics; Machine learning; Radiology; Mathematics; Statistics","score_opus":0.014450067475993525,"score_gpt":0.3054342986791619,"score_spread":0.29098423120316835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386826462","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":[0.98330635,0.00015163026,0.00050244335,0.015251214,0.00019218575,0.00025872327,0.00007101985,0.00009006145,0.00017635197],"genre_scores_gemma":[0.99641496,0.00020278081,0.000524074,0.0020523625,0.00024153963,0.000028406539,0.00018048726,0.000022460452,0.00033289965],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99783194,0.00017897718,0.00053211075,0.00035032898,0.00087976275,0.00022685903],"domain_scores_gemma":[0.9986135,0.00064979907,0.00017081278,0.00032297906,0.0000463456,0.0001965803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011245644,0.00017090564,0.00045917375,0.00020590518,0.00024730497,0.000054636614,0.00014328209,0.000027743596,0.000887304],"category_scores_gemma":[0.0017886908,0.00009844298,0.00015930408,0.00073135586,0.00035010843,0.0001272308,0.000106916385,0.000575673,0.000014179328],"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":[0.000108649845,0.00037553394,0.90590554,0.0009482419,0.0028159777,0.0010246874,0.0028547116,0.000039479128,0.010188844,0.00007794072,0.023665315,0.051995058],"study_design_scores_gemma":[0.0016615323,0.0001354047,0.7449335,0.00037811618,0.0015368541,0.000096157135,0.00094239647,0.24868129,0.00053658977,0.00017360957,0.0007984774,0.00012606132],"about_ca_topic_score_codex":0.0002694645,"about_ca_topic_score_gemma":0.00004381959,"teacher_disagreement_score":0.24864182,"about_ca_system_score_codex":0.000048760114,"about_ca_system_score_gemma":0.00004119544,"threshold_uncertainty_score":0.9715357},"labels":[],"label_agreement":null},{"id":"W4386826466","doi":"10.1016/j.media.2023.102938","title":"GAMMA challenge: Glaucoma grAding from Multi-Modality imAges","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":102,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"DiagnoCure (Canada); École de Technologie Supérieure","funders":"","keywords":"Glaucoma; Optical coherence tomography; Fundus photography; Grading (engineering); Medicine; Optometry; Fundus (uterus); Ophthalmology; Optic disc; Modality (human–computer interaction); Modalities; Artificial intelligence; Blindness; Computer science; Retinal; Fluorescein angiography","score_opus":0.02778191829118971,"score_gpt":0.3494678826587598,"score_spread":0.3216859643675701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386826466","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":[0.8263194,0.0013802656,0.07419523,0.09313556,0.00017755889,0.0002291154,0.0000938736,0.0012072539,0.0032617722],"genre_scores_gemma":[0.9888029,0.0009949997,0.003881134,0.000831745,0.0004895465,0.000026198024,0.00074835063,0.000044904107,0.0041801934],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961387,0.0002295853,0.0006792493,0.0008193525,0.0015066315,0.0006264611],"domain_scores_gemma":[0.9976083,0.00035449042,0.000151456,0.0008585713,0.00022275836,0.0008044177],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012034335,0.00032218162,0.0011575372,0.0009301575,0.00018971723,0.00009885024,0.00035540416,0.00018831858,0.0031878368],"category_scores_gemma":[0.0019127119,0.00025839938,0.0011716408,0.0033211482,0.00034612208,0.00016967683,0.00018467921,0.0005835181,0.0010837507],"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":[0.00015483555,0.0014834198,0.79217136,0.00025488553,0.019694787,0.011534566,0.0013686961,0.000018563715,0.017065525,0.000040351795,0.027067449,0.12914558],"study_design_scores_gemma":[0.0024404395,0.0000848342,0.5145689,0.00019799078,0.01566839,0.000026765954,0.00087271875,0.45810452,0.0030061102,0.0004875109,0.0039038765,0.0006379038],"about_ca_topic_score_codex":0.0027837027,"about_ca_topic_score_gemma":0.00015350177,"teacher_disagreement_score":0.45808595,"about_ca_system_score_codex":0.00007196612,"about_ca_system_score_gemma":0.00009079603,"threshold_uncertainty_score":0.9999868},"labels":[],"label_agreement":null},{"id":"W4386954264","doi":"10.1016/j.media.2023.102965","title":"Backdoor attack and defense in federated generative adversarial network-based medical image synthesis","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":37,"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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Public Safety Canada; Nvidia","keywords":"Backdoor; Computer science; Generator (circuit theory); Adversarial system; Computer security; Artificial intelligence; Deep learning; Machine learning; Data mining","score_opus":0.014849875500631417,"score_gpt":0.29797350023547114,"score_spread":0.2831236247348397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386954264","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":[0.032347172,0.00007146578,0.9517155,0.014313403,0.00029399712,0.00016384678,0.000005532406,0.00039195755,0.0006970971],"genre_scores_gemma":[0.88157207,0.00013745477,0.11357093,0.003208907,0.00097100105,0.00010074877,0.00011561326,0.00006293357,0.00026032407],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940291,0.0012853828,0.000752758,0.0010531106,0.0020206203,0.0008590415],"domain_scores_gemma":[0.99590766,0.0024528762,0.00018766818,0.00058287336,0.00016195832,0.00070695527],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003825838,0.0003631371,0.0008846822,0.0007209329,0.00036534393,0.00035051204,0.0011192632,0.00037688174,0.0018201845],"category_scores_gemma":[0.009788945,0.00032138533,0.0002966459,0.006131783,0.00046173178,0.00051900477,0.0008346629,0.0008953212,0.00021293187],"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":[0.0007389259,0.0014034797,0.12639593,0.0003560408,0.008232916,0.047257062,0.00429338,0.42493236,0.0010350778,0.0052916105,0.087523274,0.29253992],"study_design_scores_gemma":[0.0009953589,0.000028525392,0.004582943,0.000059427155,0.00027526394,0.000008475403,0.000057362002,0.99305,0.00010467862,0.00016834817,0.00032716632,0.00034249935],"about_ca_topic_score_codex":0.00036043333,"about_ca_topic_score_gemma":0.0009231426,"teacher_disagreement_score":0.8492249,"about_ca_system_score_codex":0.0001033226,"about_ca_system_score_gemma":0.0005827521,"threshold_uncertainty_score":0.9999238},"labels":[],"label_agreement":null},{"id":"W4386965001","doi":"10.1016/j.media.2023.102974","title":"Learning joint surface reconstruction and segmentation, from brain images to cortical surface parcellation","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Bell (Canada)","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Segmentation; Voxel; Computer science; Hausdorff distance; Surface reconstruction; Computer vision; Pattern recognition (psychology); Surface (topology); Computation; Mathematics; Algorithm; Geometry","score_opus":0.014258781679771555,"score_gpt":0.29365168947209586,"score_spread":0.2793929077923243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386965001","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":[0.28085107,0.000021761638,0.7107212,0.0075654127,0.00007408969,0.0001359972,0.000004141948,0.0005343642,0.00009197303],"genre_scores_gemma":[0.5026198,0.00022164601,0.49401727,0.0019806738,0.00010127004,0.00001779181,0.00016397158,0.0000240596,0.00085354026],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966074,0.0005740635,0.0006009105,0.0007069284,0.001161359,0.00034930627],"domain_scores_gemma":[0.997914,0.0008091058,0.00014789117,0.00037359004,0.00017775326,0.0005776646],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017778769,0.00018680925,0.0003883212,0.00032789598,0.00023409627,0.0003154734,0.00035532087,0.00011910532,0.0010485916],"category_scores_gemma":[0.0024264115,0.00017707815,0.00012247951,0.0028434715,0.00019591552,0.00061153836,0.0003383255,0.00037029493,0.00028312526],"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":[0.000019179894,0.000103900136,0.04787663,0.00003733017,0.00084515224,0.00025048165,0.0034454886,0.0021987013,0.48718852,0.000078959216,0.027947463,0.4300082],"study_design_scores_gemma":[0.0006594749,0.00014846363,0.06746883,0.000068003836,0.00034123083,0.000013177055,0.0010168187,0.75045496,0.17831416,0.0008023921,0.00017726824,0.00053523254],"about_ca_topic_score_codex":0.000378055,"about_ca_topic_score_gemma":0.000032726894,"teacher_disagreement_score":0.74825627,"about_ca_system_score_codex":0.00006586213,"about_ca_system_score_gemma":0.00006513544,"threshold_uncertainty_score":0.9998646},"labels":[],"label_agreement":null},{"id":"W4387004670","doi":"10.1016/j.media.2023.102980","title":"Spatiotemporal knowledge teacher–student reinforcement learning to detect liver tumors without contrast agents","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reinforcement learning; Computer science; Contrast (vision); Set (abstract data type); Workflow; Pixel; Artificial intelligence","score_opus":0.02162950575016027,"score_gpt":0.33032660725676816,"score_spread":0.3086971015066079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387004670","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":[0.054100133,0.000049048755,0.94245845,0.001318928,0.00005852372,0.00027546476,6.462861e-7,0.0004811856,0.0012576422],"genre_scores_gemma":[0.986189,0.000055478966,0.009097922,0.0004918672,0.00013799898,0.00013837678,0.000030894156,0.000017344535,0.003841132],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99728566,0.00016823149,0.0004712777,0.00062787445,0.0009417626,0.0005051986],"domain_scores_gemma":[0.99842393,0.00015760116,0.00013398165,0.0006206823,0.00011979386,0.0005440339],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00072049495,0.00020540207,0.00038887456,0.00045257004,0.00026733006,0.0001261912,0.0011413888,0.00006694937,0.00045447642],"category_scores_gemma":[0.0003666228,0.00018394346,0.00021738833,0.004420246,0.00008066737,0.00025345618,0.00077363534,0.0003556196,0.0018797719],"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":[0.000044759297,0.00050780596,0.0662777,0.00007203316,0.0028887053,0.0012548831,0.01167245,0.15486236,0.0024189346,0.0012617509,0.038488384,0.72025025],"study_design_scores_gemma":[0.00029004307,0.000068179026,0.031799734,0.000023998073,0.00017241642,0.0000033423944,0.0000748776,0.9595617,0.00051345176,0.00005374299,0.007170155,0.0002683314],"about_ca_topic_score_codex":0.00007765975,"about_ca_topic_score_gemma":0.0001535799,"teacher_disagreement_score":0.9333605,"about_ca_system_score_codex":0.00010924483,"about_ca_system_score_gemma":0.00006505198,"threshold_uncertainty_score":0.9988974},"labels":[],"label_agreement":null},{"id":"W4387521217","doi":"10.1016/j.media.2023.102985","title":"SurgT challenge: Benchmark of soft-tissue trackers for robotic surgery","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Deep learning; Benchmark (surveying); BitTorrent tracker; Segmentation; Ground truth; Benchmarking; Bounding overwatch; Computer vision; Metric (unit); Machine learning; Eye tracking","score_opus":0.04643213624207263,"score_gpt":0.35713379866465866,"score_spread":0.310701662422586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387521217","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":[0.7199214,0.001710075,0.21329637,0.047237173,0.0009216307,0.0014063773,0.00005639088,0.0010210649,0.014429505],"genre_scores_gemma":[0.9977513,0.00013744055,0.00039282636,0.00031069914,0.00016464017,0.000023620734,0.00043157916,0.0000193027,0.0007686223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978959,0.00006992645,0.0005878543,0.00030051777,0.0008051726,0.00034064922],"domain_scores_gemma":[0.99648774,0.0025584768,0.00011296318,0.00025793986,0.00017943366,0.00040344475],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014115747,0.00013584895,0.0008825236,0.0005959976,0.00005804964,0.0000108764325,0.000088654466,0.00015071391,0.005342745],"category_scores_gemma":[0.0034509366,0.00011027216,0.0007036413,0.0023092444,0.00015863308,0.000059811562,0.000027588567,0.00015368016,0.00006532174],"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":[0.0006471563,0.0012799803,0.09775896,0.0012108008,0.010808812,0.0019487732,0.0013576855,0.0035065708,0.00041868325,0.0004606059,0.01775488,0.8628471],"study_design_scores_gemma":[0.0073711528,0.00034582938,0.16639489,0.00039445705,0.011902334,0.000020497066,0.0015996936,0.76443624,0.0012205319,0.0007220583,0.04480059,0.00079172436],"about_ca_topic_score_codex":0.00004245398,"about_ca_topic_score_gemma":0.000030732455,"teacher_disagreement_score":0.86205536,"about_ca_system_score_codex":0.000019769966,"about_ca_system_score_gemma":0.000111496665,"threshold_uncertainty_score":0.9955665},"labels":[],"label_agreement":null},{"id":"W4387978272","doi":"10.1016/j.media.2023.103015","title":"Do we really need dice? The hidden region-size biases of segmentation losses","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; École de Technologie Supérieure","funders":"H2020 Marie Skłodowska-Curie Actions; Fonds de recherche du Québec – Nature et technologies; HORIZON EUROPE Marie Sklodowska-Curie Actions; Natural Sciences and Engineering Research Council of Canada","keywords":"Dice; Ground truth; Segmentation; Computer science; Artificial intelligence; Perspective (graphical); Matching (statistics); Upper and lower bounds; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.030278542921383895,"score_gpt":0.3202295275761869,"score_spread":0.289950984654803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387978272","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":[0.020825407,0.0002989491,0.93059194,0.0474908,0.00005865275,0.00018113918,0.000004643392,0.00026131983,0.00028713833],"genre_scores_gemma":[0.9699131,0.0035876685,0.023979815,0.0011736365,0.00019811402,0.00012048054,0.000038167465,0.000016943768,0.0009720399],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811494,0.00013687357,0.00037059063,0.0003494514,0.00080416165,0.00022399773],"domain_scores_gemma":[0.99680406,0.0019253405,0.00019533816,0.000818621,0.00012362821,0.0001329876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037977876,0.00011121173,0.00024099984,0.00020391119,0.00015479591,0.00007250532,0.0010966236,0.000048492286,0.000113647],"category_scores_gemma":[0.00091572833,0.00007466985,0.00019081956,0.0063144835,0.00035392668,0.00028354488,0.00030302134,0.00013624164,0.00007581594],"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":[0.000024905727,0.00031803478,0.007869409,0.000059961865,0.0017030021,0.00037434432,0.0028429038,0.003599856,0.0079175355,0.014005537,0.09711391,0.8641706],"study_design_scores_gemma":[0.0014353873,0.00018146554,0.04162998,0.00025060074,0.0023556165,0.000056352674,0.0021065162,0.8764092,0.013282383,0.051254116,0.010063688,0.00097473536],"about_ca_topic_score_codex":0.00005088501,"about_ca_topic_score_gemma":0.000036450645,"teacher_disagreement_score":0.94908774,"about_ca_system_score_codex":0.00002024289,"about_ca_system_score_gemma":0.000052303807,"threshold_uncertainty_score":0.30449483},"labels":[],"label_agreement":null},{"id":"W4388024378","doi":"10.1016/j.media.2023.103011","title":"Anatomically-aware uncertainty for semi-supervised image segmentation","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec; Compute Canada","keywords":"Segmentation; Artificial intelligence; Computer science; Inference; Pixel; Representation (politics); Scale-space segmentation; Image segmentation; Pattern recognition (psychology); Segmentation-based object categorization; Machine learning","score_opus":0.011542703190844253,"score_gpt":0.33554928277027957,"score_spread":0.3240065795794353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388024378","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":[0.44183797,0.00011161703,0.50933313,0.045595992,0.00026423158,0.00079260627,0.00006959581,0.0007324626,0.0012623874],"genre_scores_gemma":[0.94727635,0.00057820824,0.029224666,0.011790905,0.001166611,0.00031397978,0.0055624186,0.00014324796,0.003943585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99699575,0.00011513048,0.00060094596,0.00058525807,0.001122855,0.0005800419],"domain_scores_gemma":[0.9979424,0.000500164,0.000114241215,0.00043721442,0.00027030948,0.0007356853],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015073187,0.00024509872,0.0007557395,0.00068244693,0.00019012848,0.000081958395,0.00026586422,0.00018291087,0.0028843314],"category_scores_gemma":[0.0030587343,0.00019902285,0.0006833204,0.0024531595,0.00027552983,0.00013722613,0.000100813464,0.0005024083,0.0001945672],"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":[0.0009319692,0.0012302928,0.07069523,0.0016837951,0.013838865,0.0032549913,0.002153828,0.0015070584,0.119757034,0.00031794878,0.3167388,0.46789017],"study_design_scores_gemma":[0.0028025769,0.00009199893,0.0052927705,0.000070158516,0.0026711067,0.000019636562,0.00047492038,0.9818188,0.0009778073,0.00021252515,0.005321827,0.0002458532],"about_ca_topic_score_codex":0.0001756013,"about_ca_topic_score_gemma":0.000022925706,"teacher_disagreement_score":0.98031175,"about_ca_system_score_codex":0.000116538984,"about_ca_system_score_gemma":0.00019329165,"threshold_uncertainty_score":0.99802715},"labels":[],"label_agreement":null},{"id":"W4388806341","doi":"10.1016/j.media.2023.103041","title":"WarpDrive: Improving spatial normalization using manual refinements","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Toronto Rehabilitation Institute; McGill University; Douglas Mental Health University Institute; Krembil Foundation; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; National Institute of Neurological Disorders and Stroke; IXICO; H. Lundbeck A/S; Eisai; Deutsche Forschungsgemeinschaft; Servier; EU Joint Programme – Neurodegenerative Disease Research; Northern California Institute for Research and Education; National Institute of Mental Health; BioClinica; Biogen; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Computer science; Artificial intelligence; Spatial normalization; Normalization (sociology); Inference; Modalities; Pattern recognition (psychology); Neuroimaging; Process (computing); Computer vision; Machine learning; Neuroscience; Psychology","score_opus":0.05912185879799546,"score_gpt":0.42084703398665946,"score_spread":0.361725175188664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388806341","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":[0.15981258,0.000011809039,0.8369536,0.0021413965,0.000029297069,0.00015743164,0.0000098978635,0.00044158867,0.00044239915],"genre_scores_gemma":[0.96511394,0.000102564954,0.031841356,0.0011910493,0.00026007445,0.0000409015,0.0005360024,0.000035272395,0.00087883533],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985041,0.000027893757,0.00030891405,0.00031677782,0.0005925278,0.00024980708],"domain_scores_gemma":[0.9992216,0.00003541832,0.000090960646,0.00034680232,0.000106528176,0.00019868127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025394466,0.00011414914,0.00026598052,0.0004154349,0.00013057467,0.000020358777,0.00011954332,0.00006718849,0.00068507995],"category_scores_gemma":[0.00034204795,0.00010130724,0.0001670641,0.0020567814,0.00008777613,0.00009295217,0.00012955358,0.00017779485,0.000066088985],"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":[0.00016683285,0.0014853472,0.27938572,0.00047964827,0.002645926,0.002504259,0.00052271265,0.0010762938,0.21795227,0.0007254654,0.016604112,0.47645146],"study_design_scores_gemma":[0.0006417712,0.00006686795,0.034661055,0.000042792333,0.0021275508,0.000028167768,0.000052561638,0.95153576,0.0062180054,0.00016912654,0.004249609,0.00020671441],"about_ca_topic_score_codex":0.00032761533,"about_ca_topic_score_gemma":0.000024599878,"teacher_disagreement_score":0.9504595,"about_ca_system_score_codex":0.00004748712,"about_ca_system_score_gemma":0.00005275671,"threshold_uncertainty_score":0.7501145},"labels":[],"label_agreement":null},{"id":"W4388818696","doi":"10.1016/j.media.2023.103033","title":"An efficient semi-supervised quality control system trained using physics-based MRI-artefact generators and adversarial training","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"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; Department of Health and Social Care; National Institute for Health and Care Research; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Medical Research Council; Biogen; Engineering and Physical Sciences Research Council; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; University College London Hospitals NHS Foundation Trust; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Artificial intelligence; Computer science; Support vector machine; Process (computing); Set (abstract data type); Machine learning; Quality (philosophy); Feature (linguistics); Class (philosophy); Pattern recognition (psychology)","score_opus":0.018009744842974067,"score_gpt":0.3180659777950156,"score_spread":0.30005623295204154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388818696","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":[0.58246493,0.000050184677,0.4170251,0.0000876832,0.000022108268,0.00013097074,0.000028031176,0.00013027884,0.00006071936],"genre_scores_gemma":[0.995762,0.000016442093,0.0026613933,0.00038113943,0.00042791798,0.00002710061,0.00066920626,0.000037477523,0.000017320655],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99685746,0.00061478006,0.0006017638,0.00082020165,0.0006347258,0.00047103633],"domain_scores_gemma":[0.99839747,0.0000856961,0.00017960668,0.00071921694,0.00018651714,0.00043147747],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019380057,0.00030828363,0.0007324685,0.00028897135,0.00020911831,0.00010700307,0.00031976387,0.00026347188,0.00008872339],"category_scores_gemma":[0.0003599813,0.00028458275,0.0005547426,0.001301334,0.00025311057,0.000013406424,0.00007234899,0.00017796148,0.000007175765],"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":[0.000100801735,0.0001562063,0.0021123507,0.0000636856,0.001851175,0.00008815573,0.0002449401,0.014933882,0.975435,0.000011825166,0.00021904727,0.004782895],"study_design_scores_gemma":[0.0014324985,0.00008587725,0.00068733544,0.000018123043,0.0018233687,0.0000029369376,0.0006868025,0.92800176,0.06681285,0.0000036853603,0.00009733191,0.0003474065],"about_ca_topic_score_codex":0.0002486794,"about_ca_topic_score_gemma":0.00008123567,"teacher_disagreement_score":0.9130679,"about_ca_system_score_codex":0.00004982628,"about_ca_system_score_gemma":0.00019520511,"threshold_uncertainty_score":0.99996066},"labels":[],"label_agreement":null},{"id":"W4388840678","doi":"10.1016/j.media.2023.103030","title":"Combiner and HyperCombiner networks: Rules to combine multimodality MR images for prostate cancer localisation","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Knight Cancer Institute, Oregon Health and Science University; Wellcome Trust; University of Manchester; University College London; University of Cambridge; Cancer Research UK","keywords":"Computer science; Modality (human–computer interaction); Artificial intelligence; Segmentation; Pattern recognition (psychology); Parametric statistics; Machine learning; Mathematics; Statistics","score_opus":0.01712218110866384,"score_gpt":0.3275623913581904,"score_spread":0.31044021024952656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388840678","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":[0.9126521,0.0015153897,0.019518055,0.06367187,0.00019566547,0.0017049505,0.0003731821,0.0002716826,0.00009711335],"genre_scores_gemma":[0.98723483,0.0034006273,0.0012515585,0.0041162525,0.00019671982,0.0013428912,0.0012331492,0.000044173903,0.0011798029],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979284,0.00006950228,0.00046171984,0.00054928754,0.0005416846,0.00044941716],"domain_scores_gemma":[0.99840456,0.00029691894,0.00008524511,0.0003334422,0.00028037644,0.0005994431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066370075,0.00024202262,0.00074243144,0.0003165261,0.00014647747,0.000063025494,0.00009290523,0.00010604044,0.00037172687],"category_scores_gemma":[0.0004686099,0.00017942998,0.00025205262,0.0012581422,0.00019554638,0.00013535107,0.000103147446,0.00014298131,0.000035789748],"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":[0.00086527393,0.0015904747,0.65849644,0.00058213685,0.007425148,0.000428921,0.0009317712,0.0016285854,0.0017113511,0.00019259291,0.12690505,0.19924226],"study_design_scores_gemma":[0.010368201,0.0008482216,0.60350347,0.0003608384,0.008526674,0.000008924336,0.0003628679,0.36277917,0.0032282097,0.0005245431,0.008848568,0.0006403431],"about_ca_topic_score_codex":0.0012545347,"about_ca_topic_score_gemma":0.0002013844,"teacher_disagreement_score":0.3611506,"about_ca_system_score_codex":0.00012132762,"about_ca_system_score_gemma":0.0000856617,"threshold_uncertainty_score":0.7316942},"labels":[],"label_agreement":null},{"id":"W4389990429","doi":"10.1016/j.media.2023.103066","title":"Placental vessel segmentation and registration in fetoscopy: Literature review and MICCAI FetReg2021 challenge findings","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Prenatal Screening and Diagnostics","field":"Medicine","cited_by":8,"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 Toronto","funders":"UCLH Biomedical Research Centre; HORIZON EUROPE Framework Programme; Wellcome / EPSRC Centre for Interventional and Surgical Sciences; Nvidia; Wellcome Trust; Royal Academy of Engineering; University College London Hospitals NHS Foundation Trust; Horizon 2020; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research","keywords":"Fetoscopy; Computer science; Artificial intelligence; Computer vision; Segmentation; Context (archaeology); Prenatal diagnosis; Pregnancy","score_opus":0.010902822670717885,"score_gpt":0.3113714892789012,"score_spread":0.3004686666081833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389990429","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":[0.8146275,0.11658833,0.0016671458,0.06464616,0.00006579176,0.0006457333,0.0000703302,0.00017490615,0.0015140626],"genre_scores_gemma":[0.7555889,0.23867056,0.0011506892,0.0020834417,0.00009523766,0.00003445087,0.0017184322,0.000015815836,0.00064247276],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99888164,0.00006013856,0.00025200535,0.0002772622,0.00036628067,0.00016265686],"domain_scores_gemma":[0.99940795,0.00016041075,0.00004707812,0.00013295216,0.000039073817,0.00021256789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004767567,0.000110992776,0.00035828428,0.00027093303,0.00004363615,0.000041247575,0.000039209535,0.00010796184,0.00012774703],"category_scores_gemma":[0.0012757038,0.000092158174,0.00006103686,0.0014052752,0.000078070996,0.00013228464,0.00005043409,0.00023262767,0.000012019396],"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":[0.00046995498,0.001139959,0.62963045,0.01598953,0.0033279385,0.012307475,0.006553625,0.000006728929,0.0056085098,0.00034230103,0.117110655,0.2075129],"study_design_scores_gemma":[0.0076149497,0.00070693175,0.9185392,0.021630619,0.011889311,0.00039323748,0.0016414268,0.031014906,0.0020100272,0.00023649528,0.0033811782,0.0009416913],"about_ca_topic_score_codex":0.000069138,"about_ca_topic_score_gemma":0.0001004875,"teacher_disagreement_score":0.2889088,"about_ca_system_score_codex":0.00002637376,"about_ca_system_score_gemma":0.000027461567,"threshold_uncertainty_score":0.37581015},"labels":[],"label_agreement":null},{"id":"W4390747482","doi":"10.1016/j.media.2024.103085","title":"What matters in reinforcement learning for tractography","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Compute Canada","keywords":"Reinforcement learning; Tractography; Computer science; Codebase; Artificial intelligence; Function (biology); Machine learning; White matter; Software","score_opus":0.033939239268384484,"score_gpt":0.3895429358701114,"score_spread":0.3556036966017269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390747482","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":[0.007500368,0.00054508983,0.94225794,0.048745994,0.000047698264,0.00031315951,0.0000010520341,0.00026535094,0.00032335293],"genre_scores_gemma":[0.9789048,0.0016736048,0.0116818305,0.005794777,0.000099797915,0.00029311437,0.00017192171,0.000028567152,0.0013515917],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990103,0.000013795969,0.00025254872,0.0002688455,0.0002746544,0.00017980696],"domain_scores_gemma":[0.99950635,0.00013438542,0.000024607705,0.00017827225,0.000030086334,0.00012630876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002632383,0.00008843773,0.0002331478,0.00051884144,0.00003457226,0.000070238195,0.00007466255,0.000046497644,0.00044842958],"category_scores_gemma":[0.000105335734,0.00007280447,0.00025114653,0.0013286204,0.00006729,0.00018248516,0.000023268269,0.0002797573,0.0000134443635],"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":[0.000290261,0.0010519616,0.030690018,0.002036776,0.005137765,0.0023621977,0.0022810518,0.0038376334,0.037820973,0.004540199,0.07739695,0.8325542],"study_design_scores_gemma":[0.0008879011,0.00023582061,0.004288794,0.000732485,0.0029507854,0.000038233837,0.00050169555,0.64537424,0.003016005,0.0014841188,0.3401463,0.00034362427],"about_ca_topic_score_codex":0.000020379943,"about_ca_topic_score_gemma":0.0000069349394,"teacher_disagreement_score":0.97140443,"about_ca_system_score_codex":0.000032624237,"about_ca_system_score_gemma":0.000029591336,"threshold_uncertainty_score":0.49099895},"labels":[],"label_agreement":null},{"id":"W4391056022","doi":"10.1016/j.media.2024.103090","title":"Fighting the scanner effect in brain MRI segmentation with a progressive level-of-detail network trained on multi-site data","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":12,"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 Mental Health; Horizon 2020; HORIZON EUROPE Framework Programme; Horizon 2020 Framework Programme; McGill University","keywords":"Computer science; Robustness (evolution); Scanner; Segmentation; Artificial intelligence; Convolutional neural network; Software portability; Population; Data acquisition; Pattern recognition (psychology); Machine learning","score_opus":0.04749079695162298,"score_gpt":0.3614109178070805,"score_spread":0.3139201208554575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391056022","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":[0.0030094336,0.0003093456,0.98866785,0.0072447853,0.00006261337,0.00042783062,0.000022207587,0.00018164658,0.00007430538],"genre_scores_gemma":[0.33347294,0.00006475888,0.6587576,0.005741359,0.0003485674,0.0003364635,0.00064876693,0.000051865747,0.00057766284],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962678,0.0007245323,0.00054734375,0.0007408031,0.0013632899,0.00035623222],"domain_scores_gemma":[0.9970673,0.0015210889,0.00016626478,0.0009956541,0.00007618452,0.0001735402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035728002,0.00021390623,0.0004113823,0.00037693323,0.00009461859,0.00027019082,0.0014868131,0.00008639,0.00030116088],"category_scores_gemma":[0.0010129085,0.00011895214,0.0001259893,0.0038302536,0.00029033588,0.00066555507,0.00039230904,0.00045206875,0.000023428638],"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":[0.00007612119,0.00034354161,0.004941222,0.00028099012,0.0018709479,0.0019972397,0.0041187597,0.0006999655,0.0023636434,0.00021386238,0.032082178,0.95101154],"study_design_scores_gemma":[0.0006695566,0.00021860271,0.0023757021,0.0005049322,0.00037335322,0.000009422305,0.000076843615,0.98814696,0.007249135,0.00006325207,0.00010993231,0.00020232306],"about_ca_topic_score_codex":0.00015547409,"about_ca_topic_score_gemma":0.00034749295,"teacher_disagreement_score":0.98744696,"about_ca_system_score_codex":0.00005759889,"about_ca_system_score_gemma":0.00014946911,"threshold_uncertainty_score":0.48507276},"labels":[],"label_agreement":null},{"id":"W4391264577","doi":"10.1016/j.media.2024.103093","title":"Neural deformation fields for template-based reconstruction of cortical surfaces from MRI","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Segmentation; Polygon mesh; Computer vision; Surface (topology); Flow (mathematics); Surface reconstruction; Pattern recognition (psychology); Mathematics; Geometry; Computer graphics (images)","score_opus":0.03829917376689692,"score_gpt":0.3651151343577,"score_spread":0.3268159605908031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391264577","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":[0.23969628,0.000096090465,0.75391567,0.0058008144,0.00006211022,0.00015737493,0.00004470537,0.00014102412,0.00008590827],"genre_scores_gemma":[0.95280397,0.00004123355,0.04638382,0.0003358134,0.000107146334,0.00003895123,0.00024346658,0.000009134903,0.000036445468],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908936,0.000022071881,0.00033086375,0.00020293797,0.000246812,0.00010794353],"domain_scores_gemma":[0.9992487,0.00030898288,0.00005118637,0.00020057007,0.00008758706,0.000102987986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016657427,0.00007789914,0.00025430633,0.00016385259,0.000042986005,0.000018404766,0.000064758366,0.000082758044,0.00045426155],"category_scores_gemma":[0.0002449645,0.000060903698,0.00023676685,0.00053211657,0.00011746602,0.000096163334,0.000013914209,0.0001868927,0.000005135959],"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":[0.0010861058,0.0013759433,0.10614023,0.0022133484,0.0057183546,0.000280377,0.0006913676,0.003426623,0.13809432,0.0026207713,0.049071,0.6892815],"study_design_scores_gemma":[0.00026097134,0.000074299285,0.003726832,0.00007557591,0.0014533425,0.000010166362,0.000028777386,0.97835624,0.013677565,0.0008422136,0.0014215632,0.00007243157],"about_ca_topic_score_codex":0.000077231474,"about_ca_topic_score_gemma":0.000015763788,"teacher_disagreement_score":0.97492963,"about_ca_system_score_codex":0.000019693074,"about_ca_system_score_gemma":0.000052045536,"threshold_uncertainty_score":0.49738455},"labels":[],"label_agreement":null},{"id":"W4391671707","doi":"10.1016/j.media.2024.103101","title":"Blurred streamlines: A novel representation to reduce redundancy in tractography","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Streamlines, streaklines, and pathlines; Redundancy (engineering); Artificial intelligence; False positive paradox; Computer science; Tractography; Representation (politics); Pattern recognition (psychology); Algorithm; Mathematics; Computer vision; Diffusion MRI","score_opus":0.070228611807333,"score_gpt":0.4499603158126226,"score_spread":0.37973170400528955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391671707","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":[0.19355728,0.0003697577,0.76240057,0.04052943,0.000060858074,0.00053517637,0.000032316097,0.0005779828,0.001936657],"genre_scores_gemma":[0.95332265,0.00018053634,0.044476803,0.0010407923,0.0001545608,0.00016525063,0.00014301421,0.000026166343,0.0004902061],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983719,0.000021957861,0.00039982735,0.0005271797,0.00046994077,0.0002091692],"domain_scores_gemma":[0.99905014,0.00012158592,0.000032681153,0.00044711126,0.000072109455,0.0002763472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022361043,0.00012775224,0.00032894756,0.0009824805,0.00003169226,0.000045289875,0.00013150215,0.00006918364,0.0003359828],"category_scores_gemma":[0.00055646885,0.00010966732,0.00027897512,0.0055526565,0.00007955678,0.000115757415,0.00004407874,0.0003213747,0.000031705775],"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":[0.00029042774,0.003297006,0.045835648,0.0004285366,0.002162549,0.0027973896,0.0018251301,0.00021371472,0.31488904,0.0022403125,0.033906057,0.5921142],"study_design_scores_gemma":[0.0050516794,0.0007516445,0.347748,0.0030028103,0.012292724,0.0005965411,0.0015762413,0.3835024,0.07628771,0.007333722,0.15975738,0.002099153],"about_ca_topic_score_codex":0.00018010559,"about_ca_topic_score_gemma":0.00004594389,"teacher_disagreement_score":0.7597654,"about_ca_system_score_codex":0.000045654422,"about_ca_system_score_gemma":0.0000817579,"threshold_uncertainty_score":0.44721037},"labels":[],"label_agreement":null},{"id":"W4391951835","doi":"10.1016/j.media.2024.103109","title":"LESS: Label-efficient multi-scale learning for cytological whole slide image screening","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Vector Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Compute Canada","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Machine learning; Task (project management); Supervised learning; Artificial neural network","score_opus":0.03090864510067017,"score_gpt":0.3249026520584386,"score_spread":0.29399400695776845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391951835","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":[0.00827045,0.0005772002,0.98585254,0.0039559505,0.00027572337,0.0001550819,0.000006054459,0.00064478995,0.00026218186],"genre_scores_gemma":[0.42845616,0.000043482178,0.5689256,0.000459683,0.00036249592,0.00014023492,0.000031153293,0.00003306092,0.0015481266],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996963,0.0001952975,0.0004576965,0.0009275891,0.00092362124,0.0005327877],"domain_scores_gemma":[0.99845886,0.0005266431,0.00008673879,0.0004619518,0.00016182775,0.00030399565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014842548,0.00022165506,0.00043943003,0.00045877352,0.00030620684,0.0005411681,0.0008778444,0.00017914148,0.00021106323],"category_scores_gemma":[0.0007392883,0.00018336841,0.00044996402,0.0025204944,0.00020770263,0.00038591455,0.0004091261,0.00060594425,0.000115761555],"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":[0.000030846946,0.00037320456,0.0015153119,0.00018018384,0.0014475668,0.00068838696,0.0014093975,0.010594615,0.016744385,0.00039438473,0.0044477377,0.962174],"study_design_scores_gemma":[0.00034889005,0.00007866487,0.00058841245,0.000052072588,0.00035642553,0.00001595169,0.00020682743,0.9892053,0.001961864,0.000067945926,0.006893431,0.00022422103],"about_ca_topic_score_codex":0.00009439413,"about_ca_topic_score_gemma":0.00008293421,"teacher_disagreement_score":0.9786107,"about_ca_system_score_codex":0.00012032126,"about_ca_system_score_gemma":0.00009703815,"threshold_uncertainty_score":0.7477547},"labels":[],"label_agreement":null},{"id":"W4392349077","doi":"10.1016/j.media.2024.103131","title":"Tracking and mapping in medical computer vision: A review","year":2024,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":51,"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; Field (mathematics); Process (computing); Artificial intelligence; Computer vision; Tracking (education); Data science","score_opus":0.021467946330328388,"score_gpt":0.33339687273021956,"score_spread":0.31192892639989117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392349077","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.148944e-7,0.8692326,0.1298556,0.00032757764,0.00014396282,0.00016447162,0.0000047067683,0.00010435022,0.00016621021],"genre_scores_gemma":[0.0000078206485,0.9981743,0.0008274083,0.0003968105,0.00027904048,0.000019793295,0.00021591994,0.00005337832,0.000025540357],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970305,0.00017923392,0.0011162824,0.00044469896,0.00094702386,0.00028224388],"domain_scores_gemma":[0.99905294,0.00020926393,0.00006355035,0.00029257292,0.000034687975,0.00034697534],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011525385,0.0003681901,0.0022889078,0.0007613564,0.000025465495,0.000105731066,0.00026631475,0.00044715495,0.0009876667],"category_scores_gemma":[0.00028147583,0.00027131848,0.0006271666,0.002684684,0.00007920889,0.00006718758,0.000110419904,0.0009015834,0.0000920805],"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":[7.2354005e-8,0.0000123377995,0.0000015953412,0.061384983,0.0007110521,0.0010902433,0.000014655436,0.00008679052,1.5769535e-8,0.000012195941,0.0035480615,0.933138],"study_design_scores_gemma":[0.00005002456,0.0000048971933,0.0000020221325,0.08848895,0.004296832,0.0000537193,0.0000015889384,0.42849013,1.4148391e-8,0.000005484736,0.47837475,0.00023157588],"about_ca_topic_score_codex":0.000012982705,"about_ca_topic_score_gemma":0.00003298321,"teacher_disagreement_score":0.93290645,"about_ca_system_score_codex":0.00007881546,"about_ca_system_score_gemma":0.00009128651,"threshold_uncertainty_score":0.9999739},"labels":[],"label_agreement":null},{"id":"W4392455053","doi":"10.1016/j.media.2024.103134","title":"Optimisation of quantitative brain diffusion-relaxation MRI acquisition protocols with physics-informed machine learning","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada); Université de Sherbrooke","funders":"Engineering and Physical Sciences Research Council; European Commission; Agencia Estatal de Investigación; Ministerio de Ciencia, Innovación y Universidades; Ministerio de Ciencia e Innovación; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Wellcome Trust","keywords":"Diffusion MRI; Protocol (science); Computer science; Artificial intelligence; Relaxation (psychology); Machine learning; Diffusion; Algorithm; Magnetic resonance imaging; Physics; Medicine","score_opus":0.04037254488641366,"score_gpt":0.40363153447511524,"score_spread":0.36325898958870156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392455053","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":[0.020844184,0.000046009423,0.969558,0.0064511094,0.000005530361,0.0022251462,0.000012483188,0.00027008384,0.0005874721],"genre_scores_gemma":[0.8543247,0.00012119757,0.14035091,0.00060224213,0.00010219321,0.0027016338,0.00096976064,0.00004501998,0.0007823676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986051,0.000050071874,0.00033847892,0.00028103808,0.00058979896,0.00013556224],"domain_scores_gemma":[0.99905884,0.000276442,0.00015244911,0.0002280697,0.00017136807,0.000112853304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026201704,0.00012927366,0.00032325048,0.00025106076,0.00007651958,0.000030297155,0.00007720192,0.000059386522,0.0003981941],"category_scores_gemma":[0.0003114541,0.000092837065,0.00016496493,0.0015211819,0.0001583594,0.00020902956,0.00003408288,0.00030118693,0.000013836912],"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":[0.002297287,0.0038434737,0.09944618,0.005070638,0.008277735,0.00077923585,0.008490799,0.009423039,0.34874046,0.041627884,0.011014885,0.46098837],"study_design_scores_gemma":[0.0010149493,0.0007326915,0.008752499,0.00088330527,0.001685109,0.000025472156,0.00018025494,0.9654976,0.015057399,0.0011970657,0.0047352877,0.0002383712],"about_ca_topic_score_codex":0.000045349814,"about_ca_topic_score_gemma":0.000008185161,"teacher_disagreement_score":0.95607454,"about_ca_system_score_codex":0.00005967873,"about_ca_system_score_gemma":0.000116332645,"threshold_uncertainty_score":0.43599463},"labels":[],"label_agreement":null},{"id":"W4392883923","doi":"10.1016/j.media.2024.103143","title":"CellViT: