{"meta":{"query_hash":"dc115bc2231e","filters":{"topic":"Advanced Clustering Algorithms Research"},"cohort_total":421,"direct_labels_cover":0,"predictions_cover":421,"exported":421,"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/dc115bc2231e","api":"https://metacan.xera.ac/api/v1/cohort?topic=Advanced+Clustering+Algorithms+Research"},"results":[{"id":"W115127865","doi":"","title":"A New Cluster Validity Index for Fuzzy Clustering Based on Similarity Measure.","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster (spacecraft); Cluster analysis; Measure (data warehouse); Index (typography); Fuzzy clustering; Fuzzy logic; Similarity (geometry); Data mining; Mathematics; Computer science; Artificial intelligence; Pattern recognition (psychology); Statistics","score_opus":0.06919300065919722,"score_gpt":0.33919787417475383,"score_spread":0.27000487351555663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W115127865","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":[0.0002630008,0.000007690944,0.9885986,0.0018815068,0.0005140868,0.0006740193,0.000003157533,0.00042715512,0.0076307734],"genre_scores_gemma":[0.34672517,8.259025e-7,0.6492543,0.0019706937,0.00031223378,0.000028193428,0.0000026389587,0.000034535882,0.0016713786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969249,0.00008127702,0.0003675923,0.00076838623,0.0009310645,0.00092682615],"domain_scores_gemma":[0.9972817,0.0008867605,0.00008317025,0.0010749808,0.00023390433,0.00043953894],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021782485,0.00027225018,0.0002612368,0.000289713,0.00024567125,0.0002358435,0.0012987361,0.00016220455,0.000026047193],"category_scores_gemma":[0.00037936147,0.0002501791,0.00015184144,0.00054980704,0.000038086666,0.0004853879,0.000519755,0.0003661719,0.000038101032],"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":[0.001164611,0.00044190165,0.0016335034,0.00022281373,0.00005578617,0.000088233166,0.00048429702,0.14202723,0.0012488205,0.004819988,0.010093911,0.8377189],"study_design_scores_gemma":[0.0019043231,0.00034202094,0.0021662838,0.000039380076,0.00000330592,0.000009089915,0.000012312853,0.9829667,0.0035550536,0.0032955608,0.0053415275,0.0003644261],"about_ca_topic_score_codex":0.000087159904,"about_ca_topic_score_gemma":0.00045527468,"teacher_disagreement_score":0.84093946,"about_ca_system_score_codex":0.0002779348,"about_ca_system_score_gemma":0.00022491612,"threshold_uncertainty_score":0.99999505},"labels":[],"label_agreement":null},{"id":"W118196362","doi":"","title":"Type-II Fuzzy Possibilistic C-Mean Clustering","year":2009,"lang":"en","type":"article","venue":"European Society for Fuzzy Logic and Technology Conference","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":26,"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 Toronto","funders":"","keywords":"Mahalanobis distance; Fuzzy logic; Cluster analysis; Fuzzy clustering; Mathematics; Data mining; Fuzzy number; Fuzzy classification; Fuzzy set operations; Euclidean distance; Artificial intelligence; Fuzzy set; Pattern recognition (psychology); Computer science","score_opus":0.034835140925025716,"score_gpt":0.28989406581776006,"score_spread":0.25505892489273435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W118196362","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":[0.016751895,0.00071507716,0.94839466,0.0071820463,0.00028114926,0.00056818407,0.000009197855,0.0015448009,0.024553016],"genre_scores_gemma":[0.79309005,0.0001828875,0.20500582,0.00049758947,0.00006363761,0.000008916677,0.0000052790065,0.00001713063,0.0011286796],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99810165,0.000044417,0.00027233985,0.0007742902,0.0001864534,0.0006208296],"domain_scores_gemma":[0.9986712,0.000070725604,0.00010349638,0.0007313082,0.0002999144,0.00012335755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004704383,0.00025076067,0.00026319976,0.00010222489,0.0005799932,0.00014674422,0.0012835254,0.00014839864,0.0000046644423],"category_scores_gemma":[0.00017080904,0.00022795462,0.00010753725,0.00062974513,0.00036071418,0.00025420805,0.0010585162,0.0004183712,0.000028420918],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002132783,0.00012900031,0.00008244252,0.000062120555,0.000058973645,0.00006328203,0.0016360882,0.00007821928,0.0072173313,0.3247099,0.001092483,0.66484886],"study_design_scores_gemma":[0.0035851789,0.005714657,0.0036809305,0.00023750358,0.000054425964,0.00047404983,0.0015874434,0.16294168,0.0009875502,0.79952806,0.019266514,0.00194197],"about_ca_topic_score_codex":0.000001399389,"about_ca_topic_score_gemma":0.0000013714808,"teacher_disagreement_score":0.77633816,"about_ca_system_score_codex":0.000052586158,"about_ca_system_score_gemma":0.00007042442,"threshold_uncertainty_score":0.9295719},"labels":[],"label_agreement":null},{"id":"W129927049","doi":"10.1007/978-3-642-20841-6_17","title":"Spatial Entropy-Based Clustering for Mining Data with Spatial Correlation","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":7,"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 Calgary","funders":"","keywords":"Spatial analysis; Cluster analysis; Spatial correlation; Computer science; Data mining; Entropy (arrow of time); Similarity (geometry); Spatial dependence; Pattern recognition (psychology); Spatial relation; Correlation; Spatial database; Artificial intelligence; Mathematics; Statistics","score_opus":0.045589914004622825,"score_gpt":0.2901130431364683,"score_spread":0.24452312913184548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W129927049","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":[0.000014455921,0.00007438807,0.99666995,0.00025498267,0.0015130378,0.00090176804,0.000035026864,0.0001937535,0.00034261425],"genre_scores_gemma":[0.05642306,0.000005715434,0.9423057,0.0002820291,0.0006526429,0.000029820538,0.00006863422,0.00006910368,0.00016329094],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949025,0.000039929473,0.0005341734,0.0023222244,0.0012606061,0.0009405772],"domain_scores_gemma":[0.9953642,0.0007982156,0.00039662875,0.0028384353,0.00038447868,0.00021803888],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009571521,0.00058414676,0.0005385902,0.00077109225,0.0003767873,0.00053320423,0.0058411197,0.00028504507,0.000017702243],"category_scores_gemma":[0.00018792851,0.0005243631,0.00007370915,0.00039557938,0.00061380817,0.0009863043,0.0031429909,0.0006999583,0.000014024739],"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":[0.0000651276,0.000021224807,0.00004705937,0.000063771266,0.000011685264,0.000055972498,0.00032112034,0.19256912,0.00004072905,0.00042774173,0.000005124939,0.80637133],"study_design_scores_gemma":[0.0007822499,0.0005384857,0.00007147305,0.0004788101,0.000011269582,0.000044626828,1.3904625e-7,0.9897507,0.00048086158,0.0063927136,0.0008163249,0.00063234894],"about_ca_topic_score_codex":0.00017022435,"about_ca_topic_score_gemma":0.0008332422,"teacher_disagreement_score":0.805739,"about_ca_system_score_codex":0.0003636481,"about_ca_system_score_gemma":0.0010041095,"threshold_uncertainty_score":0.9997208},"labels":[],"label_agreement":null},{"id":"W1453103518","doi":"10.1016/j.neucom.2015.08.018","title":"Applying subclustering and Lp distance in Weighted K-Means with distributed centroids","year":2015,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":34,"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":"Categorical variable; Silhouette; Cluster analysis; Centroid; Pattern recognition (psychology); Feature (linguistics); Mathematics; k-means clustering; Computer science; Scaling; Metric (unit); Data mining; Multidimensional scaling; Fuzzy clustering; Minkowski space; Artificial intelligence; Algorithm; Statistics","score_opus":0.022034390108879854,"score_gpt":0.2616475139197036,"score_spread":0.23961312381082372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1453103518","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":[0.107907824,0.000078394354,0.89081794,0.00025181635,0.00011707087,0.0003845147,0.0000020596972,0.0002384564,0.00020195224],"genre_scores_gemma":[0.8525355,0.0000047382036,0.14721057,0.000083707964,0.00006708316,0.00004303018,0.0000035718097,0.00002529521,0.000026509884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978583,0.00010390902,0.00027025683,0.0006553844,0.00045634664,0.00065582],"domain_scores_gemma":[0.99900687,0.0001431024,0.0000909377,0.000412623,0.0000944373,0.0002520459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000328181,0.00020957628,0.00023362749,0.00014257873,0.00014448703,0.0002520992,0.000615879,0.00004184413,3.660957e-7],"category_scores_gemma":[0.00006579389,0.00019445913,0.000018467877,0.0008636251,0.0000662155,0.00048518015,0.0008559331,0.0003699961,0.000004057813],"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":[0.00026857507,0.00030864068,0.09041667,0.00035477887,0.00004253503,0.0025796955,0.0056693796,0.1587852,0.0030300005,0.007922235,0.00013717524,0.73048514],"study_design_scores_gemma":[0.0011998335,0.00010910328,0.004452361,0.00010363664,0.0000014441202,0.00013303792,0.00008393766,0.99056953,0.00025546915,0.00040024056,0.002444573,0.0002468326],"about_ca_topic_score_codex":0.00003105905,"about_ca_topic_score_gemma":0.000022102276,"teacher_disagreement_score":0.83178437,"about_ca_system_score_codex":0.0001441508,"about_ca_system_score_gemma":0.0000642654,"threshold_uncertainty_score":0.7929814},"labels":[],"label_agreement":null},{"id":"W1497689567","doi":"10.1007/978-3-540-45231-7_29","title":"Refined Shared Nearest Neighbors Graph for Combining Multiple Data Clusterings","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":9,"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 Waterloo","funders":"","keywords":"Computer science; k-nearest neighbors algorithm; Graph; Theoretical computer science; Data mining; Artificial intelligence","score_opus":0.0592828658569979,"score_gpt":0.30986915558395806,"score_spread":0.2505862897269602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1497689567","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":[0.000016209851,0.0003291705,0.9943068,0.0012114062,0.0021235885,0.0010385636,0.00010546768,0.0003031987,0.0005655647],"genre_scores_gemma":[0.005307243,0.000046204193,0.9915936,0.0018734157,0.00033615806,0.000052237487,0.000103944156,0.000111640096,0.000575561],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928697,0.000057752473,0.0008047213,0.0033485682,0.0014535727,0.0014657238],"domain_scores_gemma":[0.9923727,0.0016137831,0.0004050275,0.0047538523,0.00048377604,0.0003708849],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001637542,0.0008019752,0.00082199695,0.0011040783,0.00061871874,0.0012459914,0.011155986,0.0004192751,0.000013829709],"category_scores_gemma":[0.00086285966,0.00079923426,0.00015620152,0.001029411,0.00082027726,0.0017481605,0.007256021,0.0011775346,0.000023708486],"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":[0.000053079577,0.000079560166,0.000049225397,0.00025069472,0.000048188205,0.0001799741,0.0006981762,0.14094618,0.00035658767,0.0043939343,0.0004178172,0.8525266],"study_design_scores_gemma":[0.0009093086,0.0002645837,0.00003410552,0.00041406674,0.0000073221822,0.000078327415,3.0188065e-7,0.9444521,0.0002900115,0.04112396,0.011541851,0.00088407064],"about_ca_topic_score_codex":0.000037116155,"about_ca_topic_score_gemma":0.00012647519,"teacher_disagreement_score":0.8516425,"about_ca_system_score_codex":0.00041429084,"about_ca_system_score_gemma":0.00059306785,"threshold_uncertainty_score":0.9997908},"labels":[],"label_agreement":null},{"id":"W1503257002","doi":"10.1007/978-3-642-04843-2_17","title":"A Point Symmetry-Based Automatic Clustering Approach Using Differential Evolution","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","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":"Western University","funders":"","keywords":"Cluster analysis; Computer science; Point (geometry); Cluster (spacecraft); Symmetry (geometry); Measure (data warehouse); Differential evolution; Representation (politics); Data mining; Algorithm; Artificial intelligence; Pattern recognition (psychology); Mathematics; Geometry","score_opus":0.026122202958597254,"score_gpt":0.27955413089078135,"score_spread":0.2534319279321841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1503257002","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":[0.00014609206,0.00017574689,0.9967482,0.0001771692,0.0009965242,0.0006606542,0.0000037449522,0.00041738222,0.00067450065],"genre_scores_gemma":[0.1359307,0.0000033315039,0.863272,0.00024768568,0.00037207353,0.000010164922,0.0000051049046,0.000050451654,0.0001084819],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99386764,0.000106784835,0.00072593644,0.0021092577,0.0019517695,0.0012386387],"domain_scores_gemma":[0.9967433,0.00037162626,0.0003691446,0.0019355782,0.00028284235,0.0002975003],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010505826,0.0007570047,0.0007573532,0.0018385355,0.00045345945,0.00088278635,0.003999978,0.00040861694,0.000012172476],"category_scores_gemma":[0.00013481015,0.00073059544,0.00021120762,0.001172006,0.0006081747,0.0008431994,0.0020420866,0.0012847098,0.000017877557],"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":[0.0000046276677,0.00005019593,0.000003998392,0.000111671856,0.000008785159,0.000060944094,0.00014743791,0.36243185,0.00047936596,0.0015693774,9.296746e-7,0.6351308],"study_design_scores_gemma":[0.00041634584,0.00016676163,0.00006450988,0.00058250857,0.000009217368,0.00014192457,1.7764332e-7,0.96631175,0.0004563673,0.03110557,0.00001791899,0.0007269481],"about_ca_topic_score_codex":0.000036655554,"about_ca_topic_score_gemma":0.000014325565,"teacher_disagreement_score":0.6344039,"about_ca_system_score_codex":0.0018987531,"about_ca_system_score_gemma":0.0009012739,"threshold_uncertainty_score":0.9995145},"labels":[],"label_agreement":null},{"id":"W151377110","doi":"10.1007/978-3-642-37456-2_14","title":"Density-Based Clustering Based on Hierarchical Density Estimates","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":2412,"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":"Computer science; Cluster analysis; Hierarchical clustering; Data mining; Artificial intelligence","score_opus":0.021558810818848025,"score_gpt":0.2774625965106832,"score_spread":0.2559037856918352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W151377110","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":[0.00016028763,0.000044065804,0.99475133,0.0015544305,0.001182852,0.0006549079,0.0000042367715,0.00043540378,0.001212505],"genre_scores_gemma":[0.11283775,0.0000040315012,0.8837252,0.002809397,0.0003212957,0.00002467051,0.000007883185,0.00007255353,0.00019719794],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931122,0.00008708959,0.00061629416,0.002569691,0.002237341,0.0013773903],"domain_scores_gemma":[0.9941137,0.0020078185,0.0002604406,0.00265572,0.0004708926,0.0004914713],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010528447,0.0008777426,0.0008121474,0.0014711373,0.0005455339,0.0010570722,0.0047060815,0.00047100527,0.000045780034],"category_scores_gemma":[0.00039453577,0.00081441656,0.00020832744,0.0008059339,0.0012134674,0.00057003414,0.0024492554,0.0020543102,0.0002466564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019602348,0.000047472655,0.0000446695,0.00007673001,0.000006522412,0.0003030121,0.00007823299,0.61248523,0.00021084378,0.0012984546,0.000011976224,0.38541728],"study_design_scores_gemma":[0.00043308066,0.00034260546,0.0002479205,0.0005968327,0.0000047158424,0.00004912816,3.8674717e-8,0.9581263,0.0037444544,0.035481606,0.00017384492,0.0007994969],"about_ca_topic_score_codex":0.00004348464,"about_ca_topic_score_gemma":0.00008872511,"teacher_disagreement_score":0.38461778,"about_ca_system_score_codex":0.0008054438,"about_ca_system_score_gemma":0.0009778027,"threshold_uncertainty_score":0.9999799},"labels":[],"label_agreement":null},{"id":"W1516498690","doi":"10.1007/3-540-44938-8_17","title":"Finding Natural Clusters Using Multi-clusterer Combiner Based on Shared Nearest Neighbors","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":91,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Graph; Computer science; k-nearest neighbors algorithm; Set (abstract data type); Pattern recognition (psychology); Data mining; Artificial intelligence; Theoretical computer science; Mathematics","score_opus":0.04392408286800724,"score_gpt":0.3073721529406045,"score_spread":0.26344807007259724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1516498690","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":[0.00016463314,0.00017291914,0.9938387,0.00074047624,0.0034895402,0.0007765289,0.000013339492,0.00024350245,0.00056034565],"genre_scores_gemma":[0.08842174,0.000008119106,0.9055854,0.0047496646,0.00030251272,0.000016408469,0.000015107623,0.00013701683,0.0007639947],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99252003,0.00013675429,0.00077035814,0.0027409177,0.0021991928,0.0016327132],"domain_scores_gemma":[0.9955398,0.00088777737,0.00035513667,0.0023976811,0.00041236993,0.00040722804],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010404885,0.0010435502,0.00083953934,0.0018941588,0.0006725676,0.0013023468,0.0048901415,0.00048804493,0.00003492588],"category_scores_gemma":[0.00031261737,0.000977465,0.00025522072,0.0013474099,0.0008974215,0.0010757671,0.0021194182,0.002274675,0.000053714382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023547755,0.00007221013,0.000052813637,0.000072998424,0.000015354215,0.00033205227,0.00033415793,0.87624556,0.00020262212,0.00047324528,0.00001718995,0.12215823],"study_design_scores_gemma":[0.001128615,0.00020428782,0.00009149145,0.00081984705,0.000007111475,0.0000796301,3.3267276e-7,0.9936935,0.00055485894,0.0019558957,0.00039038222,0.001074076],"about_ca_topic_score_codex":0.000041876287,"about_ca_topic_score_gemma":0.000057444275,"teacher_disagreement_score":0.12108415,"about_ca_system_score_codex":0.0015112064,"about_ca_system_score_gemma":0.00076132413,"threshold_uncertainty_score":0.9997344},"labels":[],"label_agreement":null},{"id":"W1521374378","doi":"","title":"Cluster Assessment: A Complimentary Aspect of Cluster Learning","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","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":"Université du Québec à Montréal","funders":"","keywords":"Cluster (spacecraft); Computer science; Artificial intelligence; Computer network","score_opus":0.014442518119782487,"score_gpt":0.3244753965582688,"score_spread":0.3100328784384863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1521374378","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":[0.036117114,0.0000094948255,0.93655336,0.0014757989,0.00037513798,0.00022931531,0.000001069405,0.00021421428,0.025024472],"genre_scores_gemma":[0.5841779,0.0000024154017,0.4139845,0.00024031622,0.00005893061,0.000012760896,0.000002390869,0.000013870574,0.0015068955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982027,0.00010620035,0.00029789365,0.00042849977,0.0005492968,0.0004154329],"domain_scores_gemma":[0.99863523,0.00029743457,0.00009918482,0.00069940643,0.00013469199,0.00013402774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005456172,0.00015588767,0.00021336682,0.00017394176,0.00013947456,0.00010899038,0.0011099577,0.000068736525,0.00022621409],"category_scores_gemma":[0.000045677512,0.00013674283,0.00007761748,0.00035371166,0.00011049226,0.0005954973,0.0012264273,0.000763738,0.00007446734],"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":[0.00012407098,0.0012819084,0.036060758,0.000358055,0.00031795428,0.00013194277,0.0030621917,0.024423202,0.27671212,0.16568348,0.0047752475,0.48706907],"study_design_scores_gemma":[0.0012191554,0.000282675,0.010988706,0.0000228334,0.0000054614634,0.00008711734,0.00007791324,0.9666854,0.010664944,0.0030178272,0.0066159153,0.00033200835],"about_ca_topic_score_codex":0.0000643956,"about_ca_topic_score_gemma":0.00003358536,"teacher_disagreement_score":0.94226223,"about_ca_system_score_codex":0.000043672488,"about_ca_system_score_gemma":0.000076667915,"threshold_uncertainty_score":0.5576211},"labels":[],"label_agreement":null},{"id":"W153300101","doi":"10.1007/978-3-540-72432-2_82","title":"New Cluster Validity Index with Fuzzy Functions","year":2007,"lang":"en","type":"book-chapter","venue":"Advances in soft computing","topic":"Advanced Clustering Algorithms Research","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":"University of Toronto","funders":"","keywords":"Mathematics; Fuzzy logic; Measure (data warehouse); Cluster (spacecraft); Fuzzy clustering; Compact space; Cluster analysis; Fuzzy set; Index (typography); FLAME clustering; Data mining; Pattern recognition (psychology); Statistics; Artificial intelligence; Computer science; Mathematical analysis","score_opus":0.04084506286960581,"score_gpt":0.3208448999270594,"score_spread":0.27999983705745357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W153300101","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":[0.000007561564,0.0018115065,0.7784,0.00010792772,0.0007817575,0.0003388131,0.0000026622265,0.00035966205,0.2181901],"genre_scores_gemma":[0.003899246,0.00035754143,0.8190842,0.00043105832,0.0013620767,0.0000063841053,0.000021464202,0.00018128613,0.17465675],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959384,0.000044344142,0.00062603474,0.00134385,0.001086187,0.00096114085],"domain_scores_gemma":[0.99702764,0.0008153512,0.00040639605,0.0012171622,0.00023104307,0.00030242797],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006804745,0.0006079246,0.0006329334,0.0004828402,0.00031692875,0.00019997884,0.0016707854,0.00033659616,0.00005464253],"category_scores_gemma":[0.000065648244,0.0006079018,0.00012835638,0.0003452595,0.0001960235,0.0010332913,0.001450671,0.001645796,0.00022080343],"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":[0.00003708605,0.000017687595,0.00031231614,0.00007444224,0.00002467829,0.00019141422,0.0002945324,0.06881196,7.9043843e-7,0.0072629754,0.00028711825,0.922685],"study_design_scores_gemma":[0.0021493246,0.0005032946,0.0003585046,0.0018140443,0.000022982116,0.0003962378,0.000053556356,0.20670623,0.000012240271,0.09205308,0.693853,0.0020774894],"about_ca_topic_score_codex":0.00004663526,"about_ca_topic_score_gemma":0.00040409167,"teacher_disagreement_score":0.9206075,"about_ca_system_score_codex":0.0003718214,"about_ca_system_score_gemma":0.00032340316,"threshold_uncertainty_score":0.99963725},"labels":[],"label_agreement":null},{"id":"W1536355413","doi":"10.1109/ccece.2015.7129370","title":"A tweet grouping methodology utilizing inter and intra cosine similarity","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","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 Regina","funders":"","keywords":"Popularity; Cosine similarity; Computer science; Similarity (geometry); Publication; Cluster analysis; Subject (documents); Information retrieval; Microblogging; Social media; Feeling; World Wide Web; Artificial intelligence; Advertising; Psychology","score_opus":0.2558543091809517,"score_gpt":0.40551641913127173,"score_spread":0.14966210995032003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1536355413","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":[0.0063431426,0.000107446926,0.9881997,0.002183422,0.00017052775,0.00009811546,4.8192345e-7,0.00019322183,0.0027039265],"genre_scores_gemma":[0.21764049,0.000008318298,0.7814909,0.0005370987,0.000053718963,0.0000076153815,5.8728284e-7,0.000007902074,0.00025333048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862945,0.00023040212,0.00017113103,0.00040166234,0.0002073917,0.0003599406],"domain_scores_gemma":[0.998856,0.00036718912,0.000033967342,0.00039506407,0.00012659265,0.00022116811],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012628809,0.00011393747,0.00018684534,0.00011486141,0.00006470943,0.00012972779,0.0005375731,0.00006214734,0.000010772622],"category_scores_gemma":[0.00054015033,0.00009926448,0.000020548809,0.00026433473,0.00010290144,0.00053354964,0.0013506527,0.00024176619,0.000012087612],"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":[0.000055188913,0.000091340116,0.0016435749,0.00005967812,0.000056421613,0.00016948524,0.0047193253,0.0002868529,0.004151013,0.05589364,0.0021977662,0.9306757],"study_design_scores_gemma":[0.0012682413,0.00036898142,0.0010197469,0.000049448583,0.000004853141,0.0003511103,0.00069297827,0.9339637,0.006695992,0.046560306,0.008587632,0.00043698717],"about_ca_topic_score_codex":0.00009454629,"about_ca_topic_score_gemma":0.000029716302,"teacher_disagreement_score":0.9336769,"about_ca_system_score_codex":0.00006551386,"about_ca_system_score_gemma":0.000046075176,"threshold_uncertainty_score":0.4047888},"labels":[],"label_agreement":null},{"id":"W1556829956","doi":"10.1007/978-3-540-25966-4_14","title":"A Probabilistic Model Using Information Theoretic Measures for Cluster Ensembles","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":15,"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 Waterloo","funders":"","keywords":"Probabilistic logic; Computer science; Conditional probability; Cluster analysis; Probability distribution; Entropy (arrow of time); Conditional probability distribution; Data mining; Divergence (linguistics); Expectation–maximization algorithm; Statistical model; Artificial intelligence; Mathematics; Statistics","score_opus":0.03497427916053233,"score_gpt":0.29213932538523485,"score_spread":0.25716504622470254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1556829956","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":[0.000058893715,0.000112268004,0.9967858,0.00039131643,0.0005888482,0.0013376467,0.000013433342,0.00017540854,0.00053638464],"genre_scores_gemma":[0.059299514,0.000016571938,0.939643,0.0006869106,0.00018825002,0.000048934322,0.000006274488,0.0000409305,0.00006956458],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99594444,0.000031895794,0.0006461711,0.0011049754,0.0013636226,0.00090889964],"domain_scores_gemma":[0.9969434,0.0005377493,0.0003029127,0.0013065685,0.0007172282,0.00019211274],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012447231,0.0005448048,0.0004971051,0.000980933,0.00038656837,0.0008458737,0.0029968037,0.00032137035,0.0000030959002],"category_scores_gemma":[0.00044100088,0.0004916029,0.0001502455,0.0004822466,0.0008188618,0.0017679565,0.0014423712,0.0006492129,0.000012568434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012446111,0.000009127132,3.7684057e-7,0.000121672005,0.0000050098924,0.0000031708682,0.00068239786,0.7599996,0.00004017239,0.040435057,0.0000012222062,0.19868976],"study_design_scores_gemma":[0.00026752288,0.00007749817,7.213133e-7,0.00027468396,0.0000046786904,0.00003278678,1.1563743e-7,0.56012326,0.00027187256,0.43858257,0.00005160135,0.00031271775],"about_ca_topic_score_codex":0.000013127852,"about_ca_topic_score_gemma":0.000017079205,"teacher_disagreement_score":0.3981475,"about_ca_system_score_codex":0.001144717,"about_ca_system_score_gemma":0.0016294625,"threshold_uncertainty_score":0.99975353},"labels":[],"label_agreement":null},{"id":"W1559950581","doi":"10.1007/11494683_24","title":"Cluster-Based Cumulative Ensembles","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":21,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Jaccard index; Cluster (spacecraft); Computer science; Cluster analysis; Granularity; Similarity (geometry); Data mining; Hierarchical clustering; Computation; Measure (data warehouse); Single-linkage clustering; Pattern recognition (psychology); Algorithm; Artificial intelligence; Fuzzy clustering; CURE data clustering algorithm","score_opus":0.02871685949556528,"score_gpt":0.3041407387586494,"score_spread":0.2754238792630841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1559950581","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":[0.00003300895,0.00036238728,0.9918037,0.001707643,0.0010028991,0.00054634316,0.0000072287903,0.0003254967,0.0042112954],"genre_scores_gemma":[0.034574322,0.000028662425,0.9611265,0.0019755065,0.00076695863,0.000020721256,0.00000598036,0.00007322137,0.0014281012],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939263,0.00006967258,0.0006456046,0.002217397,0.0019508004,0.0011902272],"domain_scores_gemma":[0.99549526,0.0012536186,0.0003098985,0.0021755528,0.00044423554,0.0003214218],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010397121,0.0007346848,0.0006631862,0.0013741264,0.00036100872,0.00066489907,0.005143554,0.000398787,0.00003735995],"category_scores_gemma":[0.00019675761,0.000694957,0.0001813279,0.0008909575,0.0010202876,0.0009045421,0.0024656972,0.0013459476,0.00015012232],"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":[0.0000072362786,0.000022625884,0.0000044609633,0.000024559793,0.0000064008027,0.00008274017,0.0002684843,0.36775082,0.00005542626,0.002897929,0.00001160585,0.6288677],"study_design_scores_gemma":[0.00045015063,0.00019692075,0.00002718541,0.00035406553,0.000003635581,0.000049455182,8.535582e-8,0.9364316,0.0018008983,0.05614419,0.0037954287,0.000746379],"about_ca_topic_score_codex":0.000018619881,"about_ca_topic_score_gemma":0.000073222196,"teacher_disagreement_score":0.6281213,"about_ca_system_score_codex":0.0008461926,"about_ca_system_score_gemma":0.0010193286,"threshold_uncertainty_score":0.99955016},"labels":[],"label_agreement":null},{"id":"W1560541823","doi":"10.1007/978-3-540-24741-8_9","title":"LIMBO: Scalable Clustering of Categorical Data","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":260,"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 Toronto","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Data mining; Tuple; Data stream clustering; Hierarchical clustering; Bottleneck; Scalability; Measure (data warehouse); CURE data clustering algorithm; Correlation clustering; Clustering high-dimensional data; Artificial intelligence; Machine learning; Database; Mathematics","score_opus":0.047484930229229186,"score_gpt":0.3097387021538155,"score_spread":0.2622537719245863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1560541823","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":[0.000009869559,0.0004661749,0.99506855,0.00051294034,0.0012070925,0.00035647248,0.000014429224,0.00015262642,0.0022118187],"genre_scores_gemma":[0.05062989,0.000102766506,0.94811314,0.00023776125,0.00039114105,0.0000061983687,0.000015593998,0.00005766701,0.0004458115],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941866,0.000034911824,0.0007281851,0.0022928962,0.00177164,0.0009858136],"domain_scores_gemma":[0.9940843,0.00048519488,0.00031756758,0.0045070127,0.00034071732,0.0002651922],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0012051644,0.0005360007,0.0007265948,0.0009317759,0.00020677748,0.00038004888,0.011590866,0.00033633263,0.000027709166],"category_scores_gemma":[0.00021573684,0.00050949084,0.000092564835,0.0010270565,0.0010230704,0.0012304967,0.012651553,0.0011748475,0.000045928522],"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":[0.000008135601,0.0000479449,0.000010081007,0.00014013426,0.000014415236,0.00021305656,0.00028618262,0.28997484,0.00020007411,0.009538195,0.000010008741,0.69955695],"study_design_scores_gemma":[0.00030470692,0.00017680918,0.000027811173,0.00036634834,0.0000045561364,0.0001226205,1.08958794e-7,0.8738716,0.00095818925,0.123164244,0.00050020247,0.0005027671],"about_ca_topic_score_codex":0.00010510435,"about_ca_topic_score_gemma":0.000083791725,"teacher_disagreement_score":0.6990542,"about_ca_system_score_codex":0.0006443911,"about_ca_system_score_gemma":0.0013184109,"threshold_uncertainty_score":0.99973565},"labels":[],"label_agreement":null},{"id":"W1561886765","doi":"10.1007/978-3-540-30076-2_22","title":"Novel Clustering Approach that Employs Genetic Algorithm with New Representation Scheme and Multiple Objectives","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":16,"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 Calgary","funders":"","keywords":"Computer science; Cluster analysis; Partition (number theory); Scheme (mathematics); Encoding (memory); Algorithm; Graph partition; Graph; Set (abstract data type); Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.03641534816727335,"score_gpt":0.2810127521842175,"score_spread":0.24459740401694416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1561886765","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":[0.00010509773,0.00042291085,0.99760425,0.0001807415,0.00035592896,0.0007500972,0.000004856723,0.00021752625,0.0003586008],"genre_scores_gemma":[0.014621936,0.000058739424,0.9845114,0.00015988425,0.00031480976,0.000014528679,0.000004706445,0.000064808184,0.00024921625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99485147,0.00002546028,0.00039579312,0.0024173274,0.0014420863,0.00086784316],"domain_scores_gemma":[0.99738836,0.00036471555,0.0002581272,0.0014263035,0.00021754789,0.00034496275],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036337404,0.00064667675,0.00056377257,0.0008225614,0.00034392384,0.00083394017,0.0022205806,0.00026722963,0.0000035597511],"category_scores_gemma":[0.00007902767,0.0005760062,0.0000733646,0.0007622688,0.0008594554,0.0010582687,0.0024341205,0.00094264577,0.0000057390585],"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":[0.000011575158,0.00003120789,0.00016490399,0.000052852676,0.000020099775,0.000056192042,0.0012415522,0.2858587,0.0003683842,0.00021748677,5.826607e-7,0.71197647],"study_design_scores_gemma":[0.001050493,0.0002465701,0.0016562747,0.0003713059,0.000005983858,0.00052523543,0.000001617923,0.98088765,0.0013657681,0.013142261,0.000024629064,0.0007222107],"about_ca_topic_score_codex":0.00026728917,"about_ca_topic_score_gemma":0.00006472266,"teacher_disagreement_score":0.71125424,"about_ca_system_score_codex":0.0005062191,"about_ca_system_score_gemma":0.0007804301,"threshold_uncertainty_score":0.99966913},"labels":[],"label_agreement":null},{"id":"W1567786505","doi":"10.1002/0471708607.ch10","title":"Fuzzy Clustering of Heterogeneous Patterns","year":2005,"lang":"en","type":"other","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Fuzzy clustering; Data mining; Representation (politics); Fuzzy logic; Computer science; Artificial intelligence; Mathematics; Pattern recognition (psychology); Theoretical computer science","score_opus":0.01856599385683777,"score_gpt":0.29215851760196254,"score_spread":0.27359252374512477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1567786505","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000024641715,0.00024091668,0.6209994,0.000044530134,0.00020978153,0.00013618497,0.000011436735,0.00033207607,0.3780232],"genre_scores_gemma":[0.00070247776,0.00018869192,0.2551964,0.000070576476,0.00031301903,0.00001724049,0.0000039687384,0.0002797071,0.74322796],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983182,0.000037973514,0.0002551403,0.00051229727,0.0004707158,0.00040564963],"domain_scores_gemma":[0.9985312,0.000033904715,0.00015688513,0.0011302681,0.000036628284,0.000111065194],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008587566,0.00025059126,0.00033920066,0.0003436671,0.000020896623,0.000049894265,0.0015834434,0.00017980977,0.0010354181],"category_scores_gemma":[0.000010292922,0.00023322106,0.000097304845,0.00017840302,0.00003985524,0.00008515105,0.0011706246,0.00019455585,0.00017595872],"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":[0.0000051685265,0.00012064057,0.000039963168,0.0005478242,0.00016169314,0.00016638833,0.00016629152,0.0053903796,0.000182873,0.0010026196,0.032229755,0.9599864],"study_design_scores_gemma":[0.0010083743,0.0003060318,0.00006181587,0.00092058827,0.000014365394,0.00027770398,0.000017336444,0.19870546,0.002894701,0.0003055077,0.79396945,0.0015186465],"about_ca_topic_score_codex":0.00023043356,"about_ca_topic_score_gemma":0.0003243733,"teacher_disagreement_score":0.9584678,"about_ca_system_score_codex":0.000054746608,"about_ca_system_score_gemma":0.000041213687,"threshold_uncertainty_score":0.99987775},"labels":[],"label_agreement":null},{"id":"W1568806324","doi":"10.1007/3-540-45683-x_46","title":"Efficiently Clustering Documents with Committees","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":10,"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; Similarity (geometry); Set (abstract data type); Data mining; Task (project management); Group (periodic table); Cluster (spacecraft); Space (punctuation); Document clustering; Correlation clustering; Single-linkage clustering; CURE data clustering algorithm; Information retrieval; Artificial intelligence; Image (mathematics)","score_opus":0.018519313587672916,"score_gpt":0.269153790340296,"score_spread":0.2506344767526231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1568806324","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":[0.000060842016,0.0002836599,0.9902265,0.0005436329,0.00090723956,0.00056982005,0.0000039069046,0.0002985006,0.0071058865],"genre_scores_gemma":[0.05660048,0.00007649196,0.93827534,0.0008555076,0.0004166771,0.000030973984,0.0000040738887,0.000105366096,0.003635116],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993881,0.00004456852,0.0005360867,0.0020984197,0.002171846,0.0012680948],"domain_scores_gemma":[0.9963836,0.00044730757,0.0002752292,0.0022602007,0.00031424788,0.000319396],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00067568105,0.0007353229,0.00064112595,0.0011574995,0.00043609258,0.0010453721,0.005521765,0.00026770867,0.00004649772],"category_scores_gemma":[0.000055592613,0.0006251734,0.00010466983,0.0010186961,0.0010138553,0.00096144027,0.0036028237,0.0013136953,0.00013684433],"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":[0.00001191772,0.000051401385,0.000040890165,0.0000634349,0.000021912796,0.0005578496,0.0007852809,0.2799994,0.000050796825,0.0025540888,0.000021329075,0.7158417],"study_design_scores_gemma":[0.0006014543,0.00044530592,0.00006958602,0.00067616295,0.0000058430746,0.00027095477,2.4869567e-7,0.9817252,0.000550488,0.011543305,0.0031463408,0.00096508046],"about_ca_topic_score_codex":0.000022980637,"about_ca_topic_score_gemma":0.00005835374,"teacher_disagreement_score":0.7148766,"about_ca_system_score_codex":0.0006864566,"about_ca_system_score_gemma":0.00028403534,"threshold_uncertainty_score":0.99999166},"labels":[],"label_agreement":null},{"id":"W1584777468","doi":"10.1007/11811305_30","title":"A Fuzzy Subspace Algorithm for Clustering High Dimensional Data","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Cluster analysis; Fuzzy clustering; Computer science; FLAME clustering; Subspace topology; Dimension (graph theory); k-medians clustering; Cluster (spacecraft); Fuzzy logic; Clustering high-dimensional data; Data mining; Correlation clustering; Pattern recognition (psychology); Single-linkage clustering; Algorithm; CURE data clustering algorithm; Artificial intelligence; Mathematics; Combinatorics","score_opus":0.03486772328265359,"score_gpt":0.3000635860296849,"score_spread":0.26519586274703133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1584777468","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":[0.000005414817,0.00044451683,0.99437773,0.0009590042,0.002323972,0.00087965874,0.00013533162,0.0002771875,0.0005972101],"genre_scores_gemma":[0.0013895449,0.000018357181,0.9952558,0.00048589037,0.0010885746,0.000031966294,0.00011482816,0.00008476637,0.0015302252],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927568,0.000040938874,0.0006801395,0.0032815756,0.0018564432,0.0013841109],"domain_scores_gemma":[0.9937458,0.0010882845,0.000325514,0.004079757,0.0004799419,0.00028069623],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0014348316,0.0007634051,0.00075427163,0.0009719799,0.00049632305,0.00080793933,0.00928976,0.00039547827,0.000006993034],"category_scores_gemma":[0.00014544876,0.00074160594,0.00013065933,0.0007356648,0.0007755291,0.0013440333,0.010005248,0.0010460573,0.000032782384],"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":[0.0000056394674,0.00002654929,0.0000013943115,0.000042775242,0.000012601879,0.000105801344,0.00005405139,0.13688105,0.000056682118,0.0011965171,0.00017085946,0.8614461],"study_design_scores_gemma":[0.000519793,0.00016698819,0.000020688209,0.0002812272,0.0000071373015,0.00012352089,5.493044e-8,0.91919756,0.0002703518,0.07646069,0.0021872255,0.0007647794],"about_ca_topic_score_codex":0.00011343379,"about_ca_topic_score_gemma":0.00017133537,"teacher_disagreement_score":0.8606813,"about_ca_system_score_codex":0.0005727097,"about_ca_system_score_gemma":0.00081695436,"threshold_uncertainty_score":0.9995035},"labels":[],"label_agreement":null},{"id":"W1586523483","doi":"10.1007/11533719_67","title":"On Approximate Balanced Bi-clustering","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","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":"McMaster University","funders":"","keywords":"Cluster analysis; Computer science; Heuristic; Bounded function; Mathematical optimization; Cluster (spacecraft); Set (abstract data type); Quadratic programming; Quadratic equation; Constrained clustering; Heuristics; Algorithm; Correlation clustering; Theoretical computer science; Mathematics; CURE data clustering algorithm; Artificial intelligence","score_opus":0.021576937168322402,"score_gpt":0.28273569928771697,"score_spread":0.2611587621193946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1586523483","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":[0.000026719648,0.00020048214,0.98756677,0.0010196411,0.0014595381,0.00050343067,0.0000058106903,0.0004048256,0.008812806],"genre_scores_gemma":[0.024251724,0.00008691248,0.9700771,0.0022875925,0.000925159,0.00003234905,0.0000051839334,0.0001049373,0.0022290237],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99380136,0.00004150748,0.0006015168,0.0023697186,0.0018631626,0.0013227093],"domain_scores_gemma":[0.99613637,0.00062476966,0.0002716597,0.0024157409,0.0002368773,0.00031458552],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009081809,0.0007582913,0.0006774448,0.0012814285,0.00034920513,0.00075210875,0.0055154664,0.00035857983,0.000039194863],"category_scores_gemma":[0.0001487724,0.0007105035,0.00015323063,0.00082748407,0.0006613423,0.00080128905,0.0033391241,0.0015260669,0.00019326025],"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":[0.000009272439,0.000023578674,0.0000019249812,0.000037384605,0.000007049735,0.00012647473,0.0002170478,0.2603814,0.00013909653,0.005785213,0.000013825932,0.7332577],"study_design_scores_gemma":[0.00037057739,0.00022860813,0.000019110239,0.0004953673,0.0000022306567,0.00009445687,6.62334e-8,0.9231737,0.0009868353,0.07241725,0.001456342,0.000755421],"about_ca_topic_score_codex":0.000008092715,"about_ca_topic_score_gemma":0.000035573506,"teacher_disagreement_score":0.73250234,"about_ca_system_score_codex":0.00085062295,"about_ca_system_score_gemma":0.0004146173,"threshold_uncertainty_score":0.9998652},"labels":[],"label_agreement":null},{"id":"W1633233002","doi":"10.48550/arxiv.1311.2334","title":"Embed and Conquer: Scalable Embeddings for Kernel k-Means on MapReduce","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Kernel (algebra); Computer science; Scalability; Embedding; Divide and conquer algorithms; Benchmark (surveying); Cluster analysis; Parallel computing; Computation; Scaling; Theoretical computer science; Algorithm; Mathematics; Artificial intelligence; Discrete mathematics","score_opus":0.07124242219138041,"score_gpt":0.2299106971668386,"score_spread":0.15866827497545818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1633233002","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":[0.17625275,0.000042073334,0.82021546,0.00026500406,0.00043643554,0.0009025378,0.000038542916,0.0003168149,0.0015303729],"genre_scores_gemma":[0.94798297,0.00017831878,0.038549293,0.00017439257,0.00009612097,0.000018163026,0.00001792656,0.000052672214,0.012930171],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99716914,0.00009134369,0.00021271259,0.0016782766,0.0001627075,0.0006857978],"domain_scores_gemma":[0.99745905,0.00033691747,0.00019446356,0.0013533996,0.00031979894,0.00033634258],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000280848,0.00041084996,0.0004287216,0.00031539306,0.0002494604,0.00032583324,0.0019119012,0.00032628648,0.00002698944],"category_scores_gemma":[0.00009718016,0.00046828762,0.00014818826,0.00035216368,0.00020939224,0.0005364201,0.0029682731,0.00068372436,0.00012455611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020882749,0.00037685415,0.00056768104,0.0009316788,0.00036381494,0.00034966174,0.0011881943,0.63362163,0.0008556097,0.33897293,0.005217866,0.017345252],"study_design_scores_gemma":[0.000785345,0.00015738921,0.00031381747,0.00014649025,0.000021128102,0.0000077636505,0.000049143084,0.9434707,0.00048970623,0.05209306,0.0019486782,0.00051674177],"about_ca_topic_score_codex":0.00018832204,"about_ca_topic_score_gemma":0.000010183754,"teacher_disagreement_score":0.78166616,"about_ca_system_score_codex":0.00030192034,"about_ca_system_score_gemma":0.00016778361,"threshold_uncertainty_score":0.9997769},"labels":[],"label_agreement":null},{"id":"W1698234622","doi":"10.1109/wiri.2005.7","title":"An Efficient Technique for Mining Usage Profiles Using Relational Fuzzy Subtractive Clustering","year":2005,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Data mining; Computer science; Subtractive color; Fuzzy clustering; Correlation clustering; CURE data clustering algorithm; Data stream clustering; Web mining; Machine learning; Web