{"meta":{"query_hash":"ad6497fcacec","filters":{"venue":"Data Mining and Knowledge Discovery"},"cohort_total":49,"direct_labels_cover":0,"predictions_cover":49,"exported":49,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/ad6497fcacec","api":"https://metacan.xera.ac/api/v1/cohort?venue=Data+Mining+and+Knowledge+Discovery"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.051266264070474,"score_gpt":0.2920698709287232,"score_spread":0.24080360685824923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1603563923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46777833,0.00708356,0.48485848,0.0006732441,0.0010438403,0.00070312165,0.0033373602,0.0006667371,0.033855345],"genre_scores_gemma":[0.77973634,0.00015239597,0.2164375,0.00016046155,0.00014645502,0.000057842106,0.0020872147,0.000042700474,0.001179089],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983446,0.0000616669,0.00025163623,0.0008269906,0.00017155908,0.00034354755],"domain_scores_gemma":[0.9978484,0.00019750955,0.00012156072,0.0016190928,0.00006933257,0.00014411283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004665361,0.00021261965,0.00019399915,0.00008807794,0.00032678808,0.0008588638,0.001137236,0.000054238502,0.000010306642],"category_scores_gemma":[0.0001899791,0.00017482995,0.00001786299,0.00042154785,0.000071838826,0.0028062842,0.0005901269,0.00014185364,0.00003576881],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012699968,0.00094519067,0.028595945,0.0002336326,0.0002340454,0.00016833257,0.00875432,0.000013783685,0.0010327646,0.09543027,0.055614725,0.8089643],"study_design_scores_gemma":[0.0047527514,0.00064177334,0.03096133,0.0023414209,0.00028551798,0.0019293164,0.009515189,0.10529615,0.0050465553,0.0012192692,0.83328146,0.0047292695],"about_ca_topic_score_codex":0.00004510021,"about_ca_topic_score_gemma":0.0000810554,"teacher_disagreement_score":0.80423504,"about_ca_system_score_codex":0.000026949807,"about_ca_system_score_gemma":0.0002010904,"threshold_uncertainty_score":0.8282044},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.12267994048886485,"score_gpt":0.3328434296471469,"score_spread":0.21016348915828206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964878798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6446889,0.0039476748,0.29823104,0.010850749,0.008457932,0.0005197827,0.019644951,0.0027762174,0.010882737],"genre_scores_gemma":[0.6013959,0.00009333115,0.38585705,0.0001258254,0.0003332219,0.000006742753,0.011908417,0.00003358322,0.00024593106],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704856,0.00017340988,0.00036710355,0.0016261967,0.0002686843,0.00051607296],"domain_scores_gemma":[0.9589917,0.0015525124,0.00020889344,0.039001554,0.00010882188,0.00013652485],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.0045589185,0.00024723663,0.00027315484,0.0001788018,0.00034881948,0.0052395947,0.08226827,0.00019986994,0.000006038807],"category_scores_gemma":[0.12080545,0.00022906435,0.000015182195,0.00065596454,0.0002115382,0.024086546,0.38996562,0.0006699981,0.000019867819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049200094,0.000071708666,0.020030957,0.000032776195,0.000028554063,0.000018308037,0.0001935695,7.525796e-8,0.0006284548,0.0005544715,0.7576349,0.22080131],"study_design_scores_gemma":[0.0010722023,0.00008224145,0.036913216,0.00025288522,0.00004010998,0.000168835,0.0006023638,0.8874225,0.000865186,0.0065988707,0.06451005,0.001471523],"about_ca_topic_score_codex":0.00042962414,"about_ca_topic_score_gemma":0.0039465716,"teacher_disagreement_score":0.88742244,"about_ca_system_score_codex":0.000013780811,"about_ca_system_score_gemma":0.00028794172,"threshold_uncertainty_score":0.99579304},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03094374567114801,"score_gpt":0.35021581576609206,"score_spread":0.31927207009494407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972588194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07364662,0.007409867,0.86154056,0.038103513,0.0018884034,0.0031035445,0.008752585,0.00097266276,0.0045822323],"genre_scores_gemma":[0.67048895,0.00006200478,0.31763425,0.0015170854,0.0014742742,0.00016200701,0.004288467,0.000044397184,0.0043285433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874675,0.000094851195,0.00017724601,0.0006129012,0.00012656472,0.00024169472],"domain_scores_gemma":[0.99843085,0.00033315952,0.000051705985,0.00079527346,0.00014482939,0.00024415422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030803023,0.00013620836,0.00015609742,0.00008820568,0.00020238699,0.00028302218,0.00045851475,0.00004295548,0.0000033734357],"category_scores_gemma":[0.0012274696,0.00012655227,0.000018604624,0.00032341492,0.00002471483,0.0012951889,0.00035748185,0.00009788299,0.000031851512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049450883,0.0004142791,0.0021611156,0.00041366598,0.000058495774,0.00004830939,0.027839,0.0002863199,0.00011686293,0.0108018685,0.2521055,0.7052601],"study_design_scores_gemma":[0.0010223999,0.0013175533,0.013372206,0.0003208782,0.000067789995,0.000016329708,0.0010649606,0.74450487,0.00003563646,0.00023809474,0.23750645,0.00053284125],"about_ca_topic_score_codex":0.000003487169,"about_ca_topic_score_gemma":0.000009389459,"teacher_disagreement_score":0.7442185,"about_ca_system_score_codex":0.00003949928,"about_ca_system_score_gemma":0.00049121183,"threshold_uncertainty_score":0.51606524},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16263658103088974,"score_gpt":0.34844677869115825,"score_spread":0.18581019766026852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999518899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07254567,0.0016884267,0.88175964,0.00066967914,0.0008041531,0.00027593801,0.0004258714,0.000728557,0.04110204],"genre_scores_gemma":[0.937066,0.000054843054,0.060456537,0.00017805956,0.0002590801,0.000018811255,0.00057472585,0.000018663843,0.0013732614],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986051,0.00004334907,0.00019207786,0.0008007951,0.00014208707,0.00021659571],"domain_scores_gemma":[0.99695504,0.000121453006,0.00008735331,0.0026680815,0.000036856356,0.00013119263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005112116,0.00014537357,0.00015623852,0.00009960863,0.00019491969,0.00045489884,0.0021428978,0.00004924795,0.0000017522864],"category_scores_gemma":[0.0001560878,0.00013275303,0.000014611388,0.00034874293,0.00005128846,0.0019661728,0.0028872425,0.00009488208,0.00004499666],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020024052,0.00031613483,0.0017566299,0.000040877363,0.00005550854,0.000023881714,0.0035272837,0.000006282246,0.00025223912,0.028677413,0.18960401,0.7757197],"study_design_scores_gemma":[0.0011330822,0.0005093457,0.00179157,0.0003607581,0.00007027188,0.00013664975,0.004546369,0.47009313,0.0015384731,0.0017368217,0.5167896,0.0012939202],"about_ca_topic_score_codex":0.000032066182,"about_ca_topic_score_gemma":0.00003073827,"teacher_disagreement_score":0.8645204,"about_ca_system_score_codex":0.000022532917,"about_ca_system_score_gemma":0.00014128882,"threshold_uncertainty_score":0.54135114},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0726774133759716,"score_gpt":0.2994970904899545,"score_spread":0.22681967711398288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002041176","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27500522,0.002471363,0.65970147,0.0002984719,0.0014508624,0.000120863886,0.00015526603,0.00018627939,0.06061018],"genre_scores_gemma":[0.8029202,0.000052461295,0.19428936,0.00019844533,0.00040622707,0.0000028038946,0.0006452779,0.000013736347,0.001471466],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99865013,0.00003635687,0.00025093355,0.0005774126,0.00017101104,0.00031416572],"domain_scores_gemma":[0.9986705,0.0002966482,0.00007345919,0.00081151404,0.000041933377,0.00010593166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009250945,0.00014141512,0.00014852393,0.00010697644,0.00028117874,0.00024139212,0.00072222634,0.00007209503,0.000004573147],"category_scores_gemma":[0.00017009831,0.00012326761,0.000026154217,0.0003219213,0.000076492935,0.0017394713,0.0011485268,0.00010601716,0.00002214306],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061866056,0.00043510317,0.060862135,0.0000740198,0.000093208306,0.00017244277,0.014018512,0.0000069312887,0.00014571991,0.22590566,0.053640466,0.64458394],"study_design_scores_gemma":[0.0034018822,0.00047906456,0.2586576,0.0005659459,0.000105816776,0.00033836582,0.0069966563,0.24205202,0.00020761845,0.0022665358,0.48269507,0.0022334042],"about_ca_topic_score_codex":0.000012189695,"about_ca_topic_score_gemma":0.000058542675,"teacher_disagreement_score":0.64235055,"about_ca_system_score_codex":0.000017458062,"about_ca_system_score_gemma":0.000077321754,"threshold_uncertainty_score":0.50267076},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09257415986957443,"score_gpt":0.3536923389834265,"score_spread":0.26111817911385204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005934890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19604352,0.0024265232,0.796412,0.00079167355,0.0006971049,0.00064734335,0.00021916536,0.00028049556,0.0024822005],"genre_scores_gemma":[0.84641707,0.00020598162,0.15012081,0.00004638406,0.00024652408,0.000058318983,0.0008249712,0.000034689616,0.0020452386],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978982,0.000104361854,0.0002557066,0.0010502917,0.0002115408,0.00047986017],"domain_scores_gemma":[0.99675715,0.00027048704,0.000052244184,0.00275922,0.00004755203,0.00011335552],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005122537,0.00017671855,0.00022083834,0.00019528045,0.00011087055,0.0009675179,0.003463923,0.00006333683,0.0000048992038],"category_scores_gemma":[0.0003724272,0.00015534389,0.000009682387,0.0005685687,0.00008873466,0.0061349953,0.012190329,0.00021025204,0.00004977625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018727977,0.00032676352,0.010461542,0.00027901778,0.000046835838,0.0001243381,0.0052985,0.000049424256,0.0009059219,0.00046575916,0.011166283,0.9708569],"study_design_scores_gemma":[0.00041466628,0.000038309958,0.0072396575,0.000082946826,0.000003119412,0.0000314366,0.0006492968,0.98854095,0.00003809048,0.00010787488,0.0025867142,0.0002669639],"about_ca_topic_score_codex":0.000526931,"about_ca_topic_score_gemma":0.0004565036,"teacher_disagreement_score":0.9884915,"about_ca_system_score_codex":0.000041893396,"about_ca_system_score_gemma":0.00016061927,"threshold_uncertainty_score":0.9957989},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16375358