{"meta":{"query_hash":"4d1828cd258b","filters":{"venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery"},"cohort_total":18,"direct_labels_cover":0,"predictions_cover":18,"exported":18,"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/4d1828cd258b","api":"https://metacan.xera.ac/api/v1/cohort?venue=Wiley+Interdisciplinary+Reviews+Data+Mining+and+Knowledge+Discovery"},"results":[{"id":"W1574923366","doi":"10.1002/widm.1112","title":"Self‐organizing maps for latent semantic analysis of free‐form text in support of public policy analysis","year":2013,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","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":"University of Victoria","funders":"Mitacs; University of Victoria","keywords":"Computer science; Cluster analysis; Information retrieval; Unstructured data; Latent semantic analysis; Context (archaeology); Topic model; Document clustering; Natural language processing; Artificial intelligence; Big data; Data mining","score_opus":0.05294647992264497,"score_gpt":0.3458112725074737,"score_spread":0.2928647925848287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1574923366","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":[0.9304622,0.012942637,0.043728158,0.00081787107,0.00013054672,0.0022306736,0.0042652874,0.00009229166,0.0053303284],"genre_scores_gemma":[0.98969287,0.00083625637,0.004330356,0.000015180702,0.0001438698,0.00014232166,0.0045564193,0.00002911658,0.00025360915],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99691826,0.00018502529,0.0015779936,0.00072763755,0.00015486569,0.00043624593],"domain_scores_gemma":[0.99676335,0.00027304108,0.00078971026,0.0018786443,0.00017591662,0.00011931301],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001375656,0.00036336956,0.0019438161,0.0018774146,0.0001135534,0.00013342431,0.0011617738,0.00006670981,0.00025460738],"category_scores_gemma":[0.00007278374,0.0003013354,0.0007473648,0.004503287,0.0001253261,0.0010857183,0.0030798789,0.00013190538,0.000006282533],"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":[0.000026807447,0.0014034876,0.7903975,0.0010551789,0.014391103,0.0000012891605,0.0063889013,0.00002618128,0.00037223278,0.0021482373,0.039056417,0.14473265],"study_design_scores_gemma":[0.0049926834,0.0016830715,0.30969223,0.0051999106,0.109607756,0.000009728428,0.01495937,0.48282897,0.00084101286,0.016292205,0.048421364,0.0054716943],"about_ca_topic_score_codex":0.00038545424,"about_ca_topic_score_gemma":0.00097393343,"teacher_disagreement_score":0.48280278,"about_ca_system_score_codex":0.00005881788,"about_ca_system_score_gemma":0.00012666003,"threshold_uncertainty_score":0.99994385},"labels":[],"label_agreement":null},{"id":"W1903799253","doi":"10.1002/widm.1094","title":"Bayesian treed response surface models","year":2013,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; Machine learning; Bayesian probability; Artificial intelligence; Model selection; Bayesian linear regression; Tree (set theory); Inference; Gaussian process; Bayesian inference; Data mining; Mathematics; Gaussian","score_opus":0.16156548228287826,"score_gpt":0.4164045060676965,"score_spread":0.25483902378481826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1903799253","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":[0.057896327,0.01727482,0.909988,0.0007322539,0.0005651372,0.0012820356,0.000728722,0.00014654377,0.011386158],"genre_scores_gemma":[0.14403638,0.0030589357,0.8473524,0.000120144534,0.00031143904,0.0001619463,0.000253844,0.00011032877,0.0045946133],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99630064,0.0011135067,0.0009799952,0.00093083177,0.00017320648,0.0005018193],"domain_scores_gemma":[0.9947262,0.0028436265,0.00027551941,0.0018049754,0.000083921455,0.00026576704],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024840892,0.0004571412,0.00097392953,0.00009794775,0.00029489963,0.00038697032,0.0009355801,0.00013701893,0.0002549014],"category_scores_gemma":[0.0016018751,0.00033647782,0.00012422225,0.00027635312,0.00026616853,0.0019348562,0.002907539,0.0002616133,0.00014894723],"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":[0.00047092375,0.00060817803,0.00047312258,0.0014556258,0.00013274088,0.000037123216,0.007392695,6.553577e-7,0.00089136034,0.025216023,0.30862328,0.65469825],"study_design_scores_gemma":[0.0014747736,0.0008625135,0.0011527205,0.0106729055,0.0004962527,0.00020409502,0.005011088,0.10806894,0.00009065106,0.8555965,0.014261031,0.0021085467],"about_ca_topic_score_codex":0.0000123917025,"about_ca_topic_score_gemma":0.00003608944,"teacher_disagreement_score":0.83038044,"about_ca_system_score_codex":0.000046130688,"about_ca_system_score_gemma":0.00009730018,"threshold_uncertainty_score":0.99990875},"labels":[],"label_agreement":null},{"id":"W1963913493","doi":"10.1002/widm.22","title":"Ensembles of case‐based reasoning classifiers in high‐dimensional biological domains","year":2011,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"AI-based Problem Solving and Planning","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":"Discovery Centre; Ontario Institute for Cancer Research","funders":"","keywords":"Classifier (UML); Computer science; Artificial intelligence; Disjoint sets; Case-based reasoning; Random subspace method; Cluster analysis; Machine learning; Cascading classifiers; Ensemble learning; Feature selection; Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.1307819076493614,"score_gpt":0.33222079092292583,"score_spread":0.20143888327356443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963913493","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":[0.87936205,0.043974515,0.07200371,0.00016784537,0.00084981485,0.0005406909,0.00030404195,0.00012565147,0.0026717053],"genre_scores_gemma":[0.9085434,0.00047730852,0.090494476,0.000063580716,0.00006608186,0.000028881454,0.00023875343,0.000016319369,0.00007120828],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99715513,0.0005110884,0.0008419327,0.00094137056,0.00012862361,0.00042182943],"domain_scores_gemma":[0.9977061,0.0004887446,0.00034616826,0.0012765537,0.000044311295,0.00013810159],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001971457,0.00033704602,0.00071212515,0.00025606275,0.00024001235,0.00009046283,0.0011517889,0.00014896832,0.000017715387],"category_scores_gemma":[0.00018540779,0.00025622785,0.00010474435,0.00045352706,0.00023399781,0.0011147421,0.0029153351,0.0002725841,0.000013022719],"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":[0.0008878019,0.0028839177,0.1749084,0.0028705837,0.0003711937,0.007770031,0.059929237,0.00012916139,0.002127427,0.018006891,0.061040126,0.66907525],"study_design_scores_gemma":[0.012018963,0.007953429,0.042942002,0.09893575,0.000772829,0.011291557,0.01314515,0.7698427,0.003322688,0.00903835,0.021622913,0.009113661],"about_ca_topic_score_codex":0.00005596755,"about_ca_topic_score_gemma":0.00013563385,"teacher_disagreement_score":0.7697135,"about_ca_system_score_codex":0.000038374958,"about_ca_system_score_gemma":0.0001584842,"threshold_uncertainty_score":0.999989},"labels":[],"label_agreement":null},{"id":"W1980062933","doi":"10.1002/widm.1047","title":"Machine learning methods for predicting tumor response in lung cancer","year":2012,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Lung Cancer Treatments and Mutations","field":"Medicine","cited_by":21,"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":"","keywords":"Radiation therapy; Lung cancer; Medicine; Cancer; Personalization; Treatment of lung cancer; Radiation treatment planning; Intensive care medicine; Oncology; Bioinformatics; Internal medicine; Computer science; Biology","score_opus":0.07363155616305792,"score_gpt":0.4794801865354944,"score_spread":0.40584863037243646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980062933","genre_codex":"review","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":[0.29801098,0.68728536,0.008228067,0.0006786979,0.0011389405,0.0021003173,0.00067024986,0.000075215015,0.0018121589],"genre_scores_gemma":[0.8917029,0.025158266,0.066582635,0.00032211648,0.0016717223,0.002290106,0.0032682724,0.0001764529,0.008827564],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979325,0.00045820366,0.00059023325,0.00051077077,0.000070516886,0.00043776425],"domain_scores_gemma":[0.9983672,0.0006671356,0.00020202833,0.0005434819,0.00004053043,0.00017962398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027276024,0.0002761991,0.0006735657,0.00018085707,0.0002570645,0.000060082748,0.00018622479,0.000059863673,0.000034949557],"category_scores_gemma":[0.0007475543,0.00020526252,0.00011007964,0.0002464354,0.00006762057,0.0009861398,0.0008734477,0.00022593745,0.0000042735614],"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":[0.0029136378,0.0007381823,0.47444513,0.0029833121,0.00039656612,0.00001595493,0.024393044,0.0000054225784,0.00091362937,0.000033767403,0.009401577,0.48375976],"study_design_scores_gemma":[0.010965626,0.0022859976,0.09149513,0.03984348,0.0054039075,0.0005664996,0.011903323,0.1382879,0.00029395553,0.000053933596,0.697205,0.0016952404],"about_ca_topic_score_codex":0.000024688641,"about_ca_topic_score_gemma":0.00006068726,"teacher_disagreement_score":0.68780345,"about_ca_system_score_codex":0.00020324922,"about_ca_system_score_gemma":0.00018820121,"threshold_uncertainty_score":0.8370363},"labels":[],"label_agreement":null},{"id":"W1987111416","doi":"10.1002/widm.30","title":"Density‐based clustering","year":2011,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":810,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Outlier; Data set; Computer science; Data mining; Cluster (spacecraft); Set (abstract data type); Single-linkage clustering; DBSCAN; Pattern recognition (psychology); Correlation clustering; CURE data clustering algorithm; Artificial