page","score_opus":0.05623948391364995,"score_gpt":0.35776641058514536,"score_spread":0.3015269266714954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1698234622","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":[0.022017656,0.00001497133,0.9754778,0.00020366335,0.00008232726,0.0007330404,0.000004936941,0.00023169206,0.0012339125],"genre_scores_gemma":[0.32373673,4.5420774e-7,0.6758249,0.00003671177,0.00011834896,0.00010941469,0.000002583969,0.000015204653,0.00015568816],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983386,0.00005957684,0.0002513016,0.0005222237,0.00037628663,0.0004520387],"domain_scores_gemma":[0.99893534,0.00024895955,0.00008664706,0.00042803824,0.00017525852,0.00012573245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006127075,0.00015289163,0.00013765416,0.00019937755,0.00030523675,0.00013662291,0.00057686673,0.00008029075,0.000011036044],"category_scores_gemma":[0.00007743699,0.00014851823,0.000051301024,0.00030479135,0.0000485165,0.0009189206,0.00028467528,0.00016053881,0.000006877295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026642738,0.00013197443,0.00007668922,0.000026386997,0.000012176236,0.0000065595736,0.00080781215,0.8433415,0.10410443,0.0076218545,0.000013997138,0.043829948],"study_design_scores_gemma":[0.00022929665,0.00009216922,0.0002798257,0.000029264958,0.0000018625277,0.00004745734,0.0000733123,0.95391,0.044621006,0.00020429851,0.00031942184,0.00019209045],"about_ca_topic_score_codex":0.000010910224,"about_ca_topic_score_gemma":0.000007698159,"teacher_disagreement_score":0.30171907,"about_ca_system_score_codex":0.0002020679,"about_ca_system_score_gemma":0.00011266445,"threshold_uncertainty_score":0.60563976},"labels":[],"label_agreement":null},{"id":"W1712808800","doi":"10.1007/11527503_23","title":"A Genetic k-Modes Algorithm for Clustering Categorical Data","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"York University","funders":"","keywords":"Computer science; Cluster analysis; Categorical variable; Algorithm; Genetic algorithm; Data mining; Artificial intelligence; Machine learning","score_opus":0.05120452901881751,"score_gpt":0.32311428098578854,"score_spread":0.27190975196697104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1712808800","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":[0.0000023832145,0.00086330326,0.99567443,0.0006511637,0.0011377059,0.0008706691,0.000045372566,0.00026125697,0.00049371156],"genre_scores_gemma":[0.0021951408,0.00010826092,0.99481535,0.00048443623,0.0015916945,0.000041012834,0.000022200447,0.00008061084,0.00066131976],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99323535,0.00003729535,0.0007171436,0.0031581204,0.0014702745,0.0013818422],"domain_scores_gemma":[0.9940215,0.00083507673,0.00025613394,0.0041782428,0.0003624732,0.0003466227],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0010768851,0.00071149983,0.0007115748,0.00091647316,0.00040299323,0.000874803,0.011523158,0.00038949816,0.000012039378],"category_scores_gemma":[0.00016008443,0.00068969146,0.00012905439,0.00064565346,0.0006921638,0.001175692,0.009239799,0.0010257177,0.000043387765],"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":[0.0000027856825,0.000021457123,0.0000016173171,0.000035799058,0.000011250009,0.00008229632,0.000112305264,0.074408084,0.000036325906,0.0007393114,0.000019185885,0.92452955],"study_design_scores_gemma":[0.00038683714,0.00015314436,0.000018222192,0.00012933357,0.0000075723374,0.0002253043,1.1733442e-7,0.9514332,0.00015333421,0.041727662,0.0050331457,0.0007321634],"about_ca_topic_score_codex":0.000028086339,"about_ca_topic_score_gemma":0.00009133159,"teacher_disagreement_score":0.9237974,"about_ca_system_score_codex":0.0006713099,"about_ca_system_score_gemma":0.0008468619,"threshold_uncertainty_score":0.9995554},"labels":[],"label_agreement":null},{"id":"W1724273493","doi":"","title":"Analyse automatique de donnees par support vector machines non supervises","year":2012,"lang":"fr","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Humanities; Support vector machine; Computer science; Artificial intelligence; Philosophy","score_opus":0.03550654522456509,"score_gpt":0.334112047573668,"score_spread":0.29860550234910294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1724273493","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":[0.1271644,0.0023233506,0.8512155,0.011651195,0.0018440036,0.000344914,0.00002313773,0.00047826293,0.004955246],"genre_scores_gemma":[0.6365971,0.00029260173,0.3155439,0.0006365453,0.0011159666,0.000059742873,0.000009695334,0.000059051104,0.04568541],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962663,0.0003156192,0.00046495165,0.0005457083,0.0006108283,0.0017965889],"domain_scores_gemma":[0.99751186,0.0003566214,0.00009262771,0.0009937505,0.00021617542,0.00082893524],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011177477,0.00039262572,0.00041753938,0.00023994767,0.00026920828,0.00039190153,0.0012888566,0.00021491227,0.0016748054],"category_scores_gemma":[0.00025425488,0.00036176847,0.00018488395,0.00089235656,0.00023064505,0.002543187,0.0010216923,0.00046149487,0.0009799778],"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":[0.000055454482,0.0020629137,0.19950435,0.0013584441,0.00054204994,0.0006055301,0.026047897,0.0063395924,0.017811064,0.02386031,0.029368293,0.6924441],"study_design_scores_gemma":[0.0004913148,0.00029670875,0.119570345,0.00010373797,0.000043243755,0.0004532769,0.00019957052,0.8248757,0.022489436,0.0006781729,0.030068995,0.0007294589],"about_ca_topic_score_codex":0.0019522404,"about_ca_topic_score_gemma":0.00028696228,"teacher_disagreement_score":0.81853616,"about_ca_system_score_codex":0.00029585345,"about_ca_system_score_gemma":0.00038266758,"threshold_uncertainty_score":0.9998834},"labels":[],"label_agreement":null},{"id":"W182707955","doi":"10.1137/1.9781611972764.29","title":"Density-Based Clustering over an Evolving Data Stream with Noise","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1000,"is_retracted":false,"has_abstract":true,"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; Cluster analysis; Noise (video); Data mining; Artificial intelligence","score_opus":0.030329829383991817,"score_gpt":0.3020425877552507,"score_spread":0.2717127583712589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W182707955","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":[0.033831574,0.000016796224,0.96376157,0.0001642087,0.000062545296,0.00014324767,0.0000058014953,0.00040700883,0.0016072753],"genre_scores_gemma":[0.47777608,4.6547876e-7,0.52156365,0.00011077629,0.0000825446,0.0000048499214,0.000026791246,0.000018118957,0.0004167395],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792427,0.00005600346,0.00017471156,0.00078569306,0.00056994363,0.0004893601],"domain_scores_gemma":[0.99716234,0.00009492016,0.000051727508,0.002413934,0.00013588829,0.00014116801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027556304,0.00017661923,0.00015130086,0.00013078935,0.00018150077,0.00045600525,0.0020624127,0.0000438822,0.00003242761],"category_scores_gemma":[0.000026565576,0.00014558762,0.000017406008,0.00041210622,0.00006038192,0.0021846262,0.001332481,0.00017559946,0.000024183591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022932906,0.0015215679,0.044698067,0.00029681294,0.00009534013,0.0017355429,0.00038339637,0.6265996,0.02511273,0.005678869,0.0042609507,0.28938776],"study_design_scores_gemma":[0.0004971521,0.00011027314,0.011009767,0.000025070967,0.0000026428313,0.000022436001,0.000010691508,0.98565274,0.0019302057,0.0001543643,0.0003555551,0.00022911213],"about_ca_topic_score_codex":0.0010086623,"about_ca_topic_score_gemma":0.0014849422,"teacher_disagreement_score":0.4439445,"about_ca_system_score_codex":0.00008756757,"about_ca_system_score_gemma":0.00012369762,"threshold_uncertainty_score":0.5936891},"labels":[],"label_agreement":null},{"id":"W1875624538","doi":"10.1007/s11634-015-0219-5","title":"Factor probabilistic distance clustering (FPDC): a new clustering method","year":2015,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Università degli Studi di Napoli Federico II","keywords":"Cluster analysis; Correlation clustering; CURE data clustering algorithm; Single-linkage clustering; Probabilistic logic; Canopy clustering algorithm; Computer science; Data stream clustering; Fuzzy clustering; Determining the number of clusters in a data set; Clustering high-dimensional data; k-medians clustering; Transformation (genetics); Mathematics; Pattern recognition (psychology); Data mining; Artificial intelligence","score_opus":0.12235253318764872,"score_gpt":0.4083881885969034,"score_spread":0.2860356554092547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1875624538","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":[0.00025380575,0.001424383,0.9970609,0.00057155837,0.00010939121,0.00019143459,0.000030664556,0.00008627451,0.00027161284],"genre_scores_gemma":[0.23347037,0.0008756719,0.76494277,0.00004584884,0.000081718295,0.000038527214,0.00014529764,0.000016661248,0.00038312652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99742055,0.00016971379,0.0004622464,0.0011046231,0.0004795098,0.00036335576],"domain_scores_gemma":[0.99723667,0.00021814989,0.00019838534,0.0019921414,0.00010430371,0.00025036503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077598647,0.00019541361,0.0003560179,0.00035902418,0.000090695554,0.0002865333,0.0016936463,0.000060428785,0.000005051982],"category_scores_gemma":[0.0004747242,0.00018306069,0.000040445928,0.0020960968,0.0000646219,0.0030230957,0.0013103675,0.00020098496,0.000008550034],"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":[0.000028780923,0.000056040648,0.0032609822,0.00006133363,0.000076325734,0.0000094871775,0.00062571146,0.044351906,0.000288549,0.0022089055,0.000044630193,0.94898736],"study_design_scores_gemma":[0.0003160083,0.000025494386,0.0062042163,0.000026299507,0.000037639824,0.000005523121,0.00013935193,0.979554,0.000025336833,0.002718244,0.010732594,0.00021528536],"about_ca_topic_score_codex":0.00010568818,"about_ca_topic_score_gemma":0.0026813033,"teacher_disagreement_score":0.9487721,"about_ca_system_score_codex":0.0001890646,"about_ca_system_score_gemma":0.00010243148,"threshold_uncertainty_score":0.74649984},"labels":[],"label_agreement":null},{"id":"W1891514807","doi":"10.1007/3-540-47887-6_4","title":"On Data Clustering Analysis: Scalability, Constraints, and Validation","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":88,"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; Scalability; Data mining; Correlation clustering; Similarity (geometry); Consensus clustering; CURE data clustering algorithm; Artificial intelligence; Machine learning; Database","score_opus":0.050158553012031065,"score_gpt":0.31330475141825476,"score_spread":0.26314619840622366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1891514807","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":[0.00007679317,0.00015626157,0.9965968,0.0005485945,0.00046173847,0.00035170183,0.000026120597,0.00014809852,0.001633891],"genre_scores_gemma":[0.22811839,0.000117848256,0.7705205,0.00054336095,0.00026447282,0.000008942415,0.000038095295,0.000043191674,0.00034517827],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947337,0.00006789001,0.00052394456,0.0026346566,0.0013651268,0.0006746691],"domain_scores_gemma":[0.99480677,0.0009426485,0.0002187642,0.0035980006,0.00019921159,0.00023459044],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014737195,0.00047917996,0.0005944345,0.0014763157,0.0002767109,0.0008942328,0.004985479,0.00024835125,0.000046632274],"category_scores_gemma":[0.00030039222,0.0004573952,0.00007914552,0.0012803732,0.0013660111,0.0009869543,0.0063682543,0.0009094601,0.00003076098],"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":[0.0000035645617,0.000024104851,0.000048506754,0.000038652295,0.00004830076,0.00006142483,0.00019135287,0.12992072,0.000017153801,0.0032582702,0.000005178348,0.8663828],"study_design_scores_gemma":[0.00018848025,0.00011050555,0.00015260656,0.00017030982,0.000024704706,0.000047020643,1.0369042e-7,0.9595024,0.00011907911,0.039124846,0.00011646137,0.0004434672],"about_ca_topic_score_codex":0.000015132019,"about_ca_topic_score_gemma":0.000043427633,"teacher_disagreement_score":0.8659393,"about_ca_system_score_codex":0.0003089427,"about_ca_system_score_gemma":0.00018075321,"threshold_uncertainty_score":0.9997878},"labels":[],"label_agreement":null},{"id":"W191887720","doi":"10.1007/s00357-001-0018-x","title":"Optimal Variable Weighting for Ultrametric and Additive Trees and K-means Partitioning: Methods and Software","year":2001,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":96,"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":"Ultrametric space; Weighting; Outlier; Cluster analysis; Recursive partitioning; Variable (mathematics); Partition (number theory); Computer science; Monte Carlo method; Algorithm; Data mining; Tree (set theory); Mathematics; Statistics; Artificial intelligence; Machine learning; Combinatorics","score_opus":0.05001129746715327,"score_gpt":0.3724863672266711,"score_spread":0.32247506975951784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W191887720","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":[0.015805902,0.00047603608,0.9828693,0.00060460385,0.00006293168,0.00010030159,0.000003035528,0.000016717291,0.000061148996],"genre_scores_gemma":[0.050768156,0.00049365254,0.94851923,0.000021192764,0.00009047117,0.000009946366,0.00000117563,0.0000067726733,0.000089414316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991181,0.00010043989,0.00026511378,0.00018484457,0.00017054024,0.00016097433],"domain_scores_gemma":[0.99804926,0.001163131,0.0002613934,0.00010891132,0.00030605105,0.000111224996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009789171,0.000081072314,0.00015913566,0.00021528782,0.0001748815,0.00019319459,0.00013896528,0.00004785697,0.0000022926909],"category_scores_gemma":[0.0011560133,0.00006697453,0.000021864014,0.0003489734,0.00006757401,0.0007619719,0.00005215023,0.00014765527,1.7929298e-7],"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":[0.000044644246,0.000043701817,0.0012165692,0.000030705443,0.00003550225,0.0000052725513,0.0005676752,0.0009850807,0.0071133985,0.004193003,0.00008686008,0.9856776],"study_design_scores_gemma":[0.0010311614,0.0005498572,0.03813516,0.000100978345,0.000029601966,0.0006520379,0.00042493333,0.9371274,0.0023920445,0.008861195,0.010516808,0.00017880222],"about_ca_topic_score_codex":0.0000018269924,"about_ca_topic_score_gemma":6.0261385e-7,"teacher_disagreement_score":0.9854988,"about_ca_system_score_codex":0.000042879732,"about_ca_system_score_gemma":0.00004823581,"threshold_uncertainty_score":0.2731142},"labels":[],"label_agreement":null},{"id":"W1966755259","doi":"10.1109/nafips.2010.5548181","title":"A new approach to improve the accuracy of online clustering algorithm based on scatter/gather model","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","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":"Toronto Metropolitan University","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Process (computing); Cluster (spacecraft); Canopy clustering algorithm; Algorithm; CURE data clustering algorithm; Correlation clustering; Algorithm design; Data stream clustering; Artificial intelligence; Machine learning","score_opus":0.02906525681003538,"score_gpt":0.31646283583198503,"score_spread":0.2873975790219497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966755259","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":[0.0008634427,0.0000025822908,0.992044,0.0029413074,0.0002115479,0.00050634245,0.000011239537,0.0001289556,0.0032906327],"genre_scores_gemma":[0.03256154,7.1919493e-7,0.96258205,0.0013228562,0.00014725458,0.0000399324,0.0000023242046,0.00002836271,0.003314975],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794793,0.00004240001,0.00028658373,0.0006180797,0.000634736,0.00047028792],"domain_scores_gemma":[0.9974919,0.00028793054,0.00008761222,0.0017492457,0.00013648199,0.0002468605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043300603,0.00021248874,0.00020715706,0.00016536935,0.000108642016,0.00014003088,0.0023478016,0.00007801059,0.00002588298],"category_scores_gemma":[0.00017532597,0.00014139089,0.00008783866,0.0005174195,0.000053692893,0.00030854304,0.0009632801,0.00051576993,0.000044537435],"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":[0.000014911348,0.00018463141,0.000002486234,0.000016240552,0.000008843432,0.000001397569,0.0003510731,0.18294597,0.014517202,0.00067167234,0.00044519026,0.8008404],"study_design_scores_gemma":[0.00041880485,0.000089577006,0.000060121605,0.000012412949,0.000002141292,0.0000056523218,0.000023107077,0.99236166,0.005884415,0.0005173412,0.00045120486,0.00017358457],"about_ca_topic_score_codex":0.00014603802,"about_ca_topic_score_gemma":0.00003161099,"teacher_disagreement_score":0.8094157,"about_ca_system_score_codex":0.000040617142,"about_ca_system_score_gemma":0.00024833053,"threshold_uncertainty_score":0.57657534},"labels":[],"label_agreement":null},{"id":"W1972132022","doi":"10.1145/1046456.1046468","title":"Subspace clustering for high dimensional categorical data","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Clustering high-dimensional data; Categorical variable; Correlation clustering; CURE data clustering algorithm; Data mining; Subspace topology; Canopy clustering algorithm; Data stream clustering; Focus (optics); Algorithm; Pattern recognition (psychology); Artificial intelligence; Machine learning","score_opus":0.11230554248111278,"score_gpt":0.34489126193553477,"score_spread":0.23258571945442197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972132022","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":[0.0027341736,0.000037744605,0.92149484,0.07449408,0.0005146203,0.00042097952,0.000024876723,0.0002542343,0.000024437457],"genre_scores_gemma":[0.20555148,0.000007963334,0.79005224,0.0030100294,0.0005358455,0.00025416387,0.00023651395,0.000041219362,0.0003105326],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766606,0.000050961775,0.0003247646,0.00088154984,0.00049714406,0.00057949696],"domain_scores_gemma":[0.99597746,0.0003470546,0.00007833023,0.003250398,0.00017988641,0.00016689605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028889067,0.00022371842,0.00020806375,0.0001738008,0.00041065164,0.0003026644,0.003262907,0.00008812359,0.0000130062435],"category_scores_gemma":[0.0004711494,0.00021567714,0.000050599414,0.0005390499,0.0000772248,0.0024638136,0.003044442,0.00025831372,0.00023062172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019316973,0.0011348899,0.00012823619,0.00018608617,0.00033566562,0.00049634743,0.0048464206,0.5114476,0.06080486,0.14269635,0.15488613,0.12284425],"study_design_scores_gemma":[0.006744563,0.00066955073,0.0006657018,0.0000906792,0.000049621234,0.00026373108,0.00016407653,0.72116345,0.019552743,0.1915259,0.057022095,0.002087855],"about_ca_topic_score_codex":0.00008112521,"about_ca_topic_score_gemma":0.00007934668,"teacher_disagreement_score":0.20971589,"about_ca_system_score_codex":0.00017663324,"about_ca_system_score_gemma":0.00016029322,"threshold_uncertainty_score":0.8795058},"labels":[],"label_agreement":null},{"id":"W1973892392","doi":"10.1016/s0167-8655(02)00130-7","title":"Collaborative fuzzy clustering","year":2002,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":282,"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; Partition (number theory); Computer science; Data mining; Fuzzy clustering; Fuzzy logic; Theoretical computer science; Basis (linear algebra); Artificial intelligence; Mathematics","score_opus":0.034607468860997824,"score_gpt":0.26777838524257236,"score_spread":0.23317091638157453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973892392","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":[0.022829838,0.000053803407,0.96544397,0.008426816,0.00044796884,0.00025016963,0.000017435163,0.00033511803,0.0021949096],"genre_scores_gemma":[0.8383354,0.0001270265,0.1454315,0.014865034,0.0005268403,0.00025644267,0.000027341308,0.00006675348,0.00036365437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829197,0.00012455473,0.00023460391,0.0004884921,0.00039949635,0.00046087094],"domain_scores_gemma":[0.99912065,0.000117004885,0.000088250534,0.00041515843,0.00012356057,0.00013537762],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014767367,0.00017952739,0.00015394772,0.00019783311,0.00016878443,0.00024025161,0.00058076467,0.00004750667,0.00022307428],"category_scores_gemma":[0.000043003576,0.00019043892,0.000054679924,0.0005564661,0.000058486115,0.00080946815,0.0002812129,0.00023461049,0.0017741369],"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":[0.0000028267534,0.00004631335,0.00020668862,0.000026922395,0.00002389546,0.00012278407,0.0010223036,0.0003376847,0.0042543346,0.000004981078,0.0028846823,0.9910666],"study_design_scores_gemma":[0.0031539002,0.00031340242,0.0035331417,0.0003164759,0.000018950146,0.0003411532,0.00027872357,0.96238863,0.014858132,0.0012623498,0.011591747,0.0019434005],"about_ca_topic_score_codex":0.000010108695,"about_ca_topic_score_gemma":0.000009510104,"teacher_disagreement_score":0.98912317,"about_ca_system_score_codex":0.00010423004,"about_ca_system_score_gemma":0.000007001006,"threshold_uncertainty_score":0.9990031},"labels":[],"label_agreement":null},{"id":"W1977437243","doi":"10.1007/s10489-008-0129-8","title":"Parallel clustering of high dimensional data by integrating multi-objective genetic algorithm with divide and conquer","year":2008,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":29,"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 Calgary","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Divide and conquer algorithms; Centroid; CURE data clustering algorithm; Single-linkage clustering; Correlation clustering; Tree (set theory); Scalability; Canopy clustering algorithm; Fuzzy clustering; Process (computing); Node (physics); Algorithm; Artificial intelligence; Mathematics; Database","score_opus":0.039269687142191013,"score_gpt":0.2876830857060188,"score_spread":0.2484133985638278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977437243","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":[0.00465714,0.0003065735,0.9944013,0.000052937765,0.000055527125,0.0003340955,0.000027860931,0.00007897092,0.00008563268],"genre_scores_gemma":[0.31429493,0.00010442988,0.6853854,0.000068129884,0.000018763027,0.000033367873,0.000014354046,0.000017639764,0.00006296037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775726,0.00004589764,0.00037078367,0.00088967296,0.00051350694,0.0004228935],"domain_scores_gemma":[0.99821275,0.00031128354,0.00015359897,0.0010249629,0.00015211763,0.00014526573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021658844,0.00025136108,0.00031006944,0.00009403366,0.00020690168,0.000047738093,0.0013944252,0.00006755679,0.000008210866],"category_scores_gemma":[0.000053365136,0.00021003875,0.000016711976,0.00036486008,0.0004671572,0.00048674722,0.0019729591,0.0003172874,0.000012027206],"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":[0.000064062166,0.00018494952,0.00022966678,0.000052451654,0.00010206085,0.000094637486,0.001972829,0.025893472,0.0044693095,0.0016246107,0.00013457157,0.96517736],"study_design_scores_gemma":[0.00032330785,0.00015782389,0.0007631157,0.00005561879,0.000005570925,0.0001944475,0.000114753384,0.98390365,0.013381354,0.000703261,0.0000842531,0.00031284525],"about_ca_topic_score_codex":0.00040147788,"about_ca_topic_score_gemma":0.000020727404,"teacher_disagreement_score":0.96486455,"about_ca_system_score_codex":0.000048074446,"about_ca_system_score_gemma":0.00009369365,"threshold_uncertainty_score":0.85651314},"labels":[],"label_agreement":null},{"id":"W1977655121","doi":"10.1145/1281192.1281229","title":"Constraint-driven clustering","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Computer science; Constrained clustering; Data mining; Constraint (computer-aided design); Scalability; Node (physics); A priori and a posteriori; Tree (set theory); Correlation clustering; CURE data clustering algorithm; Machine learning; Mathematics; Database","score_opus":0.027766444093233224,"score_gpt":0.32127261763251275,"score_spread":0.29350617353927955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977655121","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":[0.0014194185,0.000011181873,0.955916,0.00033093904,0.00018686948,0.00007976772,2.5270828e-7,0.000330024,0.041725557],"genre_scores_gemma":[0.392698,0.0000023562573,0.6055952,0.00018692263,0.000054661974,0.0000021714993,2.6173126e-7,0.0000064908413,0.0014539569],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884546,0.000013661985,0.00015603338,0.00027008823,0.0002737371,0.00044104838],"domain_scores_gemma":[0.9992284,0.0001212899,0.000024019859,0.0004175297,0.00006151668,0.00014721265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038055045,0.00008260701,0.00008253748,0.000108709835,0.00008243868,0.000087919834,0.00073527556,0.000035991234,0.000043901517],"category_scores_gemma":[0.000039772036,0.000075957134,0.00003083429,0.0002840786,0.000063140906,0.00034120106,0.0005564102,0.00013481113,0.00015833881],"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":[0.0000062899962,0.00003497414,0.00029511136,0.000014097774,0.000013589926,0.00024094478,0.00038003837,0.0020516946,0.008665637,0.04445741,0.00021674695,0.9436235],"study_design_scores_gemma":[0.00061312725,0.00011832823,0.0027671496,0.00002251374,0.0000011152562,0.00027687536,0.00016627391,0.966113,0.015329459,0.0026188975,0.011581417,0.00039184376],"about_ca_topic_score_codex":0.00001306986,"about_ca_topic_score_gemma":0.000030213565,"teacher_disagreement_score":0.9640613,"about_ca_system_score_codex":0.000060036382,"about_ca_system_score_gemma":0.000030148725,"threshold_uncertainty_score":0.3097442},"labels":[],"label_agreement":null},{"id":"W1983989808","doi":"10.1007/s00357-005-0018-3","title":"Analysis of Global k-Means, an Incremental Heuristic for Minimum Sum-of-Squares Clustering","year":2005,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Advanced Clustering Algorithms Research","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":"Polytechnique Montréal; Group for Research in Decision Analysis; HEC Montréal","funders":"","keywords":"Cluster analysis; Heuristic; Explained sum of squares; Mathematics; Artificial intelligence; Pattern recognition (psychology); Combinatorics; Computer science; Statistics","score_opus":0.05400124671072944,"score_gpt":0.37078076021751716,"score_spread":0.31677951350678774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983989808","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":[0.18669271,0.000090315574,0.8125758,0.00038128174,0.00009166473,0.000091501395,0.00001540492,0.000008854119,0.00005241456],"genre_scores_gemma":[0.82781535,0.000019293862,0.17204139,0.000012288097,0.00008786331,0.0000029831074,0.000004215231,0.0000047152034,0.0000119249635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982712,0.000086230015,0.00075468747,0.00017284496,0.0005417122,0.0001733099],"domain_scores_gemma":[0.9980418,0.00014827203,0.00079937995,0.00035010767,0.0005602585,0.000100173784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073080196,0.00009106649,0.0003127032,0.0002971351,0.000049900682,0.000045000157,0.00072677096,0.000048058693,0.0000048261177],"category_scores_gemma":[0.00016380679,0.00008478457,0.00017005266,0.00079685653,0.000056853016,0.00069852616,0.00008169061,0.000088959336,6.9184006e-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":[0.00055011985,0.0010129098,0.01764364,0.00024406721,0.0011812566,0.000007753379,0.0017418456,0.1683648,0.12094622,0.0058836616,0.00018945071,0.6822343],"study_design_scores_gemma":[0.000463261,0.0003702082,0.051718276,0.00003155972,0.00011390897,0.000012124917,0.0001942893,0.94354504,0.0030202328,0.00021361133,0.00023812227,0.00007934187],"about_ca_topic_score_codex":0.000010167962,"about_ca_topic_score_gemma":0.00005019471,"teacher_disagreement_score":0.7751803,"about_ca_system_score_codex":0.00024575883,"about_ca_system_score_gemma":0.00011184475,"threshold_uncertainty_score":0.34574145},"labels":[],"label_agreement":null},{"id":"W1986303633","doi":"10.1049/el:20073093","title":"Performance of kernel-based fuzzy clustering","year":2007,"lang":"en","type":"article","venue":"Electronics Letters","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":25,"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","keywords":"Kernel (algebra); Artificial intelligence; Cluster analysis; Fuzzy logic; Data mining; Fuzzy clustering; Computer science; Machine learning; Pattern recognition (psychology); Mathematics","score_opus":0.010267746433416589,"score_gpt":0.26131967321908706,"score_spread":0.25105192678567045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986303633","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":[0.3580611,0.0000989716,0.6404925,0.0006929391,0.00010525534,0.000086831606,2.8647125e-7,0.000092689035,0.00036941876],"genre_scores_gemma":[0.91816974,0.000015827749,0.08099036,0.00068390125,0.000057741996,0.000005767687,0.0000013091178,0.000018514369,0.000056821125],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807924,0.000028889619,0.0002730486,0.00033588897,0.00046469376,0.000818237],"domain_scores_gemma":[0.999013,0.00012469613,0.00009978193,0.0006032635,0.00006607772,0.000093163944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069296034,0.00014536672,0.00016084027,0.00020624549,0.00009188165,0.000036714147,0.0010049985,0.000046364115,0.0000035900096],"category_scores_gemma":[0.000026020349,0.00015240049,0.00006175049,0.0005475186,0.00007088343,0.00030000356,0.0002163299,0.00032112445,0.000018367877],"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":[0.00016514846,0.0001300646,0.0028091213,0.00023483299,0.00005960311,0.00008423624,0.0004908513,0.13164596,0.5795367,0.0020765318,0.00030982896,0.28245714],"study_design_scores_gemma":[0.00071249955,0.00036952278,0.0029261115,0.000047433256,0.0000035402943,0.000026995092,0.000005895325,0.7721152,0.22099139,0.00009315594,0.0023755303,0.00033277774],"about_ca_topic_score_codex":0.000006571073,"about_ca_topic_score_gemma":0.000010657333,"teacher_disagreement_score":0.6404692,"about_ca_system_score_codex":0.00025134982,"about_ca_system_score_gemma":0.000103635655,"threshold_uncertainty_score":0.62147117},"labels":[],"label_agreement":null},{"id":"W1987111416","doi":"10.1002/widm.30","title":"Density‐based clustering","year":2011,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":810,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Outlier; Data set; Computer science; Data mining; Cluster (spacecraft); Set (abstract data type); Single-linkage clustering; DBSCAN; Pattern recognition (psychology); Correlation clustering; CURE data clustering algorithm; Artificial intelligence","score_opus":0.15651942522856147,"score_gpt":0.37289851207918545,"score_spread":0.216379086850624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987111416","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066762785,0.016310107,0.96860325,0.00014696637,0.0008680844,0.0004533319,0.00005175355,0.00021215131,0.0066780658],"genre_scores_gemma":[0.31578565,0.0047388356,0.6746106,0.00031073397,0.00062315335,0.0002075017,0.00030540433,0.00012468827,0.0032934076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970751,0.00027331882,0.0006131985,0.0012499513,0.00020890927,0.00057953584],"domain_scores_gemma":[0.9964978,0.00018032374,0.00018629528,0.002831871,0.00007036999,0.00023334534],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012494486,0.00037461307,0.00057226873,0.00022612745,0.0003815498,0.00034927213,0.0029981998,0.00008797894,0.00001849859],"category_scores_gemma":[0.00016543314,0.00031519527,0.000102412836,0.00046731948,0.00020035559,0.0032462743,0.015582321,0.0002762846,0.0001242306],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006613664,0.00029849267,0.0007937707,0.00065538235,0.000048339218,0.00015009147,0.007479899,0.000005711416,0.0002462685,0.00026354502,0.0074636955,0.9825287],"study_design_scores_gemma":[0.0015717172,0.00089897605,0.0026832288,0.0073540076,0.00010172589,0.000534586,0.0013463655,0.9414206,0.0008216036,0.0011046543,0.040119674,0.0020428589],"about_ca_topic_score_codex":0.000008572723,"about_ca_topic_score_gemma":0.000095553456,"teacher_disagreement_score":0.9804858,"about_ca_system_score_codex":0.00006526555,"about_ca_system_score_gemma":0.00012082917,"threshold_uncertainty_score":0.99993},"labels":[],"label_agreement":null},{"id":"W1990092496","doi":"10.1016/j.ins.2014.03.106","title":"A new credibilistic clustering algorithm","year":2014,"lang":"en","type":"article","venue":"Information Sciences","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":9,"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 Toronto","funders":"","keywords":"Cluster analysis; Fuzzy clustering; Computer science; FLAME clustering; Data mining; Correlation clustering; CURE data clustering algorithm; Measure (data warehouse); Pattern recognition (psychology); Fuzzy logic; Credibility; Artificial intelligence","score_opus":0.025568710353121037,"score_gpt":0.3085933236606262,"score_spread":0.28302461330750517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990092496","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":[0.00013602209,0.000009688292,0.98544633,0.0006807981,0.00043071955,0.00009391674,8.3334265e-7,0.00022813711,0.012973548],"genre_scores_gemma":[0.043584995,0.000004104492,0.95549124,0.00049092283,0.000115244344,0.0000053898957,0.0000012745577,0.0000026642786,0.0003041844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983738,0.00003841855,0.00028480095,0.00019947559,0.00075432705,0.00034916744],"domain_scores_gemma":[0.9991028,0.00016671116,0.000103263425,0.00035379056,0.00010915049,0.00016431026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009714578,0.00009809863,0.00010028768,0.00026061118,0.00031508357,0.00078627205,0.0014114017,0.000033059885,0.000024210598],"category_scores_gemma":[0.00034501034,0.00008340888,0.000029710976,0.0008957486,0.00010462528,0.0053795343,0.000474666,0.000101635844,0.00040590676],"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":[4.951787e-7,0.0000020171835,0.000009624648,0.0000053011913,9.956951e-7,2.736418e-7,0.0006313736,0.006480427,0.000015773883,0.0052720625,0.00036169228,0.98722],"study_design_scores_gemma":[0.00016176097,0.000082964834,0.0003376203,0.000011848644,4.6909142e-7,0.000022155336,0.000071420174,0.97142553,0.0001946696,0.0052365153,0.022339424,0.00011561195],"about_ca_topic_score_codex":0.000088550434,"about_ca_topic_score_gemma":0.0000056415233,"teacher_disagreement_score":0.98710436,"about_ca_system_score_codex":0.000045793207,"about_ca_system_score_gemma":0.00015530319,"threshold_uncertainty_score":0.758204},"labels":[],"label_agreement":null},{"id":"W1993343070","doi":"10.1109/icdm.2013.28","title":"Classification-Based Clustering Evaluation","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Generality; Computer science; Classifier (UML); Conceptual clustering; Data mining; Machine learning; Artificial intelligence; Task (project management); Process (computing); Pattern recognition (psychology); Fuzzy clustering; CURE data clustering algorithm","score_opus":0.06908488101264255,"score_gpt":0.34634609223937074,"score_spread":0.2772612112267282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993343070","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":[0.0027200263,0.000012431599,0.9842684,0.0024294215,0.00012091708,0.0003637688,1.2296346e-7,0.0002305231,0.009854336],"genre_scores_gemma":[0.6703062,6.8240064e-7,0.32864922,0.00022141404,0.00002704764,0.00020394246,0.0000018036861,0.0000059691515,0.0005837193],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874806,0.00007110698,0.00013974904,0.00028392446,0.000531189,0.00022598085],"domain_scores_gemma":[0.9988705,0.00010485333,0.000034873876,0.0005742467,0.00033190413,0.00008365392],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00037193656,0.00007264805,0.000059915506,0.00010032973,0.00009098138,0.00021906449,0.000602562,0.000030847645,0.00035359417],"category_scores_gemma":[0.00010143249,0.000064593776,0.000023408396,0.00030966927,0.000023271677,0.0006515852,0.0001492441,0.00007953751,0.0008507106],"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":[0.0000010453062,0.000040064413,0.00026488057,0.000011846919,0.0000052223527,8.0414014e-7,0.000086162916,0.025756173,0.0076968484,0.003384167,0.00083185255,0.9619209],"study_design_scores_gemma":[0.00019883591,0.000019012235,0.009619146,0.0000046313576,6.7880853e-7,0.0000013707726,0.000016308197,0.98701346,0.0010264893,0.0016933422,0.00032306596,0.000083669525],"about_ca_topic_score_codex":0.000054934786,"about_ca_topic_score_gemma":0.000006577137,"teacher_disagreement_score":0.9618373,"about_ca_system_score_codex":0.00011907296,"about_ca_system_score_gemma":0.000097033364,"threshold_uncertainty_score":0.9999272},"labels":[],"label_agreement":null},{"id":"W1997668352","doi":"10.1109/tkde.2012.190","title":"Efficient Cluster Labeling for Support Vector Clustering","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Cluster analysis; Disjoint sets; Interconnection; Cluster (spacecraft); Process (computing); Algorithm; Point (geometry); Function (biology); Data mining; Pattern recognition (psychology); Artificial intelligence; Mathematics","score_opus":0.03179128225384418,"score_gpt":0.3012782757759483,"score_spread":0.2694869935221041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997668352","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":[0.0018861995,0.00013514112,0.9961647,0.00016063215,0.0008012874,0.00047023536,0.000055256867,0.00027363823,0.0000529123],"genre_scores_gemma":[0.6742138,0.000045924502,0.32454228,0.00006200105,0.00016700722,0.00031074707,0.000016139154,0.00006135875,0.00058071903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853677,0.000015714946,0.00023701151,0.00059457356,0.00015663153,0.00045929142],"domain_scores_gemma":[0.99846786,0.0002896977,0.000025350855,0.0009369754,0.00009816365,0.0001819236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025910293,0.00020181386,0.00018192695,0.00021245386,0.00019275174,0.00020341546,0.00082550675,0.00006817145,0.000017511544],"category_scores_gemma":[0.00001838526,0.00020094996,0.000041302406,0.00026453706,0.000021446775,0.00049665425,0.000060933766,0.000229735,0.00009714188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012830913,0.0001480305,9.831209e-7,0.00029378332,0.000058002715,0.0000037518253,0.0006233214,0.72303885,0.0077558216,0.00009692434,0.00039859803,0.26756912],"study_design_scores_gemma":[0.00049598893,0.00009092091,0.000018839393,0.000055120792,0.000007833664,0.000021120566,0.00001239109,0.99337006,0.0031099853,0.000009696324,0.0025802653,0.00022776137],"about_ca_topic_score_codex":0.000011262733,"about_ca_topic_score_gemma":0.000008030062,"teacher_disagreement_score":0.67232764,"about_ca_system_score_codex":0.00006352431,"about_ca_system_score_gemma":0.00003841933,"threshold_uncertainty_score":0.81945014},"labels":[],"label_agreement":null},{"id":"W1998344252","doi":"10.1145/2597008.2602159","title":"The MoJo family: a story about clustering evaluation (invited talk)","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Cluster analysis; Computer science; Software; Cluster (spacecraft); Domain (mathematical analysis); Data mining; Data science; Machine learning; Programming language; Mathematics","score_opus":0.033363713175748204,"score_gpt":0.32044618986596457,"score_spread":0.28708247669021636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998344252","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":[0.008507472,0.00021195888,0.98356503,0.0023335577,0.000465488,0.00029878772,3.0482448e-7,0.00025883105,0.0043585706],"genre_scores_gemma":[0.85215515,0.00007021242,0.14147592,0.0017828444,0.00033186757,0.00023950901,0.0000033045421,0.000041234252,0.0038999578],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768674,0.00038681636,0.00018407161,0.00039626504,0.0009082271,0.00043789466],"domain_scores_gemma":[0.9981588,0.00046485523,0.00006359853,0.0009571536,0.00024752252,0.00010804359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025869978,0.00012981675,0.000108180124,0.0000882443,0.0005355022,0.00031293137,0.0012128332,0.00004854001,0.000008115169],"category_scores_gemma":[0.0004171851,0.00009177691,0.000046362937,0.00035968615,0.00008152298,0.00045067546,0.0007064118,0.00024460457,0.000088845074],"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":[0.0000052612017,0.00001232211,0.000008663087,0.000007278498,0.000010192014,0.0000016325588,0.00027392153,0.011664803,0.00324272,0.0014272494,0.0008625535,0.9824834],"study_design_scores_gemma":[0.00030988647,0.000054395496,0.001793812,0.000012362879,0.0000020940977,0.0000070157307,0.000060828308,0.9679996,0.00040606823,0.0016190262,0.027607908,0.00012700245],"about_ca_topic_score_codex":0.00004154183,"about_ca_topic_score_gemma":0.00003958702,"teacher_disagreement_score":0.9823564,"about_ca_system_score_codex":0.00016938747,"about_ca_system_score_gemma":0.000052859927,"threshold_uncertainty_score":0.41187042},"labels":[],"label_agreement":null},{"id":"W1999646319","doi":"10.1016/j.patrec.2006.01.015","title":"An objective approach to cluster validation","year":2006,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":122,"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; Covariance; Cluster (spacecraft); Data mining; Computer science; Measure (data warehouse); Separable space; Fuzzy clustering; Index (typography); Mathematics; Rand index; Artificial intelligence; Pattern recognition (psychology); Statistics","score_opus":0.02420805172161281,"score_gpt":0.27613756821425073,"score_spread":0.2519295164926379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999646319","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":[0.150254,0.0000021254966,0.8460864,0.0017505758,0.00018049062,0.00037076915,0.000012502955,0.00024785992,0.0010953053],"genre_scores_gemma":[0.8016335,6.7538207e-7,0.19185662,0.005679352,0.00039280707,0.00021126706,0.00014644458,0.00003007197,0.000049274775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807674,0.00018985182,0.00023195193,0.0006445961,0.00043964895,0.00041718828],"domain_scores_gemma":[0.9991221,0.00006407392,0.00006904483,0.0004852886,0.00012848253,0.00013102606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027704355,0.00017325369,0.00013271956,0.00028044826,0.0001390382,0.00030294867,0.0005811747,0.000051023995,0.0000147737255],"category_scores_gemma":[0.000018020097,0.00018239023,0.000050529743,0.00043317015,0.000030002006,0.0010457459,0.00014931412,0.00017494586,0.00046319625],"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":[0.00003062141,0.0005212883,0.0018288125,0.00006111953,0.00003070724,0.00002900765,0.0014783948,0.028489562,0.04441971,0.000060050617,0.0035784496,0.9194723],"study_design_scores_gemma":[0.0035697792,0.00061255833,0.051799964,0.00015259309,0.00003052678,0.0002531681,0.00026767197,0.7774859,0.15558842,0.005772802,0.0017992175,0.002667402],"about_ca_topic_score_codex":0.0001578647,"about_ca_topic_score_gemma":0.0000064340475,"teacher_disagreement_score":0.91680485,"about_ca_system_score_codex":0.00014258013,"about_ca_system_score_gemma":0.00001446373,"threshold_uncertainty_score":0.7437658},"labels":[],"label_agreement":null},{"id":"W1999677481","doi":"10.1007/s12065-013-0103-1","title":"On evolutionary subspace clustering with symbiosis","year":2014,"lang":"en","type":"article","venue":"Evolutionary Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":10,"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":"","keywords":"Cluster analysis; Computer science; Data mining; Benchmarking; Scalability; Subspace topology; Population; Artificial intelligence; Machine learning","score_opus":0.015414830467287739,"score_gpt":0.26708960754385996,"score_spread":0.2516747770765722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999677481","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":[0.0014562919,0.00017978257,0.9900294,0.0015806394,0.00033709372,0.0002348197,0.000003253233,0.00043830625,0.0057404446],"genre_scores_gemma":[0.73790586,0.000037546048,0.25982323,0.00039957717,0.00013013968,0.000069717054,0.000005367022,0.000029168787,0.0015993951],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970965,0.00016493637,0.00029000855,0.00085129304,0.00091487553,0.00068242085],"domain_scores_gemma":[0.9977239,0.00056598487,0.000099268,0.0011186177,0.00025317236,0.000239086],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031799148,0.000292327,0.00021656757,0.0002734284,0.00041655195,0.000090395384,0.0015137144,0.000092622766,0.00005699151],"category_scores_gemma":[0.00023153942,0.000262245,0.0000731015,0.0009070211,0.00022587847,0.001018366,0.00057128794,0.0004070798,0.0006898201],"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":[0.00023665045,0.00045613234,0.0012111,0.00010655671,0.00007940339,0.00010837878,0.0007359377,0.28642085,0.00061657757,0.56832844,0.0033207156,0.13837928],"study_design_scores_gemma":[0.0001453383,0.0007499204,0.003514596,0.00015089082,0.0000036639465,0.00021168834,0.000053222153,0.97260886,0.0010909592,0.016958382,0.0040603834,0.00045210126],"about_ca_topic_score_codex":0.000037203474,"about_ca_topic_score_gemma":0.0000066364178,"teacher_disagreement_score":0.73644954,"about_ca_system_score_codex":0.00036734264,"about_ca_system_score_gemma":0.00011851233,"threshold_uncertainty_score":0.99998295},"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":"W2010564375","doi":"10.1145/1389095.1389118","title":"Particle swarm clustering ensemble","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; CURE data clustering algorithm; Correlation clustering; Computer science; Consensus clustering; Data mining; Canopy clustering algorithm; Particle swarm optimization; Artificial intelligence; Robustness (evolution); Pattern recognition (psychology); Machine