{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":18,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":18,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"4d1828cd258b","filters":{"venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Hans‐Peter Kriegel","is_ca":false},{"name":"Peer Kröger","is_ca":false},{"name":"Jörg Sander","is_ca":true},{"name":"Arthur Zimek","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1565194252285615,"gpt":0.3728985120791855,"spread":0.216379086850624,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00340053,0.001490543,0.002054716,0.008395691,0.002071257,0.004955584,0.003101084,0.002351815,0.008533414],"category_scores_gemma":[0.01720308,0.0009357687,0.001820197,0.009168972,0.001702363,0.003516115,0.0035317,0.001822484,0.006697941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002795575,"about_ca_system_score_gemma":0.002694284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008082308,"about_ca_topic_score_gemma":0.004981634,"domain_scores_codex":[0.9950125,0.001133185,0.0002726587,0.001141866,0.002168474,0.0002712706],"domain_scores_gemma":[0.9942855,0.001876517,0.0004751302,0.001232438,0.001974573,0.0001558221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002393312,0.0001253394,0.007886333,0.001176343,0.0005308698,0.0003195677,0.0009416512,0.2643835,0.004868445,0.2815238,0.06140286,0.376602],"study_design_scores_gemma":[0.00003969035,0.00006405476,0.003796205,0.000299132,0.0001236625,0.0006647286,0.0003861445,0.6702391,0.006034456,0.222713,0.09544726,0.0001926038],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006066402,0.002601064,0.9721345,0.000663111,0.0002246034,0.0003432082,0.001502978,0.001607541,0.01485662],"genre_scores_gemma":[0.3066771,0.005878679,0.6572748,0.0006545893,0.0004974403,0.0007769049,0.009142983,0.001007373,0.01809016],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008533414,"threshold_uncertainty_score":0.02854711,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Cluster analysis; Artificial intelligence","authors":[{"name":"Ricardo J. G. B. Campello","is_ca":false},{"name":"Peer Kröger","is_ca":false},{"name":"Jörg Sander","is_ca":true},{"name":"Arthur Zimek","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06673601290054507,"gpt":0.3667671650858934,"spread":0.3000311521853484,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003838481,0.00129238,0.00220873,0.007239121,0.00193558,0.005234365,0.00326446,0.002048587,0.005479062],"category_scores_gemma":[0.01620496,0.0009715724,0.001876872,0.008456771,0.002068645,0.004136845,0.003505504,0.002225565,0.004590356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003100173,"about_ca_system_score_gemma":0.002988806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008484232,"about_ca_topic_score_gemma":0.006032702,"domain_scores_codex":[0.9949263,0.001283402,0.0003007831,0.001261996,0.00197574,0.0002517191],"domain_scores_gemma":[0.9935732,0.002282191,0.0005390351,0.001218934,0.002226437,0.0001600937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001408121,0.00009933129,0.007816515,0.001292713,0.0005144815,0.0002478856,0.001063313,0.1986971,0.004724952,0.3514377,0.05352438,0.380441],"study_design_scores_gemma":[0.00002663183,0.00004443609,0.004098123,0.0003759955,0.0001059325,0.0004559251,0.0004699687,0.5812464,0.004608578,0.314015,0.09439316,0.0001597448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.004099802,0.002668845,0.982375,0.0007011472,0.0001699624,0.0001955536,0.001005308,0.0009771847,0.007807297],"genre_scores_gemma":[0.2004357,0.007931127,0.7709983,0.0007484067,0.0005505387,0.0006167406,0.006550762,0.0009230143,0.01124531],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.008484232,"threshold_uncertainty_score":0.02249342,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Shi‐Yao Zhu","is_ca":false},{"name":"Dezhi Li","is_ca":false},{"name":"Haibo Feng","is_ca":true},{"name":"Tiantian