Vision Transformers for precise cell segmentation and classification","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":282,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"Universität Duisburg-Essen","keywords":"Computer science; Segmentation; Artificial intelligence; Convolutional neural network; Deep learning; Encoder; Pattern recognition (psychology); Cluster analysis; Computer vision; Scale-space segmentation; Image segmentation","score_opus":0.010348644571440708,"score_gpt":0.308377914807403,"score_spread":0.2980292702359623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392883923","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":[0.004219302,0.00044049433,0.99128693,0.0029059346,0.00019654655,0.00017239281,0.0000046228192,0.00013025204,0.0006434921],"genre_scores_gemma":[0.9611568,0.00050860125,0.037434228,0.00017884398,0.00010579067,0.00010128451,0.000034512155,0.00001134404,0.00046860133],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987049,0.000047550766,0.00022589853,0.00042594445,0.00045009397,0.0001456155],"domain_scores_gemma":[0.9994453,0.00017918626,0.000036502373,0.00015268355,0.000053634227,0.00013268608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055577216,0.00009068858,0.00013610041,0.00029621198,0.00008800035,0.00024501278,0.00017792336,0.000081232254,0.00010168447],"category_scores_gemma":[0.00003470469,0.0000777243,0.00013976237,0.0011178998,0.000057651592,0.0006418491,0.000027760207,0.00010684496,0.00002382061],"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":[0.000008897473,0.00003670826,0.00005263535,0.00012426877,0.00014561896,0.0000061906567,0.00061119173,0.00001885171,0.02617229,0.00016546847,0.0024085303,0.97024935],"study_design_scores_gemma":[0.0001902091,0.00007324032,0.0004622704,0.000016937487,0.00035798276,0.0000019046281,0.00005877757,0.9754264,0.0189446,0.00044726318,0.00392042,0.000100042875],"about_ca_topic_score_codex":0.000018381916,"about_ca_topic_score_gemma":0.00002923841,"teacher_disagreement_score":0.9754075,"about_ca_system_score_codex":0.00007769169,"about_ca_system_score_gemma":0.000058384772,"threshold_uncertainty_score":0.31695047},"labels":[],"label_agreement":null},{"id":"W4393165986","doi":"10.1016/j.media.2024.103160","title":"Plug-and-Play latent feature editing for orientation-adaptive quantitative susceptibility mapping neural networks","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":8,"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 Calgary; University of Alberta","funders":"Australian Research Council; Canadian Institutes of Health Research; Canadian HIV Trials Network, Canadian Institutes of Health Research; National Natural Science Foundation of China","keywords":"Quantitative susceptibility mapping; Computer science; Orientation (vector space); Artificial intelligence; Pattern recognition (psychology); Adaptability; Artificial neural network; Magnetic resonance imaging; Mathematics","score_opus":0.02620456957795512,"score_gpt":0.3659482357832057,"score_spread":0.33974366620525054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393165986","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":[0.0093799215,0.00073602604,0.98143417,0.007568049,0.00006897028,0.00043770036,0.000035064288,0.00019516177,0.00014495116],"genre_scores_gemma":[0.82991165,0.0001639997,0.1673187,0.0007395693,0.0005086312,0.00023827619,0.00050093466,0.000026513304,0.000591736],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986254,0.000034572884,0.00029638657,0.0004799996,0.00031424442,0.00024941942],"domain_scores_gemma":[0.99887055,0.00044065143,0.00006653874,0.00020234361,0.0001905254,0.00022940658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044771217,0.00015272325,0.00037742767,0.00018430562,0.0001471798,0.00004969704,0.000072057155,0.00012969025,0.00017915673],"category_scores_gemma":[0.0004148346,0.00011801005,0.00028224653,0.0010901523,0.00019160849,0.00013554326,0.00005001672,0.0003843446,0.0000031301226],"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":[0.0011036844,0.0016025596,0.054837745,0.0018448735,0.013136361,0.0015531251,0.011465449,0.012615198,0.009963538,0.08680637,0.120267145,0.68480396],"study_design_scores_gemma":[0.00027117186,0.00012107444,0.0029579282,0.00009726836,0.001449176,0.000013247574,0.00071299594,0.99065536,0.00015424835,0.0007911185,0.0026465075,0.00012991893],"about_ca_topic_score_codex":0.00004214571,"about_ca_topic_score_gemma":0.00005738544,"teacher_disagreement_score":0.97804016,"about_ca_system_score_codex":0.00006711948,"about_ca_system_score_gemma":0.00004713395,"threshold_uncertainty_score":0.48123103},"labels":[],"label_agreement":null},{"id":"W4393187453","doi":"10.1016/j.media.2024.103145","title":"DermSynth3D: Synthesis of in-the-wild annotated dermatology images","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; BC Cancer Foundation; Fonds National de la Recherche Luxembourg; Nvidia","keywords":"Artificial intelligence; Computer science; Dermatology; Computer vision; Pattern recognition (psychology); Medicine","score_opus":0.006955562316105821,"score_gpt":0.2746487435462664,"score_spread":0.26769318123016056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393187453","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":[0.013731787,0.0010313599,0.96508116,0.01814313,0.00018637929,0.00007915604,0.00000483715,0.00015831087,0.0015838622],"genre_scores_gemma":[0.9943614,0.00015388084,0.0049744155,0.0003835451,0.00004356042,0.000038967537,0.0000025239333,0.0000074110008,0.00003432039],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780893,0.0003355032,0.00044038374,0.00041377352,0.00073756865,0.00026382343],"domain_scores_gemma":[0.99808425,0.0011189898,0.00006574233,0.00058052025,0.00006806208,0.00008245267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008469836,0.00012800733,0.00037106048,0.0007301729,0.000048139605,0.000118181364,0.0011301916,0.00010881835,0.00028399762],"category_scores_gemma":[0.00069359585,0.000090809284,0.00024935033,0.004617208,0.00023408038,0.00037181654,0.00015067431,0.00028813127,0.00006274699],"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":[0.000019651,0.0003957151,0.008708091,0.00047499087,0.0030552258,0.0066460334,0.0033832872,0.00020834176,0.0034971228,0.0032415066,0.026518231,0.9438518],"study_design_scores_gemma":[0.00021689375,0.000046791516,0.011124879,0.00018020411,0.0013333654,0.0004066229,0.0002784425,0.91852623,0.059609424,0.0026436944,0.0052204933,0.0004129402],"about_ca_topic_score_codex":0.00028515418,"about_ca_topic_score_gemma":0.00015521303,"teacher_disagreement_score":0.98062956,"about_ca_system_score_codex":0.00004492911,"about_ca_system_score_gemma":0.00011293231,"threshold_uncertainty_score":0.3703095},"labels":[],"label_agreement":null},{"id":"W4393281987","doi":"10.1016/j.media.2024.103150","title":"Boundary-aware information maximization for self-supervised medical image segmentation","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Hôpital Notre-Dame","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Artificial intelligence; Computer science; Cluster analysis; Feature learning; Segmentation; Pattern recognition (psychology); Mutual information; Maximization; Image segmentation; Feature (linguistics); Machine learning; Mathematics","score_opus":0.007274381179233694,"score_gpt":0.2781048143756569,"score_spread":0.2708304331964232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393281987","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":[0.00067157147,0.00010737832,0.9890257,0.00798355,0.00031290852,0.00022214808,0.0000102515805,0.000621094,0.0010453655],"genre_scores_gemma":[0.21759392,0.0004782333,0.7664641,0.010504161,0.0006774491,0.00034645008,0.002890721,0.00005902667,0.0009859116],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968301,0.00015440286,0.0006145756,0.00037792342,0.0017104563,0.00031251335],"domain_scores_gemma":[0.998608,0.00031045882,0.00010154311,0.00032069124,0.00027739364,0.00038191184],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001540458,0.00017652674,0.00027473216,0.0006459683,0.00024969326,0.0012126697,0.00062559143,0.00017089353,0.0020855768],"category_scores_gemma":[0.00087955233,0.00015599732,0.00029475213,0.0022669674,0.0000879977,0.0029024873,0.00013588654,0.00027070698,0.00033018307],"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":[0.00002296503,0.0001720692,0.00031067725,0.0004062754,0.0014321303,0.00014188584,0.0075135133,0.0003775737,0.00029199364,0.007077919,0.016902195,0.9653508],"study_design_scores_gemma":[0.000502913,0.000035427485,0.00027206694,0.00003336055,0.00027411597,0.000010255636,0.00024656497,0.9773006,0.0001216755,0.00040095602,0.020624714,0.00017736189],"about_ca_topic_score_codex":0.000031366882,"about_ca_topic_score_gemma":0.000019304167,"teacher_disagreement_score":0.976923,"about_ca_system_score_codex":0.00011096308,"about_ca_system_score_gemma":0.0004330774,"threshold_uncertainty_score":0.99982417},"labels":[],"label_agreement":null},{"id":"W4396622776","doi":"10.1016/j.media.2024.103184","title":"Self-supervised anatomical continuity enhancement network for 7T SWI synthesis from 3T SWI","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of British Columbia","funders":"University of British Columbia; Compute Canada","keywords":"Susceptibility weighted imaging; Computer science; Task (project management); Pattern recognition (psychology); Artificial intelligence; Magnetic resonance imaging; Medicine","score_opus":0.010741466911618097,"score_gpt":0.32669903471585465,"score_spread":0.31595756780423656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396622776","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":[0.0153331645,0.0011889668,0.97509325,0.006027234,0.00006513878,0.0005805514,0.00010453,0.00052949355,0.0010776613],"genre_scores_gemma":[0.56236285,0.0011008237,0.43149132,0.0017061813,0.0011217016,0.0010471821,0.000414389,0.00005587227,0.0006996559],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977697,0.00005145405,0.00053932867,0.00063973514,0.00058124494,0.0004185492],"domain_scores_gemma":[0.997804,0.0010131944,0.00006254677,0.0005536739,0.00013280363,0.000433769],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005624916,0.00022598419,0.0007364123,0.00015782204,0.00011533078,0.000060700364,0.00022829878,0.00020698574,0.0038147657],"category_scores_gemma":[0.00052797847,0.00018019561,0.0006654619,0.001140218,0.000122010366,0.000085482985,0.000095631534,0.00031014698,0.00008672658],"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":[0.000430583,0.0033494774,0.008036292,0.0008705629,0.016183728,0.000740119,0.00077828794,0.000059701015,0.016716791,0.014147156,0.19338292,0.7453044],"study_design_scores_gemma":[0.00081649504,0.00016441924,0.001887198,0.00059616147,0.019413155,0.000010339312,0.00017551698,0.7345479,0.018550482,0.0065282807,0.21665746,0.0006525648],"about_ca_topic_score_codex":0.00011535121,"about_ca_topic_score_gemma":0.00006921499,"teacher_disagreement_score":0.7446518,"about_ca_system_score_codex":0.00013022724,"about_ca_system_score_gemma":0.00013112786,"threshold_uncertainty_score":0.9970959},"labels":[],"label_agreement":null},{"id":"W4396669394","doi":"10.1016/j.media.2024.103197","title":"Multi-scale relational graph convolutional network for multiple instance learning in histopathology images","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":29,"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 British Columbia; University of British Columbia Hospital","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Convolutional neural network; Magnification; Computer science; Graph; Pattern recognition (psychology); Artificial intelligence; Embedding; Theoretical computer science","score_opus":0.014425377078651583,"score_gpt":0.2764111777591579,"score_spread":0.2619858006805063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396669394","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":[0.0028093809,0.0020668432,0.9917524,0.0023719692,0.0005119376,0.000114583265,0.000008876252,0.00023302983,0.0001309906],"genre_scores_gemma":[0.5056401,0.00011984915,0.4921838,0.00047564317,0.0003696051,0.00016606283,0.00007130135,0.000017894763,0.0009557603],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979531,0.00017419191,0.0004041367,0.0006187097,0.00050184765,0.00034801124],"domain_scores_gemma":[0.9987364,0.0007249888,0.000074074575,0.00023527726,0.00011100898,0.00011828006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012026606,0.00013624274,0.0002826623,0.0004628131,0.00016282649,0.000076649165,0.0003884848,0.00014496525,0.0001333001],"category_scores_gemma":[0.0005819536,0.0001339028,0.00026650054,0.0023902885,0.00020491306,0.00046851975,0.00012393256,0.0004690824,0.000031852433],"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":[0.00015690188,0.00059796113,0.5231619,0.00031774296,0.001407111,0.0010969627,0.0026631537,0.20611317,0.0076627913,0.013533197,0.038102336,0.20518677],"study_design_scores_gemma":[0.0003657664,0.00002800207,0.055159368,0.000031715426,0.000086617365,0.000012689545,0.000012273267,0.93351096,0.00005163861,0.0013023437,0.009297067,0.0001415611],"about_ca_topic_score_codex":0.00008720698,"about_ca_topic_score_gemma":0.00074744277,"teacher_disagreement_score":0.7273978,"about_ca_system_score_codex":0.00021734441,"about_ca_system_score_gemma":0.00018322797,"threshold_uncertainty_score":0.5460397},"labels":[],"label_agreement":null},{"id":"W4398201688","doi":"10.1016/j.media.2024.103211","title":"BrainDAS: Structure-aware domain adaptation network for multi-site brain network analysis","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Adaptation (eye); Artificial intelligence; Domain (mathematical analysis); Domain adaptation; Network analysis; Neuroscience; Psychology; Mathematics; Engineering","score_opus":0.03182547527032829,"score_gpt":0.3158843965732074,"score_spread":0.2840589213028791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398201688","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":[0.015524755,0.0006383455,0.9591733,0.022838946,0.00061491266,0.00038629345,0.00034885158,0.00036025836,0.000114332],"genre_scores_gemma":[0.9510165,0.000056919154,0.027557543,0.016957631,0.0022587324,0.00016969704,0.00050980656,0.000075250406,0.0013979578],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995162,0.00058374484,0.0006576454,0.0014582308,0.0013184543,0.0008199058],"domain_scores_gemma":[0.9860722,0.0127319675,0.00015691291,0.0005504251,0.00016062456,0.0003279104],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017052707,0.00039647194,0.00090797414,0.0007758275,0.00059876346,0.00034398225,0.00043797374,0.00023007636,0.0012290647],"category_scores_gemma":[0.013028895,0.00033971108,0.001321328,0.011195375,0.0003599518,0.00038089798,0.00020113186,0.00047437663,0.00006977512],"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":[0.0005108758,0.0005100797,0.0310112,0.0004913715,0.047763973,0.001392925,0.0070534204,0.5261986,0.008748425,0.009850909,0.3230349,0.04343332],"study_design_scores_gemma":[0.00045304289,0.00006692006,0.0068229293,0.00003738116,0.005613806,0.000007104936,0.00018687878,0.96547395,0.00018724962,0.0037652273,0.016963458,0.00042202277],"about_ca_topic_score_codex":0.0001595738,"about_ca_topic_score_gemma":0.0058643147,"teacher_disagreement_score":0.9354917,"about_ca_system_score_codex":0.00014324802,"about_ca_system_score_gemma":0.00015152077,"threshold_uncertainty_score":0.99990547},"labels":[],"label_agreement":null},{"id":"W4399107553","doi":"10.1016/j.media.2024.103225","title":"MMGPL: Multimodal Medical Data Analysis with Graph Prompt Learning","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"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; Artificial intelligence; Graph; Machine learning; Theoretical computer science","score_opus":0.01196817928201128,"score_gpt":0.30379009180225885,"score_spread":0.2918219125202476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399107553","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":[0.0036442578,0.0010028618,0.9883079,0.0055846847,0.00012369227,0.00011068063,0.000010063545,0.0007820937,0.0004337589],"genre_scores_gemma":[0.9115425,0.00043142072,0.085563265,0.0010064377,0.0003439593,0.000036213587,0.0005334373,0.000044766806,0.0004980433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928723,0.00037207254,0.0006515278,0.0018908613,0.0034665335,0.0007467118],"domain_scores_gemma":[0.9957803,0.00074817,0.00012114858,0.0022353283,0.00013956235,0.00097550434],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018895041,0.00037535155,0.00087540277,0.0016499723,0.00023967958,0.0005300109,0.0041197366,0.00024660167,0.0014890603],"category_scores_gemma":[0.00073359685,0.00026197982,0.00058872515,0.020624306,0.00048400467,0.0014134282,0.0015297516,0.001418776,0.00009566909],"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":[0.00007681838,0.00081232295,0.06329954,0.00021623987,0.07313492,0.02807706,0.0013218403,0.03781097,0.00013062077,0.007156212,0.008755189,0.7792083],"study_design_scores_gemma":[0.0002228331,0.000059215938,0.002032006,0.00005467967,0.004349027,0.00004005335,0.000025958807,0.990177,0.000026610285,0.00027440875,0.0023890138,0.0003492279],"about_ca_topic_score_codex":0.0002125929,"about_ca_topic_score_gemma":0.00085538265,"teacher_disagreement_score":0.952366,"about_ca_system_score_codex":0.000036538822,"about_ca_system_score_gemma":0.00025108244,"threshold_uncertainty_score":0.99998325},"labels":[],"label_agreement":null},{"id":"W4399708787","doi":"10.1016/j.media.2024.103239","title":"CCSI: Continual Class-Specific Impression for data-free class incremental learning","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; Vector Institute; University of British Columbia","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Forgetting; Machine learning; Class (philosophy); Margin (machine learning); Cross entropy; Normalization (sociology); Deep learning; Pattern recognition (psychology); Data mining","score_opus":0.03183739835390364,"score_gpt":0.3246820824993474,"score_spread":0.29284468414544373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399708787","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":[0.001669267,0.0009197443,0.98899806,0.004590357,0.00041032356,0.00012441701,0.000020098141,0.0003914797,0.002876284],"genre_scores_gemma":[0.8630407,0.00032979494,0.12607509,0.0015995906,0.000904258,0.00006189327,0.0011566409,0.000058074955,0.0067739957],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99680287,0.00024015375,0.0004951016,0.00088988594,0.0011523707,0.0004196433],"domain_scores_gemma":[0.99765295,0.00074708683,0.00010395177,0.0010702932,0.00010596571,0.00031973916],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021051152,0.00019245474,0.00036712716,0.0004275603,0.000265253,0.0008443314,0.002196477,0.00013183603,0.0011278455],"category_scores_gemma":[0.0012993006,0.0001612701,0.00027705624,0.0014940293,0.00013558517,0.0010153624,0.0012343338,0.0005657184,0.0001738803],"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":[0.0000412638,0.00017000448,0.0008891753,0.000088255394,0.0016038847,0.0004362375,0.0016324262,0.00024846857,0.00704067,0.012678239,0.20002222,0.77514917],"study_design_scores_gemma":[0.0003844965,0.00003446605,0.00019084098,0.000031493888,0.00016092113,0.0000053301333,0.00018275507,0.6721749,0.00013990613,0.00015914766,0.32639015,0.00014565304],"about_ca_topic_score_codex":0.000043950295,"about_ca_topic_score_gemma":0.00004339937,"teacher_disagreement_score":0.8629229,"about_ca_system_score_codex":0.000060538252,"about_ca_system_score_gemma":0.00011692252,"threshold_uncertainty_score":0.99978524},"labels":[],"label_agreement":null},{"id":"W4399709995","doi":"10.1016/j.media.2024.103231","title":"Interpretable deep clustering survival machines for Alzheimer’s disease subtype discovery","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"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; National Institutes of Health; Genentech; IXICO; U.S. National Library of Medicine; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; University of Southern California; Biogen; BioClinica; Meso Scale Diagnostics; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Canadian Institutes of Health Research; National Science Foundation","keywords":"Cluster analysis; Discriminative model; Artificial intelligence; Machine learning; Computer science; Categorization; Pattern recognition (psychology); Data