{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":49,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":49,"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"},"query_hash":"ad6497fcacec","filters":{"venue":"Data Mining and Knowledge Discovery"}},"results":[{"id":"W2115482638","doi":"10.1023/b:dami.0000005258.31418.83","title":"Mining Frequent Patterns without Candidate Generation: A Frequent-Pattern Tree Approach","year":2003,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2615,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Data mining; Computer science; Scalability; Tree (set theory); Set (abstract data type); Apriori algorithm; GSP Algorithm; Association rule learning; Trie; Tree structure; Pattern recognition (psychology); Data structure; Artificial intelligence; Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.06223377143017436,"gpt":0.2906354910060366,"spread":0.2284017195758623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000626223,0.0003235563,0.0003181227,0.0001334253,0.0004049583,0.001082298,0.001475488,0.0000896878,0.000009347651],"category_scores_gemma":[0.00008109482,0.0002958364,0.00004480857,0.0003210364,0.00008453459,0.002180757,0.0008225354,0.0001487667,0.00002164632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004115632,"about_ca_system_score_gemma":0.0002053703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002051842,"about_ca_topic_score_gemma":0.0004532245,"domain_scores_codex":[0.9974858,0.0001400067,0.0004130488,0.001256015,0.0002358509,0.0004692793],"domain_scores_gemma":[0.9973748,0.0000847287,0.0001570188,0.002130726,0.00005780134,0.00019497],"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":[0.000005988209,0.0008369552,0.06569037,0.0001877766,0.0002595705,0.00004495326,0.01125097,0.0000174571,0.001106072,0.01250646,0.04609149,0.862002],"study_design_scores_gemma":[0.002526203,0.000219009,0.006705577,0.0003723191,0.0001866629,0.000386871,0.003755227,0.9131619,0.00168923,0.0001343722,0.06875874,0.002103856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1653436,0.001232436,0.8261517,0.000138587,0.0005319418,0.0002251722,0.0009919428,0.000142353,0.00524229],"genre_scores_gemma":[0.8112686,0.0001615975,0.1819956,0.0002725592,0.0004761686,0.0001282487,0.003911326,0.00004612405,0.001739785],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9131445,"threshold_uncertainty_score":0.9999547,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2282861635","doi":"10.1007/s10618-015-0444-8","title":"On the evaluation of unsupervised outlier detection: measures, datasets, and an empirical study","year":2016,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":732,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Fundação de Amparo à Pesquisa do Estado de São Paulo; Teknologi og Produktion, Det Frie Forskningsråd","keywords":"Outlier; Anomaly detection; Benchmark (surveying); Computer science; Data mining; Artificial intelligence; Ground truth; Pattern recognition (psychology); Set (abstract data type); Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1553202106037584,"gpt":0.3896393330565236,"spread":0.2343191224527651,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001566309,0.0000922582,0.0001000116,0.00005802108,0.0001980698,0.0001224542,0.0005494495,0.00003256488,0.00000472654],"category_scores_gemma":[0.000162786,0.00005084187,0.00001115007,0.0001726347,0.00007668068,0.0008075084,0.0004419382,0.00004686117,0.000002973164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001435524,"about_ca_system_score_gemma":0.00005738628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001821328,"about_ca_topic_score_gemma":0.0001494884,"domain_scores_codex":[0.9988352,0.0002492895,0.000165803,0.0004354054,0.0002219246,0.00009239586],"domain_scores_gemma":[0.9983501,0.0002275546,0.00006022117,0.00124387,0.00007414759,0.00004412834],"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":[0.00001745548,0.0003473192,0.002736675,0.000004705718,0.00002704191,3.615002e-7,0.001097008,3.396604e-7,0.0009355545,0.001339903,0.002959982,0.9905336],"study_design_scores_gemma":[0.01149496,0.008421325,0.4109178,0.0007451616,0.001179996,0.0001226086,0.01701028,0.4050826,0.03245743,0.01751009,0.09202111,0.003036718],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.844022,0.0002691213,0.1541703,0.0003045741,0.00007680342,0.0004129684,0.000388853,0.00006410934,0.000291269],"genre_scores_gemma":[0.999271,0.0000244626,0.0004891072,0.00003473082,0.00004113599,0.00005079707,0.00004261375,0.000005136854,0.00004104156],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9874969,"threshold_uncertainty_score":0.2073271,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2075949491","doi":"10.1007/s10618-012-0300-z","title":"Local outlier detection reconsidered: a generalized view on locality with applications to spatial, video, and network outlier detection","year":2012,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":294,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Locality; Anomaly detection; Computer science; Outlier; Generalization; Data mining; Artificial intelligence; Graph; Machine learning; Pattern recognition (psychology); Theoretical computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04074681739410198,"gpt":0.2935640976154808,"spread":0.2528172802213788,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005413844,0.0002228956,0.0002428287,0.0001083815,0.0004881249,0.0002835139,0.0003408306,0.0001011815,0.000003800054],"category_scores_gemma":[0.00002578319,0.0001908859,0.00002796102,0.0004677195,0.0001032931,0.0009820189,0.0004715838,0.0001488488,0.00002754779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005321857,"about_ca_system_score_gemma":0.00004449581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001846574,"about_ca_topic_score_gemma":0.001169565,"domain_scores_codex":[0.9984279,0.0001055528,0.0002846618,0.0007084559,0.0001272138,0.0003461652],"domain_scores_gemma":[0.9983899,0.0001219988,0.0001161031,0.00108867,0.00006225076,0.0002210633],"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":[0.00004324258,0.0001214009,0.0007853568,0.00003055074,0.00003116177,4.20944e-7,0.000334564,0.00002919356,0.000263998,0.001556159,0.0009734107,0.9958305],"study_design_scores_gemma":[0.002225775,0.001668139,0.0270883,0.0005228881,0.0003534322,0.000380492,0.001207136,0.1443977,0.02298373,0.002087541,0.7944059,0.002679015],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02771707,0.0007182951,0.970082,0.0001362797,0.0001417463,0.0005194106,0.00005015864,0.0002067438,0.0004283228],"genre_scores_gemma":[0.9756979,0.0001116935,0.02283985,0.0003245916,0.0003221848,0.0004211777,0.00004611711,0.00002177833,0.0002146578],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9931515,"threshold_uncertainty_score":0.7784103,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1972588194","doi":"10.1007/s10618-009-0156-z","title":"Time to CARE: a collaborative engine for practical disease prediction","year":2009,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":147,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Centers for Disease Control and Prevention; McGill University","keywords":"Computer science; Action (physics); Disease; Collaborative filtering; Health care; Order (exchange); Risk analysis (engineering); Medical costs; Machine learning; Recommender system; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.03094374567114801,"gpt":0.3502158157660921,"spread":0.3192720700949441,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003080302,0.0001362084,0.0001560974,0.00008820568,0.000202387,0.0002830222,0.0004585148,0.00004295548,0.000003373436],"category_scores_gemma":[0.00122747,0.0001265523,0.00001860462,0.0003234149,0.00002471483,0.001295189,0.0003574819,0.00009788299,0.00003185151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003949928,"about_ca_system_score_gemma":0.0004912118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003487169,"about_ca_topic_score_gemma":0.000009389459,"domain_scores_codex":[0.9987468,0.0000948512,0.000177246,0.0006129012,0.0001265647,0.0002416947],"domain_scores_gemma":[0.9984308,0.0003331595,0.00005170599,0.0007952735,0.0001448294,0.0002441542],"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":[0.0004945088,0.0004142791,0.002161116,0.000413666,0.00005849577,0.00004830939,0.027839,0.0002863199,0.0001168629,0.01080187,0.2521055,0.7052601],"study_design_scores_gemma":[0.0010224,0.001317553,0.01337221,0.0003208782,0.00006779,0.00001632971,0.001064961,0.7445049,0.00003563646,0.0002380947,0.2375064,0.0005328413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07364662,0.007409867,0.8615406,0.03810351,0.001888403,0.003103544,0.008752585,0.0009726628,0.004582232],"genre_scores_gemma":[0.670489,0.00006200478,0.3176343,0.001517085,0.001474274,0.000162007,0.004288467,0.00004439718,0.004328543],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7442185,"threshold_uncertainty_score":0.5160652,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2078064242","doi":"10.1023/b:dami.0000023674.74932.4c","title":"Pushing Convertible Constraints in Frequent Itemset Mining","year":2004,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":134,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Constraint (computer-aided design); Computer science; Data mining; Context (archaeology); Association rule learning; Convertible; A priori and a posteriori; Class (philosophy); Apriori algorithm; Monotonic function; Sequential Pattern Mining; Artificial intelligence; Mathematics; Engineering; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.04812423122534112,"gpt":0.2999252304469889,"spread":0.2518009992216478,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006001483,0.0001914476,0.0002338912,0.0001679469,0.0001771475,0.0006596675,0.001370053,0.00006857543,0.000004163047],"category_scores_gemma":[0.0001429205,0.0001880572,0.00002301893,0.0004436754,0.0001719618,0.00269697,0.001249589,0.0001384632,0.00002968026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005041645,"about_ca_system_score_gemma":0.000260768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002048042,"about_ca_topic_score_gemma":0.0003767018,"domain_scores_codex":[0.9982846,0.00003998034,0.0003458346,0.0008089613,0.0001416738,0.0003789382],"domain_scores_gemma":[0.9983996,0.0001751121,0.00008984292,0.001186813,0.00002910577,0.0001195762],"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":[0.00001281319,0.0007398567,0.01328415,0.0001588532,0.00008887381,0.0001694409,0.02157012,0.00005724798,0.001587273,0.06512616,0.01079294,0.8864123],"study_design_scores_gemma":[0.02278739,0.001062106,0.0779665,0.009119489,0.0002618,0.001482431,0.04504868,0.6490068,0.006962256,0.01190998,0.1658763,0.00851623],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6607854,0.002747791,0.3247079,0.00125736,0.0009149932,0.0003636606,0.001520706,0.0002810382,0.007421197],"genre_scores_gemma":[0.8722166,0.0001121527,0.1262277,0.0001939572,0.0001175479,0.00002989845,0.0008815663,0.00001869716,0.0002018365],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.877896,"threshold_uncertainty_score":0.7668749,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2116064560","doi":"10.1007/s10618-005-0248-3","title":"Mining Web Log Sequential Patterns with Position Coded Pre-Order Linked WAP-Tree","year":2005,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Web log analysis software; Tree (set theory); Trie; Suffix tree; Prefix; Data mining; Subsequence; Web mining; Node (physics); Web server; Fractal tree index; Tree structure; Interval tree; Web page; Data structure; Algorithm; The Internet; World Wide Web; Mathematics; Binary tree; Static web page","retraction":null,"screen_n_in":null,"score":{"opus":0.03043223887843423,"gpt":0.2874098398765441,"spread":0.2569776009981099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003406552,0.0002604002,0.0002431552,0.0001230886,0.0003168859,0.0008432153,0.001295133,0.0000883836,0.000009813011],"category_scores_gemma":[0.00003725662,0.0002239381,0.00002724366,0.000357004,0.0000983629,0.003001302,0.001188678,0.0001490298,0.00002972633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003402542,"about_ca_system_score_gemma":0.0002203737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004975872,"about_ca_topic_score_gemma":0.0007672216,"domain_scores_codex":[0.9980757,0.00006218169,0.0003167343,0.000944461,0.0002104576,0.0003905236],"domain_scores_gemma":[0.9980248,0.0001350154,0.0001385972,0.001477529,0.00008695341,0.0001370948],"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":[0.00005507024,0.0005616664,0.004878875,0.00009738216,0.0001613494,0.00003221812,0.006641196,0.00004137515,0.001596616,0.002412306,0.02143318,0.9620888],"study_design_scores_gemma":[0.002190587,0.0003287783,0.009117535,0.0005781777,0.0001488616,0.0002016608,0.001128793,0.9432654,0.0007557073,0.00004555566,0.0411676,0.001071324],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4851626,0.0005469155,0.508792,0.001024375,0.0002717532,0.0002528855,0.001577493,0.0002613068,0.00211061],"genre_scores_gemma":[0.7526994,0.0001209411,0.2399664,0.0002451001,0.0006603774,0.00006011726,0.004183121,0.00003889328,0.002025724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9610174,"threshold_uncertainty_score":0.913193,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3141059875","doi":"10.1007/s10618-005-1355-x","title":"Mining