936821682,"score_gpt":0.3177989488666944,"score_spread":0.15404535949847759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010971425","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14298168,0.0033719377,0.83906645,0.00078949437,0.0004231759,0.00042163202,0.00009029728,0.00010528128,0.012750033],"genre_scores_gemma":[0.9748136,0.000084134124,0.024566455,0.00011739513,0.0000833452,0.00002290721,0.000025492303,0.000012719374,0.00027395308],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984991,0.00016960499,0.0001943948,0.00050801446,0.0002608994,0.00036796342],"domain_scores_gemma":[0.9980503,0.00023162943,0.000051284755,0.0015922029,0.000025172281,0.000049432405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011483488,0.00015194253,0.00014295134,0.00008335234,0.00028639706,0.00035680638,0.002941236,0.000042085376,8.7851646e-7],"category_scores_gemma":[0.00010216242,0.00008779957,0.000024197187,0.00032209913,0.00011575622,0.0014072721,0.0022848723,0.00028345172,0.000006538445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011957717,0.0009155978,0.0044400245,0.00035405753,0.00016078168,0.00028051453,0.29901752,0.0015666436,0.0018988377,0.035043687,0.0064147837,0.64978796],"study_design_scores_gemma":[0.0002830366,0.00002738603,0.0055781584,0.0001536824,0.000006515913,0.000045689743,0.0024647454,0.9894086,0.000078751305,0.00079044414,0.000957433,0.00020552841],"about_ca_topic_score_codex":0.000066208384,"about_ca_topic_score_gemma":0.0001617985,"teacher_disagreement_score":0.98784196,"about_ca_system_score_codex":0.000027445765,"about_ca_system_score_gemma":0.00008664483,"threshold_uncertainty_score":0.54655975},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.1710043822641238,"score_gpt":0.36814963869519823,"score_spread":0.19714525643107444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032708445","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9567773,0.00071553566,0.041620057,0.000041255338,0.000089654226,0.00029690028,0.0003163014,0.00003368802,0.000109347],"genre_scores_gemma":[0.9965316,0.000101975274,0.0026448658,0.000035088968,0.0001997731,0.000012856983,0.00023113642,0.000021876793,0.00022080117],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986778,0.00012436042,0.00040790622,0.0004719004,0.00016971119,0.00014831945],"domain_scores_gemma":[0.9968214,0.0020066774,0.00016376891,0.0008491589,0.000087618886,0.000071356466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005785702,0.00017889554,0.0002820758,0.000067897716,0.00038660303,0.00019390573,0.00022410357,0.0001344851,0.000011804106],"category_scores_gemma":[0.0008848998,0.00012455654,0.000028366707,0.0001528536,0.00010040043,0.0006785636,0.0001749479,0.0001731504,0.0000030163283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004388741,0.0015963262,0.82532007,0.00006891651,0.00080726447,0.00037692374,0.08968792,0.001585194,0.00002588177,0.00092678115,0.023486122,0.055679724],"study_design_scores_gemma":[0.0027066206,0.000088035886,0.03653254,0.00011168276,0.00059718196,0.00021298823,0.026435716,0.9310893,0.0000012643524,0.0015956558,0.00033055485,0.00029848862],"about_ca_topic_score_codex":0.0002745634,"about_ca_topic_score_gemma":0.001754422,"teacher_disagreement_score":0.9295041,"about_ca_system_score_codex":0.000018649247,"about_ca_system_score_gemma":0.000087617445,"threshold_uncertainty_score":0.5079268},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.051955979837728185,"score_gpt":0.3072964131251066,"score_spread":0.2553404332873784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061678866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9866737,0.0022943176,0.0035608346,0.00014216785,0.00029976672,0.00019937701,0.00030059696,0.00006451887,0.0064647086],"genre_scores_gemma":[0.99354994,0.000054419037,0.0005198411,0.000023646375,0.0015505102,0.00002954363,0.0034662928,0.000020142274,0.00078564265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988128,0.000071186645,0.0002651097,0.00047102684,0.000088813256,0.00029108746],"domain_scores_gemma":[0.9992043,0.00017690747,0.000095629504,0.0004228862,0.000042875672,0.000057452267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018739027,0.00017480829,0.00030502892,0.00006443785,0.00015126268,0.0007793636,0.00040720796,0.00004527058,0.00020491678],"category_scores_gemma":[0.000018798382,0.00017820219,0.000047522895,0.00022048675,0.000059037236,0.0017401425,0.0006923609,0.00014960286,0.00002304052],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025526533,0.0005783297,0.22032194,0.00002734594,0.0003693913,0.0000036353126,0.004277977,0.000018753732,0.00015960766,0.0036094163,0.14455055,0.6260575],"study_design_scores_gemma":[0.0038861101,0.0001439781,0.33954415,0.0026345495,0.0008532021,0.0000012480374,0.046075907,0.53528696,0.00033054914,0.017882997,0.04950076,0.0038595647],"about_ca_topic_score_codex":0.00081094285,"about_ca_topic_score_gemma":0.00035804932,"teacher_disagreement_score":0.622198,"about_ca_system_score_codex":0.000016397502,"about_ca_system_score_gemma":0.000030197296,"threshold_uncertainty_score":0.7515421},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); Fuzzy clustering; Machine learning; Support vector machine; Data mining","score_opus":0.07186957610495115,"score_gpt":0.33223066228592213,"score_spread":0.260361086180971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072732320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047546364,0.0012285658,0.9485965,0.00015999473,0.00025423322,0.000118257776,0.0005409045,0.00014896759,0.0014062554],"genre_scores_gemma":[0.61043584,0.0001391495,0.3819658,0.00005243966,0.0008981257,0.000016810789,0.0035734372,0.000060115744,0.0028582746],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800634,0.00006479952,0.00020967622,0.0010445089,0.0002608342,0.0004138588],"domain_scores_gemma":[0.996532,0.00017146805,0.00004756732,0.0031218694,0.00004051541,0.00008657637],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00049023004,0.00017834101,0.00018515809,0.00009239249,0.00022924818,0.00071589043,0.0029136143,0.00004533082,0.0000024091128],"category_scores_gemma":[0.00006487053,0.00014371771,0.000009930117,0.0003011455,0.000106476684,0.004600593,0.008966632,0.00013186138,0.000015542037],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013026033,0.00041318504,0.004966421,0.00027558338,0.00007413044,0.00028299575,0.0013482948,0.00059312733,0.0011184782,0.0013690534,0.017622493,0.971806],"study_design_scores_gemma":[0.0006023248,0.000097260505,0.0011342277,0.00015314053,0.000010209926,0.000080687656,0.00018500973,0.96649575,0.00016510916,0.000045698744,0.030721953,0.00030860447],"about_ca_topic_score_codex":0.0001279364,"about_ca_topic_score_gemma":0.0005803453,"teacher_disagreement_score":0.97149736,"about_ca_system_score_codex":0.00002082783,"about_ca_system_score_gemma":0.0001192684,"threshold_uncertainty_score":0.99904865},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.10575153970874877,"score_gpt":0.3499721572955075,"score_spread":0.24422061758675873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073184692","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08875743,0.0014709776,0.9033168,0.0005699631,0.0002847929,0.00037514602,0.0040439824,0.00025142846,0.00092949154],"genre_scores_gemma":[0.1743089,0.00008017158,0.81623673,0.00021230691,0.0008675541,0.00008900134,0.0066037513,0.000037461694,0.0015641352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811995,0.00003639669,0.00032358535,0.0010644912,0.00013542335,0.00032013608],"domain_scores_gemma":[0.9972936,0.000545241,0.00013728077,0.0018063417,0.00010918533,0.000108382286],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00069982145,0.00019567765,0.00019770193,0.00011097407,0.00069774076,0.001429673,0.0012900729,0.00006419804,0.0000040371633],"category_scores_gemma":[0.00024838504,0.00017862432,0.000017992803,0.0002800479,0.000115798444,0.0052845646,0.0011106314,0.00010190102,0.00000985934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005386461,0.0007510928,0.017438281,0.00024608758,0.00032036158,0.000008500019,0.008280898,0.0002714825,0.0005611802,0.024737516,0.2393409,0.7079898],"study_design_scores_gemma":[0.00055723544,0.00007047879,0.0005858307,0.00010678493,0.00004367554,0.000054722637,0.00036507583,0.89634115,0.00014626265,0.00007499569,0.10133401,0.00031979644],"about_ca_topic_score_codex":0.000019220372,"about_ca_topic_score_gemma":0.000543781,"teacher_disagreement_score":0.89606965,"about_ca_system_score_codex":0.000026954038,"about_ca_system_score_gemma":0.0002938526,"threshold_uncertainty_score":0.99960697},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.040746817394101985,"score_gpt":0.2935640976154808,"score_spread":0.25281728022137884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075949491","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027717065,0.0007182951,0.970082,0.0001362797,0.00014174628,0.0005194106,0.000050158636,0.00020674376,0.00042832282],"genre_scores_gemma":[0.97569793,0.00011169349,0.022839852,0.00032459162,0.0003221848,0.00042117774,0.00004611711,0.000021778325,0.00021465779],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984279,0.00010555279,0.0002846618,0.00070845586,0.0001272138,0.00034616518],"domain_scores_gemma":[0.9983899,0.00012199876,0.00011610314,0.0010886695,0.00006225076,0.00022106334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005413844,0.00022289561,0.00024282865,0.00010838146,0.0004881249,0.00028351386,0.0003408306,0.00010118148,0.0000038000542],"category_scores_gemma":[0.000025783189,0.00019088594,0.000027961023,0.00046771948,0.00010329315,0.0009820189,0.00047158377,0.0001488488,0.000027547785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004324258,0.000121400924,0.0007853568,0.00003055074,0.000031161773,4.2094402e-7,0.00033456396,0.000029193558,0.00026399802,0.0015561595,0.00097341073,0.99583054],"study_design_scores_gemma":[0.0022257746,0.0016681388,0.027088301,0.0005228881,0.0003534322,0.00038049204,0.0012071362,0.14439769,0.022983732,0.0020875407,0.7944059,0.0026790153],"about_ca_topic_score_codex":0.00018465739,"about_ca_topic_score_gemma":0.0011695654,"teacher_disagreement_score":0.99315155,"about_ca_system_score_codex":0.00005321857,"about_ca_system_score_gemma":0.00004449581,"threshold_uncertainty_score":0.7784103},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04812423122534112,"score_gpt":0.2999252304469889,"score_spread":0.2518009992216478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078064242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6607854,0.0027477907,0.32470787,0.0012573604,0.00091499323,0.0003636606,0.0015207056,0.00028103823,0.0074211974],"genre_scores_gemma":[0.87221664,0.00011215274,0.1262277,0.0001939572,0.000117547934,0.000029898445,0.0008815663,0.000018697156,0.00020183649],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828464,0.000039980343,0.0003458346,0.00080896134,0.00014167384,0.00037893825],"domain_scores_gemma":[0.99839956,0.00017511212,0.00008984292,0.0011868125,0.00002910577,0.00011957618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006001483,0.00019144762,0.00023389122,0.00016794694,0.00017714754,0.00065966754,0.001370053,0.00006857543,0.000004163047],"category_scores_gemma":[0.00014292051,0.00018805717,0.000023018925,0.00044367544,0.00017196177,0.00269697,0.0012495891,0.0001384632,0.000029680255],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012813191,0.00073985674,0.0132841505,0.00015885325,0.00008887381,0.00016944093,0.021570122,0.000057247977,0.0015872726,0.06512616,0.010792939,0.88641226],"study_design_scores_gemma":[0.022787392,0.0010621059,0.077966504,0.009119489,0.0002618,0.0014824314,0.045048676,0.64900684,0.0069622556,0.011909976,0.16587628,0.00851623],"about_ca_topic_score_codex":0.00020480421,"about_ca_topic_score_gemma":0.0003767018,"teacher_disagreement_score":0.877896,"about_ca_system_score_codex":0.000050416453,"about_ca_system_score_gemma":0.00026076796,"threshold_uncertainty_score":0.7668749},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Tree (set theory); Cluster (spacecraft); Variety (cybernetics); Data mining; Artificial intelligence; Extraction (chemistry); Machine learning; Mathematics","score_opus":0.06040773208466434,"score_gpt":0.3443362713711306,"score_spread":0.2839285392864663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079040080","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36987096,0.0010674546,0.62821954,0.0001400122,0.00015384395,0.00021404018,0.00024399813,0.000036924623,0.00005319574],"genre_scores_gemma":[0.3225427,0.00022509616,0.6765233,0.000035179044,0.00014072609,0.00006279472,0.00023162863,0.00002083375,0.00021773207],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985679,0.00006793963,0.00025508416,0.000650616,0.00015507433,0.00030342516],"domain_scores_gemma":[0.9975732,0.0012547275,0.000072988994,0.00089851714,0.00008317818,0.00011738932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023873101,0.00017131567,0.0002562963,0.00012577427,0.00016704587,0.00039684348,0.00081339077,0.0000904069,0.000005448956],"category_scores_gemma":[0.000309196,0.00015689281,0.000029309589,0.00019107437,0.000170338,0.0028144687,0.0014293112,0.0001461741,0.0000036251934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013595827,0.0002143146,0.0012631143,0.00041375132,0.0001542915,0.000005941819,0.0133955395,0.00009913054,0.008588029,0.0016925622,0.0017315714,0.9723058],"study_design_scores_gemma":[0.00093558896,0.0001868791,0.0029741032,0.00032600242,0.00002023509,0.000010714411,0.002441457,0.9881946,0.0011063619,0.0027652588,0.0007243263,0.00031450533],"about_ca_topic_score_codex":0.000121106765,"about_ca_topic_score_gemma":0.000014408233,"teacher_disagreement_score":0.98809546,"about_ca_system_score_codex":0.00001629306,"about_ca_system_score_gemma":0.00007075935,"threshold_uncertainty_score":0.6397903},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.19241456294856188,"score_gpt":0.35658341041610714,"score_spread":0.16416884746754526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086829791","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013826852,0.0009646261,0.981401,0.000052971518,0.0003861318,0.0001221459,0.00039987365,0.00007760885,0.0027687699],"genre_scores_gemma":[0.75191784,0.00019329746,0.24640584,0.000025815503,0.00019236818,0.000009209494,0.00054614776,0.000030095343,0.00067938585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787855,0.00011335319,0.0003270568,0.0010047759,0.00026106348,0.00041521498],"domain_scores_gemma":[0.9959918,0.00032589052,0.00009042482,0.0033675819,0.00006336138,0.00016092806],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00064493757,0.00018228388,0.0002886598,0.00014427137,0.00012945414,0.00015688755,0.0046125436,0.000069165435,0.000005830776],"category_scores_gemma":[0.00037713494,0.00016154672,0.000022041007,0.00034316676,0.00023404896,0.002905003,0.017480293,0.00022132436,0.000012942791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000095895026,0.0004998183,0.0021888402,0.0003101905,0.0001349226,0.00017150964,0.011529577,0.000011708066,0.00044643806,0.005399827,0.003187992,0.97602326],"study_design_scores_gemma":[0.0007619996,0.0002582925,0.0052296277,0.00015855007,0.000026535183,0.00012482831,0.00072974263,0.9872235,0.0004315386,0.0010165214,0.0035257316,0.0005131421],"about_ca_topic_score_codex":0.00009914489,"about_ca_topic_score_gemma":0.000074025695,"teacher_disagreement_score":0.98721176,"about_ca_system_score_codex":0.000020237809,"about_ca_system_score_gemma":0.00016007943,"threshold_uncertainty_score":0.9904661},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02107824697066401,"score_gpt":0.2557087373958644,"score_spread":0.2346304904252004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091837657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14855991,0.00013067167,0.8481073,0.00038954342,0.00042906305,0.00015366646,0.0011828194,0.00019693724,0.0008500995],"genre_scores_gemma":[0.71403795,0.00000808796,0.2844194,0.00012481402,0.00022164006,0.000030012881,0.0009029907,0.000026159205,0.00022896584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830467,0.00002539285,0.00026563247,0.000870384,0.00016472011,0.00036919166],"domain_scores_gemma":[0.99728674,0.00052350655,0.00014556835,0.0018116947,0.00007240327,0.00016007671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041293225,0.00024380982,0.00022274221,0.00010418146,0.00039270372,0.0009338866,0.0015067251,0.00007905204,0.0000062139984],"category_scores_gemma":[0.00022359753,0.00020581947,0.00002323355,0.00028491032,0.0002275072,0.0013081743,0.0009342375,0.0002123608,0.0000127474195],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013899571,0.00026089913,0.010996693,0.00020070608,0.000057949183,0.000055922323,0.0027467755,0.0000071847,0.0007232859,0.0020319852,0.009862135,0.97304255],"study_design_scores_gemma":[0.0012247729,0.00017984059,0.0026369016,0.00025167456,0.000064624386,0.00008856204,0.00090461154,0.9715059,0.00036372727,0.000024449013,0.022022717,0.00073221687],"about_ca_topic_score_codex":0.0000931056,"about_ca_topic_score_gemma":0.001069177,"teacher_disagreement_score":0.97231036,"about_ca_system_score_codex":0.000009311581,"about_ca_system_score_gemma":0.0003362652,"threshold_uncertainty_score":0.90054905},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03631538169184479,"score_gpt":0.29980017754183547,"score_spread":0.2634847958499907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093446553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8707883,0.001459458,0.09385632,0.00075110054,0.0015139312,0.0004888476,0.0034782863,0.00040219107,0.02726158],"genre_scores_gemma":[0.94988525,0.00003749686,0.046143163,0.00019238384,0.00026327392,0.000036922956,0.002762854,0.000027366596,0.0006512644],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772906,0.00009899704,0.00042566878,0.0010879126,0.00019767242,0.0004606584],"domain_scores_gemma":[0.9976689,0.00024698264,0.00012849104,0.0017822993,0.00003984534,0.0001334686],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007052582,0.0002672709,0.00028988518,0.0002233728,0.00022646239,0.0009284169,0.0016539773,0.000102774255,0.00000848193],"category_scores_gemma":[0.00007541623,0.00025594182,0.000027831757,0.00041542167,0.00020013266,0.0027848957,0.0006467846,0.0001863521,0.000039111863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045046418,0.0026498875,0.027226582,0.0001597415,0.000081414255,0.00015028105,0.008243206,0.00007103648,0.0054181023,0.07735839,0.21603122,0.6625651],"study_design_scores_gemma":[0.005213499,0.0010599416,0.08772157,0.00214328,0.00010193425,0.00023981769,0.0076231235,0.7843979,0.0019431373,0.0031885367,0.102662414,0.00370485],"about_ca_topic_score_codex":0.00036556093,"about_ca_topic_score_gemma":0.0006125271,"teacher_disagreement_score":0.78432685,"about_ca_system_score_codex":0.000040887902,"about_ca_system_score_gemma":0.00018145371,"threshold_uncertainty_score":0.9999893},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03959326074880023,"score_gpt":0.3087525581662589,"score_spread":0.2691592974174587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098162950","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03725997,0.00021984325,0.95769775,0.0008172377,0.0007616499,0.00023201018,0.0024521474,0.00015615748,0.0004032056],"genre_scores_gemma":[0.28716868,0.00004404531,0.7077588,0.00020903791,0.00060587336,0.00019479552,0.0031103867,0.000029415005,0.0008789708],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865085,0.000028220697,0.0002435612,0.00062810665,0.00016577265,0.0002835028],"domain_scores_gemma":[0.99874645,0.00020002117,0.00012917636,0.00077222695,0.000063737585,0.00008840838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006619374,0.00014071536,0.00014804919,0.00009334278,0.0003466206,0.0006887125,0.00078759465,0.00007417669,0.0000016691909],"category_scores_gemma":[0.00017427307,0.00014009695,0.000039281447,0.0002345738,0.000033944303,0.0018874296,0.00045567725,0.000078076744,0.000007613485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057186335,0.0010611799,0.0055026263,0.0003286495,0.00045382578,0.000010164423,0.0032436466,0.00054902874,0.0106354905,0.1440742,0.14220876,0.6918753],"study_design_scores_gemma":[0.0047617694,0.00026069753,0.0036802618,0.00038544642,0.00018359399,0.0000125044635,0.00054476113,0.77513784,0.0029148152,0.0045830463,0.20668305,0.0008522011],"about_ca_topic_score_codex":0.000029676181,"about_ca_topic_score_gemma":0.00002908777,"teacher_disagreement_score":0.7745888,"about_ca_system_score_codex":0.00016137528,"about_ca_system_score_gemma":0.0003562304,"threshold_uncertainty_score":0.66412705},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02640097352747741,"score_gpt":0.29970399963040983,"score_spread":0.27330302610293244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106700114","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029276893,0.0019015804,0.0001599984,0.00009690954,0.9876504,0.00011186218,0.004687283,0.00007190625,0.0050272904],"genre_scores_gemma":[0.0003142792,0.00058746536,0.0010618694,0.000018145414,0.9903699,0.0000141801