Gu","is_ca":false},{"name":"Kasun Hewage","is_ca":true},{"name":"Rehan Sadiq","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09336277250994358,"gpt":0.3048798354911904,"spread":0.2115170629812468,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002989681,0.0002654592,0.0004756056,0.00880732,0.0008169684,0.005548588,0.0004833775,0.0007161989,0.00441311],"category_scores_gemma":[0.009894251,0.0001654704,0.0005804189,0.01512197,0.004272582,0.005924702,0.002717405,0.001168546,0.0002571741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002226399,"about_ca_system_score_gemma":0.002105844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003186981,"about_ca_topic_score_gemma":0.003835255,"domain_scores_codex":[0.996555,0.00142105,0.000376113,0.0004557705,0.001007786,0.0001843794],"domain_scores_gemma":[0.9883392,0.00842993,0.001210732,0.0003381733,0.001420653,0.0002613126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000102905,0.00005042331,0.06100114,0.01127987,0.0005786362,0.0006604595,0.02174385,0.00135057,0.0006842849,0.4553665,0.008055318,0.439126],"study_design_scores_gemma":[0.00001769594,0.0001214682,0.1761604,0.01677138,0.0007679685,0.001840197,0.08277558,0.002324801,0.001225649,0.3623749,0.3554503,0.0001696177],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.2474027,0.5209466,0.02217581,0.0465969,0.001418374,0.0001820341,0.001251255,0.0001116329,0.1599146],"genre_scores_gemma":[0.8826815,0.1090987,0.00370675,0.001493915,0.0003786108,0.00007140623,0.0003116154,0.00002124136,0.002236175],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00880732,"threshold_uncertainty_score":0.01615369,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Carson K. Leung","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2056452550767086,"gpt":0.3737852351630699,"spread":0.1681399800863613,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007411716,0.001068954,0.002249386,0.004720887,0.001573795,0.006130374,0.003655455,0.002234155,0.00296983],"category_scores_gemma":[0.0491953,0.0009751316,0.002010516,0.00725071,0.002205715,0.00996181,0.005582648,0.002440098,0.001084576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009531965,"about_ca_system_score_gemma":0.001310594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001367027,"about_ca_topic_score_gemma":0.001258265,"domain_scores_codex":[0.9872169,0.003375161,0.001569251,0.002289065,0.005087764,0.0004618657],"domain_scores_gemma":[0.9706661,0.01931822,0.002724274,0.004008632,0.002855115,0.0004277183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004502488,0.0002150418,0.02599577,0.002480737,0.001015943,0.004182295,0.001590429,0.2213745,0.002635797,0.2967042,0.01889362,0.4244614],"study_design_scores_gemma":[0.00004319474,0.00008939214,0.001938051,0.00045797,0.0001475722,0.001257471,0.0006828505,0.473299,0.002521902,0.4857137,0.03377276,0.00007609576],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.03349113,0.005203449,0.9452413,0.005333143,0.0003788949,0.000283443,0.002744247,0.0004718639,0.006852497],"genre_scores_gemma":[0.4614255,0.006387497,0.517343,0.001409746,0.001162663,0.0006141305,0.008703843,0.0001378505,0.002815768],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.007411716,"threshold_uncertainty_score":0.03919739,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","authors":[{"name":"Pawan Lingras","is_ca":true},{"name":"Georg