learning","score_opus":0.051617333080655387,"score_gpt":0.2997592064093752,"score_spread":0.24814187332871981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010564375","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":[0.046733227,0.000052798714,0.94389665,0.0005609011,0.00012730535,0.00007417877,1.3661486e-7,0.00038945346,0.008165362],"genre_scores_gemma":[0.78011024,0.000024556753,0.21378477,0.00019624167,0.00004429477,0.000012624084,1.6393187e-7,0.000008631797,0.0058184983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880785,0.000028297873,0.00013843298,0.00030099528,0.0003094372,0.00041496128],"domain_scores_gemma":[0.99917185,0.00006351769,0.00002026345,0.0005439422,0.000057815843,0.00014260563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012383997,0.000087959765,0.00009539526,0.000040889605,0.00019898379,0.000052996962,0.00065594673,0.000027101152,0.000025162844],"category_scores_gemma":[0.00003661744,0.00007992923,0.00003414003,0.00033847932,0.000048689813,0.00051729835,0.0006017744,0.00010672529,0.00042657583],"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":[0.000051431616,0.0005399925,0.0036913191,0.00007930497,0.000078240555,0.0021434042,0.0072913137,0.058771085,0.07116165,0.046624828,0.0046487763,0.80491865],"study_design_scores_gemma":[0.0003563158,0.00007894086,0.0011079956,0.000005566137,5.3027696e-7,0.00031204353,0.00002342489,0.9136127,0.079287976,0.0008717479,0.004149251,0.0001934956],"about_ca_topic_score_codex":0.000030107514,"about_ca_topic_score_gemma":0.000008975796,"teacher_disagreement_score":0.85484165,"about_ca_system_score_codex":0.00004536401,"about_ca_system_score_gemma":0.000040547984,"threshold_uncertainty_score":0.54829115},"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":"W2011191813","doi":"10.1007/s10115-009-0226-y","title":"Subspace and projected clustering: experimental evaluation and analysis","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":64,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Subspace topology; Computer science; Data mining; Range (aeronautics); Clustering high-dimensional data; Consensus clustering; Artificial intelligence; Correlation clustering; CURE data clustering algorithm; Engineering","score_opus":0.0260607623732046,"score_gpt":0.33560897402197565,"score_spread":0.30954821164877105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011191813","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":[0.1953805,0.0056063333,0.7869529,0.00021878233,0.00023814755,0.0011398525,0.00000442101,0.0002142725,0.010244761],"genre_scores_gemma":[0.9974134,0.000052033334,0.002330999,0.000023246339,0.000026219048,0.000035017954,0.000010712169,0.0000020130087,0.00010633305],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991026,0.00007900471,0.0002449848,0.00016515401,0.00025407414,0.00015417022],"domain_scores_gemma":[0.99937695,0.00003089116,0.0000859172,0.0001892623,0.00022382653,0.00009315759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005176085,0.00010210883,0.0001579597,0.0003600104,0.00014965238,0.00044407163,0.000110966765,0.0000484272,0.0000012533822],"category_scores_gemma":[0.000033573888,0.00009121774,0.000016118545,0.00058724673,0.000027439468,0.0029540102,0.00013033015,0.00006182487,0.000007393433],"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":[0.0000589572,0.00012586568,0.0026834046,0.00038344643,0.0002763455,0.000002794536,0.07744251,0.0031610806,0.0023356008,0.013434878,0.00042923682,0.8996659],"study_design_scores_gemma":[0.00045949343,0.00011097882,0.0113820685,0.000019901614,0.000015320606,0.000027186436,0.00060252164,0.9844515,0.0002112004,0.000015009641,0.0025908903,0.00011395427],"about_ca_topic_score_codex":0.000013809658,"about_ca_topic_score_gemma":0.000003917117,"teacher_disagreement_score":0.9812904,"about_ca_system_score_codex":0.000057293968,"about_ca_system_score_gemma":0.000031569543,"threshold_uncertainty_score":0.4282193},"labels":[],"label_agreement":null},{"id":"W2012187238","doi":"10.1109/isspa.2012.6310493","title":"Improving X-means clustering with MNDL","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Cluster analysis; Bayesian information criterion; Determining the number of clusters in a data set; Computer science; Correlation clustering; Single-linkage clustering; Set (abstract data type); Cluster (spacecraft); Data mining; CURE data clustering algorithm; Mathematics; Algorithm; Artificial intelligence","score_opus":0.019568434327145962,"score_gpt":0.27481909939934496,"score_spread":0.255250665072199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012187238","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":[0.0027338697,0.000050350875,0.9885185,0.000206072,0.0001670246,0.00010490094,2.5282858e-7,0.00033896533,0.007880074],"genre_scores_gemma":[0.39115843,0.0000018366078,0.6068986,0.00011346385,0.00011519347,0.000014677616,2.7316278e-7,0.0000137238585,0.001683808],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986316,0.000026092006,0.000111096735,0.00024873728,0.0003337395,0.0006487304],"domain_scores_gemma":[0.9991004,0.0000585265,0.00003364211,0.000546351,0.000053802632,0.00020728583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025722448,0.00011641118,0.0000986328,0.00008225173,0.000120841054,0.00012486964,0.00064948376,0.000030297355,0.000023660488],"category_scores_gemma":[0.00002465804,0.00008719511,0.000021867385,0.0003090771,0.000034611574,0.0013722674,0.0006379445,0.00015251305,0.000108695356],"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":[0.000020952319,0.00013788926,0.0035634313,0.000084484636,0.000034741563,0.0000389052,0.0020024634,0.0048472225,0.008039496,0.012380421,0.00016345043,0.9686865],"study_design_scores_gemma":[0.00045443425,0.00014435455,0.0020516762,0.000021544995,0.0000025284814,0.00017258263,0.00012146544,0.98629403,0.0065741176,0.00009659856,0.0037031062,0.0003635539],"about_ca_topic_score_codex":0.000058851023,"about_ca_topic_score_gemma":0.000017339218,"teacher_disagreement_score":0.9814468,"about_ca_system_score_codex":0.00007195216,"about_ca_system_score_gemma":0.000032227814,"threshold_uncertainty_score":0.35557136},"labels":[],"label_agreement":null},{"id":"W2012862892","doi":"10.1007/s10462-004-2901-4","title":"Statistical, Evolutionary, and Neurocomputing Clustering Techniques: Cluster-Based vs Object-Based Approaches","year":2005,"lang":"en","type":"article","venue":"Artificial Intelligence Review","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"Natural Sciences and Engineering Research Council of Canada; University of Regina","keywords":"Cluster analysis; Computer science; Artificial neural network; Set (abstract data type); Self-organizing map; Artificial intelligence; Hierarchical clustering; Data mining; Genetic algorithm; Object (grammar); Machine learning; Correlation clustering; Cluster (spacecraft); Pattern recognition (psychology)","score_opus":0.10217262922586404,"score_gpt":0.35377746189472176,"score_spread":0.2516048326688577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012862892","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":[0.00006351367,0.0072027217,0.9853158,0.005748209,0.00008634227,0.0009144914,0.000005567759,0.0004060637,0.00025726375],"genre_scores_gemma":[0.11854297,0.0018886037,0.8764797,0.0026436131,0.0001943462,0.00018169191,0.000009824643,0.000039937793,0.000019298863],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99670565,0.00032745034,0.0008260347,0.0008966991,0.00056129746,0.0006828441],"domain_scores_gemma":[0.9978989,0.0007173406,0.00018646881,0.0007927218,0.00015487145,0.00024974375],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011211464,0.00032872954,0.00046368167,0.00019098682,0.00033976356,0.00023533351,0.000984009,0.00008381776,0.000032309465],"category_scores_gemma":[0.00045610458,0.00031649723,0.00009761372,0.0007750601,0.0002503991,0.00045456112,0.00052938855,0.0004102827,0.000118510434],"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":[0.000011482731,0.00009703683,0.0000089564965,0.0009282416,0.000005348006,0.000012678804,0.000040016002,0.009671544,0.000080430786,0.004746498,0.00012299129,0.9842748],"study_design_scores_gemma":[0.000032669966,0.00018150228,0.000020270983,0.0013669058,0.000011975074,0.000034294488,0.000011008033,0.98275924,0.0043809838,0.0013108453,0.0095411725,0.000349139],"about_ca_topic_score_codex":0.000022800554,"about_ca_topic_score_gemma":0.000018878049,"teacher_disagreement_score":0.98392564,"about_ca_system_score_codex":0.00016191,"about_ca_system_score_gemma":0.00019826803,"threshold_uncertainty_score":0.9999287},"labels":[],"label_agreement":null},{"id":"W2013358657","doi":"10.2333/bhmk.41.115","title":"A General Formulation of Cluster Analysis with Dimension Reduction and Subspace Separation","year":2014,"lang":"en","type":"article","venue":"Behaviormetrika","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Japan Society for the Promotion of Science","keywords":"Subspace topology; Dimensionality reduction; Dimension (graph theory); Cluster analysis; Reduction (mathematics); Mathematics; Cluster (spacecraft); Factorial; Separation (statistics); Principal component analysis; Extension (predicate logic); Computer science; Pattern recognition (psychology); Algorithm; Artificial intelligence; Data mining; Statistics; Combinatorics","score_opus":0.019064604396722078,"score_gpt":0.32239569922186634,"score_spread":0.30333109482514425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013358657","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":[0.5038756,0.000012534613,0.49588436,0.000053916054,0.000023180488,0.00009254446,4.7035243e-7,0.000026617392,0.000030764022],"genre_scores_gemma":[0.86743957,0.000005817133,0.13229786,0.0000068342442,0.00002185865,0.000011011619,0.000008487989,0.000006152651,0.00020240083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890506,0.00006770451,0.00017826022,0.00030086748,0.00037849764,0.00016958742],"domain_scores_gemma":[0.99925077,0.000040552168,0.00011864553,0.0003670918,0.00015673845,0.000066187524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031829436,0.000096322576,0.00017112301,0.00058150664,0.00008358742,0.000056794528,0.00014179516,0.000051581064,0.0000025005882],"category_scores_gemma":[0.000023120105,0.00008069162,0.0000385815,0.0017348822,0.00003281299,0.00059173454,0.00010792195,0.00007623866,0.0000016295967],"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":[0.00032660438,0.0004518601,0.10945587,0.00009719726,0.00029256384,0.000006924848,0.0031713159,0.1074362,0.1726625,0.009801856,0.00011432423,0.59618276],"study_design_scores_gemma":[0.0007459338,0.00048251287,0.17257525,0.000012437164,0.00013464021,0.000027644925,0.00002079002,0.79598874,0.029569061,0.00013774552,0.000113942755,0.00019129286],"about_ca_topic_score_codex":0.00007679633,"about_ca_topic_score_gemma":0.000023767523,"teacher_disagreement_score":0.68855256,"about_ca_system_score_codex":0.00005090149,"about_ca_system_score_gemma":0.000017025553,"threshold_uncertainty_score":0.3290509},"labels":[],"label_agreement":null},{"id":"W2013578504","doi":"10.1109/icassp.2014.6855216","title":"Efficient unimodality test in clustering by signature testing","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Unimodality; Signature (topology); Cluster analysis; Hierarchical clustering; Statistic; Statistical hypothesis testing; Computer science; Test statistic; Algorithm; Mathematics; Pattern recognition (psychology); Data mining; Statistics; Artificial intelligence","score_opus":0.01849794104842726,"score_gpt":0.28076863114923545,"score_spread":0.26227069010080817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013578504","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":[0.015476357,0.00003915216,0.9754234,0.0004512455,0.00009392689,0.00014047977,0.0000013310643,0.000275273,0.008098869],"genre_scores_gemma":[0.7302256,6.5035147e-7,0.2691755,0.00016546971,0.000031873347,0.000011460124,7.1812957e-7,0.000010793222,0.00037791597],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982854,0.000090575486,0.00022767633,0.000504526,0.00038125948,0.0005105251],"domain_scores_gemma":[0.99824667,0.0009188619,0.000046200777,0.0005749418,0.00008810711,0.00012522333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007284861,0.00014368795,0.00015328157,0.000112222486,0.000098503755,0.00013137325,0.00094542804,0.000070827686,0.0000060225298],"category_scores_gemma":[0.0010314714,0.0001306868,0.000022417571,0.00086955755,0.000042852924,0.00013487757,0.0008386799,0.0003506087,0.000031370582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074849304,0.00043262495,0.0068352013,0.00011380934,0.0000064882233,0.000042714964,0.00056244276,0.47088954,0.053557668,0.0043229153,0.00050935266,0.46271977],"study_design_scores_gemma":[0.00026859494,0.00006713805,0.0015944102,0.000030739822,3.1414152e-7,0.000008324292,0.000011031536,0.9950157,0.0016929574,0.0006208126,0.00052321976,0.00016675945],"about_ca_topic_score_codex":0.00011805167,"about_ca_topic_score_gemma":0.00002706767,"teacher_disagreement_score":0.7147493,"about_ca_system_score_codex":0.00012512655,"about_ca_system_score_gemma":0.000033778208,"threshold_uncertainty_score":0.53292537},"labels":[],"label_agreement":null},{"id":"W2020287868","doi":"10.1016/j.eswa.2007.11.045","title":"A genetic fuzzy <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si218.gif\" overflow=\"scroll\"><mml:mrow><mml:mi>k</mml:mi></mml:mrow></mml:math>-Modes algorithm for clustering categorical data","year":2007,"lang":"lv","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Algorithm; Fuzzy logic; Crossover; Categorical variable; Computer science; Genetic algorithm; Operator (biology); Cluster analysis; Mathematics; Artificial intelligence; Machine learning","score_opus":0.034403805891581714,"score_gpt":0.29495871503319476,"score_spread":0.26055490914161306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020287868","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":[0.024560709,0.002504152,0.9617415,0.0003319232,0.00084179884,0.00034012488,0.00019651865,0.0002826203,0.00920066],"genre_scores_gemma":[0.802465,0.00038160078,0.18865213,0.0003093408,0.0023672467,0.0048114643,0.00033333065,0.00031831552,0.0003615327],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993938,0.0001293564,0.0011125254,0.0017390306,0.001492098,0.0015889478],"domain_scores_gemma":[0.9939603,0.0008886759,0.0007240746,0.0035045478,0.00022532458,0.0006970828],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013126812,0.0005209107,0.0003134588,0.00026703157,0.0012605328,0.0010349238,0.0029822255,0.00064329174,0.00025642416],"category_scores_gemma":[0.0001928778,0.00071599474,0.00028876105,0.0009701645,0.00052332197,0.00094588724,0.0023200517,0.0006552302,0.00067312],"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":[0.0002305374,0.0003902637,0.0000053296717,0.0009708445,0.00059146184,0.00034138106,0.0028798545,0.009681406,0.0019656848,0.90687174,0.010265258,0.06580625],"study_design_scores_gemma":[0.00090303534,0.00048103713,0.00003036001,0.00035210932,0.000101407095,0.001061666,0.0011899441,0.96845216,0.012577982,0.00008170414,0.014077214,0.0006913575],"about_ca_topic_score_codex":0.0015156802,"about_ca_topic_score_gemma":0.0002721815,"teacher_disagreement_score":0.95877075,"about_ca_system_score_codex":0.00006366064,"about_ca_system_score_gemma":0.0008229521,"threshold_uncertainty_score":0.9995291},"labels":[],"label_agreement":null},{"id":"W2020492796","doi":"10.2333/bhmk.28.153","title":"Space Distortion and Monotone Admissibility in Agglomerative Clustering","year":2001,"lang":"en","type":"article","venue":"Behaviormetrika","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":"Saint Paul University","funders":"","keywords":"Cluster analysis; Distortion (music); Monotone polygon; Hierarchical clustering; Mathematics; Monotonic function; Space (punctuation); Algorithm; Computer science; Statistics","score_opus":0.03308515863390581,"score_gpt":0.33067564014191975,"score_spread":0.2975904815080139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020492796","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":[0.56148547,0.00018564306,0.43758285,0.00016982316,0.00008194112,0.00021345571,0.0000012531201,0.00007811002,0.00020146751],"genre_scores_gemma":[0.9636517,0.00011085415,0.035661142,0.00001819423,0.00002327135,0.000045447236,0.0000016519573,0.000010459565,0.000477255],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984685,0.00007414898,0.00024078983,0.0005165751,0.00031993646,0.00038002038],"domain_scores_gemma":[0.9991643,0.00008028701,0.00005919597,0.00046738412,0.000055391403,0.0001734847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038835267,0.0001428424,0.00018187478,0.00035183385,0.000098862685,0.00011305644,0.0003498122,0.00006697913,0.000013344318],"category_scores_gemma":[0.00014559735,0.00014504943,0.000029172328,0.001202693,0.00006221099,0.00072730624,0.00045542384,0.0002386283,0.000010736835],"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":[0.00006378789,0.00036891646,0.15822095,0.00003353823,0.0000062533777,0.00034589897,0.0017989909,0.000614512,0.007152333,0.00035565026,0.00002038991,0.8310188],"study_design_scores_gemma":[0.0013983785,0.00031978067,0.8830725,0.000069195994,0.000005784706,0.00014670264,0.00016258763,0.10606563,0.0062950063,0.00084146485,0.0011055998,0.0005173931],"about_ca_topic_score_codex":0.00022153842,"about_ca_topic_score_gemma":0.00017854794,"teacher_disagreement_score":0.8305014,"about_ca_system_score_codex":0.0002892133,"about_ca_system_score_gemma":0.00004501163,"threshold_uncertainty_score":0.5914944},"labels":[],"label_agreement":null},{"id":"W2022006917","doi":"10.1145/1645953.1646069","title":"Clustering web queries","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Weighting; Classifier (UML); Set (abstract data type); Population; Search engine; Information retrieval; Metric (unit); Artificial intelligence","score_opus":0.018877849317098013,"score_gpt":0.3006797422883326,"score_spread":0.2818018929712346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022006917","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":[0.0012227672,0.000037954684,0.96552813,0.0026785466,0.00011269999,0.000060107363,1.9767134e-7,0.0004687513,0.02989085],"genre_scores_gemma":[0.45815387,0.00001548795,0.53675836,0.0006357689,0.000057728073,0.000004038936,2.5233015e-7,0.0000047132685,0.0043697823],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908245,0.000019242354,0.00010861843,0.0002493906,0.00023620456,0.00030409606],"domain_scores_gemma":[0.9993656,0.000030979474,0.000017003395,0.00045543766,0.000043862106,0.00008707704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000116768555,0.00008204108,0.00008353345,0.000075667434,0.0000890374,0.00014875407,0.0007075295,0.000026671943,0.000026763264],"category_scores_gemma":[0.0000297955,0.0000721082,0.00002717478,0.00027679687,0.000022050242,0.00057636894,0.00026923954,0.000100084806,0.00011574314],"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":[0.000005882548,0.000041240703,0.000035270998,0.000007568364,0.000005200134,0.000064996224,0.00031724936,0.0020151203,0.010330068,0.03673571,0.0009473309,0.94949436],"study_design_scores_gemma":[0.000253553,0.00016538842,0.0011867367,0.000011729038,4.8751866e-7,0.000057417492,0.000026471527,0.9737675,0.004848312,0.006192479,0.013272017,0.00021788338],"about_ca_topic_score_codex":0.000004603606,"about_ca_topic_score_gemma":0.0000062183767,"teacher_disagreement_score":0.9717524,"about_ca_system_score_codex":0.000037492486,"about_ca_system_score_gemma":0.000036173024,"threshold_uncertainty_score":0.29404873},"labels":[],"label_agreement":null},{"id":"W2022201359","doi":"10.1016/j.eswa.2013.07.002","title":"Cluster center initialization algorithm for K-modes clustering","year":2013,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":120,"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 Waterloo","funders":"","keywords":"Initialization; Computer science; Cluster analysis; Cluster (spacecraft); Center (category theory); Algorithm; Data mining; Artificial intelligence; Pattern recognition (psychology); Computer network","score_opus":0.02231767915479643,"score_gpt":0.304274552149248,"score_spread":0.28195687299445155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022201359","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":[0.00002765104,0.00018644518,0.9942246,0.00063971855,0.00014739079,0.0034546817,0.000015653844,0.00036561492,0.000938253],"genre_scores_gemma":[0.055838395,0.000025241527,0.9125229,0.00038236735,0.00057077914,0.029246042,0.00006342767,0.000068125206,0.0012827362],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817586,0.000057364097,0.00034662124,0.0005887427,0.0003551376,0.0004762739],"domain_scores_gemma":[0.9982127,0.00015169305,0.00012749142,0.00087524473,0.00045382945,0.00017903083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015534495,0.00021249287,0.00021452115,0.00015492117,0.00035434487,0.0004921066,0.00081345235,0.00008135871,0.0000082079605],"category_scores_gemma":[0.000011913165,0.00017763968,0.000047197256,0.00041264706,0.000060784434,0.0009471851,0.00024269056,0.000100144025,0.00013391313],"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":[0.000021597532,0.00050677004,0.00011871157,0.00033206647,0.00017550532,0.0000042436277,0.003030563,0.02020861,0.004388544,0.024283133,0.011907866,0.9350224],"study_design_scores_gemma":[0.00068480306,0.00007032254,0.000025749254,0.000052987085,0.0000018474736,0.000055414774,0.0002058217,0.94835085,0.00039318978,0.00027829246,0.04962541,0.00025528405],"about_ca_topic_score_codex":0.00015200683,"about_ca_topic_score_gemma":0.0000078082285,"teacher_disagreement_score":0.9347671,"about_ca_system_score_codex":0.00013438039,"about_ca_system_score_gemma":0.000055808472,"threshold_uncertainty_score":0.7243936},"labels":[],"label_agreement":null},{"id":"W2023420371","doi":"10.5539/mas.v3n2p75","title":"Genetic Algorithm for Document Clustering with Simultaneous and Ranked Mutation","year":2009,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Mutation; Mutation rate; Computer science; Genetic algorithm; Population; Similarity (geometry); Local optimum; Operator (biology); Chromosome; Algorithm; Data mining; Correlation clustering; Document clustering; Artificial intelligence; Machine learning; Genetics; Biology","score_opus":0.010406362118062418,"score_gpt":0.2725208109599084,"score_spread":0.262114448841846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023420371","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":[0.005962344,0.00004635018,0.9926939,0.00020101607,0.000044015236,0.00066957466,0.000001249596,0.00014904249,0.0002325155],"genre_scores_gemma":[0.5061201,0.0000033535512,0.49367097,0.00010270562,0.000018609147,0.000041207815,3.229445e-7,0.000005672576,0.00003708563],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99788606,0.000010394803,0.00017866788,0.000695156,0.00064208254,0.0005876473],"domain_scores_gemma":[0.99901295,0.00012564959,0.00006644056,0.00046426797,0.0001392376,0.00019148256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038096786,0.00016825771,0.00015350732,0.00016406753,0.0004621596,0.00044507015,0.00086706365,0.000032424858,6.947802e-7],"category_scores_gemma":[0.000025207215,0.00014512625,0.000015628704,0.0005458069,0.0002567104,0.00045296687,0.00023325087,0.00010253986,0.0000036747517],"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":[0.000015073352,0.00001585674,5.3226825e-7,0.0000066614407,0.0000025855447,0.000015560918,0.00085228763,0.053980403,0.021992914,0.00038829466,6.751121e-7,0.92272913],"study_design_scores_gemma":[0.0007206337,0.00025625477,0.00014815577,0.000010433516,0.0000026768087,0.000078263845,0.000034597717,0.9826735,0.003991817,0.011848395,0.000031052754,0.00020417488],"about_ca_topic_score_codex":0.0000046661057,"about_ca_topic_score_gemma":0.0000026513753,"teacher_disagreement_score":0.9286931,"about_ca_system_score_codex":0.0001276816,"about_ca_system_score_gemma":0.000113364564,"threshold_uncertainty_score":0.59180766},"labels":[],"label_agreement":null},{"id":"W2026643052","doi":"10.1007/s11047-009-9173-5","title":"Flocking based approach for data clustering","year":2009,"lang":"en","type":"article","venue":"Natural Computing","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":27,"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 Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Particle swarm optimization; Fuzzy clustering; Correlation clustering; CURE data clustering algorithm; Data mining; Canopy clustering algorithm; Artificial intelligence; Consensus clustering; Machine learning","score_opus":0.0709870533393512,"score_gpt":0.3606660983964147,"score_spread":0.28967904505706354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026643052","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":[0.00071461016,0.00025706974,0.9970004,0.00052363623,0.00035751256,0.00033069582,0.0000026907676,0.000440903,0.0003724908],"genre_scores_gemma":[0.4716772,3.7453853e-7,0.5277918,0.00029087707,0.00017724876,0.0000014484681,0.000026642301,0.0000079852125,0.000026410658],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780595,0.000055492583,0.0002652548,0.00081741373,0.00041475185,0.00064114854],"domain_scores_gemma":[0.99815255,0.00029288378,0.00009496393,0.0012261564,0.0001372801,0.00009613753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007515574,0.00018643896,0.00020835093,0.0001399757,0.0003859438,0.000331029,0.0030126697,0.000065218905,5.4682647e-7],"category_scores_gemma":[0.00026141573,0.00017798136,0.000058463123,0.00048111257,0.000022528517,0.00066060503,0.0012426499,0.00040504494,0.0000025300367],"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":[0.00001405277,0.00003386739,0.000015278209,0.000045613648,0.000008041865,0.000007640487,0.00009770853,0.104177125,0.0013784551,0.0005144924,0.00019706422,0.89351064],"study_design_scores_gemma":[0.00049227226,0.000060793765,0.0001854121,0.000036879523,0.00000220189,0.000020562265,0.000009965728,0.9976449,0.0005033428,0.00021473732,0.0006046546,0.00022428729],"about_ca_topic_score_codex":0.000005524078,"about_ca_topic_score_gemma":7.802248e-7,"teacher_disagreement_score":0.8934678,"about_ca_system_score_codex":0.000094719886,"about_ca_system_score_gemma":0.000060005666,"threshold_uncertainty_score":0.7257869},"labels":[],"label_agreement":null},{"id":"W2028768445","doi":"10.1109/ifsa-nafips.2013.6608463","title":"A granular recursive fuzzy meta-clustering algorithm for social networks","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Cluster analysis; Fuzzy clustering; Data mining; Computer science; Fuzzy logic; FLAME clustering; Artificial intelligence; Canopy clustering algorithm","score_opus":0.049427383107694296,"score_gpt":0.3102288841149434,"score_spread":0.26080150100724914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028768445","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":[0.00003532472,0.00018771618,0.99519455,0.001725768,0.00035305048,0.0009009394,0.000004053502,0.00032258505,0.0012759921],"genre_scores_gemma":[0.004279439,0.000015684102,0.9909006,0.0005060301,0.00041197188,0.0010012259,0.000006156941,0.0000368968,0.0028420014],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977591,0.00008142481,0.00029871077,0.0006238378,0.00039953168,0.0008374169],"domain_scores_gemma":[0.99864393,0.00023043295,0.00008674244,0.00049920945,0.00035891507,0.00018074815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003642439,0.00025053832,0.00039626943,0.00012559061,0.0003964508,0.0003923471,0.0012132286,0.00011967848,0.00008360178],"category_scores_gemma":[0.00004134432,0.0002106065,0.0002876526,0.00043750444,0.00007564029,0.000983408,0.0007307503,0.00023809276,0.0000854335],"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":[0.0000033890797,0.000041632004,0.0000014636286,0.000016536047,0.00021148783,0.000009350934,0.0003302996,0.0028446764,0.000084050356,0.004511169,0.0038434204,0.9881025],"study_design_scores_gemma":[0.0004542436,0.00010254789,0.00005518347,0.000004090629,0.000039176197,0.000016447835,0.000053001266,0.97920763,0.00023926672,0.016346393,0.0031955729,0.00028646388],"about_ca_topic_score_codex":0.00010383987,"about_ca_topic_score_gemma":0.000009773805,"teacher_disagreement_score":0.98781604,"about_ca_system_score_codex":0.000093425915,"about_ca_system_score_gemma":0.00003921194,"threshold_uncertainty_score":0.85882837},"labels":[],"label_agreement":null},{"id":"W2029272463","doi":"10.1016/j.ejor.2011.01.016","title":"Globally optimal clusterwise regression by mixed logical-quadratic programming","year":2011,"lang":"en","type":"article","venue":"European Journal of Operational Research","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":35,"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; Group for Research in Decision Analysis","funders":"","keywords":"Computer science; Regression analysis; Integer programming; Quadratic equation; Mathematical optimization; Operations research; Mathematics; Statistics","score_opus":0.1333836776367603,"score_gpt":0.376373881362056,"score_spread":0.24299020372529573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029272463","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":[0.034452394,0.00059684087,0.9537784,0.0017913325,0.0003097617,0.0003270373,0.0000040678133,0.00005066948,0.008689516],"genre_scores_gemma":[0.52671343,0.00007667574,0.4715045,0.000095382915,0.00025205265,0.00000621497,0.00000323202,0.000030323203,0.0013182007],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99321055,0.0023374802,0.0007249838,0.00040260656,0.0026467207,0.0006776629],"domain_scores_gemma":[0.9967219,0.00029472917,0.00019476554,0.00046733645,0.0018483822,0.00047287135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008105674,0.00018572541,0.00023654726,0.00032986084,0.00047532155,0.0006268449,0.0027521914,0.000040862236,0.000109945126],"category_scores_gemma":[0.0011548372,0.00013480322,0.000107508466,0.00073438574,0.0002621706,0.0012534013,0.0011927236,0.0010312625,0.00020914034],"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":[0.001128827,0.0025354985,0.00055017567,0.00010692733,0.0002547248,0.010214275,0.006655483,0.0047403355,0.042270638,0.02800859,0.048985284,0.8545492],"study_design_scores_gemma":[0.019673904,0.040625278,0.034162056,0.0034547248,0.00006058218,0.01237768,0.0048746127,0.3937828,0.0634524,0.0069997297,0.41616297,0.004373269],"about_ca_topic_score_codex":0.000004419346,"about_ca_topic_score_gemma":6.236648e-7,"teacher_disagreement_score":0.850176,"about_ca_system_score_codex":0.00018555323,"about_ca_system_score_gemma":0.00037246698,"threshold_uncertainty_score":0.604468},"labels":[],"label_agreement":null},{"id":"W2029698681","doi":"10.1145/2395116.2395117","title":"The effectiveness of lloyd-type methods for the k-means problem","year":2012,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":185,"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 Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Office of Naval Research; Israel Science Foundation; United States-Israel Binational Science Foundation; National Science Foundation","keywords":"Computer science; Cluster analysis; Heuristic; Probabilistic logic; Popularity; Process (computing); Algorithm; Type (biology); Quality (philosophy); Data mining; Artificial intelligence; Mathematical optimization; Mathematics","score_opus":0.05066538846456285,"score_gpt":0.4219683914484055,"score_spread":0.3713030029838426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029698681","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":[0.002811858,0.0016304307,0.9904679,0.0033287122,0.00133549,0.00033299637,4.655925e-7,0.00000654514,0.0000856203],"genre_scores_gemma":[0.120699234,0.0001136707,0.87848526,0.000058487654,0.00032209893,0.000016527152,2.7152486e-8,0.000015488118,0.0002891894],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981109,0.0009366471,0.0002548131,0.000073104704,0.0003402152,0.00028430554],"domain_scores_gemma":[0.9890963,0.008793597,0.000314201,0.0013411945,0.00039829538,0.000056448367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010052808,0.00007751206,0.00015593415,0.000032870375,0.00028964516,0.0000621501,0.0053722076,0.000029423343,9.3540393e-7],"category_scores_gemma":[0.004780509,0.000029692992,0.00016655042,0.00034549957,0.00010633255,0.0003077902,0.0014105159,0.0002876012,0.0000013554102],"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":[0.00070035725,0.0002141064,0.0018188172,0.00022529894,0.00061953696,0.0000018500242,0.0022174628,0.016072106,0.06833603,0.017498428,0.0016321943,0.8906638],"study_design_scores_gemma":[0.0027390881,0.001598482,0.06103181,0.0006116288,0.00019236859,0.00080686196,0.00041847536,0.113977276,0.2942013,0.37314925,0.15080237,0.00047105955],"about_ca_topic_score_codex":0.0000038075905,"about_ca_topic_score_gemma":5.9375657e-7,"teacher_disagreement_score":0.89019275,"about_ca_system_score_codex":0.00006615232,"about_ca_system_score_gemma":0.00009080346,"threshold_uncertainty_score":0.99829876},"labels":[],"label_agreement":null},{"id":"W2032084149","doi":"10.1016/j.ins.2013.11.004","title":"Relative entropy fuzzy c-means clustering","year":2013,"lang":"en","type":"article","venue":"Information Sciences","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":113,"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 Toronto","funders":"","keywords":"Cluster analysis; Fuzzy clustering; Pattern recognition (psychology); Artificial intelligence; Fuzzy logic; Data mining; Entropy (arrow of time); Computer science; FLAME clustering; Mathematics; Machine learning; CURE data clustering algorithm","score_opus":0.02682990070830507,"score_gpt":0.30065639858746507,"score_spread":0.27382649787916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032084149","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":[0.00329873,0.000012271799,0.9607177,0.001863375,0.00027653298,0.0002191789,9.509018e-7,0.00018711113,0.033424195],"genre_scores_gemma":[0.5765584,0.000015668582,0.42198628,0.0007807184,0.000053618918,0.000080699705,0.0000019993731,0.000003796888,0.0005188165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984282,0.000038612867,0.00029179096,0.00017374825,0.0006980307,0.00036960642],"domain_scores_gemma":[0.99916506,0.00012501953,0.00012165505,0.0002775748,0.00020328326,0.000107379696],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004729774,0.00009658231,0.000088252906,0.0002587706,0.00039392416,0.00092788134,0.0011891528,0.000034509103,0.000057935104],"category_scores_gemma":[0.00016927287,0.00007789387,0.00003157453,0.00089095935,0.00019393914,0.017643422,0.00047389086,0.00012799403,0.0019892405],"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":[0.000003077483,0.000024475454,0.00052277325,0.000033024317,0.000014432843,0.0000024176006,0.011845933,0.049840324,0.0007568835,0.12940079,0.001912986,0.8056429],"study_design_scores_gemma":[0.00015315622,0.000076133234,0.0020281193,0.000014509357,4.4528002e-7,0.000016064694,0.000420535,0.9758576,0.0004115299,0.014256454,0.006621932,0.00014350878],"about_ca_topic_score_codex":0.000099121,"about_ca_topic_score_gemma":0.0000033738709,"teacher_disagreement_score":0.9260173,"about_ca_system_score_codex":0.00006863215,"about_ca_system_score_gemma":0.00008250203,"threshold_uncertainty_score":0.9987878},"labels":[],"label_agreement":null},{"id":"W2032920196","doi":"10.1016/j.eswa.2011.09.154","title":"Evolutionary feature selection via structure retention","year":2011,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":17,"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":"Granular computing; Curse of dimensionality; Cluster analysis; Computer science; Particle swarm optimization; Dimensionality reduction; Granulation; Fuzzy set; Artificial intelligence; Mathematics; Pattern recognition (psychology); Feature selection; Feature (linguistics); Fuzzy logic; Reduction (mathematics); Algorithm; Data mining; Rough set","score_opus":0.021056378203984503,"score_gpt":0.2632772240430977,"score_spread":0.2422208458391132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032920196","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":[0.00021486904,0.0005544404,0.99660844,0.00017731133,0.00013556342,0.0008250367,0.0000060968264,0.00040475707,0.0010734713],"genre_scores_gemma":[0.570019,0.000014918031,0.4262373,0.00004633217,0.00030708718,0.0015965726,0.000025251858,0.000028869652,0.0017246729],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986114,0.00006265098,0.00016488868,0.00050121965,0.00037240682,0.0002874429],"domain_scores_gemma":[0.9988154,0.000021726893,0.000106128115,0.00066584523,0.00026885356,0.00012201156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007889477,0.00015304727,0.00012943518,0.0001331347,0.00035526726,0.00006965654,0.000588243,0.00010607426,0.000014388545],"category_scores_gemma":[0.000005135522,0.00012619609,0.000030303896,0.0007931312,0.000052265048,0.0005165885,0.000104072125,0.00020951283,0.000051097355],"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":[0.0003457223,0.0014411807,0.006887394,0.0007010891,0.00076183723,0.000078717596,0.019344559,0.011292106,0.2072006,0.4326561,0.049433757,0.26985693],"study_design_scores_gemma":[0.0015424785,0.0007202235,0.01807464,0.00021156725,0.000023301955,0.0025673807,0.0007163344,0.73854333,0.011447352,0.009383385,0.2150917,0.0016783166],"about_ca_topic_score_codex":0.000153796,"about_ca_topic_score_gemma":0.000012666346,"teacher_disagreement_score":0.72725123,"about_ca_system_score_codex":0.00017409826,"about_ca_system_score_gemma":0.00006682729,"threshold_uncertainty_score":0.51461273},"labels":[],"label_agreement":null},{"id":"W2034996776","doi":"10.2333/bhmk.40.1","title":"Hierarchically Structured Fuzzy c-Means Clustering","year":2013,"lang":"en","type":"article","venue":"Behaviormetrika","topic":"Advanced Clustering Algorithms Research","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":"McGill University","funders":"","keywords":"Centroid; Fuzzy logic; Data mining; Cluster analysis; Fuzzy clustering; Cluster (spacecraft); Extension (predicate logic); Hierarchical clustering; Extant taxon; Single-linkage clustering; Pattern recognition (psychology); Mathematics; Hierarchy; Computer science; Artificial intelligence; FLAME clustering; CURE data clustering algorithm","score_opus":0.021141757707111235,"score_gpt":0.28846440525270595,"score_spread":0.2673226475455947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034996776","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":[0.119167894,0.000111244495,0.87581176,0.0005944158,0.0005733813,0.0006281969,0.000004142042,0.0005957746,0.0025131982],"genre_scores_gemma":[0.5659558,0.000015695414,0.43211883,0.000132783,0.000117506,0.0001365217,0.0000032461778,0.00003637484,0.0014832143],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973734,0.00007686996,0.00036826762,0.00063041993,0.00075413,0.000796937],"domain_scores_gemma":[0.9981836,0.00012251643,0.0000827798,0.0010800346,0.00017868576,0.0003523829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022536604,0.0002441793,0.0002549767,0.0004995453,0.00021425531,0.00047155394,0.001825199,0.00012302342,0.00014807231],"category_scores_gemma":[0.00012284712,0.00022591223,0.00010626772,0.0012875486,0.00009203155,0.0010628775,0.0011090938,0.000476985,0.00037839374],"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":[0.0000047703015,0.0000860136,0.0025938624,0.000020858015,0.000012994846,0.000057203233,0.00033699186,0.0005486113,0.017862504,0.0012627899,0.00046444207,0.97674894],"study_design_scores_gemma":[0.0044129514,0.001321425,0.66258204,0.00015957536,0.00004172024,0.0007247575,0.0002444856,0.25867358,0.021771107,0.029362533,0.017426519,0.003279336],"about_ca_topic_score_codex":0.00014965307,"about_ca_topic_score_gemma":0.000016981916,"teacher_disagreement_score":0.9734696,"about_ca_system_score_codex":0.0001536553,"about_ca_system_score_gemma":0.00008213628,"threshold_uncertainty_score":0.9212433},"labels":[],"label_agreement":null},{"id":"W2036163493","doi":"10.1145/1141277.1141422","title":"CLUC","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cluster analysis; Categorical variable; Cohesion (chemistry); Data mining; Scalability; Similarity (geometry); Artificial intelligence; Pattern recognition (psychology); Machine learning","score_opus":0.007823885945915845,"score_gpt":0.25728392612711454,"score_spread":0.2494600401811987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036163493","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":[0.0009566502,0.00001881636,0.9251054,0.0006139384,0.00006304868,0.000029007026,9.215112e-8,0.00022623425,0.072986834],"genre_scores_gemma":[0.29660714,0.0000014341542,0.6822967,0.00013496117,0.00009103086,0.000006787336,4.4433713e-7,0.000004954388,0.020856578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994434,0.000009645004,0.000059471193,0.00014835819,0.0001638382,0.00017529164],"domain_scores_gemma":[0.9996223,0.00002583349,0.000008125467,0.00028759195,0.000028343587,0.00002783469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000064815176,0.000037081812,0.000035657355,0.000037523656,0.0000418806,0.00006342657,0.00045248255,0.000013453784,0.000025588824],"category_scores_gemma":[0.000006489585,0.000031326195,0.000014606989,0.0001893669,0.000014676461,0.00022227541,0.00022326775,0.00004657746,0.00026136023],"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":[0.000001433995,0.00006338389,0.00038895544,0.000006272544,0.0000032576813,0.00006105864,0.00003498174,0.0029369143,0.0035067215,0.641586,0.009373066,0.34203795],"study_design_scores_gemma":[0.00041302154,0.00006825104,0.009903209,0.0000050270655,5.1539877e-7,0.000055508583,0.000009838049,0.77773553,0.022849455,0.105942726,0.082716584,0.0003002993],"about_ca_topic_score_codex":0.00006675837,"about_ca_topic_score_gemma":0.0000070631004,"teacher_disagreement_score":0.77479863,"about_ca_system_score_codex":0.00001989572,"about_ca_system_score_gemma":0.000013525935,"threshold_uncertainty_score":0.3359344},"labels":[],"label_agreement":null},{"id":"W2040963032","doi":"10.1142/s0219649211002973","title":"Effectiveness of Heuristic Based Approach on the Performance of Indexing and Clustering of High Dimensional Data","year":2011,"lang":"en","type":"article","venue":"Journal of Information & Knowledge Management","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Cluster analysis; Computer science; Search engine indexing; Data mining; Curse of dimensionality; Hierarchical clustering; DBSCAN; Dimensionality reduction; Clustering high-dimensional data; Heuristic; CURE data clustering algorithm; Correlation clustering; Machine learning; Artificial intelligence","score_opus":0.04405171062011411,"score_gpt":0.2708279659291963,"score_spread":0.2267762553090822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040963032","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":[0.10047051,0.000042031752,0.8963369,0.0000135779765,0.00014612649,0.00023077846,0.0000038064109,0.0000053094827,0.0027509353],"genre_scores_gemma":[0.93110704,0.00001702128,0.0688443,0.000007587232,0.000008284305,0.000003464496,0.0000021332542,0.0000032093196,0.0000069427806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998659,0.00011806246,0.0005807043,0.00008448586,0.00044416144,0.000113542905],"domain_scores_gemma":[0.99830633,0.00024158241,0.00060856587,0.00046479664,0.00034276716,0.000035976762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002141235,0.00008885382,0.00020792418,0.00033902633,0.000051433442,0.000018616172,0.00093964126,0.0000223858,0.0000030754736],"category_scores_gemma":[0.0000777864,0.000060768485,0.00003107013,0.00030050188,0.00007680028,0.0010099511,0.00090429076,0.00013878851,0.0000014076089],"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":[0.0021008116,0.0014117011,0.0017447193,0.019121427,0.0007476088,0.000011586714,0.008470062,0.38217103,0.0007098477,0.061608493,0.00021187188,0.52169085],"study_design_scores_gemma":[0.0007830911,0.00039108307,0.018819606,0.0007079273,0.000014787457,0.0000098540995,0.00012485,0.9747914,0.0041060927,0.00013495007,0.000048641217,0.00006769487],"about_ca_topic_score_codex":0.000003484879,"about_ca_topic_score_gemma":1.6628958e-7,"teacher_disagreement_score":0.83063656,"about_ca_system_score_codex":0.00004150868,"about_ca_system_score_gemma":0.00004292477,"threshold_uncertainty_score":0.2478067},"labels":[],"label_agreement":null},{"id":"W2049769908","doi":"10.1007/bf02960771","title":"Clustering DTDs: An interactive two-level approach","year":2002,"lang":"en","type":"article","venue":"Journal of Computer Science and Technology","topic":"Advanced Clustering Algorithms Research","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":"Simon Fraser University","funders":"","keywords":"Computer science; Cluster analysis; Document type definition; Document Structure Description; XML; Information retrieval; Data mining; Artificial intelligence","score_opus":0.04570929441094207,"score_gpt":0.31330563583075194,"score_spread":0.26759634141980987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049769908","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":[0.031227954,0.00014149155,0.9664255,0.0013815624,0.0004007778,0.00007232195,3.212776e-7,0.00008548553,0.0002646036],"genre_scores_gemma":[0.4725325,0.000025653037,0.527236,0.00009289015,0.000088897,0.0000016325773,2.5610682e-8,0.000004520719,0.000017882658],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980512,0.000043079574,0.0003489206,0.00041951382,0.0006829623,0.0004543018],"domain_scores_gemma":[0.9981445,0.000058393307,0.00024589454,0.00052119634,0.0008327311,0.00019725476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095975795,0.00014231734,0.00025826934,0.0013332224,0.0002547764,0.0003389143,0.0026190283,0.000067223715,0.0000028571799],"category_scores_gemma":[0.000097566466,0.00011718884,0.00003125159,0.0019662923,0.0006663621,0.0028522203,0.0014403377,0.0005228734,0.000005411373],"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":[0.0000044874746,0.0001232512,0.00008498118,0.0000072465855,0.000012130284,0.00009236856,0.0007865646,0.0011820447,0.002608196,0.002555326,0.00004415321,0.99249923],"study_design_scores_gemma":[0.0005168344,0.00069394533,0.00021849967,0.00002986213,0.0000021875753,0.0032045501,0.00008420119,0.9901481,0.001777017,0.0028447653,0.00033688132,0.00014311564],"about_ca_topic_score_codex":0.0000024225574,"about_ca_topic_score_gemma":0.0000010256257,"teacher_disagreement_score":0.9923561,"about_ca_system_score_codex":0.000118019765,"about_ca_system_score_gemma":0.00009660588,"threshold_uncertainty_score":0.48668498},"labels":[],"label_agreement":null},{"id":"W2051549497","doi":"10.1109/foci.2007.371524","title":"Fuzzy