mining","score_opus":0.019210361013252256,"score_gpt":0.3603439240123461,"score_spread":0.34113356299909386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399709995","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":[0.08265632,0.005499873,0.8986596,0.006626459,0.0003724947,0.00054254645,0.00007223508,0.00017418384,0.005396325],"genre_scores_gemma":[0.99192995,0.00019166307,0.0007210986,0.0005903393,0.00038176906,0.00011915386,0.00042237132,0.000031757587,0.0056119165],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779695,0.000077782686,0.00031490414,0.0004662773,0.00091983384,0.0004242313],"domain_scores_gemma":[0.99868923,0.000298069,0.000025546391,0.00027109336,0.00013387178,0.000582184],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007680746,0.00017896201,0.0004425702,0.00042174922,0.00008356311,0.0002567143,0.00016605055,0.000059364076,0.004910152],"category_scores_gemma":[0.000763814,0.00012967199,0.000633493,0.0009216872,0.0001483911,0.00031892705,0.00016304683,0.00023655998,0.000087287655],"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":[0.0031076912,0.0016675895,0.49634713,0.002128895,0.039731573,0.006482655,0.000521887,0.000041846928,0.0029194395,0.00054052274,0.010854892,0.4356559],"study_design_scores_gemma":[0.0009865245,0.00020752086,0.068157956,0.00024867748,0.01762204,0.000011659124,0.00013549112,0.9065,0.0003378417,0.00031716286,0.005210625,0.0002644978],"about_ca_topic_score_codex":0.0001101383,"about_ca_topic_score_gemma":0.00015693452,"teacher_disagreement_score":0.9092736,"about_ca_system_score_codex":0.000039819028,"about_ca_system_score_gemma":0.00020989354,"threshold_uncertainty_score":0.9959995},"labels":[],"label_agreement":null},{"id":"W4400016384","doi":"10.1016/j.media.2024.103243","title":"CP-Net: Instance-aware part segmentation network for biological cell parsing","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CReATe Fertility Centre; University of Toronto","funders":"Temerty Faculty of Medicine, University of Toronto; Natural Sciences and Engineering Research Council of Canada; Vector Institute; Government of Ontario; Ontario Research Foundation","keywords":"Segmentation; Parsing; Computer science; Artificial intelligence; Market segmentation; Image segmentation; Pattern recognition (psychology); Feature (linguistics); Computer vision","score_opus":0.02439601499852344,"score_gpt":0.3100596373806054,"score_spread":0.2856636223820819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400016384","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":[0.0016182637,0.0010597673,0.9929779,0.0032564448,0.00023451359,0.00022419362,0.000011834363,0.000321592,0.00029545123],"genre_scores_gemma":[0.54230964,0.0010698085,0.449597,0.0035328446,0.0016632274,0.0005526075,0.00044101468,0.00003554184,0.0007983371],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981016,0.0000831435,0.00037304888,0.0006400977,0.000398028,0.00040406044],"domain_scores_gemma":[0.998696,0.0005332747,0.000071967384,0.00041548038,0.00006807361,0.000215172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004261085,0.00015605081,0.00027236203,0.00011991772,0.00020960775,0.0001889125,0.00058241794,0.00010214201,0.0001672105],"category_scores_gemma":[0.00006617621,0.0001242187,0.00026387564,0.0026439899,0.00010657613,0.00035305606,0.0001450654,0.00020043459,0.000061979736],"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":[0.000030098287,0.0003547511,0.0026171554,0.0001561529,0.0012124442,0.00028508523,0.0005899661,0.023003124,0.0030584906,0.020662954,0.15421963,0.7938101],"study_design_scores_gemma":[0.00017168628,0.000048536844,0.0002008663,0.000037332018,0.00025333802,0.000004192929,0.000025522275,0.94275105,0.00088891416,0.0074479026,0.047934335,0.00023633408],"about_ca_topic_score_codex":0.000004949731,"about_ca_topic_score_gemma":0.00002124878,"teacher_disagreement_score":0.9197479,"about_ca_system_score_codex":0.000058815785,"about_ca_system_score_gemma":0.000056285484,"threshold_uncertainty_score":0.5065492},"labels":[],"label_agreement":null},{"id":"W4400188830","doi":"10.1016/j.media.2024.103257","title":"The ACROBAT 2022 challenge: Automatic registration of breast cancer tissue","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"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":"Orionin Tutkimussäätiö; Turun Yliopisto; Vetenskapsrådet; Cancerfonden; VINNOVA; Karolinska Institutet; European Commission; Swedish e-Science Research Centre; Turun Yliopistosäätiö; Syöpäsäätiö; European Federation of Pharmaceutical Industries and Associations","keywords":"Computer science; Artificial intelligence; Image registration; Breast cancer; Computer vision; Pattern recognition (psychology); Cancer; Medicine; Image (mathematics)","score_opus":0.0076311122557927704,"score_gpt":0.3052339521346472,"score_spread":0.29760283987885444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400188830","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":[0.0019811785,0.0033926333,0.9414963,0.05002761,0.0006595439,0.00010255783,0.000007947701,0.00021548974,0.0021167195],"genre_scores_gemma":[0.99292874,0.0019082312,0.0020884124,0.00017346363,0.00034175153,0.00007764833,0.0000050782182,0.000011388293,0.0024652581],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813557,0.00010981927,0.00033769137,0.00031102585,0.0009246971,0.00018120198],"domain_scores_gemma":[0.99896675,0.00021560941,0.00009474151,0.00052886584,0.0000999282,0.000094112416],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009095488,0.00009394227,0.0001860047,0.00014503142,0.00012264041,0.0001876299,0.00069116853,0.000068976726,0.0014041587],"category_scores_gemma":[0.00009934783,0.00006261398,0.00014402179,0.0015410284,0.00015827577,0.00033939208,0.00012899695,0.0001998074,0.00008195495],"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":[0.0000023074333,0.000026432403,0.000030316123,0.00007611152,0.0006360157,0.000049772672,0.00035051137,0.00005810735,0.0006477595,0.0021542625,0.007872759,0.98809564],"study_design_scores_gemma":[0.00006624952,0.000035233836,0.0012503562,0.0000649188,0.0003597944,0.000021926722,0.000044534652,0.98664904,0.0010168147,0.0011500159,0.009236962,0.00010417455],"about_ca_topic_score_codex":0.0004616556,"about_ca_topic_score_gemma":0.0011330431,"teacher_disagreement_score":0.9909476,"about_ca_system_score_codex":0.00010548507,"about_ca_system_score_gemma":0.00019247358,"threshold_uncertainty_score":0.9995087},"labels":[],"label_agreement":null},{"id":"W4400768355","doi":"10.1016/j.media.2024.103278","title":"Generating multi-pathological and multi-modal images and labels for brain MRI","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":15,"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":"EPSRC Centre for Doctoral Training in Medical Imaging; Engineering and Physical Sciences Research Council; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Avid Radiopharmaceuticals; Genentech; Royal Academy of Engineering; IXICO; H. Lundbeck A/S; Centre For Medical Engineering, King’s College London; Servier; Eisai; King's College London; National Institutes of Health; National Institute on Aging; National Institute for Health and Care Research; Northern California Institute for Research and Education; Nvidia; Wellcome Trust; University of Southern California; Pfizer; BioClinica; Biogen; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; European Commission; National Center for Advancing Translational Sciences; Medical Research Council; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Alzheimer's Association","keywords":"Computer science; Segmentation; Artificial intelligence; Categorical variable; Generative model; Synthetic data; Modal; Pattern recognition (psychology); Machine learning; Generative grammar","score_opus":0.018465209063195195,"score_gpt":0.3049406073021934,"score_spread":0.2864753982389982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400768355","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":[0.0054202615,0.0026147407,0.98233426,0.009182288,0.00012335855,0.00015137091,0.00002064507,0.000128371,0.000024696476],"genre_scores_gemma":[0.23457286,0.00024345536,0.762898,0.0013679548,0.00026812212,0.000044654826,0.000015832402,0.000014364282,0.0005747359],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997921,0.00022539932,0.00033710105,0.0008222208,0.00032482686,0.0003694423],"domain_scores_gemma":[0.99855775,0.00072375435,0.00004801772,0.00027924083,0.000094200834,0.0002970671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012948052,0.00022134403,0.000431143,0.00021682472,0.00024943738,0.0007180195,0.00034137405,0.00013507016,0.0000767398],"category_scores_gemma":[0.0010693473,0.00016307938,0.00020643258,0.00072295923,0.00027081644,0.00049748964,0.00036633664,0.0002119572,0.0000073992037],"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":[0.000018052015,0.00040628327,0.0032549102,0.00021621885,0.0025542404,0.0013225646,0.0021296842,0.0018735959,0.08108975,0.001898779,0.012513239,0.89272267],"study_design_scores_gemma":[0.00037697854,0.000048288402,0.0012664596,0.00002091717,0.00027178793,0.00001846759,0.00003822243,0.9954867,0.001173311,0.00011191898,0.0009786828,0.00020829691],"about_ca_topic_score_codex":0.00004893562,"about_ca_topic_score_gemma":0.000075443175,"teacher_disagreement_score":0.99361306,"about_ca_system_score_codex":0.000015817239,"about_ca_system_score_gemma":0.000047173336,"threshold_uncertainty_score":0.6923879},"labels":[],"label_agreement":null},{"id":"W4401170997","doi":"10.1016/j.media.2024.103287","title":"Image-level supervision and self-training for transformer-based cross-modality tumor segmentation","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","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":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Fonds de Recherche du Québec - Santé; Compute Canada","keywords":"Computer science; Artificial intelligence; Segmentation; Modality (human–computer interaction); Image segmentation; Modalities; Pattern recognition (psychology); Deep learning; Machine learning; Computer vision","score_opus":0.0338594690691731,"score_gpt":0.35617742369687416,"score_spread":0.3223179546277011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401170997","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":[0.017764311,0.0002280106,0.9753992,0.005831924,0.000057029552,0.0002634846,0.000035474015,0.0003244739,0.000096102754],"genre_scores_gemma":[0.47129783,0.000055592383,0.5274105,0.0008157149,0.000096628464,0.00017126178,0.00008771434,0.000015716174,0.000049025773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981138,0.000056566565,0.00037429784,0.00063723983,0.0005090353,0.00030904994],"domain_scores_gemma":[0.9987191,0.0005343798,0.00004475843,0.00034690727,0.00011047381,0.0002443649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006703659,0.00016146693,0.0002627149,0.00021462532,0.00023242433,0.00040240356,0.00041468706,0.000058144702,0.00008398972],"category_scores_gemma":[0.00012617001,0.00013799475,0.0002308832,0.0015741877,0.0001373944,0.0008244794,0.000050787326,0.00016761333,0.00001330046],"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":[0.000064822394,0.0007498877,0.0020766053,0.0011973397,0.0019131422,0.00030676043,0.005474543,0.0019725403,0.04493943,0.008115949,0.0024339634,0.930755],"study_design_scores_gemma":[0.0003398588,0.000038798844,0.0014955194,0.000020190113,0.00025078806,0.000006425066,0.000035323657,0.99105144,0.0027214831,0.0028301706,0.0010448874,0.00016510538],"about_ca_topic_score_codex":0.00002491044,"about_ca_topic_score_gemma":0.00002545126,"teacher_disagreement_score":0.98907894,"about_ca_system_score_codex":0.00004909472,"about_ca_system_score_gemma":0.00014073211,"threshold_uncertainty_score":0.56272626},"labels":[],"label_agreement":null},{"id":"W4401683276","doi":"10.1016/j.media.2024.103305","title":"Neural implicit surface reconstruction of freehand 3D ultrasound volume with geometric constraints","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Innovative Research Group Project of the National Natural Science Foundation of China; Government of Alberta","keywords":"Artificial intelligence; Computer science; Computer vision; Point cloud; Robustness (evolution); Segmentation; Surface reconstruction; Visualization; Imaging phantom; Iterative closest point; 3D reconstruction; Surface (topology); Mathematics","score_opus":0.00790621936922627,"score_gpt":0.2694161975329444,"score_spread":0.2615099781637181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401683276","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":[0.041062478,0.00030733654,0.956726,0.0005889162,0.00013165978,0.00011990795,0.000016004984,0.00029673002,0.0007509725],"genre_scores_gemma":[0.75327057,0.00009362936,0.24591297,0.00025739323,0.00005710436,0.00000961914,0.000026000873,0.000012476475,0.0003602094],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970906,0.00015026494,0.00056930794,0.0005801666,0.0012912942,0.00031840734],"domain_scores_gemma":[0.99825114,0.00051425037,0.00013740953,0.0005255235,0.000219397,0.000352291],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009226406,0.00018890334,0.00045750992,0.0008513376,0.00006588726,0.00025900835,0.00070560933,0.00011979511,0.0043012057],"category_scores_gemma":[0.0006953438,0.00014360879,0.00020765427,0.00628579,0.0008566971,0.00073992927,0.00011868257,0.0003463396,0.00005990962],"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":[0.000008743032,0.00013036461,0.012605649,0.00014800987,0.001642993,0.00049319165,0.00029240112,0.00006542138,0.015475695,0.00018332468,0.0042792116,0.964675],"study_design_scores_gemma":[0.0011360918,0.0006159433,0.01596743,0.00037086665,0.0026443845,0.0013026899,0.00029155263,0.86616474,0.10941393,0.00069362187,0.00034095833,0.0010578193],"about_ca_topic_score_codex":0.00017051189,"about_ca_topic_score_gemma":0.000023508404,"teacher_disagreement_score":0.96361715,"about_ca_system_score_codex":0.00005897662,"about_ca_system_score_gemma":0.000154581,"threshold_uncertainty_score":0.996609},"labels":[],"label_agreement":null},{"id":"W4401852142","doi":"10.1016/j.media.2024.103309","title":"Establishing group-level brain structural connectivity incorporating anatomical knowledge under latent space modeling","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"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; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Inference; Computer science; Generative model; Artificial intelligence; Machine learning; Statistical inference; Bayesian inference; Bayesian probability; Pattern recognition (psychology); Generative grammar; Mathematics; Statistics","score_opus":0.07956383460373577,"score_gpt":0.39229125966041684,"score_spread":0.31272742505668105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401852142","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":[0.23479314,0.0003483201,0.749459,0.014245587,0.000052660835,0.0001599534,0.000016918279,0.00049294514,0.00043146082],"genre_scores_gemma":[0.9629775,0.000027554048,0.03549442,0.00083499285,0.0002512774,0.000030476987,0.00013364069,0.000041330502,0.00020876828],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979028,0.00009810426,0.0004334686,0.00068148685,0.0005442822,0.00033983865],"domain_scores_gemma":[0.99847174,0.0005047375,0.000062684725,0.00043848468,0.00012982827,0.00039250893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000702527,0.00023269583,0.0005152656,0.00042767075,0.0001719892,0.00016713965,0.00020476377,0.00014469605,0.00023985698],"category_scores_gemma":[0.00094995304,0.00019024657,0.00035884595,0.0020223032,0.00018051763,0.00034274283,0.00020960683,0.0008379512,0.000021338452],"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":[0.00034374578,0.0020659894,0.06374292,0.0022269331,0.010980958,0.0055729016,0.002815608,0.015603726,0.128633,0.25922778,0.024680356,0.48410606],"study_design_scores_gemma":[0.0002560033,0.000025018999,0.0018786389,0.00012540573,0.0008801253,0.000066213695,0.000076296645,0.98766714,0.00042222327,0.008015208,0.000386807,0.0002008875],"about_ca_topic_score_codex":0.00022340156,"about_ca_topic_score_gemma":0.000112835565,"teacher_disagreement_score":0.9720634,"about_ca_system_score_codex":0.00017193877,"about_ca_system_score_gemma":0.000148519,"threshold_uncertainty_score":0.775803},"labels":[],"label_agreement":null},{"id":"W4402282873","doi":"10.1016/j.media.2024.103342","title":"ATEC23 Challenge: Automated prediction of treatment effectiveness in ovarian cancer using histopathological images","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Taiwan University of Science and Technology; Tri-Service General Hospital; National Science and Technology Council","keywords":"Bevacizumab; Medicine; Ovarian cancer; Perforation; Oncology; Cancer; Internal medicine; Adverse effect; Medical physics; Chemotherapy","score_opus":0.0252842723934936,"score_gpt":0.33213852774531333,"score_spread":0.3068542553518197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402282873","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":[0.15168187,0.0019048991,0.844237,0.00070555863,0.0004981609,0.00018016936,0.000022149978,0.0005739384,0.00019623882],"genre_scores_gemma":[0.9954727,0.00044904847,0.003857853,0.000016504415,0.00008465,0.00007927341,0.0000067460446,0.0000096897775,0.000023479668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979739,0.0003693782,0.00037679827,0.00057609443,0.00047034686,0.00023345479],"domain_scores_gemma":[0.99921536,0.00018490407,0.00007053063,0.00035067232,0.000073859264,0.000104658975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008325869,0.00016250071,0.0004287013,0.00061894365,0.00004975363,0.000059813454,0.00030782536,0.00015359145,0.00016010768],"category_scores_gemma":[0.00009793762,0.00012659654,0.00022002966,0.0025677285,0.00013375978,0.00035322306,0.00010464699,0.00017867745,0.000006781287],"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":[0.00018730205,0.0018157377,0.052882742,0.0012307415,0.0053243376,0.005655008,0.004766189,0.03232094,0.1910229,0.001274247,0.00038470753,0.70313513],"study_design_scores_gemma":[0.0003073335,0.00016655627,0.036125567,0.000136398,0.0004044323,0.00001598349,0.000011490148,0.9556322,0.006831997,0.00017016874,0.00009382543,0.000104061335],"about_ca_topic_score_codex":0.0020918672,"about_ca_topic_score_gemma":0.00017785408,"teacher_disagreement_score":0.92331123,"about_ca_system_score_codex":0.0011146647,"about_ca_system_score_gemma":0.00024190432,"threshold_uncertainty_score":0.51624566},"labels":[],"label_agreement":null},{"id":"W4402565067","doi":"10.1016/j.media.2024.103346","title":"Semi-supervised ViT knowledge distillation network with style transfer normalization for colorectal liver metastases survival prediction","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"Fonds de Recherche du Québec - Santé; Institut TransMedTech; Institut de Valorisation des Données; Natural Sciences and Engineering Research Council of Canada; Institut Du Cancer de Montréal; Canada First Research Excellence Fund; Université de Montréal","keywords":"Normalization (sociology); Distillation; Computer science; Artificial intelligence; Transfer of learning; Machine learning; Chemistry; Chromatography","score_opus":0.011029659896524527,"score_gpt":0.25581270989714217,"score_spread":0.24478305000061765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402565067","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":[0.009145434,0.0006661491,0.9883373,0.0003020779,0.00051092636,0.0002830177,0.00005318535,0.00038447,0.00031746665],"genre_scores_gemma":[0.98908275,0.00013665638,0.009297894,0.000053122825,0.0006992996,0.00014099006,0.00040975245,0.000024804694,0.00015470604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997875,0.00019969883,0.0003475322,0.00058114255,0.0006943175,0.0003023525],"domain_scores_gemma":[0.99891573,0.0003712448,0.000033456865,0.00027178088,0.00023333127,0.00017446846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009019383,0.00018945892,0.0003147447,0.00028005484,0.00019957162,0.00027792162,0.00030553262,0.000120079865,0.00028768016],"category_scores_gemma":[0.00009115776,0.00015139987,0.0002480909,0.003133422,0.00009884154,0.0008655455,0.00005482052,0.00016428813,0.000020662246],"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":[0.0011249335,0.0010613035,0.021281539,0.0017451342,0.018604608,0.00040049807,0.010424368,0.08400949,0.0045993333,0.014599918,0.021979766,0.8201691],"study_design_scores_gemma":[0.00035046233,0.00019330665,0.0026192656,0.00005046155,0.001344502,0.000008411209,0.000024127407,0.9895144,0.0007902459,0.00008283031,0.004848176,0.00017380426],"about_ca_topic_score_codex":0.00009043668,"about_ca_topic_score_gemma":0.0010053688,"teacher_disagreement_score":0.9799373,"about_ca_system_score_codex":0.00014589576,"about_ca_system_score_gemma":0.00016025295,"threshold_uncertainty_score":0.61739075},"labels":[],"label_agreement":null},{"id":"W4403015917","doi":"10.1016/j.media.2024.103357","title":"A Foundation Language-Image Model of the Retina (FLAIR): encoding expert knowledge in text supervision","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":78,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"DiagnoCure (Canada); Centre Hospitalier de l’Université de Montréal; Université du Québec","funders":"Fonds de recherche du Québec","keywords":"Encoding (memory); Computer science; Foundation (evidence); Image (mathematics); Fluid-attenuated inversion recovery; Artificial intelligence; Natural language processing; Retina; Computer vision; Psychology; Medicine; Neuroscience; Radiology; Magnetic resonance