{"meta":{"query_hash":"a0222b839387","filters":{"venue":"Journal of Medical Artificial Intelligence"},"cohort_total":5,"direct_labels_cover":0,"predictions_cover":5,"exported":5,"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/a0222b839387","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Medical+Artificial+Intelligence"},"results":[{"id":"W2887167108","doi":"10.21037/jmai.2018.07.02","title":"Machine learning and serious games: opportunities and requirements for detection of mild cognitive impairment","year":2018,"lang":"en","type":"article","venue":"Journal of Medical Artificial Intelligence","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","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 Manitoba","funders":"","keywords":"Cognitive impairment; Cognition; Computer science; Psychology; Cognitive psychology; Neuroscience","score_opus":0.08365877540182218,"score_gpt":0.35260653585190294,"score_spread":0.26894776045008073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887167108","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":[0.9277458,0.00026567842,0.070168324,0.0011849226,0.00020217725,0.0002678357,0.0000056623608,0.0000060288303,0.00015353427],"genre_scores_gemma":[0.9970022,0.0019965435,0.00048557957,0.0003064631,0.0001606527,0.000006190074,8.798525e-7,0.000010754338,0.000030727624],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980771,0.00014158517,0.0006378457,0.00020714353,0.00070649874,0.00022980754],"domain_scores_gemma":[0.9988683,0.00032334423,0.00040423765,0.000051287578,0.000053488435,0.00029934445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023255092,0.000117637224,0.00022222861,0.0000716673,0.00017090669,0.000019973008,0.00011110286,0.00008663074,0.0006273372],"category_scores_gemma":[0.000928103,0.00009943067,0.000043113174,0.0000846444,0.00087832916,0.0001921415,0.00012791037,0.00026456048,0.000009518102],"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":[0.0003609071,0.00015569161,0.004028746,0.00005067011,0.000037190002,0.000021815113,0.0019971798,0.000007815992,0.00797449,0.000072122246,0.000016563847,0.9852768],"study_design_scores_gemma":[0.0021609985,0.023911698,0.037950862,0.0029804932,0.000509246,0.00092255074,0.0404978,0.10345607,0.73996943,0.021462,0.024888372,0.0012904858],"about_ca_topic_score_codex":0.00011488802,"about_ca_topic_score_gemma":0.0001190853,"teacher_disagreement_score":0.9839863,"about_ca_system_score_codex":0.000072966555,"about_ca_system_score_gemma":0.000035859794,"threshold_uncertainty_score":0.68689024},"labels":[],"label_agreement":null},{"id":"W2909847169","doi":"10.21037/jmai.2019.01.01","title":"Promises and limitations of deep learning for medical image segmentation","year":2019,"lang":"en","type":"article","venue":"Journal of Medical Artificial Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Deep learning; Computer vision; Segmentation; Image (mathematics); Computer science","score_opus":0.043449062245623435,"score_gpt":0.36256073053461263,"score_spread":0.3191116682889892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909847169","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":[0.58381057,0.000516384,0.39611408,0.018375589,0.00047514564,0.00030081332,4.918653e-7,0.000012301445,0.00039465664],"genre_scores_gemma":[0.9815713,0.0012704509,0.016209137,0.00047108968,0.0003967542,0.000004480082,0.0000043138625,0.000016036322,0.000056438013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973783,0.00008200524,0.00089250255,0.00013836562,0.0013324188,0.0001764131],"domain_scores_gemma":[0.9971366,0.001628051,0.00038532488,0.00007666478,0.0003500252,0.00042331743],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024094454,0.00009868558,0.0003879659,0.00015153563,0.000053590382,0.000024416742,0.00016993945,0.00013638465,0.00052844494],"category_scores_gemma":[0.018544067,0.00007399959,0.00012717405,0.00014455487,0.0002600372,0.00011666428,0.00004044278,0.0007045718,0.000009816397],"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":[0.00030096833,0.00023530854,0.0026913271,0.00025190116,0.00008520801,0.00005150995,0.0009134556,0.0001259567,0.012037587,0.0034931193,0.0001157906,0.9796979],"study_design_scores_gemma":[0.0020072,0.004531862,0.003989395,0.002434116,0.00044123968,0.0017213312,0.00726337,0.9093662,0.045248512,0.01281531,0.009807581,0.00037388387],"about_ca_topic_score_codex":0.00000878825,"about_ca_topic_score_gemma":0.0000048364063,"teacher_disagreement_score":0.979324,"about_ca_system_score_codex":0.00002623638,"about_ca_system_score_gemma":0.0002618643,"threshold_uncertainty_score":0.98972315},"labels":[],"label_agreement":null},{"id":"W2974630971","doi":"10.21037/jmai.2019.09.04","title":"Artificial intelligence and colorectal polyp detection","year":2019,"lang":"en","type":"article","venue":"Journal of Medical Artificial Intelligence","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; University of British Columbia","funders":"","keywords":"Colorectal cancer; Colonoscopy; Incidence (geometry); Medicine; Cancer; Cause of death; Internal medicine; Oncology; General