intelligence","score_opus":0.15651942522856147,"score_gpt":0.37289851207918545,"score_spread":0.216379086850624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987111416","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":[0.0066762785,0.016310107,0.96860325,0.00014696637,0.0008680844,0.0004533319,0.00005175355,0.00021215131,0.0066780658],"genre_scores_gemma":[0.31578565,0.0047388356,0.6746106,0.00031073397,0.00062315335,0.0002075017,0.00030540433,0.00012468827,0.0032934076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970751,0.00027331882,0.0006131985,0.0012499513,0.00020890927,0.00057953584],"domain_scores_gemma":[0.9964978,0.00018032374,0.00018629528,0.002831871,0.00007036999,0.00023334534],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012494486,0.00037461307,0.00057226873,0.00022612745,0.0003815498,0.00034927213,0.0029981998,0.00008797894,0.00001849859],"category_scores_gemma":[0.00016543314,0.00031519527,0.000102412836,0.00046731948,0.00020035559,0.0032462743,0.015582321,0.0002762846,0.0001242306],"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":[0.00006613664,0.00029849267,0.0007937707,0.00065538235,0.000048339218,0.00015009147,0.007479899,0.000005711416,0.0002462685,0.00026354502,0.0074636955,0.9825287],"study_design_scores_gemma":[0.0015717172,0.00089897605,0.0026832288,0.0073540076,0.00010172589,0.000534586,0.0013463655,0.9414206,0.0008216036,0.0011046543,0.040119674,0.0020428589],"about_ca_topic_score_codex":0.000008572723,"about_ca_topic_score_gemma":0.000095553456,"teacher_disagreement_score":0.9804858,"about_ca_system_score_codex":0.00006526555,"about_ca_system_score_gemma":0.00012082917,"threshold_uncertainty_score":0.99993},"labels":[],"label_agreement":null},{"id":"W1994891592","doi":"10.1002/widm.31","title":"Mining uncertain data","year":2011,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":59,"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":"Association rule learning; Key (lock); Affinity analysis; Computer science; Uncertain data; Data mining; Associative property; Probabilistic logic; Database transaction; K-optimal pattern discovery; Task (project management); Process (computing); Knowledge extraction; Data science; Artificial intelligence; Database; Engineering; Mathematics","score_opus":0.2056452550767086,"score_gpt":0.37378523516306994,"score_spread":0.16813998008636133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994891592","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":[0.017680584,0.14730968,0.76388806,0.00140081,0.003500306,0.0018483542,0.0049188975,0.0008444527,0.058608837],"genre_scores_gemma":[0.043811835,0.015923658,0.9242844,0.00042608846,0.0011189934,0.00027048547,0.009617159,0.00011777852,0.0044295783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996368,0.00020375423,0.00082714274,0.0019087724,0.00017627963,0.00051603274],"domain_scores_gemma":[0.99190104,0.00021100625,0.0003132478,0.0072959904,0.000049701262,0.00022901305],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0019085425,0.0004201336,0.0006201417,0.00016136144,0.00050061033,0.0005521415,0.007952281,0.000095519244,0.000030999305],"category_scores_gemma":[0.00019642623,0.00034381897,0.00006931986,0.0005886029,0.00021862265,0.0060684895,0.029120442,0.0002111112,0.00016463285],"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":[0.000009015727,0.00023996325,0.00047048106,0.00014361611,0.0000482912,0.000024279201,0.0069999653,7.4100406e-8,0.000024662117,0.0013058387,0.16632254,0.8244113],"study_design_scores_gemma":[0.00095790054,0.00046272803,0.0018255471,0.0053468747,0.0003007074,0.00049928157,0.005342634,0.28315327,0.00006195145,0.0012048528,0.6987407,0.0021035357],"about_ca_topic_score_codex":0.0000252897,"about_ca_topic_score_gemma":0.00010563793,"teacher_disagreement_score":0.8223077,"about_ca_system_score_codex":0.000029016572,"about_ca_system_score_gemma":0.00015536799,"threshold_uncertainty_score":0.99990135},"labels":[],"label_agreement":null},{"id":"W2026082078","doi":"10.1002/widm.17","title":"Introducing WIREs Data Mining and Knowledge Discovery","year":2011,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","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 Alberta","funders":"","keywords":"Knowledge extraction; Cluster analysis; Data science; Computer science; Data mining; Data stream mining; Artificial intelligence","score_opus":0.07684688907758393,"score_gpt":0.32811955453709646,"score_spread":0.25127266545951255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026082078","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":[0.5815375,0.3837514,0.009902617,0.00017877563,0.0022263585,0.0010405546,0.002101795,0.000059345268,0.01920169],"genre_scores_gemma":[0.8740069,0.07537696,0.024496041,0.00029296946,0.0037842817,0.00009687096,0.014916098,0.00018820078,0.00684166],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99674016,0.00020380734,0.0009450133,0.0014526154,0.00009852897,0.000559874],"domain_scores_gemma":[0.9961537,0.000079217156,0.0003512239,0.0031564487,0.000049976337,0.00020942348],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0016432896,0.00054897304,0.0007291454,0.000113864524,0.0004034726,0.00034391513,0.001618371,0.00022896731,0.000017439139],"category_scores_gemma":[0.00019982655,0.0004507416,0.000099565455,0.00017153216,0.00039628835,0.00038985288,0.015373796,0.00021851988,0.000021426462],"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":[0.0003406039,0.0004029932,0.0050018304,0.0013032628,0.00039073516,0.000016346992,0.011582839,9.056801e-7,0.0027091675,0.000112669404,0.31309336,0.66504526],"study_design_scores_gemma":[0.004343461,0.002604997,0.0053874827,0.013775456,0.0016723516,0.0010901394,0.023317015,0.030690705,0.0014653463,0.000525816,0.9095636,0.0055636526],"about_ca_topic_score_codex":0.000012048129,"about_ca_topic_score_gemma":0.00045425506,"teacher_disagreement_score":0.65948164,"about_ca_system_score_codex":0.000019338677,"about_ca_system_score_gemma":0.00016651589,"threshold_uncertainty_score":0.9997944},"labels":[],"label_agreement":null},{"id":"W2069255081","doi":"10.1002/widm.40","title":"Fuzzy