imaging","score_opus":0.01632020237077082,"score_gpt":0.34574680577638284,"score_spread":0.32942660340561203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403015917","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":[0.8985086,0.004389178,0.06225344,0.01556157,0.00012523186,0.00022606672,0.000007669846,0.00014967771,0.018778527],"genre_scores_gemma":[0.9945318,0.00039774238,0.0017829281,0.00029656882,0.00014062018,0.0000140315215,0.000050650866,0.000023106048,0.0027625186],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976735,0.00018023407,0.000593019,0.00043975812,0.000842645,0.00027086062],"domain_scores_gemma":[0.99888706,0.00020111052,0.00006869303,0.0005237382,0.00014904389,0.00017035546],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011783679,0.00018540912,0.0005910484,0.0007509138,0.00006912105,0.00007302647,0.00026644478,0.000113510185,0.0014631188],"category_scores_gemma":[0.0010155337,0.00011568237,0.0007147158,0.003348763,0.00025575125,0.00019096496,0.00014251466,0.00045630732,0.0000838083],"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":[0.0001831727,0.001550345,0.027236056,0.001641406,0.0041648867,0.0013025817,0.031130679,0.00050513214,0.643219,0.00040331073,0.011738358,0.2769251],"study_design_scores_gemma":[0.00034892707,0.000026071382,0.0015002546,0.0007255138,0.0017582526,0.00001499522,0.0015815569,0.98495173,0.008459305,0.00006035294,0.00043493795,0.00013811867],"about_ca_topic_score_codex":0.00061619165,"about_ca_topic_score_gemma":0.0001812613,"teacher_disagreement_score":0.9844466,"about_ca_system_score_codex":0.000111860165,"about_ca_system_score_gemma":0.00020818289,"threshold_uncertainty_score":0.9994497},"labels":[],"label_agreement":null},{"id":"W4403243140","doi":"10.1016/j.media.2024.103365","title":"RFMiD: Retinal Image Analysis for multi-Disease Detection challenge","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Artificial intelligence; Diabetic retinopathy; Disease; Macular degeneration; Glaucoma; Central retinal artery occlusion; Preprocessor; Medicine; Fundus (uterus); Contextual image classification; Optometry; Retinal; Ophthalmology; Pattern recognition (psychology); Pathology; Image (mathematics); Diabetes mellitus","score_opus":0.02624280849333781,"score_gpt":0.3576893885822046,"score_spread":0.3314465800888668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403243140","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":[0.03826761,0.004053201,0.94279504,0.012829915,0.00014512963,0.0003489917,0.00009536137,0.0005470679,0.00091767585],"genre_scores_gemma":[0.97854644,0.0007734106,0.0133226905,0.0006622438,0.000714213,0.00015186268,0.000698069,0.00007140079,0.0050596735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99562037,0.00018418605,0.0008719262,0.0012173067,0.0014347003,0.0006714945],"domain_scores_gemma":[0.9969702,0.00029801298,0.00013816443,0.00083957665,0.00048688,0.0012671686],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015596503,0.00043422208,0.0013267848,0.0027208629,0.00023689351,0.00027643482,0.00028970142,0.00020438046,0.0032912027],"category_scores_gemma":[0.0019525834,0.00034887102,0.0037216682,0.0072263665,0.00035735552,0.00028127772,0.00008962195,0.0006123173,0.0002463009],"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":[0.0032368596,0.006817795,0.10852899,0.0071798735,0.3532957,0.02427292,0.0026542866,0.0005102919,0.039687954,0.0004129237,0.015931511,0.43747088],"study_design_scores_gemma":[0.0008807144,0.00013095592,0.013274764,0.00013911974,0.12064932,0.000019957391,0.00023019518,0.85722744,0.00093085185,0.00007328376,0.006032576,0.00041080933],"about_ca_topic_score_codex":0.00032102704,"about_ca_topic_score_gemma":0.00024390686,"teacher_disagreement_score":0.9402788,"about_ca_system_score_codex":0.00016118935,"about_ca_system_score_gemma":0.00021338003,"threshold_uncertainty_score":0.99989635},"labels":[],"label_agreement":null},{"id":"W4403909094","doi":"10.1016/j.media.2024.103381","title":"A cross-attention-based deep learning approach for predicting functional stroke outcomes using 4D CTP imaging and clinical metadata","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"","keywords":"Metadata; Computer science; Artificial intelligence; Deep learning; Stroke (engine); Machine learning; World Wide Web","score_opus":0.033867064350132356,"score_gpt":0.3710186549519243,"score_spread":0.33715159060179195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403909094","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":[0.15488663,0.0007980064,0.8418891,0.0012319082,0.00017366627,0.0003005863,0.000040687675,0.0001892378,0.00049021025],"genre_scores_gemma":[0.8755023,0.000032115615,0.11781129,0.0010812975,0.0007399982,0.000068618494,0.0012893098,0.00006689267,0.0034082122],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99645126,0.00012296936,0.00091832184,0.00091887626,0.0011410067,0.00044757672],"domain_scores_gemma":[0.9979482,0.0009268271,0.00015580551,0.00038358584,0.00018984266,0.00039570403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025715178,0.00028290803,0.00082122505,0.0006046042,0.0002924614,0.0004895927,0.0001726858,0.00014613211,0.00062128296],"category_scores_gemma":[0.00317309,0.00022660584,0.0009615607,0.00077896204,0.000473958,0.00038229334,0.0002267788,0.0007090207,0.000004984281],"study_design_candidate":"observational","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":[0.0000757067,0.00017213251,0.97237813,0.00035903606,0.0069066985,0.00015821606,0.000024287172,0.0005971813,0.00038451582,0.000019519775,0.0005056728,0.018418884],"study_design_scores_gemma":[0.0015208169,0.000041629963,0.06336987,0.00005868557,0.014494483,0.0000255836,0.0002777904,0.9184073,0.000029978555,0.0000027807994,0.001593907,0.00017712875],"about_ca_topic_score_codex":0.00008855351,"about_ca_topic_score_gemma":0.000006820392,"teacher_disagreement_score":0.91781014,"about_ca_system_score_codex":0.000110575675,"about_ca_system_score_gemma":0.00017559489,"threshold_uncertainty_score":0.9240718},"labels":[],"label_agreement":null},{"id":"W4404055034","doi":"10.1016/j.media.2024.103389","title":"Editorial for Special Issue on Foundation Models for Medical Image Analysis","year":2024,"lang":"en","type":"editorial","venue":"Medical Image Analysis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Foundation (evidence); Computer science; Image (mathematics); Artificial intelligence; Data science; Geography","score_opus":0.0070945737540653265,"score_gpt":0.34453436390558956,"score_spread":0.33743979015152425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404055034","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001255028,0.00015945616,0.29063773,0.010586609,0.69398046,0.0009798389,0.00053809787,0.000234984,0.0028702791],"genre_scores_gemma":[0.000042499232,0.00069508277,0.007925931,0.0011182268,0.9602225,0.00054417906,0.02142545,0.0002660117,0.007760126],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9838141,0.00029839086,0.0022875662,0.0024192699,0.009854056,0.0013265742],"domain_scores_gemma":[0.98795676,0.0061100684,0.0006578281,0.0013406995,0.0018362022,0.0020984537],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.007003233,0.0011294807,0.0041653244,0.0032069238,0.00040272644,0.0006241797,0.001203951,0.0034003248,0.009721879],"category_scores_gemma":[0.05078726,0.00092886685,0.005215892,0.003823323,0.00076104485,0.00029623014,0.00029459293,0.0046914,0.00033399957],"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":[0.00083141885,0.00044573317,0.0000075217768,0.00084773323,0.02302562,0.0002371043,0.00014278674,0.00013812147,0.0000117911,0.00010661911,0.94729435,0.026911221],"study_design_scores_gemma":[0.0025064307,0.00034888426,0.0000019121715,0.00028722503,0.05248849,0.0000027340507,0.00003052734,0.3335982,0.000008186795,0.000818637,0.6093972,0.000511628],"about_ca_topic_score_codex":0.00042594213,"about_ca_topic_score_gemma":0.00024401181,"teacher_disagreement_score":0.33789718,"about_ca_system_score_codex":0.0006579233,"about_ca_system_score_gemma":0.0026661286,"threshold_uncertainty_score":0.9993162},"labels":[],"label_agreement":null},{"id":"W4404768704","doi":"10.1016/j.media.2024.103400","title":"Prediction of the upright articulated spine shape in the operating room using conditioned neural kernel fields","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Centre hospitalier universitaire Sainte-Justine; Centre Hospitalier Universitaire de Québec; Chung Hua University; Compute Canada","keywords":"Artificial intelligence; Computer science; SPINE (molecular biology); Computer vision; Artificial neural network; Kernel (algebra); Pattern recognition (psychology); Mathematics; Machine learning; Biology; Combinatorics","score_opus":0.013660729993830322,"score_gpt":0.2557247947042363,"score_spread":0.24206406471040598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404768704","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":[0.92001563,0.00062892,0.076126985,0.0025178755,0.00019140626,0.00007808705,0.0000124470325,0.0001123667,0.00031626222],"genre_scores_gemma":[0.9992082,0.000030695315,0.00021435351,0.00030269916,0.00013765383,0.000007375397,0.000039904986,0.0000111670615,0.000047932856],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983134,0.00014777343,0.00048465247,0.0001883117,0.00066159375,0.00020425547],"domain_scores_gemma":[0.99945766,0.00012219192,0.000029282572,0.00026822413,0.000040406543,0.000082209954],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006745796,0.00012678729,0.00028181155,0.00021284886,0.0000795625,0.0000912956,0.00026925193,0.00009618185,0.0013072698],"category_scores_gemma":[0.00037018204,0.000068416106,0.00029959925,0.002402901,0.000111589936,0.00013525401,0.000038431852,0.0004830694,0.00000676696],"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":[0.000006882213,0.00054617395,0.06479449,0.0011522148,0.011425491,0.0014330129,0.008624523,0.7413337,0.10034333,0.00040531592,0.012218013,0.05771681],"study_design_scores_gemma":[0.000114986084,0.00000431952,0.007859321,0.000102409045,0.0010598447,0.000009597365,0.00012876169,0.9897557,0.0007879148,0.0000402423,0.00007092916,0.0000659576],"about_ca_topic_score_codex":0.00015991974,"about_ca_topic_score_gemma":0.00004848777,"teacher_disagreement_score":0.24842197,"about_ca_system_score_codex":0.00003132356,"about_ca_system_score_gemma":0.000027814212,"threshold_uncertainty_score":0.99960566},"labels":[],"label_agreement":null},{"id":"W4405494868","doi":"10.1016/j.media.2024.103439","title":"Personalized dental crown design: A point-to-mesh completion network","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":17,"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","funders":"MEDTEQ+; Natural Sciences and Engineering Research Council of Canada; King Fahd University of Petroleum and Minerals","keywords":"Crown (dentistry); Point (geometry); Computer science; Artificial intelligence; Orthodontics; Mathematics; Medicine; Geometry","score_opus":0.013217806012718668,"score_gpt":0.25885082124515635,"score_spread":0.2456330152324377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405494868","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":[0.009558075,0.0016418318,0.986647,0.0006351276,0.00015753695,0.00006646688,0.00001011779,0.00062035007,0.0006634956],"genre_scores_gemma":[0.987406,0.00015577786,0.010522372,0.00048974645,0.0004973914,0.00002749868,0.00010780112,0.000043727254,0.0007496862],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980086,0.000095442236,0.0003759091,0.00036564222,0.00073974975,0.00041466395],"domain_scores_gemma":[0.9991438,0.00015108124,0.000014606752,0.00024328665,0.000051532632,0.0003956934],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00078168727,0.00021520529,0.0004928641,0.00045164028,0.00009931204,0.0002195031,0.0002441762,0.000114782975,0.0054000425],"category_scores_gemma":[0.00009449058,0.00019004042,0.0005993218,0.0026584829,0.00007016435,0.000117098614,0.000050681916,0.0002985585,0.00075582525],"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":[0.00004498074,0.00010354506,0.0010876128,0.00021227259,0.01360599,0.0013127524,0.0012898787,0.758758,0.0020819989,0.00019392476,0.17039818,0.050910853],"study_design_scores_gemma":[0.00011664076,0.0000133850735,0.000095718206,0.00006457759,0.0019443687,0.000008817839,0.00006434507,0.99496555,0.000050389164,0.00008679648,0.0023678245,0.0002216033],"about_ca_topic_score_codex":0.000072921175,"about_ca_topic_score_gemma":0.00008884124,"teacher_disagreement_score":0.97784793,"about_ca_system_score_codex":0.00009060326,"about_ca_system_score_gemma":0.000030831663,"threshold_uncertainty_score":0.99550915},"labels":[],"label_agreement":null},{"id":"W4406642521","doi":"10.1016/j.media.2025.103473","title":"Towards contrast-agnostic soft segmentation of the spinal cord","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Polytechnique Montréal","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Neurological Disorders and Stroke; Fonds de recherche du Québec – Nature et technologies; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Réseau en Bio-Imagerie du Quebec; Canadian Institutes of Health Research; National Institutes of Health; Canada Research Chairs; Canada First Research Excellence Fund; Boettcher Foundation; Canada Foundation for Innovation","keywords":"Segmentation; Artificial intelligence; Contrast (vision); Computer science; Computer vision; Pattern recognition (psychology); Anatomy; Medicine","score_opus":0.006067156222850755,"score_gpt":0.27762898365622074,"score_spread":0.27156182743337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406642521","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":[0.0662982,0.000863811,0.9255177,0.0028415592,0.0002674819,0.00008332805,0.00000986608,0.00012041901,0.0039976677],"genre_scores_gemma":[0.9980671,0.00010029368,0.0008327208,0.00056882063,0.000052660915,0.0000113825645,0.000014263012,0.000007660956,0.00034511008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844235,0.00007504597,0.00042812142,0.00017160607,0.0006758046,0.00020707054],"domain_scores_gemma":[0.9993087,0.00010810447,0.000050776893,0.00030742207,0.00008824792,0.00013677053],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039886712,0.00012923086,0.0004029441,0.00025362024,0.000059421272,0.000027341031,0.00034725966,0.00007656104,0.0010043847],"category_scores_gemma":[0.001176989,0.00008775987,0.00038987465,0.0020909854,0.00023088779,0.000056842488,0.000058097343,0.00024421568,0.000014957222],"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":[0.00003985561,0.0002835044,0.043688554,0.00063657557,0.011407324,0.00008007141,0.0001849432,0.00511098,0.018598229,0.00037706137,0.020216862,0.89937603],"study_design_scores_gemma":[0.00097219663,0.000046730554,0.047517344,0.00041443907,0.011072242,0.0000034509499,0.00026849553,0.9122224,0.024724476,0.00059648755,0.0018233565,0.00033839018],"about_ca_topic_score_codex":0.00015826937,"about_ca_topic_score_gemma":0.00004023615,"teacher_disagreement_score":0.9317689,"about_ca_system_score_codex":0.00003938997,"about_ca_system_score_gemma":0.000068898815,"threshold_uncertainty_score":0.9999088},"labels":[],"label_agreement":null},{"id":"W4407080228","doi":"10.1016/j.media.2025.103483","title":"Harmonizing flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; École de Technologie Supérieure; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Compute Canada","keywords":"Harmonization; Computer science; Artificial intelligence; Econometrics; Mathematics; Physics","score_opus":0.022535602287254545,"score_gpt":0.3132272608554435,"score_spread":0.29069165856818896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407080228","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":[0.017734421,0.0006485017,0.9684142,0.011960068,0.000021316515,0.00041922374,0.000010695391,0.00021274804,0.00057886104],"genre_scores_gemma":[0.31937242,0.0012699942,0.6713379,0.0049856235,0.00025142735,0.00039572432,0.0004037217,0.000052475723,0.00193069],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985506,0.000026238156,0.0004053073,0.00041636135,0.00032078606,0.00028069818],"domain_scores_gemma":[0.99885875,0.00016938717,0.000067643756,0.00048111402,0.00020711713,0.00021596364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003998216,0.00016900914,0.00044953712,0.00040843128,0.0002668803,0.00005575186,0.00018760026,0.00012425653,0.0001820157],"category_scores_gemma":[0.0007225646,0.00015224959,0.00022612742,0.0013161793,0.00007835819,0.0001364715,0.00015109428,0.00021141784,0.0000029756347],"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":[0.00041726837,0.0010714115,0.048477333,0.0014298132,0.0046355557,0.00015011357,0.002280798,0.0031481953,0.083635874,0.0036623965,0.042057782,0.80903345],"study_design_scores_gemma":[0.0017385447,0.00003678377,0.0012213497,0.00018286856,0.0032554434,0.000009189807,0.0003774499,0.94845206,0.0072353105,0.0011851307,0.036085445,0.00022045478],"about_ca_topic_score_codex":0.00006936889,"about_ca_topic_score_gemma":0.00003559811,"teacher_disagreement_score":0.94530386,"about_ca_system_score_codex":0.000061461615,"about_ca_system_score_gemma":0.00007733513,"threshold_uncertainty_score":0.6208558},"labels":[],"label_agreement":null},{"id":"W4407269389","doi":"10.1016/j.media.2025.103491","title":"HistoKernel: Whole slide image level Maximum Mean Discrepancy kernels for pan-cancer predictive modelling","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","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":"EPSRC Centre for Doctoral Training in Medical Imaging; Engineering and Physical Sciences Research Council; Sierra Oncology","keywords":"Artificial intelligence; Mathematics; Computer science; Pattern recognition (psychology); Computer vision","score_opus":0.02527294268600958,"score_gpt":0.311818302738887,"score_spread":0.2865453600528774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407269389","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":[0.0014889919,0.00073945033,0.98925394,0.005731067,0.00056221586,0.0003392027,0.000092311115,0.00030675434,0.0014860784],"genre_scores_gemma":[0.60674495,0.00054125086,0.37471643,0.0029646934,0.0008491424,0.0012665126,0.00010091906,0.000082649465,0.012733461],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964197,0.00013970355,0.0006852465,0.0011111697,0.001040674,0.000603496],"domain_scores_gemma":[0.9977457,0.0003122078,0.00023441465,0.0010112363,0.00042613837,0.0002703187],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00093296025,0.000316621,0.0006481783,0.00058384705,0.00031280352,0.0002442166,0.0014258445,0.00019652699,0.00019214586],"category_scores_gemma":[0.00028789183,0.00029040675,0.00063566625,0.002437599,0.00024654274,0.00097224914,0.0004443599,0.0003981758,0.000034310542],"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":[0.0003979172,0.0010024306,0.003150128,0.0006181946,0.011134838,0.00023179155,0.0056278473,0.031439397,0.0061986167,0.006252405,0.049973104,0.88397336],"study_design_scores_gemma":[0.0006430049,0.00005741869,0.0004406068,0.000082552375,0.0011451007,0.0000016398951,0.0000853301,0.974929,0.0032843864,0.012700619,0.006334374,0.00029597097],"about_ca_topic_score_codex":0.0010701766,"about_ca_topic_score_gemma":0.00045209622,"teacher_disagreement_score":0.9434896,"about_ca_system_score_codex":0.00052206166,"about_ca_system_score_gemma":0.00038782659,"threshold_uncertainty_score":0.9999548},"labels":[],"label_agreement":null},{"id":"W4407599638","doi":"10.1016/j.media.2025.103501","title":"Neighbor-aware calibration of segmentation networks with penalty-based constraints","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Ministère de l’Emploi et de la Solidarité Sociale (Québec)","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Computer science; Calibration; Artificial intelligence; Computer vision; Pattern recognition (psychology); Mathematics","score_opus":0.005711010240022647,"score_gpt":0.28069177106980087,"score_spread":0.27498076082977824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407599638","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":[0.00044546003,0.000034336488,0.99666137,0.0018840742,0.000044150434,0.00018474426,0.000004208704,0.00017141226,0.0005702461],"genre_scores_gemma":[0.70117813,0.000019871071,0.29465127,0.0038027272,0.000025961855,0.000049947917,0.00015145572,0.0000074797886,0.00011312669],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976215,0.00023150562,0.0005415003,0.0003976483,0.0009883882,0.00021950164],"domain_scores_gemma":[0.99853396,0.00029965033,0.00022364066,0.00048243205,0.00026117978,0.0001991042],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006713295,0.00015314374,0.00036993963,0.0005215077,0.000077006815,0.00010612334,0.00063193945,0.000111843816,0.0011204999],"category_scores_gemma":[0.00024101321,0.000119967786,0.00014829681,0.0030207168,0.0004563906,0.0004425587,0.00009361044,0.00020555519,0.0000025920353],"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":[0.00012950119,0.0012886871,0.04490748,0.0004203147,0.0039545638,0.00045520318,0.00060065836,0.007369347,0.007389649,0.007126217,0.016117766,0.9102406],"study_design_scores_gemma":[0.0006447902,0.00006793241,0.0011743683,0.00008779681,0.0003929422,0.0000014762468,0.000069241294,0.9575278,0.039707985,0.0001815997,0.000009395699,0.0001346815],"about_ca_topic_score_codex":0.00008426035,"about_ca_topic_score_gemma":0.000049893915,"teacher_disagreement_score":0.9501584,"about_ca_system_score_codex":0.00005745165,"about_ca_system_score_gemma":0.0004008229,"threshold_uncertainty_score":0.99979264},"labels":[],"label_agreement":null},{"id":"W4407763442","doi":"10.1016/j.media.2025.103503","title":"Hyperfusion: A hypernetwork approach to multimodal integration of tabular and medical imaging data for predictive modeling","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; Biotechnology and Biological Sciences Research Council; Child Mind