surgery; Disease","score_opus":0.028525185784608133,"score_gpt":0.33072993466385864,"score_spread":0.30220474887925053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974630971","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":[0.8253472,0.0004291079,0.16056728,0.011419946,0.0016523533,0.00019409935,7.4535575e-7,0.000028204338,0.0003610656],"genre_scores_gemma":[0.9958224,0.0004273437,0.0016671653,0.0008222405,0.0011838304,0.000002011689,0.0000011349061,0.000024445673,0.000049398583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964459,0.00011638704,0.0012191423,0.00028237386,0.0015701094,0.00036609266],"domain_scores_gemma":[0.99803203,0.00045713357,0.00038314672,0.00016922934,0.0002540701,0.00070438796],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024912078,0.00020052391,0.00055216294,0.00029209102,0.000096543234,0.000079962294,0.00030368587,0.00025585745,0.0012513429],"category_scores_gemma":[0.0031592401,0.00015473191,0.00018815346,0.00037888592,0.000386127,0.00016320778,0.00009887455,0.0015530711,0.00015845505],"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":[0.0005808212,0.00026462472,0.0018017483,0.000073101975,0.00007215658,0.00029602743,0.00042051557,0.00012043459,0.01612269,0.007306185,0.000051350034,0.9728903],"study_design_scores_gemma":[0.00031593684,0.006140815,0.004463661,0.0017796321,0.0003835228,0.0105067175,0.004005126,0.5681772,0.32524076,0.071750954,0.00641401,0.00082165183],"about_ca_topic_score_codex":0.00006613024,"about_ca_topic_score_gemma":0.000017263977,"teacher_disagreement_score":0.97206867,"about_ca_system_score_codex":0.00008182642,"about_ca_system_score_gemma":0.0002910991,"threshold_uncertainty_score":0.9996616},"labels":[],"label_agreement":null},{"id":"W4381987696","doi":"10.21037/jmai-23-10","title":"Approximating femoral neck bone mineral density from hand, knee, and pelvis X-rays using deep learning","year":2023,"lang":"en","type":"article","venue":"Journal of Medical Artificial Intelligence","topic":"Body Composition Measurement Techniques","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Activation Laboratories; University of Toronto; AUG Signals (Canada); Sunnybrook Health Science Centre; Health Sciences Centre","funders":"","keywords":"Pelvis; Bone mineral; Femoral neck; Medicine; Orthodontics; Geology; Radiology; Anatomy; Computer science; Osteoporosis; Internal medicine","score_opus":0.0887147532116295,"score_gpt":0.34555590967411615,"score_spread":0.2568411564624866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381987696","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":[0.8302786,0.00026327552,0.16705163,0.0018719548,0.00028419663,0.00012538725,8.0558266e-7,0.0000802511,0.000043904023],"genre_scores_gemma":[0.9694048,0.00011899688,0.029179364,0.00024471796,0.0010014527,0.0000016417343,0.000006410976,0.000022869046,0.000019743682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965955,0.00015350098,0.0010593315,0.0002244298,0.0016547557,0.00031247846],"domain_scores_gemma":[0.9983821,0.00023671397,0.00043403707,0.00013190848,0.00037274443,0.0004424824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022229988,0.00017643145,0.0005317713,0.00027795517,0.00022747873,0.00010504104,0.00015559023,0.00019500405,0.00023571534],"category_scores_gemma":[0.0023422185,0.00014879943,0.00014211769,0.00043711462,0.00026625104,0.00016979332,0.00012726933,0.0010131273,0.000028514867],"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":[0.00090722495,0.00058977166,0.037651844,0.00021412587,0.00024171446,0.0033651728,0.0032662258,0.00057083106,0.3974708,0.00080177793,0.0006011669,0.5543194],"study_design_scores_gemma":[0.0007991415,0.0014918807,0.010705488,0.002953101,0.00044470228,0.0023179282,0.0031960316,0.78726107,0.17886211,0.010861684,0.0005593249,0.00054753665],"about_ca_topic_score_codex":0.00008440963,"about_ca_topic_score_gemma":0.000024846655,"teacher_disagreement_score":0.78669024,"about_ca_system_score_codex":0.00008761646,"about_ca_system_score_gemma":0.00014108064,"threshold_uncertainty_score":0.60678643},"labels":[],"label_agreement":null},{"id":"W4404456084","doi":"10.21037/jmai-24-148","title":"The long road ahead: navigating obstacles and building bridges for clinical integration of artificial intelligence technologies","year":2024,"lang":"en","type":"article","venue":"Journal of Medical Artificial Intelligence","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Artificial intelligence; Computer science; Engineering; Architectural engineering; Transport engineering; Construction engineering","score_opus":0.29487668016752616,"score_gpt":0.5312757897015817,"score_spread":0.23639910953405557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404456084","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":[0.55181754,0.013357367,0.39269885,0.038138334,0.0033674526,0.0005183829,0.000007265155,0.00008120422,0.00001360361],"genre_scores_gemma":[0.982901,0.010454613,0.004918654,0.0001361518,0.0015286244,0.000021900254,0.0000044502262,0.000023541626,0.000011091014],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9945716,0.00017251058,0.0032923424,0.00038196155,0.0011425412,0.00043900922],"domain_scores_gemma":[0.9929089,0.004877734,0.00066238455,0.0002841778,0.0009771498,0.0002896577],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0072790477,0.00024037191,0.0006152307,0.00022045986,0.00032969797,0.00021465302,0.0004936527,0.00045125818,0.00003900848],"category_scores_gemma":[0.017425204,0.00015729615,0.00034833016,0.0005909252,0.0012362468,0.00027670237,0.0001011326,0.0015489,0.000012944629],"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":[0.0003248657,0.00016356037,0.0006267707,0.00022689159,0.000072853865,0.0000415232,0.0010451132,0.00002488925,0.001356714,0.03240571,0.00017275925,0.96353835],"study_design_scores_gemma":[0.000028365132,0.0028328453,0.00051471434,0.007387085,0.00033230855,0.0007415256,0.044823915,0.14922902,0.52101326,0.2704452,0.0022559196,0.0003958807],"about_ca_topic_score_codex":0.00015284236,"about_ca_topic_score_gemma":0.00016486186,"teacher_disagreement_score":0.96314245,"about_ca_system_score_codex":0.0001137424,"about_ca_system_score_gemma":0.00081904675,"threshold_uncertainty_score":0.99085146},"labels":[],"label_agreement":null}]}