Peters","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1580328407861034,"gpt":0.3397054162188211,"spread":0.1816725754327177,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00455,0.001927416,0.003073147,0.007205703,0.001771518,0.007815208,0.003453179,0.002362218,0.01540955],"category_scores_gemma":[0.01402891,0.0007834507,0.002979143,0.007810429,0.001457857,0.003692702,0.003360792,0.001668983,0.01133956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002504504,"about_ca_system_score_gemma":0.002774663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00376345,"about_ca_topic_score_gemma":0.002483388,"domain_scores_codex":[0.9927666,0.001845651,0.0006339521,0.001390201,0.003015583,0.0003479118],"domain_scores_gemma":[0.9954502,0.001219409,0.000386966,0.001147217,0.001688825,0.0001073136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001744994,0.00007182892,0.002099337,0.001558706,0.0005484601,0.0003093874,0.0005268421,0.1461247,0.002320646,0.2743931,0.07033493,0.5015376],"study_design_scores_gemma":[0.000085293,0.0001139584,0.00189791,0.0006224003,0.0002226373,0.000620449,0.0006146003,0.3714744,0.00421786,0.3701199,0.2498414,0.0001691696],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003869543,0.003002388,0.9509876,0.0008551104,0.0004556856,0.0006035947,0.001589863,0.001432954,0.0372032],"genre_scores_gemma":[0.1522773,0.004981334,0.8068827,0.0006350449,0.000546474,0.001094663,0.007618689,0.0005805179,0.02538338],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01540955,"threshold_uncertainty_score":0.05155009,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Keivan Kianmehr","is_ca":true},{"name":"Mehmet Kaya","is_ca":false},{"name":"Abdallah M. ElSheikh","is_ca":true},{"name":"Jamal Jida","is_ca":false},{"name":"Reda Alhajj","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06305845491350742,"gpt":0.3417930014364239,"spread":0.2787345465229165,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004993999,0.0006029322,0.001108749,0.003182098,0.001027048,0.001650505,0.001615134,0.0009727199,0.001669481],"category_scores_gemma":[0.008150985,0.0002921155,0.001194241,0.002681039,0.001146535,0.001696626,0.001123828,0.001072831,0.0004346635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009465434,"about_ca_system_score_gemma":0.001510288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004776614,"about_ca_topic_score_gemma":0.002673996,"domain_scores_codex":[0.9966456,0.001148867,0.0002886343,0.0004919005,0.001284203,0.0001407703],"domain_scores_gemma":[0.9973477,0.001302834,0.0002275734,0.0001740485,0.0008675726,0.00008027849],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001340931,0.0002909097,0.003137926,0.0003057903,0.0002107715,0.0006918834,0.0006837372,0.2626016,0.00521588,0.3225338,0.003495286,0.4006983],"study_design_scores_gemma":[0.000009295232,0.0000321343,0.0002671366,0.00002443257,0.00002318417,0.0001043946,0.00003224262,0.9572064,0.001132992,0.03827092,0.002882792,0.00001408337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00776189,0.0005021964,0.9898723,0.0001841301,0.00003613617,0.00007199076,0.00003627723,0.0001309423,0.001404105],"genre_scores_gemma":[0.2239308,0.0005188477,0.7738146,0.00009996346,0.0001027267,0.0002032936,0.000144961,0.00002528055,0.001159616],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004993999,"threshold_uncertainty_score":0.02641112,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Issam El Naqa","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07363155616305792,"gpt":0.4794801865354944,"spread":0.4058486303724365,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003869288,0.0006761898,0.0009827357,0.002768657,0.0003162855,0.001141655,0.001020702,0.001271751,0.001191169],"category_scores_gemma":[0.01410331,0.0002501648,0.0008024704,0.00170817,0.0005014232,0.0006921692,0.000628347,0.001488588,0.0005801561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008746497,"about_ca_system_score_gemma":0.0009574814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003635101,"about_ca_topic_score_gemma":0.001934324,"domain_scores_codex":[0.9985713,0.0007072975,0.0001497894,0.0002307928,0.0002618402,0.00007901019],"domain_scores_gemma":[0.9899645,0.008491483,0.0006808368,0.0002336962,0.0005227779,0.0001066312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001698631,0.0002282886,0.03114075,0.000237756,0.0002073078,0.0001460919,0.00005043103,0.7214701,0.0008340065,0.00537923,0.003149405,0.2369868],"study_design