Institute; Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; University of California; National Institutes of Health; Ministry of Health, State of Israel; Stavros Niarchos Foundation; U.S. Department of Defense; James S. McDonnell Foundation; Alzheimer's Disease Neuroimaging Initiative; Israel Science Foundation; National Institute on Aging; Commonwealth Scientific and Industrial Research Organisation; University of Cambridge; Canadian Institute for Advanced Research; Leon Levy Foundation; Harvard University; Massachusetts General Hospital; Alzheimer's Association; Medical Research Council; Howard Hughes Medical Institute","keywords":"Computer science; Artificial intelligence; Computer vision; Machine learning","score_opus":0.02037254151537225,"score_gpt":0.3356412056160552,"score_spread":0.31526866410068294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407763442","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":[0.0070137326,0.0005203376,0.9824875,0.009206906,0.000098772325,0.0002810793,0.000016168906,0.00007711504,0.0002983948],"genre_scores_gemma":[0.71795696,0.000047651025,0.2804973,0.001128042,0.0001231564,0.000046355894,0.00015727506,0.000008217219,0.000035005014],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705917,0.00022996792,0.0005549353,0.00083862664,0.001027622,0.00028967368],"domain_scores_gemma":[0.99770826,0.000463325,0.000090047266,0.0010863923,0.00029478222,0.00035716337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024989499,0.000160124,0.00048919744,0.00043546397,0.00014856437,0.000078164776,0.0016982623,0.00012869072,0.000029681958],"category_scores_gemma":[0.0052549685,0.00013208522,0.000105846724,0.0017310783,0.00010562212,0.00029878673,0.0014122151,0.00038865433,0.0000010775984],"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":[0.00010991955,0.0004658959,0.022795482,0.00041023683,0.0010959834,0.000038129467,0.002101368,0.04536405,0.00014471095,0.0048538935,0.0033527606,0.9192676],"study_design_scores_gemma":[0.0003125328,0.000021609036,0.00054522685,0.00011438991,0.00025919665,0.0000035584885,0.00014276932,0.9980019,0.000012330982,0.0002802152,0.00020256879,0.000103702114],"about_ca_topic_score_codex":0.00095050695,"about_ca_topic_score_gemma":0.00009513806,"teacher_disagreement_score":0.95263785,"about_ca_system_score_codex":0.00003555366,"about_ca_system_score_gemma":0.0002584274,"threshold_uncertainty_score":0.62910676},"labels":[],"label_agreement":null},{"id":"W4407942234","doi":"10.1016/j.media.2025.103494","title":"Exploring the values underlying machine learning research in medical image analysis","year":2025,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":5,"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","funders":"","keywords":"Artificial intelligence; Computer science; Image (mathematics); Machine learning; Computer vision","score_opus":0.6769723147849942,"score_gpt":0.6144296277153716,"score_spread":0.06254268706962263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407942234","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041124184,0.98155403,0.006089203,0.009044175,0.0003025763,0.0007654597,0.000009168473,0.000101363265,0.0017227867],"genre_scores_gemma":[0.0023438544,0.9936329,0.00027851728,0.0003469145,0.0006528696,0.00048959436,0.0007352618,0.00004844182,0.0014716248],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98743737,0.0036178606,0.0024177183,0.0011703902,0.004267973,0.0010886741],"domain_scores_gemma":[0.98793113,0.008877124,0.0003522792,0.0012757381,0.00064845185,0.0009152713],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015693199,0.00052151026,0.0037336892,0.0063531646,0.0006324965,0.0001854733,0.0010520399,0.0006615962,0.004593221],"category_scores_gemma":[0.021702887,0.00033626755,0.0023116076,0.026620327,0.0007722318,0.00023762064,0.00044687768,0.0059595187,0.0002592458],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013222902,0.0001925341,0.001329558,0.00583601,0.0050997534,0.00058822625,0.00074826163,0.0000075460885,1.9725718e-7,0.000024095243,0.000249954,0.98591065],"study_design_scores_gemma":[0.00031076698,0.000364739,0.0011129157,0.05919035,0.16297546,0.00012283715,0.012000984,0.0923991,0.000019554951,0.0007509673,0.66901636,0.0017359348],"about_ca_topic_score_codex":0.01199346,"about_ca_topic_score_gemma":0.0043501537,"teacher_disagreement_score":0.9841747,"about_ca_system_score_codex":0.0006752097,"about_ca_system_score_gemma":0.0031364113,"threshold_uncertainty_score":0.9999089},"labels":[],"label_agreement":null},{"id":"W4408052092","doi":"10.1016/j.media.2025.103538","title":"Graph-based prototype inverse-projection for identifying cortical sulcal pattern abnormalities in congenital heart disease","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiovascular Function and Risk Factors","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Holland Bloorview Kids Rehabilitation Hospital; University of Toronto","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Neurological Disorders and Stroke; National Institutes of Health; National Heart, Lung, and Blood Institute; Ministry of Science and ICT, South Korea","keywords":"Artificial intelligence; Projection (relational algebra); Computer science; Graph; Computer vision; Pattern recognition (psychology); Anatomy; Medicine; Algorithm; Theoretical computer science","score_opus":0.019769023957759167,"score_gpt":0.3153291550869829,"score_spread":0.29556013112922375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408052092","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":[0.70236117,0.0001640951,0.29208776,0.0036387974,0.00033933084,0.0011035486,0.000028504048,0.00011755584,0.00015925283],"genre_scores_gemma":[0.99645025,0.0000141895425,0.00025691214,0.002261242,0.000104321654,0.00025258644,0.00024864048,0.000012607083,0.00039925487],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981464,0.00016721855,0.0004197726,0.00035716477,0.0006333267,0.0002761204],"domain_scores_gemma":[0.99901485,0.00016431289,0.000035178713,0.00029082806,0.00016964975,0.000325163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072911126,0.00015199248,0.00051715376,0.000867018,0.000101662845,0.000047767793,0.00006705838,0.00012910269,0.00063753367],"category_scores_gemma":[0.0012353935,0.00012483039,0.0009780576,0.0014034436,0.00021560825,0.00009051914,0.000028076987,0.00031531844,0.000016745063],"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":[0.0008469711,0.000336336,0.9908303,0.00034351886,0.0019161607,0.00020716616,0.00007759842,0.00002508137,0.00016250768,0.00002333896,0.0019156487,0.003315355],"study_design_scores_gemma":[0.00454388,0.00013621073,0.90726453,0.00016233229,0.007460343,0.0000099093295,0.00058644643,0.07630939,0.0005577888,0.00006942809,0.0026551294,0.00024463062],"about_ca_topic_score_codex":0.0007585611,"about_ca_topic_score_gemma":0.00076815055,"teacher_disagreement_score":0.2940891,"about_ca_system_score_codex":0.00009599321,"about_ca_system_score_gemma":0.0003264077,"threshold_uncertainty_score":0.6980547},"labels":[],"label_agreement":null},{"id":"W4408634392","doi":"10.1016/j.media.2025.103547","title":"Medical SAM adapter: Adapting segment anything model for medical image segmentation","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":334,"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":"Ministry of Education - Singapore; Ministry of Education; National University of Singapore","keywords":"Artificial intelligence; Computer vision; Segmentation; Computer science; Adapter (computing); Image segmentation; Image (mathematics)","score_opus":0.014697149688372452,"score_gpt":0.33526344771584266,"score_spread":0.3205662980274702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408634392","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":[0.0005427894,0.0002195633,0.9738762,0.022494564,0.0002731392,0.00059211283,0.000014316825,0.00075128494,0.0012360492],"genre_scores_gemma":[0.03355499,0.00039913863,0.9393429,0.024094481,0.00030232844,0.000542451,0.00022920409,0.00004571771,0.0014888006],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9892675,0.00048194645,0.0018233623,0.0013710029,0.0060915677,0.0009646146],"domain_scores_gemma":[0.99504775,0.0013983644,0.00037094278,0.0011129868,0.0005340101,0.0015359642],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006977229,0.00048928306,0.0010077376,0.0010954047,0.00044271653,0.0004691545,0.0030316943,0.00059430156,0.002889996],"category_scores_gemma":[0.009115491,0.000434802,0.0007162925,0.0027551935,0.0005469976,0.0012446182,0.0011931311,0.00094516337,0.000050349096],"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":[0.00005525917,0.00090184674,0.00043880852,0.00033597127,0.0023153198,0.00059779966,0.0015913452,0.0001742413,0.004025926,0.0047522318,0.05010478,0.93470645],"study_design_scores_gemma":[0.0013612771,0.000060922914,0.00006310279,0.00024889133,0.00055284204,0.000015152026,0.00018183325,0.9857798,0.009410754,0.0016155287,0.00031813275,0.00039171806],"about_ca_topic_score_codex":0.00018982968,"about_ca_topic_score_gemma":0.00018885545,"teacher_disagreement_score":0.9856056,"about_ca_system_score_codex":0.00030903777,"about_ca_system_score_gemma":0.0014681001,"threshold_uncertainty_score":0.9998104},"labels":[],"label_agreement":null},{"id":"W4409161079","doi":"10.1016/j.media.2025.103559","title":"Improved unsupervised 3D lung lesion detection and localization by fusing global and local features: Validation in 3D low-dose computed tomography","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Lung Cancer Diagnosis and Treatment","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":"Artificial Intelligence in Medicine (Canada)","funders":"Samsung Medical Center, Sungkyunkwan University; Institute for Information and Communications Technology Promotion; Seoul National University; Ministry of Health and Welfare; Ministry of Trade, Industry and Energy; Ministry of Food and Drug Safety; Korea Medical Device Development Fund","keywords":"Artificial intelligence; Computed tomography; Computer science; Computer vision; Pattern recognition (psychology); Radiology; Medicine","score_opus":0.004103300644462484,"score_gpt":0.2765436820288232,"score_spread":0.2724403813843607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409161079","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":[0.5443856,0.003166679,0.45057178,0.0012448361,0.00007020825,0.0003839126,0.000010919841,0.000058005702,0.00010805185],"genre_scores_gemma":[0.99756116,0.0006296231,0.00067278376,0.0008040077,0.000031260293,0.00002685126,0.00025031174,0.0000074242726,0.000016583737],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985812,0.00010932603,0.00032831935,0.00044049302,0.00034727508,0.00019342724],"domain_scores_gemma":[0.99940777,0.00007514576,0.000062962485,0.00017340135,0.000096178344,0.00018452022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002571234,0.00017428226,0.00041821803,0.00036339182,0.00010522335,0.0000665172,0.000042940177,0.0001806188,0.000046480985],"category_scores_gemma":[0.00010161521,0.0001442993,0.00010039214,0.0020319624,0.00014335442,0.000104952174,0.000053495878,0.0001447211,4.7157334e-7],"study_design_candidate":"observational","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":[0.0003802203,0.00075699633,0.5936231,0.0004810889,0.0017438144,0.0000911423,0.00018305966,0.0001716388,0.0023518852,0.000012119762,0.000784128,0.39942083],"study_design_scores_gemma":[0.004750801,0.00012924986,0.2744697,0.00046589505,0.0034746071,0.000008815056,0.00012740826,0.7122864,0.0039857575,0.00002510308,0.00010978637,0.00016647653],"about_ca_topic_score_codex":0.0016429605,"about_ca_topic_score_gemma":0.0008900014,"teacher_disagreement_score":0.71211475,"about_ca_system_score_codex":0.0002906849,"about_ca_system_score_gemma":0.00006856179,"threshold_uncertainty_score":0.5884355},"labels":[],"label_agreement":null},{"id":"W4409328585","doi":"10.1016/j.media.2025.103571","title":"From tissue to sound: A new paradigm for medical sonic interaction design","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Music Technology and Sound Studies","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":false,"ca_institutions":"Concordia University","funders":"","keywords":"Sound (geography); Human–computer interaction; Computer science; Acoustics; Artificial intelligence; Physics","score_opus":0.018957600114458614,"score_gpt":0.3358606046118199,"score_spread":0.31690300449736125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409328585","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":[0.0018779912,0.00028567715,0.92790484,0.068907,0.00037015197,0.00015125012,0.0000020419398,0.0001914902,0.0003095345],"genre_scores_gemma":[0.6386848,0.00015185369,0.33354715,0.021588208,0.0007891406,0.00029208788,0.000036364072,0.000017298691,0.004893075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809295,0.00010629808,0.00036963873,0.0005482335,0.0005695646,0.0003132907],"domain_scores_gemma":[0.9980246,0.0009918972,0.000057438763,0.00057365635,0.00005522664,0.00029716978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007534229,0.00014875807,0.00045001903,0.000426725,0.00018964244,0.00011508447,0.0012060048,0.00023754334,0.0007458914],"category_scores_gemma":[0.0025741076,0.000123459,0.00019541339,0.0016307755,0.000112662885,0.00017577804,0.0003857414,0.00027382319,0.0001011464],"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":[0.00006231468,0.00023331086,0.0005269204,0.00001778705,0.004100353,0.00016659142,0.0029827112,0.00005373227,0.0000903346,0.03155325,0.35300434,0.6072084],"study_design_scores_gemma":[0.0016869603,0.00025282646,0.0013924865,0.00013371713,0.0018741121,0.000009970232,0.00038998693,0.40733704,0.0015154924,0.35929033,0.22549923,0.00061786716],"about_ca_topic_score_codex":0.00063306367,"about_ca_topic_score_gemma":0.00092054746,"teacher_disagreement_score":0.63680685,"about_ca_system_score_codex":0.0000614345,"about_ca_system_score_gemma":0.00028898014,"threshold_uncertainty_score":0.8166988},"labels":[],"label_agreement":null},{"id":"W4409762848","doi":"10.1016/j.media.2025.103600","title":"ProtoASNet: Comprehensive evaluation and enhanced performance with uncertainty estimation for aortic stenosis classification in echocardiography","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; University of British Columbia","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Stenosis; Cardiology; Internal medicine; Medicine; Radiology; Artificial intelligence; Computer science","score_opus":0.015351166396583077,"score_gpt":0.37529175444290136,"score_spread":0.3599405880463183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409762848","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":[0.95572627,0.00018759482,0.041472845,0.0005157292,0.00001551102,0.0017827629,0.000010103391,0.000021009657,0.00026816013],"genre_scores_gemma":[0.99660754,0.00016132045,0.0011822911,0.00019914693,0.00001364532,0.0013785518,0.0004317757,0.0000064477604,0.000019291201],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99871075,0.00006723024,0.00025738214,0.0003147944,0.000502483,0.00014736778],"domain_scores_gemma":[0.99911296,0.000099303405,0.000073182295,0.00021729528,0.00038999494,0.000107230844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028127225,0.00012079565,0.00039489203,0.000499094,0.0000648943,0.000023938588,0.000034449193,0.0000645311,0.00003742398],"category_scores_gemma":[0.00018705062,0.00009043951,0.0003679777,0.0013982762,0.00009614533,0.000089117355,0.000012666573,0.000075221535,0.0000014663879],"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":[0.0005405517,0.00025237064,0.7957273,0.0002802817,0.004492527,0.000002186598,0.00008868612,0.0009519975,0.00021984604,0.000012057376,0.000041427716,0.19739078],"study_design_scores_gemma":[0.0019799091,0.000091933216,0.6389171,0.00011155135,0.0075870594,1.6655704e-7,0.00011949287,0.35096273,0.00013880654,0.00003369674,0.0000056836384,0.00005189888],"about_ca_topic_score_codex":0.00007426158,"about_ca_topic_score_gemma":0.000011273655,"teacher_disagreement_score":0.35001072,"about_ca_system_score_codex":0.00010570932,"about_ca_system_score_gemma":0.00014343433,"threshold_uncertainty_score":0.36880162},"labels":[],"label_agreement":null},{"id":"W4410020272","doi":"10.1016/j.media.2025.103596","title":"Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université du Québec","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec","keywords":"Artificial intelligence; Segmentation; Computer science; Computer vision; Shot (pellet); Foundation (evidence); Pattern recognition (psychology); Materials science; Geography","score_opus":0.02816809076505809,"score_gpt":0.3418809072649658,"score_spread":0.3137128164999077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410020272","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":[0.0043067196,0.00012620517,0.9922553,0.0022057283,0.00011209384,0.00036451424,0.0000035789735,0.00022574466,0.0004001744],"genre_scores_gemma":[0.24509253,0.00006424865,0.7523202,0.0018129819,0.000041481588,0.0001705104,0.00012223974,0.000011023653,0.00036481544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974887,0.00015467618,0.0005589555,0.00060587295,0.00089168496,0.00030010665],"domain_scores_gemma":[0.9983419,0.000515731,0.0001592198,0.00043982232,0.00029731443,0.00024598042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013309082,0.00017909212,0.00037440163,0.0011672286,0.00020408953,0.0003878144,0.00059764815,0.00011450653,0.00021589774],"category_scores_gemma":[0.0020474566,0.00016237368,0.00016890386,0.0039865943,0.00015891362,0.00057582936,0.0002810376,0.00016816905,0.000007024145],"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":[0.000009686257,0.00017999098,0.00032427697,0.00008092897,0.000489403,0.00001279455,0.00044771546,0.00026380035,0.0034417063,0.002466682,0.0018896367,0.9903934],"study_design_scores_gemma":[0.00050332805,0.00005125476,0.00040001262,0.00002759488,0.00040759673,0.0000015478932,0.00007001109,0.98134965,0.01332019,0.0036499414,0.00006396549,0.00015492663],"about_ca_topic_score_codex":0.00012665997,"about_ca_topic_score_gemma":0.000023526592,"teacher_disagreement_score":0.9902384,"about_ca_system_score_codex":0.00011812855,"about_ca_system_score_gemma":0.00017823922,"threshold_uncertainty_score":0.6621406},"labels":[],"label_agreement":null},{"id":"W4410781874","doi":"10.1016/j.media.2025.103648","title":"Corrigendum to “LESS: Label-efficient multi-scale learning for cytological whole slide image screening” [Medical Image Analysis 94 (2024): 103109]","year":2025,"lang":"en","type":"erratum","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Vector Institute; University of British Columbia","funders":"","keywords":"Artificial intelligence; Image (mathematics); Computer science; Scale (ratio); Computer vision; Pattern recognition (psychology); Machine learning; Cartography; Geography","score_opus":0.025653145658127943,"score_gpt":0.31852275399436714,"score_spread":0.2928696083362392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410781874","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":[0.00009672951,0.0008760659,0.9752681,0.008030218,0.010073361,0.00088743947,0.00021432474,0.0008221586,0.0037315506],"genre_scores_gemma":[0.0015953437,0.00059188186,0.5285827,0.005332885,0.003827901,0.0013624362,0.0027013475,0.00022417225,0.45578134],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9834783,0.0012495054,0.0025400526,0.004312833,0.0061299354,0.002289354],"domain_scores_gemma":[0.9911166,0.0010174644,0.0010495598,0.0028903377,0.0015493174,0.0023767615],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.0051152594,0.0014528579,0.0039688926,0.0047251824,0.0010920365,0.0012460224,0.0062361658,0.0023820975,0.00401367],"category_scores_gemma":[0.009030796,0.0013185039,0.003423665,0.018364402,0.00090566033,0.0005234094,0.0033440671,0.005095349,0.00034798257],"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":[0.000097276,0.0009002704,0.0006877482,0.00031531684,0.009797978,0.0011786347,0.00045808533,0.0015693841,0.00021364652,0.000026513662,0.915964,0.06879116],"study_design_scores_gemma":[0.0010836675,0.0002490311,0.00095769524,0.00026636914,0.008894736,0.000018204431,0.000239849,0.8201726,0.00014513453,0.000024984032,0.16678038,0.0011673361],"about_ca_topic_score_codex":0.0011913538,"about_ca_topic_score_gemma":0.0028628767,"teacher_disagreement_score":0.8186032,"about_ca_system_score_codex":0.000872092,"about_ca_system_score_gemma":0.0017109143,"threshold_uncertainty_score":0.9998221},"labels":[],"label_agreement":null},{"id":"W4410836011","doi":"10.1016/j.media.2025.103619","title":"Deep learning detection of acute and sub-acute lesion activity from single-timepoint conventional brain MRI in multiple sclerosis","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NeuroRx Research (Canada); Montreal Neurological Institute and Hospital","funders":"Biogen","keywords":"Multiple sclerosis; Artificial intelligence; Medicine; Lesion; Deep learning; Neuroscience; Psychology; Computer