Customer Value: From Association Rules to Direct Marketing","year":2005,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Consumer Market Behavior and Pricing","field":"Business, Management and Accounting","cited_by":117,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Association rule learning; Profit (economics); Computer science; Data mining; Liberian dollar; Direct marketing; Customer lifetime value; Customer value; Marketing; Artificial intelligence; Machine learning; Customer retention; Business; Economics; Finance","retraction":null,"screen_n_in":null,"score":{"opus":0.03081130680570864,"gpt":0.2724500237614445,"spread":0.2416387169557359,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001721778,0.0002407202,0.0003013031,0.000244125,0.0003174103,0.001019262,0.0004194648,0.00008908775,0.000137113],"category_scores_gemma":[0.001156931,0.0002397806,0.00004765089,0.0003256862,0.00002113547,0.00287422,0.001073962,0.0001151654,0.0003246163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005745494,"about_ca_system_score_gemma":0.00003317615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005485662,"about_ca_topic_score_gemma":0.0008039051,"domain_scores_codex":[0.9983701,0.00005840522,0.0003314464,0.0006255175,0.0002236742,0.000390821],"domain_scores_gemma":[0.998475,0.0007219609,0.000190451,0.0005095982,0.00007115172,0.00003190919],"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":[0.0000922464,0.00008247417,0.4113661,0.00006944741,0.00007492074,0.000005011433,0.0006713798,0.000003914129,0.0004219501,0.00005335912,0.0728948,0.5142643],"study_design_scores_gemma":[0.0006684645,0.000004671067,0.3125533,0.0004685353,0.0004074737,0.000001078877,0.001393433,0.006928707,0.000042772,0.000009137526,0.6768397,0.0006826952],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9281328,0.001013369,0.00004970183,0.0003620448,0.000577673,0.0001183757,0.0001922048,0.0001240583,0.06942983],"genre_scores_gemma":[0.9899226,0.0000459981,0.002027384,0.0005631355,0.002425049,0.00001361992,0.001166923,0.00004517689,0.003790069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.603945,"threshold_uncertainty_score":0.9828768,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3043874967","doi":"10.1007/s10618-020-00705-9","title":"Deep soccer analytics: learning an action-value function for evaluating soccer players","year":2020,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":104,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Analytics; Value (mathematics); Action (physics); Function (biology); Machine learning; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.2560302781838675,"gpt":0.3534881577537748,"spread":0.09745787956990726,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008001341,0.0001831411,0.0003385897,0.0001139479,0.0003602932,0.000345402,0.0002585133,0.0000937482,0.0001271698],"category_scores_gemma":[0.0002743739,0.0002001643,0.00007013056,0.000187523,0.00004785286,0.00148928,0.0001621289,0.0001615026,0.00005108556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003461605,"about_ca_system_score_gemma":0.00005338591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006612065,"about_ca_topic_score_gemma":0.00008428837,"domain_scores_codex":[0.9984903,0.00001556678,0.0004672228,0.0006991726,0.00004620993,0.0002815145],"domain_scores_gemma":[0.9990783,0.00009656801,0.0002846063,0.0003626213,0.00004482519,0.0001330215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001067279,0.000519547,0.5430571,0.001179503,0.00135602,0.000007221255,0.02215504,0.0488583,0.000262644,0.06605015,0.02082248,0.2946647],"study_design_scores_gemma":[0.0005590324,0.0002761197,0.006439381,0.00002204121,0.00006842288,0.000001160732,0.002377401,0.9503763,0.000008331049,0.0003236246,0.03925632,0.0002918885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8333876,0.004262447,0.1549308,0.0003560309,0.001018301,0.0003259758,0.0008066507,0.00009493393,0.004817174],"genre_scores_gemma":[0.9945105,0.0002784345,0.001233203,0.0003509152,0.0007241347,0.00001532687,0.001542105,0.00004004204,0.001305297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.901518,"threshold_uncertainty_score":0.8162463,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159328231","doi":"10.1007/s10618-007-0083-9","title":"Mining functional dependencies from data","year":2007,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Correctness; Pruning; Computer science; Data mining; Information loss; Process (computing); Functional dependency; Series (stratigraphy); Axiom; Algorithm; Artificial intelligence; Mathematics; Relational database","retraction":null,"screen_n_in":null,"score":{"opus":0.1034148320734652,"gpt":0.31561346603797,"spread":0.2121986339645047,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001092281,0.0001881126,0.0001867049,0.0001055306,0.0003371352,0.0007192429,0.003147606,0.0000716495,0.00001355888],"category_scores_gemma":[0.0002168367,0.0001758057,0.00001803008,0.000328955,0.0001030351,0.004151947,0.005595378,0.0001195615,0.00005010357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001799326,"about_ca_system_score_gemma":0.0001654879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001779809,"about_ca_topic_score_gemma":0.0005836725,"domain_scores_codex":[0.997919,0.00002993794,0.0003122714,0.001161176,0.000230299,0.0003472863],"domain_scores_gemma":[0.9957344,0.0006457626,0.0001011042,0.003335474,0.00004576189,0.00013751],"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":[0.00001328286,0.0001774762,0.004796071,0.00001915448,0.00008363476,0.00002519579,0.002170813,8.62048e-7,0.0004233313,0.003818288,0.1007225,0.8877494],"study_design_scores_gemma":[0.001630315,0.0001169963,0.0856199,0.0004416991,0.0001709942,0.0001390261,0.008828195,0.4990967,0.0007573664,0.0009093064,0.4006273,0.001662188],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08638476,0.002713471,0.9014692,0.0001833117,0.0008886975,0.00009018718,0.003950774,0.0001848585,0.004134744],"genre_scores_gemma":[0.3274169,0.0001870957,0.6388255,0.0003062172,0.001528342,0.00001337226,0.0287067,0.00004114154,0.002974775],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8860872,"threshold_uncertainty_score":0.7169149,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2079040080","doi":"10.1007/s10618-013-0311-4","title":"A framework for semi-supervised and unsupervised optimal extraction of clusters from hierarchies","year":2013,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Tree (set theory); Cluster (spacecraft); Variety (cybernetics); Data mining; Artificial intelligence; Extraction (chemistry); Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.06040773208466434,"gpt":0.3443362713711306,"spread":0.2839285392864663,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000238731,0.0001713157,0.0002562963,0.0001257743,0.0001670459,0.0003968435,0.0008133908,0.0000904069,0.000005448956],"category_scores_gemma":[0.000309196,0.0001568928,0.00002930959,0.0001910744,0.000170338,0.002814469,0.001429311,0.0001461741,0.000003625193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001629306,"about_ca_system_score_gemma":0.00007075935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001211068,"about_ca_topic_score_gemma":0.00001440823,"domain_scores_codex":[0.9985679,0.00006793963,0.0002550842,0.000650616,0.0001550743,0.0003034252],"domain_scores_gemma":[0.9975732,0.001254727,0.00007298899,0.0008985171,0.00008317818,0.0001173893],"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":[0.0001359583,0.0002143146,0.001263114,0.0004137513,0.0001542915,0.000005941819,0.01339554,0.00009913054,0.008588029,0.001692562,0.001731571,0.9723058],"study_design_scores_gemma":[0.000935589,0.0001868791,0.002974103,0.0003260024,0.00002023509,0.00001071441,0.002441457,0.9881946,0.001106362,0.002765259,0.0007243263,0.0003145053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.369871,0.001067455,0.6282195,0.0001400122,0.000153844,0.0002140402,0.0002439981,0.00003692462,0.00005319574],"genre_scores_gemma":[0.3225427,0.0002250962,0.6765233,0.00003517904,0.0001407261,0.00006279472,0.0002316286,0.00002083375,0.0002177321],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9880955,"threshold_uncertainty_score":0.6397903,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1603563923","doi":"10.1023/a:1022419032620","title":"Extracting Share Frequent Itemsets with Infrequent Subsets","year":2003,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Data mining; Association rule learning; Computer science; Measure (data warehouse); Property (philosophy); Database transaction; Heuristic; Set (abstract data type); Closure (psychology); Artificial intelligence; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.051266264070474,"gpt":0.2920698709287232,"spread":0.2408036068582492,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004665361,0.0002126196,0.0001939991,0.00008807794,0.0003267881,0.0008588638,0.001137236,0.0000542385,0.00001030664],"category_scores_gemma":[0.0001899791,0.00017483,0.00001786299,0.0004215479,0.00007183883,0.002806284,0.0005901269,0.0001418536,0.00003576881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002694981,"about_ca_system_score_gemma":0.0002010904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004510021,"about_ca_topic_score_gemma":0.0000810554,"domain_scores_codex":[0.9983446,0.0000616669,0.0002516362,0.0008269906,0.0001715591,0.0003435476],"domain_scores_gemma":[0.9978484,0.0001975096,0.0001215607,0.001619093,0.00006933257,0.0001441128],"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":[0.00001269997,0.0009451907,0.02859594,0.0002336326,0.0002340454,0.0001683326,0.00875432,0.00001378369,0.001032765,0.09543027,0.05561472,0.8089643],"study_design_scores_gemma":[0.004752751,0.0006417733,0.03096133,0.002341421,0.000285518,0.001929316,0.009515189,0.1052961,0.005046555,0.001219269,0.8332815,0.00472927],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4677783,0.00708356,0.4848585,0.0006732441,0.00104384,0.0007031217,0.00333736,0.0006667371,0.03385535],"genre_scores_gemma":[0.7797363,0.000152396,0.2164375,0.0001604616,0.000146455,0.00005784211,0.002087215,0.00004270047,0.001179089],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.804235,"threshold_uncertainty_score":0.8282044,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2086829791","doi":"10.1007/s10618-011-0221-2","title":"DHCC: Divisive hierarchical clustering of categorical data","year":2011,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Data mining; Initialization; Similarity (geometry); Linear subspace; Single-linkage clustering; Hierarchical clustering; Artificial intelligence; Pattern recognition (psychology); CURE data clustering algorithm; Correlation clustering; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1924145629485619,"gpt":0.3565834104161071,"spread":0.1641688474675453,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0006449376,0.0001822839,0.0002886598,0.0001442714,0.0001294541,0.0001568875,0.004612544,0.00006916543,0.000005830776],"category_scores_gemma":[0.0003771349,0.0001615467,0.00002204101,0.0003431668,0.000234049,0.002905003,0.01748029,0.0002213244,0.00001294279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002023781,"about_ca_system_score_gemma":0.0001600794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009914489,"about_ca_topic_score_gemma":0.00007402569,"domain_scores_codex":[0.9978786,0.0001133532,0.0003270568,0.001004776,0.0002610635,0.000415215],"domain_scores_gemma":[0.9959918,0.0003258905,0.00009042482,0.003367582,0.00006336138,0.0001609281],"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":[0.00009589503,0.0004998183,0.00218884,0.0003101905,0.0001349226,0.0001715096,0.01152958,0.00001170807,0.0004464381,0.005399827,0.003187992,0.9760233],"study_design_scores_gemma":[0.0007619996,0.0002582925,0.005229628,0.0001585501,0.00002653518,0.0001248283,0.0007297426,0.9872235,0.0004315386,0.001016521,0.003525732,0.0005131421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01382685,0.0009646261,0.981401,0.00005297152,0.0003861318,0.0001221459,0.0003998737,0.00007760885,0.00276877],"genre_scores_gemma":[0.7519178,0.0001932975,0.2464058,0.0000258155,0.0001923682,0.000009209494,0.0005461478,0.00003009534,0.0006793858],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9872118,"threshold_uncertainty_score":0.9904661,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2072732320","doi":"10.1007/s10618-005-0019-1","title":"Data Clustering with Partial