565,0.004404083,0.00005251559,0.0031775322],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99577177,0.00033553195,0.0007632859,0.0013932546,0.0010790429,0.0006571443],"domain_scores_gemma":[0.9913553,0.0037311744,0.0006309672,0.003870559,0.00022259552,0.00018943369],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0023991594,0.00060114666,0.00093011657,0.00034078362,0.00036542074,0.0009461672,0.00547045,0.00070249866,0.000014853106],"category_scores_gemma":[0.0030142139,0.00043564467,0.0001599398,0.00062766986,0.00028623187,0.0018559975,0.00397609,0.00080660125,0.000094192685],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028092274,0.00013500488,0.000045494646,0.00010055167,0.00017190601,0.000005496748,0.0023956697,4.011549e-7,0.000009648401,0.000066719695,0.9800925,0.016948482],"study_design_scores_gemma":[0.00041838863,0.00012473651,0.000012705673,0.00061761326,0.00028863404,0.000002471007,0.00067834643,0.0006131534,0.000029857307,0.000005072193,0.9967045,0.000504526],"about_ca_topic_score_codex":0.00009502688,"about_ca_topic_score_gemma":0.00024192336,"teacher_disagreement_score":0.016611962,"about_ca_system_score_codex":0.000053358523,"about_ca_system_score_gemma":0.0009798753,"threshold_uncertainty_score":0.9999104},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06223377143017436,"score_gpt":0.29063549100603664,"score_spread":0.22840171957586228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115482638","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16534355,0.0012324364,0.8261517,0.00013858697,0.0005319418,0.00022517223,0.0009919428,0.00014235303,0.00524229],"genre_scores_gemma":[0.81126857,0.00016159753,0.18199562,0.0002725592,0.00047616864,0.0001282487,0.003911326,0.000046124045,0.001739785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974858,0.0001400067,0.00041304884,0.001256015,0.0002358509,0.0004692793],"domain_scores_gemma":[0.9973748,0.0000847287,0.00015701876,0.0021307257,0.000057801342,0.00019497004],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000626223,0.00032355633,0.00031812274,0.00013342535,0.0004049583,0.0010822976,0.0014754876,0.0000896878,0.000009347651],"category_scores_gemma":[0.00008109482,0.00029583636,0.00004480857,0.00032103638,0.00008453459,0.002180757,0.00082253537,0.00014876675,0.000021646318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059882086,0.00083695515,0.06569037,0.00018777662,0.00025957052,0.00004495326,0.011250967,0.000017457096,0.0011060716,0.0125064645,0.046091493,0.86200196],"study_design_scores_gemma":[0.002526203,0.00021900902,0.0067055775,0.00037231907,0.0001866629,0.00038687096,0.0037552272,0.91316193,0.0016892301,0.00013437215,0.06875874,0.0021038558],"about_ca_topic_score_codex":0.00020518425,"about_ca_topic_score_gemma":0.0004532245,"teacher_disagreement_score":0.91314447,"about_ca_system_score_codex":0.000041156323,"about_ca_system_score_gemma":0.00020537034,"threshold_uncertainty_score":0.9999547},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03043223887843423,"score_gpt":0.2874098398765441,"score_spread":0.2569776009981099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116064560","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48516262,0.0005469155,0.50879204,0.0010243745,0.00027175323,0.0002528855,0.0015774933,0.00026130676,0.0021106105],"genre_scores_gemma":[0.7526994,0.00012094112,0.23996638,0.00024510015,0.0006603774,0.00006011726,0.0041831215,0.00003889328,0.0020257244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807566,0.000062181694,0.00031673428,0.00094446103,0.00021045758,0.00039052364],"domain_scores_gemma":[0.9980248,0.00013501536,0.00013859716,0.0014775291,0.00008695341,0.0001370948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034065524,0.00026040018,0.00024315524,0.0001230886,0.0003168859,0.0008432153,0.0012951326,0.0000883836,0.000009813011],"category_scores_gemma":[0.000037256617,0.0002239381,0.000027243661,0.00035700397,0.0000983629,0.003001302,0.0011886776,0.00014902983,0.000029726332],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055070243,0.0005616664,0.0048788753,0.00009738216,0.00016134944,0.00003221812,0.006641196,0.000041375155,0.0015966162,0.0024123061,0.021433176,0.96208876],"study_design_scores_gemma":[0.0021905869,0.00032877832,0.009117535,0.00057817774,0.00014886155,0.00020166078,0.0011287931,0.94326544,0.00075570727,0.00004555566,0.0411676,0.0010713243],"about_ca_topic_score_codex":0.000049758717,"about_ca_topic_score_gemma":0.00076722156,"teacher_disagreement_score":0.96101743,"about_ca_system_score_codex":0.000034025416,"about_ca_system_score_gemma":0.00022037365,"threshold_uncertainty_score":0.91319305},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0352025202348579,"score_gpt":0.2851548256075449,"score_spread":0.249952305372687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154217032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8694665,0.00039073982,0.123744875,0.00020672158,0.00016480667,0.00014422633,0.0017407855,0.00010070209,0.004040689],"genre_scores_gemma":[0.935253,0.000042784424,0.06318785,0.00006154334,0.0001292234,0.000007350239,0.0009886516,0.000010698565,0.00031888654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861914,0.000036182606,0.0002735557,0.0006248115,0.00018429542,0.00026203273],"domain_scores_gemma":[0.9985238,0.00007343256,0.0001332224,0.0011404972,0.00003878451,0.00009030318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027387575,0.00018387428,0.0002298507,0.0001093448,0.00014858629,0.00031577892,0.0012297815,0.000043772718,0.000004199612],"category_scores_gemma":[0.000020349586,0.00015435244,0.000024707802,0.00027689352,0.000081597434,0.0017388839,0.00077287946,0.00007971603,0.0000046102377],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000291901,0.00043236584,0.0089327255,0.000056393015,0.00008113572,0.000022908755,0.0040574404,0.0000029017367,0.0034282077,0.0028663203,0.0073604225,0.97273],"study_design_scores_gemma":[0.009974956,0.003847947,0.12626189,0.003212299,0.00052259397,0.0005780154,0.019054487,0.79071313,0.013947664,0.00026262293,0.027688382,0.0039359764],"about_ca_topic_score_codex":0.00004097932,"about_ca_topic_score_gemma":0.00018500937,"teacher_disagreement_score":0.968794,"about_ca_system_score_codex":0.000014884667,"about_ca_system_score_gemma":0.00014111797,"threshold_uncertainty_score":0.629431},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.27892127732114425,"score_gpt":0.467167125821036,"score_spread":0.18824584849989173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158459641","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76474565,0.0007577817,0.22818337,0.001171681,0.000088624394,0.0005163038,0.0037248975,0.00019798834,0.00061372],"genre_scores_gemma":[0.9444284,0.000038123675,0.041282214,0.00028200413,0.00025571417,0.000056734672,0.012535791,0.00003299324,0.0010880674],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855113,0.000039718692,0.000250619,0.0008041965,0.000117422394,0.00023692088],"domain_scores_gemma":[0.99741375,0.0006418268,0.000100705176,0.0016260506,0.00007845301,0.00013920978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076642836,0.00016920586,0.00039110243,0.00016456409,0.000118629796,0.00010585613,0.00040741885,0.000059214086,0.0000032243977],"category_scores_gemma":[0.0015322581,0.0001528625,0.000049693583,0.00046563998,0.00009493291,0.00089637213,0.00075899815,0.00010351983,0.0000023614277],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009473392,0.0020162135,0.14905389,0.00044149472,0.0014504973,0.00005170154,0.0030057568,0.000008809001,0.0038655552,0.0009300299,0.42803633,0.4101924],"study_design_scores_gemma":[0.006815442,0.0010812785,0.044259015,0.00044907935,0.0061201537,0.00019182684,0.00552628,0.5073028,0.001123767,0.00040797167,0.4252391,0.0014833062],"about_ca_topic_score_codex":0.000018407147,"about_ca_topic_score_gemma":0.0000613604,"teacher_disagreement_score":0.507294,"about_ca_system_score_codex":0.000024929494,"about_ca_system_score_gemma":0.00017640651,"threshold_uncertainty_score":0.6233552},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.10341483207346523,"score_gpt":0.31561346603796997,"score_spread":0.21219863396450472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159328231","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08638476,0.0027134712,0.9014692,0.00018331174,0.00088869745,0.00009018718,0.0039507737,0.00018485848,0.0041347444],"genre_scores_gemma":[0.32741687,0.00018709573,0.6388255,0.0003062172,0.0015283417,0.0000133722615,0.028706696,0.00004114154,0.0029747752],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997919,0.000029937935,0.00031227138,0.0011611762,0.00023029897,0.00034728632],"domain_scores_gemma":[0.9957344,0.0006457626,0.00010110425,0.003335474,0.000045761888,0.00013751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010922808,0.00018811261,0.00018670494,0.00010553064,0.00033713522,0.0007192429,0.0031476056,0.0000716495,0.000013558882],"category_scores_gemma":[0.00021683672,0.00017580572,0.000018030085,0.00032895504,0.000103035134,0.0041519473,0.005595378,0.00011956152,0.000050103572],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000132828645,0.0001774762,0.0047960714,0.000019154479,0.00008363476,0.00002519579,0.0021708133,8.6204795e-7,0.0004233313,0.0038182882,0.100722484,0.88774943],"study_design_scores_gemma":[0.0016303154,0.00011699633,0.0856199,0.00044169906,0.00017099419,0.00013902612,0.008828195,0.49909666,0.00075736636,0.0009093064,0.40062734,0.0016621877],"about_ca_topic_score_codex":0.00017798092,"about_ca_topic_score_gemma":0.0005836725,"teacher_disagreement_score":0.88608724,"about_ca_system_score_codex":0.000017993263,"about_ca_system_score_gemma":0.00016548792,"threshold_uncertainty_score":0.7169149},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09401072320475932,"score_gpt":0.3028926707297767,"score_spread":0.20888194752501738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159694214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.744359,0.0032022942,0.24861164,0.00030743596,0.00028009492,0.00010646214,0.0014882238,0.0002547168,0.0013901178],"genre_scores_gemma":[0.97685534,0.00009434215,0.019692713,0.0000065778245,0.00008133326,0.0000048377633,0.0029029865,0.0000075819776,0.00035427866],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867135,0.000034016924,0.00030046958,0.00070150953,0.00013404382,0.000158582],"domain_scores_gemma":[0.99663997,0.00029358073,0.00018089237,0.00283604,0.000025254672,0.000024271161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024075841,0.00012777731,0.00017170