science; Pathology; Psychiatry","score_opus":0.037144037094959184,"score_gpt":0.31749190746002515,"score_spread":0.280347870365066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410836011","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":[0.8723917,0.00023547951,0.12376849,0.0032046689,0.00003512723,0.00021729486,0.00001872107,0.000037827285,0.000090718946],"genre_scores_gemma":[0.9965264,0.0014294187,0.001594162,0.0001445984,0.000040108273,0.00003667153,0.000092033675,0.000012218653,0.00012438423],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99738014,0.00035873815,0.00049911416,0.0005135964,0.00093103916,0.00031736758],"domain_scores_gemma":[0.9981716,0.0009939125,0.00014999142,0.00025395572,0.00021050489,0.00022003178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000854204,0.00019270416,0.000822203,0.0008150079,0.00014864028,0.000031895182,0.00011237952,0.00017445756,0.00032353442],"category_scores_gemma":[0.002855603,0.00016946593,0.00033164723,0.0016036532,0.0004507371,0.00015365648,0.00027307722,0.00055621966,0.0000067367137],"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":[0.00047068347,0.00038996094,0.10188779,0.00005934918,0.004251251,0.00003905416,0.00014568138,0.00002270145,0.8082549,8.311922e-7,0.00008669553,0.0843911],"study_design_scores_gemma":[0.0024302048,0.00011976359,0.64562,0.00022418454,0.0017702067,0.0000012044796,0.00013039587,0.20346752,0.14606915,0.000014170416,0.000049409115,0.000103811944],"about_ca_topic_score_codex":0.0014287608,"about_ca_topic_score_gemma":0.0019896524,"teacher_disagreement_score":0.6621857,"about_ca_system_score_codex":0.00016719104,"about_ca_system_score_gemma":0.000069054404,"threshold_uncertainty_score":0.691062},"labels":[],"label_agreement":null},{"id":"W4411122136","doi":"10.1016/j.media.2025.103650","title":"Evaluation of techniques for automated classification and artery quantification of the circle of Willis on TOF-MRA images: The CROWN challenge","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cerebrovascular and Carotid Artery Diseases","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Artificial intelligence; Crown (dentistry); Circle of Willis; Computer vision; Computer science; Pattern recognition (psychology); Mathematics; Medicine; Radiology; Orthodontics","score_opus":0.02559972452756481,"score_gpt":0.3423675114762819,"score_spread":0.3167677869487171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411122136","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":[0.9506286,0.0010607354,0.031231126,0.012080507,0.0000771448,0.002150025,0.00010070237,0.00010700865,0.002564175],"genre_scores_gemma":[0.9993495,0.00018708232,0.00012013752,0.00012068028,0.000018843655,0.00010266737,0.000064069915,0.0000053459203,0.00003168509],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981827,0.00024691992,0.00043226773,0.00019360421,0.00086524244,0.0000792499],"domain_scores_gemma":[0.99821806,0.00021647064,0.00021795924,0.0005595536,0.0007497774,0.000038156708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018405342,0.000079176716,0.0003230504,0.00019847316,0.00005493697,0.000008154613,0.00013333691,0.000071157156,0.00007840476],"category_scores_gemma":[0.0014344413,0.000047992406,0.00034690232,0.00066258153,0.00034204125,0.0000484357,0.000025573832,0.00007014955,3.8118435e-7],"study_design_candidate":"observational","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":[0.00036290384,0.0034813439,0.052584786,0.0020978758,0.010134396,7.575427e-7,0.0014166015,0.00007363903,0.18151306,0.0014619249,0.006633103,0.7402396],"study_design_scores_gemma":[0.0008785652,0.00011958097,0.7869391,0.00031451898,0.01156246,9.991445e-7,0.0006994476,0.115186304,0.083825804,0.00029115868,0.00011581707,0.00006626322],"about_ca_topic_score_codex":0.000044476685,"about_ca_topic_score_gemma":0.000029054712,"teacher_disagreement_score":0.74017334,"about_ca_system_score_codex":0.000027834281,"about_ca_system_score_gemma":0.00016815236,"threshold_uncertainty_score":0.19570735},"labels":[],"label_agreement":null},{"id":"W4411438887","doi":"10.1016/j.media.2025.103677","title":"When evidence modeling meets knowledge distillation: Towards reliable contrast-enhanced knowledge distillation for non-contrast medical image segmentation","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","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":"Western University","funders":"","keywords":"Contrast (vision); Computer science; Artificial intelligence; Segmentation; Domain knowledge; Distillation; Pattern recognition (psychology); Machine learning; Chemistry","score_opus":0.01639260718222609,"score_gpt":0.3587668278257788,"score_spread":0.3423742206435527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411438887","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":[0.033174638,0.002083712,0.93664575,0.019716758,0.000544236,0.00090268714,0.000017308661,0.00018919232,0.006725741],"genre_scores_gemma":[0.973042,0.00075171894,0.021139838,0.001012804,0.0008788126,0.00022163808,0.0005186143,0.000056978777,0.0023775648],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994985,0.00022896592,0.0014571279,0.0010549477,0.0015190282,0.0007549167],"domain_scores_gemma":[0.99590886,0.0011526587,0.00027807878,0.00062349654,0.0010700705,0.0009668249],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0033219447,0.0004784961,0.0014077971,0.00072585465,0.0004182745,0.00018986095,0.00047748364,0.00043089906,0.001721797],"category_scores_gemma":[0.0148239825,0.00040579846,0.0007114957,0.0016591403,0.00045169587,0.0004659164,0.0001916424,0.0008767067,0.0000589292],"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":[0.001901326,0.002494466,0.014235769,0.004206694,0.009947924,0.0003354471,0.005038734,0.0028517873,0.04057855,0.0011920705,0.05218917,0.8650281],"study_design_scores_gemma":[0.003506735,0.0001091171,0.0026561676,0.0015335821,0.004052091,0.000012891592,0.00021032633,0.9831524,0.0016313578,0.00041838895,0.0023536603,0.00036329543],"about_ca_topic_score_codex":0.00032512122,"about_ca_topic_score_gemma":0.0002005922,"teacher_disagreement_score":0.9803006,"about_ca_system_score_codex":0.00040466175,"about_ca_system_score_gemma":0.0012057486,"threshold_uncertainty_score":0.99983937},"labels":[],"label_agreement":null},{"id":"W4412433844","doi":"10.1016/j.media.2025.103711","title":"CLASS-M: Adaptive stain separation-based contrastive learning with pseudo-labeling for histopathological image classification","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","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":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; ARUP Laboratories; National Institutes of Health; Huntsman Cancer Institute; University of Utah","keywords":"Artificial intelligence; Class (philosophy); Pattern recognition (psychology); Stain; Computer science; Computer vision; Image (mathematics); Mathematics; Pathology; Medicine; Staining","score_opus":0.014088078634863782,"score_gpt":0.3105851636818431,"score_spread":0.2964970850469793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412433844","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":[0.004119258,0.000067980356,0.9898545,0.004315848,0.00009068211,0.00030659212,0.000005376753,0.00023295118,0.001006799],"genre_scores_gemma":[0.787241,0.000010551944,0.21097314,0.00087556784,0.000068469715,0.00027349434,0.00004385531,0.0000106626185,0.0005032998],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974774,0.00032941625,0.00042785687,0.00076559675,0.0006596661,0.0003400499],"domain_scores_gemma":[0.99766845,0.0008966859,0.0002389128,0.00040484115,0.0006432987,0.00014779565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011971564,0.00020376737,0.0004221316,0.000460003,0.00035986013,0.0001833596,0.0005250771,0.00016512975,0.00007076859],"category_scores_gemma":[0.0011920377,0.00016694918,0.00020556162,0.002252685,0.0002912201,0.00041240492,0.00006905846,0.00043045974,0.000012476123],"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":[0.0033809326,0.0024531856,0.037418794,0.0004379345,0.0075075873,0.00081187196,0.0035051059,0.065293975,0.108870886,0.085202694,0.014416727,0.6707003],"study_design_scores_gemma":[0.00081683806,0.00026372494,0.0023677882,0.000032870244,0.00051580084,0.0000021619562,0.00018405438,0.9924109,0.0017754378,0.00051088084,0.0009302427,0.00018932218],"about_ca_topic_score_codex":0.0000504801,"about_ca_topic_score_gemma":0.000104529914,"teacher_disagreement_score":0.92711693,"about_ca_system_score_codex":0.00040985332,"about_ca_system_score_gemma":0.0005057902,"threshold_uncertainty_score":0.680799},"labels":[],"label_agreement":null},{"id":"W4412584687","doi":"10.1016/j.media.2025.103716","title":"PitVis-2023 challenge: Workflow recognition in videos of endoscopic pituitary surgery","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":7,"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":"Department for Science, Innovation and Technology; Horizon 2020 Framework Programme; Cancer Research UK; Wellcome / EPSRC Centre for Interventional and Surgical Sciences; Wellcome Trust; Royal Academy of Engineering; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research","keywords":"Workflow; Computer science; Artificial intelligence; Database","score_opus":0.03061313576358627,"score_gpt":0.3268501300808107,"score_spread":0.29623699431722444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412584687","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":[0.9446583,0.0016672479,0.0098007675,0.009190002,0.00023055323,0.00028251138,0.000010520575,0.000104474,0.034055628],"genre_scores_gemma":[0.99765205,0.00041562712,0.0004176515,0.0009472331,0.00006837327,0.000017644961,0.00015841179,0.0000072389025,0.0003157785],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981609,0.00014273057,0.00064468017,0.00027809147,0.00054679107,0.00022683348],"domain_scores_gemma":[0.99819565,0.0012021337,0.00008088249,0.00022709956,0.00011422812,0.00017998529],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009029991,0.00011947945,0.00073064683,0.0010286829,0.00002726854,0.000008166258,0.00007256446,0.0001535393,0.00682757],"category_scores_gemma":[0.0023577577,0.00010257653,0.0003900865,0.002772038,0.00011598633,0.00007080133,0.00003636066,0.00028627453,0.000044938373],"study_design_candidate":"observational","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":[0.0002108007,0.0010561812,0.2657098,0.0002765122,0.001875425,0.0008025314,0.00018628637,0.00003164102,0.00007564154,0.000046447658,0.00062628445,0.72910243],"study_design_scores_gemma":[0.010929214,0.00019460816,0.90374887,0.0031151895,0.0062966947,0.0000064782703,0.0008739514,0.0637821,0.0014886883,0.0030755792,0.0059487848,0.00053981197],"about_ca_topic_score_codex":0.00017818078,"about_ca_topic_score_gemma":0.00019684374,"teacher_disagreement_score":0.72856265,"about_ca_system_score_codex":0.000041097806,"about_ca_system_score_gemma":0.00014212324,"threshold_uncertainty_score":0.9940803},"labels":[],"label_agreement":null},{"id":"W4412860472","doi":"10.1016/j.media.2025.103715","title":"Attend-and-Refine: Interactive keypoint estimation and quantitative cervical vertebrae analysis for bone age assessment","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion; Korea Advanced Institute of Science and Technology; Ministry of Health and Welfare; Korea Health Industry Development Institute; National Research Foundation of Korea; Ministry of Science and ICT, South Korea; Ministry of Health and Family Welfare; Ministry of Food and Drug Safety; Ministry of Trade, Industry and Energy","keywords":"Computer science; Consistency (knowledge bases); Annotation; Process (computing); Artificial intelligence; Vertebra; Cervical vertebrae; Machine learning; Data mining; Pattern recognition (psychology); Medicine","score_opus":0.011626643756951978,"score_gpt":0.35715661818151534,"score_spread":0.34552997442456335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412860472","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":[0.24451002,0.00044785909,0.75164616,0.0016433663,0.00011178063,0.00018039504,0.000068400994,0.000055130473,0.0013368622],"genre_scores_gemma":[0.9752397,0.00007340921,0.023015123,0.00071563263,0.000024807689,0.000066770815,0.000370277,0.000011268653,0.00048298706],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977909,0.00017837962,0.00057865353,0.00061420794,0.00054739375,0.00029047122],"domain_scores_gemma":[0.9983864,0.0007747139,0.00016444124,0.0002964734,0.00014869205,0.00022927852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007051797,0.00023400749,0.0008262593,0.0014922349,0.00019813543,0.0002613495,0.00017033418,0.00011416386,0.00059663085],"category_scores_gemma":[0.0007669115,0.00020618588,0.00069713395,0.0033306803,0.00032925815,0.0003921294,0.00017532919,0.00031199682,0.000011844095],"study_design_candidate":"observational","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":[0.0006790115,0.0018232266,0.68938345,0.00078332156,0.114324406,0.0018776314,0.0021164988,0.00042041994,0.0031861193,0.014967034,0.008269475,0.16216943],"study_design_scores_gemma":[0.00089900504,0.000048808517,0.46489474,0.000046850946,0.014602935,0.00000957795,0.00074409996,0.5168775,0.00015538959,0.0013453707,0.00017448637,0.00020123465],"about_ca_topic_score_codex":0.000563495,"about_ca_topic_score_gemma":0.00097266835,"teacher_disagreement_score":0.7307297,"about_ca_system_score_codex":0.00007292266,"about_ca_system_score_gemma":0.00004022738,"threshold_uncertainty_score":0.84080166},"labels":[],"label_agreement":null},{"id":"W4412979322","doi":"10.1016/j.media.2025.103749","title":"MedCLIP-SAMv2: Towards universal text-driven medical image segmentation","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":false,"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; Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Computer vision; Segmentation; Image segmentation; Image (mathematics); Pattern recognition (psychology)","score_opus":0.012013374653484442,"score_gpt":0.3527614810408809,"score_spread":0.34074810638739644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412979322","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":[0.07770632,0.0005486058,0.36419463,0.54585844,0.0006272511,0.0007401413,0.000050276587,0.0006843226,0.009589992],"genre_scores_gemma":[0.73279047,0.002226541,0.04215141,0.20714651,0.0014946382,0.00017808184,0.0015743863,0.00015574656,0.012282222],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99463165,0.0003002464,0.0007982948,0.0008256223,0.002877598,0.0005665903],"domain_scores_gemma":[0.99695003,0.00074847374,0.00015693753,0.0007725216,0.0003911679,0.0009808561],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012735948,0.00034506893,0.0010343337,0.0012738021,0.00017547623,0.00008694779,0.00054356764,0.00043483387,0.020429377],"category_scores_gemma":[0.0066981465,0.0003005977,0.00072710234,0.0037990275,0.0006811913,0.00024394355,0.00034602464,0.0007682486,0.00032621832],"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":[0.00050528935,0.0034335814,0.050420526,0.00092802173,0.016271608,0.009565935,0.0015180135,0.000054832875,0.010396802,0.0005152615,0.4644888,0.44190133],"study_design_scores_gemma":[0.024280287,0.0007990641,0.15794457,0.0027671577,0.060543884,0.00015405616,0.0032645965,0.34664783,0.029953262,0.00073965883,0.37057322,0.002332401],"about_ca_topic_score_codex":0.0015079431,"about_ca_topic_score_gemma":0.00050731434,"teacher_disagreement_score":0.65508413,"about_ca_system_score_codex":0.00056228956,"about_ca_system_score_gemma":0.0017387536,"threshold_uncertainty_score":0.9999446},"labels":[],"label_agreement":null},{"id":"W4413159892","doi":"10.1016/j.media.2025.103743","title":"Exploring the robustness of TractOracle methods in RL-based tractography","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Robustness (evolution); Artificial intelligence; Computer science; Tractography; Computer vision; Diffusion MRI; Biology; Magnetic resonance imaging; Radiology; Medicine","score_opus":0.16667939381837615,"score_gpt":0.47539322498763364,"score_spread":0.3087138311692575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413159892","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":[0.10927947,0.000101672114,0.8809969,0.008753973,0.000022306363,0.00016428606,0.0000024102626,0.00006731368,0.0006116736],"genre_scores_gemma":[0.85109514,0.00011719543,0.14780708,0.00072472927,0.000023886392,0.00015657139,0.000013540723,0.000009831605,0.00005201148],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99880177,0.00012193253,0.0003938253,0.00023493086,0.000290578,0.00015697017],"domain_scores_gemma":[0.9987039,0.0005489022,0.00007830845,0.0005061504,0.00008259917,0.000080162274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073083676,0.00009963363,0.00040011905,0.00061182975,0.000044525004,0.000008818836,0.00021037574,0.00004259838,0.00015584494],"category_scores_gemma":[0.000593519,0.000067143585,0.00032681818,0.0041462462,0.00021294206,0.00007664188,0.000034372057,0.00035422636,4.8860255e-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":[0.00022548325,0.0029629795,0.13072555,0.00043037726,0.0016205319,0.00015460972,0.00029851086,0.00329453,0.0456391,0.0012827924,0.0013528271,0.81201273],"study_design_scores_gemma":[0.0018135064,0.000089746114,0.5667722,0.00039922944,0.0048485766,0.0000066085117,0.00044862434,0.30822706,0.10483779,0.0007847378,0.011446375,0.0003255254],"about_ca_topic_score_codex":0.00007768951,"about_ca_topic_score_gemma":0.000021691105,"teacher_disagreement_score":0.8116872,"about_ca_system_score_codex":0.000021317603,"about_ca_system_score_gemma":0.000077759534,"threshold_uncertainty_score":0.2738036},"labels":[],"label_agreement":null},{"id":"W4413275632","doi":"10.1016/j.media.2025.103764","title":"BiasPruner: Mitigating bias transfer in continual learning for fair medical image analysis","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Domain Adaptation and Few-Shot Learning","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":"Simon Fraser University; University of Victoria; University of British Columbia; University of British Columbia Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Transfer of learning; Computer science; Image (mathematics); Computer vision; Machine learning","score_opus":0.01483735090395529,"score_gpt":0.30610355023936614,"score_spread":0.29126619933541087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413275632","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":[0.039840408,0.00016729847,0.948731,0.007977841,0.00010438469,0.00017321936,0.0000034236004,0.00022530323,0.0027771275],"genre_scores_gemma":[0.96218234,0.000061985535,0.033215422,0.0025176734,0.00008801761,0.00007681601,0.000100864745,0.000018471545,0.0017384173],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945337,0.0007623892,0.0012023959,0.0009966993,0.0017639867,0.00074079016],"domain_scores_gemma":[0.9964075,0.002071192,0.00014663058,0.0005491351,0.00029197359,0.0005335749],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004801581,0.0003183877,0.001109568,0.0023085456,0.0003069119,0.00040969162,0.0013836889,0.000308537,0.0014935435],"category_scores_gemma":[0.008262879,0.0002914931,0.0011332807,0.011060287,0.00031471378,0.0005489297,0.00024999675,0.0009463797,0.0000377667],"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":[0.00015915273,0.0013646743,0.21926555,0.0003604816,0.02382001,0.0018903748,0.01303807,0.011232772,0.0034902536,0.023121096,0.0040364456,0.6982211],"study_design_scores_gemma":[0.0013988807,0.00003964115,0.011789846,0.00007219354,0.0016410813,0.0000023531074,0.00082851364,0.9793706,0.00038401317,0.00019644301,0.0039507216,0.00032571304],"about_ca_topic_score_codex":0.00038944057,"about_ca_topic_score_gemma":0.0013257127,"teacher_disagreement_score":0.9681378,"about_ca_system_score_codex":0.00008442895,"about_ca_system_score_gemma":0.0003787099,"threshold_uncertainty_score":0.99995375},"labels":[],"label_agreement":null},{"id":"W4413384488","doi":"10.1016/j.media.2025.103772","title":"A doppler-exclusive computational diagnostic framework to enhance conventional 2-D clinical ultrasound with 3-D mitral valve dynamics and cardiac hemodynamics","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiovascular Function and Risk Factors","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hemodynamics; Mitral valve; Cardiology; Doppler effect; Dynamics (music); Internal medicine; Medicine; Ultrasound; Doppler echocardiography; Computer science; Radiology; Artificial intelligence; Physics; Diastole; Acoustics","score_opus":0.004639162723404445,"score_gpt":0.32223845265999806,"score_spread":0.31759928993659364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413384488","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":[0.2962992,0.00044014372,0.699994,0.0022588014,0.000250822,0.00027921525,0.00006397003,0.000051901327,0.00036193183],"genre_scores_gemma":[0.9713907,0.0005714334,0.023035621,0.0027792358,0.00024279828,0.00004051172,0.0008190921,0.000021277829,0.0010993219],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99730885,0.00020090898,0.00056726276,0.0006183569,0.0010118127,0.00029283107],"domain_scores_gemma":[0.9960996,0.0025373946,0.00008908019,0.00037195536,0.0002965534,0.000605441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066132966,0.00023698191,0.00095295644,0.000381765,0.0001515294,0.00006163077,0.00011676538,0.00026517783,0.00048328622],"category_scores_gemma":[0.0036792804,0.00018617102,0.0018067245,0.0015864877,0.00048752414,0.000061678744,0.00009194791,0.00064093515,0.0000273327],"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":[0.00023607926,0.00035456865,0.9631619,0.00007060357,0.021959249,0.00016122378,0.00011340892,0.0006065854,0.0000060285965,0.002036048,0.0020546736,0.009239634],"study_design_scores_gemma":[0.0010548191,0.00019659274,0.94818497,0.00021845051,0.013106668,0.00005153482,0.00032898985,0.035076242,0.00000975798,0.00066185236,0.0008398076,0.00027032458],"about_ca_topic_score_codex":0.00007733863,"about_ca_topic_score_gemma":0.000085917905,"teacher_disagreement_score":0.67695844,"about_ca_system_score_codex":0.000117957505,"about_ca_system_score_gemma":0.00033378293,"threshold_uncertainty_score":0.7591834},"labels":[],"label_agreement":null},{"id":"W4414919761","doi":"10.1016/j.media.2025.103832","title":"Fusion