Supervision","year":2006,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); Fuzzy clustering; Machine learning; Support vector machine; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.07186957610495115,"gpt":0.3322306622859221,"spread":0.260361086180971,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00049023,0.000178341,0.0001851581,0.00009239249,0.0002292482,0.0007158904,0.002913614,0.00004533082,0.000002409113],"category_scores_gemma":[0.00006487053,0.0001437177,0.000009930117,0.0003011455,0.0001064767,0.004600593,0.008966632,0.0001318614,0.00001554204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002082783,"about_ca_system_score_gemma":0.0001192684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001279364,"about_ca_topic_score_gemma":0.0005803453,"domain_scores_codex":[0.9980063,0.00006479952,0.0002096762,0.001044509,0.0002608342,0.0004138588],"domain_scores_gemma":[0.996532,0.0001714681,0.00004756732,0.003121869,0.00004051541,0.00008657637],"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":[0.0001302603,0.000413185,0.004966421,0.0002755834,0.00007413044,0.0002829958,0.001348295,0.0005931273,0.001118478,0.001369053,0.01762249,0.971806],"study_design_scores_gemma":[0.0006023248,0.0000972605,0.001134228,0.0001531405,0.00001020993,0.00008068766,0.0001850097,0.9664958,0.0001651092,0.00004569874,0.03072195,0.0003086045],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04754636,0.001228566,0.9485965,0.0001599947,0.0002542332,0.0001182578,0.0005409045,0.0001489676,0.001406255],"genre_scores_gemma":[0.6104358,0.0001391495,0.3819658,0.00005243966,0.0008981257,0.00001681079,0.003573437,0.00006011574,0.002858275],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9714974,"threshold_uncertainty_score":0.9990487,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1999518899","doi":"10.1007/s10618-014-0398-2","title":"Mining outlying aspects on numeric data","year":2015,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Subspace topology; Object (grammar); Outlier; Computer science; Data mining; Set (abstract data type); Rank (graph theory); Heuristic; Curse of dimensionality; Measure (data warehouse); Data set; Mathematics; Artificial intelligence; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.1626365810308897,"gpt":0.3484467786911583,"spread":0.1858101976602685,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005112116,0.0001453736,0.0001562385,0.00009960863,0.0001949197,0.0004548988,0.002142898,0.00004924795,0.000001752286],"category_scores_gemma":[0.0001560878,0.000132753,0.00001461139,0.0003487429,0.00005128846,0.001966173,0.002887242,0.00009488208,0.00004499666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002253292,"about_ca_system_score_gemma":0.0001412888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003206618,"about_ca_topic_score_gemma":0.00003073827,"domain_scores_codex":[0.9986051,0.00004334907,0.0001920779,0.0008007951,0.0001420871,0.0002165957],"domain_scores_gemma":[0.996955,0.000121453,0.00008735331,0.002668082,0.00003685636,0.0001311926],"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":[0.00002002405,0.0003161348,0.00175663,0.00004087736,0.00005550854,0.00002388171,0.003527284,0.000006282246,0.0002522391,0.02867741,0.189604,0.7757197],"study_design_scores_gemma":[0.001133082,0.0005093457,0.00179157,0.0003607581,0.00007027188,0.0001366497,0.004546369,0.4700931,0.001538473,0.001736822,0.5167896,0.00129392],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07254567,0.001688427,0.8817596,0.0006696791,0.0008041531,0.000275938,0.0004258714,0.000728557,0.04110204],"genre_scores_gemma":[0.937066,0.00005484305,0.06045654,0.0001780596,0.0002590801,0.00001881126,0.0005747259,0.00001866384,0.001373261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8645204,"threshold_uncertainty_score":0.5413511,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2073184692","doi":"10.1007/s10618-005-1359-6","title":"Data Mining for Inventory Item Selection with Cross-Selling Considerations","year":2005,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Association rule learning; Computer science; Data mining; Profit (economics); Selection (genetic algorithm); Greedy algorithm; Machine learning; Algorithm; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.1057515397087488,"gpt":0.3499721572955075,"spread":0.2442206175867587,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006998215,0.0001956777,0.0001977019,0.0001109741,0.0006977408,0.001429673,0.001290073,0.00006419804,0.000004037163],"category_scores_gemma":[0.000248385,0.0001786243,0.0000179928,0.0002800479,0.0001157984,0.005284565,0.001110631,0.000101901,0.00000985934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002695404,"about_ca_system_score_gemma":0.0002938526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001922037,"about_ca_topic_score_gemma":0.000543781,"domain_scores_codex":[0.99812,0.00003639669,0.0003235854,0.001064491,0.0001354234,0.0003201361],"domain_scores_gemma":[0.9972936,0.000545241,0.0001372808,0.001806342,0.0001091853,0.0001083823],"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":[0.00005386461,0.0007510928,0.01743828,0.0002460876,0.0003203616,0.000008500019,0.008280898,0.0002714825,0.0005611802,0.02473752,0.2393409,0.7079898],"study_design_scores_gemma":[0.0005572354,0.00007047879,0.0005858307,0.0001067849,0.00004367554,0.00005472264,0.0003650758,0.8963411,0.0001462627,0.00007499569,0.101334,0.0003197964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08875743,0.001470978,0.9033168,0.0005699631,0.0002847929,0.000375146,0.004043982,0.0002514285,0.0009294915],"genre_scores_gemma":[0.1743089,0.00008017158,0.8162367,0.0002123069,0.0008675541,0.00008900134,0.006603751,0.00003746169,0.001564135],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8960696,"threshold_uncertainty_score":0.999607,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2010971425","doi":"10.1007/s10618-011-0212-3","title":"Measuring the component overlapping in the Gaussian mixture model","year":2011,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Cluster analysis; Gaussian; Computer science; Algorithm; Set (abstract data type); Component (thermodynamics); Multivariate normal distribution; Mixture model; Measure (data warehouse); Mathematics; Data mining; Multivariate statistics; Pattern recognition (psychology); Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1637535893682168,"gpt":0.3177989488666944,"spread":0.1540453594984776,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001148349,0.0001519425,0.0001429513,0.00008335234,0.0002863971,0.0003568064,0.002941236,0.00004208538,8.785165e-7],"category_scores_gemma":[0.0001021624,0.00008779957,0.00002419719,0.0003220991,0.0001157562,0.001407272,0.002284872,0.0002834517,0.000006538445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002744577,"about_ca_system_score_gemma":0.00008664483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006620838,"about_ca_topic_score_gemma":0.0001617985,"domain_scores_codex":[0.9984991,0.000169605,0.0001943948,0.0005080145,0.0002608994,0.0003679634],"domain_scores_gemma":[0.9980503,0.0002316294,0.00005128475,0.001592203,0.00002517228,0.0000494324],"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":[0.0001195772,0.0009155978,0.004440024,0.0003540575,0.0001607817,0.0002805145,0.2990175,0.001566644,0.001898838,0.03504369,0.006414784,0.649788],"study_design_scores_gemma":[0.0002830366,0.00002738603,0.005578158,0.0001536824,0.000006515913,0.00004568974,0.002464745,0.9894086,0.00007875131,0.0007904441,0.000957433,0.0002055284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1429817,0.003371938,0.8390664,0.0007894944,0.0004231759,0.000421632,0.00009029728,0.0001052813,0.01275003],"genre_scores_gemma":[0.9748136,0.00008413412,0.02456645,0.0001173951,0.0000833452,0.00002290721,0.0000254923,0.00001271937,0.0002739531],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.987842,"threshold_uncertainty_score":0.5465598,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161479324","doi":"10.1007/s10618-006-0051-9","title":"Privacy-preserving boosting","year":2007,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Boosting (machine learning); AdaBoost; Computer science; Artificial intelligence; Classifier (UML); Machine learning; Generalization; Bipartite graph; Data mining; Pattern recognition (psychology); Theoretical computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0657895914618925,"gpt":0.3222549855121698,"spread":0.2564653940502773,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00221129,0.0002504253,0.0002528454,0.0002413546,0.00032042,0.000740834,0.04090703,0.0001392394,0.000004551064],"category_scores_gemma":[0.03138594,0.0002385275,0.00003020555,0.0006148696,0.0001523254,0.004942505,0.2971122,0.000269984,0.00002686844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004349758,"about_ca_system_score_gemma":0.0001064575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000486314,"about_ca_topic_score_gemma":0.00009758741,"domain_scores_codex":[0.9975041,0.00005687156,0.0004031092,0.001115911,0.00024573,0.0006742515],"domain_scores_gemma":[0.9825156,0.000904222,0.0001539172,0.0162385,0.00005821292,0.0001295456],"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":[0.00001722025,0.0001313753,0.0149998,0.0001374322,0.00006211478,0.0001133113,0.001174605,3.567894e-7,0.001319584,0.00299257,0.4702968,0.5087548],"study_design_scores_gemma":[0.002831252,0.0003698151,0.04068751,0.002033193,0.0001213752,0.0004887108,0.004551137,0.6441846,0.01278613,0.07130892,0.2168804,0.003756901],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2472229,0.005487497,0.7220064,0.003649189,0.001311086,0.0002398613,0.0002500126,0.001533156,0.01829996],"genre_scores_gemma":[0.4881388,0.0001547369,0.5104984,0.0001336413,0.0002485163,0.000005365981,0.0002983086,0.00003146613,0.000490785],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6441842,"threshold_uncertainty_score":0.9767731,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098162950","doi":"10.1023/b:dami.0000023675.04946.f1","title":"Building Association-Rule Based Sequential Classifiers for Web-Document Prediction","year":2004,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Association rule learning; Data mining; Web application; Predictive modelling; Web server; Association (psychology); Web mining; Machine learning; Web page; Information retrieval; World Wide Web; The Internet","retraction":null,"screen_n_in":null,"score":{"opus":0.03959326074880023,"gpt":0.3087525581662589,"spread":0.2691592974174587,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006619374,0.0001407154,0.0001480492,0.00009334278,0.0003466206,0.0006887125,0.0007875946,0.00007417669,0.000001669191],"category_scores_gemma":[0.0001742731,0.0001400969,0.00003928145,0.0002345738,0.0000339443,0.00188743,0.0004556772,0.00007807674,0.000007613485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001613753,"about_ca_system_score_gemma":0.0003562304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002967618,"about_ca_topic_score_gemma":0.00002908777,"domain_scores_codex":[0.9986508,0.0000282207,0.0002435612,0.0006281066,0.0001657727,0.0002835028],"domain_scores_gemma":[0.9987465,0.0002000212,0.0001291764,0.000772227,0.00006373759,0.00008840838],"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":[0.00005718633,0.00106118,0.005502626,0.0003286495,0.0004538258,0.00001016442,0.003243647,0.0005490287,0.01063549,0.1440742,0.1422088,0.6918753],"study_design_scores_gemma":[0.004761769,0.0002606975,0.003680262,0.0003854464,0.000183594,0.00001250446,0.0005447611,0.7751378,0.002914815,0.004583046,0.2066831,0.0008522011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03725997,0.0002198432,0.9576977,0.0008172377,0.0007616499,0.0002320102,0.002452147,0.0001561575,0.0004032056],"genre_scores_gemma":[0.2871687,0.00004404531,0.7077588,0.0002090379,0.0006058734,0.0001947955,0.003110387,0.000029415,0.0008789708],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7745888,"threshold_uncertainty_score":0.6641271,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1964878798","doi":"10.1007/s10618-010-0208-4","title":"Publishing anonymous survey rating data","year":2010,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Anonymity; Computer science; Database transaction; Graph; Information retrieval; Personally identifiable information; Internet privacy; Data mining; Similarity (geometry); k-anonymity; Computer security; Theoretical computer