733,0.0000989292,0.00010886681,0.00036076596,0.002715456,0.00006217286,0.0000022674262],"category_scores_gemma":[0.00017479993,0.00011235319,0.00001586423,0.00022781605,0.00013809917,0.0034683256,0.0029708722,0.000063515356,0.000007896276],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035630484,0.0006630691,0.2990901,0.00012811161,0.00010363891,0.0000047662224,0.0023336497,0.000013512382,0.028942667,0.0655508,0.042038992,0.56109506],"study_design_scores_gemma":[0.001411599,0.00007814277,0.3370076,0.00029366423,0.000081288534,0.0000050136205,0.005904335,0.5673396,0.013713083,0.0041876812,0.069073334,0.0009046807],"about_ca_topic_score_codex":0.00041364078,"about_ca_topic_score_gemma":0.00038294547,"teacher_disagreement_score":0.56732607,"about_ca_system_score_codex":0.000010906504,"about_ca_system_score_gemma":0.000058349353,"threshold_uncertainty_score":0.5046038},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0657895914618925,"score_gpt":0.3222549855121698,"score_spread":0.2564653940502773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161479324","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24722286,0.005487497,0.7220064,0.0036491887,0.0013110855,0.00023986131,0.00025001258,0.0015331557,0.018299963],"genre_scores_gemma":[0.4881388,0.00015473686,0.5104984,0.00013364131,0.0002485163,0.000005365981,0.00029830862,0.00003146613,0.000490785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975041,0.000056871562,0.00040310924,0.0011159108,0.00024573,0.0006742515],"domain_scores_gemma":[0.9825156,0.000904222,0.00015391721,0.016238503,0.000058212918,0.00012954563],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00221129,0.00025042534,0.00025284544,0.00024135465,0.00032042,0.00074083405,0.040907033,0.00013923945,0.0000045510637],"category_scores_gemma":[0.031385936,0.00023852747,0.000030205552,0.00061486964,0.00015232539,0.004942505,0.2971122,0.00026998395,0.000026868443],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017220249,0.00013137527,0.014999803,0.00013743219,0.000062114785,0.00011331132,0.0011746052,3.5678937e-7,0.0013195835,0.0029925704,0.4702968,0.5087548],"study_design_scores_gemma":[0.002831252,0.00036981513,0.040687513,0.0020331931,0.00012137515,0.00048871076,0.0045511373,0.6441846,0.0127861295,0.07130892,0.21688044,0.0037569006],"about_ca_topic_score_codex":0.0000486314,"about_ca_topic_score_gemma":0.00009758741,"teacher_disagreement_score":0.64418423,"about_ca_system_score_codex":0.000043497585,"about_ca_system_score_gemma":0.000106457504,"threshold_uncertainty_score":0.9767731},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.15532021060375845,"score_gpt":0.3896393330565236,"score_spread":0.23431912245276515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2282861635","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84402204,0.00026912132,0.15417027,0.0003045741,0.00007680342,0.00041296842,0.00038885296,0.000064109336,0.00029126898],"genre_scores_gemma":[0.999271,0.000024462595,0.0004891072,0.000034730823,0.000041135987,0.000050797065,0.00004261375,0.0000051368543,0.000041041556],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988352,0.00024928947,0.00016580295,0.0004354054,0.00022192458,0.00009239586],"domain_scores_gemma":[0.9983501,0.00022755458,0.000060221166,0.0012438695,0.00007414759,0.000044128337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015663095,0.000092258204,0.00010001161,0.000058021076,0.00019806977,0.00012245418,0.0005494495,0.000032564876,0.0000047265403],"category_scores_gemma":[0.00016278597,0.000050841867,0.000011150069,0.00017263467,0.000076680684,0.00080750836,0.00044193817,0.000046861172,0.000002973164],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017455483,0.0003473192,0.0027366749,0.000004705718,0.00002704191,3.6150016e-7,0.0010970075,3.3966037e-7,0.0009355545,0.0013399029,0.0029599823,0.99053365],"study_design_scores_gemma":[0.01149496,0.008421325,0.4109178,0.0007451616,0.0011799956,0.00012260865,0.017010277,0.40508255,0.032457434,0.017510092,0.09202111,0.003036718],"about_ca_topic_score_codex":0.000018213275,"about_ca_topic_score_gemma":0.00014948842,"teacher_disagreement_score":0.9874969,"about_ca_system_score_codex":0.000014355243,"about_ca_system_score_gemma":0.000057386278,"threshold_uncertainty_score":0.20732713},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06737345868108362,"score_gpt":0.3006821942314548,"score_spread":0.23330873555037118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2470642288","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14643703,0.0018619576,0.8425545,0.00039487137,0.0002651059,0.00011576029,0.0004257874,0.00012750404,0.007817499],"genre_scores_gemma":[0.9428765,0.00015273037,0.055371672,0.000027552996,0.00008980041,0.0000072518596,0.00031198605,0.000010432092,0.0011520482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988655,0.00009532072,0.00021403328,0.0005279133,0.000120995726,0.00017627457],"domain_scores_gemma":[0.99826,0.00026897693,0.00012076961,0.0012634534,0.000035413697,0.000051350045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005679463,0.00012022727,0.0001745506,0.000099629084,0.00008955009,0.00015443063,0.0010285354,0.000044286524,0.0000020841721],"category_scores_gemma":[0.00028183317,0.000079323,0.000018686247,0.00018032499,0.00007917074,0.0016577402,0.0009278987,0.000051914223,0.000009952495],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032885007,0.0002127229,0.0063665383,0.00014885969,0.00003723384,0.0000021089818,0.002336855,6.7864823e-7,0.00847051,0.015572524,0.0066754576,0.9601436],"study_design_scores_gemma":[0.013339987,0.0011482375,0.071731135,0.0042963354,0.00030403055,0.00023475692,0.003959037,0.70636064,0.009054681,0.0022194686,0.18381281,0.0035389059],"about_ca_topic_score_codex":0.000020448288,"about_ca_topic_score_gemma":0.000011003462,"teacher_disagreement_score":0.9566047,"about_ca_system_score_codex":0.000008394629,"about_ca_system_score_gemma":0.00006609001,"threshold_uncertainty_score":0.32346982},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.09958120661649893,"score_gpt":0.30668627265241966,"score_spread":0.20710506603592072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2545851563","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031548936,0.0002622377,0.95885116,0.0018499234,0.0010711217,0.0002266273,0.0059216884,0.000085117965,0.0001832123],"genre_scores_gemma":[0.9555705,0.000049643993,0.03318159,0.00007201389,0.000243369,0.00005388253,0.008529888,0.00001517059,0.0022839452],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852735,0.000053230957,0.00021789239,0.0008520199,0.000119336575,0.00023014616],"domain_scores_gemma":[0.99751425,0.000531457,0.00009759448,0.0016981296,0.000070162365,0.00008838902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031272016,0.00014147493,0.000144025,0.000084746905,0.0002985216,0.0002114007,0.0010414587,0.00006349175,0.000007747107],"category_scores_gemma":[0.00035348447,0.00009126174,0.000020420248,0.00010890999,0.00007324325,0.0034307735,0.0014513156,0.000042859632,0.000042610955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007555173,0.00025307873,0.0011418199,0.00005475814,0.00004721068,0.0000031802715,0.00037699533,9.870741e-7,0.014793875,0.003417852,0.26455125,0.71528345],"study_design_scores_gemma":[0.005034267,0.0003675561,0.018489726,0.0013687117,0.00020600508,0.000032369102,0.0020047198,0.86271656,0.004350824,0.002569271,0.10152002,0.0013399606],"about_ca_topic_score_codex":0.000021289623,"about_ca_topic_score_gemma":0.00012578182,"teacher_disagreement_score":0.92566955,"about_ca_system_score_codex":0.000016929855,"about_ca_system_score_gemma":0.000115115414,"threshold_uncertainty_score":0.37215456},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.08877169197371115,"score_gpt":0.3433036432579842,"score_spread":0.25453195128427303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755646241","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57733035,0.0009504731,0.41988802,0.0009233714,0.00018423106,0.00017944118,0.00010949689,0.00005371652,0.0003808891],"genre_scores_gemma":[0.9903111,0.00008624629,0.008389804,0.000079630256,0.00018509461,0.000015923952,0.0000665149,0.000012111262,0.0008535865],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998595,0.00009838333,0.00018960978,0.00071682467,0.00013262239,0.00026754575],"domain_scores_gemma":[0.997842,0.00039148945,0.00013732782,0.0014829962,0.000029723791,0.0001164446],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00091424264,0.00018827771,0.00023591671,0.000066935085,0.0015238817,0.0020691617,0.001472377,0.00006591093,3.8281345e-7],"category_scores_gemma":[0.0004271238,0.00013697396,0.000017158074,0.00008146024,0.00017338281,0.0010298104,0.0026395565,0.00016625645,0.000005117123],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011397017,0.00002019896,0.10584336,0.00006221333,0.000026157903,0.0000019404606,0.005974991,9.575904e-7,0.00021475348,0.0010243425,0.00031441706,0.88650525],"study_design_scores_gemma":[0.0011556848,0.00004463477,0.86968464,0.0002776995,0.00004816971,0.000019085774,0.000418153,0.119814835,0.00006376348,0.0002282257,0.007862923,0.00038219074],"about_ca_topic_score_codex":0.00020787786,"about_ca_topic_score_gemma":0.00026052387,"teacher_disagreement_score":0.88612306,"about_ca_system_score_codex":0.000010469367,"about_ca_system_score_gemma":0.000042411706,"threshold_uncertainty_score":0.999776},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.20507464499303893,"score_gpt":0.3555595803813095,"score_spread":0.1504849353882706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810490377","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020267966,0.0010839243,0.9644464,0.00095168734,0.000623437,0.00043048986,0.029705144,0.00020050786,0.00053158327],"genre_scores_gemma":[0.066121496,0.00007788814,0.8095101,0.00021973402,0.0007852207,0.000186227,0.122503266,0.000052377465,0.0005436883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963353,0.00006383267,0.00053616625,0.0024295412,0.0002682605,0.00036685664],"domain_scores_gemma":[0.99409395,0.000530649,0.0003201588,0.004767869,0.00011239806,0.00017498396],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00084072707,0.00041070994,0.0004483671,0.00015652325,0.0003751598,0.0011750308,0.005108274,0.00024309279,0.0000028182374],"category_scores_gemma":[0.000400643,0.0004268358,0.00006762198,0.0002465324,0.00011235954,0.0022303092,0.01281509,0.00032298945,0.000014374103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049184022,0.00040890675,0.0003211457,0.00088063715,0.00023802623