association rule mining framework and its application to effective fuzzy associative classification","year":2011,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Western University","funders":"","keywords":"Association rule learning; Data mining; Fuzzy classification; Artificial intelligence; Fuzzy set operations; Fuzzy logic; Computer science; Neuro-fuzzy; Defuzzification; Machine learning; Fuzzy rule; Fuzzy set; Classifier (UML); Fuzzy number; Fuzzy clustering; Pattern recognition (psychology); Fuzzy control system","score_opus":0.06305845491350742,"score_gpt":0.3417930014364239,"score_spread":0.27873454652291646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069255081","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":[0.21439926,0.041283466,0.69667166,0.0029851436,0.0020833355,0.0064104013,0.0023116516,0.0007227068,0.03313234],"genre_scores_gemma":[0.6774543,0.006834169,0.3069936,0.0005601042,0.0010804996,0.003097192,0.0018585281,0.000119456374,0.0020021703],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99686205,0.0003425706,0.0006987105,0.0014275984,0.00022856629,0.00044052265],"domain_scores_gemma":[0.9969053,0.00066336215,0.0006116478,0.0014235242,0.00016226899,0.00023386814],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021003755,0.00038289354,0.00059913134,0.00019711434,0.00057495706,0.0004116947,0.0012315974,0.0002021172,0.0000033227175],"category_scores_gemma":[0.0007779156,0.00035079618,0.00007446211,0.0007755583,0.00005512388,0.0027488074,0.004140799,0.0002787736,0.00015562115],"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":[0.00002343047,0.00031433292,0.0044449386,0.00017035054,0.000112708294,0.0000027005963,0.030411886,1.9952465e-7,0.00039440242,0.010152288,0.014061409,0.93991137],"study_design_scores_gemma":[0.0038538438,0.003199786,0.46138605,0.020399002,0.0018127788,0.00023167118,0.028122233,0.28143704,0.0015359931,0.051222723,0.13801853,0.008780336],"about_ca_topic_score_codex":0.0000098188975,"about_ca_topic_score_gemma":0.000039234816,"teacher_disagreement_score":0.931131,"about_ca_system_score_codex":0.000204167,"about_ca_system_score_gemma":0.00007020217,"threshold_uncertainty_score":0.9998944},"labels":[],"label_agreement":null},{"id":"W2130674512","doi":"10.1002/widm.1131","title":"Biomedical informatics and panomics for evidence‐based radiation therapy","year":2014,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"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":"Canadian Institutes of Health Research","keywords":"Informatics; Translational bioinformatics; Radiation therapy; Health informatics; Computer science; Medical physics; Data science; Personalized medicine; Precision medicine; Interface (matter); Bioinformatics; Translational research informatics; Radiation oncology; Systems biology; Health informatics tools; Medicine; Genomics; Engineering informatics; Pathology; Biology; Genome; Internal medicine","score_opus":0.08553935413831011,"score_gpt":0.39373271732820714,"score_spread":0.30819336318989704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130674512","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":[0.5933101,0.18077958,0.2144439,0.006535922,0.0013879198,0.0022671544,0.00020647133,0.00012994288,0.0009389977],"genre_scores_gemma":[0.7242819,0.15740606,0.10389657,0.0045442744,0.0032809419,0.00031471162,0.0052388865,0.00015583253,0.00088080455],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984014,0.00013398138,0.00068443787,0.00038873253,0.00012840651,0.00026302747],"domain_scores_gemma":[0.99807936,0.0007522929,0.00023611182,0.00066053553,0.000041653686,0.00023004539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002286842,0.000242911,0.0006304909,0.00015010059,0.00021822056,0.00015877957,0.00026409517,0.000098470955,0.000007309739],"category_scores_gemma":[0.0012969159,0.00017281686,0.00008963044,0.00013190649,0.00026648835,0.0007753019,0.0005737076,0.00021880309,0.0000064385204],"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":[0.00017657314,0.00010884916,0.004737082,0.0011461183,0.000041909458,0.0000012833561,0.0013790262,8.394742e-7,0.00021142531,0.00004822548,0.02298231,0.96916634],"study_design_scores_gemma":[0.0027850762,0.0011533413,0.0022840174,0.008029062,0.00024847744,0.00009613898,0.00064286106,0.54053193,0.000028257859,0.00009207205,0.4437367,0.00037207123],"about_ca_topic_score_codex":0.0000019592399,"about_ca_topic_score_gemma":0.0000016503428,"teacher_disagreement_score":0.9687943,"about_ca_system_score_codex":0.00003227427,"about_ca_system_score_gemma":0.00011606616,"threshold_uncertainty_score":0.7047267},"labels":[],"label_agreement":null},{"id":"W2131550814","doi":"10.1002/widm.1068","title":"Reverse