science; Database; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1226799404888649,"gpt":0.3328434296471469,"spread":0.2101634891582821,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.004558919,0.0002472366,0.0002731548,0.0001788018,0.0003488195,0.005239595,0.08226827,0.0001998699,0.000006038807],"category_scores_gemma":[0.1208054,0.0002290643,0.0000151822,0.0006559645,0.0002115382,0.02408655,0.3899656,0.0006699981,0.00001986782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001378081,"about_ca_system_score_gemma":0.0002879417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004296241,"about_ca_topic_score_gemma":0.003946572,"domain_scores_codex":[0.9970486,0.0001734099,0.0003671036,0.001626197,0.0002686843,0.000516073],"domain_scores_gemma":[0.9589917,0.001552512,0.0002088934,0.03900155,0.0001088219,0.0001365248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004920009,0.00007170867,0.02003096,0.0000327762,0.00002855406,0.00001830804,0.0001935695,7.525796e-8,0.0006284548,0.0005544715,0.7576349,0.2208013],"study_design_scores_gemma":[0.001072202,0.00008224145,0.03691322,0.0002528852,0.00004010998,0.000168835,0.0006023638,0.8874225,0.000865186,0.006598871,0.06451005,0.001471523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6446889,0.003947675,0.298231,0.01085075,0.008457932,0.0005197827,0.01964495,0.002776217,0.01088274],"genre_scores_gemma":[0.6013959,0.00009333115,0.385857,0.0001258254,0.0003332219,0.000006742753,0.01190842,0.00003358322,0.0002459311],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8874224,"threshold_uncertainty_score":0.995793,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2884063665","doi":"10.1007/s10618-018-0578-6","title":"Extreme-value-theoretic estimation of local intrinsic dimensionality","year":2018,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Statistical Mechanics and Entropy","field":"Physics and Astronomy","cited_by":52,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Google (Canada)","funders":"","keywords":"Curse of dimensionality; Discriminative model; Estimator; Outlier; Measure (data warehouse); Intrinsic dimension; Extreme value theory; Mathematics; Random variable; Similarity measure; Similarity (geometry); Dimension (graph theory); Pattern recognition (psychology); Artificial intelligence; Computer science; Data mining; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03719904815149069,"gpt":0.3063922545785057,"spread":0.2691932064270151,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002122752,0.0001014643,0.0001607145,0.00002949129,0.00008156224,0.00003945618,0.000153733,0.00002299097,0.0001194473],"category_scores_gemma":[0.00004252741,0.00008599878,0.0000203664,0.00008336624,0.0002322067,0.0002147166,0.0002944096,0.00004734371,0.00002197774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006560343,"about_ca_system_score_gemma":0.00004324163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007143556,"about_ca_topic_score_gemma":0.000002690892,"domain_scores_codex":[0.999267,0.00004237008,0.0001953316,0.0002645063,0.00008618706,0.0001445707],"domain_scores_gemma":[0.9992933,0.0001658385,0.00006426677,0.0003736134,0.00004582161,0.00005712079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000293345,0.00009294357,0.0006667417,0.00002595959,0.00002928848,4.050002e-7,0.0002024129,0.000002565199,0.00006216663,0.7012349,0.001594635,0.2960587],"study_design_scores_gemma":[0.001278874,0.0003284359,0.005855665,0.000363218,0.0002166587,0.000002893635,0.00211804,0.8925074,0.003047727,0.09167659,0.002118168,0.000486367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4361515,0.0001361243,0.5595815,0.00002226338,0.0002483026,0.00005620024,0.000694379,0.000009609414,0.003100112],"genre_scores_gemma":[0.9949011,0.000002986668,0.004146819,0.00001164512,0.0001969708,0.000002553621,0.0006048043,0.00000896972,0.0001241142],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8925048,"threshold_uncertainty_score":0.3506929,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2470642288","doi":"10.1007/s10618-016-0475-9","title":"Ensembles of label noise filters: a ranking approach","year":2016,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Noise (video); Machine learning; Artificial intelligence; Filter (signal processing); Ranking (information retrieval); Ensemble learning; Process (computing); Data mining; Noise measurement; Pattern recognition (psychology); Noise reduction","retraction":null,"screen_n_in":null,"score":{"opus":0.06737345868108362,"gpt":0.3006821942314548,"spread":0.2333087355503712,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005679463,0.0001202273,0.0001745506,0.00009962908,0.00008955009,0.0001544306,0.001028535,0.00004428652,0.000002084172],"category_scores_gemma":[0.0002818332,0.000079323,0.00001868625,0.000180325,0.00007917074,0.00165774,0.0009278987,0.00005191422,0.000009952495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008394629,"about_ca_system_score_gemma":0.00006609001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002044829,"about_ca_topic_score_gemma":0.00001100346,"domain_scores_codex":[0.9988655,0.00009532072,0.0002140333,0.0005279133,0.0001209957,0.0001762746],"domain_scores_gemma":[0.99826,0.0002689769,0.0001207696,0.001263453,0.0000354137,0.00005135005],"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":[0.00003288501,0.0002127229,0.006366538,0.0001488597,0.00003723384,0.000002108982,0.002336855,6.786482e-7,0.00847051,0.01557252,0.006675458,0.9601436],"study_design_scores_gemma":[0.01333999,0.001148237,0.07173114,0.004296335,0.0003040305,0.0002347569,0.003959037,0.7063606,0.009054681,0.002219469,0.1838128,0.003538906],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.146437,0.001861958,0.8425545,0.0003948714,0.0002651059,0.0001157603,0.0004257874,0.000127504,0.007817499],"genre_scores_gemma":[0.9428765,0.0001527304,0.05537167,0.000027553,0.00008980041,0.00000725186,0.000311986,0.00001043209,0.001152048],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9566047,"threshold_uncertainty_score":0.3234698,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4376956106","doi":"10.1007/s10618-023-00931-x","title":"On the evaluation of outlier detection and one-class classification: a comparative study of algorithms, model selection, and ensembles","year":2023,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Danmarks Frie Forskningsfond; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Anomaly detection; Outlier; Artificial intelligence; Machine learning; One-class classification; Computer science; Class (philosophy); Selection (genetic algorithm); Pattern recognition (psychology); Support vector machine; Focus (optics); Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.2707064289841571,"gpt":0.3888650291681965,"spread":0.1181586001840393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008629459,0.00008340736,0.0001336964,0.0001205535,0.0002195897,0.00007812394,0.0002026646,0.00003431394,5.378078e-7],"category_scores_gemma":[0.00005868347,0.00006561433,0.000009573524,0.0004461246,0.00006702246,0.0003890769,0.0002417495,0.00006057682,7.890523e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001427951,"about_ca_system_score_gemma":0.0000648146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000250738,"about_ca_topic_score_gemma":0.0001907392,"domain_scores_codex":[0.9990701,0.0001268752,0.0002029248,0.0003472263,0.0001796799,0.0000731687],"domain_scores_gemma":[0.999032,0.0002288117,0.0001322775,0.0004188191,0.0001656079,0.00002251536],"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":[0.00009432316,0.001601022,0.002683695,0.0001328094,0.0003105285,2.790009e-7,0.0455602,0.0009770091,0.01656848,0.05696161,0.003353398,0.8717567],"study_design_scores_gemma":[0.0002371755,0.0001917079,0.009416461,0.00002389989,0.00004443982,0.000001725227,0.003345968,0.9835851,0.001585302,0.001462005,0.00003509375,0.00007114719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8858157,0.00008950975,0.1132767,0.00009201104,0.00002493556,0.0003495174,0.00003755886,0.00004907616,0.0002649139],"genre_scores_gemma":[0.9982055,0.0000455231,0.001529802,0.000005887892,0.0000147722,0.00008777652,0.00001629329,0.000004254017,0.00009016324],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9826081,"threshold_uncertainty_score":0.2675675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2969639627","doi":"10.1007/s10618-019-00651-1","title":"A unified view of density-based methods forsemi-supervised clustering and classification","year":2019,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Cluster analysis; Computer science; Artificial intelligence; Semi-supervised learning; Supervised learning; Graph; Machine learning; Correlation clustering; Data stream clustering; Data mining; Pattern recognition (psychology); CURE data clustering algorithm; Artificial neural network; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.09721739508829468,"gpt":0.386530902237729,"spread":0.2893135071494343,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001002371,0.0001467651,0.0002766571,0.0001439967,0.000084602,0.0001902091,0.000801823,0.00006259911,0.00000192315],"category_scores_gemma":[0.0001643665,0.0001359055,0.00002229512,0.0003163439,0.00008982856,0.001216107,0.001642147,0.0001133299,0.000005378084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002202813,"about_ca_system_score_gemma":0.0001215583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001491545,"about_ca_topic_score_gemma":0.00002122515,"domain_scores_codex":[0.9985254,0.0002003544,0.0002567185,0.0006297573,0.0001482139,0.0002395036],"domain_scores_gemma":[0.9979522,0.0005321049,0.00009003241,0.001262348,0.00008023184,0.00008309018],"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":[0.00004262703,0.00007497635,0.001931966,0.0007539531,0.00003325137,0.000003778182,0.001503357,0.00004064608,0.02432386,0.001233202,0.00008644981,0.969972],"study_design_scores_gemma":[0.0005777606,0.00008297612,0.002426936,0.000243089,0.00001035732,0.00000982108,0.0003463083,0.992991,0.001809734,0.00008702137,0.001233195,0.0001818365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1591879,0.0008004551,0.8390418,0.00007436128,0.0001696313,0.0001779289,0.00003623713,0.00004582778,0.0004658655],"genre_scores_gemma":[0.4597875,0.0001297389,0.5394104,0.00003871328,0.000033101,0.00001032502,0.0001111946,0.000018348,0.0004607197],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9929503,"threshold_uncertainty_score":0.5542066,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2545851563","doi":"10.1007/s10618-016-0481-y","title":"Multiple Bayesian discriminant functions for high-dimensional massive data classification","year":2016,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Université Pierre et Marie Curie; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Artificial intelligence; Pattern recognition (psychology); Weighting; Naive Bayes classifier; Machine learning; Computer science; Linear discriminant analysis; Discriminant; Bayesian probability; Classifier (UML); Bayesian inference; Feature (linguistics); Clustering high-dimensional data; Data mining; Mathematics; Support vector machine; Cluster analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.09958120661649893,"gpt":0.3066862726524197,"spread":0.2071050660359207,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003127202,0.0001414749,0.000144025,0.00008474691,0.0002985216,0.0002114007,0.001041459,0.00006349175,0.000007747107],"category_scores_gemma":[0.0003534845,0.00009126174,0.00002042025,0.00010891,0.00007324325,0.003430774,0.001451316,0.00004285963,0.00004261095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001692985,"about_ca_system_score_gemma":0.0001151154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002128962,"about_ca_topic_score_gemma":0.0001257818,"domain_scores_codex":[0.9985273,0.00005323096,0.0002178924,0.0008520199,0.0001193366,0.0002301462],"domain_scores_gemma":[0.9975142,0.000531457,0.00009759448,0.00169813,0.00007016236,0.00008838902],"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":[0.00007555173,0.0002530787,0.00114182,0.00005475814,0.00004721068,0.000003180272,0.0003769953,9.870741e-7,0.01479387,0.003417852,0.2645513,0.7152835],"study_design_scores_gemma":[0.005034267,0.0003675561,0.01848973,0.001368712,0.0002060051,0.0000323691,0.00200472,0.8627166,0.004350824,0.002569271,0.10152,0.001339961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03154894,0.0002622377,0.9588512,0.001849923,0.001071122,0.0002266273,0.005921688,0.00008511796,0.0001832123],"genre_scores_gemma":[0.9555705,0.00004964399,0.03318159,0.00007201389,0.000243369,0.00005388253,0.008529888,0.00001517059,0.002283945],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9256696,"threshold_uncertainty_score":0.3721546,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158459641","doi":"10.1007/s10618-015-0408-z","title":"Tractome: a visual data mining tool for brain connectivity analysis","year":2015,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Visualization; Scalability; Artificial intelligence; Visual analytics; Process (computing); Set (abstract data type); Data visualization; Data set; Data mining; Machine learning; Human–computer