,0.000006183033,0.0033079376,0.0023723503,0.00014361214,0.01253683,0.29462478,0.6851104],"study_design_scores_gemma":[0.0004444029,0.000034933444,0.00017594082,0.0003087851,0.00010123519,0.0000029405435,0.000113678165,0.9808395,0.000011853823,0.0012302307,0.016238086,0.0004984478],"about_ca_topic_score_codex":0.000023446599,"about_ca_topic_score_gemma":0.00005927711,"teacher_disagreement_score":0.9784671,"about_ca_system_score_codex":0.000041757565,"about_ca_system_score_gemma":0.0011615411,"threshold_uncertainty_score":0.99986184},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.037199048151490686,"score_gpt":0.3063922545785057,"score_spread":0.26919320642701505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884063665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43615147,0.00013612432,0.5595815,0.000022263379,0.00024830265,0.000056200242,0.00069437904,0.000009609414,0.0031001118],"genre_scores_gemma":[0.9949011,0.0000029866676,0.0041468185,0.0000116451165,0.00019697078,0.0000025536206,0.0006048043,0.00000896972,0.00012411416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926704,0.00004237008,0.00019533158,0.0002645063,0.00008618706,0.00014457073],"domain_scores_gemma":[0.9992933,0.00016583847,0.000064266766,0.0003736134,0.000045821613,0.000057120793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021227518,0.000101464255,0.00016071447,0.000029491292,0.00008156224,0.000039456183,0.00015373297,0.000022990975,0.00011944728],"category_scores_gemma":[0.00004252741,0.000085998785,0.000020366399,0.00008336624,0.00023220673,0.00021471664,0.00029440963,0.000047343714,0.000021977745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000293345,0.00009294357,0.0006667417,0.000025959594,0.000029288478,4.0500015e-7,0.00020241286,0.000002565199,0.00006216663,0.7012349,0.0015946353,0.29605868],"study_design_scores_gemma":[0.0012788742,0.00032843594,0.005855665,0.000363218,0.00021665866,0.0000028936352,0.0021180396,0.8925074,0.0030477273,0.091676585,0.002118168,0.000486367],"about_ca_topic_score_codex":0.000071435556,"about_ca_topic_score_gemma":0.0000026908917,"teacher_disagreement_score":0.8925048,"about_ca_system_score_codex":0.000006560343,"about_ca_system_score_gemma":0.000043241635,"threshold_uncertainty_score":0.35069287},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0757148656264769,"score_gpt":0.33957449440473064,"score_spread":0.26385962877825375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894980798","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06412975,0.00057631487,0.92931,0.0008459876,0.0003342037,0.00011569745,0.00012764444,0.00019931713,0.0043610376],"genre_scores_gemma":[0.7611699,0.000072047515,0.23636203,0.00015172525,0.0004664535,0.000015293786,0.00083192403,0.000019592346,0.0009110174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840343,0.00010769021,0.00021205432,0.00083801046,0.00016913486,0.00026965648],"domain_scores_gemma":[0.99755156,0.00030809658,0.00013817694,0.0018207467,0.00008496294,0.00009647956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069082325,0.0001772872,0.00016494507,0.000117806674,0.00035878696,0.00067268364,0.0011506642,0.00008838509,0.0000056651666],"category_scores_gemma":[0.0003800834,0.00014365952,0.0000118373655,0.00045260228,0.00016491502,0.0016657057,0.00072581315,0.00018565093,0.00005346184],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008546699,0.00025540942,0.025889887,0.00010063508,0.000057814894,0.0000040550112,0.0048773335,8.878618e-7,0.0009901616,0.07178422,0.007658148,0.888296],"study_design_scores_gemma":[0.001324303,0.0006088335,0.15891114,0.00094209204,0.00008025403,0.000073167605,0.0018234225,0.7161181,0.0001380723,0.0010726912,0.117757626,0.0011503331],"about_ca_topic_score_codex":0.000026683427,"about_ca_topic_score_gemma":0.0000754251,"teacher_disagreement_score":0.88714564,"about_ca_system_score_codex":0.000020222544,"about_ca_system_score_gemma":0.00012776311,"threshold_uncertainty_score":0.64867043},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Statistics; Popularity; Basketball; Computer science; Generosity; Econometrics; Psychology; Mathematics; Geography; Social psychology","score_opus":0.24888413932482473,"score_gpt":0.33297201709110424,"score_spread":0.08408787776627952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950515936","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9784772,0.0056949295,0.0008569319,0.00013497614,0.0007096475,0.00014816012,0.0015988274,0.0000122935235,0.012367076],"genre_scores_gemma":[0.99525267,0.0006240736,0.0007507726,0.000049400256,0.0003157715,0.000014401187,0.00034570275,0.00002133059,0.0026258626],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99875814,0.0000035607281,0.00041515287,0.00051966676,0.000020733944,0.0002827289],"domain_scores_gemma":[0.9985458,0.00008961628,0.00030659276,0.0009852656,0.000018593597,0.000054116048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009114015,0.00013970619,0.0003368584,0.00015596896,0.00034764048,0.00056067243,0.0005847266,0.00006702425,0.000022835848],"category_scores_gemma":[0.00056007673,0.00014434976,0.00004323951,0.000054806398,0.00010042685,0.0012757007,0.00042525685,0.000080661346,0.000025077561],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032221924,0.000073282055,0.95562536,0.00013843224,0.00003080943,0.000004939995,0.0008463407,0.0000120806235,0.000003824314,0.018779086,0.005166776,0.019286867],"study_design_scores_gemma":[0.002602093,0.00012916733,0.6658866,0.00064209977,0.000037966704,0.000008089814,0.0009753286,0.18368952,0.000050226794,0.0036137267,0.14138818,0.0009770355],"about_ca_topic_score_codex":0.00046842918,"about_ca_topic_score_gemma":0.0012515461,"teacher_disagreement_score":0.28973877,"about_ca_system_score_codex":0.000018587358,"about_ca_system_score_gemma":0.00003622291,"threshold_uncertainty_score":0.5886413},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.09721739508829468,"score_gpt":0.386530902237729,"score_spread":0.2893135071494343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969639627","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15918787,0.0008004551,0.8390418,0.000074361276,0.0001696313,0.00017792895,0.00003623713,0.000045827783,0.00046586545],"genre_scores_gemma":[0.4597875,0.00012973894,0.53941035,0.000038713282,0.000033101,0.000010325024,0.0001111946,0.000018348,0.00046071966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852544,0.00020035444,0.0002567185,0.0006297573,0.00014821386,0.00023950364],"domain_scores_gemma":[0.9979522,0.00053210487,0.00009003241,0.0012623476,0.00008023184,0.00008309018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010023707,0.0001467651,0.00027665708,0.00014399669,0.000084602,0.00019020907,0.00080182304,0.00006259911,0.00000192315],"category_scores_gemma":[0.00016436652,0.00013590552,0.000022295117,0.0003163439,0.00008982856,0.0012161069,0.0016421467,0.00011332988,0.0000053780836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004262703,0.00007497635,0.0019319662,0.0007539531,0.000033251366,0.000003778182,0.0015033571,0.00004064608,0.024323864,0.0012332018,0.000086449814,0.96997195],"study_design_scores_gemma":[0.0005777606,0.00008297612,0.0024269363,0.00024308896,0.0000103573175,0.00000982108,0.00034630825,0.992991,0.0018097342,0.00008702137,0.0012331953,0.00018183653],"about_ca_topic_score_codex":0.000014915451,"about_ca_topic_score_gemma":0.000021225147,"teacher_disagreement_score":0.9929503,"about_ca_system_score_codex":0.000022028125,"about_ca_system_score_gemma":0.00012155827,"threshold_uncertainty_score":0.5542066},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.25603027818386753,"score_gpt":0.3534881577537748,"score_spread":0.09745787956990726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043874967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8333876,0.004262447,0.15493084,0.00035603088,0.0010183005,0.00032597577,0.00080665067,0.00009493393,0.004817174],"genre_scores_gemma":[0.99451053,0.00027843454,0.0012332035,0.0003509152,0.00072413473,0.000015326874,0.0015421053,0.00004004204,0.0013052969],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849033,0.000015566779,0.0004672228,0.00069917255,0.000046209934,0.00028151454],"domain_scores_gemma":[0.99907833,0.00009656801,0.0002846063,0.00036262133,0.000044825192,0.00013302152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080013415,0.00018314114,0.00033858974,0.00011394786,0.00036029323,0.00034540196,0.00025851332,0.0000937482,0.00012716978],"category_scores_gemma":[0.00027437392,0.00020016429,0.00007013056,0.00018752295,0.000047852864,0.0014892801,0.00016212894,0.00016150264,0.00005108556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010672787,0.000519547,0.54305714,0.0011795032,0.0013560195,0.0000072212547,0.022155037,0.0488583,0.00026264403,0.06605015,0.020822478,0.29466465],"study_design_scores_gemma":[0.0005590324,0.00027611965,0.006439381,0.000022041206,0.00006842288,0.0000011607316,0.002377401,0.9503763,0.000008331049,0.00032362464,0.039256323,0.0002918885],"about_ca_topic_score_codex":0.00006612065,"about_ca_topic_score_gemma":0.000084288375,"teacher_disagreement_score":0.901518,"about_ca_system_score_codex":0.00003461605,"about_ca_system_score_gemma":0.000053385913,"threshold_uncertainty_score":0.8162463},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1118581280584065,"score_gpt":0.3593757391597357,"score_spread":0.2475176111013292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097249106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049363907,0.00026065137,0.94934016,0.00030264337,0.00021738335,0.00009578186,0.000116517745,0.00013250086,0.00017046256],"genre_scores_gemma":[0.68161064,0.0000029735183,0.31778207,0.00014870231,0.00024523758,0.000004906492,0.00015969966,0.000024123725,0.000021642123],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979986,0.00014384631,0.00025317693,0.00089802383,0.00031342456,0.00039291708],"domain_scores_gemma":[0.9984917,0.00019064415,0.000082940336,0.0009337211,0.00006224165,0.00023875116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048920413,0.0001929901,0.00020785214,0.00010435751,0.00036452946,0.0008891634,0.0013621801,0.000056969282,0.0000038799562],"category_scores_gemma":[0.00018141788,0.00019243594,0.00002541384,0.00042048085,0.000062128405,0.0018913257,0.0018080026,0.00016239942,0.000006101256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025050578,0.0009777207,0.0024049017,0.00094182283,0.00017342299,0.00038974942,0.022934416,0.34404656,0.05828543,0.0022449084,0.0009348159,0.5664157],"study_design_scores_gemma":[0.0004435211,0.00006712917,0.0003241969,0.00009051457,0.000008799915,0.000012877565,0.00025821445,0.99760044,0.00038539228,0.000011189679,0.00055474264,0.00024298299],"about_ca_topic_score_codex":0.000015190778,"about_ca_topic_score_gemma":0.000008904171,"teacher_disagreement_score":0.6535539,"about_ca_system_score_codex":0.00005523118,"about_ca_system_score_gemma":0.00028069637,"threshold_uncertainty_score":0.85742235},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Generalization; Measure (data warehouse); Context (archaeology); Single-linkage clustering; Correlation clustering; Rand index; Contingency table; Cluster (spacecraft)","score_opus":0.11934352232843241,"score_gpt":0.3518487569469944,"score_spread":0.23250523461856198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099831365","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12853445,0.0045824866,0.86611676,0.00004569649,0.00024042782,0.00016168547,0.00010674834,0.000025944997,0.00018578845],"genre_scores_gemma":[0.8359038,0.0007846965,0.16231085,0.0000453316,0.00018313879,0.000023986842,0.0003071633,0.000020809235,0.00042017642],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990955,0.000071437695,0.0001989703,0.0002834186,0.0001230708,0.00022761001],"domain_scores_gemma":[0.99903953,0.00023695096,0.000087312634,0.000481516,0.00007070039,0.000083985586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000559789,0.00011869107,0.00019614589,0.00006407303,0.00018319779,0.0002791145,0.00046039862,0.000033181946,1.3189998e-7],"category_scores_gemma":[0.00007585051,0.000113213864,0.000009353937,0.00013151065,0.00014801759,0.0015630738,0.0022037055,0.00004984508,1.0574472e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035371198,0.00019028132,0.03437091,0.002554737,0.0003265592,0.00000945237,0.079228595,0.0076553575,0.00040906642,0.0058747227,0.0070047183,0.86202186],"study_design_scores_gemma":[0.0007869597,0.00012256035,0.0008010114,0.0003074005,0.000011493647,0.000009882675,0.004280188,0.9909282,0.000019247644,0.000352966,0.0022016973,0.00017839126],"about_ca_topic_score_codex":0.000060345345,"about_ca_topic_score_gemma":0.00052432163,"teacher_disagreement_score":0.98327285,"about_ca_system_score_codex":0.00001843867,"about_ca_system_score_gemma":0.00004663206,"threshold_uncertainty_score":0.46167275},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.030811306805708635,"score_gpt":0.2724500237614445,"score_spread":0.24163871695573585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3141059875","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9281328,0.0010133688,0.00004970183,0.00036204478,0.00057767297,0.00011837574,0.00019220482,0.00012405828,0.06942983],"genre_scores_gemma":[0.98992264,0.000045998102,0.002027384,0.0005631355,0.0024250485,0.000013619916,0.001166923,0.000045176894,0.0037900687],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983701,0.000058405218,0.00033144638,0.0006255175,0.00022367421,0.00039082102],"domain_scores_gemma":[0.99847496,0.0007219609,0.00019045097,0.00050959823,0.00007115172,0.000031909192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017217777,0.00024072023,0.00030130308,0.00024412495,0.00031741033,0.0010192621,0.00041946478,0.00008908775,0.00013711302],"category_scores_gemma":[0.0011569306,0.00023978061,0.00004765089,0.00032568615,0.000021135465,0.00287422,0.0010739617,0.000115165356,0.0003246163],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000922464,0.00008247417,0.41136613,0.000069447415,0.00007492074,0.000005011433,0.0006713798,0.000003914129,0.00042195013,0.000053359123,0.072894804,0.51426435],"study_design_scores_gemma":[0.0006684645,0.0000046710675,0.3125533,0.00046853535,0.00040747368,0.0000010788768,0.001393433,0.0069287065,0.000042771997,0.000009137526,0.6768397,0.00068269524],"about_ca_topic_score_codex":0.0005485662,"about_ca_topic_score_gemma":0.0008039051,"teacher_disagreement_score":0.60394496,"about_ca_system_score_codex":0.000057454938,"about_ca_system_score_gemma":0.00003317615,"threshold_uncertainty_score":0.98287684},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1432772631699324,"score_gpt":0.40712493858682247,"score_spread":0.2638476754168901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199460270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24616581,0.000988783,0.75166523,0.00024890792,0.00017683493,0.00019190926,0.0002699879,0.000031703064,0.0002608434],"genre_scores_gemma":[0.9248499,0.00002156734,0.074669,0.000055986246,0.00005413613,0.000027413085,0.0001829803,0.000014911691,0.00012408003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822116,0.000268043,0.00038433794,0.0005912976,0.00020316098,0.00033202567],"domain_scores_gemma":[0.9968937,0.0016424551,0.00009996482,0.001167895,0.00013471892,0.000061239785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016072837,0.00014424582,0.0002822106,0.000089618006,0.00014761942,0.00037236576,0.0009940519,0.000056412922,0.0000021175165],"category_scores_gemma":[0.0010064219,0.00011808566,0.00004869586,0.00045014065,0.00022469388,0.0011066208,0.0012483422,0.00013933808,6.3147445e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067413,0.00042057427,0.01724934,0.0017238209,0.00007033429,0.00006724065,0.0060433396,0.00096578413,0.012054464,0.000834706,0.00026275936,0.96024024],"study_design_scores_gemma":[0.0014742158,0.000033188375,0.008626503,0.0006840639,0.00000891727,0.000012341097,0.002641491,0.98408353,0.0018594515,0.00010964223,0.00022698393,0.00023964056],"about_ca_topic_score_codex":0.000032026568,"about_ca_topic_score_gemma":0.00032021772,"teacher_disagreement_score":0.98311776,"about_ca_system_score_codex":0.000035602214,"about_ca_system_score_gemma":0.00051084044,"threshold_uncertainty_score":0.48153937},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0352025202348579,"score_gpt":0.2851548256075449,"score_spread":0.249952305372687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239981520","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8694665,0.00039073982,0.123744875,0.00020672158,0.00016480667,0.00014422633,0.0017407855,0.00010070209,0.004040689],"genre_scores_gemma":[0.935253,0.000042784424,0.06318785,0.00006154334,0.0001292234,0.000007350239,0.0009886516,0.000010698565,0.00031888654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861914,0.000036182606,0.0002735557,0.0006248115,0.00018429542,0.00026203273],"domain_scores_gemma":[0.9985238,0.00007343256,0.0001332224,0.0011404972,0.00003878451,0.00009030318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027387575,0.00018387428,0.0002298507,0.0001093448,0.00014858629,0.00031577892,0.0012297815,0.000043772718,0.000004199612],"category_scores_gemma":[0.000020349586,0.00015435244,0.000024707802,0.00027689352,0.000081597434,0.0017388839,0.00077287946,0.00007971603,0.0000046102377],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000291901,0.00043236584,0.0089327255,0.000056393015,0.00008113572,0.000022908755,0.0040574404,0.0000029017367,0.0034282077,0.0028663203,0.0073604225,0.97273],"study_design_scores_gemma":[0.009974956,0.003847947,0.12626189,0.003212299,0.00052259397,0.0005780154,0.019054487,0.79071313,0.013947664,0.00026262293,0.027688382,0.0039359764],"about_ca_topic_score_codex":0.00004097932,"about_ca_topic_score_gemma":0.00018500937,"teacher_disagreement_score":0.968794,"about_ca_system_score_codex":0.000014884667,"about_ca_system_score_gemma":0.00014111797,"threshold_uncertainty_score":0.629431},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.031453118059549263,"score_gpt":0.30222898437326057,"score_spread":0.2707758663137113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283736551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030278396,0.00044012172,0.9948609,0.00021866708,0.00026870464,0.00010626041,0.00010046751,0.00024504884,0.00073202443],"genre_scores_gemma":[0.711107,0.0000033680537,0.28801474,0.00012853606,0.00006590472,0.00004270327,0.00041735152,0.000012012586,0.00020834862],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889535,0.00010143479,0.00017800218,0.0005087827,0.00015947591,0.0001569601],"domain_scores_gemma":[0.99892414,0.00011272466,0.000105696294,0.0007837734,0.000037994483,0.000035654964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004148,0.000112717134,0.00010988914,0.000121562465,0.0003787974,0.0003134501,0.0010763846,0.000019149393,0.0000065306704],"category_scores_gemma":[0.00015806252,0.0001142003,0.000016083286,0.00025920366,0.000056406516,0.0018972747,0.0019414366,0.00012489634,0.0000027348908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008001284,0.0004896148,0.003747246,0.00019998054,0.00003277214,0.000028067449,0.00499597,0.00012762182,0.007099197,0.013998175,0.012438633,0.95676273],"study_design_scores_gemma":[0.00020362115,0.00009069417,0.00024100525,0.000047583122,0.000006815709,0.000009643997,0.00013223068,0.9928955,0.00077554386,0.0009839879,0.0044317567,0.00018164108],"about_ca_topic_score_codex":0.00003122918,"about_ca_topic_score_gemma":0.0000145372405,"teacher_disagreement_score":0.9927679,"about_ca_system_score_codex":0.00004326618,"about_ca_system_score_gemma":0.0002243084,"threshold_uncertainty_score":0.4656953},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.27070642898415714,"score_gpt":0.3888650291681965,"score_spread":0.11815860018403934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376956106","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88581574,0.000089509755,0.113276705,0.00009201104,0.00002493556,0.00034951736,0.000037558864,0.000049076156,0.0002649139],"genre_scores_gemma":[0.99820554,0.000045523102,0.0015298021,0.0000058878923,0.000014772203,0.00008777652,0.00001629329,0.000004254017,0.000090163245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990701,0.00012687524,0.00020292481,0.00034722633,0.00017967995,0.0000731687],"domain_scores_gemma":[0.99903196,0.00022881165,0.00013227752,0.0004188191,0.00016560793,0.000022515358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086294586,0.00008340736,0.0001336964,0.00012055347,0.00021958973,0.000078123936,0.00020266457,0.000034313944,5.378078e-7],"category_scores_gemma":[0.000058683472,0.00006561433,0.000009573524,0.00044612456,0.00006702246,0.00038907691,0.00024174947,0.00006057682,7.890523e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009432316,0.0016010215,0.0026836947,0.00013280942,0.00031052853,2.7900094e-7,0.045560196,0.0009770091,0.016568478,0.05696161,0.0033533983,0.8717567],"study_design_scores_gemma":[0.00023717545,0.00019170786,0.009416461,0.000023899895,0.00004443982,0.0000017252265,0.0033459677,0.98358506,0.0015853