engineering of gene regulatory networks from biological data","year":2012,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Saskatchewan","funders":"","keywords":"Biological network; Gene regulatory network; Biological data; Reverse engineering; Computer science; Inference; Network topology; Data mining; Data science; Machine learning; Artificial intelligence; Computational biology; Biology; Bioinformatics; Gene","score_opus":0.06458627543732233,"score_gpt":0.3164829617760331,"score_spread":0.25189668633871076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131550814","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":[0.6528322,0.33557752,0.0097898645,0.000021474534,0.0005796324,0.00021716909,0.0008102724,0.000016347773,0.0001555263],"genre_scores_gemma":[0.95634377,0.019583223,0.0069478774,0.00003623885,0.0019198516,0.00001688978,0.01490612,0.00004367698,0.00020237596],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99775904,0.00021502402,0.00066352566,0.00086472475,0.0000951587,0.00040252807],"domain_scores_gemma":[0.99625534,0.00006403259,0.0002716327,0.0031970784,0.000032934287,0.0001790049],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001230123,0.00033783852,0.00064055703,0.000062869476,0.000099558245,0.00003568957,0.0012599265,0.0002141596,0.000020890284],"category_scores_gemma":[0.00016031117,0.00027693997,0.00013344068,0.00017863639,0.00016338636,0.000105847954,0.0066451123,0.00012963281,0.000009075033],"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":[0.00048259678,0.0011690714,0.11559342,0.00058710383,0.0020633035,0.000015683296,0.001648342,0.00041896172,0.20967376,0.000051821135,0.39623645,0.27205947],"study_design_scores_gemma":[0.0031952707,0.0011346461,0.09475028,0.0077696773,0.0036824932,0.00031583526,0.0031473297,0.117472194,0.01693245,0.000040128474,0.7461799,0.005379826],"about_ca_topic_score_codex":0.000004364824,"about_ca_topic_score_gemma":0.000019683424,"teacher_disagreement_score":0.3499434,"about_ca_system_score_codex":0.000014359192,"about_ca_system_score_gemma":0.000038442857,"threshold_uncertainty_score":0.9999683},"labels":[],"label_agreement":null},{"id":"W3045868447","doi":"10.1002/widm.1383","title":"Predicting disease‐associated genes: Computational methods, databases, and evaluations","year":2020,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Saskatchewan; Princess Margaret Cancer Centre; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Identification (biology); Computer science; Computational model; Focus (optics); Machine learning; Data science; Set (abstract data type); Point (geometry); Biological data; Modelling biological systems; Artificial intelligence; Bioinformatics; Systems biology; Biology","score_opus":0.09762632397675337,"score_gpt":0.40110903499238115,"score_spread":0.3034827110156278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045868447","genre_codex":"review","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":[0.20966513,0.50508493,0.27381027,0.0015799828,0.0006673261,0.0013756927,0.006226441,0.00006652995,0.0015237281],"genre_scores_gemma":[0.7148184,0.06330925,0.12825647,0.002200917,0.0026667267,0.0002045659,0.087416254,0.00015189864,0.0009754847],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984,0.00024985458,0.0004997371,0.00056625606,0.00008009356,0.00020411315],"domain_scores_gemma":[0.9989637,0.00009156408,0.00020031804,0.00047588174,0.000046653775,0.0002218952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090847694,0.00022323814,0.000310824,0.000028831537,0.00027479787,0.0001151826,0.0003093145,0.00005998315,0.000009395798],"category_scores_gemma":[0.0003692217,0.00019456085,0.00006112673,0.000107315194,0.00012826218,0.00007285317,0.0029573513,0.00010764628,0.0000064608216],"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":[0.00028224138,0.00027672775,0.030082585,0.0012385512,0.0005084592,0.0000076093884,0.0041120206,0.00025536804,0.0020071133,0.00020846905,0.15611361,0.80490726],"study_design_scores_gemma":[0.0018537168,0.0005653025,0.008631499,0.0025463048,0.0008315134,0.000050725725,0.0029439002,0.7304514,0.00006195552,0.00042613177,0.25032228,0.0013152737],"about_ca_topic_score_codex":0.0000013924903,"about_ca_topic_score_gemma":0.000026399453,"teacher_disagreement_score":0.80359197,"about_ca_system_score_codex":0.00000966367,"about_ca_system_score_gemma":0.00011791596,"threshold_uncertainty_score":0.7933961},"labels":[],"label_agreement":null},{"id":"W3082381194","doi":"10.1002/widm.1388","title":"Smart city and resilient city: Differences and connections","year":2020,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Smart Cities and Technologies","field":"Engineering","cited_by":62,"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 Key Research and Development Program of China; China Scholarship Council","keywords":"Smart city; Computer science; Hazard; Focus (optics); Urban planning; Architectural engineering; Data science; Sociology; Regional science; Civil engineering; Computer security; Internet of