interaction; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.2789212773211442,"gpt":0.467167125821036,"spread":0.1882458484998917,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007664284,0.0001692059,0.0003911024,0.0001645641,0.0001186298,0.0001058561,0.0004074188,0.00005921409,0.000003224398],"category_scores_gemma":[0.001532258,0.0001528625,0.00004969358,0.00046564,0.00009493291,0.0008963721,0.0007589982,0.0001035198,0.000002361428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002492949,"about_ca_system_score_gemma":0.0001764065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001840715,"about_ca_topic_score_gemma":0.0000613604,"domain_scores_codex":[0.9985511,0.00003971869,0.000250619,0.0008041965,0.0001174224,0.0002369209],"domain_scores_gemma":[0.9974138,0.0006418268,0.0001007052,0.001626051,0.00007845301,0.0001392098],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009473392,0.002016213,0.1490539,0.0004414947,0.001450497,0.00005170154,0.003005757,0.000008809001,0.003865555,0.0009300299,0.4280363,0.4101924],"study_design_scores_gemma":[0.006815442,0.001081279,0.04425902,0.0004490794,0.006120154,0.0001918268,0.00552628,0.5073028,0.001123767,0.0004079717,0.4252391,0.001483306],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7647457,0.0007577817,0.2281834,0.001171681,0.00008862439,0.0005163038,0.003724898,0.0001979883,0.00061372],"genre_scores_gemma":[0.9444284,0.00003812368,0.04128221,0.0002820041,0.0002557142,0.00005673467,0.01253579,0.00003299324,0.001088067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.507294,"threshold_uncertainty_score":0.6233552,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2005934890","doi":"10.1007/s10618-013-0336-8","title":"Clustering categorical data in projected spaces","year":2013,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Cluster analysis; Categorical variable; Computer science; Data mining; Outlier; CURE data clustering algorithm; Curse of dimensionality; Clustering high-dimensional data; Correlation clustering; Canopy clustering algorithm; Data stream clustering; Anomaly detection; Probabilistic logic; Set (abstract data type); Artificial intelligence; Pattern recognition (psychology); Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.09257415986957443,"gpt":0.3536923389834265,"spread":0.261118179113852,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005122537,0.0001767185,0.0002208383,0.0001952804,0.0001108705,0.0009675179,0.003463923,0.00006333683,0.000004899204],"category_scores_gemma":[0.0003724272,0.0001553439,0.000009682387,0.0005685687,0.00008873466,0.006134995,0.01219033,0.000210252,0.00004977625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000418934,"about_ca_system_score_gemma":0.0001606193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000526931,"about_ca_topic_score_gemma":0.0004565036,"domain_scores_codex":[0.9978982,0.0001043619,0.0002557066,0.001050292,0.0002115408,0.0004798602],"domain_scores_gemma":[0.9967571,0.000270487,0.00005224418,0.00275922,0.00004755203,0.0001133555],"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":[0.00001872798,0.0003267635,0.01046154,0.0002790178,0.00004683584,0.0001243381,0.0052985,0.00004942426,0.0009059219,0.0004657592,0.01116628,0.9708569],"study_design_scores_gemma":[0.0004146663,0.00003830996,0.007239657,0.00008294683,0.000003119412,0.0000314366,0.0006492968,0.9885409,0.00003809048,0.0001078749,0.002586714,0.0002669639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1960435,0.002426523,0.796412,0.0007916735,0.0006971049,0.0006473433,0.0002191654,0.0002804956,0.002482201],"genre_scores_gemma":[0.8464171,0.0002059816,0.1501208,0.00004638406,0.0002465241,0.00005831898,0.0008249712,0.00003468962,0.002045239],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9884915,"threshold_uncertainty_score":0.9957989,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154217032","doi":"10.1007/s10618-009-0133-6","title":"Fast incremental mining of web sequential patterns with PLWAP tree","year":2009,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Data mining; Tree (set theory); Metadata; Web mining; Database; Web log analysis software; Web page; Information retrieval; Web navigation; World Wide Web; Static web page","retraction":null,"screen_n_in":null,"score":{"opus":0.0352025202348579,"gpt":0.2851548256075449,"spread":0.249952305372687,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002738757,0.0001838743,0.0002298507,0.0001093448,0.0001485863,0.0003157789,0.001229782,0.00004377272,0.000004199612],"category_scores_gemma":[0.00002034959,0.0001543524,0.0000247078,0.0002768935,0.00008159743,0.001738884,0.0007728795,0.00007971603,0.000004610238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001488467,"about_ca_system_score_gemma":0.000141118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004097932,"about_ca_topic_score_gemma":0.0001850094,"domain_scores_codex":[0.9986191,0.00003618261,0.0002735557,0.0006248115,0.0001842954,0.0002620327],"domain_scores_gemma":[0.9985238,0.00007343256,0.0001332224,0.001140497,0.00003878451,0.00009030318],"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":[0.0000291901,0.0004323658,0.008932726,0.00005639302,0.00008113572,0.00002290875,0.00405744,0.000002901737,0.003428208,0.00286632,0.007360423,0.97273],"study_design_scores_gemma":[0.009974956,0.003847947,0.1262619,0.003212299,0.000522594,0.0005780154,0.01905449,0.7907131,0.01394766,0.0002626229,0.02768838,0.003935976],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8694665,0.0003907398,0.1237449,0.0002067216,0.0001648067,0.0001442263,0.001740786,0.0001007021,0.004040689],"genre_scores_gemma":[0.935253,0.00004278442,0.06318785,0.00006154334,0.0001292234,0.000007350239,0.0009886516,0.00001069857,0.0003188865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.968794,"threshold_uncertainty_score":0.629431,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2002041176","doi":"10.1007/s10618-006-0046-6","title":"Relational peculiarity-oriented mining","year":2007,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"National Natural Science Foundation of China","keywords":"Relevance (law); Computer science; Identification (biology); Relational database; Data mining; Task (project management); Focus (optics); Information retrieval; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0726774133759716,"gpt":0.2994970904899545,"spread":0.2268196771139829,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009250945,0.0001414151,0.0001485239,0.0001069764,0.0002811787,0.0002413921,0.0007222263,0.00007209503,0.000004573147],"category_scores_gemma":[0.0001700983,0.0001232676,0.00002615422,0.0003219213,0.00007649294,0.001739471,0.001148527,0.0001060172,0.00002214306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001745806,"about_ca_system_score_gemma":0.00007732175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001218969,"about_ca_topic_score_gemma":0.00005854268,"domain_scores_codex":[0.9986501,0.00003635687,0.0002509335,0.0005774126,0.000171011,0.0003141657],"domain_scores_gemma":[0.9986705,0.0002966482,0.00007345919,0.000811514,0.00004193338,0.0001059317],"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":[0.00006186606,0.0004351032,0.06086214,0.0000740198,0.00009320831,0.0001724428,0.01401851,0.000006931289,0.0001457199,0.2259057,0.05364047,0.6445839],"study_design_scores_gemma":[0.003401882,0.0004790646,0.2586576,0.0005659459,0.0001058168,0.0003383658,0.006996656,0.242052,0.0002076184,0.002266536,0.4826951,0.002233404],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2750052,0.002471363,0.6597015,0.0002984719,0.001450862,0.0001208639,0.000155266,0.0001862794,0.06061018],"genre_scores_gemma":[0.8029202,0.0000524613,0.1942894,0.0001984453,0.0004062271,0.000002803895,0.0006452779,0.00001373635,0.001471466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6423506,"threshold_uncertainty_score":0.5026708,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2894980798","doi":"10.1007/s10618-018-0592-8","title":"Classification with label noise: a Markov chain sampling framework","year":2018,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Australian Research Council","keywords":"Markov chain; Computer science; Probabilistic logic; Correctness; Artificial intelligence; Noise (video); Markov chain Monte Carlo; Pattern recognition (psychology); Sampling (signal processing); Machine learning; Probability distribution; Variable-order Markov model; Hidden Markov model; Algorithm; Markov model; Bayesian probability; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.0757148656264769,"gpt":0.3395744944047306,"spread":0.2638596287782538,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006908232,0.0001772872,0.0001649451,0.0001178067,0.000358787,0.0006726836,0.001150664,0.00008838509,0.000005665167],"category_scores_gemma":[0.0003800834,0.0001436595,0.00001183737,0.0004526023,0.000164915,0.001665706,0.0007258132,0.0001856509,0.00005346184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002022254,"about_ca_system_score_gemma":0.0001277631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002668343,"about_ca_topic_score_gemma":0.0000754251,"domain_scores_codex":[0.9984034,0.0001076902,0.0002120543,0.0008380105,0.0001691349,0.0002696565],"domain_scores_gemma":[0.9975516,0.0003080966,0.0001381769,0.001820747,0.00008496294,0.00009647956],"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":[0.00008546699,0.0002554094,0.02588989,0.0001006351,0.00005781489,0.000004055011,0.004877334,8.878618e-7,0.0009901616,0.07178422,0.007658148,0.888296],"study_design_scores_gemma":[0.001324303,0.0006088335,0.1589111,0.000942092,0.00008025403,0.0000731676,0.001823422,0.7161181,0.0001380723,0.001072691,0.1177576,0.001150333],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06412975,0.0005763149,0.92931,0.0008459876,0.0003342037,0.0001156974,0.0001276444,0.0001993171,0.004361038],"genre_scores_gemma":[0.7611699,0.00007204751,0.236362,0.0001517253,0.0004664535,0.00001529379,0.000831924,0.00001959235,0.0009110174],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8871456,"threshold_uncertainty_score":0.6486704,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2950515936","doi":"10.1007/s10618-017-0497-y","title":"Adjusting for scorekeeper bias in NBA box scores","year":2017,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":12,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Statistics; Popularity; Basketball; Computer science; Generosity; Econometrics; Psychology; Mathematics; Geography; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.2488841393248247,"gpt":0.3329720170911042,"spread":0.08408787776627952,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009114015,0.0001397062,0.0003368584,0.000155969,0.0003476405,0.0005606724,0.0005847266,0.00006702425,0.00002283585],"category_scores_gemma":[0.0005600767,0.0001443498,0.00004323951,0.0000548064,0.0001004268,0.001275701,0.0004252568,0.00008066135,0.00002507756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001858736,"about_ca_system_score_gemma":0.00003622291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004684292,"about_ca_topic_score_gemma":0.001251546,"domain_scores_codex":[0.9987581,0.000003560728,0.0004151529,0.0005196668,0.00002073394,0.0002827289],"domain_scores_gemma":[0.9985458,0.00008961628,0.0003065928,0.0009852656,0.0000185936,0.00005411605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003222192,0.00007328206,0.9556254,0.0001384322,0.00003080943,0.000004939995,0.0008463407,0.00001208062,0.000003824314,0.01877909,0.005166776,0.01928687],"study_design_scores_gemma":[0.002602093,0.0001291673,0.6658866,0.0006420998,0.0000379667,0.000008089814,0.0009753286,0.1836895,0.00005022679,0.003613727,0.1413882,0.0009770355],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9784772,0.00569493,0.0008569319,0.0001349761,0.0007096475,0.0001481601,0.001598827,0.00001229352,0.01236708],"genre_scores_gemma":[0.9952527,0.0006240736,0.0007507726,0.00004940026,0.0003157715,0.00001440119,0.0003457027,0.00002133059,0.002625863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2897388,"threshold_uncertainty_score":0.5886413,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159694214","doi":"10.1007/s10618-005-0013-7","title":"Discovering Classification from Data of Multiple Sources","year":2006,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Hong Kong University of Science and Technology","keywords":"Computer science; Class (philosophy); Artificial intelligence; Perspective (graphical); Machine learning; Supervised learning; Test data; Labeled data; Semi-supervised learning; Data