{"meta":{"query_hash":"2ffd0b89d978","filters":{"venue":"Annual Review of Biomedical Data Science"},"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/2ffd0b89d978","api":"https://metacan.xera.ac/api/v1/cohort?venue=Annual+Review+of+Biomedical+Data+Science"},"results":[{"id":"W3087893815","doi":"10.1146/annurev-biodatasci-092820-114757","title":"Ethical Machine Learning in Healthcare","year":2021,"lang":"en","type":"article","venue":"Annual Review of Biomedical Data Science","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":479,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"National Institute on Minority Health and Health Disparities","keywords":"Health care; Pipeline (software); Ethical issues; Selection (genetic algorithm); Frame (networking); Healthcare system","score_opus":0.19240625568719402,"score_gpt":0.518899363750473,"score_spread":0.3264931080632789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087893815","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036259969,0.045909386,0.035220154,0.87415045,0.0028750312,0.00005751645,0.0000714591,0.00005300675,0.03803705],"genre_scores_gemma":[0.49373662,0.09224717,0.03840081,0.34085187,0.019364629,0.00058008434,0.0001879933,0.00023271884,0.014398106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92891985,0.053953115,0.002291261,0.003068164,0.00959992,0.002167666],"domain_scores_gemma":[0.8982011,0.08200955,0.003999,0.0066494993,0.0061201244,0.003020798],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06553072,0.0005211338,0.0009881723,0.0014336421,0.004018919,0.010950272,0.0018216001,0.012016048,0.004743126],"category_scores_gemma":[0.11118262,0.00041990585,0.0007542342,0.0012831991,0.033924613,0.011444943,0.007351228,0.014949558,0.0011241458],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016088958,0.000022955905,0.00059102604,0.00017800796,0.000017861648,0.00008268174,0.0014716887,0.00056797644,0.000060926694,0.9218505,0.027168885,0.04797144],"study_design_scores_gemma":[0.000012136549,0.000019707908,0.00031767724,0.0008600331,0.0000076102438,0.00017532615,0.00074565824,0.00081043196,0.00013217561,0.8835843,0.11331569,0.000019280571],"about_ca_topic_score_codex":0.002196424,"about_ca_topic_score_gemma":0.002079176,"teacher_disagreement_score":0.9344693,"about_ca_system_score_codex":0.006368436,"about_ca_system_score_gemma":0.012735394,"threshold_uncertainty_score":0.3465637},"labels":[],"label_agreement":null},{"id":"W3088213682","doi":"10.1146/annurev-biodatasci-092820-033938","title":"Probabilistic Machine Learning for Healthcare","year":2021,"lang":"en","type":"preprint","venue":"Annual Review of Biomedical Data Science","topic":"Machine Learning in Healthcare","field":"Computer Science","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":"Vector Institute","funders":"National Institute of Biomedical Imaging and Bioengineering; National Heart, Lung, and Blood Institute","keywords":"Probabilistic logic; Machine learning; Computer science; Artificial intelligence; Generative grammar; Pipeline (software); Health care; Statistical model","score_opus":0.0634074103074424,"score_gpt":0.40393777739137143,"score_spread":0.34053036708392903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088213682","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026212705,0.17641824,0.7344178,0.05153031,0.0031318604,0.00009458814,0.001115574,0.0010484537,0.029621905],"genre_scores_gemma":[0.30372933,0.2659435,0.36799988,0.012261606,0.01636687,0.0007057723,0.0032820057,0.00072640105,0.028984692],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970958,0.0014696436,0.00011260623,0.00044307837,0.00077804184,0.00010080258],"domain_scores_gemma":[0.9931456,0.0052510216,0.00025668024,0.0005505464,0.00060681946,0.00018926992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004806476,0.0010618379,0.0013554695,0.0016630739,0.0005770928,0.0035118535,0.0013644