Things; Engineering","score_opus":0.09336277250994358,"score_gpt":0.3048798354911904,"score_spread":0.21151706298124684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082381194","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":[0.8809704,0.113901414,0.000799649,0.00081549806,0.00037413771,0.00025707943,0.00033422644,0.00025189496,0.0022956815],"genre_scores_gemma":[0.9533109,0.045695964,0.00047650686,0.000057867128,0.0001619088,0.000037928057,0.00009499923,0.000021281865,0.00014266116],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99881494,0.000043812925,0.00035182494,0.00050218764,0.00005947155,0.00022775964],"domain_scores_gemma":[0.9992099,0.00015269013,0.00005155873,0.0004487549,0.000013473897,0.00012364509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020667819,0.00026403216,0.0004953834,0.00006770471,0.0002471315,0.00020507982,0.0002865871,0.000086602675,0.000017972168],"category_scores_gemma":[0.00014346991,0.00021068129,0.000039001574,0.00015940204,0.00026264973,0.00062738865,0.002353093,0.00019766435,0.0000060456637],"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":[0.000095842195,0.00013460082,0.1938511,0.0038003863,0.00035664832,0.00003911631,0.016301591,0.0000034480815,0.00042547839,0.0009686694,0.19662729,0.58739585],"study_design_scores_gemma":[0.002627511,0.001928538,0.13830526,0.011992864,0.0009818625,0.0004640705,0.048358064,0.09051173,0.0003341341,0.0021410626,0.69837034,0.0039845337],"about_ca_topic_score_codex":0.0000056167455,"about_ca_topic_score_gemma":0.0001301324,"teacher_disagreement_score":0.5834113,"about_ca_system_score_codex":0.000013340016,"about_ca_system_score_gemma":0.000011770779,"threshold_uncertainty_score":0.85913336},"labels":[],"label_agreement":null},{"id":"W3137237563","doi":"10.1002/widm.1436","title":"Blockchain networks: Data structures of Bitcoin, Monero, Zcash, Ethereum, Ripple, and Iota","year":2021,"lang":"en","type":"preprint","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Topological and Geometric Data Analysis","field":"Computer Science","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":"University of Manitoba","funders":"National Science Foundation of Sri Lanka","keywords":"Blockchain; Cryptocurrency; Computer science; Asset (computer security); Popularity; Big data; Data science; Computer security; Data mining","score_opus":0.09912994489545705,"score_gpt":0.35639318000931836,"score_spread":0.2572632351138613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137237563","genre_codex":"review","genre_gemma":"empirical","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":[0.06941899,0.78055936,0.1402078,0.000648773,0.0018147688,0.0007455282,0.0059133647,0.00008961053,0.0006018349],"genre_scores_gemma":[0.6160029,0.2737572,0.0810865,0.00030146833,0.0015736996,0.00010923042,0.025771853,0.00011530748,0.0012818343],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99344224,0.00078612095,0.0016166167,0.0032429341,0.00033877313,0.00057330244],"domain_scores_gemma":[0.9888972,0.0006544951,0.001010424,0.009051264,0.00010992182,0.00027666148],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002520871,0.0008255366,0.0022345094,0.00043840625,0.00030072377,0.0010433864,0.0080814455,0.00044221728,0.000050949515],"category_scores_gemma":[0.0006317545,0.0006078763,0.0002412229,0.0010840377,0.00050061557,0.0010357345,0.12977724,0.0008616292,0.0000055889573],"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":[0.00005420556,0.0005778998,0.003352484,0.0030173927,0.0010952542,0.00016523378,0.0037235457,0.00020382731,0.00005013301,0.0007596924,0.09565628,0.8913441],"study_design_scores_gemma":[0.0016634434,0.0007509309,0.008530874,0.020392464,0.003098566,0.0006229184,0.0051832744,0.8606544,0.000036649573,0.005209009,0.08891283,0.004944624],"about_ca_topic_score_codex":0.00010152581,"about_ca_topic_score_gemma":0.00045289312,"teacher_disagreement_score":0.88639945,"about_ca_system_score_codex":0.000031759893,"about_ca_system_score_gemma":0.00019385532,"threshold_uncertainty_score":0.9999936},"labels":[],"label_agreement":null},{"id":"W4234482552","doi":"10.1002/widm.16","title":"Rough clustering","year":2011,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","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":"Saint Mary's University","funders":"","keywords":"Cluster analysis; Rough set; Computer science; Fuzzy clustering; Data mining; Similarity (geometry); Artificial intelligence; Self-organizing map; Set (abstract data type); Pattern recognition (psychology); Image (mathematics)","score_opus":0.15803284078610344,"score_gpt":0.3397054162188211,"score_spread":0.18167257543271767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234482552","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":[0.017799677,0.18619615,0.53504103,0.0006056209,0.005086207,0.0012871287,0.00023454076,0.0005721884,0.25317746],"genre_scores_gemma":[0.633905,0.03145389,0.3283932,0.000691792,0.0012754325,0.00019047444,0.00051537796,0.00010960837,0.0034652585],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976039,0.0001816688,0.0006203306,0.0010418305,0.00011726389,0.00043504144],"domain_scores_gemma":[0.9972286,0.000081376784,0.0001983866,0.0023070308,0.000028381375,0.00015618908],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00096291176,0.0003424989,0.0005436946,0.000114643306,0.0003610189,0.00037184168,0.0026277069,0.000084221465,0.000026307844],"category_scores_gemma":[0.00006132058,0.00025481236,0.000106471736,0.00032220528,0.00012812152,0.0034872373,0.012501846,0.00017774598,0.00015435946],"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":[0.000028204537,0.00026286105,0.00096390524,0.000318449,0.000047844987,0.000067390276,0.01863318,5.242906e-7,0.000022588983,0.0016129751,0.04680566,0.9312364],"study_design_scores_gemma":[0.0030476728,0.0025768345,0.012851556,0.015066553,0.0004555524,0.0018628428,0.0061614905,0.32084042,0.00012382603,0.010552384,0.62067544,0.0057854075],"about_ca_topic_score_codex":0.000009504374,"about_ca_topic_score_gemma":0.000070392445,"teacher_disagreement_score":0.925451,"about_ca_system_score_codex":0.000026245381,"about_ca_system_score_gemma":0.00005418567,"threshold_uncertainty_score":0.9999904},"labels":[],"label_agreement":null},{"id":"W4285781363","doi":"10.1002/widm.1343","title":"Density‐based clustering","year":2019,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","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":"University of Alberta","funders":"","keywords":"Computer science; Cluster analysis; Artificial intelligence","score_opus":0.06673601290054507,"score_gpt":0.3667671650858934,"score_spread":0.30003115218534837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285781363","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":[0.042607516,0.025625624,0.92201144,0.00060308276,0.0018624732,0.0010120642,0.000082919505,0.00027652868,0.005918353],"genre_scores_gemma":[0.6197993,0.005663145,0.3584121,0.0005886046,0.0009509553,0.0002115989,0.0007197741,0.00018294789,0.013471547],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969705,0.00025850654,0.0005830735,0.0013590276,0.00025306587,0.00057583046],"domain_scores_gemma":[0.99610555,0.00030845174,0.00018078218,0.0031443934,0.00006590065,0.00019491774],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012614767,0.0003697553,0.00064107816,0.00021829629,0.00026689708,0.000580901,0.0028156743,0.000088943394,0.00002057156],"category_scores_gemma":[0.00012919359,0.0003118947,0.000106272084,0.0004833117,0.00011612133,0.0032793113,0.015987229,0.00029751405,0.00039361793],"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":[0.000064549014,0.00022501152,0.0020308855,0.0013738865,0.000054090717,0.0000754631,0.002631999,0.00009062741,0.0010146779,0.00023642399,0.01032604,0.9818764],"study_design_scores_gemma":[0.00091261644,0.00036855426,0.00076262304,0.004225052,0.000028729604,0.0001698976,0.00043279282,0.94368577,0.00017753014,0.00018897792,0.048179116,0.00086835766],"about_ca_topic_score_codex":0.000003631454,"about_ca_topic_score_gemma":0.000045052937,"teacher_disagreement_score":0.981008,"about_ca_system_score_codex":0.00008435822,"about_ca_system_score_gemma":0.00013629267,"threshold_uncertainty_score":0.9999333},"labels":[],"label_agreement":null},{"id":"W4388731451","doi":"10.1002/widm.1523","title":"The use of gene expression datasets in feature selection research: 20 years of inherent bias?","year":2023,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","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":"Dalhousie University","funders":"Global Affairs Canada; Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Feature selection; Preprocessor; Computer science; Selection (genetic algorithm); Feature (linguistics); Machine learning; Data mining; DNA microarray; Data pre-processing; Artificial intelligence; Biological data; Data science; Bioinformatics; Gene; Gene expression; Biology; Genetics","score_opus":0.28383519852189343,"score_gpt":0.42745225951905635,"score_spread":0.14361706099716293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388731451","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":[0.94751483,0.04963511,0.00022696196,0.00023261391,0.00037530783,0.00060768606,0.0012813351,0.000010251608,0.000115881114],"genre_scores_gemma":[0.8715091,0.10637575,0.0015227849,0.000025120808,0.00040163676,0.00022524636,0.016234718,0.000054960783,0.0036507268],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983686,0.0004594455,0.00039514955,0.00044507443,0.00013910746,0.00019262171],"domain_scores_gemma":[0.99866813,0.00012302653,0.00018257307,0.00092442596,0.000057135378,0.000044729888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013365588,0.00011730041,0.00021686552,0.0001422049,0.000120380384,0.00005104235,0.00045359624,0.000097812816,0.0000024556173],"category_scores_gemma":[0.00039946826,0.000083428204,0.000048328642,0.0004842014,0.00015553687,0.000054103326,0.0017570277,0.00013849133,0.0000042745637],"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":[0.00018868127,0.000087705404,0.0024431092,0.00014449604,0.000018162737,0.0000012023414,0.0005391685,0.000007984364,0.36140752,0.000005864047,0.52238274,0.112773396],"study_design_scores_gemma":[0.00056238804,0.00036458002,0.012911083,0.002919542,0.000028342158,0.000010591605,0.001981296,0.0010514834,0.080970086,0.00002720662,0.89891225,0.0002611292],"about_ca_topic_score_codex":0.0000050563067,"about_ca_topic_score_gemma":0.00019691997,"teacher_disagreement_score":0.37652954,"about_ca_system_score_codex":0.000012808091,"about_ca_system_score_gemma":0.00008247451,"threshold_uncertainty_score":0.34021035},"labels":[],"label_agreement":null},{"id":"W4396913259","doi":"10.1002/widm.1546","title":"Decoding