Clustering and Mapping of Ordinal Values to Numerical","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Cluster analysis; Fuzzy clustering; Feature (linguistics); Measure (data warehouse); Mathematics; Pattern recognition (psychology); Fuzzy set; Fuzzy logic; Ordinal optimization; Data mining; Artificial intelligence; Ordinal regression; Ordinal data; Object (grammar); Computer science; FLAME clustering; Algorithm; CURE data clustering algorithm; Statistics","score_opus":0.030559089090553892,"score_gpt":0.32468563521561433,"score_spread":0.29412654612506045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051549497","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":[0.027672525,0.00002798612,0.965997,0.0003352976,0.00008136253,0.000089381014,2.214688e-7,0.00008301429,0.0057132225],"genre_scores_gemma":[0.45996648,0.0000020157277,0.53955853,0.00008140452,0.000030462277,0.0000016710857,6.64942e-8,0.000004630309,0.00035475215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988842,0.00001840378,0.0001955434,0.0002772157,0.00028916702,0.00033546466],"domain_scores_gemma":[0.9993144,0.0001345269,0.000028400667,0.00028011037,0.00007154776,0.00017099697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004993356,0.000081733466,0.00013303188,0.00017520066,0.00006063554,0.000046076657,0.00041835537,0.000026896736,0.000004784651],"category_scores_gemma":[0.00007099661,0.00007425224,0.00002084288,0.0004874284,0.000034576016,0.00022301123,0.0009130306,0.000089918314,0.000012274615],"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":[0.000028257258,0.000045535522,0.001514968,0.00006847661,0.000018116794,0.000060630162,0.0019322215,0.002143265,0.019771429,0.0067789713,0.00009743565,0.9675407],"study_design_scores_gemma":[0.001394629,0.0011307488,0.09096217,0.00024415957,0.000005335356,0.000446746,0.0014173128,0.8331034,0.048442572,0.0141184125,0.0076142987,0.0011201851],"about_ca_topic_score_codex":0.000047317964,"about_ca_topic_score_gemma":0.000005446914,"teacher_disagreement_score":0.96642053,"about_ca_system_score_codex":0.000034797653,"about_ca_system_score_gemma":0.000016113858,"threshold_uncertainty_score":0.30279183},"labels":[],"label_agreement":null},{"id":"W2052493879","doi":"10.1109/cec.2012.6252895","title":"Symbiotic evolutionary subspace clustering","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Institute for Materials Science; Natural Sciences and Engineering Research Council of Canada; Dalhousie University","keywords":"Cluster analysis; Data mining; Computer science; Centroid; Subspace topology; CURE data clustering algorithm; Clustering high-dimensional data; Correlation clustering; Single-linkage clustering; Canopy clustering algorithm; Cardinality (data modeling); Artificial intelligence; Pattern recognition (psychology)","score_opus":0.025139009780897566,"score_gpt":0.2933772242592968,"score_spread":0.26823821447839924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052493879","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":[0.002869503,0.0003065655,0.9838322,0.0006915042,0.0004603243,0.00009311936,3.2458613e-7,0.00035306363,0.011393391],"genre_scores_gemma":[0.65533674,0.000008684606,0.339458,0.00010556375,0.00013719294,0.000008184709,5.210481e-7,0.000009217829,0.004935908],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870867,0.000042717682,0.000113939066,0.00021613158,0.00032097998,0.00059755275],"domain_scores_gemma":[0.99911505,0.00008427919,0.000023297574,0.00051584037,0.000049654605,0.00021188991],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022534071,0.00009932599,0.00008764341,0.00009280633,0.00012232772,0.00005981579,0.0006480163,0.000039903094,0.000051202616],"category_scores_gemma":[0.00004500452,0.00009121213,0.000035040903,0.00034789759,0.000035740148,0.0011459545,0.00079136546,0.00013485359,0.00049984193],"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":[0.000040902018,0.0010256399,0.031159865,0.0003082438,0.00014704299,0.00012127407,0.0055521387,0.014210344,0.02435264,0.48603114,0.015687164,0.4213636],"study_design_scores_gemma":[0.0004403539,0.00008912254,0.028642435,0.000031052223,0.0000032705245,0.0003233298,0.00013302066,0.94742864,0.004571426,0.0012958483,0.016490253,0.00055126974],"about_ca_topic_score_codex":0.000018028748,"about_ca_topic_score_gemma":0.0000022156266,"teacher_disagreement_score":0.9332183,"about_ca_system_score_codex":0.00011916778,"about_ca_system_score_gemma":0.000028042663,"threshold_uncertainty_score":0.6424623},"labels":[],"label_agreement":null},{"id":"W2063036182","doi":"10.1504/ijdmb.2006.009920","title":"Bi-level clustering of mixed categorical and numerical biomedical data","year":2006,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Categorical variable; Cluster analysis; Data type; Computer science; Data mining; Artificial intelligence; Machine learning","score_opus":0.10190478292986778,"score_gpt":0.35695398446423293,"score_spread":0.25504920153436517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063036182","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":[0.0057584406,0.00015871972,0.99251634,0.0008636056,0.00038890625,0.000028239065,0.00020083971,0.000010294088,0.000074640106],"genre_scores_gemma":[0.17561944,0.000102291895,0.82392293,0.000028021517,0.00018602323,2.0401328e-7,0.00011659532,0.000004668612,0.000019833555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981415,0.000027943624,0.0007155047,0.00015890003,0.0007922238,0.00016392196],"domain_scores_gemma":[0.9984868,0.0002742905,0.0003933182,0.0005062743,0.000228262,0.00011102865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007990333,0.00009886799,0.00020389566,0.00025033302,0.000042863645,0.00018323978,0.002725622,0.000050073697,0.0000019762347],"category_scores_gemma":[0.000304641,0.000077425924,0.000017089578,0.00016571456,0.00013207197,0.0020467998,0.0038607297,0.00016165087,9.288214e-7],"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":[0.000033374505,0.00009267765,0.0006406522,0.000053183216,0.00009095223,0.000090737776,0.0003120343,0.000054879943,0.00020839696,0.00021456828,0.0029415425,0.995267],"study_design_scores_gemma":[0.00062458,0.00011973539,0.0014818226,0.00008508408,0.000009285175,0.0015151843,0.00015658012,0.99239,0.000070307535,0.00013382283,0.003316827,0.00009680893],"about_ca_topic_score_codex":0.000032975728,"about_ca_topic_score_gemma":0.000003830962,"teacher_disagreement_score":0.9951702,"about_ca_system_score_codex":0.000025645224,"about_ca_system_score_gemma":0.000107468186,"threshold_uncertainty_score":0.5064929},"labels":[],"label_agreement":null},{"id":"W2065468535","doi":"10.1504/ijsise.2013.051504","title":"A correlation based stochastic partitional algorithm for accurate cluster analysis","year":2013,"lang":"en","type":"article","venue":"International Journal of Signal and Imaging Systems Engineering","topic":"Advanced Clustering Algorithms Research","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":"Western University","funders":"","keywords":"Correlation; Cluster (spacecraft); Computer science; Algorithm; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.009204340715160656,"score_gpt":0.2568217004772642,"score_spread":0.24761735976210356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065468535","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":[0.0013751028,0.00023571377,0.9967852,0.0006719005,0.0007242478,0.00016049326,0.000009602956,0.000030677693,0.000007023404],"genre_scores_gemma":[0.8688705,0.0000026465084,0.1306048,0.000066352055,0.00034914952,0.000039004266,0.000006573984,0.000011413036,0.000049575894],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986267,0.00002656011,0.00045134505,0.00017053589,0.00052625494,0.00019858465],"domain_scores_gemma":[0.9982526,0.00034700727,0.00023506643,0.0000895543,0.0009578253,0.00011797631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003773717,0.00012517655,0.00021225562,0.00061188004,0.00004984832,0.00046209389,0.00043162453,0.000026357035,0.000016694106],"category_scores_gemma":[0.000073442156,0.00011180216,0.00012167374,0.0002428937,0.000019490386,0.0010689399,0.00007634286,0.00014780636,0.0000051077045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058657984,0.000016987398,0.00010778887,0.00001321684,0.00027298997,0.000010204936,0.000054289045,0.9770197,0.0006654181,0.00028360504,0.000108031585,0.021441886],"study_design_scores_gemma":[0.0005839484,0.000035054116,0.0008561358,0.00009913778,0.000032572643,0.00013679246,0.000018292307,0.99772614,0.00006172166,0.00015711489,0.00017612985,0.00011692953],"about_ca_topic_score_codex":0.000025570072,"about_ca_topic_score_gemma":1.5702008e-7,"teacher_disagreement_score":0.86749536,"about_ca_system_score_codex":0.000109978864,"about_ca_system_score_gemma":0.0000503717,"threshold_uncertainty_score":0.455916},"labels":[],"label_agreement":null},{"id":"W2067021889","doi":"10.1016/j.patcog.2008.08.037","title":"A distance-relatedness dynamic model for clustering high dimensional data of arbitrary shapes and densities","year":2008,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":45,"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 Waterloo","funders":"","keywords":"Cluster analysis; Outlier; Computer science; Algorithm; Cluster (spacecraft); Measure (data warehouse); Data mining; Correlation clustering; Determining the number of clusters in a data set; Visualization; Process (computing); CURE data clustering algorithm; Pattern recognition (psychology); Mathematics; Artificial intelligence","score_opus":0.0906646566591676,"score_gpt":0.30605559204328986,"score_spread":0.21539093538412224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067021889","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":[0.27757835,0.0000942826,0.721727,0.00010391206,0.00007307133,0.00016438232,0.00020010634,0.000051914856,0.000006964674],"genre_scores_gemma":[0.8688928,0.00008029538,0.13063875,0.000072173476,0.000022899902,0.00003310107,0.00019294379,0.000016125578,0.000050906077],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987827,0.000031301683,0.00023745483,0.00045945405,0.0002512425,0.00023783949],"domain_scores_gemma":[0.99920666,0.00015481401,0.0000925312,0.00035205294,0.00013198351,0.00006197629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015359366,0.00012774569,0.00017952012,0.00009990804,0.00014948941,0.000030558782,0.0004168254,0.000055464392,0.000003040505],"category_scores_gemma":[0.000034175726,0.0001294789,0.000026247792,0.00010125618,0.000101556594,0.0007654582,0.0006180454,0.00011819906,0.0000036367942],"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":[0.00015808464,0.00019313919,0.0004724519,0.0006749788,0.000103974904,0.00008098485,0.0020720134,0.022977084,0.0027030017,0.000050915845,0.000087101,0.97042626],"study_design_scores_gemma":[0.00048207003,0.000049118655,0.0012179154,0.00012954204,0.000006978698,0.00009143754,0.000015441767,0.99350506,0.00027701384,0.004066574,0.0000028711595,0.00015594687],"about_ca_topic_score_codex":0.000042275056,"about_ca_topic_score_gemma":0.000052021704,"teacher_disagreement_score":0.970528,"about_ca_system_score_codex":0.000035294717,"about_ca_system_score_gemma":0.00004486551,"threshold_uncertainty_score":0.52799964},"labels":[],"label_agreement":null},{"id":"W2067475588","doi":"10.5539/ijsp.v2n1p73","title":"Modelling Students' Length of Stay at University Using Coxian Phase-type Distributions","year":2013,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Type (biology); Term (time); Phase (matter); Order (exchange); Mathematics education; Computer science; Sociology; Psychology; Business; Chemistry; Physics","score_opus":0.04458694132785159,"score_gpt":0.345093190856324,"score_spread":0.30050624952847244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067475588","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":[0.39067557,0.00001623177,0.6089481,0.00008075415,0.0001180108,0.00005265577,0.000097296455,0.0000026890689,0.000008681386],"genre_scores_gemma":[0.6746583,0.00004905106,0.325242,0.0000033010638,0.000018290595,1.228125e-7,0.0000034998561,0.0000020324687,0.00002339175],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988978,0.000061973515,0.00028419273,0.00012103632,0.00052594475,0.0001090328],"domain_scores_gemma":[0.9978338,0.0001827171,0.00023708555,0.00011117091,0.0015409462,0.000094287025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000318767,0.000063350955,0.00012473812,0.0000740203,0.0000743877,0.00006953998,0.0005851772,0.00002322985,0.000026513464],"category_scores_gemma":[0.00010495279,0.00005949611,0.00002652181,0.000100172176,0.00011045426,0.00036887178,0.00036291083,0.00012585073,0.0000011196349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011408125,0.0049439725,0.064823695,0.00031538334,0.0018031817,0.00045427642,0.0047228327,0.4392571,0.012636427,0.25659248,0.0008044484,0.21250542],"study_design_scores_gemma":[0.00088595226,0.0002557653,0.0022591301,0.000035348257,0.000011131467,0.00005571075,0.000037050962,0.9411035,0.00044818775,0.054449566,0.00036985494,0.00008877848],"about_ca_topic_score_codex":0.00010067057,"about_ca_topic_score_gemma":0.000004298055,"teacher_disagreement_score":0.50184643,"about_ca_system_score_codex":0.00025783214,"about_ca_system_score_gemma":0.000094710784,"threshold_uncertainty_score":0.24261808},"labels":[],"label_agreement":null},{"id":"W2071486909","doi":"10.1007/s00357-009-9028-x","title":"Assessing Congruence Among Ultrametric Distance Matrices","year":2009,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":37,"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":"Ultrametric space; Mathematics; Resampling; Congruence (geometry); Type I and type II errors; Permutation (music); Mantel test; Distance matrices in phylogeny; Combinatorics; Statistics; Statistic; Normalization (sociology); Discrete mathematics; Biology; Genetics","score_opus":0.042940639641067625,"score_gpt":0.35797349114821986,"score_spread":0.3150328515071522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071486909","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":[0.07474333,0.00033800848,0.92258096,0.0011741068,0.00021848352,0.000058406735,2.2979287e-7,0.00003440423,0.00085209816],"genre_scores_gemma":[0.8849389,0.00012158555,0.11471693,0.00004235502,0.00010075978,8.962088e-7,2.6588384e-7,0.000004023842,0.00007430088],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983991,0.000086072614,0.00046210297,0.00018042083,0.0006612075,0.00021108941],"domain_scores_gemma":[0.99816054,0.00021991433,0.0006808185,0.00032305636,0.0004946874,0.00012098737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007072142,0.00009023771,0.00016417282,0.00035752356,0.0001074563,0.0005479723,0.0009179914,0.00004963483,0.0000025357217],"category_scores_gemma":[0.0004349057,0.000077053264,0.00006199399,0.0012371137,0.000054939617,0.003419289,0.000027229002,0.0003006731,0.000006556572],"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":[0.000013612681,0.00014820862,0.0035798098,0.000019862302,0.000013127678,0.00005826721,0.00027111234,0.0014736828,0.027971247,0.011054778,0.00022971189,0.9551666],"study_design_scores_gemma":[0.00044796694,0.00026228346,0.77283394,0.00015077124,0.000009393786,0.00017559949,0.00018495352,0.21146055,0.005331699,0.00711744,0.0018028328,0.0002225917],"about_ca_topic_score_codex":0.0000020152397,"about_ca_topic_score_gemma":4.252685e-7,"teacher_disagreement_score":0.954944,"about_ca_system_score_codex":0.00018102779,"about_ca_system_score_gemma":0.00011504898,"threshold_uncertainty_score":0.5284109},"labels":[],"label_agreement":null},{"id":"W2072723323","doi":"10.1016/j.eswa.2014.03.042","title":"An interval weighed fuzzy c-means clustering by genetically guided alternating optimization","year":2014,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":32,"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":"National Natural Science Foundation of China","keywords":"Cluster analysis; Fuzzy clustering; Weighting; Mathematics; Correlation clustering; Data mining; CURE data clustering algorithm; Fuzzy logic; FLAME clustering; k-medians clustering; Heuristic; Interval (graph theory); Partition (number theory); Computer science; Pattern recognition (psychology); Mathematical optimization; Algorithm; Artificial intelligence; Combinatorics","score_opus":0.016637616564232523,"score_gpt":0.30557719769351444,"score_spread":0.2889395811292819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072723323","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":[0.00032753867,0.00017031313,0.99583715,0.00036567904,0.00013063669,0.00081529183,0.00000527649,0.00048797028,0.001860133],"genre_scores_gemma":[0.23728754,0.000022557037,0.75999904,0.00016493458,0.00037596314,0.0017597231,0.00003610992,0.0000561811,0.0002979482],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976153,0.00017356066,0.0004560192,0.00075901207,0.0005372657,0.0004588768],"domain_scores_gemma":[0.99781644,0.00010633777,0.00017267311,0.0013431766,0.00027581406,0.0002855797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037708823,0.00023231852,0.00024386965,0.00012346124,0.0003431717,0.00046105406,0.0014778014,0.00007651438,0.000005867577],"category_scores_gemma":[0.000027844322,0.00020844945,0.000034189212,0.00043227305,0.00007054249,0.00055351027,0.00020074692,0.00015886492,0.000036898942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009160149,0.00014134578,0.00006913299,0.000049506296,0.00003409242,0.0000023863613,0.00089941674,0.94163054,0.015023087,0.006529613,0.00074445957,0.03486725],"study_design_scores_gemma":[0.00037522605,0.00013912375,0.000013706419,0.000051612005,0.000002288119,0.00005253267,0.000085456646,0.9883196,0.00083542865,0.00006386046,0.009792401,0.0002687871],"about_ca_topic_score_codex":0.0001600728,"about_ca_topic_score_gemma":0.000009489626,"teacher_disagreement_score":0.23696,"about_ca_system_score_codex":0.00014222064,"about_ca_system_score_gemma":0.000044910248,"threshold_uncertainty_score":0.85003215},"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":"W2074553505","doi":"10.1080/02664760903186049","title":"Clustering probability distributions","year":2010,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Joint probability distribution; Probability distribution; Computer science; Mathematics; Probability density function; Algorithm; Statistical physics; Data mining; Statistics; Physics","score_opus":0.01810154605205502,"score_gpt":0.29800518970734263,"score_spread":0.27990364365528764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074553505","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":[0.0036603962,0.0000040238165,0.9947535,0.00018407122,0.0004735366,0.000091281894,0.000038775797,0.000026103471,0.0007683356],"genre_scores_gemma":[0.21529275,0.0000039667534,0.7845392,0.000018131654,0.00011339309,0.0000030175556,0.0000015301542,0.0000059783965,0.000022041437],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987537,0.000016282116,0.00039654877,0.00014554989,0.00043621598,0.00025168207],"domain_scores_gemma":[0.9986377,0.00023594484,0.00023654984,0.0003641839,0.00035133748,0.00017429233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054068916,0.000094185976,0.00017059372,0.00007590694,0.00012129843,0.00012418083,0.0007747958,0.000048241265,0.000017696866],"category_scores_gemma":[0.00025560876,0.000082695566,0.00003453574,0.00022514515,0.000094889,0.0001900746,0.00027045808,0.00066265697,0.000013412783],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006610142,0.00027254806,0.00009429708,0.00008764456,0.000051874333,0.00014281474,0.00063331047,0.0051670135,0.029385434,0.5154784,0.002041152,0.44657946],"study_design_scores_gemma":[0.0014488646,0.00036019625,0.005233863,0.000028536615,0.000023007766,0.0005918498,0.00006089952,0.37384287,0.0080415495,0.5925037,0.017365452,0.0004991783],"about_ca_topic_score_codex":0.0000013773886,"about_ca_topic_score_gemma":0.0000100289035,"teacher_disagreement_score":0.4460803,"about_ca_system_score_codex":0.000067708104,"about_ca_system_score_gemma":0.00016501236,"threshold_uncertainty_score":0.33722273},"labels":[],"label_agreement":null},{"id":"W2076089275","doi":"10.1007/s00357-006-0018-y","title":"Generation of Random Clusters with Specified Degree of Separation","year":2006,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":122,"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":"Mathematics; Cluster (spacecraft); Constraint (computer-aided design); Dimension (graph theory); Degree (music); Outlier; Covariance; Set (abstract data type); Separation (statistics); Combinatorics; Pattern recognition (psychology); Algorithm; Artificial intelligence; Computer science; Statistics","score_opus":0.12329393467636098,"score_gpt":0.3420131434182264,"score_spread":0.21871920874186546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076089275","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":[0.12572671,0.000064481355,0.87302876,0.00035306838,0.000101897785,0.00010618728,7.50785e-7,0.000006781293,0.00061137823],"genre_scores_gemma":[0.89267373,0.000022590893,0.1070485,0.0000048774773,0.00014792754,0.0000022548936,0.000002833118,0.0000054840293,0.00009178695],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985024,0.000096578115,0.00060392095,0.000115925315,0.0005807628,0.0001004392],"domain_scores_gemma":[0.99816036,0.00009120929,0.00071751536,0.00025741925,0.000738736,0.00003478672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005271394,0.000073226955,0.00019998883,0.00022205782,0.0000363423,0.000033534463,0.0003234625,0.000043269658,0.0000024403305],"category_scores_gemma":[0.000043890694,0.000057005953,0.00005477055,0.00034719723,0.000059311147,0.00063305564,0.000024134495,0.000107719265,0.0000010443578],"study_design_candidate":"bench_or_experimental","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":[0.00058290275,0.00024972885,0.0006657574,0.00006340298,0.00004816011,0.0000074598806,0.00045348122,0.063721836,0.8272604,0.0076680942,0.0006943919,0.09858439],"study_design_scores_gemma":[0.002772119,0.00063780084,0.043042485,0.0000885496,0.000022476754,0.00009263968,0.00009039294,0.6862508,0.2654493,0.0009384516,0.00047254763,0.00014242246],"about_ca_topic_score_codex":0.000007405482,"about_ca_topic_score_gemma":0.000009717539,"teacher_disagreement_score":0.76694703,"about_ca_system_score_codex":0.000080868216,"about_ca_system_score_gemma":0.00011532332,"threshold_uncertainty_score":0.23246354},"labels":[],"label_agreement":null},{"id":"W2077025240","doi":"10.1142/s0218488508005133","title":"FUZZY CLUSTERING OF FEATURE VECTORS WITH SOME ORDINAL VALUED ATTRIBUTES USING GRADIENT DESCENT FOR LEARNING","year":2008,"lang":"en","type":"article","venue":"International Journal of Uncertainty Fuzziness and Knowledge-Based Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Ordinal data; Ordinal regression; Ordinal Scale; Cluster analysis; Gradient descent; Pattern recognition (psychology); Fuzzy clustering; Artificial intelligence; Feature (linguistics); Ordinal optimization; Fuzzy set; Data mining; Fuzzy logic; Statistics; Computer science; Artificial neural network","score_opus":0.04545949455616138,"score_gpt":0.30771333468718276,"score_spread":0.2622538401310214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077025240","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":[0.24724449,0.0013481312,0.74956894,0.00021076023,0.0013246927,0.00024595685,0.000012888378,0.00002403392,0.000020115138],"genre_scores_gemma":[0.9764952,0.000045143814,0.02278989,0.000010546322,0.00052899634,0.000013902709,0.0000054211537,0.000022818977,0.000088097724],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978519,0.00015925261,0.00059589103,0.00029541415,0.00076290686,0.0003346349],"domain_scores_gemma":[0.9959978,0.000355363,0.00067006185,0.00017819913,0.0026195627,0.00017904236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073468377,0.00023394913,0.00049225136,0.00049279374,0.00021941053,0.00013480725,0.00079726375,0.00007832097,7.3148203e-7],"category_scores_gemma":[0.00018997946,0.00017723409,0.00015362134,0.00031746837,0.00014450013,0.00049243437,0.00017049778,0.00031377684,4.2438023e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010811714,0.00030775936,0.008740152,0.00051092816,0.0004375004,0.00023805127,0.0011187759,0.97267413,0.005453523,0.0018968327,0.0000729694,0.007468221],"study_design_scores_gemma":[0.003312976,0.0008486227,0.0013947662,0.0013671938,0.0000277258,0.0011479381,0.00024239479,0.98939574,0.0011148754,0.00012116622,0.0007544079,0.0002722075],"about_ca_topic_score_codex":0.00007502803,"about_ca_topic_score_gemma":0.000013967083,"teacher_disagreement_score":0.72925067,"about_ca_system_score_codex":0.00039093953,"about_ca_system_score_gemma":0.0005250686,"threshold_uncertainty_score":0.7227397},"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":"W2079184215","doi":"10.5539/cis.v3n3p23","title":"An Improved Clustering Algorithm Based on Density Distribution Function","year":2010,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Computer science; Point (geometry); Algorithm; Scale (ratio); Distribution (mathematics); Core (optical fiber); Function (biology); Pattern recognition (psychology); Mathematics; Artificial intelligence; Physics; Geometry; Mathematical analysis","score_opus":0.008231189996876725,"score_gpt":0.2644429853575031,"score_spread":0.2562117953606264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079184215","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":[0.013585986,6.88086e-7,0.9847545,0.00015255816,0.0009856765,0.00015419841,0.00000515536,0.00019521253,0.00016605029],"genre_scores_gemma":[0.6615575,0.0000013502965,0.33771223,0.0006070006,0.00009034523,0.000008399583,0.000017820908,0.0000025485988,0.0000028235454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985916,0.000022564729,0.00021723087,0.00031534358,0.00052914134,0.00032413783],"domain_scores_gemma":[0.9986767,0.00004619046,0.00008566077,0.00058590865,0.00037392846,0.00023160886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008788983,0.00012170611,0.00009102201,0.00024220535,0.0005753331,0.0010067655,0.0007528056,0.000051169878,0.0000029233975],"category_scores_gemma":[0.000049071445,0.000110176195,0.000020474608,0.0007503708,0.00021963888,0.011684743,0.00033564251,0.00026550196,0.000023614755],"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":[0.0000075261682,0.000020199448,0.000044318534,0.0000072827265,7.080655e-7,4.9321477e-7,0.00014555905,0.004708899,0.0019672627,0.001717696,0.000016607071,0.99136347],"study_design_scores_gemma":[0.00027687394,0.00027156324,0.017691702,0.0000064728283,7.034377e-7,0.000015007252,0.00000704111,0.97850186,0.0016060998,0.00013063356,0.0013555675,0.00013650817],"about_ca_topic_score_codex":0.000009875874,"about_ca_topic_score_gemma":0.0000017965828,"teacher_disagreement_score":0.9912269,"about_ca_system_score_codex":0.00005870247,"about_ca_system_score_gemma":0.00012300319,"threshold_uncertainty_score":0.97082627},"labels":[],"label_agreement":null},{"id":"W2080476941","doi":"10.1016/j.patcog.2007.11.011","title":"A convergence theorem for the fuzzy subspace clustering (FSC) algorithm","year":2007,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Subsequence; Convergence (economics); Cluster analysis; Subspace topology; Sequence (biology); Algorithm; Mathematics; Fuzzy logic; Set (abstract data type); Computer science; Mathematical optimization; Artificial intelligence","score_opus":0.044762448138194626,"score_gpt":0.3136870178531478,"score_spread":0.26892456971495315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080476941","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":[0.0020795595,0.0001162958,0.9947789,0.0007976635,0.0009081074,0.00063059636,0.00002298191,0.00020634338,0.00045958097],"genre_scores_gemma":[0.580035,0.0001715432,0.41679534,0.0011541911,0.00092019426,0.0003598182,0.000039167862,0.000071168884,0.00045361757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814516,0.00006059738,0.00027507904,0.00048296948,0.00040266485,0.0006335068],"domain_scores_gemma":[0.9980325,0.00095303805,0.00011476653,0.00052395934,0.00025577116,0.00011993376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013522285,0.00018281955,0.00014368683,0.00011623227,0.00033307975,0.00017395745,0.00085427787,0.0000746499,0.000022083139],"category_scores_gemma":[0.000116737865,0.00014534625,0.000096208074,0.000355531,0.000081991304,0.00045708212,0.00033698248,0.00023014855,0.00015578954],"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":[0.00001265823,0.000021885156,0.000048650047,0.000025518651,0.00001692384,0.000013085797,0.00039062975,0.000057692814,0.00039492006,0.000045261222,0.000050161987,0.9989226],"study_design_scores_gemma":[0.0009963847,0.00020699014,0.0025875848,0.00010072533,0.000016264896,0.00013395504,0.00037983264,0.9658268,0.0154609755,0.011578584,0.0022307457,0.00048115823],"about_ca_topic_score_codex":0.000057971534,"about_ca_topic_score_gemma":0.00008339334,"teacher_disagreement_score":0.99844146,"about_ca_system_score_codex":0.00009806257,"about_ca_system_score_gemma":0.00002972589,"threshold_uncertainty_score":0.5927048},"labels":[],"label_agreement":null},{"id":"W2082539276","doi":"10.1016/j.ins.2012.02.042","title":"Feature selection using structural similarity","year":2012,"lang":"en","type":"article","venue":"Information Sciences","topic":"Advanced Clustering Algorithms Research","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":"University of Alberta","funders":"","keywords":"Cardinality (data modeling); Feature selection; Pattern recognition (psychology); Similarity (geometry); Data mining; Cluster analysis; Partition (number theory); Curse of dimensionality; Feature (linguistics); Computer science; Mathematics; Artificial intelligence; Selection (genetic algorithm); Combinatorics","score_opus":0.057503571108182994,"score_gpt":0.37055909314857566,"score_spread":0.31305552204039266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082539276","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":[0.088627875,0.000029554,0.90860355,0.0005776324,0.00050518353,0.000092485614,0.0000013136834,0.00013337808,0.0014290024],"genre_scores_gemma":[0.7541294,0.0000012886235,0.24556656,0.00019198046,0.00007517625,0.0000024130784,8.541691e-7,0.0000011288279,0.000031196476],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884814,0.00003260602,0.000116097166,0.00009094413,0.00055560877,0.000356628],"domain_scores_gemma":[0.9995402,0.000038712817,0.000085547115,0.00012588761,0.00011847187,0.00009117988],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00060764916,0.00007074369,0.000059283175,0.00017827124,0.0005159333,0.00040698922,0.0005498003,0.000041091225,0.000009650338],"category_scores_gemma":[0.0000972518,0.000057101483,0.000020839332,0.0010084435,0.00009619806,0.013872795,0.00019458441,0.00012771101,0.000039707094],"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":[0.000013695135,0.000034782322,0.047916476,0.00008707265,0.000022503902,9.602153e-7,0.015086889,0.12506409,0.0039683883,0.07092075,0.002113653,0.7347708],"study_design_scores_gemma":[0.00007100769,0.000022574857,0.010761264,0.0000044899175,6.6006857e-7,0.00005769878,0.00011532155,0.9808371,0.0020892965,0.0005952263,0.00534073,0.00010463232],"about_ca_topic_score_codex":0.000025190813,"about_ca_topic_score_gemma":0.0000016890464,"teacher_disagreement_score":0.85577303,"about_ca_system_score_codex":0.000084801344,"about_ca_system_score_gemma":0.00007979246,"threshold_uncertainty_score":0.99991965},"labels":[],"label_agreement":null},{"id":"W2082738974","doi":"10.1109/cicare.2014.7007849","title":"A novel mixed values k-prototypes algorithm with application to health care databases mining","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"Institute of Genetics","keywords":"Categorical variable; Cluster analysis; Data mining; Computer science; Variable (mathematics); Field (mathematics); Representation (politics); Algorithm; Database; Artificial intelligence; Machine learning; Mathematics","score_opus":0.02655961038866402,"score_gpt":0.3337965133803607,"score_spread":0.3072369029916967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082738974","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":[0.0004948563,0.00004671374,0.9966426,0.0012335022,0.000056916557,0.0007665332,0.000010198503,0.00032704417,0.0004216486],"genre_scores_gemma":[0.015756056,0.0000023581865,0.9829753,0.0006444831,0.0000894365,0.00030790045,0.000017562717,0.000019541589,0.00018735582],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981767,0.00005729849,0.00018729341,0.00064516935,0.0004863274,0.00044720087],"domain_scores_gemma":[0.9984341,0.00012589945,0.00006469268,0.00093090953,0.00019514984,0.0002492402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032153536,0.00015758889,0.00018835833,0.00014060501,0.00021558613,0.000110293346,0.0007750806,0.000020848001,0.000002671172],"category_scores_gemma":[0.00005303018,0.00012575643,0.000020009813,0.000553318,0.000036966845,0.0003846575,0.00047797192,0.00009878143,0.000044368357],"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":[0.0000073970773,0.000033097782,0.00003938534,0.000039844184,0.000006919874,8.543082e-7,0.0011128759,0.0014320154,0.00041333403,0.0021370226,0.00018989362,0.99458736],"study_design_scores_gemma":[0.00084168505,0.0010517759,0.0014159852,0.00011228186,0.0000029368018,0.000043489832,0.0009916591,0.9568345,0.008172867,0.00011950942,0.029905459,0.0005078334],"about_ca_topic_score_codex":0.000393485,"about_ca_topic_score_gemma":0.00016626544,"teacher_disagreement_score":0.99407953,"about_ca_system_score_codex":0.00011223352,"about_ca_system_score_gemma":0.0001311523,"threshold_uncertainty_score":0.5128198},"labels":[],"label_agreement":null},{"id":"W2086478515","doi":"10.1126/science.1151268","title":"Response to Comment on \"Clustering by Passing Messages Between Data Points\"","year":2008,"lang":"en","type":"article","venue":"Science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":65,"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 Toronto","funders":"","keywords":"Generalization; Heuristic; Cluster analysis; Vertex (graph theory); Affinity propagation; Probabilistic logic; Substitution (logic); Computer science; Algorithm; Combinatorics; Graph; Chemistry; Mathematics; Theoretical computer science; Artificial intelligence; Correlation clustering; Mathematical analysis","score_opus":0.10641529095600079,"score_gpt":0.37877880338952974,"score_spread":0.27236351243352896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086478515","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":[0.037667166,0.000032115073,0.92151105,0.03980799,0.00023812501,0.00021655897,0.000027262735,0.00018683333,0.0003129006],"genre_scores_gemma":[0.61426455,0.000011879475,0.37956378,0.0053124055,0.00007262412,0.00001773169,0.0000048188867,0.00002073456,0.0007314468],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99633396,0.00016317873,0.0002259941,0.0010884074,0.0014289797,0.00075949496],"domain_scores_gemma":[0.9965191,0.00047067934,0.000058093232,0.0024479749,0.00010003285,0.00040410712],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0028619939,0.00016071161,0.00016882324,0.00030244078,0.0009512442,0.00032816757,0.0064529106,0.000029445877,0.0000064834967],"category_scores_gemma":[0.00083765184,0.00014948673,0.000018180483,0.0013278037,0.00044138645,0.0015153512,0.0057651103,0.00022316547,0.000142287],"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":[0.00035845416,0.00036169417,0.002953075,0.000040666888,0.000031384614,0.0005307179,0.010116812,0.0047643636,0.19456363,0.0005873723,0.100409776,0.68528205],"study_design_scores_gemma":[0.0014390728,0.0013815631,0.03294069,0.00034206838,0.0000047984017,0.00017196556,0.00021608421,0.3398672,0.11923777,0.0011797191,0.50166726,0.0015517902],"about_ca_topic_score_codex":0.000026876376,"about_ca_topic_score_gemma":0.0000013318166,"teacher_disagreement_score":0.68373024,"about_ca_system_score_codex":0.00028843214,"about_ca_system_score_gemma":0.00025869664,"threshold_uncertainty_score":0.99892265},"labels":[],"label_agreement":null},{"id":"W2086582257","doi":"10.1007/bf02962204","title":"Sequential combination methods for data clustering analysis","year":2002,"lang":"en","type":"article","venue":"Journal of Computer Science and Technology","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Computer science; CURE data clustering algorithm; Correlation clustering; Canopy clustering algorithm; Data stream clustering; Constrained clustering; Fuzzy clustering; Data mining; Clustering high-dimensional data; Algorithm; Artificial intelligence","score_opus":0.0811634130080792,"score_gpt":0.41144146351408606,"score_spread":0.3302780505060069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086582257","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":[0.00219037,0.00028260166,0.99313796,0.0038226545,0.00041156472,0.00008853243,7.640435e-7,0.00004824037,0.00001732031],"genre_scores_gemma":[0.11511713,0.00005582459,0.88469046,0.00006153928,0.00005544231,0.000001932162,2.8172684e-7,0.0000033778815,0.000013980861],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848086,0.00004910745,0.0003499289,0.00039198133,0.0004116127,0.00031648926],"domain_scores_gemma":[0.9978072,0.00015652021,0.0002618177,0.00078066654,0.00089779147,0.000096017066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027162281,0.0000921247,0.00026860702,0.0019524797,0.00024341326,0.0002757224,0.0034268913,0.00006392233,0.0000021289086],"category_scores_gemma":[0.0002754952,0.00007915496,0.000041544918,0.0039518783,0.00039309793,0.0016705458,0.002235003,0.00020469914,8.8123545e-7],"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":[0.0000018166078,0.00003460798,0.0000609741,0.00000647301,0.000057054272,0.000009322101,0.000083215135,0.00045491772,0.00173938,0.0028851936,0.00007375263,0.9945933],"study_design_scores_gemma":[0.0003546798,0.00030464868,0.00008978865,0.0000086716955,0.00002756807,0.00025152144,0.00000726029,0.98965645,0.0015773379,0.005577754,0.0020607621,0.00008354622],"about_ca_topic_score_codex":0.0000014859204,"about_ca_topic_score_gemma":0.0000012309982,"teacher_disagreement_score":0.99450976,"about_ca_system_score_codex":0.00006937212,"about_ca_system_score_gemma":0.00007849855,"threshold_uncertainty_score":0.6368073},"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":"W2088308919","doi":"10.1109/icdmw.2011.162","title":"TeamExp: Top-k Team Formation in Social Networks","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Set (abstract data type); Computer science; Social network (sociolinguistics); Communication skills; Knowledge management; Social media; World Wide Web; Medical education","score_opus":0.04316863286285745,"score_gpt":0.2991666233186445,"score_spread":0.2559979904557871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088308919","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":[0.0031128798,0.000010217245,0.9542479,0.000109976085,0.00009249378,0.00009728872,1.1718077e-7,0.0001312355,0.04219789],"genre_scores_gemma":[0.8622862,0.0000058959968,0.13669725,0.00013483033,0.000089261666,0.00002294584,7.6928643e-7,0.0000060342704,0.0007567997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916375,0.00003829179,0.00014956499,0.00017302966,0.00017436942,0.00030100244],"domain_scores_gemma":[0.99966353,0.000022402603,0.00002883598,0.00020463984,0.000036991954,0.000043591353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018957687,0.00006674248,0.00007839948,0.000104254075,0.000081236176,0.00004485411,0.00053499924,0.000051151106,0.000031950865],"category_scores_gemma":[0.00001527684,0.00006109362,0.000022915687,0.00036545293,0.000022441072,0.00086239673,0.00031284388,0.00015878372,0.000051722265],"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":[0.000020870191,0.00017113067,0.0008695682,0.000018231336,0.0000070351552,0.000042330128,0.010347773,0.0017207611,0.00023378684,0.06296705,0.0034264128,0.9201751],"study_design_scores_gemma":[0.00030647346,0.00005421215,0.0043851906,0.0000064920478,3.6556668e-7,0.000015014233,0.00015301409,0.98604697,0.0016024988,0.0063728318,0.0009133112,0.00014360862],"about_ca_topic_score_codex":0.00005419044,"about_ca_topic_score_gemma":0.00002668361,"teacher_disagreement_score":0.98432624,"about_ca_system_score_codex":0.00007549205,"about_ca_system_score_gemma":0.0000139756,"threshold_uncertainty_score":0.24913253},"labels":[],"label_agreement":null},{"id":"W2089055054","doi":"10.1145/1401890.1401956","title":"Finding non-redundant, statistically significant regions in high dimensional data","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Disjoint sets; Computer science; Cluster (spacecraft); Outlier; Data mining; Single-linkage clustering; Clustering high-dimensional data; Subspace topology; Complete-linkage clustering; Data point; Correlation clustering; Determining the number of clusters in a data set; CURE data clustering algorithm; Pattern recognition (psychology); Artificial intelligence; Mathematics; Combinatorics","score_opus":0.10470996700155884,"score_gpt":0.3439923630461722,"score_spread":0.23928239604461338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089055054","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":[0.011948102,0.000010138696,0.98577565,0.0012532162,0.00014359709,0.00014726068,0.000026658941,0.000097358825,0.0005980128],"genre_scores_gemma":[0.42992985,0.00001654303,0.5685577,0.00011347371,0.000032673317,0.000009066357,0.00002646466,0.000009960856,0.0013042827],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979486,0.000059029982,0.0002691845,0.0006784492,0.0005536832,0.00049104966],"domain_scores_gemma":[0.9979619,0.0004239273,0.000039650247,0.0013381888,0.00006814266,0.00016819489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003107999,0.00012714155,0.00017121529,0.00017545432,0.00019125958,0.000059621052,0.0018878313,0.000041901512,0.00004308532],"category_scores_gemma":[0.00022664144,0.000113462665,0.000015756457,0.0005454281,0.00014868096,0.0006289182,0.001916132,0.0002620393,0.00012144716],"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":[0.00018598106,0.0023419491,0.008631247,0.00016180101,0.0001694143,0.019749967,0.003218761,0.056071196,0.02791096,0.54125196,0.10387244,0.23643434],"study_design_scores_gemma":[0.0005204628,0.00007631245,0.018490687,0.000029647079,0.000001093695,0.00013008645,0.000012973169,0.9751111,0.0003769333,0.0043641436,0.0006429841,0.00024352872],"about_ca_topic_score_codex":0.00031293798,"about_ca_topic_score_gemma":0.000043868036,"teacher_disagreement_score":0.91903996,"about_ca_system_score_codex":0.00008419678,"about_ca_system_score_gemma":0.00025757862,"threshold_uncertainty_score":0.4626873},"labels":[],"label_agreement":null},{"id":"W2093156537","doi":"10.1007/s10044-007-0088-4","title":"Hierarchical clustering of subpopulations with a dissimilarity based on the likelihood ratio statistic: application to clustering massive data sets","year":2007,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Cluster analysis; Mathematics; Statistic; Hierarchical clustering; Multinomial distribution; Poisson distribution; Multivariate normal distribution; Statistics; Data mining; Computer science; Multivariate statistics","score_opus":0.03091776160389113,"score_gpt":0.3354578783523037,"score_spread":0.3045401167484125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093156537","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":[0.0015964806,0.000006336986,0.9946455,0.0027464363,0.0000063554335,0.0006715439,0.00019591785,0.00004629654,0.000085128275],"genre_scores_gemma":[0.8774816,0.000002919872,0.12178784,0.00027622897,0.000028731383,0.0002365725,0.0001654137,0.000011341687,0.000009360572],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981647,0.000069931826,0.00036023904,0.0006531398,0.00045602146,0.00029597184],"domain_scores_gemma":[0.997193,0.00054330507,0.00015921425,0.0017765979,0.0001427892,0.00018512788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006673663,0.00015545153,0.00022399469,0.00031526593,0.00034913587,0.00013764443,0.0010329782,0.00003784699,0.000008308174],"category_scores_gemma":[0.00004234431,0.00011448043,0.00004171809,0.0017423165,0.000081221144,0.00015561971,0.0005849554,0.00018884521,0.0000049594005],"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":[0.000040042985,0.00028452463,0.018225608,0.00006918236,0.00027430104,0.000004575236,0.00046723435,0.1810209,0.0011944149,0.0030801853,0.000029932897,0.7953091],"study_design_scores_gemma":[0.00013186384,0.000042989446,0.06852243,0.000014588523,0.000074913885,0.000001242111,0.000053974327,0.93037015,0.00020211091,0.00029372633,0.00016255288,0.00012947967],"about_ca_topic_score_codex":0.00026763152,"about_ca_topic_score_gemma":0.0026313695,"teacher_disagreement_score":0.8758851,"about_ca_system_score_codex":0.0000480169,"about_ca_system_score_gemma":0.000039002098,"threshold_uncertainty_score":0.4668376},"labels":[],"label_agreement":null},{"id":"W2095980495","doi":"10.1145/2740908.2742474","title":"Short-Text Clustering using Statistical Semantics","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":25,"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 Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Term (time); Similarity (geometry); Semantics (computer science); Representation (politics); Selection (genetic algorithm); Measure (data warehouse); Computation; Space (punctuation); Data mining; Artificial intelligence; Matrix (chemical analysis); Document clustering; Pattern recognition (psychology); Algorithm","score_opus":0.13068816452266865,"score_gpt":0.3815659194037594,"score_spread":0.25087775488109076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095980495","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":[0.0041153664,0.000022651755,0.99284273,0.00021220006,0.00028981507,0.00009296096,0.0000015233472,0.00021970688,0.0022030554],"genre_scores_gemma":[0.33370402,0.0000017310462,0.6658034,0.000056695342,0.000060474085,0.0000023249154,7.972256e-7,0.000011561904,0.00035902142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841917,0.0000549313,0.00019259036,0.00034782922,0.0005384929,0.00044701848],"domain_scores_gemma":[0.9989058,0.00009817693,0.000018508148,0.0005078582,0.00014867327,0.00032102177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033359491,0.000120216886,0.00014244678,0.00009090266,0.000079530524,0.00020987946,0.00068604655,0.0000446205,0.000011659156],"category_scores_gemma":[0.00012451972,0.00011068309,0.000021103928,0.0002946551,0.000059672133,0.00048358322,0.001056704,0.00016207101,0.00009436504],"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":[0.00004025978,0.00023801591,0.0015527814,0.00011433077,0.000069675145,0.0010598374,0.0020310115,0.16995752,0.003940362,0.08545558,0.0022630778,0.73327756],"study_design_scores_gemma":[0.0001520753,0.000046961286,0.00016802998,0.0000093140725,0.0000016247465,0.00010200668,0.0000605693,0.9960502,0.0004823311,0.001914246,0.00085812993,0.00015453585],"about_ca_topic_score_codex":0.000036611575,"about_ca_topic_score_gemma":0.000010481915,"teacher_disagreement_score":0.82609266,"about_ca_system_score_codex":0.00014171696,"about_ca_system_score_gemma":0.00010138988,"threshold_uncertainty_score":0.45135254},"labels":[],"label_agreement":null},{"id":"W2096879261","doi":"","title":"Measures of Clustering Quality: A Working Set of Axioms for Clustering","year":2008,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":141,"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 Waterloo","funders":"","keywords":"Cluster analysis; Axiom; Impossibility; Constrained clustering; Computer science; Correlation clustering; Theoretical computer science; Fuzzy clustering; Data mining; Mathematics; Set (abstract data type); CURE data clustering algorithm; Artificial intelligence","score_opus":0.17760896120554284,"score_gpt":0.35983169362462686,"score_spread":0.18222273241908402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096879261","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":[0.015251761,0.00022664064,0.98305213,0.00007737976,0.00039992583,0.0004916431,0.000008060041,0.00015539608,0.00033707923],"genre_scores_gemma":[0.97765857,0.000009333461,0.022065684,0.00003010738,0.000077612014,0.000077598255,0.000007171937,0.000012549854,0.000061363986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974428,0.00007975425,0.0011682858,0.00019652957,0.00075520086,0.00035747423],"domain_scores_gemma":[0.99785054,0.00015601754,0.0008673548,0.00038899886,0.00065878045,0.00007828181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008386247,0.00017345208,0.00039848106,0.0003319068,0.00024931488,0.00016607672,0.0007375107,0.00008530613,4.2794284e-7],"category_scores_gemma":[0.00022711043,0.00016364871,0.00008593741,0.00060126005,0.000090670954,0.002898641,0.0002819751,0.00013932816,0.0000019225138],"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":[0.00014885762,0.000031459334,0.00046289165,0.0067874365,0.000046011475,0.0000032481394,0.026579145,0.43813053,0.0062447167,0.00076103,0.0000431736,0.5207615],"study_design_scores_gemma":[0.0005459254,0.000091630965,0.00021162094,0.00042347424,0.0000028065858,0.000098972625,0.00077023567,0.9947432,0.0020774885,0.000022476877,0.0008380746,0.00017406497],"about_ca_topic_score_codex":0.00007649262,"about_ca_topic_score_gemma":0.0000084165595,"teacher_disagreement_score":0.9624068,"about_ca_system_score_codex":0.00008111746,"about_ca_system_score_gemma":0.00012475377,"threshold_uncertainty_score":0.6673401},"labels":[],"label_agreement":null},{"id":"W2097507414","doi":"10.1109/icdm.2006.151","title":"Speedup Clustering with Hierarchical Ranking","year":2006,"lang":"en","type":"article","venue":"Proceedings","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":4,"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; Canada's Michael Smith Genome Sciences Centre","keywords":"Speedup; Cluster analysis; Computer science; Ranking (information retrieval); Pairwise comparison; Data mining; Hierarchical clustering; Algorithm; Artificial intelligence; Parallel computing","score_opus":0.009744494059777837,"score_gpt":0.2418840382192615,"score_spread":0.23213954415948365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097507414","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":[0.055718563,0.000048401704,0.91729337,0.001166157,0.00008837303,0.00020315667,4.30827e-7,0.00054198597,0.024939576],"genre_scores_gemma":[0.67236114,0.0000028464583,0.32635057,0.000080264734,0.0002316546,0.000025238533,6.20864e-7,0.000023225291,0.0009244451],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981739,0.000005646571,0.00018278736,0.0005026692,0.00056827656,0.0005667142],"domain_scores_gemma":[0.9994579,0.000038789658,0.000060451966,0.00018132804,0.00015898589,0.00010254671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002378314,0.00016701699,0.00015889309,0.00016287199,0.00019185731,0.00038765938,0.00084505416,0.000048923284,0.000007293271],"category_scores_gemma":[0.000027629185,0.00014057597,0.000033526463,0.00061863847,0.00008615574,0.0008379868,0.00051891257,0.00030103393,0.00003697044],"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":[0.00036676467,0.0005449646,0.021482136,0.00081134605,0.0001128308,0.0005405869,0.00448518,0.00785716,0.074692994,0.2837274,0.0031190405,0.6022596],"study_design_scores_gemma":[0.002159434,0.0004760812,0.01113912,0.00027789935,0.000009806837,0.0008820939,0.00009921648,0.9206416,0.019529633,0.025838617,0.017885247,0.0010612581],"about_ca_topic_score_codex":0.00003662184,"about_ca_topic_score_gemma":0.0000054194734,"teacher_disagreement_score":0.91278446,"about_ca_system_score_codex":0.00008623726,"about_ca_system_score_gemma":0.000036734586,"threshold_uncertainty_score":0.57325214},"labels":[],"label_agreement":null},{"id":"W2099837874","doi":"","title":"Human Cluster Evaluation and Formal Quality Measures: A Comparative Study","year":2012,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":37,"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 Waterloo","funders":"National Science Foundation","keywords":"Cluster analysis; Computer science; Data mining; Disjoint sets; Partition (number theory); Consistency (knowledge bases); Set (abstract data type); Contrast (vision); Fuzzy clustering; Machine learning; Artificial intelligence; Mathematics","score_opus":0.09701167708169886,"score_gpt":0.3631882371902808,"score_spread":0.2661765601085819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099837874","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":[0.93535435,0.00027346573,0.055534888,0.0002311326,0.00012645365,0.0012679356,0.00013249138,0.0004028976,0.0066764],"genre_scores_gemma":[0.9935379,0.0000012008297,0.0057374467,0.00014916832,0.00013505886,0.00011154648,0.000050663963,0.000029193514,0.0002478367],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962032,0.0006391473,0.00051492424,0.0005490059,0.0012910754,0.00080267945],"domain_scores_gemma":[0.99832726,0.00020974646,0.0001519998,0.00069411617,0.00013937379,0.00047749933],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.002028275,0.0002983805,0.00032948796,0.00019472458,0.00041311,0.0019023992,0.00086594466,0.000088505985,0.000043010456],"category_scores_gemma":[0.00025166216,0.00026465114,0.000075463446,0.0005219232,0.00010946308,0.019801723,0.0014525654,0.00048803855,0.00040203345],"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":[0.00028043738,0.0040019606,0.72362006,0.00016112007,0.0003427644,0.000021381311,0.008246342,0.00028417772,0.000562335,0.012341475,0.0010659682,0.24907196],"study_design_scores_gemma":[0.012005106,0.0020292532,0.85192144,0.00019332983,0.00008894042,0.00011746716,0.0033684084,0.04657215,0.0036751435,0.03502295,0.04161376,0.0033920307],"about_ca_topic_score_codex":0.000003982845,"about_ca_topic_score_gemma":0.0000025753736,"teacher_disagreement_score":0.24567993,"about_ca_system_score_codex":0.0000853089,"about_ca_system_score_gemma":0.00008012195,"threshold_uncertainty_score":0.99998057},"labels":[],"label_agreement":null},{"id":"W2100405508","doi":"10.1109/nafips.2008.4531218","title":"Discovering structure in labeled data","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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","keywords":"Cluster analysis; Computer science; Hierarchical clustering; Class (philosophy); Similarity (geometry); Data mining; Measure (data warehouse); Cluster (spacecraft); Artificial intelligence; Similarity measure; Data structure; Pattern recognition (psychology); Mathematics","score_opus":0.08347915006166517,"score_gpt":0.329163074094694,"score_spread":0.2456839240330288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100405508","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":[0.19991092,0.000058947848,0.79831403,0.00037784711,0.000112419046,0.00009033388,0.00000744662,0.00012455031,0.0010034943],"genre_scores_gemma":[0.74674314,0.000022801123,0.2523881,0.000060997318,0.00002970491,0.0000016754616,0.000005666896,0.000005865986,0.0007420379],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899405,0.000022306018,0.00010725428,0.00037294233,0.0002444722,0.00025896865],"domain_scores_gemma":[0.9986738,0.00004436893,0.000014721214,0.0011994435,0.000016677672,0.000050970237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008038976,0.00006941113,0.00008635031,0.000075951466,0.00005864012,0.000042141113,0.0019346285,0.000025009864,0.000022544917],"category_scores_gemma":[0.000055927772,0.000058634098,0.0000071426284,0.00040651843,0.000031180032,0.0010442396,0.002018839,0.00015424132,0.00001820483],"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":[0.00007025237,0.0005055043,0.05464252,0.00018651874,0.00009500107,0.005159591,0.0090975305,0.07507145,0.07739888,0.05470975,0.006699983,0.716363],"study_design_scores_gemma":[0.0005323957,0.000027366308,0.013975191,0.000012449052,3.1304072e-7,0.00014445567,0.000023751338,0.9770824,0.00370138,0.0014237413,0.002862331,0.00021425255],"about_ca_topic_score_codex":0.00010241946,"about_ca_topic_score_gemma":0.00013722657,"teacher_disagreement_score":0.9020109,"about_ca_system_score_codex":0.00003760554,"about_ca_system_score_gemma":0.000053479078,"threshold_uncertainty_score":0.35950533},"labels":[],"label_agreement":null},{"id":"W2103991913","doi":"10.1093/bioinformatics/btg030","title":"<i>K</i>-ary clustering with optimal leaf ordering for gene expression data","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Leverhulme Trust; Florida State University; Natural Sciences and Engineering Research Council of Canada; Burroughs Wellcome Fund","keywords":"Cluster analysis; Hierarchical clustering; Computer science; Tree (set theory); Binary tree; Pairwise comparison; Hierarchical clustering of networks; Single-linkage clustering; Robustness (evolution); CURE data clustering algorithm; Data mining; Algorithm; Nearest-neighbor chain algorithm; Correlation clustering; Canopy clustering algorithm; Tree structure; Mathematics; Artificial intelligence; Gene; Biology; Combinatorics; Genetics","score_opus":0.055061850156336696,"score_gpt":0.306350724116407,"score_spread":0.2512888739600703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103991913","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":[0.0007065247,0.00006439203,0.997188,0.000059173693,0.00017200684,0.00037961258,0.000020383106,0.00018375654,0.0012261719],"genre_scores_gemma":[0.005356442,0.000023571485,0.9941798,0.00009599646,0.00004178732,0.000035050572,0.000029435345,0.000022119955,0.00021582785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984377,0.000021745238,0.00032238153,0.00030717917,0.00039498022,0.0005159879],"domain_scores_gemma":[0.99793106,0.00011480147,0.00011957916,0.0015556351,0.00010276326,0.00017617413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004352963,0.00018353196,0.00017630866,0.00010250155,0.0002421556,0.0002511642,0.0015856228,0.000059369202,0.000004228434],"category_scores_gemma":[0.0001802609,0.00014998717,0.000025372663,0.00028300018,0.0000460651,0.0020031044,0.0011331387,0.00014614065,0.000017214143],"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":[0.00033431657,0.00042140874,0.00024060217,0.0027860897,0.00022671043,0.00012384942,0.01016453,0.45759565,0.023364475,0.0051362063,0.0069696447,0.49263653],"study_design_scores_gemma":[0.0007020261,0.00014003713,0.0000068202535,0.00006884495,0.0000034306888,0.00010088073,0.00016140928,0.96436507,0.016518569,0.000049077582,0.017634094,0.00024976765],"about_ca_topic_score_codex":0.0000020007562,"about_ca_topic_score_gemma":0.0000019404933,"teacher_disagreement_score":0.5067694,"about_ca_system_score_codex":0.000051568015,"about_ca_system_score_gemma":0.00015298178,"threshold_uncertainty_score":0.6116299},"labels":[],"label_agreement":null},{"id":"W2105120842","doi":"10.1007/s10898-011-9691-4","title":"An efficient algorithm for maximal margin clustering","year":2011,"lang":"en","type":"article","venue":"Journal of Global Optimization","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":9,"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":"Air Force Office of Scientific Research; National Institutes of Health; National Science Foundation","keywords":"Margin (machine learning); Cluster analysis; Mathematics; Curse of dimensionality; Dimensionality reduction; Convergence (economics); Algorithm; Extension (predicate logic); Computational complexity theory; Computer science; Artificial intelligence; Machine learning; Statistics","score_opus":0.027345270433135983,"score_gpt":0.3021882505185445,"score_spread":0.2748429800854085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105120842","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":[0.00071501045,0.000054952536,0.9981276,0.000079550075,0.0005453239,0.00016264769,0.0000066410475,0.00004016172,0.00026813353],"genre_scores_gemma":[0.028098047,0.0000118400785,0.97168714,0.000044092332,0.00013016515,0.000004187258,0.0000013050393,0.00000980187,0.000013451725],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867666,0.00005669664,0.00038746433,0.0001952741,0.0003938799,0.00029002604],"domain_scores_gemma":[0.99869835,0.00002424841,0.00028869693,0.00025374437,0.0005546594,0.00018032448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004898872,0.000116536925,0.00017443778,0.000090156995,0.00009814673,0.00011519393,0.00079552055,0.00005860815,0.000011593196],"category_scores_gemma":[0.000051740608,0.00010627619,0.00008397487,0.0003604007,0.000029311273,0.0007619506,0.00013639317,0.00010207092,0.0000023530758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039645944,0.00011263644,0.000032584812,0.0000063312636,0.000013210095,0.00002282734,0.00012527598,0.85196054,0.000021300151,0.00043143737,0.000023376313,0.14721084],"study_design_scores_gemma":[0.0006766836,0.0005888333,0.00039546864,0.000023239356,0.0000067818632,0.00022971828,0.000035314584,0.9973371,0.00016638821,0.00035898146,0.000069928414,0.00011154614],"about_ca_topic_score_codex":0.000006231558,"about_ca_topic_score_gemma":0.000001031921,"teacher_disagreement_score":0.14709929,"about_ca_system_score_codex":0.0002594272,"about_ca_system_score_gemma":0.00010471941,"threshold_uncertainty_score":0.43338174},"labels":[],"label_agreement":null},{"id":"W2105790475","doi":"10.1109/icpr.2006.88","title":"A K-means-based Algorithm for Projective Clustering","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Cluster analysis; Computer science; Projective test; Algorithm; Artificial intelligence; Mathematics; Pure mathematics","score_opus":0.020212233679205004,"score_gpt":0.30347532922713905,"score_spread":0.28326309554793405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105790475","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":[0.00003745347,0.00003332218,0.9949433,0.00043180285,0.00016470074,0.00063105917,0.000006646662,0.00045354682,0.003298121],"genre_scores_gemma":[0.003343566,7.0991956e-7,0.993447,0.00014026267,0.00015607002,0.00026568756,0.0000049144633,0.000020546886,0.0026212186],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998436,0.000032622,0.00019528685,0.0005024892,0.00031875557,0.00051490177],"domain_scores_gemma":[0.99903184,0.00019937387,0.000046622074,0.0004560851,0.00019796644,0.00006810863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025161603,0.00015253617,0.00014875749,0.00016356308,0.00016779646,0.00016991106,0.00070564094,0.000052980027,0.0000070011743],"category_scores_gemma":[0.000023651228,0.00013937909,0.000080718855,0.00041405478,0.000043557335,0.00038444542,0.0002375185,0.00010661904,0.000022182032],"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":[0.000007874122,0.00008257002,0.000010422246,0.000024475461,0.00000782352,0.000013087523,0.000049749557,0.008558334,0.00039778117,0.0028988512,0.00048117043,0.9874679],"study_design_scores_gemma":[0.00071269757,0.00014443528,0.00008112804,0.000011683757,0.0000014136109,0.000008897931,0.000013363413,0.98527485,0.0054764245,0.0029467803,0.005137862,0.00019047291],"about_ca_topic_score_codex":0.00015543523,"about_ca_topic_score_gemma":0.00005042136,"teacher_disagreement_score":0.9872774,"about_ca_system_score_codex":0.00014128222,"about_ca_system_score_gemma":0.00011673999,"threshold_uncertainty_score":0.5683714},"labels":[],"label_agreement":null},{"id":"W2106899369","doi":"10.1142/s0218001408006922","title":"CLUSTERING QUALITY MEASURES BASED ON COMPARING THE PROXIMITY MATRICES FOR THE MEMBERSHIP VECTORS AND THE OBJECTS","year":2008,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Cluster analysis; Data mining; Pattern recognition (psychology); Rand index; Partition (number theory); Mathematics; Feature vector; Artificial intelligence; Fuzzy clustering; Correlation clustering; Metric (unit); Feature (linguistics); Single-linkage clustering; Computer science; CURE data clustering algorithm; Combinatorics","score_opus":0.2650123592300616,"score_gpt":0.3802203558425662,"score_spread":0.11520799661250458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106899369","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":[0.05405933,0.00014907078,0.93811667,0.006735107,0.0006201108,0.00024893633,0.0000050550198,0.00001328292,0.00005242268],"genre_scores_gemma":[0.99623054,0.00019215581,0.002462429,0.00079468725,0.00028585838,0.000020610765,8.1907336e-7,0.00000603293,0.0000068521085],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998331,0.0002592756,0.00044435242,0.0001719737,0.00063872006,0.00015466697],"domain_scores_gemma":[0.9963726,0.0025825668,0.00032269172,0.00014874998,0.00052028545,0.00005310805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018825327,0.000110333196,0.000146628,0.00009839332,0.0004106798,0.00030961327,0.00079519354,0.000028257913,0.0000075446073],"category_scores_gemma":[0.00062128424,0.000056187087,0.00009062941,0.00011516149,0.00031818246,0.000371182,0.00014333558,0.0002906227,0.0000035864105],"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":[0.0006570618,0.000078829864,0.0007369697,0.000022325525,0.0000976222,0.000019397365,0.0034455787,0.0078097982,0.00014530485,0.00073283503,0.00001520672,0.9862391],"study_design_scores_gemma":[0.0003791025,0.0001257429,0.0022510414,0.0001426477,0.0000144799415,0.00020295315,0.00079062255,0.97661024,0.0059666084,0.013288521,0.00009514498,0.00013290938],"about_ca_topic_score_codex":0.00007577491,"about_ca_topic_score_gemma":0.0000784145,"teacher_disagreement_score":0.98610616,"about_ca_system_score_codex":0.00004030726,"about_ca_system_score_gemma":0.000045182762,"threshold_uncertainty_score":0.31586584},"labels":[],"label_agreement":null},{"id":"W2111253950","doi":"10.1109/dexa.2002.1045928","title":"Clustering Web sessions by sequence alignment","year":2004,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Cluster analysis; Sequence (biology); World Wide Web; Information retrieval; Artificial intelligence","score_opus":0.03441255174344665,"score_gpt":0.32684877228899994,"score_spread":0.2924362205455533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111253950","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":[0.0026512304,0.000045584715,0.98961866,0.0027618199,0.00016711566,0.00013390814,0.0000035338205,0.0003612401,0.0042569367],"genre_scores_gemma":[0.4597847,0.00004730597,0.5365685,0.0005643026,0.000038232356,0.000039547773,0.0000021252374,0.00001467566,0.0029406098],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849546,0.000026129932,0.00016549406,0.0004172812,0.00044643087,0.00044920165],"domain_scores_gemma":[0.9990956,0.000039893148,0.000031144467,0.00059705577,0.00004530078,0.00019100482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015302195,0.00012604454,0.00010449249,0.00006403239,0.00017279814,0.00014059899,0.000995017,0.000041354288,0.000033441404],"category_scores_gemma":[0.00002537599,0.00010926018,0.000034214292,0.00033931207,0.000049740767,0.0005596329,0.0008851156,0.00014769314,0.00018608237],"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":[0.000010290236,0.00035246005,0.00006922535,0.00006180156,0.000058685277,0.00031436805,0.0012964163,0.098307334,0.6608332,0.030292349,0.0052210013,0.20318288],"study_design_scores_gemma":[0.00192169,0.00029740704,0.000073809824,0.0001570168,0.000004143608,0.00024164259,0.0001759664,0.83245325,0.1298522,0.011846814,0.02208252,0.00089352747],"about_ca_topic_score_codex":0.000057382866,"about_ca_topic_score_gemma":0.00001220136,"teacher_disagreement_score":0.73414594,"about_ca_system_score_codex":0.00026369593,"about_ca_system_score_gemma":0.00012310906,"threshold_uncertainty_score":0.44555008},"labels":[],"label_agreement":null},{"id":"W2111596024","doi":"10.1109/tpami.2007.1138","title":"Cumulative Voting Consensus Method for Partitions with Variable Number of Clusters","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":232,"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 Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Categorical variable; Probabilistic logic; Voting; Entropy (arrow of time); Consensus clustering; Data mining; Algorithm; Mathematics; Correlation clustering; Artificial intelligence; CURE data clustering algorithm; Machine learning","score_opus":0.034566888328313325,"score_gpt":0.3610294286362877,"score_spread":0.32646254030797434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111596024","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":[0.0010280998,0.000010440796,0.99834126,0.0001633653,0.00005894132,0.00020943672,0.000045881457,0.000046874422,0.000095705705],"genre_scores_gemma":[0.6322931,0.000005698924,0.3674509,0.00008259188,0.000006479512,0.000018160328,0.000001884175,0.000008189438,0.00013301348],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984789,0.000076721495,0.00039837713,0.00044663285,0.00028045964,0.00031893834],"domain_scores_gemma":[0.9980628,0.001083485,0.00014347935,0.0003385895,0.00024561636,0.00012604479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007467918,0.00016847005,0.0003078692,0.00034028542,0.00021085731,0.00004999258,0.0002716447,0.000050097515,0.000042978227],"category_scores_gemma":[0.000014663677,0.000141651,0.00013287188,0.001294473,0.00009600412,0.00016501702,0.0000074748646,0.000203425,0.000003188],"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":[0.00006891842,0.00015247472,0.00047197216,0.000043805157,0.00070006424,0.000007383599,0.00049378397,0.47374475,0.00035437068,0.0005830588,0.0000017584446,0.52337766],"study_design_scores_gemma":[0.00017123726,0.00014705113,0.00016537515,0.000032284952,0.0002152806,0.000025179523,0.00009869716,0.9163387,0.08211159,0.0004946573,0.000027324995,0.00017263516],"about_ca_topic_score_codex":0.0009647158,"about_ca_topic_score_gemma":0.0007331924,"teacher_disagreement_score":0.631265,"about_ca_system_score_codex":0.000040517414,"about_ca_system_score_gemma":0.000028772694,"threshold_uncertainty_score":0.577636},"labels":[],"label_agreement":null},{"id":"W2111827030","doi":"10.1186/1756-0381-7-7","title":"Semi-supervised consensus clustering for gene expression data analysis","year":2014,"lang":"en","type":"article","venue":"BioData Mining","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Cluster analysis; Computer science; Data mining; Consensus clustering; Computational biology; Expression (computer science); Artificial intelligence; Biology; Correlation clustering; CURE data clustering algorithm","score_opus":0.10870116120127883,"score_gpt":0.350048260191916,"score_spread":0.24134709899063717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111827030","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":[0.009160727,0.00009615543,0.98954815,0.00029908068,0.00021241573,0.00019267082,0.00019287046,0.0001903047,0.00010763375],"genre_scores_gemma":[0.100251526,0.000008777801,0.8988735,0.000102494276,0.00016945071,0.000026265225,0.00039335602,0.000019435933,0.00015516976],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975791,0.00011049992,0.00032733305,0.0010838093,0.0003712849,0.0005279975],"domain_scores_gemma":[0.9956253,0.0006040205,0.0001127965,0.0033836307,0.00010081248,0.00017341977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010748924,0.00018652648,0.00030423436,0.00028189865,0.00027555652,0.00028352565,0.0032198285,0.00007660229,0.000009857924],"category_scores_gemma":[0.00063049985,0.00017847959,0.00006704203,0.00076485926,0.000054739427,0.00055216544,0.0039583724,0.000107037326,0.000014821318],"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":[0.0001242456,0.00013840171,0.0022234092,0.0002391892,0.0006212818,0.000048752372,0.0015851946,0.017231265,0.23725398,0.00023383195,0.0066864477,0.733614],"study_design_scores_gemma":[0.0004974369,0.00004901356,0.00019217124,0.00003076276,0.000039380524,0.000009660277,0.000063021114,0.98215234,0.009976949,0.000034052187,0.0067231623,0.00023204969],"about_ca_topic_score_codex":0.000024657864,"about_ca_topic_score_gemma":0.000017973636,"teacher_disagreement_score":0.96492106,"about_ca_system_score_codex":0.00003882491,"about_ca_system_score_gemma":0.000049171987,"threshold_uncertainty_score":0.72781867},"labels":[],"label_agreement":null},{"id":"W2112317819","doi":"10.1109/apccas.2008.4746001","title":"Cluster validation for subspace clustering on high dimensional data","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"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; Subspace topology; Computer science; Clustering high-dimensional data; Cluster (spacecraft); Data mining; k-medians clustering; Correlation clustering; Single-linkage clustering; Fuzzy clustering; CURE data clustering algorithm; Pattern recognition (psychology); Determining the number of clusters in a data set; Artificial intelligence","score_opus":0.11038308959026868,"score_gpt":0.3447051931064546,"score_spread":0.2343221035161859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112317819","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":[0.0115690045,0.00001025613,0.98431504,0.0027217856,0.00039943095,0.00036318504,0.00001610059,0.00022169341,0.0003835024],"genre_scores_gemma":[0.26510778,0.000009877869,0.72925884,0.00057483325,0.00020756066,0.000046791924,0.00009155446,0.000026641936,0.0046761124],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981215,0.000049978364,0.00019683044,0.00070853945,0.00052296085,0.0004002064],"domain_scores_gemma":[0.99777603,0.00039090804,0.00005359715,0.0015361485,0.00012764147,0.000115675786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035772618,0.00014932179,0.00014573232,0.00012085238,0.0002990774,0.000082313054,0.0015320851,0.000055853954,0.000019165715],"category_scores_gemma":[0.00015549011,0.00013126146,0.000033051045,0.00023655401,0.0000479587,0.00095467456,0.0016204753,0.00013235451,0.00010371983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078064785,0.0010475079,0.0004202239,0.00025964098,0.00021955458,0.0002445023,0.0015788286,0.5261884,0.011039403,0.042686533,0.12204335,0.29349142],"study_design_scores_gemma":[0.00077757525,0.00015400379,0.0004184136,0.000015669324,0.0000016698773,0.00006153249,0.000004273056,0.9887448,0.0052960655,0.00066117215,0.0036637844,0.00020101643],"about_ca_topic_score_codex":0.000033756198,"about_ca_topic_score_gemma":0.000009334396,"teacher_disagreement_score":0.46255642,"about_ca_system_score_codex":0.000076507305,"about_ca_system_score_gemma":0.00006848165,"threshold_uncertainty_score":0.53526866},"labels":[],"label_agreement":null},{"id":"W2113334100","doi":"10.1016/j.jbi.2008.11.004","title":"Efficient layered density-based clustering of categorical data","year":2008,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Cluster analysis; Computer science; Categorical variable; Data mining; Scalability; CURE data clustering algorithm; Single-linkage clustering; Clustering high-dimensional data; Correlation clustering; Artificial intelligence; Pattern recognition (psychology); Machine learning; Database","score_opus":0.06798969841812494,"score_gpt":0.32353461207813417,"score_spread":0.2555449136600092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113334100","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":[0.025726417,0.000040481078,0.9732424,0.00046912747,0.00036659013,0.000063032814,0.0000057133852,0.000020555206,0.00006570068],"genre_scores_gemma":[0.49097902,0.000022218741,0.50875497,0.00013278311,0.0000907018,4.0439286e-7,0.0000041847024,0.00000587634,0.0000098485025],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968574,0.000052269203,0.0011908094,0.00009278053,0.0014945756,0.00031218198],"domain_scores_gemma":[0.997626,0.0002785158,0.00062564795,0.000755262,0.0003777258,0.00033682867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010857953,0.00011748471,0.0003530254,0.00037142812,0.00009293487,0.00003470117,0.0022869785,0.00009028076,0.000006971892],"category_scores_gemma":[0.000498022,0.00008895771,0.000078255245,0.0006715061,0.000272501,0.00037591136,0.0011200197,0.00042562804,0.000011439307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045458626,0.0031082185,0.00057855085,0.0019315012,0.00048980635,0.0032034162,0.015012785,0.6147596,0.004797563,0.001083358,0.016798517,0.33778206],"study_design_scores_gemma":[0.0007737466,0.00028031194,0.00018750648,0.00005505968,0.0000050504004,0.0010030534,0.000075003736,0.9949704,0.00057575194,0.000051320436,0.0019314873,0.00009134017],"about_ca_topic_score_codex":0.0000053634126,"about_ca_topic_score_gemma":4.1687665e-7,"teacher_disagreement_score":0.4652526,"about_ca_system_score_codex":0.00009531719,"about_ca_system_score_gemma":0.00050813187,"threshold_uncertainty_score":0.4249813},"labels":[],"label_agreement":null},{"id":"W2113439791","doi":"10.5539/cis.v4n3p88","title":"A Genetic K-means Clustering Algorithm Based on the Optimized Initial Centers","year":2011,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Cluster analysis; Cluster (spacecraft); Convergence (economics); Algorithm; Genetic algorithm; k-medoids; k-medians clustering; CURE data clustering algorithm; Correlation clustering; Artificial intelligence; Machine learning","score_opus":0.035164000121881894,"score_gpt":0.2771619605297209,"score_spread":0.24199796040783902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113439791","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":[0.0009213651,0.0000031951429,0.99469227,0.00033564155,0.0004198047,0.00022117543,0.000002194424,0.00010507261,0.0032992747],"genre_scores_gemma":[0.12382806,0.000008752688,0.87362707,0.0024568217,0.00004607309,0.000022257951,7.5174233e-7,0.0000039538095,0.000006272042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842745,0.000047673107,0.0002650601,0.00025267582,0.00062930805,0.00037781644],"domain_scores_gemma":[0.9989331,0.000103507045,0.00008760461,0.00053048163,0.00019175964,0.00015359308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000662895,0.00013128766,0.000101219855,0.00032444962,0.00048445046,0.0005863393,0.0014222674,0.000026271102,0.000013062846],"category_scores_gemma":[0.00004319386,0.00009278593,0.0000316838,0.0007756351,0.00037147445,0.004316821,0.00073986495,0.00015524281,0.000046507816],"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":[0.000016227586,0.000028057475,0.000029502435,0.000013149752,0.0000037108073,0.0000059390572,0.0039181695,0.029027391,0.000016713777,0.002291468,0.000096622585,0.96455306],"study_design_scores_gemma":[0.00038198475,0.00014009385,0.003285145,0.000022624794,7.519964e-7,0.000022623573,0.000036229212,0.9950224,0.00027667347,0.00011228829,0.0005774072,0.00012177776],"about_ca_topic_score_codex":0.000011677524,"about_ca_topic_score_gemma":2.034538e-7,"teacher_disagreement_score":0.965995,"about_ca_system_score_codex":0.00005398346,"about_ca_system_score_gemma":0.0001157714,"threshold_uncertainty_score":0.56540835},"labels":[],"label_agreement":null},{"id":"W2113755034","doi":"10.1145/1569901.1570232","title":"Evolutionary clustering with arbitrary subspaces","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Linear subspace; Subspace topology; Computer science; Correlation clustering; Canopy clustering algorithm; Set (abstract data type); Constrained clustering; CURE data clustering algorithm; Evolutionary algorithm; Algorithm; Data mining; Mathematics; Mathematical optimization; Theoretical computer science; Artificial intelligence","score_opus":0.012674477805760215,"score_gpt":0.2639241954487666,"score_spread":0.2512497176430064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113755034","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":[0.003983485,0.00011953003,0.97195137,0.002875761,0.00005167632,0.00010387817,3.1594487e-7,0.00044033065,0.020473668],"genre_scores_gemma":[0.35543245,0.000011844607,0.642129,0.00045480859,0.000052930438,0.000006087525,7.5099337e-7,0.0000062957415,0.0019058126],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880654,0.000024725063,0.00010287431,0.00033941018,0.00036909967,0.00035734815],"domain_scores_gemma":[0.9992869,0.00004253211,0.000025280571,0.00046883064,0.00006079163,0.000115696035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000089880086,0.0001132898,0.00009959329,0.00010436306,0.00012359812,0.00010037549,0.0006747966,0.000030694566,0.000017527953],"category_scores_gemma":[0.000009715063,0.0000870455,0.000023376675,0.00041846803,0.00003870723,0.0008405353,0.00017779879,0.00015217479,0.00005071105],"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":[0.00017757599,0.0005041892,0.0015967013,0.00006392654,0.00007539919,0.0011018219,0.0015151404,0.036616392,0.0065086437,0.12215969,0.0040683993,0.8256121],"study_design_scores_gemma":[0.00064520084,0.00073935685,0.02491096,0.00004946184,0.0000020565933,0.0003993792,0.00006684585,0.956364,0.0023157862,0.010958539,0.0030902675,0.00045818044],"about_ca_topic_score_codex":0.000010928121,"about_ca_topic_score_gemma":0.0000073932897,"teacher_disagreement_score":0.9197476,"about_ca_system_score_codex":0.000054917928,"about_ca_system_score_gemma":0.000060539045,"threshold_uncertainty_score":0.35496122},"labels":[],"label_agreement":null},{"id":"W2114217619","doi":"10.1109/nnsp.1997.622414","title":"An improved scheme for the fuzzifier in fuzzy clustering","year":2002,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Fuzzy clustering; Data mining; Computer science; Correlation clustering; Fuzzy set; Embedding; Constrained clustering; Scheme (mathematics); Probabilistic logic; Fuzzy logic; Artificial intelligence; CURE data clustering algorithm; Mathematics","score_opus":0.04832545442196626,"score_gpt":0.31937943448412687,"score_spread":0.27105398006216064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114217619","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":[0.0014518753,0.00010344458,0.9942025,0.0016771735,0.00017208907,0.0004051205,8.5243903e-7,0.00014058656,0.0018463392],"genre_scores_gemma":[0.3649817,0.0000284516,0.63075626,0.0004531062,0.00013896152,0.00021528226,5.6064636e-7,0.000021787191,0.0034038604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998786,0.000030073294,0.0001741949,0.00037122614,0.00018421884,0.00045428518],"domain_scores_gemma":[0.99881756,0.00021411313,0.000027569333,0.0007985859,0.000060106104,0.00008206214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035483684,0.000108117456,0.000102240694,0.000085267115,0.00014038461,0.00019101208,0.0012881911,0.00004534372,0.000030938612],"category_scores_gemma":[0.00006032274,0.0000757459,0.000038263446,0.00034571183,0.00003800787,0.00063164014,0.00034334627,0.0001660574,0.000028386245],"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":[0.000018693916,0.00015742387,0.00014516672,0.000036342102,0.000017066983,0.000012389941,0.0014200379,0.0072157467,0.015551171,0.0050642323,0.00046752585,0.96989423],"study_design_scores_gemma":[0.0004110328,0.00008853725,0.00027819662,0.000004884129,4.8743743e-7,0.0000068720283,0.000060974926,0.99547136,0.0007194966,0.00075817056,0.0020839386,0.00011604038],"about_ca_topic_score_codex":0.000046574532,"about_ca_topic_score_gemma":0.00010677345,"teacher_disagreement_score":0.9882556,"about_ca_system_score_codex":0.000058226487,"about_ca_system_score_gemma":0.000012191789,"threshold_uncertainty_score":0.3088828},"labels":[],"label_agreement":null},{"id":"W2114848212","doi":"10.1016/j.neucom.2011.08.032","title":"Clustering in applications with multiple data sources—A mutual subspace clustering approach","year":2012,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":10,"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":"Linear subspace; Cluster analysis; Computer science; Subspace topology; Data mining; Clustering high-dimensional data; Set (abstract data type); Data set; Data point; Correlation clustering; Pattern recognition (psychology); Cluster (spacecraft); Artificial intelligence; Mathematics","score_opus":0.057235792663626425,"score_gpt":0.30596122055709757,"score_spread":0.24872542789347113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114848212","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":[0.025629967,0.000116281655,0.9721922,0.00010811977,0.000112081354,0.00064402627,0.0000031850077,0.00038609566,0.0008080104],"genre_scores_gemma":[0.5798779,0.0000031292814,0.41964597,0.0000754276,0.00025226013,0.000057776182,0.000010391897,0.000036118567,0.000041012503],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99686337,0.00014647386,0.0003635562,0.00096750824,0.0005277414,0.0011313554],"domain_scores_gemma":[0.9973462,0.00038186955,0.0001453312,0.0018162066,0.00005481131,0.0002555351],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00075398025,0.00028188096,0.00027225658,0.00026067498,0.0003080818,0.0002494898,0.0026988871,0.00007170415,0.0000012306616],"category_scores_gemma":[0.00007535075,0.0002743519,0.000029223926,0.0010844282,0.000069487585,0.0014063665,0.004821718,0.0005978474,0.000029550623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005199541,0.00057729724,0.07012197,0.0003602654,0.000035676872,0.00005184106,0.0053352215,0.5006472,0.002269094,0.00027762874,0.000046380792,0.42022547],"study_design_scores_gemma":[0.0005987711,0.000033256867,0.007887048,0.000040554656,0.00000275822,0.00018583245,0.00016541856,0.9887819,0.00015289705,0.0000058244955,0.0018412933,0.00030439688],"about_ca_topic_score_codex":0.000048492195,"about_ca_topic_score_gemma":0.000049097085,"teacher_disagreement_score":0.554248,"about_ca_system_score_codex":0.00010226421,"about_ca_system_score_gemma":0.000051655483,"threshold_uncertainty_score":0.99997085},"labels":[],"label_agreement":null},{"id":"W2117544284","doi":"10.1145/375663.375672","title":"Data bubbles","year":2001,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cluster analysis; Computer science; CURE data clustering algorithm; Canopy clustering algorithm; Data mining; Data stream clustering; Correlation clustering; Hierarchical clustering; Data compression; Data set; Set (abstract data type); Fuzzy clustering; Constrained clustering; Determining the number of clusters in a data set; Artificial intelligence","score_opus":0.12925317243936482,"score_gpt":0.3804818146787029,"score_spread":0.25122864223933805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117544284","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":[0.0004195057,0.000048356575,0.9748729,0.0014947699,0.00008277842,0.00003670061,0.0000016881523,0.000224812,0.022818511],"genre_scores_gemma":[0.040980216,0.00008687309,0.94302744,0.00033568995,0.00010206887,0.000004337301,0.0000072142348,0.00000793113,0.015448245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919796,0.000014911109,0.00006794193,0.00029758015,0.00021124243,0.00021034996],"domain_scores_gemma":[0.99831104,0.00004799094,0.000010019657,0.0015351702,0.000030297148,0.00006547646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016048992,0.000045800123,0.000046823712,0.000040367006,0.0000530497,0.00009837045,0.0025731917,0.000014770303,0.000059905273],"category_scores_gemma":[0.00004622868,0.00003801651,0.0000071659388,0.00027626564,0.000019820349,0.0007834401,0.0020748707,0.00006208274,0.00030767533],"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":[0.0000022187337,0.000038960545,0.00028572624,0.0000038078092,0.0000072561024,0.000121592806,0.000045736404,0.00026032192,0.00045550996,0.023197936,0.008227439,0.9673535],"study_design_scores_gemma":[0.00012245926,0.000020220818,0.0005414826,0.0000031456889,3.39351e-7,0.0000781798,0.000011227818,0.72631633,0.00028843177,0.0036396221,0.26888064,0.0000978971],"about_ca_topic_score_codex":0.000021995776,"about_ca_topic_score_gemma":0.000015578582,"teacher_disagreement_score":0.9672556,"about_ca_system_score_codex":0.000013495107,"about_ca_system_score_gemma":0.000025511334,"threshold_uncertainty_score":0.47816733},"labels":[],"label_agreement":null},{"id":"W2118001196","doi":"10.1145/2464576.2464653","title":"Flat vs. symbiotic evolutionary subspace clusterings","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Subspace topology; Cluster analysis; Cluster (spacecraft); Computer science; Representation (politics); Space (punctuation); Property (philosophy); Artificial intelligence; Pattern recognition (psychology); Mathematics; Data mining","score_opus":0.011335472641119722,"score_gpt":0.24955873640691234,"score_spread":0.23822326376579261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118001196","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":[0.013476784,0.00009493712,0.9682619,0.005211052,0.00037476906,0.00037528263,8.179861e-7,0.0006834958,0.011520964],"genre_scores_gemma":[0.54472893,0.00002228168,0.42337784,0.00063783943,0.00011268768,0.0000676184,0.0000031287686,0.00002632801,0.031023344],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983483,0.00004349289,0.00017663503,0.00045093754,0.00043394632,0.00054671225],"domain_scores_gemma":[0.9987822,0.000104282044,0.000035848967,0.0007379684,0.00012993283,0.00020977865],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000116252864,0.0001506271,0.00013947798,0.0001250489,0.00015021453,0.00022400099,0.0011069376,0.000064099324,0.00033830368],"category_scores_gemma":[0.000041440006,0.00013398567,0.000038972565,0.00039342346,0.00007448905,0.0012702253,0.0010860137,0.00019253352,0.0030424863],"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":[0.0000611153,0.00051596947,0.00480839,0.0005113739,0.00022070536,0.00036997715,0.0031138898,0.010049073,0.09990596,0.2101872,0.21124363,0.45901275],"study_design_scores_gemma":[0.0004025208,0.0001709306,0.01220225,0.000023670658,0.0000018224853,0.00014592016,0.0000568411,0.966202,0.0029552456,0.005113998,0.012295211,0.0004295857],"about_ca_topic_score_codex":0.00023496822,"about_ca_topic_score_gemma":0.000004027986,"teacher_disagreement_score":0.9561529,"about_ca_system_score_codex":0.0001317192,"about_ca_system_score_gemma":0.000052446154,"threshold_uncertainty_score":0.9977338},"labels":[],"label_agreement":null},{"id":"W2118013824","doi":"10.1007/s10115-010-0367-z","title":"Statistical semantics for enhancing document clustering","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":35,"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 Waterloo","funders":"","keywords":"Semantic similarity; Computer science; Cluster analysis; Document clustering; Similarity (geometry); Vector space model; Explicit semantic analysis; Semantics (computer science); Representation (politics); Benchmark (surveying); Context (archaeology); Artificial intelligence; Information retrieval; Distributional semantics; Data mining; Natural language processing; Semantic computing; Semantic technology; Semantic Web","score_opus":0.012131819968422273,"score_gpt":0.3032534578081119,"score_spread":0.29112163783968964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118013824","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":[0.0013238626,0.000054168762,0.9943241,0.00007007845,0.0011739304,0.00037061237,0.000006977087,0.000093411414,0.0025828967],"genre_scores_gemma":[0.8967787,0.000019171086,0.10235521,0.00003892464,0.00022022243,0.00013908125,0.000014138799,0.000007988332,0.00042658744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991048,0.000019729408,0.00034423478,0.00012377354,0.00016583475,0.00024163265],"domain_scores_gemma":[0.9991529,0.00018624391,0.00007727305,0.00024257849,0.00022995948,0.00011105931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000537654,0.00009313502,0.0001294619,0.00011989107,0.00017353744,0.00046499373,0.0002491954,0.000056958997,0.0000021586357],"category_scores_gemma":[0.00012047925,0.00008362466,0.00001741457,0.00011960101,0.000026468455,0.0024741609,0.00022686127,0.00013390738,0.00007456307],"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":[0.00001982205,0.000036683417,0.00011393069,0.0020168263,0.000037517526,0.0000022007778,0.010729343,0.0009884767,0.0032402375,0.53394,0.0014741666,0.44740078],"study_design_scores_gemma":[0.00039161573,0.00006480171,0.00015884021,0.00004177726,0.0000019512665,0.000039675404,0.00017182526,0.82432014,0.00059765007,0.0002712749,0.17380065,0.00013980485],"about_ca_topic_score_codex":0.00000824185,"about_ca_topic_score_gemma":0.000030395173,"teacher_disagreement_score":0.8954548,"about_ca_system_score_codex":0.0000307707,"about_ca_system_score_gemma":0.00005157014,"threshold_uncertainty_score":0.4483945},"labels":[],"label_agreement":null},{"id":"W2120468118","doi":"10.1007/978-3-540-71701-0_5","title":"Hierarchical