_scores_gemma":[0.000006952106,0.0000252166,0.001091064,0.00001890679,0.000009131036,0.00002820303,0.00000937067,0.9926106,0.0002314015,0.005582015,0.000381553,0.000005580093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09847089,0.008735287,0.882654,0.00332988,0.0002697842,0.0003326437,0.001507387,0.001202537,0.003497515],"genre_scores_gemma":[0.8153774,0.002175735,0.1771834,0.0004448679,0.00037487,0.0004826819,0.001829793,0.00006741039,0.002063831],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003869288,"threshold_uncertainty_score":0.02046305,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Issam El Naqa","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08553935413831011,"gpt":0.3937327173282071,"spread":0.308193363189897,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0126538,0.0008645469,0.001212638,0.00544891,0.0006435016,0.00674095,0.001901984,0.002842733,0.005138141],"category_scores_gemma":[0.02585529,0.0005387084,0.001193762,0.00840656,0.004406961,0.009034151,0.003979187,0.006028557,0.002041753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002761889,"about_ca_system_score_gemma":0.004318857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001158065,"about_ca_topic_score_gemma":0.000985426,"domain_scores_codex":[0.9940578,0.002951995,0.0005437644,0.0005955394,0.001728896,0.0001219595],"domain_scores_gemma":[0.9724355,0.02176651,0.001326931,0.002225666,0.00177189,0.0004734919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005278501,0.00007911515,0.002470484,0.003424725,0.0001626978,0.0001526415,0.0002751037,0.003860765,0.0008463419,0.4708263,0.03984476,0.4780043],"study_design_scores_gemma":[0.00001585002,0.00004890782,0.001937014,0.003260687,0.00006127684,0.0003458771,0.0003262747,0.01127109,0.0007895422,0.665331,0.3165689,0.00004352449],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003632848,0.3037127,0.5096236,0.1417298,0.003125804,0.0004183598,0.001755409,0.001341536,0.03465979],"genre_scores_gemma":[0.06828666,0.3438624,0.5556625,0.01795554,0.006737553,0.0008273524,0.002102726,0.0003689479,0.00419632],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0126538,"threshold_uncertainty_score":0.06692046,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Anna Saranti","is_ca":false},{"name":"Bastian Pfeifer","is_ca":false},{"name":"Christoph Gollob","is_ca":false},{"name":"Karl Stampfer","is_ca":false},{"name":"Andreas Holzinger","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04651008609473661,"gpt":0.3084817585943116,"spread":0.261971672499575,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002003486,0.0007216914,0.0007748455,0.0009592985,0.0002431049,0.002432082,0.002467616,0.001772049,0.003606732],"category_scores_gemma":[0.006393147,0.0004216798,0.0007381717,0.00179643,0.002322828,0.004443779,0.002378926,0.002779862,0.001415219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001262836,"about_ca_system_score_gemma":0.001010406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006783745,"about_ca_topic_score_gemma":0.004688219,"domain_scores_codex":[0.9993617,0.0002091313,0.00002134157,0.0001447903,0.0002275257,0.00003547945],"domain_scores_gemma":[0.9956077,0.002809225,0.0001720854,0.0007538127,0.0005330457,0.0001241263],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000854763,0.00008625669,0.003463381,0.0009939317,0.0002281856,0.0001231411,0.0001744076,0.2813472,0.002020816,0.1480951,0.04002308,0.5233591],"study_design_scores_gemma":[0.000007382631,0.00002341318,0.0009035465,0.0001725112,0.0000154771,0.00004969696,0.00007214402,0.7198033,0.001233623,0.2466059,0.03108556,0.00002739783],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.02930931,0.03149126,0.8966966,0.02710755,0.0005379395,0.00006635335,0.002782395,0.002637148,0.009371527],"genre_scores_gemma":[0.5147474,0.0523471,0.4098724,0.005054372,0.001922546,0.0002166994,0.007403768,0.0007504383,0.007685279],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.006783745,"threshold_uncertainty_score":0.01348853,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Rahul