mining; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.09401072320475932,"gpt":0.3028926707297767,"spread":0.2088819475250174,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002407584,0.0001277773,0.0001717073,0.0000989292,0.0001088668,0.000360766,0.002715456,0.00006217286,0.000002267426],"category_scores_gemma":[0.0001747999,0.0001123532,0.00001586423,0.0002278161,0.0001380992,0.003468326,0.002970872,0.00006351536,0.000007896276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000109065,"about_ca_system_score_gemma":0.00005834935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004136408,"about_ca_topic_score_gemma":0.0003829455,"domain_scores_codex":[0.9986714,0.00003401692,0.0003004696,0.0007015095,0.0001340438,0.000158582],"domain_scores_gemma":[0.99664,0.0002935807,0.0001808924,0.00283604,0.00002525467,0.00002427116],"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":[0.00003563048,0.0006630691,0.2990901,0.0001281116,0.0001036389,0.000004766222,0.00233365,0.00001351238,0.02894267,0.0655508,0.04203899,0.5610951],"study_design_scores_gemma":[0.001411599,0.00007814277,0.3370076,0.0002936642,0.00008128853,0.00000501362,0.005904335,0.5673396,0.01371308,0.004187681,0.06907333,0.0009046807],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.744359,0.003202294,0.2486116,0.000307436,0.0002800949,0.0001064621,0.001488224,0.0002547168,0.001390118],"genre_scores_gemma":[0.9768553,0.00009434215,0.01969271,0.000006577824,0.00008133326,0.000004837763,0.002902986,0.000007581978,0.0003542787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5673261,"threshold_uncertainty_score":0.5046038,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2032708445","doi":"10.1007/s10618-007-0086-6","title":"Classification trees and decision-analytic feedforward control: a case study from the video game industry","year":2008,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Modeling, Simulation, and Optimization","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Feed forward; Video game; Model predictive control; Decision tree; Probabilistic logic; Control (management); Machine learning; Artificial intelligence; Data mining; Engineering; Multimedia; Control engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1710043822641238,"gpt":0.3681496386951982,"spread":0.1971452564310744,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005785702,0.0001788955,0.0002820758,0.00006789772,0.000386603,0.0001939057,0.0002241036,0.0001344851,0.00001180411],"category_scores_gemma":[0.0008848998,0.0001245565,0.00002836671,0.0001528536,0.0001004004,0.0006785636,0.0001749479,0.0001731504,0.000003016328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001864925,"about_ca_system_score_gemma":0.00008761745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002745634,"about_ca_topic_score_gemma":0.001754422,"domain_scores_codex":[0.9986778,0.0001243604,0.0004079062,0.0004719004,0.0001697112,0.0001483195],"domain_scores_gemma":[0.9968214,0.002006677,0.0001637689,0.0008491589,0.00008761889,0.00007135647],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004388741,0.001596326,0.8253201,0.00006891651,0.0008072645,0.0003769237,0.08968792,0.001585194,0.00002588177,0.0009267812,0.02348612,0.05567972],"study_design_scores_gemma":[0.002706621,0.00008803589,0.03653254,0.0001116828,0.000597182,0.0002129882,0.02643572,0.9310893,0.000001264352,0.001595656,0.0003305548,0.0002984886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9567773,0.0007155357,0.04162006,0.00004125534,0.00008965423,0.0002969003,0.0003163014,0.00003368802,0.000109347],"genre_scores_gemma":[0.9965316,0.0001019753,0.002644866,0.00003508897,0.0001997731,0.00001285698,0.0002311364,0.00002187679,0.0002208012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9295041,"threshold_uncertainty_score":0.5079268,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3099831365","doi":"10.1007/s10618-015-0426-x","title":"Generalization of clustering agreements and distances for overlapping clusters and network communities","year":2015,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Generalization; Measure (data warehouse); Context (archaeology); Single-linkage clustering; Correlation clustering; Rand index; Contingency table; Cluster (spacecraft)","retraction":null,"screen_n_in":null,"score":{"opus":0.1193435223284324,"gpt":0.3518487569469944,"spread":0.232505234618562,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000559789,0.0001186911,0.0001961459,0.00006407303,0.0001831978,0.0002791145,0.0004603986,0.00003318195,1.319e-7],"category_scores_gemma":[0.00007585051,0.0001132139,0.000009353937,0.0001315106,0.0001480176,0.001563074,0.002203705,0.00004984508,1.057447e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001843867,"about_ca_system_score_gemma":0.00004663206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006034534,"about_ca_topic_score_gemma":0.0005243216,"domain_scores_codex":[0.9990955,0.00007143769,0.0001989703,0.0002834186,0.0001230708,0.00022761],"domain_scores_gemma":[0.9990395,0.000236951,0.00008731263,0.000481516,0.00007070039,0.00008398559],"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":[0.000353712,0.0001902813,0.03437091,0.002554737,0.0003265592,0.00000945237,0.07922859,0.007655357,0.0004090664,0.005874723,0.007004718,0.8620219],"study_design_scores_gemma":[0.0007869597,0.0001225603,0.0008010114,0.0003074005,0.00001149365,0.000009882675,0.004280188,0.9909282,0.00001924764,0.000352966,0.002201697,0.0001783913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1285345,0.004582487,0.8661168,0.00004569649,0.0002404278,0.0001616855,0.0001067483,0.000025945,0.0001857884],"genre_scores_gemma":[0.8359038,0.0007846965,0.1623109,0.0000453316,0.0001831388,0.00002398684,0.0003071633,0.00002080924,0.0004201764],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9832729,"threshold_uncertainty_score":0.4616728,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2755646241","doi":"10.1007/s10618-017-0540-z","title":"Bounding the difference between RankRC and RankSVM and application to multi-level rare class kernel ranking","year":2017,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Kernel method; Kernel (algebra); Computer science; Bounding overwatch; Mathematics; Projection (relational algebra); Algorithm; Support vector machine; Machine learning; Artificial intelligence; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.08877169197371115,"gpt":0.3433036432579842,"spread":0.254531951284273,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009142426,0.0001882777,0.0002359167,0.00006693508,0.001523882,0.002069162,0.001472377,0.00006591093,3.828135e-7],"category_scores_gemma":[0.0004271238,0.000136974,0.00001715807,0.00008146024,0.0001733828,0.00102981,0.002639557,0.0001662564,0.000005117123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001046937,"about_ca_system_score_gemma":0.00004241171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002078779,"about_ca_topic_score_gemma":0.0002605239,"domain_scores_codex":[0.998595,0.00009838333,0.0001896098,0.0007168247,0.0001326224,0.0002675458],"domain_scores_gemma":[0.997842,0.0003914894,0.0001373278,0.001482996,0.00002972379,0.0001164446],"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":[0.00001139702,0.00002019896,0.1058434,0.00006221333,0.0000261579,0.000001940461,0.005974991,9.575904e-7,0.0002147535,0.001024342,0.0003144171,0.8865052],"study_design_scores_gemma":[0.001155685,0.00004463477,0.8696846,0.0002776995,0.00004816971,0.00001908577,0.000418153,0.1198148,0.00006376348,0.0002282257,0.007862923,0.0003821907],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5773304,0.0009504731,0.419888,0.0009233714,0.0001842311,0.0001794412,0.0001094969,0.00005371652,0.0003808891],"genre_scores_gemma":[0.9903111,0.00008624629,0.008389804,0.00007963026,0.0001850946,0.00001592395,0.0000665149,0.00001211126,0.0008535865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8861231,"threshold_uncertainty_score":0.999776,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4283736551","doi":"10.1007/s10618-022-00843-2","title":"VPint: value propagation-based spatial interpolation","year":2022,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":7,"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":"Horizon 2020; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Interpolation (computer graphics); Multivariate interpolation; Value (mathematics); Computer science; Mathematics; Algorithm; Bilinear interpolation; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03145311805954926,"gpt":0.3022289843732606,"spread":0.2707758663137113,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004148,0.0001127171,0.0001098891,0.0001215625,0.0003787974,0.0003134501,0.001076385,0.00001914939,0.00000653067],"category_scores_gemma":[0.0001580625,0.0001142003,0.00001608329,0.0002592037,0.00005640652,0.001897275,0.001941437,0.0001248963,0.000002734891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004326618,"about_ca_system_score_gemma":0.0002243084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003122918,"about_ca_topic_score_gemma":0.00001453724,"domain_scores_codex":[0.9988953,0.0001014348,0.0001780022,0.0005087827,0.0001594759,0.0001569601],"domain_scores_gemma":[0.9989241,0.0001127247,0.0001056963,0.0007837734,0.00003799448,0.00003565496],"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":[0.00008001284,0.0004896148,0.003747246,0.0001999805,0.00003277214,0.00002806745,0.00499597,0.0001276218,0.007099197,0.01399818,0.01243863,0.9567627],"study_design_scores_gemma":[0.0002036212,0.00009069417,0.0002410053,0.00004758312,0.000006815709,0.000009643997,0.0001322307,0.9928955,0.0007755439,0.0009839879,0.004431757,0.0001816411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00302784,0.0004401217,0.9948609,0.0002186671,0.0002687046,0.0001062604,0.0001004675,0.0002450488,0.0007320244],"genre_scores_gemma":[0.711107,0.000003368054,0.2880147,0.0001285361,0.00006590472,0.00004270327,0.0004173515,0.00001201259,0.0002083486],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9927679,"threshold_uncertainty_score":0.4656953,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3199460270","doi":"10.1007/s10618-021-00794-0","title":"A Lagrangian-based score for assessing the quality of pairwise constraints in semi-supervised clustering","year":2021,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis","funders":"","keywords":"Cluster analysis; Pairwise comparison; Constrained clustering; Constraint (computer-aided design); Computer science; Data mining; Machine learning; Key (lock); Artificial intelligence; Correlation clustering; Mathematics; CURE data clustering algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.1432772631699324,"gpt":0.4071249385868225,"spread":0.2638476754168901,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001607284,0.0001442458,0.0002822106,0.00008961801,0.0001476194,0.0003723658,0.0009940519,0.00005641292,0.000002117516],"category_scores_gemma":[0.001006422,0.0001180857,0.00004869586,0.0004501407,0.0002246939,0.001106621,0.001248342,0.0001393381,6.314744e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003560221,"about_ca_system_score_gemma":0.0005108404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003202657,"about_ca_topic_score_gemma":0.0003202177,"domain_scores_codex":[0.9982212,0.000268043,0.0003843379,0.0005912976,0.000203161,0.0003320257],"domain_scores_gemma":[0.9968937,0.001642455,0.00009996482,0.001167895,0.0001347189,0.00006123979],"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":[0.000067413,0.0004205743,0.01724934,0.001723821,0.00007033429,0.00006724065,0.00604334,0.0009657841,0.01205446,0.000834706,0.0002627594,0.9602402],"study_design_scores_gemma":[0.001474216,0.00003318837,0.008626503,0.0006840639,0.00000891727,0.0000123411,0.002641491,0.9840835,0.001859452,0.0001096422,0.0002269839,0.0002396406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2461658,0.000988783,0.7516652,0.0002489079,0.0001768349,0.0001919093,0.0002699879,0.00003170306,0.0002608434],"genre_scores_gemma":[0.9248499,0.00002156734,0.074669,0.00005598625,0.00005413613,0.00002741309,0.0001829803,0.00001491169,0.00012408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9831178,"threshold_uncertainty_score":0.4815394,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061678866","doi":"10.1007/s10618-013-0330-1","title":"What distinguish one from its peers in social networks?","year":2013,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Taiwan University; National Science Council; Intel Corporation","keywords":"Uniqueness; Identification (biology); Computer science; Task (project management); Vertex (graph theory); Group (periodic table); Social network (sociolinguistics); Social network analysis; Theoretical computer science; Data mining; Machine learning; Graph; Mathematics; World Wide Web; Social media; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.05195597983772818,"gpt":0.3072964131251066,"spread":0.2553404332873784,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001873903,0.0001748083,0.0003050289,0.00006443785,0.0001512627,0.0007793636,0.000407208,0.00004527058,0.0002049168],"category_scores_gemma":[0.00001879838,0.0001782022,0.0000475229,0.0002204867,0.00005903724,0.001740142,0.0006923609,0.0001496029,0.00002304052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000163975,"about_ca_system_score_gemma":0.0000301973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008109428,"about_ca_topic_score_gemma":0.0003580493,"domain_scores_codex":[0.9988128,0.00007118665,0.0002651097,0.0004710268,0.00008881326,0.0002910875],"domain_scores_gemma":[0.9992043,0.0001769075,0.0000956295,0.0004228862,0.00004287567,0.00005745227],"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":[0.00002552653,0.0005783297,0.2203219,0.00002734594,0.0003693913,0.000003635313,0.004277977,0.00001875373,0.0001596077,0.003609416,0.1445505,0.6260575],"study_design_scores_gemma":[0.00388611,0.0001439781,0.3395441,0.00263455,0.0008532021,0.000001248037,0.04607591,0.535287,0.0003305491,0.017883,0.04950076,0.003859565],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9866737,0.002294318,0.003560835,0.0001421678,0.0002997667,0.000199377,0.000300597,0.00006451887,0.006464709],"genre_scores_gemma":[0.9935499,0.00005441904,0.0005198411,0.00002364637,0.00155051,0.00002954363,0.003466293,0.00002014227,0.0007856427],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.622198,"threshold_uncertainty_score":0.7515421,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106700114","doi":"10.1007/s10618-012-0257-y","title":"Guest editorial: special issue on a decade of mining the Web","year":2012,"lang":"en","type":"editorial","venue":"Data Mining and Knowledge Discovery","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Web mining; World Wide Web; Computer science; Data science; Domain (mathematical analysis); Web intelligence; Web development; The Internet; Web page","retraction":null,"screen_n_in":null,"score":{"opus":0.02640097352747741,"gpt":0.2997039996304098,"spread":0.2733030261029324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.002399159,0.0006011467,0.0009301166,0.0003407836,0.0003654207,0.0009461672,0.00547045,0.0007024987,0.00001485311],"category_scores_gemma":[0.003014214,0.0004356447,0.0001599398,0.0006276699,0.0002862319,0.001855997,0.00397609,0.0008066013,0.00009419268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005335852,"about_ca_system_score_gemma":0.0009798753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009502688,"about_ca_topic_score_gemma":0.0002419234,"domain_scores_codex":[0.9957718,0.0003355319,0.0007632859,0.001393255,0.001079043,0.0006571443],"domain_scores_gemma":[0.9913553,0.003731174,0.0006309672,0.003870559,0.0002225955,0.0001894337],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002809227,0.0001350049,0.00004549465,0.0001005517,0.000171906,0.000005496748,0.00239567,4.011549e-7,0.000009648401,0.00006671969,0.9800925,0.01694848],"study_design_scores_gemma":[0.0004183886,0.0001247365,0.00001270567,0.0006176133,0.000288634,0.000002471007,0.0006783464,0.0006131534,0.00002985731,0.000005072193,0.9967045,0.000504526],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.0002927689,0.00190158,0.0001599984,0.00009690954,0.9876504,0.0001118622,0.004687283,0.00007190625,0.00502729],"genre_scores_gemma":[0.0003142792,0.0005874654,0.001061869,0.00001814541,0.9903699,0.00001418016,0.004404083,0.00005251559,0.003177532],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.01661196,"threshold_uncertainty_score":0.9999104,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4239981520","doi":"10.1007/s10618-009-0144-3","title":"Fast incremental mining of web sequential patterns with PLWAP tree","year":2009,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Data mining; Tree (set theory); Web mining; Information retrieval; World Wide Web; Mathematics; Web service","retraction":null,"screen_n_in":null,"score":{"opus":0.0352025202348579,"gpt":0.2851548256075449,"spread":0.249952305372687,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002738757,0.0001838743,0.0002298507,0.0001093448,0.0001485863,0.0003157789,0.001229782,0.00004377272,0.000004199612],"category_scores_gemma":[0.00002034959,0.0001543524,0.0000247078,0.0002768935,0.00008159743,0.001738884,0.0007728795,0.00007971603,0.000004610238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001488467,"about_ca_system_score_gemma":0.000141118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004097932,"about_ca_topic_score_gemma":0.0001850094,"domain_scores_codex":[0.9986191,0.00003618261,0.0002735557,0.0006248115,0.0001842954,0.0002620327],"domain_scores_gemma":[0.9985238,0.00007343256,0.0001332224,0.001140497,0.00003878451,0.00009030318],"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":[0.0000291901,0.0004323658,0.008932726,0.00005639302,0.00008113572,0.00002290875,0.00405744,0.000002901737,0.003428208,0.00286632,0.007360423,0.97273],"study_design_scores_gemma":[0.009974956,0.003847947,0.1262619,0.003212299,0.000522594,0.0005780154,0.01905449,0.7907131,0.01394766,0.0002626229,0.02768838,0.003935976],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8694665,0.0003907398,0.1237449,0.0002067216,0.0001648067,0.0001442263,0.001740786,0.0001007021,0.004040689],"genre_scores_gemma":[0.935253,0.00004278442,0.06318785,0.00006154334,0.0001292234,0.000007350239,0.0009886516,0.00001069857,0.0003188865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.968794,"threshold_uncertainty_score":0.629431,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387703477","doi":"10.1007/s10618-023-00970-4","title":"Mondrian forest for data stream classification under memory constraints","year":2023,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Mondrian; Computer science; Trimming; Data stream mining; Node (physics); Data stream; Data mining; Theoretical computer science; Machine learning; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.1783262536153769,"gpt":0.3657060325522407,"spread":0.1873797789368638,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00104093,0.0002063997,0.0002299079,0.0002017639,0.0002383668,0.0006555675,0.003862182,0.00009517006,0.000002336548],"category_scores_gemma":[0.0004486193,0.0001976496,0.00002332046,0.0004241433,0.0002258867,0.00356686,0.004964947,0.00009029896,0.00003393518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002236737,"about_ca_system_score_gemma":0.000238284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003182521,"about_ca_topic_score_gemma":0.0002584097,"domain_scores_codex":[0.9978774,0.0000599187,0.0003031298,0.001188679,0.0001566399,0.0004142774],"domain_scores_gemma":[0.9949428,0.0005640408,0.0001248551,0.004213381,0.00005286227,0.0001021043],"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":[0.00001801491,0.0001219955,0.001521486,0.0001029482,0.00007355712,0.00001011337,0.0008550946,0.000001569702,0.0002797811,0.04083245,0.3566593,0.5995237],"study_design_scores_gemma":[0.001310537,0.0002752905,0.01354924,0.0004380042,0.0001168564,0.00004887265,0.004578587,0.9277051,0.0003896772,0.006999974,0.0435492,0.00103866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03548891,0.0003970751,0.9417938,0.0009203596,0.0009769206,0.0006243553,0.01422013,0.001354535,0.004223948],"genre_scores_gemma":[0.7813126,0.0002123728,0.159855,0.0001274245,0.0003368746,0.0000964413,0.05633205,0.00005584316,0.001671384],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9277036,"threshold_uncertainty_score":0.8059915,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408175168","doi":"10.1007/s10618-024-01084-1","title":"Efficient outlier detection in numerical and categorical data","year":2025,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":2,"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":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo; Carnegie Mellon University","keywords":"Categorical variable; Anomaly detection; Outlier; Computer science; Data mining; Artificial intelligence; Pattern recognition (psychology); Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.03590234063653296,"gpt":0.3165941644719431,"spread":0.2806918238354101,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003019688,0.00009048959,0.0001203073,0.0001267348,0.0001303852,0.0002090576,0.0007722382,0.00005207381,6.704764e-7],"category_scores_gemma":[0.00006553371,0.00008228589,0.00000813364,0.0004628646,0.00005023259,0.0004014554,0.002265637,0.0001004452,0.000003342126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002015124,"about_ca_system_score_gemma":0.0000558637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007756984,"about_ca_topic_score_gemma":0.00008431434,"domain_scores_codex":[0.9989729,0.00003735179,0.0001707562,0.0006249898,0.00005521134,0.0001387876],"domain_scores_gemma":[0.9986552,0.0001003018,0.00003172753,0.001158266,0.00001474583,0.00003978653],"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":[0.00001275813,0.0002376972,0.002395018,0.00004004362,0.0000157285,0.000004820749,0.0004959368,0.000008711675,0.0003274534,0.01409222,0.003452075,0.9789175],"study_design_scores_gemma":[0.0002546484,0.00003436705,0.009390613,0.00003372632,0.00001393925,0.00001621161,0.000220628,0.9652631,0.0003276566,0.0004242789,0.02384271,0.0001781199],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05818643,0.000779892,0.9392631,0.0002327385,0.0001370533,0.0001071108,0.00005233938,0.00008911567,0.001152223],"genre_scores_gemma":[0.9929909,0.00005371825,0.006428877,0.00004814737,0.00002940607,0.0000164956,0.00007001287,0.000003843072,0.0003585935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9787394,"threshold_uncertainty_score":0.3355521,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391572936","doi":"10.1007/s10618-023-01001-y","title":"VEM$$^2$$L: an easy but effective framework for fusing text and structure knowledge on sparse knowledge graph completion","year":2024,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"National Natural Science Foundation of China","keywords":"Computer science; Knowledge graph; Graph; Information retrieval; Artificial intelligence; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.05877690887851249,"gpt":0.3329948927339794,"spread":0.2742179838554669,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006815006,0.0004167952,0.0004283853,0.0003414128,0.0004469457,0.001341227,0.0009204592,0.000227082,0.000003283621],"category_scores_gemma":[0.0002656564,0.0003729246,0.00006843804,0.0004602972,0.0001566254,0.002064431,0.001059088,0.0003768856,0.00001469927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006396593,"about_ca_system_score_gemma":0.0001696322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002519769,"about_ca_topic_score_gemma":0.000181399,"domain_scores_codex":[0.9972176,0.0002091372,0.0003434549,0.00159375,0.0001496412,0.0004864053],"domain_scores_gemma":[0.996999,0.00129531,0.00007698452,0.001333741,0.00009523852,0.0001997549],"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":[0.00007340822,0.0002799448,0.0004307829,0.0009042457,0.0001299338,0.00001691688,0.01375118,0.00003175986,0.0007636428,0.1532664,0.001794336,0.8285574],"study_design_scores_gemma":[0.001191626,0.0006779916,0.002193147,0.002958926,0.000167412,0.000086377,0.001140017,0.9338253,0.0006378886,0.026497,0.02943654,0.001187832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3615168,0.0133977,0.6201701,0.0000848409,0.002405417,0.0005696487,0.000728423,0.0002938353,0.0008332354],"genre_scores_gemma":[0.9534194,0.0001086681,0.04452622,0.00006314986,0.001006043,0.00004466265,0.0004452244,0.000055171,0.0003314049],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9337935,"threshold_uncertainty_score":0.9998723,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2091837657","doi":"10.1007/s10618-010-0199-1","title":"Improving constrained pattern mining with first-fail-based heuristics","year":2010,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal; Polytechnique Montréal; École de Technologie Supérieure","funders":"","keywords":"Heuristics; Data mining; Computer science; Process (computing); Data stream mining; State (computer science); Sequential Pattern Mining; Machine learning; Artificial intelligence; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.02107824697066401,"gpt":0.2557087373958644,"spread":0.2346304904252004,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004129322,0.0002438098,0.0002227422,0.0001041815,0.0003927037,0.0009338866,0.001506725,0.00007905204,0.000006213998],"category_scores_gemma":[0.0002235975,0.0002058195,0.00002323355,0.0002849103,0.0002275072,0.001308174,0.0009342375,0.0002123608,0.00001274742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009311581,"about_ca_system_score_gemma":0.0003362652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000931056,"about_ca_topic_score_gemma":0.001069177,"domain_scores_codex":[0.9983047,0.00002539285,0.0002656325,0.000870384,0.0001647201,0.0003691917],"domain_scores_gemma":[0.9972867,0.0005235065,0.0001455684,0.001811695,0.00007240327,0.0001600767],"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":[0.00001389957,0.0002608991,0.01099669,0.0002007061,0.00005794918,0.00005592232,0.002746776,0.0000071847,0.0007232859,0.002031985,0.009862135,0.9730425],"study_design_scores_gemma":[0.001224773,0.0001798406,0.002636902,0.0002516746,0.00006462439,0.00008856204,0.0009046115,0.9715059,0.0003637273,0.00002444901,0.02202272,0.0007322169],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1485599,0.0001306717,0.8481073,0.0003895434,0.000429063,0.0001536665,0.001182819,0.0001969372,0.0008500995],"genre_scores_gemma":[0.714038,0.00000808796,0.2844194,0.000124814,0.0002216401,0.00003001288,0.0009029907,0.0000261592,0.0002289658],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9723104,"threshold_uncertainty_score":0.9005491,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414033870","doi":"10.1007/s10618-025-01158-8","title":"Detecting