Density-Based Clustering of Categorical Data and a Simplification","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","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":"York University","funders":"","keywords":"Categorical variable; Cluster analysis; Data mining; Computer science; CURE data clustering algorithm; Outlier; Pattern recognition (psychology); Basis (linear algebra); Hierarchical clustering; Single-linkage clustering; Canopy clustering algorithm; Artificial intelligence; Correlation clustering; Algorithm; Mathematics; Machine learning","score_opus":0.06047806953614623,"score_gpt":0.33107722062942646,"score_spread":0.27059915109328025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120468118","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":[0.000081263504,0.00018355127,0.99819165,0.00051280303,0.00036983326,0.0003055176,0.00000871827,0.000088486384,0.0002581885],"genre_scores_gemma":[0.13324249,0.000026553666,0.8661403,0.0003188263,0.00018337203,0.0000028393174,0.000016175161,0.000028116707,0.000041357307],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957656,0.000043765318,0.00056305673,0.0017626712,0.0012366539,0.0006282444],"domain_scores_gemma":[0.99561757,0.0010060628,0.00023703648,0.0026284482,0.0002732165,0.00023764434],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016141763,0.00036757943,0.0004881524,0.00096369296,0.00017647137,0.00024232583,0.004508063,0.00028105694,0.0000032817716],"category_scores_gemma":[0.00024887815,0.00035215684,0.00004692233,0.0006679747,0.0011091814,0.00050046196,0.005065698,0.00097009505,0.000005550558],"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":[0.000014859384,0.000028465307,0.000052537293,0.0001040887,0.0000067552137,0.000104724786,0.00020837545,0.031105468,0.0003313581,0.004207722,0.0000023849916,0.9638333],"study_design_scores_gemma":[0.00022884122,0.000122113,0.0002145267,0.00013322504,0.0000039730157,0.00008918608,9.898193e-8,0.96800274,0.00080469955,0.029782988,0.00028590218,0.00033173105],"about_ca_topic_score_codex":0.00002834072,"about_ca_topic_score_gemma":0.00007622712,"teacher_disagreement_score":0.9635015,"about_ca_system_score_codex":0.000226753,"about_ca_system_score_gemma":0.00054589583,"threshold_uncertainty_score":0.99989307},"labels":[],"label_agreement":null},{"id":"W2120498775","doi":"10.1109/icsmc.2007.4413889","title":"Hard-fuzzy clustering: A cooperative approach","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":11,"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 Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Fuzzy clustering; Correlation clustering; CURE data clustering algorithm; Data mining; Canopy clustering algorithm; Data stream clustering; Clustering high-dimensional data; Artificial intelligence; Single-linkage clustering; Fuzzy logic; Consensus clustering; Machine learning","score_opus":0.04187945832137895,"score_gpt":0.3151919733077678,"score_spread":0.27331251498638887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120498775","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":[0.0012032704,0.000030444942,0.89636683,0.00022869877,0.00014456984,0.00018881752,5.045134e-7,0.00034507472,0.10149179],"genre_scores_gemma":[0.13905366,0.000004750815,0.8474678,0.0003267002,0.000096626085,0.000016873493,0.0000015317722,0.000015604508,0.013016492],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982174,0.00003939201,0.0002149173,0.00050565845,0.00043397615,0.00058863184],"domain_scores_gemma":[0.99885786,0.00011031281,0.000033458025,0.000640611,0.00015371428,0.00020402428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007005606,0.00015018349,0.0001514408,0.00014847721,0.00015830252,0.00018330348,0.001045883,0.00006022811,0.00001790121],"category_scores_gemma":[0.00006751038,0.00012700686,0.000043794647,0.0006380028,0.00007143891,0.0005531519,0.00080177194,0.00023375417,0.0001537929],"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":[0.00011077791,0.00071519165,0.0002741394,0.00012061413,0.00013304828,0.000603144,0.006155076,0.036816142,0.021729521,0.19365756,0.0036950107,0.73598975],"study_design_scores_gemma":[0.0009574186,0.0002544638,0.0025190262,0.000015709347,0.0000022277998,0.00030473288,0.00037394874,0.9711228,0.011620672,0.0019165726,0.010312324,0.0006001247],"about_ca_topic_score_codex":0.000023076227,"about_ca_topic_score_gemma":0.000008952436,"teacher_disagreement_score":0.9343066,"about_ca_system_score_codex":0.00010062848,"about_ca_system_score_gemma":0.00005493549,"threshold_uncertainty_score":0.51791894},"labels":[],"label_agreement":null},{"id":"W2122129637","doi":"10.1109/icmlc.2004.1382092","title":"A new efficient validity index for fuzzy clustering","year":2005,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Index (typography); Computer science; Cluster analysis; Fuzzy logic; Fuzzy clustering; Fuzzy set; Data mining; Artificial intelligence; World Wide Web","score_opus":0.05092293168649851,"score_gpt":0.3326614497502807,"score_spread":0.2817385180637822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122129637","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":[0.0013635738,0.00002471657,0.9926153,0.0018626,0.00022920553,0.00031584414,0.0000010676002,0.00031945892,0.0032682377],"genre_scores_gemma":[0.19993402,0.0000022175884,0.79412454,0.00021855769,0.00031080013,0.000030454119,5.8603337e-7,0.000013485761,0.005365351],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984974,0.0000237683,0.00019092765,0.00042940426,0.00035907526,0.0004993865],"domain_scores_gemma":[0.9989468,0.00015076122,0.000037894995,0.00056173955,0.000084032974,0.00021880904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031320893,0.00012806756,0.00013252802,0.00011019972,0.00013376014,0.00016771139,0.00092713255,0.00005002086,0.000026686219],"category_scores_gemma":[0.0000696201,0.00011658895,0.00006990972,0.00029016964,0.000017624585,0.00028359352,0.0006811937,0.000120932746,0.000092690454],"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":[0.000017382938,0.000051487947,0.000032879805,0.000021088048,0.000008623927,0.0000036346419,0.00032275936,0.21195966,0.000535804,0.0049915537,0.002075094,0.77998],"study_design_scores_gemma":[0.0005693613,0.00007098518,0.0002190323,0.000008536172,9.695459e-7,0.000014374147,0.000009695449,0.97552913,0.0024189348,0.0010594534,0.019940581,0.00015894648],"about_ca_topic_score_codex":0.000036947025,"about_ca_topic_score_gemma":0.000040127616,"teacher_disagreement_score":0.7798211,"about_ca_system_score_codex":0.00014294934,"about_ca_system_score_gemma":0.00010608359,"threshold_uncertainty_score":0.4754359},"labels":[],"label_agreement":null},{"id":"W2126636333","doi":"10.1109/ictai.2005.57","title":"Determining the optimal number of clusters using a new evolutionary algorithm","year":2005,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Evolutionary algorithm; Cluster analysis; Benchmark (surveying); Computer science; Determining the number of clusters in a data set; Algorithm; Entropy (arrow of time); Evolutionary computation; Set (abstract data type); Cluster (spacecraft); Fitness function; Genetic algorithm; Data mining; Mathematical optimization; Mathematics; Artificial intelligence; Machine learning; Correlation clustering; Canopy clustering algorithm","score_opus":0.03369832156042135,"score_gpt":0.33716241651616463,"score_spread":0.3034640949557433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126636333","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":[0.013874084,0.00003533847,0.98403096,0.00064869475,0.0001100466,0.00012138639,0.0000011027884,0.00008139229,0.0010969695],"genre_scores_gemma":[0.0391091,0.000004130322,0.9589936,0.00016424607,0.00018037006,0.0000024884487,5.1474655e-7,0.000011754796,0.0015337735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985678,0.00005464618,0.00024816644,0.00028972994,0.00046786343,0.00037178633],"domain_scores_gemma":[0.9990497,0.00013764383,0.000063701315,0.0005185334,0.00011753185,0.00011284283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019966047,0.00012310894,0.00013344605,0.00006346975,0.0001359104,0.00006340505,0.0010161592,0.000044654815,0.00006136668],"category_scores_gemma":[0.000039043494,0.00009084079,0.00006751037,0.00038022108,0.0000937842,0.0007234075,0.00078904163,0.00016568863,0.00005853514],"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":[0.0000045774395,0.00004885811,0.00038006343,0.0000059577937,0.000021781669,0.0000061009514,0.0006148814,0.08417705,0.00016691732,0.00065444247,0.000577811,0.9133416],"study_design_scores_gemma":[0.00032908068,0.000024357054,0.0007508644,0.00001369469,0.0000027719148,0.00009212124,0.000041851243,0.9963628,0.0005357285,0.00014891979,0.001581934,0.00011585715],"about_ca_topic_score_codex":0.00007902375,"about_ca_topic_score_gemma":0.0000035594264,"teacher_disagreement_score":0.9132257,"about_ca_system_score_codex":0.00012649407,"about_ca_system_score_gemma":0.00018116494,"threshold_uncertainty_score":0.37043798},"labels":[],"label_agreement":null},{"id":"W2127033147","doi":"10.1109/cidm.2009.4938666","title":"Fuzzy p-mode prototypes: A generalization of frequency-based cluster prototypes for clustering categorical objects","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Fuzzy clustering; Cluster analysis; Categorical variable; Pattern recognition (psychology); FLAME clustering; Fuzzy logic; Generalization; Fuzzy set; Artificial intelligence; Mathematics; Data mining; Computer science; Feature (linguistics); CURE data clustering algorithm; Machine learning","score_opus":0.02177035882438115,"score_gpt":0.32354277869719095,"score_spread":0.3017724198728098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127033147","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":[0.0012230928,0.000030428368,0.99204755,0.00094418507,0.00010476132,0.0038311416,0.0000046022856,0.0002588176,0.0015553934],"genre_scores_gemma":[0.40229684,0.0000027235762,0.5962121,0.00036502324,0.00008227321,0.0007795805,0.000011148296,0.000019482635,0.00023082005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978957,0.000083446495,0.00044153308,0.0005718893,0.00047750527,0.0005299054],"domain_scores_gemma":[0.9985679,0.00010772351,0.00013595207,0.00066710025,0.0003883917,0.00013292771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003203317,0.00022504097,0.00028929653,0.0002309058,0.00012780755,0.00010374274,0.0008460716,0.000120764904,0.000006207383],"category_scores_gemma":[0.00013401789,0.00019567127,0.00010657372,0.0005894117,0.000048571557,0.0005178457,0.00012658518,0.00013743142,0.000007978972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008342315,0.0016778838,0.0006675163,0.0020633566,0.00013017596,0.000055193203,0.00356889,0.4079024,0.154763,0.19000112,0.0010886462,0.23724762],"study_design_scores_gemma":[0.0011795498,0.0008532956,0.00018338433,0.00004550654,0.000004965582,0.000010147718,0.000010451152,0.9203085,0.0449879,0.03192241,0.00020227933,0.00029163476],"about_ca_topic_score_codex":0.000057835317,"about_ca_topic_score_gemma":0.000035892303,"teacher_disagreement_score":0.5124061,"about_ca_system_score_codex":0.00013449269,"about_ca_system_score_gemma":0.00025628097,"threshold_uncertainty_score":0.7979243},"labels":[],"label_agreement":null},{"id":"W2127258367","doi":"10.1109/icdm.2002.1183901","title":"A parameterless method for efficiently discovering clusters of arbitrary shape in large datasets","year":2003,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Correlation clustering; CURE data clustering algorithm; sort; Single-linkage clustering; Data mining; Canopy clustering algorithm; Data stream clustering; Similarity (geometry); Fuzzy clustering; Artificial intelligence; Range (aeronautics); Scalability; Pattern recognition (psychology); Database","score_opus":0.02762599778356411,"score_gpt":0.35514079866748477,"score_spread":0.32751480088392065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127258367","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":[0.015005129,0.000051033105,0.9838004,0.00007322934,0.00011635482,0.00041900182,0.00008716302,0.000043883898,0.00040376894],"genre_scores_gemma":[0.13244419,0.0000039575516,0.8672532,0.00013394743,0.0000067447677,0.000058299076,0.000015917,0.000013701876,0.00007005052],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815845,0.00014656052,0.00033251918,0.00050566305,0.0003049691,0.00055181433],"domain_scores_gemma":[0.9985643,0.0005662118,0.00007292553,0.00066748355,0.000037180605,0.00009191655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010955512,0.00014297316,0.00025488966,0.00021541717,0.0000533415,0.00006858192,0.00085376465,0.00004920678,0.000010943387],"category_scores_gemma":[0.00023281379,0.00013003022,0.00006718824,0.0005769821,0.000031382486,0.0005196782,0.00039054605,0.00015029714,0.0000036618796],"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":[0.00037207708,0.0031012692,0.0023496824,0.0017811093,0.00021443809,0.0002686478,0.0070791836,0.13159908,0.02021003,0.35934633,0.0009116517,0.4727665],"study_design_scores_gemma":[0.0010716774,0.00009985048,0.0002032552,0.00003864512,0.0000020227633,0.000012860618,0.0001345152,0.98282737,0.012504096,0.001552849,0.0013732916,0.00017955218],"about_ca_topic_score_codex":0.000030302439,"about_ca_topic_score_gemma":0.000033259486,"teacher_disagreement_score":0.8512283,"about_ca_system_score_codex":0.00005751075,"about_ca_system_score_gemma":0.00007480783,"threshold_uncertainty_score":0.53024787},"labels":[],"label_agreement":null},{"id":"W2129184179","doi":"10.1109/ictai.2008.62","title":"An Empirical Analysis on the Stability of Clustering Algorithms","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Cluster analysis; Computer science; Stability (learning theory); CURE data clustering algorithm; Correlation clustering; Canopy clustering algorithm; Data mining; Scalability; Machine learning; Artificial intelligence; Unsupervised learning; Selection (genetic algorithm); Algorithm","score_opus":0.0953566139620425,"score_gpt":0.3693955361560635,"score_spread":0.27403892219402104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129184179","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":[0.18751784,0.000005975997,0.8107523,0.0006122432,0.000036835176,0.00010163778,0.0000019541046,0.00009656435,0.0008746657],"genre_scores_gemma":[0.88520926,0.0000057236502,0.114495456,0.00016480264,0.000024351697,0.00001105386,8.854851e-7,0.0000057922416,0.000082679784],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981286,0.0002167909,0.00026193386,0.0004513911,0.00063708716,0.00030420744],"domain_scores_gemma":[0.997762,0.0004072998,0.00005808212,0.0015014842,0.00014919827,0.0001218953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062096183,0.00011883353,0.00022673314,0.00017329559,0.00019466759,0.00003876086,0.0013599988,0.00004241785,0.0000915754],"category_scores_gemma":[0.00009738801,0.00007470486,0.00012549791,0.0016386495,0.00017811182,0.00030251764,0.00039771653,0.00019057198,0.000015799753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002912586,0.004984102,0.20983298,0.00013562005,0.002324138,0.0004437278,0.031751536,0.38798848,0.01831321,0.012225685,0.0010665721,0.3306427],"study_design_scores_gemma":[0.00009401955,0.00017781275,0.02828604,0.0000018472037,0.000006819369,0.00000790349,0.00007349451,0.9624072,0.008629775,0.00016849757,0.00004869863,0.00009793289],"about_ca_topic_score_codex":0.000082420054,"about_ca_topic_score_gemma":0.000047418383,"teacher_disagreement_score":0.69769144,"about_ca_system_score_codex":0.00006309057,"about_ca_system_score_gemma":0.00005795633,"threshold_uncertainty_score":0.30463758},"labels":[],"label_agreement":null},{"id":"W2129192715","doi":"10.1109/foci.2007.371525","title":"Likelihood Based Fuzzy Clustering for Data Sets of Mixed Features","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","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":"Thompson Rivers University","funders":"","keywords":"Fuzzy clustering; Cluster analysis; FLAME clustering; Correlation clustering; Canopy clustering algorithm; CURE data clustering algorithm; Computer science; Data mining; Data stream clustering; Pattern recognition (psychology); Feature (linguistics); Artificial intelligence; Algorithm; Mathematics","score_opus":0.05533363372637953,"score_gpt":0.35965094907401307,"score_spread":0.3043173153476335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129192715","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":[0.0011794411,0.0000700268,0.996276,0.0004587693,0.00027666494,0.00030100765,0.00002249811,0.00014810942,0.0012674716],"genre_scores_gemma":[0.14465033,0.0000024079716,0.8548551,0.00012211053,0.00005250046,0.000008290047,0.000023701157,0.000015383317,0.00027018998],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982438,0.000026372902,0.000270537,0.0005191953,0.0004036197,0.00053644367],"domain_scores_gemma":[0.997494,0.0004965393,0.00007704057,0.0016332834,0.00016085667,0.00013831981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011578797,0.0001309499,0.00017959566,0.0001667146,0.00008528071,0.000068683934,0.002400926,0.00006620824,0.0000054003626],"category_scores_gemma":[0.00020891863,0.000117143456,0.000046193734,0.00036050827,0.00004404941,0.0004801665,0.0014465144,0.00012413174,0.000005561672],"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":[0.000092642666,0.00013124761,0.00013118665,0.00021026963,0.000033261702,0.000023137402,0.00013427417,0.0015690979,0.009327674,0.0015725674,0.0031967885,0.98357785],"study_design_scores_gemma":[0.001100284,0.00019516062,0.0027022166,0.000044707536,0.0000045292545,0.000015892509,0.000045390505,0.9439315,0.046972062,0.001711337,0.0030242472,0.0002526801],"about_ca_topic_score_codex":0.000049866572,"about_ca_topic_score_gemma":0.00019633703,"teacher_disagreement_score":0.9833252,"about_ca_system_score_codex":0.000039809223,"about_ca_system_score_gemma":0.000090791145,"threshold_uncertainty_score":0.47769716},"labels":[],"label_agreement":null},{"id":"W2129500661","doi":"10.1109/tkde.2008.162","title":"Mining Projected Clusters in High-Dimensional Spaces","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"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; Computer science; Curse of dimensionality; Linear subspace; Outlier; Clustering high-dimensional data; Data mining; CURE data clustering algorithm; Data point; Correlation clustering; Computation; Pattern recognition (psychology); Canopy clustering algorithm; Single-linkage clustering; Algorithm; Artificial intelligence; Mathematics","score_opus":0.03923416376241975,"score_gpt":0.2902071390881266,"score_spread":0.2509729753257069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129500661","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":[0.078350835,0.00016864784,0.92071116,0.00007827223,0.00035839542,0.000118287775,0.00001671544,0.00016877997,0.000028896402],"genre_scores_gemma":[0.86483985,0.00007677724,0.1347946,0.0000128572465,0.00003863903,0.000024136294,0.000008119606,0.00001836168,0.00018665669],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988579,0.000025108617,0.00016783019,0.00047709525,0.00017202593,0.00030005295],"domain_scores_gemma":[0.9990692,0.00016970372,0.000017036058,0.000610294,0.00003472555,0.00009900614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014709024,0.00014903606,0.00015295281,0.00036157656,0.00013051172,0.000044512766,0.0005477946,0.000054011,0.0000037087975],"category_scores_gemma":[0.00001167857,0.00015192889,0.00001649736,0.00056374643,0.000034427132,0.0007464144,0.00003680541,0.00025896032,0.00001544827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052059346,0.0004295947,0.00007480193,0.00017402534,0.00007519741,0.00030747306,0.0030339607,0.82337093,0.0050621238,0.00012366245,0.0004251665,0.166871],"study_design_scores_gemma":[0.00050530396,0.000056586734,0.00035238947,0.00007545039,0.0000024845833,0.00009525517,0.000015176133,0.996149,0.0021019115,0.0000030423028,0.00046135043,0.00018203264],"about_ca_topic_score_codex":0.00003081904,"about_ca_topic_score_gemma":0.000040483894,"teacher_disagreement_score":0.786489,"about_ca_system_score_codex":0.00005529967,"about_ca_system_score_gemma":0.00006496651,"threshold_uncertainty_score":0.619548},"labels":[],"label_agreement":null},{"id":"W2131287878","doi":"10.5539/mas.v7n9p10","title":"A Novel Center Point Initialization Technique for K-means Clustering Algorithm","year":2013,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Initialization; Cluster analysis; Computer science; Histogram; Algorithm; Point (geometry); k-means clustering; Center (category theory); Data mining; Pattern recognition (psychology); Artificial intelligence; Mathematics; Image (mathematics)","score_opus":0.027544671519506275,"score_gpt":0.29343813413077985,"score_spread":0.26589346261127356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131287878","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":[0.000049975693,0.0000050637723,0.99569064,0.00034839346,0.00018160278,0.0017290949,0.000008919846,0.00028540622,0.001700915],"genre_scores_gemma":[0.16671832,0.0000017373768,0.8314574,0.00030025473,0.00006353883,0.0013320958,0.0000035352864,0.000023456143,0.00009966596],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971084,0.000012834354,0.00030567648,0.0009402525,0.0007737612,0.0008590777],"domain_scores_gemma":[0.9984142,0.00007444,0.00010107931,0.00082266086,0.00035467322,0.00023291775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000774459,0.00021331388,0.000185659,0.00033366468,0.0005129789,0.0006350417,0.0021078011,0.00007133513,0.000009200068],"category_scores_gemma":[0.00006283571,0.00020578175,0.000048757673,0.0009753265,0.00032630813,0.0014896556,0.0011989744,0.00017870065,0.00004717641],"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":[0.0000031696686,0.00007548009,0.0000022449408,0.000021505088,0.0000029635687,9.869856e-7,0.00057800516,0.002872527,0.7822195,0.0029590665,0.000034201956,0.21123031],"study_design_scores_gemma":[0.0004325391,0.00004577259,0.000050388422,0.00001907112,9.0941654e-7,0.000032908203,0.000023291494,0.93776315,0.048857123,0.012313522,0.00021803561,0.0002432574],"about_ca_topic_score_codex":0.000032698197,"about_ca_topic_score_gemma":0.0000047695776,"teacher_disagreement_score":0.9348906,"about_ca_system_score_codex":0.0002490605,"about_ca_system_score_gemma":0.00017260386,"threshold_uncertainty_score":0.8391536},"labels":[],"label_agreement":null},{"id":"W2138629976","doi":"10.5539/mas.v4n7p148","title":"Ontology Based Fuzzy Document Clustering Scheme","year":2010,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Computer science; Document clustering; Fuzzy clustering; Vector space model; Semantic similarity; Information retrieval; Ontology; Data mining; Clustering high-dimensional data; Artificial intelligence","score_opus":0.015323686627275629,"score_gpt":0.29284564271317476,"score_spread":0.27752195608589914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138629976","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":[0.015923938,0.000008752149,0.9696484,0.00076701195,0.0005210084,0.00027114805,6.9380826e-7,0.00032356565,0.012535436],"genre_scores_gemma":[0.5932497,5.58855e-7,0.406264,0.0002656034,0.000040842697,0.000055774944,3.3935518e-7,0.000009250157,0.000113940136],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964926,0.000018772054,0.00025619104,0.0011042168,0.0011123329,0.0010158736],"domain_scores_gemma":[0.9978295,0.000095788695,0.00008477898,0.001497554,0.00014263415,0.0003497662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011841411,0.00021086942,0.00019769637,0.00031501782,0.0005610836,0.0004600773,0.003666163,0.00008380382,0.000023752678],"category_scores_gemma":[0.00008627651,0.00020156294,0.000040590807,0.0010298477,0.00075218565,0.00071544666,0.0015747473,0.0005678199,0.00014879716],"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":[0.000007933996,0.000035374876,0.000032635016,0.000009833683,0.0000019100037,0.00001233932,0.00027339664,0.0023483061,0.8719087,0.023635132,0.00001098535,0.10172343],"study_design_scores_gemma":[0.0003685406,0.00003149831,0.00041620212,0.000004778482,7.53738e-7,0.00002015076,0.000008865812,0.9456304,0.03572224,0.016830921,0.0007168581,0.0002488378],"about_ca_topic_score_codex":0.000021447875,"about_ca_topic_score_gemma":0.00006356625,"teacher_disagreement_score":0.94328207,"about_ca_system_score_codex":0.00014471693,"about_ca_system_score_gemma":0.00042583057,"threshold_uncertainty_score":0.82194984},"labels":[],"label_agreement":null},{"id":"W2141277572","doi":"10.1109/tkde.2013.53","title":"Extended Subtree: A New Similarity Function for Tree Structured Data","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Similarity (geometry); Edit distance; Cluster analysis; Data mining; Tree (set theory); Function (biology); Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.058334273774491116,"score_gpt":0.3147285319055442,"score_spread":0.25639425813105304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141277572","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":[0.0002911379,0.0002965762,0.9975629,0.00017524858,0.0007290294,0.00040630126,0.00023193871,0.0002726035,0.000034257257],"genre_scores_gemma":[0.48982087,0.00016227135,0.50792813,0.000058365902,0.00035730787,0.00013187822,0.00028171198,0.000072716204,0.0011867181],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848485,0.000017771565,0.0001994576,0.0007802632,0.00016218526,0.00035545244],"domain_scores_gemma":[0.99718904,0.00021041633,0.000026773636,0.0022794886,0.00007526279,0.00021903691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018178154,0.00019893702,0.00017697942,0.00017593334,0.00016747482,0.00021780928,0.0016271911,0.000084755426,0.000021011994],"category_scores_gemma":[0.000029631288,0.00019577288,0.000027693482,0.00032515696,0.000020760657,0.002130516,0.00008591426,0.00026954163,0.000025828556],"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":[0.00001999081,0.000073653515,0.0000010966638,0.00008858158,0.00006453335,0.0000015722787,0.00011196876,0.006567033,0.004280792,0.00013930873,0.0027702635,0.9858812],"study_design_scores_gemma":[0.00062829914,0.00010226514,0.00043963388,0.000026652842,0.000020346835,0.000012209596,0.000009937925,0.9872869,0.001693562,0.0003292407,0.009231338,0.00021958107],"about_ca_topic_score_codex":0.000048858095,"about_ca_topic_score_gemma":0.00010802828,"teacher_disagreement_score":0.9856616,"about_ca_system_score_codex":0.000040776547,"about_ca_system_score_gemma":0.00008051616,"threshold_uncertainty_score":0.79833865},"labels":[],"label_agreement":null},{"id":"W2142989018","doi":"10.1109/icws.2008.120","title":"Adaptive Quality Recommendation Mechanism for Software Service Provisioning","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Dynamism; Cluster analysis; Granularity; Provisioning; Service provider; Feature (linguistics); Service (business); Quality of service; Data mining; Software; Index (typography); Quality (philosophy); Computer network; World Wide Web; Artificial intelligence","score_opus":0.12744566175716318,"score_gpt":0.3667250012835386,"score_spread":0.2392793395263754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142989018","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":[0.0011920849,0.0000028368345,0.99545,0.002079064,0.00013948747,0.00038820438,0.000005091612,0.00036612822,0.0003770728],"genre_scores_gemma":[0.037679162,0.000004192034,0.9604933,0.00081536075,0.00004366256,0.000104963096,0.000008678237,0.0000116905685,0.0008389719],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877506,0.00006799812,0.00020611756,0.00040587134,0.0002472146,0.00029773405],"domain_scores_gemma":[0.9986391,0.0003353587,0.00007303286,0.00035051897,0.00051556097,0.000086393644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036025848,0.00010356598,0.00012312591,0.00006748963,0.0003591847,0.00004862726,0.0005297101,0.000047566893,0.000019015888],"category_scores_gemma":[0.00023992141,0.00009539888,0.00003848269,0.00032393142,0.000013838311,0.0007345489,0.00037857075,0.000109068584,0.00003924297],"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":[0.000084110245,0.00017430873,0.00006534206,0.00010749976,0.000041568226,0.000011008776,0.0030535448,0.0012600336,0.0019292815,0.21163042,0.0009128195,0.78073007],"study_design_scores_gemma":[0.0007981697,0.00026289004,0.00036770426,0.000019540801,0.000001483264,0.000033876695,0.00018084518,0.93587226,0.011646968,0.04936115,0.0011348262,0.00032026757],"about_ca_topic_score_codex":0.00010737263,"about_ca_topic_score_gemma":0.000028523544,"teacher_disagreement_score":0.9346122,"about_ca_system_score_codex":0.000094087074,"about_ca_system_score_gemma":0.00009434929,"threshold_uncertainty_score":0.38902533},"labels":[],"label_agreement":null},{"id":"W2147809251","doi":"10.1007/978-0-387-36795-8_9","title":"Unsupervised Learning: Clustering","year":2007,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":18,"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; Unsupervised learning; Computer science; Artificial intelligence","score_opus":0.06366156814888656,"score_gpt":0.312241148465601,"score_spread":0.24857958031671445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147809251","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.9356354e-7,0.00013523891,0.5058659,0.00008653297,0.00018897925,0.000122359,5.357411e-7,0.00045704684,0.49314305],"genre_scores_gemma":[0.00010291742,0.00012360202,0.15559222,0.00016250543,0.00022139624,0.000005133838,0.0000064452493,0.000080939135,0.8437049],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971508,0.000019790805,0.000402204,0.0008810941,0.0008885767,0.00065753824],"domain_scores_gemma":[0.9981666,0.00018317993,0.000121733494,0.0010587743,0.00019930094,0.00027039996],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00043806472,0.00043210163,0.00039347706,0.00045264082,0.00018191095,0.00022563507,0.00180751,0.0003789898,0.00051874755],"category_scores_gemma":[0.000042513442,0.00042723885,0.0001673585,0.00009966104,0.000089648136,0.000327181,0.0019238142,0.0012484039,0.0012706222],"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":[0.000012687147,0.000014121886,0.0000026319628,0.00010092099,0.000074391304,0.00051147555,0.00020038427,0.0024880369,0.00007669926,0.2351682,0.0005580367,0.76079243],"study_design_scores_gemma":[0.0003901284,0.00019104859,0.000008422783,0.00015770391,0.000006626194,0.00011641611,0.000008321193,0.22190027,0.00013490437,0.0108422395,0.76535726,0.0008866703],"about_ca_topic_score_codex":0.000012944187,"about_ca_topic_score_gemma":0.00001926483,"teacher_disagreement_score":0.76479924,"about_ca_system_score_codex":0.00021836394,"about_ca_system_score_gemma":0.0001060126,"threshold_uncertainty_score":0.99981797},"labels":[],"label_agreement":null},{"id":"W2148260866","doi":"10.4236/jsea.2014.78059","title":"D-IMPACT: A Data Preprocessing Algorithm to Improve the Performance of Clustering","year":2014,"lang":"en","type":"article","venue":"Journal of Software Engineering and Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; University of Tokyo; Institute of Medical Science, University of Tokyo; Research Organization of Information and Systems","keywords":"Cluster analysis; Computer science; Preprocessor; Data mining; Outlier; Data pre-processing; CURE data clustering algorithm; Noise (video); Algorithm; Canopy clustering algorithm; Correlation clustering; Pattern recognition (psychology); Artificial intelligence; Image (mathematics)","score_opus":0.013876194593148983,"score_gpt":0.2891263948725445,"score_spread":0.2752502002793955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148260866","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":[0.018601403,0.00015780504,0.9809152,0.000115175084,0.00005384646,0.00011282636,0.0000059580284,0.000034353794,0.000003445117],"genre_scores_gemma":[0.3658792,0.000035303958,0.6338364,0.000016786342,0.00018591975,0.000016876462,7.432426e-7,0.000011212713,0.000017531582],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991398,0.00001061151,0.0002733587,0.00017561264,0.00023329002,0.00016734371],"domain_scores_gemma":[0.99866503,0.00023346095,0.00014548321,0.000668194,0.00017518614,0.000112644644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005668641,0.000089109,0.00014686643,0.000104242536,0.000096835036,0.00008187569,0.0011384757,0.000024701216,4.700511e-7],"category_scores_gemma":[0.00021619236,0.000063180116,0.000026728256,0.00033937386,0.000023671351,0.00042824936,0.0005777377,0.0001997744,0.0000011124172],"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":[0.000002661089,0.000021148724,0.00025777548,0.00008746784,0.000020633106,4.1656588e-7,0.00020461473,0.12374488,0.0017069874,0.000039833103,0.000018674475,0.87389493],"study_design_scores_gemma":[0.0001307397,0.00012978824,0.003362161,0.00009202478,0.000006381768,0.00008740363,0.00000965475,0.99258363,0.0006564608,0.00003296917,0.0028252383,0.00008355409],"about_ca_topic_score_codex":0.0000038563076,"about_ca_topic_score_gemma":2.8956865e-7,"teacher_disagreement_score":0.87381136,"about_ca_system_score_codex":0.000027849028,"about_ca_system_score_gemma":0.0000462315,"threshold_uncertainty_score":0.25764102},"labels":[],"label_agreement":null},{"id":"W2149433841","doi":"10.1109/wi.2003.1241276","title":"Incremental document clustering using cluster similarity histograms","year":2004,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":48,"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 Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Document clustering; Fuzzy clustering; Data mining; Information retrieval; Brown clustering; Conceptual clustering; Correlation clustering; Histogram; Consensus clustering; Similarity measure; Similarity (geometry); CURE data clustering algorithm; Artificial intelligence; Image (mathematics)","score_opus":0.03597026134903813,"score_gpt":0.32169177144347144,"score_spread":0.2857215100944333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149433841","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":[0.027562851,0.000041877716,0.9689276,0.0008962742,0.0003679415,0.00028310227,7.5008967e-7,0.00034178246,0.0015778079],"genre_scores_gemma":[0.41519874,0.000005187383,0.58401203,0.0005027912,0.00006574319,0.000011906342,0.0000010501435,0.000016294227,0.00018628627],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977665,0.000054708868,0.00030880838,0.000574402,0.0006488825,0.00064671563],"domain_scores_gemma":[0.99888027,0.00003631282,0.00006540506,0.00072626397,0.000079379206,0.00021234824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003913557,0.00021258068,0.00018720864,0.00015078853,0.00027434944,0.00029777875,0.0010542248,0.00007106879,0.000039747934],"category_scores_gemma":[0.000027456274,0.00020319219,0.000082371334,0.00041142013,0.00008024929,0.0011045624,0.0018456278,0.00025918556,0.00006598567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007540415,0.000542098,0.00037467649,0.0001654759,0.00012913899,0.0003559832,0.0027036709,0.7200405,0.025443941,0.018779863,0.00017192354,0.23121734],"study_design_scores_gemma":[0.0030255045,0.00026803053,0.00036381662,0.00009236231,0.0000089314535,0.00030616263,0.00014213283,0.9645935,0.01484256,0.012570528,0.0029518248,0.00083462015],"about_ca_topic_score_codex":0.00065324723,"about_ca_topic_score_gemma":0.00012218706,"teacher_disagreement_score":0.3876359,"about_ca_system_score_codex":0.0010539441,"about_ca_system_score_gemma":0.00010629108,"threshold_uncertainty_score":0.82859373},"labels":[],"label_agreement":null},{"id":"W2150062453","doi":"10.1186/1751-0473-9-5","title":"PFClust: an optimised implementation of a parameter-free clustering algorithm","year":2014,"lang":"en","type":"article","venue":"Source Code for Biology and Medicine","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"World Anti-Doping Agency","keywords":"Computer science; Cluster analysis; Data mining; Algorithm; Data science; Artificial intelligence","score_opus":0.031641960745721155,"score_gpt":0.38136154057600685,"score_spread":0.3497195798302857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150062453","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":[0.017224163,0.00010632934,0.9809511,0.001120923,0.00019347834,0.0002816321,0.000019569761,0.00006285798,0.000039951952],"genre_scores_gemma":[0.21459712,0.00005852615,0.78424996,0.00041452266,0.00037099328,0.00008913066,0.000056405777,0.000020159938,0.00014315922],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886596,0.00010088833,0.00026247805,0.00035804266,0.0001057491,0.00030685146],"domain_scores_gemma":[0.9988097,0.00036796147,0.00011382196,0.00047952103,0.00010057733,0.00012842969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007312703,0.00012249856,0.00026372087,0.00012303721,0.00012225048,0.000009075776,0.0005377174,0.000079821795,0.000008832171],"category_scores_gemma":[0.00024191823,0.00009838804,0.000026720016,0.00012492061,0.0002467602,0.00012297805,0.0003110727,0.00009598407,4.6683832e-7],"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":[0.00002951773,0.000018413095,0.00019720478,0.000049976356,0.000022328057,5.9440674e-7,0.0011766849,0.0003796726,0.004144994,0.0015184818,0.000086515094,0.9923756],"study_design_scores_gemma":[0.0035454181,0.0028985795,0.0004998255,0.000037963557,0.000014522718,0.000023237795,0.00047152507,0.97068626,0.002503479,0.011732798,0.0074294973,0.00015686857],"about_ca_topic_score_codex":0.00006899119,"about_ca_topic_score_gemma":0.000046900834,"teacher_disagreement_score":0.99221873,"about_ca_system_score_codex":0.000016309861,"about_ca_system_score_gemma":0.000021196809,"threshold_uncertainty_score":0.40121478},"labels":[],"label_agreement":null},{"id":"W2155874464","doi":"10.1109/icpr.2008.4761242","title":"A novel validity measure for clusters of arbitrary shapes and densities","year":2008,"lang":"en","type":"article","venue":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Measure (data warehouse); Cluster analysis; Computer science; Cluster (spacecraft); Neighbourhood (mathematics); Mathematics; Algorithm; Data mining; Statistical physics; Artificial intelligence; Physics; Mathematical analysis","score_opus":0.19587218909234413,"score_gpt":0.32822098272933664,"score_spread":0.1323487936369925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155874464","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":[0.6241953,0.000024185962,0.32207856,0.007917323,0.0021088647,0.0022140872,0.0022419156,0.00068189186,0.03853791],"genre_scores_gemma":[0.9824761,0.0004960397,0.013314428,0.0013713846,0.0007244535,0.000728935,0.0004501046,0.00010411707,0.0003344275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933368,0.000031367545,0.0013411412,0.0019847609,0.0024023915,0.0009035192],"domain_scores_gemma":[0.99035645,0.0002983761,0.0011787824,0.0002096125,0.0075371014,0.00041966775],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084675214,0.00093163346,0.0008065572,0.0013581901,0.00050699495,0.0009644321,0.0020576594,0.00040561095,0.0004929767],"category_scores_gemma":[0.00058419065,0.0009958699,0.0003459486,0.0004261313,0.00046385406,0.002889367,0.00060888246,0.00097176904,0.0001388537],"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":[0.003081996,0.0036875214,0.016650885,0.0015888163,0.0019893663,0.00008859793,0.007962864,0.000024540155,0.06600304,0.039243285,0.0027454193,0.85693365],"study_design_scores_gemma":[0.017942198,0.0059813936,0.02648896,0.009404159,0.000301924,0.0025884467,0.0065745735,0.72828466,0.109922156,0.0853374,0.0009161702,0.006257938],"about_ca_topic_score_codex":0.000096426236,"about_ca_topic_score_gemma":0.00002825973,"teacher_disagreement_score":0.8506757,"about_ca_system_score_codex":0.000411059,"about_ca_system_score_gemma":0.00023764778,"threshold_uncertainty_score":0.99924916},"labels":[],"label_agreement":null},{"id":"W2155880472","doi":"10.1109/ideas.2006.52","title":"Visualization of Web Usage Patterns","year":2006,"lang":"en","type":"article","venue":"Proceedings - International Database Engineering and Applications Symposium","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"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; Concordia University","keywords":"Computer science; Cluster analysis; Data mining; Visualization; Multidimensional scaling; Rendering (computer graphics); Fidelity; Data visualization; Fuzzy logic; Fuzzy clustering; Relational database; Web mining; Machine learning; Artificial intelligence; Web page; World Wide Web","score_opus":0.007642618741154016,"score_gpt":0.25967164109081486,"score_spread":0.25202902234966085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155880472","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":[0.0126390755,0.00005303651,0.9851776,0.00027996488,0.00008131301,0.00019923844,0.00008988171,0.00018765309,0.0012922621],"genre_scores_gemma":[0.9418232,0.00015451241,0.057013635,0.000018919023,0.0002710337,0.00026991023,0.0001478591,0.000021786995,0.00027913612],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896383,0.0000024942415,0.0002441403,0.0003178812,0.00030815674,0.0001634806],"domain_scores_gemma":[0.99942863,0.000043261924,0.00008771061,0.00016416104,0.00022114062,0.000055083354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014795519,0.00011650364,0.00009728293,0.00023792256,0.000058171714,0.00011603926,0.00052266696,0.000031956435,0.000004947098],"category_scores_gemma":[0.000021149142,0.00012595009,0.00002388043,0.00031703667,0.000023517166,0.000624242,0.00031412175,0.00008531069,0.00000519923],"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":[0.0000047367153,0.00016119324,0.0034711312,0.00026316717,0.000032877404,0.000001656646,0.000085850974,0.0057473895,0.4002951,0.5865011,0.00030597317,0.0031298161],"study_design_scores_gemma":[0.00032375127,0.000022457183,0.0015893886,0.00008832604,0.0000065035665,0.000035157267,0.000014366867,0.9411384,0.03103037,0.00044788155,0.025077906,0.0002254823],"about_ca_topic_score_codex":0.000027218157,"about_ca_topic_score_gemma":7.1923074e-7,"teacher_disagreement_score":0.935391,"about_ca_system_score_codex":0.000045045672,"about_ca_system_score_gemma":0.000016269812,"threshold_uncertainty_score":0.5136095},"labels":[],"label_agreement":null},{"id":"W2161173962","doi":"","title":"Towards Property-Based Classification of Clustering Paradigms","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":43,"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 Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Constrained clustering; Correlation clustering; Impossibility; CURE data clustering algorithm; Data stream clustering; Canopy clustering algorithm; Data mining; Set (abstract data type); Consensus clustering; Fuzzy clustering; Conceptual clustering; Machine learning; Artificial intelligence; Theoretical computer science","score_opus":0.04395941345548841,"score_gpt":0.31657841053949193,"score_spread":0.2726189970840035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161173962","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":[0.006894927,0.000003764079,0.98030853,0.0013467794,0.00022938754,0.00015887195,7.252983e-7,0.0001644069,0.010892577],"genre_scores_gemma":[0.6363583,8.251607e-7,0.36296785,0.000045676083,0.000027322269,0.00001994107,8.4870334e-7,0.0000069112,0.00057230645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989052,0.00002797551,0.00019743691,0.00028939865,0.0003476017,0.00023241591],"domain_scores_gemma":[0.9989279,0.000045695466,0.00006081968,0.00073910836,0.00013776479,0.00008873662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028316662,0.00008894625,0.00011242861,0.000107653854,0.000056994053,0.00006443164,0.0009129726,0.000055717865,0.000031172945],"category_scores_gemma":[0.00008014406,0.000059818583,0.000037877155,0.00032370642,0.00007829628,0.0003108431,0.00022472732,0.00020839674,0.000029125149],"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":[0.000014404818,0.00011783451,0.0002993626,0.0000711857,0.00000840688,0.000006016379,0.00019227216,0.0022615865,0.3233567,0.024864191,0.00010659171,0.6487014],"study_design_scores_gemma":[0.00021575845,0.000060165257,0.003443195,0.00000852714,7.35062e-7,0.0000063833736,0.000007300683,0.9463304,0.045002155,0.00047530426,0.0043484867,0.000101549624],"about_ca_topic_score_codex":0.000054422624,"about_ca_topic_score_gemma":0.00006471234,"teacher_disagreement_score":0.94406885,"about_ca_system_score_codex":0.000023279632,"about_ca_system_score_gemma":0.00013938666,"threshold_uncertainty_score":0.24393311},"labels":[],"label_agreement":null},{"id":"W2161806858","doi":"10.1109/icsmc.2006.384571","title":"GRIDBSCAN: GRId Density-Based Spatial Clustering of Applications with Noise","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Innovation Council; National Research Council Canada; Simon Fraser University","funders":"","keywords":"DBSCAN; Cluster analysis; Computer science; Noise (video); Grid; Data mining; Benchmark (surveying); Set (abstract data type); Data set; Artificial intelligence; Pattern recognition (psychology); Correlation clustering; CURE data clustering algorithm; Image (mathematics); Mathematics","score_opus":0.00793827355241549,"score_gpt":0.24188464356674572,"score_spread":0.23394637001433022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161806858","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":[0.0030335584,0.000010792574,0.99417526,0.00032220464,0.000050104856,0.0002798615,0.0000036425042,0.00017744911,0.0019471196],"genre_scores_gemma":[0.48042476,7.280643e-7,0.5190085,0.00005411808,0.000123574,0.00006854152,0.000006022134,0.000012357495,0.00030136757],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875355,0.00002617621,0.00020068105,0.00034055422,0.0004003602,0.0002786548],"domain_scores_gemma":[0.9989389,0.0000796558,0.00007564387,0.00065149995,0.00018272508,0.00007153205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011579003,0.00011772445,0.00014822204,0.00012794802,0.00009699158,0.00005646394,0.0006213441,0.000033863595,0.000010619363],"category_scores_gemma":[0.000005608034,0.000098790675,0.00003479129,0.0004536553,0.000086904176,0.00019334875,0.00024293004,0.00010718372,0.000018757828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013991752,0.0007142473,0.008275398,0.0003420579,0.00004717282,0.00008836956,0.0001381653,0.73066264,0.027889332,0.017358236,0.00060720847,0.21373728],"study_design_scores_gemma":[0.0006867762,0.00014143855,0.0066927075,0.000023771881,0.000004112678,0.000022103799,0.000007652277,0.94538933,0.044343483,0.00047213602,0.0019881278,0.0002283364],"about_ca_topic_score_codex":0.0010255491,"about_ca_topic_score_gemma":0.00068264233,"teacher_disagreement_score":0.47739118,"about_ca_system_score_codex":0.000054850796,"about_ca_system_score_gemma":0.00010344682,"threshold_uncertainty_score":0.40285668},"labels":[],"label_agreement":null},{"id":"W2162062774","doi":"10.1109/isvd.2006.18","title":"CRYSTAL - A new density-based fast and efficient clustering algorithm","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":13,"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 Calgary","funders":"University of Alberta","keywords":"Delaunay triangulation; Cluster analysis; CURE data clustering algorithm; Correlation clustering; Computer science; Canopy clustering algorithm; Bowyer–Watson algorithm; Fuzzy clustering; DBSCAN; Single-linkage clustering; Algorithm; Regular polygon; Cluster (spacecraft); Voronoi diagram; Data mining; Artificial intelligence; Mathematics","score_opus":0.011153836378406603,"score_gpt":0.25285739249769534,"score_spread":0.24170355611928873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162062774","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":[0.005530931,0.000054809225,0.9921172,0.00054920575,0.00012511894,0.00015873964,0.0000014009578,0.00031669775,0.0011458857],"genre_scores_gemma":[0.11505839,0.0000011063076,0.882403,0.00015058863,0.00013123237,0.000006501785,0.0000020766997,0.000016114387,0.002230966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835044,0.00003632224,0.00019342439,0.0005089367,0.0004328334,0.00047805422],"domain_scores_gemma":[0.9991631,0.000086856955,0.00003948798,0.0004462707,0.00006938388,0.00019491163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017512651,0.00016703506,0.00015654326,0.00015777726,0.00016802257,0.0002890714,0.00045571724,0.000051185078,0.000012891783],"category_scores_gemma":[0.000015056153,0.00015547943,0.000040658528,0.00036742457,0.000064531916,0.00018689783,0.0006308304,0.0001519963,0.000027687964],"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":[0.000012575949,0.00012762344,0.00014379235,0.00003907512,0.000011095783,0.00019223115,0.00017960332,0.18730499,0.005525664,0.0022238158,0.0006455308,0.803594],"study_design_scores_gemma":[0.0005922216,0.000060035556,0.0009663399,0.000015209512,0.0000015189221,0.00006169248,0.000012471303,0.99356395,0.003266807,0.00047144014,0.0007938284,0.00019447497],"about_ca_topic_score_codex":0.000512863,"about_ca_topic_score_gemma":0.00006778898,"teacher_disagreement_score":0.806259,"about_ca_system_score_codex":0.00008006292,"about_ca_system_score_gemma":0.000104636754,"threshold_uncertainty_score":0.6340267},"labels":[],"label_agreement":null},{"id":"W2163067442","doi":"10.1109/icdm.2009.118","title":"A New MCA-Based Divisive Hierarchical Algorithm for Clustering Categorical Data","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"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; Similarity (geometry); Hierarchical clustering; Data mining; Pattern recognition (psychology); Algorithm; Canopy clustering algorithm; Single-linkage clustering; Subspace topology; Artificial intelligence; Linear subspace; CURE data clustering algorithm; Correlation clustering; Mathematics; Machine learning","score_opus":0.05942537267736089,"score_gpt":0.3551315825387727,"score_spread":0.29570620986141183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163067442","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":[0.000011859118,0.00005567262,0.99186337,0.006386007,0.00024035478,0.0005018696,0.000017551587,0.00042696236,0.0004963821],"genre_scores_gemma":[0.0065451944,0.0000045609504,0.99061984,0.0009968262,0.00042414077,0.00002117631,0.00004700411,0.000019606032,0.0013216711],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99709404,0.000060885355,0.0003263052,0.00107531,0.00061649183,0.0008269763],"domain_scores_gemma":[0.99691993,0.0004295545,0.00005844249,0.0019928669,0.00012195272,0.0004772247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039981317,0.00024591162,0.0002850157,0.00018039152,0.00021210482,0.00032832797,0.0037605043,0.00010094627,0.000022441624],"category_scores_gemma":[0.00017964562,0.00021871529,0.00008124608,0.00055436365,0.00004194257,0.000840147,0.0013457274,0.00032435264,0.00004191597],"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":[0.000009900257,0.000058813417,0.0000020890657,0.0000064183805,0.0000087147655,0.00003734448,0.000047522968,0.0010382127,0.00011975839,0.0028853016,0.0033771882,0.99240875],"study_design_scores_gemma":[0.0010498369,0.0003415542,0.00014713604,0.000010154597,0.0000038961516,0.000026164105,0.0000055934784,0.9774343,0.0005361,0.010701859,0.009457848,0.00028559347],"about_ca_topic_score_codex":0.00005520573,"about_ca_topic_score_gemma":0.0000096814265,"teacher_disagreement_score":0.9921231,"about_ca_system_score_codex":0.000119392,"about_ca_system_score_gemma":0.00035665042,"threshold_uncertainty_score":0.89189506},"labels":[],"label_agreement":null},{"id":"W2163097311","doi":"","title":"Proximity Graphs for Clustering and Manifold Learning","year":2004,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":120,"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 Toronto","funders":"","keywords":"Cluster analysis; Lattice graph; Dimensionality reduction; Computer science; Line graph; Mathematics; Graph; Pattern recognition (psychology); Voltage graph; Theoretical computer science; Artificial intelligence","score_opus":0.022688260320615685,"score_gpt":0.28182495072565483,"score_spread":0.25913669040503917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163097311","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":[0.012334722,0.00014022188,0.98582673,0.0002813896,0.0002473138,0.0005218023,0.000001375167,0.00037209658,0.00027436184],"genre_scores_gemma":[0.9677492,0.000006619242,0.031877995,0.00008369782,0.000043849308,0.00013389705,0.0000055566848,0.000009353646,0.00008986994],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988008,0.000023862745,0.0003595758,0.00019001415,0.00030548,0.0003202414],"domain_scores_gemma":[0.9992769,0.0000367033,0.00020221405,0.00016297169,0.00023050205,0.00009075604],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00034932664,0.00013427871,0.00014564353,0.00017858489,0.00044713993,0.001061691,0.0003265833,0.000059987953,1.8163468e-7],"category_scores_gemma":[0.00009078638,0.00012371951,0.000027947583,0.00029857105,0.000026877737,0.0064119697,0.00018037694,0.00018373004,0.000005738258],"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":[0.000039945848,0.000027428185,0.00026757404,0.003547616,0.00001678365,0.0000053466233,0.0073811864,0.4327811,0.0008751774,0.02505668,0.000024515777,0.52997667],"study_design_scores_gemma":[0.0006390283,0.00010927764,0.00018145893,0.00014177304,0.0000018568047,0.00012944333,0.0002708816,0.9956893,0.0002519228,0.0008621284,0.0015559036,0.00016704625],"about_ca_topic_score_codex":0.000026904858,"about_ca_topic_score_gemma":0.0000021850144,"teacher_disagreement_score":0.9554144,"about_ca_system_score_codex":0.0000833964,"about_ca_system_score_gemma":0.000056853154,"threshold_uncertainty_score":0.9999753},"labels":[],"label_agreement":null},{"id":"W2164582339","doi":"10.1109/ijcnn.2006.247041","title":"PARTCAT: A Subspace Clustering Algorithm for High Dimensional Categorical Data","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Subspace topology; Data mining; Dimension (graph theory); Similarity (geometry); Clustering high-dimensional data; Artificial intelligence; Artificial neural network; Cluster (spacecraft); Pattern recognition (psychology); Algorithm; Mathematics; Machine learning","score_opus":0.08700548172302576,"score_gpt":0.3200420799469654,"score_spread":0.23303659822393963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164582339","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":[0.0073307464,0.00004794984,0.96847945,0.018740296,0.002694737,0.00081398664,0.000087559194,0.00036375478,0.0014415061],"genre_scores_gemma":[0.88534874,0.000025162153,0.10774924,0.0007499927,0.0033028265,0.00020598012,0.00012379423,0.000052551186,0.0024417283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644053,0.000035674446,0.0005390928,0.001045252,0.0010900458,0.0008493939],"domain_scores_gemma":[0.9979443,0.0002657383,0.00028706994,0.0006574048,0.000706267,0.00013923302],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007108852,0.00037339143,0.00032135847,0.00013084877,0.00042036356,0.0006787482,0.0035965487,0.00010504021,0.000023259312],"category_scores_gemma":[0.00007272784,0.00028466334,0.000093789495,0.00040797298,0.00016870102,0.0009756375,0.0013278272,0.0005292122,0.000053766365],"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":[0.00036278623,0.000545853,0.00018976117,0.00006492181,0.00023009411,0.00008751153,0.000254928,0.16231738,0.004513971,0.3456495,0.1495404,0.33624288],"study_design_scores_gemma":[0.00058951654,0.00015744794,0.00053537183,0.000055928736,0.000009000386,0.000122053774,0.0000105483105,0.9707219,0.0005703593,0.024962252,0.0019371912,0.00032840198],"about_ca_topic_score_codex":0.00017037982,"about_ca_topic_score_gemma":0.000036947797,"teacher_disagreement_score":0.87801796,"about_ca_system_score_codex":0.00016951462,"about_ca_system_score_gemma":0.00009322597,"threshold_uncertainty_score":0.99996054},"labels":[],"label_agreement":null},{"id":"W2164665696","doi":"10.1109/ijcnn.2006.246962","title":"Refining Spherical K-Means for Clustering Documents","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Advanced Clustering Algorithms Research","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":"McMaster University","funders":"","keywords":"Convexity; Cluster analysis; Mathematical optimization; Constraint (computer-aided design); Set (abstract data type); Computer science; Maximization; Algorithm; Linear programming; Mathematics; Function (biology); Optimization problem; Artificial intelligence","score_opus":0.06047978020347221,"score_gpt":0.318466311927053,"score_spread":0.25798653172358077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164665696","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":[0.022102125,0.000030997984,0.9342531,0.015306575,0.002779726,0.00061980734,0.000013699482,0.000500158,0.024393793],"genre_scores_gemma":[0.8932073,0.00001791967,0.09591331,0.0011631261,0.002349334,0.00025254153,0.000010980603,0.000049041475,0.0070364345],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973721,0.000023309229,0.0004733776,0.00062345533,0.0007923574,0.00071541814],"domain_scores_gemma":[0.9987541,0.00016419617,0.0002432478,0.00025625108,0.0004868872,0.00009535819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047101168,0.0002860482,0.00024043336,0.0000855447,0.00034446863,0.00071349146,0.0017870131,0.00007565182,0.000027584043],"category_scores_gemma":[0.000065490705,0.00022095146,0.000125975,0.00032066068,0.000109603425,0.0006908954,0.0004235298,0.0004111863,0.000048112037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005448988,0.000302798,0.0011586113,0.00008817424,0.00016405304,0.000049034148,0.00046585884,0.48981214,0.018080447,0.2769196,0.06153065,0.15088372],"study_design_scores_gemma":[0.0005521818,0.00019856267,0.0006032663,0.000119710494,0.0000049675623,0.000054624736,0.000019965308,0.9748298,0.00088251807,0.014516045,0.00793141,0.0002869593],"about_ca_topic_score_codex":0.00007648235,"about_ca_topic_score_gemma":0.000021169271,"teacher_disagreement_score":0.8711052,"about_ca_system_score_codex":0.00018250955,"about_ca_system_score_gemma":0.000043242737,"threshold_uncertainty_score":0.9010139},"labels":[],"label_agreement":null},{"id":"W2165944636","doi":"10.1109/icsmc.2007.4413785","title":"Image segmentation using joint clustering analysis of attribute data and relationship data","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Segmentation-based object categorization; Computer science; Image segmentation; Segmentation; Artificial intelligence; Pattern recognition (psychology); Scale-space segmentation; Data mining; Market segmentation","score_opus":0.2598599314233456,"score_gpt":0.4275597758651129,"score_spread":0.16769984444176728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165944636","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":[0.039958935,0.000041244228,0.9595518,0.00010361736,0.000040603325,0.000099640434,0.00007182843,0.00004697691,0.00008535059],"genre_scores_gemma":[0.26904133,0.000007660666,0.73073703,0.000014636326,0.0000141022465,3.445504e-7,0.00014525883,0.0000048241777,0.00003483779],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846953,0.000052944655,0.00034894524,0.000539835,0.00035644782,0.00023229221],"domain_scores_gemma":[0.9971685,0.0003077657,0.0001222375,0.0022258584,0.00009460765,0.000081048325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018900688,0.00008410829,0.00017694024,0.00043669422,0.00011448612,0.000114089955,0.001327976,0.000032004562,0.00000869227],"category_scores_gemma":[0.00029409476,0.00008225543,0.00001713416,0.0014540837,0.000058900605,0.0020061256,0.0048653577,0.00010389168,0.0000018552366],"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":[0.00008669381,0.00036960587,0.20720822,0.00052730506,0.0026047258,0.00020469066,0.0040147714,0.083035834,0.26427492,0.0021471307,0.00045963432,0.43506646],"study_design_scores_gemma":[0.00013912503,0.0000102950235,0.04177951,0.000008973095,0.00006482545,0.000007877813,0.000114958784,0.9568937,0.0008197809,0.00006224761,0.0000151383,0.00008358348],"about_ca_topic_score_codex":0.00015530201,"about_ca_topic_score_gemma":0.00017648509,"teacher_disagreement_score":0.87385786,"about_ca_system_score_codex":0.00005575802,"about_ca_system_score_gemma":0.000032649565,"threshold_uncertainty_score":0.606432},"labels":[],"label_agreement":null},{"id":"W2169629580","doi":"10.1109/ictai.2008.128","title":"Oracle Clustering: Dynamic Partitioning Based on Random Observations","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 New Brunswick","funders":"","keywords":"Cluster analysis; Computer science; Dynamism; Oracle; Stability (learning theory); Data mining; Function (biology); Sampling (signal processing); Algorithm; Artificial intelligence; Machine learning","score_opus":0.060515682179626516,"score_gpt":0.3047927912108204,"score_spread":0.2442771090311939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169629580","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":[0.005946544,0.000009963794,0.98862594,0.0017643436,0.00014191208,0.00016166939,0.0000013777207,0.00041444457,0.0029338063],"genre_scores_gemma":[0.6142136,0.0000070994092,0.38305402,0.00054495886,0.00002188514,0.0000497619,0.0000049805344,0.000012331345,0.0020913698],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986633,0.00006221553,0.00018824147,0.0003496949,0.0004026419,0.00033387227],"domain_scores_gemma":[0.9988883,0.00025514018,0.000040187868,0.0006043128,0.000100241465,0.00011182318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018329975,0.00011437977,0.00012631924,0.00012537744,0.00041551006,0.00008303489,0.0005627144,0.000037014837,0.000045796678],"category_scores_gemma":[0.000121048826,0.00010677426,0.000052810916,0.00051204994,0.000057613404,0.00046737771,0.00018823886,0.0001574809,0.00014200808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008430912,0.0002975719,0.0011593284,0.000029758081,0.000018673607,0.0002086148,0.0004766347,0.9555004,0.0017817304,0.0039821654,0.0007927433,0.03566802],"study_design_scores_gemma":[0.0009783785,0.000077918914,0.005684749,0.000016574346,7.1235496e-7,0.000017721139,0.000007203875,0.99128866,0.00040802508,0.00032745118,0.0010609443,0.00013167474],"about_ca_topic_score_codex":0.000021587242,"about_ca_topic_score_gemma":0.00002133213,"teacher_disagreement_score":0.60826707,"about_ca_system_score_codex":0.00010031482,"about_ca_system_score_gemma":0.000088508496,"threshold_uncertainty_score":0.4354128},"labels":[],"label_agreement":null},{"id":"W2170006979","doi":"10.1007/s10107-010-0349-7","title":"An improved column generation algorithm for minimum sum-of-squares clustering","year":2010,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; HEC Montréal","funders":"","keywords":"Mathematics; Column (typography); Cluster analysis; Explained sum of squares; Bottleneck; Algorithm; Column generation; Set (abstract data type); Centroid; Point (geometry); Combinatorics; Square (algebra); Euclidean space; Mathematical optimization; Computer science; Statistics; Geometry","score_opus":0.03302216249232391,"score_gpt":0.33510104580939204,"score_spread":0.3020788833170681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170006979","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":[0.012084117,0.000013771266,0.98631954,0.00010729538,0.0002807694,0.00091755844,0.000004337287,0.0002283322,0.00004427244],"genre_scores_gemma":[0.10706017,5.661294e-7,0.89227706,0.000016442305,0.00022302786,0.00029391653,0.000007821333,0.000029252002,0.00009175244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981113,0.000042907093,0.00046132423,0.00047940592,0.00035799772,0.0005470617],"domain_scores_gemma":[0.99839544,0.00026653576,0.00013202638,0.0007561165,0.00024550044,0.00020438276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007982343,0.0001830071,0.00028460808,0.00011031126,0.00019411971,0.0003413293,0.0008900949,0.00012542332,0.000011335193],"category_scores_gemma":[0.00028240052,0.00017321816,0.00009593284,0.00025975803,0.00012076437,0.00058191916,0.00027331154,0.00025393802,0.0000072888333],"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":[0.0000023743285,0.0001681135,0.000002708311,0.00012650051,0.000010606461,0.0000023294806,0.00041426977,0.000049016922,0.09746256,0.0021290996,0.0000062350714,0.8996262],"study_design_scores_gemma":[0.00037091612,0.00036098115,0.0000065600766,0.000022209999,0.0000060819034,0.000019858964,0.000059629507,0.9743242,0.02008656,0.004070641,0.0004745788,0.00019775816],"about_ca_topic_score_codex":0.000009879556,"about_ca_topic_score_gemma":0.000022237386,"teacher_disagreement_score":0.97427523,"about_ca_system_score_codex":0.000030678693,"about_ca_system_score_gemma":0.00005622868,"threshold_uncertainty_score":0.70636314},"labels":[],"label_agreement":null},{"id":"W2170896428","doi":"10.1109/icdm.2009.143","title":"Semi-supervised Density-Based Clustering","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence; Set (abstract data type); Pattern recognition (psychology); Cluster (spacecraft); Data mining; Noise (video); Feature (linguistics); Image (mathematics)","score_opus":0.022955954467767742,"score_gpt":0.2907169793540355,"score_spread":0.26776102488626774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170896428","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":[0.0053112623,0.000018456898,0.986061,0.002632782,0.00011024412,0.00012016867,2.7059824e-7,0.00056348677,0.005182354],"genre_scores_gemma":[0.5140666,0.0000021267695,0.48319697,0.0018587424,0.000049398932,0.000004227219,9.578881e-7,0.000007218209,0.0008137434],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853635,0.000044732613,0.00016309219,0.0004112407,0.00039666757,0.0004479337],"domain_scores_gemma":[0.99890196,0.00007271633,0.000024644596,0.0007400979,0.000095798154,0.00016475831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002080427,0.00013602285,0.00013945794,0.00013122497,0.00013429933,0.00017842109,0.0009627696,0.000050690098,0.0000286106],"category_scores_gemma":[0.00004193115,0.00012575816,0.000055558678,0.00044504725,0.000023772407,0.0004218846,0.00023868863,0.00017006324,0.00013343823],"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":[0.000030747007,0.00018642996,0.00019955379,0.000033943317,0.000013398029,0.0002809607,0.00035617873,0.044025093,0.035501126,0.0073609087,0.0008423575,0.9111693],"study_design_scores_gemma":[0.0003961722,0.000114674964,0.0010931173,0.000013789624,8.0298827e-7,0.000018493307,0.0000072572793,0.980961,0.015079575,0.0013314103,0.0008034578,0.00018020054],"about_ca_topic_score_codex":0.000011500472,"about_ca_topic_score_gemma":0.000006597969,"teacher_disagreement_score":0.93693596,"about_ca_system_score_codex":0.000075866716,"about_ca_system_score_gemma":0.00006337599,"threshold_uncertainty_score":0.5128269},"labels":[],"label_agreement":null},{"id":"W2174016580","doi":"","title":"Estimation and Selection in Regression Clustering","year":2011,"lang":"en","type":"article","venue":"European Journal of Pure and Applied Mathematics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Cluster analysis; Mathematics; Correlation clustering; CURE data clustering algorithm; Regression analysis; Regression; Single-linkage clustering; Clustering high-dimensional data; Data mining; Statistics; Artificial intelligence; Computer science","score_opus":0.03784475837396073,"score_gpt":0.2723698911089335,"score_spread":0.23452513273497277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2174016580","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":[0.081878886,0.00006451216,0.91559285,0.00002993242,0.000020157158,0.000051423296,5.6268895e-8,0.000012954084,0.0023492132],"genre_scores_gemma":[0.46186733,0.000041038358,0.53804034,0.000008450247,0.000018638397,3.7878135e-7,2.2281087e-8,0.0000065244544,0.0000172702],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993862,0.000034881457,0.00025240434,0.000089202214,0.00013525054,0.000102064674],"domain_scores_gemma":[0.9996538,0.000032357013,0.00016822736,0.000059296097,0.00002877162,0.000057553927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067716045,0.00006974273,0.00011489997,0.00011814033,0.0000433751,0.000050118164,0.00016488747,0.000013099797,0.0000014174145],"category_scores_gemma":[0.000028530138,0.000053457403,0.000010650663,0.00012162306,0.000020857422,0.00021297409,0.00015227766,0.00016229201,0.0000023069354],"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":[0.00002226923,0.00008583122,0.000027413687,0.0001721209,0.000010673118,0.00009033082,0.011851099,0.00070057163,0.008858269,0.004418104,0.000035245426,0.97372806],"study_design_scores_gemma":[0.0016214835,0.0004894141,0.004325288,0.00088394096,0.000014369566,0.0015671081,0.00090756937,0.94988203,0.010342524,0.029510072,0.00013390917,0.00032227125],"about_ca_topic_score_codex":1.8405865e-7,"about_ca_topic_score_gemma":4.6453889e-7,"teacher_disagreement_score":0.9734058,"about_ca_system_score_codex":0.0000129191785,"about_ca_system_score_gemma":0.000009935076,"threshold_uncertainty_score":0.21799298},"labels":[],"label_agreement":null},{"id":"W2185184584","doi":"","title":"A characterization of linkage-based hierarchical clustering","year":2016,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":50,"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 Waterloo","funders":"","keywords":"Linkage (software); Hierarchical clustering of networks; Hierarchical clustering; Computer science; Class (philosophy); Cluster analysis; Complete linkage; Locality; Hierarchical database model; Mathematics; Artificial intelligence; Algorithm; Data mining; Canopy clustering algorithm; Correlation clustering","score_opus":0.04192133453023034,"score_gpt":0.3573990556538818,"score_spread":0.31547772112365147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185184584","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":[0.21194491,0.00006394974,0.78357786,0.0040692952,0.000116147734,0.00009692478,0.0000018956398,0.000029375036,0.00009963896],"genre_scores_gemma":[0.9575171,0.00010857504,0.041386675,0.000022706112,0.00021264331,0.000004225592,0.0000010153889,0.000025472938,0.00072159275],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955961,0.0011174718,0.00063685124,0.0002640732,0.0018398977,0.00054556684],"domain_scores_gemma":[0.99632674,0.0014913881,0.00037424781,0.00041085258,0.0011566627,0.0002401183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005287281,0.00012969661,0.0003198446,0.0010326977,0.00018597177,0.00010631195,0.0014750268,0.000090248315,0.000050257826],"category_scores_gemma":[0.0026816074,0.00008555382,0.00012683873,0.0009162197,0.00020102915,0.0006055057,0.00065356283,0.0014144495,0.000020342703],"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":[0.00020559455,0.00012101756,0.00348348,0.000092199836,0.000028421302,0.00013946946,0.00029935784,0.002284849,0.66111326,0.00028286845,0.000011061367,0.33193845],"study_design_scores_gemma":[0.004362864,0.0038728095,0.024978997,0.0015202075,0.0000074678314,0.00035736876,0.000028709967,0.8356362,0.11714706,0.001535756,0.010155603,0.0003969591],"about_ca_topic_score_codex":0.000011197745,"about_ca_topic_score_gemma":0.0000021050867,"teacher_disagreement_score":0.8333514,"about_ca_system_score_codex":0.00017164726,"about_ca_system_score_gemma":0.0003522251,"threshold_uncertainty_score":0.61451584},"labels":[],"label_agreement":null},{"id":"W2234615877","doi":"10.1080/10618600.2018.1546593","title":"A General Hybrid Clustering Technique","year":2018,"lang":"en","type":"preprint","venue":"Journal of Computational and Graphical Statistics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Division of Mathematical Sciences; Defense Threat Reduction Agency","keywords":"Cluster analysis; Single-linkage clustering; Complete-linkage clustering; Dendrogram; Complete linkage; Correlation clustering; CURE data clustering algorithm; Series (stratigraphy); Regular polygon; Mathematics; k-medians clustering; Computer science; Joins; Hamming distance; Combinatorics; Data mining; Artificial intelligence; Geometry","score_opus":0.020955277286332633,"score_gpt":0.3180252457379465,"score_spread":0.2970699684516139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2234615877","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":[0.0026892922,0.00022959262,0.9956621,0.00054707495,0.000578626,0.00016124133,0.00008034919,0.000028439303,0.000023313576],"genre_scores_gemma":[0.03935481,0.00013560474,0.9598658,0.00015148381,0.00042630866,0.000008999169,0.000012929479,0.000015818829,0.000028248238],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99775565,0.00012818606,0.00069106556,0.0003118791,0.00085417443,0.00025907642],"domain_scores_gemma":[0.9974967,0.0005151413,0.00052130496,0.00020301432,0.0010109505,0.0002528754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004794802,0.00022559961,0.00041169242,0.00036229767,0.00012935032,0.00027530678,0.00080029806,0.000119288634,0.0000050683925],"category_scores_gemma":[0.00018335946,0.00019902916,0.00010233911,0.00018251133,0.00023383703,0.00016250885,0.001429167,0.00097455055,0.0000017780337],"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":[0.0002214491,0.00058043667,0.00050510734,0.0018270188,0.00082191685,0.0035284054,0.00058797264,0.4636712,0.00024957585,0.13508223,0.013333252,0.3795914],"study_design_scores_gemma":[0.00020669187,0.0002135841,0.0022687858,0.00012572871,0.000010887249,0.00067088654,9.5149414e-7,0.45569018,0.00004104571,0.54030013,0.00031795818,0.00015318733],"about_ca_topic_score_codex":0.000005981103,"about_ca_topic_score_gemma":0.0000010083354,"teacher_disagreement_score":0.4052179,"about_ca_system_score_codex":0.00006271652,"about_ca_system_score_gemma":0.00026714726,"threshold_uncertainty_score":0.8116174},"labels":[],"label_agreement":null},{"id":"W2237415976","doi":"","title":"Using Pivots to Speed-Up k-Medoids Clustering","year":2011,"lang":"en","type":"article","venue":"Cadernos de Linguística e Teoria da Literatura (Universidade Federal de Minas Gerais)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Medoid; Cluster analysis; Computer science; k-medoids; Data mining; Canopy clustering algorithm; Correlation clustering; CURE data clustering algorithm; Algorithm; Set (abstract data type); Artificial intelligence","score_opus":0.07390989392732218,"score_gpt":0.31530947885642335,"score_spread":0.24139958492910119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2237415976","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":[0.1303115,0.00020276985,0.8618888,0.00061463274,0.0016005957,0.0005300381,0.00002241643,0.0005566167,0.004272585],"genre_scores_gemma":[0.539603,0.000007799684,0.45634544,0.0006676021,0.0006063027,0.000009722103,0.000008355669,0.00007808882,0.0026737065],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99525404,0.00027040497,0.00051012647,0.0012956583,0.00072162,0.0019481628],"domain_scores_gemma":[0.9967803,0.0002778357,0.00017599744,0.001183747,0.00042340346,0.0011587166],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005656428,0.00062526803,0.0005587256,0.00076670875,0.00080459367,0.002058365,0.0024094628,0.00039409177,0.00012204959],"category_scores_gemma":[0.00048208173,0.00071654056,0.00022549414,0.001422656,0.00018434132,0.001603459,0.0016104388,0.0011029488,0.00016091805],"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":[0.0018278868,0.0008491365,0.002106885,0.0011105475,0.00078274834,0.014959281,0.24572484,0.019811887,0.4587214,0.15122825,0.0043275636,0.09854956],"study_design_scores_gemma":[0.0028941305,0.0009549337,0.0031655869,0.0008539616,0.00008314041,0.0020013384,0.0023412316,0.94794637,0.012875553,0.0075644306,0.01665724,0.0026620834],"about_ca_topic_score_codex":0.00021105571,"about_ca_topic_score_gemma":0.000008224817,"teacher_disagreement_score":0.9281345,"about_ca_system_score_codex":0.0010181789,"about_ca_system_score_gemma":0.00041198722,"threshold_uncertainty_score":0.9995286},"labels":[],"label_agreement":null},{"id":"W2270192120","doi":"10.1371/journal.pone.0144059","title":"A Comparison Study on Similarity and Dissimilarity Measures in Clustering Continuous Data","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":408,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"Universiti Malaya","keywords":"Similarity (geometry); Cluster analysis; Computer science; Data mining; Benchmark (surveying); Distance measures; Similarity measure; Measure (data warehouse); Cluster (spacecraft); Pattern recognition (psychology); Artificial intelligence; Geography","score_opus":0.43152004598405463,"score_gpt":0.4023074041110184,"score_spread":0.029212641873036238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2270192120","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":[0.8611459,0.00021314346,0.13537756,0.0013184033,0.00008157251,0.0010133717,0.00002034751,0.0002453682,0.0005843471],"genre_scores_gemma":[0.9568639,0.0000070659726,0.042935453,0.000059899703,0.00004276871,0.000026374906,0.0000047909293,0.000013886516,0.000045849763],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972825,0.00026790737,0.0003030888,0.00075001863,0.0010012446,0.00039525083],"domain_scores_gemma":[0.99784046,0.0001788096,0.00006778325,0.0015519001,0.000121521494,0.00023955021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013595278,0.00017172439,0.00042349307,0.00014517881,0.000086676846,0.00022834502,0.001563195,0.00005693714,0.0000010986611],"category_scores_gemma":[0.0007806861,0.00016827084,0.0000103700795,0.00033362088,0.00005996576,0.00060110964,0.0029094333,0.00048102657,0.0000093996505],"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":[0.00048279433,0.031879593,0.8636237,0.00024354347,0.0003874583,0.0005972164,0.019107495,0.0019792705,0.0018242609,0.0002853788,0.0003865876,0.07920274],"study_design_scores_gemma":[0.0021372149,0.0009779115,0.08587564,0.00016540212,0.00001857557,0.0000045039424,0.0008618334,0.90819937,0.0007884608,0.0005243316,0.000096850956,0.0003499153],"about_ca_topic_score_codex":0.00018972749,"about_ca_topic_score_gemma":0.00059086765,"teacher_disagreement_score":0.9062201,"about_ca_system_score_codex":0.000107117026,"about_ca_system_score_gemma":0.000062030755,"threshold_uncertainty_score":0.6861886},"labels":[],"label_agreement":null},{"id":"W2276374992","doi":"","title":"A novel evolutionary clustering algorithm based on Gaussian mixture model","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 Victoria","funders":"","keywords":"Cluster analysis; Determining the number of clusters in a data set; Correlation clustering; CURE data clustering algorithm; Single-linkage clustering; Canopy clustering algorithm; Computer science; Fuzzy clustering; Benchmark (surveying); Evolutionary algorithm; Data mining; Algorithm; Entropy (arrow of time); Clustering high-dimensional data; Artificial intelligence","score_opus":0.01715317738749668,"score_gpt":0.2689564433357263,"score_spread":0.25180326594822966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2276374992","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":[0.000034104407,0.00002509114,0.98410374,0.001640982,0.00014863697,0.0001932895,0.000013196188,0.00046721945,0.013373763],"genre_scores_gemma":[0.039838437,0.0000010636471,0.95474106,0.00054261467,0.00014565661,0.000040266266,0.000010113911,0.000025908132,0.0046549058],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977421,0.000030608986,0.00024264323,0.0006548157,0.0007308662,0.0005989611],"domain_scores_gemma":[0.998777,0.000091264825,0.00005149926,0.0008341928,0.000105244915,0.00014083968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017533063,0.00023164193,0.00016935643,0.00025045185,0.00022203881,0.00014224794,0.0009768185,0.00010428692,0.000019604531],"category_scores_gemma":[0.000018685385,0.00020891601,0.00008565922,0.0005254166,0.00005621945,0.00045881496,0.00042072264,0.0002977385,0.00006599984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008020588,0.0001793453,0.0000063208663,0.000011760812,0.0000037094076,0.000028245415,0.00001926254,0.94650555,0.0016694693,0.004408246,0.0011800649,0.045980033],"study_design_scores_gemma":[0.00057528954,0.00007340412,0.00032477765,0.00002747136,0.0000012847388,0.000031346288,0.0000037935604,0.9951539,0.00054081046,0.0023105915,0.0006937121,0.00026364098],"about_ca_topic_score_codex":0.000112736256,"about_ca_topic_score_gemma":0.00001769063,"teacher_disagreement_score":0.048648357,"about_ca_system_score_codex":0.00023213755,"about_ca_system_score_gemma":0.00014541142,"threshold_uncertainty_score":0.85193473},"labels":[],"label_agreement":null},{"id":"W2278576066","doi":"10.3166/isi.20.5.77-101","title":"Matérialisation de cubes de données par des partitions d’ensembles de n-uplets","year":2015,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy","score_opus":0.08654406474758126,"score_gpt":0.3013027100652112,"score_spread":0.21475864531762995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2278576066","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":[0.21174392,0.0010241498,0.78162104,0.0010594649,0.00077279843,0.00035439583,0.00005054496,0.00032042302,0.003053276],"genre_scores_gemma":[0.76958275,0.0004217315,0.22843656,0.00033004803,0.00047993351,0.00019584518,0.00007001448,0.00003226618,0.00045082974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99638057,0.0005437782,0.0008313741,0.0002708413,0.0006410235,0.0013324429],"domain_scores_gemma":[0.99720895,0.00027121403,0.00035334536,0.00055544946,0.0009846154,0.0006264133],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0024334828,0.00033897415,0.00031544443,0.000368989,0.0008048827,0.0016759152,0.0007302635,0.00030462764,0.000034736764],"category_scores_gemma":[0.0022572372,0.00038815156,0.00011325473,0.0008722093,0.00074195466,0.01010335,0.00035796475,0.00035152546,0.00036869367],"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":[0.0001403471,0.00020187274,0.006603343,0.002188219,0.00014337273,0.00008745708,0.19944596,0.26187286,0.0010984611,0.05268474,0.007101953,0.4684314],"study_design_scores_gemma":[0.0009606633,0.00032339364,0.007664796,0.0010232176,0.00004063108,0.0009594015,0.004845003,0.7763075,0.008457906,0.17597415,0.022841226,0.0006021004],"about_ca_topic_score_codex":0.0015075384,"about_ca_topic_score_gemma":0.0001923383,"teacher_disagreement_score":0.55783886,"about_ca_system_score_codex":0.0030488926,"about_ca_system_score_gemma":0.0015252306,"threshold_uncertainty_score":0.99985707},"labels":[],"label_agreement":null},{"id":"W2286286503","doi":"10.1007/978-3-319-49487-6_3","title":"Theoretical Analysis of the k-Means Algorithm – A Survey","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":91,"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; Heuristics; Algorithm; Cluster analysis; Extension (predicate logic); Simplicity; k-means clustering; Artificial intelligence","score_opus":0.018668256590251276,"score_gpt":0.28678644875811515,"score_spread":0.26811819216786387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2286286503","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":[0.000022651775,0.00011581502,0.9960999,0.0006088878,0.00085515797,0.00029168857,0.00006117363,0.00006434925,0.001880386],"genre_scores_gemma":[0.14934923,0.00006115323,0.848594,0.00062589225,0.00029980505,0.000014352743,0.000006254364,0.00006404743,0.0009852847],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949561,0.00018915081,0.0006062053,0.0015081902,0.00195774,0.00078263826],"domain_scores_gemma":[0.99399716,0.0020753075,0.00032428544,0.0028535519,0.0005726646,0.00017702673],"candidate_categories":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0023057335,0.0004525155,0.0007807244,0.001313883,0.00021685327,0.00022795249,0.0072659478,0.00027853955,0.00007152547],"category_scores_gemma":[0.0004329725,0.00027743133,0.0003432321,0.0030446206,0.0031971529,0.00032003914,0.0040211855,0.0007809637,0.000015955457],"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":[0.0000040746345,0.000020837066,0.00012713856,0.000010187776,0.00011108954,0.000020152154,0.0002241561,0.022387773,0.000041417414,0.080964245,0.0000022460638,0.8960867],"study_design_scores_gemma":[0.00013460746,0.000067556284,0.0017315426,0.0001455696,0.00003200969,0.000012555665,4.2305516e-8,0.8422289,0.00051790604,0.15471388,0.00008060535,0.0003348078],"about_ca_topic_score_codex":0.000030868843,"about_ca_topic_score_gemma":0.00013598047,"teacher_disagreement_score":0.8957519,"about_ca_system_score_codex":0.000327894,"about_ca_system_score_gemma":0.0006153568,"threshold_uncertainty_score":0.9999678},"labels":[],"label_agreement":null},{"id":"W2320187719","doi":"10.1515/jisys.2004.13.4.329","title":"Evolutionary, Neural, and Statistical Approaches to Interval Clustering for Web Mining","year":2004,"lang":"en","type":"article","venue":"Journal of Intelligent Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cluster analysis; Data mining; Web mining; Artificial intelligence; Machine learning; World Wide Web; Web service","score_opus":0.15315841354830215,"score_gpt":0.33149553045794183,"score_spread":0.1783371169096397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2320187719","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":[0.021098679,0.00060581666,0.976049,0.0009428744,0.0009348279,0.00030621391,0.0000066810067,0.00002240659,0.00003351969],"genre_scores_gemma":[0.67696774,0.000015252075,0.32263723,0.000032730062,0.00025615437,0.000017037317,4.7409793e-7,0.000013373414,0.00006001249],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831223,0.00006664722,0.0006248017,0.00024018159,0.0004311792,0.00032494994],"domain_scores_gemma":[0.9988483,0.00027620568,0.00020303047,0.00019793847,0.00019959998,0.0002749126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007009379,0.00013942865,0.0002986012,0.00025907683,0.000099410994,0.00022651795,0.0005848975,0.000045947818,0.0000011987704],"category_scores_gemma":[0.00025415188,0.000116472016,0.0000685325,0.00017631342,0.00004340008,0.000382408,0.00030205838,0.00017370806,0.000004777807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003434245,0.0002640277,0.000469573,0.0007648766,0.0002204116,0.000275831,0.00536685,0.839524,0.002078895,0.02428695,0.0012290528,0.12517613],"study_design_scores_gemma":[0.0005475423,0.0011898235,0.0002889491,0.0004289209,0.000008639755,0.0017552205,0.00096610864,0.9905852,0.00036392442,0.0007214215,0.0029433197,0.0002009502],"about_ca_topic_score_codex":0.000012133575,"about_ca_topic_score_gemma":0.0000062903973,"teacher_disagreement_score":0.65586907,"about_ca_system_score_codex":0.00026838243,"about_ca_system_score_gemma":0.00010847028,"threshold_uncertainty_score":0.4749591},"labels":[],"label_agreement":null},{"id":"W2355122750","doi":"","title":"Multilevel Clustering Algorithm Using Core-Sets Coarsening","year":2013,"lang":"en","type":"article","venue":"Jisuanji kexue yu tansuo","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cluster analysis; Hierarchical clustering; Vertex (graph theory); Algorithm; Core (optical fiber); Enhanced Data Rates for GSM Evolution; Data mining; Theoretical computer science; Graph; Artificial intelligence","score_opus":0.07943376252303293,"score_gpt":0.34899215693311125,"score_spread":0.26955839441007834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2355122750","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":[0.033355378,0.00013815868,0.96350425,0.00018960761,0.0008904988,0.00063209055,0.000011431496,0.00055635674,0.0007221991],"genre_scores_gemma":[0.2316212,0.000014717069,0.7668256,0.00023469586,0.00021540967,0.00007605272,0.000006308762,0.00007431797,0.0009316656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99619704,0.00009552533,0.00057517824,0.0009895051,0.0009032727,0.0012394657],"domain_scores_gemma":[0.9975525,0.00025402824,0.00020064769,0.0012370585,0.0003320218,0.00042372776],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003838289,0.00043128233,0.00043905035,0.00033587942,0.0004553305,0.00060166675,0.0017586902,0.00018831677,0.00011089359],"category_scores_gemma":[0.00014302561,0.00043734652,0.00013465417,0.00074118294,0.00014889921,0.0017874136,0.0015458995,0.0005724416,0.00051279063],"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":[0.000007990467,0.00013097814,0.00022919883,0.000079309706,0.00007589134,0.00027102986,0.0013637573,0.017001698,0.028757915,0.00038329684,0.000395486,0.9513034],"study_design_scores_gemma":[0.0006559579,0.000077283934,0.0010001359,0.00009834823,0.000007241999,0.00022299672,0.00012736705,0.99327,0.0021060165,0.0011138709,0.0007975737,0.0005232023],"about_ca_topic_score_codex":0.00038714366,"about_ca_topic_score_gemma":0.000014056632,"teacher_disagreement_score":0.9762683,"about_ca_system_score_codex":0.00031558092,"about_ca_system_score_gemma":0.00013466185,"threshold_uncertainty_score":0.99980783},"labels":[],"label_agreement":null},{"id":"W2370156110","doi":"","title":"Cluster Analysis and Visualization Enhanced Genetic Algorithm——II. Analysis of Cases and Validation","year":2004,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CAE (Canada)","funders":"","keywords":"Visualization; Computer science; Consistency (knowledge bases); Cluster (spacecraft); Robustness (evolution); Data mining; Dimension (graph theory); Algorithm; Process (computing); Cluster analysis; Genetic algorithm; Machine learning; Artificial intelligence; Mathematics; Chemistry","score_opus":0.015945932551580253,"score_gpt":0.3218239109678345,"score_spread":0.30587797841625425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2370156110","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":[0.2924785,0.000061175226,0.7072156,0.000079400575,0.000013234835,0.00008465496,0.000004281723,0.0000393105,0.000023871395],"genre_scores_gemma":[0.70490956,0.00008513296,0.29483753,0.0000392516,0.000008233522,0.000007851412,0.000015038854,0.000004902236,0.00009246789],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867415,0.000061709005,0.00028680087,0.0004431983,0.00034263573,0.00019148692],"domain_scores_gemma":[0.9991019,0.00014387723,0.00010678907,0.0003665756,0.00018852968,0.00009234227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018835958,0.00011992817,0.00029993302,0.0010815278,0.00012509982,0.00009388705,0.0002028467,0.00005051295,0.000014407989],"category_scores_gemma":[0.000080199396,0.00011063513,0.00007383749,0.004027469,0.00007843831,0.00039559466,0.0003550898,0.000046014608,8.5083474e-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":[0.00002336901,0.0002890053,0.0060330546,0.00008452724,0.0052262773,0.000037892776,0.00436933,0.4647474,0.010881491,0.0037692776,0.000007419346,0.50453097],"study_design_scores_gemma":[0.00041549566,0.00014757717,0.033401698,0.00000652021,0.0007284498,0.000009540513,0.00004686139,0.9240197,0.04048241,0.0005669546,0.000007939525,0.00016685882],"about_ca_topic_score_codex":0.00034131535,"about_ca_topic_score_gemma":0.00012127029,"teacher_disagreement_score":0.5043641,"about_ca_system_score_codex":0.000045909324,"about_ca_system_score_gemma":0.000026792339,"threshold_uncertainty_score":0.45115694},"labels":[],"label_agreement":null},{"id":"W23725892","doi":"10.1007/978-3-642-37186-8_4","title":"Spectral Clustering: An Explorative Study of Proximity Measures","year":2013,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":7,"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 Ottawa","funders":"","keywords":"Cluster analysis; Spectral clustering; Measure (data warehouse); Computer science; Euclidean distance; Similarity (geometry); Data mining; Similarity