Sharma","is_ca":false},{"name":"Iman Beheshti","is_ca":true},{"name":"M. Tanveer","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2945758434165034,"gpt":0.4957101721639551,"spread":0.2011343287474517,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003867085,0.001198779,0.001302334,0.00222256,0.0002537107,0.001328201,0.0009241003,0.0008551409,0.0007929213],"category_scores_gemma":[0.01162728,0.0001890614,0.001204254,0.0009489183,0.0002593973,0.0008399112,0.0004865899,0.0008811488,0.0002571613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005077614,"about_ca_system_score_gemma":0.0006364456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002635216,"about_ca_topic_score_gemma":0.003186495,"domain_scores_codex":[0.9987565,0.0004807124,0.000171694,0.0002386326,0.0003059029,0.00004656721],"domain_scores_gemma":[0.9943153,0.003645871,0.0003904466,0.0001852668,0.001332095,0.0001309895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001044065,0.0002676648,0.1662095,0.003475777,0.002855298,0.0001943323,0.0001525754,0.01729412,0.001281343,0.001006769,0.007871879,0.7983466],"study_design_scores_gemma":[0.0003296557,0.00416706,0.2399556,0.007604672,0.01177239,0.002038204,0.0007346387,0.6860559,0.01106359,0.01144033,0.0245097,0.0003282066],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4783305,0.4050582,0.09527157,0.005576129,0.0009579718,0.0005061862,0.005640718,0.001296773,0.007361986],"genre_scores_gemma":[0.9408675,0.0353771,0.01923432,0.0006948101,0.0004828497,0.0002068841,0.002464299,0.00003587175,0.0006363747],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003867085,"threshold_uncertainty_score":0.02045137,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Lizhi Liu","is_ca":true},{"name":"Fang‐Xiang Wu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06458627543732233,"gpt":0.3164829617760331,"spread":0.2518966863387108,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003083751,0.0004823913,0.0005309018,0.002370236,0.0003313026,0.001224783,0.001021577,0.0005198554,0.001019335],"category_scores_gemma":[0.01798254,0.0002990527,0.001202463,0.001713016,0.0008753513,0.00113358,0.001346634,0.001349109,0.0004640421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005465035,"about_ca_system_score_gemma":0.001023348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001229498,"about_ca_topic_score_gemma":0.001433161,"domain_scores_codex":[0.9980458,0.0008135547,0.0001215474,0.0003611427,0.0005962696,0.00006153016],"domain_scores_gemma":[0.9891306,0.007849708,0.0007810675,0.001482859,0.0006865663,0.00006916078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002051023,0.0001980305,0.01410162,0.0008954353,0.0003014314,0.0008301163,0.0003729316,0.3286235,0.02526834,0.1037225,0.002652795,0.5228282],"study_design_scores_gemma":[0.00001579663,0.00003128312,0.001081644,0.00006432563,0.00004302015,0.00026289,0.00008560999,0.8821526,0.01808341,0.0930234,0.005139849,0.00001612917],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02590086,0.0003198186,0.9714039,0.0003552261,0.00003268399,0.00009294321,0.0004075541,0.0006754837,0.0008115828],"genre_scores_gemma":[0.2450379,0.0008646235,0.7505174,0.0001698393,0.0000561702,0.0001653494,0.002248829,0.00009102884,0.0008489345],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003083751,"threshold_uncertainty_score":0.01630861,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Hugh Chipman","is_ca":true},{"name":"Edward I. George","is_ca":false},{"name":"Robert B. Gramacy","is_ca":false},{"name":"Robert