017,0.001462005,0.00003509375,0.00007114719],"about_ca_topic_score_codex":0.000025073796,"about_ca_topic_score_gemma":0.00019073917,"teacher_disagreement_score":0.9826081,"about_ca_system_score_codex":0.000014279511,"about_ca_system_score_gemma":0.0000648146,"threshold_uncertainty_score":0.26756746},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.17832625361537688,"score_gpt":0.3657060325522407,"score_spread":0.18737977893686383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387703477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03548891,0.0003970751,0.9417938,0.0009203596,0.0009769206,0.00062435534,0.014220128,0.0013545346,0.004223948],"genre_scores_gemma":[0.7813126,0.00021237279,0.15985502,0.0001274245,0.00033687457,0.0000964413,0.056332048,0.00005584316,0.0016713843],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787736,0.000059918704,0.00030312978,0.0011886791,0.00015663989,0.0004142774],"domain_scores_gemma":[0.9949428,0.00056404085,0.0001248551,0.0042133806,0.000052862273,0.0001021043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00104093,0.00020639968,0.00022990794,0.00020176388,0.00023836683,0.0006555675,0.0038621817,0.00009517006,0.000002336548],"category_scores_gemma":[0.0004486193,0.00019764956,0.000023320456,0.0004241433,0.00022588673,0.0035668605,0.0049649472,0.000090298956,0.00003393518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018014915,0.00012199552,0.0015214859,0.0001029482,0.000073557116,0.000010113369,0.00085509464,0.0000015697022,0.00027978115,0.040832452,0.3566593,0.59952366],"study_design_scores_gemma":[0.0013105369,0.00027529048,0.013549239,0.0004380042,0.00011685641,0.00004887265,0.004578587,0.9277051,0.00038967715,0.0069999737,0.0435492,0.00103866],"about_ca_topic_score_codex":0.00003182521,"about_ca_topic_score_gemma":0.00025840965,"teacher_disagreement_score":0.92770356,"about_ca_system_score_codex":0.000022367374,"about_ca_system_score_gemma":0.00023828396,"threshold_uncertainty_score":0.8059915},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05877690887851249,"score_gpt":0.33299489273397936,"score_spread":0.27421798385546686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391572936","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36151677,0.013397699,0.6201701,0.000084840896,0.0024054174,0.0005696487,0.00072842295,0.00029383533,0.00083323545],"genre_scores_gemma":[0.95341945,0.00010866814,0.044526216,0.000063149855,0.0010060427,0.000044662647,0.0004452244,0.000055171,0.00033140488],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972176,0.00020913722,0.00034345486,0.0015937496,0.0001496412,0.0004864053],"domain_scores_gemma":[0.99699897,0.0012953101,0.00007698452,0.0013337407,0.00009523852,0.00019975485],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006815006,0.00041679517,0.00042838528,0.00034141276,0.0004469457,0.0013412265,0.0009204592,0.00022708201,0.0000032836215],"category_scores_gemma":[0.00026565642,0.00037292458,0.00006843804,0.0004602972,0.00015662539,0.002064431,0.0010590878,0.00037688558,0.000014699274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007340822,0.00027994483,0.0004307829,0.00090424565,0.0001299338,0.000016916878,0.013751176,0.000031759857,0.00076364283,0.1532664,0.0017943355,0.82855743],"study_design_scores_gemma":[0.0011916264,0.0006779916,0.0021931473,0.0029589257,0.00016741198,0.000086377004,0.0011400174,0.93382525,0.00063788856,0.026496997,0.029436542,0.001187832],"about_ca_topic_score_codex":0.000025197689,"about_ca_topic_score_gemma":0.00018139902,"teacher_disagreement_score":0.9337935,"about_ca_system_score_codex":0.000063965934,"about_ca_system_score_gemma":0.00016963217,"threshold_uncertainty_score":0.99987227},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1674946705782729,"score_gpt":0.43586677779388994,"score_spread":0.26837210721561705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401666276","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07173932,0.038002245,0.7337181,0.0012870805,0.010564487,0.0015898112,0.13448459,0.00055742793,0.008056971],"genre_scores_gemma":[0.8948025,0.00057772896,0.02130219,0.0009935668,0.0030985833,0.00009195967,0.06366882,0.000114244656,0.015350399],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99704605,0.0001860787,0.0005886095,0.0013072382,0.00042115577,0.00045087424],"domain_scores_gemma":[0.9957396,0.0019828049,0.00010014161,0.001998252,0.00003766196,0.00014157109],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004624117,0.00023140457,0.00033838573,0.00017061859,0.0003175814,0.0026824486,0.0014811197,0.00008105216,0.000069013644],"category_scores_gemma":[0.0015921316,0.00018039165,0.00007776871,0.00049864524,0.000119110315,0.0023165082,0.0021943124,0.00010868802,0.00008928861],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004114622,0.00005423227,0.00032346067,0.00010551724,0.000106018466,0.00003659696,0.00066064514,0.000075718846,0.000007249033,0.0056799673,0.763801,0.2291085],"study_design_scores_gemma":[0.0002618789,0.000059134058,0.00027348136,0.00026895304,0.000089436355,0.00001332386,0.0007255858,0.16961396,0.000009147724,0.0030172335,0.8253931,0.00027477494],"about_ca_topic_score_codex":0.00003748714,"about_ca_topic_score_gemma":0.0004990714,"teacher_disagreement_score":0.8230632,"about_ca_system_score_codex":0.000022459788,"about_ca_system_score_gemma":0.00010740582,"threshold_uncertainty_score":0.9983529},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03590234063653296,"score_gpt":0.31659416447194305,"score_spread":0.2806918238354101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408175168","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058186434,0.000779892,0.9392631,0.00023273852,0.00013705331,0.00010711085,0.00005233938,0.00008911567,0.001152223],"genre_scores_gemma":[0.9929909,0.000053718246,0.0064288774,0.000048147365,0.000029406068,0.000016495604,0.00007001287,0.000003843072,0.00035859353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989729,0.000037351787,0.00017075623,0.0006249898,0.00005521134,0.00013878764],"domain_scores_gemma":[0.9986552,0.00010030183,0.00003172753,0.0011582656,0.000014745832,0.00003978653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030196883,0.000090489586,0.00012030734,0.00012673475,0.00013038517,0.00020905756,0.00077223824,0.000052073807,6.7047637e-7],"category_scores_gemma":[0.00006553371,0.000082285886,0.00000813364,0.00046286455,0.00005023259,0.0004014554,0.0022656368,0.000100445235,0.0000033421263],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000127581325,0.00023769724,0.0023950182,0.00004004362,0.000015728498,0.000004820749,0.0004959368,0.000008711675,0.00032745342,0.014092223,0.003452075,0.97891754],"study_design_scores_gemma":[0.00025464842,0.000034367054,0.009390613,0.000033726323,0.000013939252,0.000016211608,0.00022062802,0.9652631,0.0003276566,0.00042427893,0.023842711,0.00017811988],"about_ca_topic_score_codex":0.00007756984,"about_ca_topic_score_gemma":0.000084314335,"teacher_disagreement_score":0.97873944,"about_ca_system_score_codex":0.000020151245,"about_ca_system_score_gemma":0.0000558637,"threshold_uncertainty_score":0.33555213},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03636783725970738,"score_gpt":0.31255536409908324,"score_spread":0.27618752683937586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414033870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76230216,0.0015336962,0.22550859,0.00047240552,0.0006716693,0.00020035604,0.00025559083,0.00056624174,0.008489294],"genre_scores_gemma":[0.846014,0.0000594098,0.15244712,0.0002084791,0.00007219225,0.000017221266,0.00009320495,0.000014294701,0.0010740417],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985772,0.00004767171,0.00022954906,0.0007730906,0.000089608635,0.0002829012],"domain_scores_gemma":[0.9980706,0.00046342405,0.00006175001,0.0012907584,0.000036210236,0.000077241355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070287066,0.00017780458,0.00021895599,0.00026110272,0.00024718043,0.0008688878,0.0011623354,0.0000578654,4.1415274e-7],"category_scores_gemma":[0.00065946137,0.00017241703,0.00001435404,0.000429698,0.00006290326,0.0020386337,0.0049530785,0.00011993439,0.000004579254],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015008444,0.000051983872,0.017997969,0.00012570102,0.00004589805,0.000011788333,0.0033663732,1.4645312e-7,0.0016683092,0.005453178,0.016092157,0.95517147],"study_design_scores_gemma":[0.006115146,0.0020733594,0.19178598,0.016706483,0.0006207894,0.00073445705,0.03648766,0.17274159,0.06531206,0.011676986,0.48651135,0.0092341555],"about_ca_topic_score_codex":0.00013202049,"about_ca_topic_score_gemma":0.00019198336,"teacher_disagreement_score":0.94593734,"about_ca_system_score_codex":0.000022110813,"about_ca_system_score_gemma":0.00009204408,"threshold_uncertainty_score":0.83787054},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.031970765629140495,"score_gpt":0.29588145799663446,"score_spread":0.263910692367494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417267046","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037449107,0.0016300231,0.95993054,0.00009015579,0.0004375163,0.00015851673,0.00006549373,0.000040807838,0.0001978542],"genre_scores_gemma":[0.965618,0.000048639868,0.03360411,0.000048324204,0.00006486536,0.00002077352,0.00041621603,0.000008043251,0.00017101958],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990012,0.000026238662,0.00024544887,0.00045318238,0.000083728366,0.00019020791],"domain_scores_gemma":[0.9987323,0.0004977957,0.00013778692,0.00049650355,0.00010318249,0.000032401014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019622751,0.00013719373,0.00018072245,0.00014070429,0.00014411115,0.00013040197,0.0005319394,0.000059592396,4.951567e-7],"category_scores_gemma":[0.00006867203,0.00011624211,0.00003233689,0.00038094795,0.00010407533,0.0017608358,0.00029299443,0.00008693375,1.0948555e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016984905,0.0005271618,0.017868387,0.0010763744,0.0005186288,0.0000066331922,0.0029972675,0.24403478,0.000728432,0.07295075,0.009889998,0.6477031],"study_design_scores_gemma":[0.00046127004,0.000049611128,0.007016617,0.00042710768,0.000028930575,0.0000038125597,0.00015042331,0.9910749,0.00006735479,0.00044798426,0.00012465278,0.00014733571],"about_ca_topic_score_codex":0.000004785639,"about_ca_topic_score_gemma":0.00004242464,"teacher_disagreement_score":0.9281689,"about_ca_system_score_codex":0.000015846705,"about_ca_system_score_gemma":0.00008272872,"threshold_uncertainty_score":0.47402155},"labels":[],"label_agreement":null}]}