308,0.0031828799,0.008233107],"category_scores_gemma":[0.016845586,0.000565612,0.00094710226,0.0020404535,0.0023902308,0.003921225,0.002272271,0.0054952414,0.0032893727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044773005,0.000039552946,0.0010814092,0.0007305613,0.00012554457,0.00011390265,0.00013237899,0.034454446,0.00028140313,0.68878764,0.05329898,0.22090934],"study_design_scores_gemma":[0.000010916781,0.000016943173,0.00029523516,0.00025373095,0.000015049147,0.00008444153,0.00002633024,0.039296567,0.00011892809,0.8988251,0.061031893,0.00002496999],"about_ca_topic_score_codex":0.002539893,"about_ca_topic_score_gemma":0.0013500217,"teacher_disagreement_score":0.008233107,"about_ca_system_score_codex":0.0021493644,"about_ca_system_score_gemma":0.002063523,"threshold_uncertainty_score":0.027542472},"labels":[],"label_agreement":null},{"id":"W4205275616","doi":"10.1146/annurev-biodatasci-092820-112713","title":"Neoantigen Controversies","year":2021,"lang":"en","type":"review","venue":"Annual Review of Biomedical Data Science","topic":"Immunotherapy and Immune Responses","field":"Immunology and Microbiology","cited_by":19,"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 Cancer Institute; National Institutes of Health; Mark Foundation For Cancer Research; U.S. National Library of Medicine; Canadian Institute for Advanced Research","keywords":"Immunotherapy; Immune system; Biology; Computational biology; Mutation; Genome; Immunology; Genetics; Gene","score_opus":0.04828805774457154,"score_gpt":0.3864174976505118,"score_spread":0.33812943990594024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205275616","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010571836,0.9947589,0.00015704111,0.0028054125,0.00094950956,0.0000018824492,0.0000086141545,0.000005481038,0.0012074142],"genre_scores_gemma":[0.0014002271,0.991559,0.000195462,0.0038265754,0.0020340306,0.0000066993475,0.000025838646,0.0000043168848,0.00094781653],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99928576,0.00016629913,0.000086418135,0.00014721445,0.00025429853,0.000060026905],"domain_scores_gemma":[0.9975325,0.0017204995,0.0002172903,0.00007330803,0.0003266705,0.00012971471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021918276,0.00074948714,0.0013637586,0.0022144746,0.00055801007,0.0024357487,0.001394172,0.0026996918,0.004371403],"category_scores_gemma":[0.003985526,0.00026965392,0.00057014724,0.002451381,0.002371648,0.0042348295,0.0015312136,0.0041716327,0.0024785073],"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":[0.00011519053,0.00005484582,0.00030462974,0.013510129,0.00007890284,0.0006631401,0.00029963284,0.0003079415,0.0018765248,0.0410008,0.076716,0.8650723],"study_design_scores_gemma":[0.0000069706325,0.000033667344,0.00030203414,0.0043186992,0.000042151583,0.0020038697,0.00015706834,0.000037358055,0.00043559496,0.012153887,0.9804951,0.000013583637],"about_ca_topic_score_codex":0.00065479334,"about_ca_topic_score_gemma":0.0007394352,"teacher_disagreement_score":0.004371403,"about_ca_system_score_codex":0.0012339249,"about_ca_system_score_gemma":0.0023281567,"threshold_uncertainty_score":0.014623821},"labels":[],"label_agreement":null},{"id":"W4404349303","doi":"10.1146/annurev-biodatasci-040324-030052","title":"Spatial Transcriptomics Brings New Challenges and Opportunities for Trajectory Inference","year":2024,"lang":"en","type":"review","venue":"Annual Review of Biomedical Data Science","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","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":"University of British Columbia","funders":"","keywords":"Granularity; Slicing; Trajectory; Inference; Computer science; Data science; Porting; Data mining; Point (geometry); Spatial analysis; Big data; Artificial intelligence; Mathematics; World Wide Web; Statistics","score_opus":0.18259250018667267,"score_gpt":0.3853224184956924,"score_spread":0.2027299183090197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404349303","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079049,0.85757035,0.12800856,0.005806862,0.0013978397,0.000048868933,0.0009971097,0.00049800787,0.00488194],"genre_scores_gemma":[0.006778487,0.9090949,0.07558164,0.0023225565,0.0019151609,0.0001743857,0.0015493724,0.00025533908,0.0023281581],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982541,0.00047371633,0.00012281988,0.0005208316,0.0005558608,0.00007270789],"domain_scores_gemma":[0.9873546,0.0101272175,0.00037775797,0.0006331709,0.0013160519,0.00019123871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060013426,0.0013881333,0.0027465366,0.003327804,0.0006999452,0.003926084,0.0031613775,0.0026269446,0.0041958694],"category_scores_gemma":[0.009683893,0.0010991571,0.001895118,0.0045968452,0.0025450275,0.005355772,0.0024003934,0.0050906767,0.0036484997],"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":[0.000056086665,0.000038862956,0.0018949508,0.016159398,0.00036114658,0.00024005158,0.00038831637,0.006664807,0.00554637,0.08974478,0.03504959,0.8438555],"study_design_scores_gemma":[0.000014774548,0.00006512877,0.0019935905,0.004490625,0.00021256256,0.0008802423,0.00032910873,0.009076206,0.0039091166,0.110762894,0.8680952,0.00017046017],"about_ca_topic_score_codex":0.0036759984,"about_ca_topic_score_gemma":0.00506215,"teacher_disagreement_score":0.0060013426,"about_ca_system_score_codex":0.0016200012,"about_ca_system_score_gemma":0.0032749807,"threshold_uncertainty_score":0.03173852},"labels":[],"label_agreement":null},{"id":"W4407730739","doi":"10.1146/annurev-biodatasci-103123-095824","title":"Evaluation and Regulation of Artificial Intelligence Medical Devices for Clinical Decision Support","year":2025,"lang":"en","type":"review","venue":"Annual Review of Biomedical Data Science","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Health Economics","funders":"National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute","keywords":"Enthusiasm; Optimism; Health care; Equity (law); Patient safety; Risk analysis (engineering); Psychology; Knowledge management; Business; Computer science; Political science","score_opus":0.5002733274395434,"score_gpt":0.6473847839691036,"score_spread":0.14711145652956015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407730739","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010837204,0.9952057,0.0005872729,0.0016835314,0.0003123275,0.000038889157,0.000026979253,0.000007996299,0.002028906],"genre_scores_gemma":[0.0024097748,0.9938328,0.0015004815,0.0013795428,0.000384318,0.0001027043,0.000051162315,0.000005540093,0.00033363546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98381436,0.007674707,0.0023015055,0.0008013848,0.0050693923,0.00033861905],"domain_scores_gemma":[0.95338166,0.037478417,0.00343272,0.00096440397,0.0043928777,0.00034984233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019464891,0.0009184417,0.0024768244,0.0043935776,0.0004353817,0.0034585965,0.0024087331,0.0032880455,0.0043222657],"category_scores_gemma":[0.0406558,0.00051347713,0.0017815611,0.0031219756,0.0024138968,0.0028539656,0.0018239651,0.00353776,0.0013292852],"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":[0.0000997674,0.00005873066,0.00025019076,0.05236433,0.00032219596,0.000081977174,0.00015331953,0.00064844365,0.00040568045,0.029768787,0.01894835,0.8968982],"study_design_scores_gemma":[0.000103734994,0.00017221342,0.0016358239,0.117943116,0.00065297895,0.0005867654,0.00017239484,0.0004782415,0.00086859014,0.01593558,0.86138064,0.00006988863],"about_ca_topic_score_codex":0.0017839583,"about_ca_topic_score_gemma":0.0019777524,"teacher_disagreement_score":0.019464891,"about_ca_system_score_codex":0.0027238023,"about_ca_system_score_gemma":0.007716434,"threshold_uncertainty_score":0.10294145},"labels":[],"label_agreement":null}]}