McCulloch","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1615654822828783,"gpt":0.4164045060676965,"spread":0.2548390237848183,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004411372,0.001060637,0.002137496,0.001466627,0.000447238,0.002401935,0.003066724,0.00281921,0.009895732],"category_scores_gemma":[0.0161201,0.0008434252,0.001621542,0.002266233,0.001001769,0.002186038,0.001405913,0.002081994,0.003078228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001197307,"about_ca_system_score_gemma":0.001211163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005931905,"about_ca_topic_score_gemma":0.004536224,"domain_scores_codex":[0.9972204,0.001381727,0.0001134229,0.000487664,0.0006238323,0.0001729302],"domain_scores_gemma":[0.9952257,0.003394727,0.0004057684,0.0002556827,0.0005989039,0.0001192058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008333032,0.00004688416,0.001673322,0.000264747,0.0001560552,0.00009407075,0.0001453299,0.5349441,0.0005862385,0.4034536,0.008120726,0.05043156],"study_design_scores_gemma":[0.0000188992,0.00001593671,0.0003112864,0.00003555292,0.00002447789,0.00003491158,0.00001405051,0.8518364,0.00007658805,0.1424693,0.005141771,0.00002083594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006359495,0.001453691,0.982969,0.0009361448,0.0001039885,0.00007087347,0.001248852,0.0004472145,0.006410758],"genre_scores_gemma":[0.50743,0.007711989,0.4391696,0.001357087,0.00054918,0.001444647,0.00441535,0.0005840433,0.03733817],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009895732,"threshold_uncertainty_score":0.03310454,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Witold Pedrycz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07684688907758393,"gpt":0.3281195545370965,"spread":0.2512726654595125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005356273,0.0008949119,0.000981005,0.004822283,0.001131379,0.006608853,0.002336733,0.001572449,0.00962285],"category_scores_gemma":[0.0181545,0.0008699637,0.001613969,0.006419112,0.003444727,0.01145679,0.006290936,0.003855094,0.003929699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001239912,"about_ca_system_score_gemma":0.002298545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001291175,"about_ca_topic_score_gemma":0.0009757808,"domain_scores_codex":[0.9957646,0.001097137,0.0004919381,0.0008445581,0.001625014,0.0001766768],"domain_scores_gemma":[0.9892247,0.006272083,0.0005519057,0.002260003,0.001365492,0.0003258499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000235209,0.00002666287,0.0004677911,0.0001883172,0.00004833901,0.0000960111,0.0001149081,0.003842544,0.0003656321,0.8946285,0.009775016,0.09042273],"study_design_scores_gemma":[0.000009452133,0.000009798985,0.0001026657,0.0001125274,0.00002905021,0.0001128636,0.00006597472,0.03031309,0.0009259302,0.859305,0.1089987,0.00001483477],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"editorial","genre_scores_codex":[0.001498699,0.001438602,0.9780011,0.005878421,0.0008176956,0.0000808,0.0005120924,0.001183469,0.01058923],"genre_scores_gemma":[0.06303994,0.005568425,0.9019418,0.003037055,0.001251025,0.0005322217,0.001666343,0.0007203789,0.0222428],"genre_candidate":"editorial","genre_consensus":null,"teacher_disagreement_score":0.00962285,"threshold_uncertainty_score":0.03219163,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Ping Luo","is_ca":true},{"name":"Bolin Chen","is_ca":false},{"name":"Bo Liao","is_ca":false},{"name":"Fang‐Xiang Wu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09762632397675337,"gpt":0.4011090349923812,"spread":0.3034827110156278,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009956671,0.001098266,0.001713248,0.00463331,0.0004767026,0.002877533,0.001983987,0.001189332,0.002640844],"category_scores_gemma":[0.02816241,0.0003245129,0.0009871728,0.00677867,0.0006026519,0.002015416,0.001110671,0.001175711,0.0007218015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001394649,"about_ca_system_score_gemma":0.002191141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008161902,"about_ca_topic_score_gemma":0.004515131,"domain_scores_codex":[0.9960259,0.00174096,0.0003938599,0.0005001657,0.001240478,0.00009864046],"domain_scores_gemma":[0.9807472,0.01620538,0.000469969,0.0007399015,0.001613761,0.0002237488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0008930206,0.0007139686,0.03321322,0.003018826,0.001211246,0.0002321217,0.00008977409,0.3383516,0.000934722,0.0215638,0.02631275,0.5734649],"study_design_scores_gemma":[0.000156236,0.0001481188,0.00305609,0.0003152612,0.0002330386,0.0001327525,0.00007037804,0.9656103,0.001316607,0.02298727,0.005937865,0.00003603173],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.2103693,0.09829155,0.6346725,0.008089847,0.001221463,0.001486561,0.02178327,0.006466387,0.01761895],"genre_scores_gemma":[0.5820759,0.02674563,0.3702436,0.0009870613,0.0003761829,0.001604022,0.01608204,0.000254371,0.001631168],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.009956671,"threshold_uncertainty_score":0.05265653,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Bernie C. Till","is_ca":true},{"name":"Justin Longo","is_ca":true},{"name":"A. R. Dobell","is_ca":true},{"name":"Peter F. Driessen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05294647992264497,"gpt":0.3458112725074737,"spread":0.2928647925848287,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002919586,0.000868012,0.0009218038,0.004722957,0.001189353,0.002552938,0.001685093,0.001208834,0.002490382],"category_scores_gemma":[0.01613243,0.0005259514,0.001461376,0.003663651,0.001307225,0.002840703,0.002347181,0.001968912,0.001500433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001401091,"about_ca_system_score_gemma":0.001616785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004308277,"about_ca_topic_score_gemma":0.00451024,"domain_scores_codex":[0.9979199,0.0009841796,0.000130452,0.0003624287,0.0004762148,0.0001267981],"domain_scores_gemma":[0.9911465,0.006623557,0.0005703642,0.0006457891,0.0008753123,0.000138511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003227226,0.0002290649,0.005114338,0.0004544378,0.0002785299,0.0003487852,0.001548738,0.3571495,0.004159722,0.1319693,0.0139143,0.4845105],"study_design_scores_gemma":[0.000009952957,0.00001321477,0.0005855648,0.00001929608,0.00001223163,0.00003338703,0.0001653764,0.8994825,0.001029776,0.09638742,0.002244008,0.00001725243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007796889,0.0002103015,0.9897534,0.0002594542,0.0000335144,0.00007662829,0.0003172146,0.0008163222,0.000736207],"genre_scores_gemma":[0.2545559,0.0004644914,0.739115,0.0001464337,0.0001835989,0.0007006256,0.002145608,0.0003424056,0.002345846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004722957,"threshold_uncertainty_score":0.0154404,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Bruno Iochins Grisci","is_ca":true},{"name":"Bruno César Feltes","is_ca":false},{"name":"Joice de Faria Poloni","is_ca":false},{"name":"Pedro Henrique Narloch","is_ca":false},{"name":"Márcio Dorn","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2838351985218934,"gpt":0.4274522595190564,"spread":0.1436170609971629,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08791871,0.0007651712,0.002211465,0.004587166,0.0006464325,0.005796011,0.002298246,0.001438248,0.001488091],"category_scores_gemma":[0.1577439,0.0005574349,0.001376036,0.01019191,0.003233196,0.005053633,0.00220738,0.003435479,0.0007311601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002165631,"about_ca_system_score_gemma":0.001805569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001314566,"about_ca_topic_score_gemma":0.001058543,"domain_scores_codex":[0.9375048,0.03960359,0.005695235,0.005384838,0.01135069,0.0004608154],"domain_scores_gemma":[0.7410305,0.2155561,0.009212708,0.01416514,0.01948095,0.000554604],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003500228,0.00009477734,0.02551744,0.006507264,0.00211445,0.0002175672,0.0008527301,0.005218522,0.002054708,0.0434922,0.0252972,0.8882832],"study_design_scores_gemma":[0.0003569476,0.0009097595,0.06152196,0.01648054,0.002209036,0.00189454,0.00138211,0.07083129,0.02123703,0.4093029,0.4132797,0.0005941312],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.05007363,0.4809087,0.3949169,0.05511505,0.005388099,0.0002779419,0.002196888,0.0008817927,0.01024104],"genre_scores_gemma":[0.5834417,0.1894115,0.185283,0.02317584,0.01009917,0.001334297,0.003481225,0.0007568593,0.003016288],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9120813,"threshold_uncertainty_score":0.4649642,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Cüneyt