and reacting to smart home novelties","year":2025,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Network for Business Sustainability","funders":"Defense Advanced Research Projects Agency; National Institutes of Health; National Science Foundation","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.03636783725970738,"gpt":0.3125553640990832,"spread":0.2761875268393759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007028707,0.0001778046,0.000218956,0.0002611027,0.0002471804,0.0008688878,0.001162335,0.0000578654,4.141527e-7],"category_scores_gemma":[0.0006594614,0.000172417,0.00001435404,0.000429698,0.00006290326,0.002038634,0.004953078,0.0001199344,0.000004579254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002211081,"about_ca_system_score_gemma":0.00009204408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001320205,"about_ca_topic_score_gemma":0.0001919834,"domain_scores_codex":[0.9985772,0.00004767171,0.0002295491,0.0007730906,0.00008960863,0.0002829012],"domain_scores_gemma":[0.9980706,0.000463424,0.00006175001,0.001290758,0.00003621024,0.00007724136],"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":[0.00001500844,0.00005198387,0.01799797,0.000125701,0.00004589805,0.00001178833,0.003366373,1.464531e-7,0.001668309,0.005453178,0.01609216,0.9551715],"study_design_scores_gemma":[0.006115146,0.002073359,0.191786,0.01670648,0.0006207894,0.000734457,0.03648766,0.1727416,0.06531206,0.01167699,0.4865113,0.009234156],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7623022,0.001533696,0.2255086,0.0004724055,0.0006716693,0.000200356,0.0002555908,0.0005662417,0.008489294],"genre_scores_gemma":[0.846014,0.0000594098,0.1524471,0.0002084791,0.00007219225,0.00001722127,0.00009320495,0.0000142947,0.001074042],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9459373,"threshold_uncertainty_score":0.8378705,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2093446553","doi":"10.1007/s10618-005-0022-6","title":"An Erratum on #x201C;Pushing Convertible Constraints in Frequent Itemset Mining#x201D;","year":2006,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Prefix; Order (exchange); Combinatorics; Convertible; Function (biology); Mathematics; Physics; Philosophy; Linguistics; Biology; Business; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.03631538169184479,"gpt":0.2998001775418355,"spread":0.2634847958499907,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007052582,0.0002672709,0.0002898852,0.0002233728,0.0002264624,0.0009284169,0.001653977,0.0001027743,0.00000848193],"category_scores_gemma":[0.00007541623,0.0002559418,0.00002783176,0.0004154217,0.0002001327,0.002784896,0.0006467846,0.0001863521,0.00003911186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000408879,"about_ca_system_score_gemma":0.0001814537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003655609,"about_ca_topic_score_gemma":0.0006125271,"domain_scores_codex":[0.9977291,0.00009899704,0.0004256688,0.001087913,0.0001976724,0.0004606584],"domain_scores_gemma":[0.9976689,0.0002469826,0.000128491,0.001782299,0.00003984534,0.0001334686],"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":[0.00004504642,0.002649887,0.02722658,0.0001597415,0.00008141425,0.000150281,0.008243206,0.00007103648,0.005418102,0.07735839,0.2160312,0.6625651],"study_design_scores_gemma":[0.005213499,0.001059942,0.08772157,0.00214328,0.0001019343,0.0002398177,0.007623123,0.7843979,0.001943137,0.003188537,0.1026624,0.00370485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8707883,0.001459458,0.09385632,0.0007511005,0.001513931,0.0004888476,0.003478286,0.0004021911,0.02726158],"genre_scores_gemma":[0.9498852,0.00003749686,0.04614316,0.0001923838,0.0002632739,0.00003692296,0.002762854,0.0000273666,0.0006512644],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7843269,"threshold_uncertainty_score":0.9999893,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401666276","doi":"10.1007/s10618-024-01054-7","title":"Bayesian network Motifs for reasoning over heterogeneous unlinked datasets","year":2024,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; University of Toronto; University of New Brunswick","funders":"","keywords":"Computer science; Probabilistic logic; Bayesian network; Python (programming language); Data mining; Aggregate (composite); Real world data; Bayesian probability; Machine learning; Set (abstract data type); Artificial intelligence; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.1674946705782729,"gpt":0.4358667777938899,"spread":0.2683721072156171,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004624117,0.0002314046,0.0003383857,0.0001706186,0.0003175814,0.002682449,0.00148112,0.00008105216,0.00006901364],"category_scores_gemma":[0.001592132,0.0001803917,0.00007776871,0.0004986452,0.0001191103,0.002316508,0.002194312,0.000108688,0.00008928861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002245979,"about_ca_system_score_gemma":0.0001074058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003748714,"about_ca_topic_score_gemma":0.0004990714,"domain_scores_codex":[0.9970461,0.0001860787,0.0005886095,0.001307238,0.0004211558,0.0004508742],"domain_scores_gemma":[0.9957396,0.001982805,0.0001001416,0.001998252,0.00003766196,0.0001415711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004114622,0.00005423227,0.0003234607,0.0001055172,0.0001060185,0.00003659696,0.0006606451,0.00007571885,0.000007249033,0.005679967,0.763801,0.2291085],"study_design_scores_gemma":[0.0002618789,0.00005913406,0.0002734814,0.000268953,0.00008943635,0.00001332386,0.0007255858,0.169614,0.000009147724,0.003017233,0.8253931,0.0002747749],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07173932,0.03800225,0.7337181,0.00128708,0.01056449,0.001589811,0.1344846,0.0005574279,0.008056971],"genre_scores_gemma":[0.8948025,0.000577729,0.02130219,0.0009935668,0.003098583,0.00009195967,0.06366882,0.0001142447,0.0153504],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8230632,"threshold_uncertainty_score":0.9983529,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3097249106","doi":"10.1007/s10618-020-00720-w","title":"An exemplar-based clustering using efficient variational message passing","year":2020,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Cluster analysis; Computer science; Correlation clustering; Message passing; Affinity propagation; Constrained clustering; Graph partition; CURE data clustering algorithm; Canopy clustering algorithm; Data mining; Graph; Theoretical computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1118581280584065,"gpt":0.3593757391597357,"spread":0.2475176111013292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004892041,0.0001929901,0.0002078521,0.0001043575,0.0003645295,0.0008891634,0.00136218,0.00005696928,0.000003879956],"category_scores_gemma":[0.0001814179,0.0001924359,0.00002541384,0.0004204809,0.00006212841,0.001891326,0.001808003,0.0001623994,0.000006101256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005523118,"about_ca_system_score_gemma":0.0002806964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001519078,"about_ca_topic_score_gemma":0.000008904171,"domain_scores_codex":[0.9979986,0.0001438463,0.0002531769,0.0008980238,0.0003134246,0.0003929171],"domain_scores_gemma":[0.9984917,0.0001906441,0.00008294034,0.0009337211,0.00006224165,0.0002387512],"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":[0.0002505058,0.0009777207,0.002404902,0.0009418228,0.000173423,0.0003897494,0.02293442,0.3440466,0.05828543,0.002244908,0.0009348159,0.5664157],"study_design_scores_gemma":[0.0004435211,0.00006712917,0.0003241969,0.00009051457,0.000008799915,0.00001287756,0.0002582145,0.9976004,0.0003853923,0.00001118968,0.0005547426,0.000242983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04936391,0.0002606514,0.9493402,0.0003026434,0.0002173833,0.00009578186,0.0001165177,0.0001325009,0.0001704626],"genre_scores_gemma":[0.6816106,0.000002973518,0.3177821,0.0001487023,0.0002452376,0.000004906492,0.0001596997,0.00002412372,0.00002164212],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6535539,"threshold_uncertainty_score":0.8574224,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2810490377","doi":"10.1007/s10618-020-00677-w","title":"Model-based exception mining for object-relational data","year":2020,"lang":"en","type":"preprint","venue":"Data Mining and Knowledge Discovery","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Object (grammar); Outlier; Data mining; Metric (unit); Bayesian network; Probabilistic logic; Relational model; Representation (politics); Relational database; Population; Statistical relational learning; Artificial intelligence; Object model; Graphical model; Data modeling; Statistical model; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.2050746449930389,"gpt":0.3555595803813095,"spread":0.1504849353882706,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008407271,0.0004107099,0.0004483671,0.0001565233,0.0003751598,0.001175031,0.005108274,0.0002430928,0.000002818237],"category_scores_gemma":[0.000400643,0.0004268358,0.00006762198,0.0002465324,0.0001123595,0.002230309,0.01281509,0.0003229895,0.0000143741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004175756,"about_ca_system_score_gemma":0.001161541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000234466,"about_ca_topic_score_gemma":0.00005927711,"domain_scores_codex":[0.9963353,0.00006383267,0.0005361662,0.002429541,0.0002682605,0.0003668566],"domain_scores_gemma":[0.994094,0.000530649,0.0003201588,0.004767869,0.0001123981,0.000174984],"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":[0.00004918402,0.0004089068,0.0003211457,0.0008806371,0.0002380262,0.000006183033,0.003307938,0.00237235,0.0001436121,0.01253683,0.2946248,0.6851104],"study_design_scores_gemma":[0.0004444029,0.00003493344,0.0001759408,0.0003087851,0.0001012352,0.000002940543,0.0001136782,0.9808395,0.00001185382,0.001230231,0.01623809,0.0004984478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002026797,0.001083924,0.9644464,0.0009516873,0.000623437,0.0004304899,0.02970514,0.0002005079,0.0005315833],"genre_scores_gemma":[0.0661215,0.00007788814,0.8095101,0.000219734,0.0007852207,0.000186227,0.1225033,0.00005237747,0.0005436883],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9784671,"threshold_uncertainty_score":0.9998618,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4417267046","doi":"10.1007/s10618-025-01180-w","title":"Certifying robustness of graph convolutional networks for node perturbation with polyhedra abstract interpretation","year":2025,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Nemzeti Kutatási Fejlesztési és Innovációs Hivatal; Mitacs; Knut och Alice Wallenbergs Stiftelse","keywords":"Robustness (evolution); Graph; Convolutional neural network; Adversarial system; Polyhedron; Training set","retraction":null,"screen_n_in":null,"score":{"opus":0.03197076562914049,"gpt":0.2958814579966345,"spread":0.263910692367494,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001962275,0.0001371937,0.0001807224,0.0001407043,0.0001441112,0.000130402,0.0005319394,0.0000595924,4.951567e-7],"category_scores_gemma":[0.00006867203,0.0001162421,0.00003233689,0.000380948,0.0001040753,0.001760836,0.0002929944,0.00008693375,1.094855e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000158467,"about_ca_system_score_gemma":0.00008272872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004785639,"about_ca_topic_score_gemma":0.00004242464,"domain_scores_codex":[0.9990012,0.00002623866,0.0002454489,0.0004531824,0.00008372837,0.0001902079],"domain_scores_gemma":[0.9987323,0.0004977957,0.0001377869,0.0004965035,0.0001031825,0.00003240101],"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":[0.00169849,0.0005271618,0.01786839,0.001076374,0.0005186288,0.000006633192,0.002997268,0.2440348,0.000728432,0.07295075,0.009889998,0.6477031],"study_design_scores_gemma":[0.00046127,0.00004961113,0.007016617,0.0004271077,0.00002893058,0.00000381256,0.0001504233,0.9910749,0.00006735479,0.0004479843,0.0001246528,0.0001473357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03744911,0.001630023,0.9599305,0.00009015579,0.0004375163,0.0001585167,0.00006549373,0.00004080784,0.0001978542],"genre_scores_gemma":[0.965618,0.00004863987,0.03360411,0.0000483242,0.00006486536,0.00002077352,0.000416216,0.000008043251,0.0001710196],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9281689,"threshold_uncertainty_score":0.4740216,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}