cognitive health using machine learning: A comprehensive evaluation for diagnosis of significant memory concern","year":2024,"lang":"en","type":"preprint","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":15,"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 Manitoba; Health Sciences Centre","funders":"Science and Engineering Research Board; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Ministry of Electronics and Information technology; Eisai; Department of Science and Technology, Ministry of Science and Technology, India; Pfizer; Novartis Pharmaceuticals Corporation; Council of Scientific and Industrial Research, India; 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":"Support vector machine; Artificial intelligence; Machine learning; Computer science; Neuroimaging; Feature selection; Population; Psychology; Medicine; Psychiatry","score_opus":0.29457584341650345,"score_gpt":0.49571017216395513,"score_spread":0.20113432874745168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396913259","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":[0.57718,0.40758598,0.0017621947,0.0004375943,0.0008538644,0.0069175945,0.004363032,0.000050116294,0.0008495746],"genre_scores_gemma":[0.9191517,0.058402825,0.002017774,0.00011000821,0.00064041704,0.0015580322,0.017281216,0.00013319848,0.0007048111],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99506885,0.0009509849,0.0014306078,0.0015408809,0.00047988776,0.00052881014],"domain_scores_gemma":[0.99648917,0.00097190135,0.00083603174,0.0007835196,0.0006617495,0.0002576529],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0036607361,0.00061858754,0.0019303842,0.00046030615,0.00030678487,0.00020269591,0.00040467083,0.00019535799,0.000099321776],"category_scores_gemma":[0.0009161771,0.00050936034,0.00041843057,0.00027629206,0.00036439495,0.00028773994,0.008547128,0.0008771648,0.000013585613],"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":[0.0013960783,0.0011785292,0.03455594,0.053774565,0.0019755894,0.000048907998,0.012382258,0.000011547199,0.00045905676,0.00001361929,0.013533965,0.88066995],"study_design_scores_gemma":[0.009394375,0.007374169,0.004164401,0.364904,0.015749697,0.00025619258,0.043704756,0.53844315,0.0015661002,0.0009986701,0.011079065,0.0023654678],"about_ca_topic_score_codex":0.00005865068,"about_ca_topic_score_gemma":0.00007194268,"teacher_disagreement_score":0.8783045,"about_ca_system_score_codex":0.00024120009,"about_ca_system_score_gemma":0.0015009484,"threshold_uncertainty_score":0.9997358},"labels":[],"label_agreement":null},{"id":"W4402576412","doi":"10.1002/widm.1554","title":"From <scp>3D</scp> point‐cloud data to explainable geometric deep learning: State‐of‐the‐art and future challenges","year":2024,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":17,"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":"Austrian Science Fund; Amt der NÖ Landesregierung","keywords":"Point cloud; Computer science; Cloud computing; State (computer science); Deep learning; Point (geometry); Data science; Artificial intelligence; Algorithm; Geometry","score_opus":0.046510086094736613,"score_gpt":0.3084817585943116,"score_spread":0.261971672499575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402576412","genre_codex":"review","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":[0.40610564,0.5544401,0.0035725085,0.0034929372,0.0025838881,0.001506508,0.0016109339,0.00018207349,0.02650541],"genre_scores_gemma":[0.5938399,0.33748427,0.019400539,0.00031434937,0.005387063,0.00011055412,0.006161117,0.0003353094,0.03696692],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99740124,0.00023746515,0.0005269875,0.0012775637,0.00020766085,0.00034907152],"domain_scores_gemma":[0.9970709,0.00045813515,0.0001459774,0.0021353893,0.000011951413,0.0001776216],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0011120085,0.00032193688,0.0004791838,0.00012374594,0.00037967082,0.00026545028,0.0012852472,0.00008076555,0.000043132048],"category_scores_gemma":[0.00027733413,0.00022717142,0.00006677979,0.0007815308,0.00025158425,0.0011301581,0.010040122,0.00032386117,0.0003235549],"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":[0.0000062061667,0.000078102545,0.00047156488,0.0002850771,0.000045598244,0.0000072885387,0.01285874,0.000009072992,0.00021041233,0.000010848931,0.18273236,0.80328476],"study_design_scores_gemma":[0.0001041985,0.00009696751,0.0035716922,0.0013235618,0.000118057505,0.000041450403,0.005382746,0.005940328,0.000033908207,0.00014011687,0.9830718,0.00017519444],"about_ca_topic_score_codex":0.000036582365,"about_ca_topic_score_gemma":0.00034154358,"teacher_disagreement_score":0.8031095,"about_ca_system_score_codex":0.000055654084,"about_ca_system_score_gemma":0.000029272338,"threshold_uncertainty_score":0.99796647},"labels":[],"label_agreement":null}]}