and pure feature extraction framework for intraoperative hyperspectral of thyroid lesion","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Infrared Thermography in Medicine","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Xi'an Institute of Optics and Precision Mechanics; Canadian Anesthesiologists' Society","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Thyroid cancer; Thyroid nodules; Robustness (evolution); Fusion; Cascade; Thyroid","score_opus":0.008032420561623182,"score_gpt":0.3375897405711067,"score_spread":0.3295573200094835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414919761","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":[0.5679907,0.003487658,0.3987579,0.027169388,0.00019256657,0.0006144006,0.000022492286,0.00006849234,0.0016963494],"genre_scores_gemma":[0.94672424,0.00095473084,0.04940527,0.0017938887,0.00029979326,0.00003688227,0.00012474881,0.00001589197,0.0006445618],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99850595,0.00007290312,0.00032947882,0.00033472505,0.0005401584,0.0002168016],"domain_scores_gemma":[0.998709,0.00039398763,0.00010460673,0.0003075914,0.00030257687,0.00018220625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005435979,0.0001691425,0.0006449291,0.00062827347,0.00010411452,0.00001403626,0.00010145654,0.0003646121,0.0005073108],"category_scores_gemma":[0.0019973898,0.00012151954,0.00032013864,0.001601937,0.00032714658,0.000076841614,0.000037439568,0.000573527,0.0000012333275],"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":[0.0036752902,0.0016488492,0.056142718,0.0015102631,0.013248319,0.00042014272,0.0046179774,0.000009971902,0.6436677,0.022985794,0.02729498,0.224778],"study_design_scores_gemma":[0.02269665,0.005685295,0.40039772,0.00674818,0.0749986,0.0002801162,0.020702891,0.05462702,0.35540187,0.04786749,0.008827242,0.001766915],"about_ca_topic_score_codex":0.000024374685,"about_ca_topic_score_gemma":0.000012608415,"teacher_disagreement_score":0.3787335,"about_ca_system_score_codex":0.000041838048,"about_ca_system_score_gemma":0.00010222588,"threshold_uncertainty_score":0.5554697},"labels":[],"label_agreement":null},{"id":"W4414982617","doi":"10.1016/j.media.2025.103807","title":"A novel gradient inversion attack framework to investigate privacy vulnerabilities during retinal image-based federated learning","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"Canada Research Chairs","keywords":"Generalizability theory; Convolutional neural network; Deep learning; Data set; Differential privacy; Vulnerability (computing); Artificial neural network; Inversion (geology); Information privacy; Training set","score_opus":0.020796750789016834,"score_gpt":0.29876690050068483,"score_spread":0.277970149711668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414982617","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":[0.22768837,0.00004126662,0.6945763,0.0764377,0.00011354059,0.00013888696,0.0000052576447,0.0008199709,0.00017871619],"genre_scores_gemma":[0.42834446,0.00001695465,0.5692935,0.0020270748,0.00003657786,0.00004555165,0.00003642559,0.000015158257,0.00018431759],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957452,0.00034901308,0.0006823085,0.0012524808,0.0012159456,0.0007550933],"domain_scores_gemma":[0.9931357,0.00082847173,0.00018921314,0.0050652204,0.00031499,0.00046642145],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0014854608,0.00035206947,0.0006235306,0.0012644172,0.0006480376,0.00067902525,0.014055148,0.00030531597,0.00021614393],"category_scores_gemma":[0.14811265,0.0003286204,0.00028546603,0.007015378,0.00053161284,0.0006346804,0.03650961,0.001380013,0.000080280544],"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":[0.0006247486,0.0034771736,0.1839905,0.0025561112,0.009630453,0.0034000603,0.0047735237,0.012405245,0.1601987,0.00618808,0.53071487,0.082040556],"study_design_scores_gemma":[0.0005910911,0.00007383372,0.0046771914,0.00042438685,0.00026143075,0.0000045390657,0.00013159355,0.96190125,0.022299718,0.007928271,0.0012526409,0.0004540364],"about_ca_topic_score_codex":0.0003045231,"about_ca_topic_score_gemma":0.000045801295,"teacher_disagreement_score":0.94949603,"about_ca_system_score_codex":0.00031232048,"about_ca_system_score_gemma":0.00030873696,"threshold_uncertainty_score":0.9999166},"labels":[],"label_agreement":null},{"id":"W4416040400","doi":"10.1016/j.media.2025.103857","title":"Adaptive mix for semi-supervised medical image segmentation","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National University's Basic Research Foundation of China; China Scholarship Council; Natural Science Foundation of Liaoning Province; National Natural Science Foundation of China","keywords":"Overfitting; Segmentation; Perturbation (astronomy); Image segmentation; Pattern recognition (psychology); Image (mathematics)","score_opus":0.012633380039165325,"score_gpt":0.31778882447609685,"score_spread":0.30515544443693154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416040400","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":[0.0008362985,0.00014441753,0.9791366,0.01809895,0.000099971345,0.00033208367,0.0000104672,0.0001960911,0.0011451085],"genre_scores_gemma":[0.16156097,0.00029322557,0.82089645,0.013388305,0.00037212437,0.000981448,0.00025441806,0.00003065667,0.0022223867],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99724674,0.00012885267,0.00050775433,0.0006922829,0.0010338445,0.00039055222],"domain_scores_gemma":[0.9977332,0.0008379684,0.00010827693,0.00070019625,0.00024622167,0.0003741436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063630147,0.00019156633,0.00040246896,0.00033467598,0.00023311835,0.00010258559,0.0013443872,0.00015021588,0.0005066588],"category_scores_gemma":[0.0008478597,0.0001689649,0.00033883334,0.003305118,0.00021856626,0.00047275296,0.00036405883,0.00026724345,0.000059526777],"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":[0.00008247417,0.0008887241,0.0010405213,0.000106522435,0.0032219393,0.00020934656,0.000691979,0.00063781097,0.008255186,0.03936474,0.08416763,0.86133313],"study_design_scores_gemma":[0.0007142699,0.0000330707,0.00039818016,0.000026816844,0.0004363656,0.0000029332784,0.000066929235,0.98676515,0.003028306,0.0057326932,0.0026032066,0.00019210116],"about_ca_topic_score_codex":0.0000314175,"about_ca_topic_score_gemma":0.000083202736,"teacher_disagreement_score":0.9861273,"about_ca_system_score_codex":0.000082959166,"about_ca_system_score_gemma":0.00021867079,"threshold_uncertainty_score":0.6890189},"labels":[],"label_agreement":null},{"id":"W4416535178","doi":"10.1016/j.media.2025.103883","title":"Extreme cardiac MRI analysis under respiratory motion: Results of the CMRxMotion challenge","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Science and Technology Innovation Plan Of Shanghai Science and Technology Commission; International Science and Technology Cooperation Programme; National Key Research and Development Program of China; Shanghai Rising-Star Program; Fudan University; Science and Technology Commission of Shanghai Municipality; Key Technologies Research and Development Program; Shanghai Municipal Education Commission; National Natural Science Foundation of China","keywords":"Robustness (evolution); Segmentation; Magnetic resonance imaging; Cardiac magnetic resonance; Deep learning; Image quality; Motion (physics)","score_opus":0.021587272762190364,"score_gpt":0.30409470299316577,"score_spread":0.2825074302309754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416535178","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":[0.1440739,0.016364198,0.4947011,0.11321804,0.0020204578,0.001234053,0.0004216902,0.00044775053,0.22751881],"genre_scores_gemma":[0.99527204,0.00029583374,0.00026200857,0.0016544182,0.00022131465,0.000014999328,0.00012285636,0.000011872029,0.0021446417],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996916,0.00036232284,0.0007389628,0.00048539042,0.0012254043,0.00027190152],"domain_scores_gemma":[0.99738866,0.0005055323,0.00019206335,0.0012349178,0.00046025042,0.00021859091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015268825,0.00019535123,0.0009968771,0.00096287753,0.00011766132,0.000026457601,0.00023313862,0.00019597553,0.00031206536],"category_scores_gemma":[0.0031465976,0.00013730675,0.0020119091,0.0064151534,0.00037473082,0.00006515177,0.00014839215,0.00038461044,0.00001871283],"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":[0.0003897116,0.0024381457,0.7799684,0.00041331007,0.087294415,0.00017249254,0.00084044004,0.0025786636,0.0012677115,0.0019987507,0.07687735,0.045760617],"study_design_scores_gemma":[0.0019414173,0.000045174987,0.898204,0.00015612143,0.07788098,0.0000012822479,0.00040138318,0.00825117,0.0017400415,0.00019109555,0.010968579,0.00021876034],"about_ca_topic_score_codex":0.0003518207,"about_ca_topic_score_gemma":0.000117174684,"teacher_disagreement_score":0.85119814,"about_ca_system_score_codex":0.000113098096,"about_ca_system_score_gemma":0.00023833482,"threshold_uncertainty_score":0.55992067},"labels":[],"label_agreement":null},{"id":"W4417483711","doi":"10.1016/j.media.2025.103915","title":"DTG: Dual transformers-based generative adversarial networks for retinal 2D/3D OCT image classification","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Université de Montréal; Hôpital Maisonneuve-Rosemont","funders":"Université de Montréal","keywords":"Optical coherence tomography; Pattern recognition (psychology); Convolutional neural network; Classifier (UML); Transformer; Deep learning; Contextual image classification; Generative grammar","score_opus":0.014424068914491498,"score_gpt":0.3305399040351102,"score_spread":0.3161158351206187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417483711","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":[0.011178692,0.00025579613,0.9606717,0.022427412,0.00015024844,0.00039327206,0.00003361431,0.00012076765,0.0047684624],"genre_scores_gemma":[0.94812274,0.00019011147,0.03893189,0.0052287355,0.0010493438,0.00018807175,0.0021109853,0.00004655731,0.004131553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99662185,0.00023074943,0.0008574456,0.0007832379,0.00093657925,0.0005701654],"domain_scores_gemma":[0.9978653,0.00043131105,0.00019351559,0.00048237023,0.000601376,0.00042612178],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013620527,0.00035279684,0.0010660617,0.0008449926,0.00030727885,0.00011721941,0.00021431867,0.00027849013,0.0012711802],"category_scores_gemma":[0.001294287,0.00028901006,0.0013458093,0.0027689857,0.0005204763,0.00016452404,0.000029402856,0.00055913016,0.000023663366],"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":[0.013025475,0.0063542766,0.07340231,0.0019598724,0.06336787,0.0021946353,0.001538154,0.0043993006,0.118273996,0.0017186807,0.21154,0.50222546],"study_design_scores_gemma":[0.0033639811,0.0001796143,0.004168721,0.00013023273,0.019227557,0.0000068426234,0.0003498378,0.96382856,0.0028833244,0.00004963259,0.005512132,0.00029954533],"about_ca_topic_score_codex":0.00016915197,"about_ca_topic_score_gemma":0.00007556854,"teacher_disagreement_score":0.95942926,"about_ca_system_score_codex":0.00016401196,"about_ca_system_score_gemma":0.0004782797,"threshold_uncertainty_score":0.9999562},"labels":[],"label_agreement":null},{"id":"W4417530586","doi":"10.1016/j.media.2025.103920","title":"GloW-VSNet: A scribble-based weakly supervised framework for global-view vitiligo lesion segmentation","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"melanin and skin pigmentation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"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 British Columbia; Vancouver Coastal Health","funders":"Shenzhen Science and Technology Innovation Program; Natural Sciences and Engineering Research Council of Canada; Shenzhen University; University of British Columbia; National Natural Science Foundation of China","keywords":"Segmentation; Vitiligo; Pattern recognition (psychology); Image segmentation; Cluster analysis; Noise (video); Consistency (knowledge bases); Market segmentation","score_opus":0.012372055032451954,"score_gpt":0.3405596409592523,"score_spread":0.3281875859268003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417530586","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":[0.076773115,0.0006485045,0.9191976,0.0019460556,0.00014658144,0.0002964135,0.000055965887,0.000022414155,0.0009133094],"genre_scores_gemma":[0.9196238,0.000473061,0.06638863,0.00790818,0.0002528175,0.00022143169,0.004563278,0.000019702105,0.0005491189],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984978,0.00012893259,0.00034967283,0.00042899465,0.00035868422,0.00023592998],"domain_scores_gemma":[0.99923944,0.00006602252,0.000075167976,0.00033567564,0.00014344136,0.00014024012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041109655,0.00016412909,0.000275217,0.00009876303,0.00011933826,0.000057228368,0.00022055832,0.00024864532,0.00041508756],"category_scores_gemma":[0.00053927687,0.0001491614,0.00033724494,0.00073171884,0.00007981784,0.0000066679354,0.0000505278,0.000075899385,0.000011468484],"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":[0.0012539363,0.0013353154,0.03449994,0.0009626428,0.0057335575,0.000048572834,0.00013251856,0.00049451075,0.6028008,0.004478611,0.059545256,0.28871432],"study_design_scores_gemma":[0.008151804,0.00079112966,0.017093655,0.0005975985,0.007695777,0.0000053215213,0.001002022,0.122399665,0.79571265,0.009371957,0.035835236,0.0013431843],"about_ca_topic_score_codex":0.000060644095,"about_ca_topic_score_gemma":0.0001382672,"teacher_disagreement_score":0.852809,"about_ca_system_score_codex":0.000044825712,"about_ca_system_score_gemma":0.00015913349,"threshold_uncertainty_score":0.60826254},"labels":[],"label_agreement":null},{"id":"W7117294798","doi":"10.1016/j.media.2025.103925","title":"Spatial-frequency dual-constrained Mamba diffusion model for cross-modal generation from CFP to FFA","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Science and Technology Innovation Plan Of Shanghai Science and Technology Commission; Science and Technology Commission of Shanghai Municipality; Shanghai Pudong New Area Health Commission; National Natural Science Foundation of China","keywords":"Noise reduction; Feature (linguistics); Pattern recognition (psychology); Constraint (computer-aided design); Retinal; Wavelet; Gamut; Convolution (computer science)","score_opus":0.01580299769263544,"score_gpt":0.3460638778647273,"score_spread":0.3302608801720919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117294798","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":[0.32327837,0.00010619065,0.66137767,0.014137983,0.000065476364,0.00020497214,0.00008413664,0.00006583252,0.00067937246],"genre_scores_gemma":[0.95511883,0.00004491216,0.032394014,0.004350287,0.00046533174,0.000087489214,0.0014582372,0.000022663498,0.0060582375],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720204,0.000078058634,0.000742337,0.00074090273,0.00083683064,0.00039981055],"domain_scores_gemma":[0.9982224,0.0001585069,0.00011592506,0.0006220793,0.00037241133,0.0005086379],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006179897,0.00027349376,0.0008600867,0.00068191474,0.00022366666,0.00014415958,0.00018864396,0.00019709399,0.0010428245],"category_scores_gemma":[0.0017723498,0.00022420604,0.0008179963,0.0014647477,0.00019522206,0.000120777855,0.00009239789,0.0002585459,0.000041203148],"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":[0.0008718829,0.002468429,0.22916412,0.00030709876,0.016222188,0.0009372592,0.00129977,0.0055053607,0.53812885,0.0017200866,0.034185305,0.16918966],"study_design_scores_gemma":[0.0014238005,0.00005541369,0.009778101,0.00007819215,0.0061497227,0.0000029651121,0.00003874564,0.9779052,0.0031725885,0.00091145956,0.00027146735,0.00021232893],"about_ca_topic_score_codex":0.00244557,"about_ca_topic_score_gemma":0.00064231147,"teacher_disagreement_score":0.97239983,"about_ca_system_score_codex":0.00010971263,"about_ca_system_score_gemma":0.00028129516,"threshold_uncertainty_score":0.99987036},"labels":[],"label_agreement":null},{"id":"W7117463490","doi":"10.1016/j.media.2025.103927","title":"Multi-cancer framework with cancer-aware attention and adversarial mutual-information minimization for whole slide image classification","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"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":"Israel Innovation Authority; Technion-Israel Institute of Technology; Ministry of Science and Technology, Israel; Israel Science Foundation; University of Toronto; Israel Cancer Association; Israel Cancer Association USA","keywords":"Leverage (statistics); Generalizability theory; Adversarial system; Regularization (linguistics); Scalability; Focus (optics); Construct (python library); Minification","score_opus":0.01122081343523291,"score_gpt":0.30923430122183787,"score_spread":0.29801348778660497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117463490","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":[0.0029382503,0.00010700744,0.98878455,0.007218103,0.00033043002,0.00036622133,0.00003526164,0.00015343181,0.00006675361],"genre_scores_gemma":[0.52147704,0.0006792091,0.47263852,0.002163391,0.0004389001,0.0012795489,0.00039179073,0.000025434563,0.00090617675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982291,0.000081268074,0.00043202142,0.00045436277,0.0005602931,0.00024293987],"domain_scores_gemma":[0.9985404,0.00017312975,0.00027861472,0.000402696,0.0004817386,0.00012340539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039145487,0.00017394837,0.00028965058,0.00047739566,0.00026222307,0.00030231656,0.00036888695,0.00019911263,0.00008561709],"category_scores_gemma":[0.00035132494,0.00015317467,0.00012655352,0.0020837875,0.00013513325,0.0018229235,0.00010036275,0.0002052484,0.000009381133],"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":[0.0005782098,0.00038893626,0.025990121,0.0007453057,0.0035733308,0.0000094239695,0.0028693916,0.0035928967,0.0056878603,0.0028395222,0.020415166,0.93330985],"study_design_scores_gemma":[0.0011607965,0.000043728352,0.01783955,0.00012430071,0.0007552353,7.2939775e-7,0.00019209248,0.97496927,0.00071639026,0.00022236138,0.0037917907,0.00018375958],"about_ca_topic_score_codex":0.00037092163,"about_ca_topic_score_gemma":0.00044718536,"teacher_disagreement_score":0.97137636,"about_ca_system_score_codex":0.0002489673,"about_ca_system_score_gemma":0.00024464508,"threshold_uncertainty_score":0.6246282},"labels":[],"label_agreement":null},{"id":"W898114428","doi":"10.1016/j.media.2015.06.004","title":"Adaptive multi-level conditional random fields for detection and segmentation of small enhanced pathology in medical images","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NeuroRx Research (Canada); McGill University; McGill University Health Centre","funders":"","keywords":"Segmentation; Artificial intelligence; Pattern recognition (psychology); Voxel; Conditional random field; Computer science; Image segmentation; Probabilistic logic; Context (archaeology); Graphical model; Computer vision","score_opus":0.0446848011939909,"score_gpt":0.3367311574336902,"score_spread":0.2920463562396993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W898114428","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":[0.009205055,0.00007858218,0.9893856,0.00085827877,0.000066485634,0.0002851909,0.000017441402,0.00005758593,0.000045748737],"genre_scores_gemma":[0.5860499,0.0000595135,0.41280803,0.0007664427,0.00003889586,0.00016606657,0.0000590479,0.000006072433,0.000045979694],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975832,0.00032643863,0.00060395105,0.00040960504,0.00086165697,0.00021513186],"domain_scores_gemma":[0.99825346,0.00066742924,0.00019530856,0.00020550929,0.00032131595,0.00035696157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020060756,0.00013622118,0.0004417815,0.00044767105,0.000039422597,0.00003128897,0.0003759855,0.0002137874,0.00016353982],"category_scores_gemma":[0.0034879402,0.00011969706,0.00012457563,0.00072297576,0.00033369692,0.00032192786,0.00014395136,0.00021933409,0.0000030036567],"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":[0.0003207419,0.00078125956,0.0009419683,0.00009648836,0.0006414049,0.00029363675,0.0028218625,0.0000665308,0.036414277,0.0002722089,0.0007711006,0.9565785],"study_design_scores_gemma":[0.00972088,0.00043425645,0.006083446,0.00005553778,0.00028233713,0.000035409485,0.0005129227,0.6201459,0.35927457,0.0031446188,0.000008447206,0.00030163242],"about_ca_topic_score_codex":0.00012955512,"about_ca_topic_score_gemma":0.000434973,"teacher_disagreement_score":0.9562769,"about_ca_system_score_codex":0.00005026993,"about_ca_system_score_gemma":0.00017787382,"threshold_uncertainty_score":0.48811045},"labels":[],"label_agreement":null}]}