Gürcan Akçora","is_ca":true},{"name":"Yulia R. Gel","is_ca":false},{"name":"Murat Kantarcıoğlu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09912994489545705,"gpt":0.3563931800093184,"spread":0.2572632351138613,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002397797,0.000813767,0.0009989867,0.004443416,0.003074379,0.008428796,0.001903516,0.001712253,0.01192498],"category_scores_gemma":[0.01479611,0.0008403423,0.0009935838,0.007408002,0.004085848,0.01900381,0.003597036,0.003061089,0.002871397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002420155,"about_ca_system_score_gemma":0.002795441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005704311,"about_ca_topic_score_gemma":0.005650478,"domain_scores_codex":[0.9975389,0.0007453176,0.0002808616,0.0005089092,0.0007242103,0.0002017514],"domain_scores_gemma":[0.9927024,0.00275108,0.001155349,0.002068043,0.0008798155,0.0004432774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007090699,0.00002840439,0.0009102594,0.0001450583,0.00001842842,0.0001670379,0.0004532707,0.007195396,0.000411575,0.9524361,0.008001956,0.03016159],"study_design_scores_gemma":[0.0000194709,0.00002273419,0.0003331237,0.0001798448,0.00001737046,0.000245237,0.0001992767,0.03491123,0.001065033,0.8704444,0.09252433,0.00003801812],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.03574146,0.006083803,0.8715752,0.007654107,0.0006804775,0.0009020487,0.01137332,0.003421526,0.06256815],"genre_scores_gemma":[0.4933323,0.009468522,0.4344153,0.001709563,0.0007052873,0.002600725,0.01695172,0.001026508,0.03979],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.01192498,"threshold_uncertainty_score":0.03989303,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Niloofar Arshadi","is_ca":true},{"name":"Igor Jurišica","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1307819076493614,"gpt":0.3322207909229258,"spread":0.2014388832735644,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008395516,0.0007739135,0.001420855,0.004234848,0.0008543211,0.0022032,0.002038153,0.001200386,0.001884934],"category_scores_gemma":[0.02150876,0.0004583741,0.001305004,0.003470349,0.0008706839,0.00279987,0.002359716,0.00147349,0.0004407812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001328203,"about_ca_system_score_gemma":0.001117329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004370361,"about_ca_topic_score_gemma":0.004685128,"domain_scores_codex":[0.9961779,0.001532837,0.000367865,0.0006443143,0.001067828,0.0002091906],"domain_scores_gemma":[0.982419,0.01243789,0.001082488,0.001768658,0.001862477,0.0004294159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001934147,0.0003359143,0.01640696,0.0002127483,0.000423726,0.0003748241,0.0004875634,0.5304404,0.002026839,0.01717772,0.003582752,0.4283372],"study_design_scores_gemma":[0.00001546463,0.00003229642,0.001335331,0.00003299062,0.00005706507,0.00007029962,0.00006457304,0.9721262,0.0009510477,0.02386036,0.001438617,0.0000156612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08676454,0.001124908,0.906648,0.000751606,0.00007407505,0.0002255651,0.0003277001,0.0008832562,0.00320034],"genre_scores_gemma":[0.5797074,0.0005122118,0.4173094,0.0002191988,0.00009545141,0.0002757133,0.0009061655,0.00005025084,0.0009242557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008395516,"threshold_uncertainty_score":0.04440027,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}