measure; Distance measures; Distance matrix; Usability; Boundary (topology); Artificial intelligence; Pattern recognition (psychology); Mathematics; Algorithm","score_opus":0.1191461492858851,"score_gpt":0.3554448074291799,"score_spread":0.2362986581432948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W23725892","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":[0.0011990083,0.00010402004,0.9442823,0.00024785564,0.00018050915,0.0013261378,0.0000071908157,0.000108934066,0.05254404],"genre_scores_gemma":[0.4363323,0.0010768571,0.561143,0.00016655974,0.000052077696,0.0001803994,0.00002708958,0.00002198845,0.0009997815],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773544,0.00008285829,0.0007410446,0.00035702257,0.0008202297,0.00026339825],"domain_scores_gemma":[0.9956167,0.00015840335,0.00037789583,0.002885641,0.00082199374,0.0001393968],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001101824,0.00022670737,0.0003141262,0.0010010952,0.00036197604,0.00052796083,0.004787133,0.00008243849,0.000007030543],"category_scores_gemma":[0.00005493222,0.00021806441,0.00002830586,0.0004916318,0.0006422452,0.015922507,0.00430326,0.00050076615,0.000030555184],"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":[0.000008721258,0.00026215755,0.00007494577,0.000055411467,0.000018594965,0.0000011637918,0.03315069,0.005488986,0.000018358676,0.17825352,0.000042885877,0.7826246],"study_design_scores_gemma":[0.00041383048,0.0005840201,0.0013060104,0.00011513333,0.0000032654073,0.000014471438,0.00037127742,0.98471785,0.00002749124,0.00833835,0.0037843187,0.00032400023],"about_ca_topic_score_codex":0.000062021056,"about_ca_topic_score_gemma":0.00006681795,"teacher_disagreement_score":0.97922885,"about_ca_system_score_codex":0.0001588439,"about_ca_system_score_gemma":0.00025277157,"threshold_uncertainty_score":0.9978413},"labels":[],"label_agreement":null},{"id":"W2373927542","doi":"10.1142/s0219622016500267","title":"A Hybrid Artificial Fish Swarm Simulated Annealing Optimization Algorithm for Automatic Identification of Clusters","year":2016,"lang":"en","type":"article","venue":"International Journal of Information Technology & Decision Making","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Crandall University; National Research Council Canada; Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Simulated annealing; Swarm behaviour; Fuzzy logic; Fuzzy clustering; A priori and a posteriori; Robustness (evolution); Algorithm; Rate of convergence; Data mining; Convergence (economics); Artificial intelligence","score_opus":0.013617359455804386,"score_gpt":0.3266986201948819,"score_spread":0.3130812607390775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2373927542","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":[0.0180187,0.000017101178,0.9789358,0.0015983013,0.0010567777,0.00023000744,0.000030963336,0.00010369926,0.000008679969],"genre_scores_gemma":[0.43839204,0.000021937703,0.561448,0.00006497258,0.0000498423,0.000006594482,0.000004451576,0.000007560572,0.00000464264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968925,0.000034007884,0.0017734327,0.0001563472,0.00092963787,0.00021406691],"domain_scores_gemma":[0.99401546,0.00060894823,0.001965271,0.00030456332,0.0030604831,0.000045293662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011049135,0.00013563498,0.00024242132,0.0020869654,0.000098140314,0.00018336004,0.001639755,0.00012348946,0.000012046501],"category_scores_gemma":[0.0020120696,0.00010868578,0.00012759503,0.0004926973,0.00008720089,0.0032800187,0.00030623065,0.00015461593,0.000008492439],"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":[0.000041276515,0.000022233775,0.000010215624,0.000009082241,0.000048849644,0.000005024396,0.000094175295,0.18018419,0.00059186004,0.0008726565,0.000056943718,0.8180635],"study_design_scores_gemma":[0.0008817113,0.00011895662,0.000043262473,0.0004812204,0.000007693262,0.00018135297,0.000073355266,0.95604134,0.019064307,0.022801954,0.00019625912,0.00010858442],"about_ca_topic_score_codex":5.5513294e-7,"about_ca_topic_score_gemma":1.8206775e-7,"teacher_disagreement_score":0.8179549,"about_ca_system_score_codex":0.00028195564,"about_ca_system_score_gemma":0.00012755163,"threshold_uncertainty_score":0.44320774},"labels":[],"label_agreement":null},{"id":"W2390764","doi":"10.1007/978-3-642-20841-6_22","title":"Semi-supervised Parameter-Free Divisive Hierarchical Clustering of Categorical Data","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","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":"Université de Sherbrooke","funders":"","keywords":"Cluster analysis; Computer science; Categorical variable; Hierarchical clustering; Artificial intelligence; Canopy clustering algorithm; CURE data clustering algorithm; Data mining; Single-linkage clustering; Correlation clustering; Constrained clustering; Pattern recognition (psychology); Data stream clustering; Constraint (computer-aided design); Dendrogram; Machine learning; Mathematics","score_opus":0.06073154317108151,"score_gpt":0.3008922138382473,"score_spread":0.24016067066716582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2390764","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":[0.0000469893,0.00032965,0.9954942,0.00041662063,0.0014477273,0.0005339072,0.000045173903,0.00017004817,0.0015156746],"genre_scores_gemma":[0.061709393,0.00011034002,0.93692565,0.00033244878,0.0005240553,0.00001554563,0.000027006672,0.00008161232,0.00027393195],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928166,0.00010556718,0.000988429,0.002868698,0.0020084279,0.0012122234],"domain_scores_gemma":[0.9897041,0.0015366061,0.00038516382,0.0075732465,0.00039364124,0.00040727408],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0013923887,0.0007270021,0.0010342465,0.001086668,0.00022961857,0.00034844215,0.020106941,0.00045562486,0.000037368893],"category_scores_gemma":[0.0008085124,0.000667838,0.00015649795,0.0009387565,0.0016352725,0.0012217851,0.025887523,0.00181799,0.0000298381],"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":[0.000023634315,0.00006609156,0.000037787995,0.00012673592,0.000030121588,0.00029603843,0.00081909617,0.009335771,0.000115804585,0.0043804506,0.000029474108,0.984739],"study_design_scores_gemma":[0.00040236086,0.0002831987,0.00008378962,0.00027314626,0.000008209276,0.00013543919,1.6559139e-7,0.8173631,0.0005055427,0.17996727,0.00035442482,0.0006233517],"about_ca_topic_score_codex":0.00008863229,"about_ca_topic_score_gemma":0.00007034693,"teacher_disagreement_score":0.98411566,"about_ca_system_score_codex":0.00032335328,"about_ca_system_score_gemma":0.0007865429,"threshold_uncertainty_score":0.9995773},"labels":[],"label_agreement":null},{"id":"W2394938095","doi":"","title":"Hybrid hierarchical clustering: cluster assessment via cluster validation indices.","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 Ottawa","funders":"","keywords":"Cluster analysis; Hierarchical clustering; Single-linkage clustering; Computer science; Data mining; Benchmark (surveying); Cluster (spacecraft); Brown clustering; Correlation clustering; Fuzzy clustering; Consensus clustering; Hierarchical clustering of networks; CURE data clustering algorithm; Pattern recognition (psychology); Artificial intelligence; Geography","score_opus":0.025519508021927914,"score_gpt":0.33101121721370524,"score_spread":0.3054917091917773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2394938095","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":[0.012789696,0.00004169222,0.9740768,0.002494246,0.0010065406,0.0005117866,0.0000027571384,0.00046633332,0.008610132],"genre_scores_gemma":[0.6389428,0.000009207371,0.35761574,0.0010927038,0.00042181558,0.00008714117,0.000015855212,0.00003712525,0.0017776586],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960096,0.00034196023,0.0005308322,0.00068798824,0.0011518336,0.0012777888],"domain_scores_gemma":[0.9976571,0.00033169004,0.00014375518,0.001150793,0.00013810855,0.00057853316],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013772263,0.00034133007,0.00030965442,0.00034623884,0.00029172102,0.00038894574,0.0014774479,0.00011738032,0.00018031747],"category_scores_gemma":[0.00006737407,0.0003021179,0.00012226269,0.00042926823,0.00011110649,0.0027017265,0.002310925,0.000639014,0.00045808888],"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":[0.00014087265,0.0018370872,0.011494485,0.00035365942,0.00029353736,0.000088580375,0.0034203099,0.01850536,0.0055401204,0.02075013,0.010034974,0.9275409],"study_design_scores_gemma":[0.0013671853,0.00017925893,0.0071678087,0.000029452462,0.000010894282,0.00031785294,0.000025376921,0.9663342,0.0057286457,0.0024875933,0.015659338,0.0006923844],"about_ca_topic_score_codex":0.000031421685,"about_ca_topic_score_gemma":0.000004047466,"teacher_disagreement_score":0.9478288,"about_ca_system_score_codex":0.000350096,"about_ca_system_score_gemma":0.00010136435,"threshold_uncertainty_score":0.9999431},"labels":[],"label_agreement":null},{"id":"W2398976774","doi":"10.5591/978-1-57735-516-8/ijcai11-195","title":"Discerning linkage-based algorithms among hierarchical clustering methods","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Algorithm; Hierarchical clustering; Linkage (software); Class (philosophy); Canopy clustering algorithm; Hierarchical clustering of networks; Complete linkage; Focus (optics); Data mining; Correlation clustering; Artificial intelligence","score_opus":0.07758011686625375,"score_gpt":0.3613604285279193,"score_spread":0.2837803116616655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398976774","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":[0.0013052942,0.00003342901,0.9855373,0.00018554059,0.000371151,0.00021188459,8.968987e-7,0.00074893184,0.011605597],"genre_scores_gemma":[0.06397444,0.0000038530275,0.93443215,0.00016262675,0.00009399238,0.000051368785,0.0000015760561,0.000035684145,0.0012443227],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710244,0.0003825269,0.00038007885,0.000801595,0.0005145709,0.00081878365],"domain_scores_gemma":[0.9979926,0.00036009634,0.0000881792,0.0010767186,0.0001070112,0.0003753915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011292846,0.00026808085,0.00028427807,0.00027786568,0.0002586513,0.00019996605,0.0018682661,0.00012548162,0.00015827303],"category_scores_gemma":[0.0001771531,0.00023291228,0.00012888215,0.00063764094,0.00020862199,0.0007501832,0.0013980783,0.00062789465,0.00007786004],"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":[0.000017095745,0.000119883385,0.0010132835,0.000044916935,0.000032030064,0.00016104957,0.0015053375,0.0024012008,0.0012491924,0.0026192789,0.00003077754,0.9908059],"study_design_scores_gemma":[0.00040338899,0.00013152837,0.006238766,0.000037515598,0.0000033372467,0.000018107778,0.00003662954,0.97833407,0.011957628,0.0020332362,0.00046706956,0.00033870563],"about_ca_topic_score_codex":0.00016277915,"about_ca_topic_score_gemma":0.000018913775,"teacher_disagreement_score":0.99046725,"about_ca_system_score_codex":0.00009983048,"about_ca_system_score_gemma":0.00009050055,"threshold_uncertainty_score":0.9497887},"labels":[],"label_agreement":null},{"id":"W2399784609","doi":"","title":"Bruno Simeone's Work in Clustering.","year":2011,"lang":"en","type":"article","venue":"Cologne Twente Workshop on Graphs and Combinatorial Optimization","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":"HEC Montréal","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence","score_opus":0.025207815627535973,"score_gpt":0.25765075609501553,"score_spread":0.23244294046747957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2399784609","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":[0.028783072,0.00035916327,0.960874,0.00041521783,0.0047263396,0.000842096,0.0000014705059,0.00042948697,0.003569133],"genre_scores_gemma":[0.8808942,0.00057197385,0.11773742,0.00022168113,0.000065560685,0.00012227001,0.000008523482,0.000040708346,0.000337669],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982179,0.00013547385,0.0003178074,0.0005783974,0.00029920627,0.0004512518],"domain_scores_gemma":[0.9990123,0.00015864061,0.00011111612,0.00045804633,0.00010798415,0.00015193656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000347777,0.00022306648,0.00025932826,0.00037949003,0.00016141076,0.0001267253,0.000595538,0.00017375316,0.000026258205],"category_scores_gemma":[0.000109061904,0.00022606782,0.000051478684,0.0014285388,0.00010279444,0.00042262312,0.00044896407,0.0003405324,0.0000079052525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002869248,0.002560079,0.0062951637,0.000090819936,0.00012766925,0.00035186962,0.0054878104,0.43401524,0.00005389789,0.32120287,0.0011982203,0.22574711],"study_design_scores_gemma":[0.005962053,0.0012217881,0.008876815,0.00033292142,0.000015222603,0.000015346184,0.00017153566,0.9442329,0.00019697494,0.03716251,0.00081435865,0.0009975738],"about_ca_topic_score_codex":0.000017484217,"about_ca_topic_score_gemma":0.0000073740093,"teacher_disagreement_score":0.8521111,"about_ca_system_score_codex":0.00008181659,"about_ca_system_score_gemma":0.000038470855,"threshold_uncertainty_score":0.9218778},"labels":[],"label_agreement":null},{"id":"W2408186052","doi":"10.1137/1.9781611973440.96","title":"Density-Based Clustering Validation","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":262,"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; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Cluster analysis; Computer science; Data mining; Kernel density estimation; Cluster (spacecraft); Kernel (algebra); Mathematics; Artificial intelligence; Pattern recognition (psychology); Statistics; Combinatorics","score_opus":0.02015969811375551,"score_gpt":0.284899446381844,"score_spread":0.2647397482680885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2408186052","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":[0.0041747196,0.0000016115697,0.9903093,0.0007407663,0.00014193027,0.00006346686,7.707574e-8,0.00031847018,0.004249689],"genre_scores_gemma":[0.5202144,3.0011725e-7,0.47898623,0.0002843829,0.00004120487,0.000005648779,8.886765e-7,0.000005674014,0.0004613044],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907404,0.00006507905,0.000103645034,0.00025970544,0.0002699811,0.00022752241],"domain_scores_gemma":[0.99921113,0.00011516944,0.000025304287,0.00049453095,0.00007578744,0.00007809412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003345482,0.000071911774,0.00007471737,0.00008736449,0.000094967756,0.00013626221,0.0005213515,0.000028224513,0.000014618865],"category_scores_gemma":[0.00008506835,0.0000668047,0.000025542424,0.00022391163,0.000018676837,0.0003083158,0.00027278007,0.00008212535,0.00016279228],"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":[0.000011732739,0.00007471466,0.0007118647,0.000064620275,0.00001092541,0.00001509127,0.0001882131,0.13165647,0.015511261,0.0356356,0.000393315,0.81572616],"study_design_scores_gemma":[0.00018368925,0.000038064438,0.0004239237,0.000005903991,4.485261e-7,0.0000043538507,0.0000018497127,0.9618256,0.034128785,0.0013662581,0.0019306727,0.00009043209],"about_ca_topic_score_codex":0.000014630244,"about_ca_topic_score_gemma":0.000006047398,"teacher_disagreement_score":0.83016914,"about_ca_system_score_codex":0.000040443356,"about_ca_system_score_gemma":0.00002268143,"threshold_uncertainty_score":0.27242166},"labels":[],"label_agreement":null},{"id":"W2417989999","doi":"","title":"Hierarchical Information-Theoretic Co-clustering for High Dimensional Data","year":2011,"lang":"en","type":"article","venue":"HKBU Institutional Repository (Hong Kong Baptist University)","topic":"Advanced Clustering Algorithms Research","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":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Cluster analysis; Hierarchical clustering; Data mining; Biclustering; Data science; Artificial intelligence; Fuzzy clustering; CURE data clustering algorithm","score_opus":0.03773163137134344,"score_gpt":0.2488227367389772,"score_spread":0.21109110536763376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2417989999","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":[0.010014872,0.000013496416,0.9728039,0.00009142124,0.0007942018,0.00030556277,0.00010195027,0.00022766228,0.01564696],"genre_scores_gemma":[0.72728175,0.000006065096,0.2706084,0.0000809885,0.00015413343,0.00000584836,0.00020993949,0.000012742389,0.0016401265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980397,0.00008163069,0.00029464526,0.0005609006,0.0006044042,0.0004187177],"domain_scores_gemma":[0.99813306,0.0001888048,0.00012919436,0.0010252143,0.00028222072,0.00024151348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026531407,0.0002055148,0.0001890053,0.00038823672,0.0011750425,0.00015296464,0.0022374003,0.00011285066,0.00002123416],"category_scores_gemma":[0.00013067637,0.00022807461,0.000068800626,0.00041206984,0.0005870846,0.003664517,0.0014854886,0.00028390897,0.000060301172],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030728173,0.00018680419,0.00066856697,0.00012875865,0.0001242617,0.0008137445,0.00044533855,0.0066100336,0.0006077723,0.97795457,0.0005095134,0.011643352],"study_design_scores_gemma":[0.004000044,0.00049922883,0.019391801,0.00030045654,0.00007243705,0.0014745926,0.00015904527,0.89511263,0.0038838752,0.008326474,0.065284446,0.0014949538],"about_ca_topic_score_codex":0.00010312742,"about_ca_topic_score_gemma":0.000008050882,"teacher_disagreement_score":0.9696281,"about_ca_system_score_codex":0.00035217297,"about_ca_system_score_gemma":0.00055899145,"threshold_uncertainty_score":0.9300613},"labels":[],"label_agreement":null},{"id":"W2494099403","doi":"10.1145/2851613.2851643","title":"PatchWork, a scalable density-grid clustering algorithm","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Cluster analysis; Computer science; Scalability; SPARK (programming language); CURE data clustering algorithm; Data mining; Canopy clustering algorithm; Correlation clustering; Computation; Knowledge extraction; Data stream clustering; Anomaly detection; Outlier; Algorithm; Artificial intelligence; Database","score_opus":0.017057390880455377,"score_gpt":0.2673199606908087,"score_spread":0.25026256981035333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2494099403","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":[0.00091445923,0.00003394351,0.9928827,0.0018453219,0.00056775217,0.00014910681,0.000002435501,0.00056763,0.0030366268],"genre_scores_gemma":[0.024596306,0.000053693486,0.9580076,0.00028171108,0.0003082987,0.000034560522,5.9047517e-7,0.00002867729,0.016688593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978146,0.00006820112,0.00023669678,0.0006270064,0.0005208831,0.00073261803],"domain_scores_gemma":[0.9983708,0.00021428835,0.000049009504,0.0009603523,0.0001552582,0.00025028028],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035048017,0.00018663259,0.00019634192,0.0001397482,0.00016344068,0.00017963942,0.0012250679,0.00007324203,0.00009338309],"category_scores_gemma":[0.000079320795,0.00012320677,0.00006777726,0.00046798837,0.00007710839,0.0009530478,0.0015350268,0.00014024632,0.0008275414],"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":[0.0000034329591,0.00003455135,0.00009988416,0.000006718873,0.000011482452,0.00007170814,0.00005651294,0.000057309637,0.002991818,0.000773987,0.0010020769,0.9948905],"study_design_scores_gemma":[0.0019932897,0.00035278214,0.0012867809,0.0002139371,0.0000051661023,0.0003753646,0.00004379513,0.89907444,0.048609763,0.00889432,0.038091797,0.0010585458],"about_ca_topic_score_codex":0.000048351583,"about_ca_topic_score_gemma":0.000020607842,"teacher_disagreement_score":0.993832,"about_ca_system_score_codex":0.00015284777,"about_ca_system_score_gemma":0.00006504205,"threshold_uncertainty_score":0.9999504},"labels":[],"label_agreement":null},{"id":"W2512875827","doi":"10.18637/jss.v072.i05","title":"<b>RSKC</b>: An<i>R</i>Package for a Robust and Sparse K-Means Clustering Algorithm","year":2016,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Outlier; Cluster analysis; Computer science; Data mining; R package; Identification (biology); Algorithm; Monte Carlo method; Artificial intelligence; Mathematics; Statistics","score_opus":0.033844006603445616,"score_gpt":0.3084657004614797,"score_spread":0.2746216938580341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512875827","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":[0.00033361156,0.00009500085,0.99828714,0.0006310376,0.0002733649,0.00015850387,0.00015309542,0.00006111642,0.000007142326],"genre_scores_gemma":[0.0039340183,0.00006315737,0.9954907,0.00010404449,0.00024053085,0.000009092897,0.0000014639207,0.000027678501,0.00012931647],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804986,0.00008658684,0.0004928761,0.00033641013,0.00053299265,0.00050129154],"domain_scores_gemma":[0.99709547,0.0014405621,0.00020828958,0.00032886225,0.0004284634,0.0004983586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062444387,0.00018241405,0.00034270814,0.00014136602,0.00015089664,0.00017845619,0.00068444415,0.0000749302,0.000023210972],"category_scores_gemma":[0.0012378943,0.00012241036,0.0000640147,0.00014959488,0.00015533851,0.0010296287,0.00031650305,0.00021424763,0.0000069052103],"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":[0.000054378168,0.00006938931,0.000106422325,0.00004848534,0.000026923215,0.00022277333,0.0001412652,0.00023752694,0.00040973138,0.001164303,0.00042867826,0.9970901],"study_design_scores_gemma":[0.009139725,0.0061507537,0.0089109475,0.0008803841,0.0000845441,0.0034839557,0.00017790716,0.87037826,0.0015938944,0.0860487,0.011792129,0.0013588076],"about_ca_topic_score_codex":0.0000050348476,"about_ca_topic_score_gemma":0.000005809253,"teacher_disagreement_score":0.9957313,"about_ca_system_score_codex":0.000117581396,"about_ca_system_score_gemma":0.000111130255,"threshold_uncertainty_score":0.49917495},"labels":[],"label_agreement":null},{"id":"W2515705452","doi":"10.18637/jss.v073.i07","title":"My Early Interactions with Jan and Some of His Lost Papers","year":2016,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Advanced Clustering Algorithms Research","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 Victoria","funders":"","keywords":"Period (music); Scaling; Multidimensional scaling; Computer science; History; Mathematics; Art; Machine learning","score_opus":0.012775728765790148,"score_gpt":0.2838603270710328,"score_spread":0.2710845983052427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515705452","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":[0.02084496,0.000047952304,0.9781627,0.0007423414,0.00008309336,0.00003827943,0.000028441384,0.000010822168,0.000041397278],"genre_scores_gemma":[0.44815913,0.000040715484,0.55137914,0.00003980085,0.000057481608,0.0000010505096,1.6962464e-7,0.000009344552,0.00031315957],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99896353,0.000042032094,0.0002680243,0.00013199402,0.00040703866,0.00018736297],"domain_scores_gemma":[0.99828583,0.0009527828,0.00016661303,0.00015095025,0.00024566893,0.00019815392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013670333,0.00008126407,0.00018703479,0.000096888965,0.000044686196,0.000041910105,0.00028672046,0.00002248225,0.000060625047],"category_scores_gemma":[0.00047966556,0.00004623168,0.000025172509,0.00011329687,0.00018337264,0.0006098609,0.00012654149,0.00017438355,0.000008495708],"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":[0.00018422745,0.00012177304,0.0061970074,0.00006225516,0.000102836755,0.0003896009,0.00043980766,0.000040332903,0.0031689191,0.012277083,0.00034010393,0.97667605],"study_design_scores_gemma":[0.014548596,0.018753208,0.768164,0.0044106706,0.00021102841,0.0062364107,0.00052430294,0.0058759297,0.011697601,0.14466743,0.022877142,0.0020337088],"about_ca_topic_score_codex":0.000008198306,"about_ca_topic_score_gemma":0.0000028914199,"teacher_disagreement_score":0.97464234,"about_ca_system_score_codex":0.000065859866,"about_ca_system_score_gemma":0.000078879064,"threshold_uncertainty_score":0.18852732},"labels":[],"label_agreement":null},{"id":"W2520601089","doi":"10.1145/2938503.2938520","title":"A new scalable aggregation scheme for fuzzy clustering Taking unstructured textual resources as a case","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Cluster analysis; Computer science; Scalability; Scheme (mathematics); Fuzzy clustering; Data mining; Artificial intelligence; Fuzzy logic; Correlation clustering; CURE data clustering algorithm; Machine learning; Database; Mathematics","score_opus":0.026825741286833293,"score_gpt":0.3094472715279418,"score_spread":0.28262153024110853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520601089","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":[0.02009723,0.000052677264,0.97580373,0.0011948183,0.00016123896,0.00037916197,0.0000032794917,0.00034120335,0.0019666736],"genre_scores_gemma":[0.25727808,0.0000040044047,0.7342226,0.00010500328,0.00022518402,0.000038413506,6.1791144e-7,0.000023574996,0.0081025185],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998123,0.00004206679,0.00026634117,0.0006030077,0.00037612816,0.00058945257],"domain_scores_gemma":[0.9985545,0.00030909918,0.00013683818,0.0006078927,0.00014881254,0.00024283622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028616824,0.0001872677,0.00017717341,0.00018093426,0.0002807631,0.00028734538,0.00071248057,0.00008958563,0.00008194688],"category_scores_gemma":[0.00041702876,0.00013232972,0.00006910811,0.00039832422,0.000050825733,0.0009149429,0.0006269913,0.000100424615,0.000056620614],"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":[0.000039444276,0.000008497304,0.000028501674,0.000026253307,0.000018015839,0.00019219125,0.00049138896,0.0003315865,0.009187149,0.0048034317,0.0004340863,0.98443943],"study_design_scores_gemma":[0.0063954396,0.0007689068,0.0001498131,0.00054010516,0.0000135127175,0.008836851,0.00058428815,0.86090136,0.05369289,0.032434076,0.034377802,0.0013049495],"about_ca_topic_score_codex":0.00032887558,"about_ca_topic_score_gemma":0.00018996697,"teacher_disagreement_score":0.9831345,"about_ca_system_score_codex":0.00015289748,"about_ca_system_score_gemma":0.00012593216,"threshold_uncertainty_score":0.5396249},"labels":[],"label_agreement":null},{"id":"W2525029050","doi":"10.1007/978-3-319-47160-0_1","title":"Advances in Rough and Soft Clustering: Meta-Clustering, Dynamic Clustering, Data-Stream Clustering","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"Saint Mary's University","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Fuzzy clustering; Data stream clustering; CURE data clustering algorithm; Canopy clustering algorithm; Correlation clustering; Consensus clustering; Conceptual clustering; Clustering high-dimensional data; Artificial intelligence; Machine learning","score_opus":0.04102602574981118,"score_gpt":0.3191668127387236,"score_spread":0.2781407869889124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2525029050","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":[0.000020547333,0.006295671,0.9866653,0.0009586946,0.0020657517,0.0010839821,0.00007740824,0.00042936756,0.0024032567],"genre_scores_gemma":[0.048496,0.004355631,0.94227886,0.001012147,0.0008191058,0.00015642507,0.000044640157,0.00034132766,0.0024958795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98840606,0.00016757137,0.0016276268,0.0052497867,0.0021597228,0.0023892422],"domain_scores_gemma":[0.9919216,0.0011977204,0.00073287357,0.0052663884,0.0003033143,0.0005780956],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.0023548508,0.0016885266,0.002016761,0.002104175,0.000509614,0.0013693876,0.010320695,0.0006718818,0.000050952545],"category_scores_gemma":[0.00033694287,0.0014435515,0.00024925038,0.0010779648,0.0015791869,0.0050826203,0.022879934,0.0019324442,0.000051319075],"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":[0.00003516134,0.00003880013,0.000021903785,0.00030574627,0.000067910914,0.0003863959,0.0005083306,0.17100008,0.00009543503,0.0001909064,0.0000038740945,0.82734543],"study_design_scores_gemma":[0.0009590837,0.00029095865,0.000056696346,0.0011714738,0.000051953848,0.0005330568,0.0000012752911,0.97630733,0.000065243636,0.01337673,0.005581012,0.0016052038],"about_ca_topic_score_codex":0.00008566772,"about_ca_topic_score_gemma":0.005165661,"teacher_disagreement_score":0.8257403,"about_ca_system_score_codex":0.0010877568,"about_ca_system_score_gemma":0.0005938742,"threshold_uncertainty_score":0.9996673},"labels":[],"label_agreement":null},{"id":"W2529045002","doi":"10.1007/s10115-016-0998-9","title":"Finding multiple stable clusterings","year":2016,"lang":"en","type":"article","venue":"Knowledge and Information Systems","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":"Simon Fraser University","funders":"Office of Naval Research; National Science Foundation","keywords":"Cluster analysis; Computer science; Data mining; Constrained clustering; Clustering high-dimensional data; Spectral clustering; Fuzzy clustering; Correlation clustering; Consensus clustering; Partition (number theory); CURE data clustering algorithm; Stability (learning theory); Machine learning; Artificial intelligence; Mathematics","score_opus":0.022548493315349666,"score_gpt":0.2736265916603705,"score_spread":0.2510780983450208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529045002","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":[0.0047340933,0.00022384975,0.98159647,0.00012158056,0.0005395984,0.00020807842,0.0000054462907,0.00018033877,0.012390518],"genre_scores_gemma":[0.9928983,0.00007328569,0.004041505,0.000028669134,0.00008257851,0.00005321547,0.0000018511868,0.0000058419564,0.0028147802],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991032,0.00003738832,0.00028578303,0.00013057608,0.0001810781,0.0002619663],"domain_scores_gemma":[0.9992027,0.0001558547,0.00008670562,0.00027969797,0.00017034484,0.00010464793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039127754,0.00009507349,0.00011946516,0.00017933313,0.00015263738,0.00028575154,0.0003230508,0.000048431557,0.0000036538463],"category_scores_gemma":[0.00010640192,0.00006444844,0.000018719033,0.00022301638,0.000026488005,0.0063912934,0.0003625768,0.0000531164,0.00048436262],"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":[0.000017923303,0.000029954192,0.002227983,0.000526317,0.000030355232,0.000002948287,0.008420843,0.00024133349,0.0028659818,0.03969935,0.0034992583,0.94243777],"study_design_scores_gemma":[0.0010005746,0.00006843887,0.0012514404,0.00022511036,0.000001120048,0.00005478034,0.00017827998,0.32065454,0.0011967033,0.00008074491,0.6750448,0.00024345791],"about_ca_topic_score_codex":0.000013658701,"about_ca_topic_score_gemma":0.0000022314773,"teacher_disagreement_score":0.9881642,"about_ca_system_score_codex":0.000083933846,"about_ca_system_score_gemma":0.00003732493,"threshold_uncertainty_score":0.62256634},"labels":[],"label_agreement":null},{"id":"W2532543454","doi":"10.1109/is.2006.348479","title":"A Method for Fuzzy Clustering with Ordinal Attributes Replaced by Fuzzy Set Parameters","year":2006,"lang":"en","type":"article","venue":"2006 3rd International IEEE Conference Intelligent Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Mathematics; Ordinal data; Fuzzy set; Ordinal regression; Cluster analysis; Fuzzy clustering; Fuzzy logic; Ordinal optimization; Data mining; Set (abstract data type); Artificial intelligence; Fuzzy classification; Pattern recognition (psychology); Computer science; Statistics","score_opus":0.05653600829032689,"score_gpt":0.33658797172013016,"score_spread":0.28005196342980326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2532543454","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":[0.0029212655,0.00013686066,0.990007,0.0012719724,0.0016675642,0.0010515162,0.00029531468,0.00028256295,0.002365957],"genre_scores_gemma":[0.6440184,0.000035880857,0.338798,0.0001601239,0.0005189455,0.0010011955,0.0002719333,0.00008051408,0.015114985],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958981,0.00018470893,0.00087528606,0.001122015,0.0011070987,0.0008127626],"domain_scores_gemma":[0.99679303,0.00069742743,0.00042812753,0.00074246794,0.0011413705,0.0001975714],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009129891,0.00046063177,0.0005074418,0.0003459435,0.00020565411,0.0009829998,0.0020568657,0.00015623856,0.000019342311],"category_scores_gemma":[0.00010489791,0.0004097003,0.00015240809,0.0004057128,0.00011282274,0.000788735,0.00027327213,0.0003313181,0.00006443739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012095474,0.00076072523,0.0026660166,0.00059367163,0.0011277648,0.00021729757,0.0010127946,0.7070045,0.033792917,0.09498873,0.09270602,0.06392],"study_design_scores_gemma":[0.0007952894,0.00041637407,0.000045472578,0.00030689657,0.000016155698,0.00025417987,0.00019496435,0.94661486,0.01724217,0.0018576527,0.031605363,0.0006506322],"about_ca_topic_score_codex":0.0021720806,"about_ca_topic_score_gemma":0.00022603526,"teacher_disagreement_score":0.651209,"about_ca_system_score_codex":0.0005066683,"about_ca_system_score_gemma":0.00017645233,"threshold_uncertainty_score":0.9998355},"labels":[],"label_agreement":null},{"id":"W2554498112","doi":"10.1109/ijcnn.2016.7727579","title":"LVC: Local Variance-based Clustering","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"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 Waterloo","funders":"","keywords":"Cluster analysis; DBSCAN; Computer science; Spectral clustering; Variance (accounting); Data mining; Artificial intelligence; Outlier; Pattern recognition (psychology); CURE data clustering algorithm; Correlation clustering; Clustering high-dimensional data; Single-linkage clustering","score_opus":0.021927587469671387,"score_gpt":0.28175319326366105,"score_spread":0.25982560579398967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2554498112","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":[0.00014394676,0.000013503034,0.9917178,0.0032683683,0.00023390945,0.00008841252,9.0709284e-7,0.00040046652,0.004132645],"genre_scores_gemma":[0.4883545,0.0000041433195,0.5065581,0.00043640274,0.00007605078,0.000024742714,1.9887987e-7,0.000015098037,0.004530773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856246,0.00004655933,0.00015613475,0.00041800388,0.00036039413,0.00045646675],"domain_scores_gemma":[0.9988155,0.00020147106,0.000029413135,0.0007204425,0.00008113783,0.0001520682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022371407,0.00011703021,0.00011187845,0.000092266244,0.00008579206,0.0000837418,0.0010160246,0.000046198496,0.00011318016],"category_scores_gemma":[0.000052928197,0.00007483903,0.000041693227,0.00028792542,0.00008839773,0.00051807624,0.00051942345,0.00007916218,0.0004565084],"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":[0.000010346204,0.00002866462,0.00004540758,0.000010982669,0.0000061366113,0.000047428242,0.000026454525,0.003252212,0.0046832394,0.008117658,0.00026628593,0.9835052],"study_design_scores_gemma":[0.00095089636,0.00011139495,0.00040872814,0.000058266312,8.2950106e-7,0.000022534643,0.0000058458795,0.9660908,0.018174175,0.0027256734,0.0111911325,0.00025974846],"about_ca_topic_score_codex":0.000018844252,"about_ca_topic_score_gemma":0.000011546863,"teacher_disagreement_score":0.98324543,"about_ca_system_score_codex":0.00013302412,"about_ca_system_score_gemma":0.000093329014,"threshold_uncertainty_score":0.5867644},"labels":[],"label_agreement":null},{"id":"W2556640145","doi":"10.3233/jifs-169172","title":"Double fuzzy C-means model and its application in the technology innovation of China","year":2016,"lang":"en","type":"article","venue":"Journal of Intelligent & Fuzzy Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Department of Family and Community Medicine, University of Toronto; National Social Science Fund of China; National Natural Science Foundation of China","keywords":"Fuzzy logic; Data mining; Computer science; Class (philosophy); Fuzzy clustering; Cluster analysis; Index (typography); Cluster (spacecraft); Artificial intelligence; Set (abstract data type); Fuzzy set; Pattern recognition (psychology)","score_opus":0.03422056838834272,"score_gpt":0.3118910415095601,"score_spread":0.2776704731212174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2556640145","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":[0.20168735,0.00068699487,0.7949668,0.0018623066,0.00014419627,0.0003126652,0.0000013778141,0.000013813667,0.00032444551],"genre_scores_gemma":[0.9962008,0.00022065332,0.0033704124,0.000013135801,0.00006140818,0.000022130578,1.7385105e-7,0.0000072582434,0.00010405447],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983005,0.00006872266,0.0007686762,0.00017168258,0.0004912241,0.00019918475],"domain_scores_gemma":[0.99841964,0.000094384806,0.00055692176,0.00034937606,0.00054678874,0.000032857737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014873743,0.0001021885,0.0002306864,0.00072340237,0.000043007392,0.00004236451,0.0009698788,0.00008377209,3.11328e-7],"category_scores_gemma":[0.00009764495,0.000057112975,0.000031678654,0.00119317,0.000050943356,0.00044261815,0.00014870611,0.00022190022,0.0000048737197],"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":[0.00016220998,0.00031100772,0.0021209028,0.00028599967,0.00007498958,0.000030030065,0.003540213,0.072753675,0.13747732,0.5826038,0.00013097373,0.20050888],"study_design_scores_gemma":[0.0024413632,0.0011555677,0.0014990785,0.0013735151,0.000017067141,0.001355122,0.0013694852,0.84466255,0.058873367,0.0848351,0.0019355819,0.00048221476],"about_ca_topic_score_codex":0.000015976304,"about_ca_topic_score_gemma":0.0000055340724,"teacher_disagreement_score":0.7945134,"about_ca_system_score_codex":0.00011777948,"about_ca_system_score_gemma":0.00008333634,"threshold_uncertainty_score":0.23289995},"labels":[],"label_agreement":null},{"id":"W2580505187","doi":"","title":"A New Measure For Clustering Model Selection","year":2008,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo","keywords":"Measure (data warehouse); Cluster analysis; Selection (genetic algorithm); Computer science; Data mining; Artificial intelligence","score_opus":0.024037401848323613,"score_gpt":0.24678027070918093,"score_spread":0.2227428688608573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2580505187","genre_codex":"methods","genre_gemma":"other","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":[0.029199889,0.000078704805,0.9691858,0.00034677255,0.0002684734,0.00048119854,0.00001066815,0.00019236957,0.00023610747],"genre_scores_gemma":[0.002384047,0.000071662915,0.47527757,0.0000056059025,0.00005385348,0.0000014433973,0.000060176026,0.000031112195,0.5221145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983701,0.00003071233,0.00012459503,0.0005787483,0.00048813145,0.0004076941],"domain_scores_gemma":[0.9988083,0.000035929635,0.00019427994,0.00040356597,0.00039504332,0.00016284034],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00011784995,0.00024176064,0.00035383913,0.00036782448,0.00033869062,0.000041441413,0.0010920678,0.00028236787,0.000009723837],"category_scores_gemma":[0.000020968906,0.00030908678,0.00019040269,0.00035054225,0.00002730107,0.0006059147,0.00018074005,0.00029037512,0.000014102834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012054169,0.00018277818,0.000034249886,0.0017048864,0.0004677612,0.00008262292,0.34719303,0.2169273,0.032828066,0.0011210355,0.015782757,0.38247007],"study_design_scores_gemma":[0.00094460027,0.00018264314,0.00008869511,0.00017517245,0.00003034153,0.000014152482,0.0048249047,0.9896762,0.002673834,0.0005966334,0.0003884801,0.00040436696],"about_ca_topic_score_codex":0.006517375,"about_ca_topic_score_gemma":0.02387457,"teacher_disagreement_score":0.7727489,"about_ca_system_score_codex":0.00020619354,"about_ca_system_score_gemma":0.0004392759,"threshold_uncertainty_score":0.9999361},"labels":[],"label_agreement":null},{"id":"W2582229329","doi":"10.3390/ijgi6010030","title":"A Novel Divisive Hierarchical Clustering Algorithm for Geospatial Analysis","year":2017,"lang":"en","type":"article","venue":"ISPRS International Journal of Geo-Information","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Cluster analysis; Geospatial analysis; Computer science; Hierarchical clustering; Single-linkage clustering; Correlation clustering; CURE data clustering algorithm; Robustness (evolution); Pattern recognition (psychology); Context (archaeology); Data mining; Artificial intelligence; Algorithm; Geography; Cartography","score_opus":0.01706036113338718,"score_gpt":0.33289478348858553,"score_spread":0.3158344223551984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2582229329","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":[0.0012055888,0.000009004792,0.9942595,0.0021762522,0.0018360226,0.00017303225,0.00008504397,0.000025155896,0.00023042025],"genre_scores_gemma":[0.21146522,0.000029969295,0.787428,0.00031822125,0.00062293914,0.00001994313,0.000037862697,0.000008290143,0.00006950484],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975423,0.000024049325,0.00077329145,0.00013975859,0.0012261355,0.0002944479],"domain_scores_gemma":[0.99595624,0.00017196545,0.0012302777,0.00045039362,0.0020361536,0.000154965],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007710873,0.00015496202,0.0002795117,0.000854972,0.00039166783,0.0014719559,0.0030106194,0.00008066384,0.000012699795],"category_scores_gemma":[0.00072717277,0.00014235069,0.00032732566,0.00016669881,0.000072986215,0.008603553,0.0007707245,0.00030378878,0.000016843356],"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":[0.000076910175,0.000045777695,0.00012791331,0.000009395932,0.00067495246,0.000012481129,0.0008653271,0.015764743,0.00010670751,0.0012044662,0.00011769691,0.9809936],"study_design_scores_gemma":[0.0016630567,0.00015411382,0.0076594776,0.00003870989,0.000045615994,0.00013662771,0.00005555744,0.98324955,0.00041860505,0.0010727183,0.005343665,0.00016230719],"about_ca_topic_score_codex":0.00007766648,"about_ca_topic_score_gemma":0.000017549926,"teacher_disagreement_score":0.9808313,"about_ca_system_score_codex":0.00024278108,"about_ca_system_score_gemma":0.00015515264,"threshold_uncertainty_score":0.9995646},"labels":[],"label_agreement":null},{"id":"W2583764785","doi":"10.1109/icmla.2016.0089","title":"A Parallel K-Medoids Algorithm for Clustering based on MapReduce","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Cluster analysis; Computer science; CURE data clustering algorithm; Data stream clustering; Medoid; Canopy clustering algorithm; Correlation clustering; Data mining; Big data; Algorithm; Scale (ratio); Parallel computing; Machine learning","score_opus":0.028868289273536685,"score_gpt":0.3075938819899316,"score_spread":0.2787255927163949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2583764785","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":[0.00003345722,0.000009164808,0.99249583,0.0041921586,0.00030292335,0.0004282567,0.000008936816,0.00038589406,0.002143368],"genre_scores_gemma":[0.009481573,0.000004627058,0.98217595,0.00054531445,0.00013848871,0.00025949467,9.343212e-7,0.00002696713,0.007366657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980581,0.00004573647,0.00021051102,0.00062812056,0.00042937606,0.00062820036],"domain_scores_gemma":[0.99822617,0.0005363592,0.000045915804,0.0008782225,0.00012109834,0.00019224445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032974148,0.00018765377,0.00017117152,0.00016550747,0.00013806479,0.00011232653,0.0011256452,0.00006658307,0.000021581403],"category_scores_gemma":[0.00010128293,0.00012368905,0.00009375042,0.00023331509,0.000056086716,0.00040034723,0.00034450987,0.00008596178,0.0001341434],"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":[0.000018189665,0.00005121674,0.0000032127489,0.000011000866,0.0000069066878,0.000009510878,0.000026081105,0.0026951386,0.001045338,0.0016656269,0.0005522458,0.99391556],"study_design_scores_gemma":[0.001455031,0.00032930024,0.000065068816,0.00005208545,0.000001112964,0.0000071621853,0.000004707786,0.98557496,0.0034433932,0.0015218224,0.0073190313,0.0002263347],"about_ca_topic_score_codex":0.000009755586,"about_ca_topic_score_gemma":0.0000053159033,"teacher_disagreement_score":0.9936892,"about_ca_system_score_codex":0.00014122372,"about_ca_system_score_gemma":0.0000888929,"threshold_uncertainty_score":0.50438935},"labels":[],"label_agreement":null},{"id":"W2597766798","doi":"","title":"NP-Hardness of Euclidean Sum-of-Squares Clustering","year":2008,"lang":"fr","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; HEC Montréal; Polytechnique Montréal","funders":"","keywords":"Cluster analysis; Mathematics; Combinatorics; Euclidean distance; Explained sum of squares; Computer science; Artificial intelligence; Statistics","score_opus":0.03416253621654149,"score_gpt":0.2831926804146098,"score_spread":0.24903014419806832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2597766798","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":[0.05831697,0.010818468,0.9231961,0.0044505643,0.0010579583,0.0008768201,0.00012141235,0.00044020673,0.0007215372],"genre_scores_gemma":[0.5750702,0.002260879,0.41371566,0.00035383366,0.0002731816,0.00017736049,0.000010564127,0.00013463476,0.008003707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937905,0.00052515295,0.0015120115,0.0010376257,0.0013776573,0.001757035],"domain_scores_gemma":[0.9948026,0.00049162173,0.0007959279,0.0024303102,0.0008230509,0.000656504],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013781526,0.00067366945,0.0011345025,0.00096043246,0.0004112134,0.00014288821,0.0027637966,0.00055092043,0.00007811789],"category_scores_gemma":[0.0006871344,0.00077954616,0.00046057312,0.0020618306,0.001066351,0.0014369427,0.0022959213,0.0010046242,0.00003217771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007454111,0.0031703755,0.056346655,0.0038504698,0.0006757908,0.0033033574,0.013502853,0.17613839,0.0720056,0.082130834,0.008716051,0.5794142],"study_design_scores_gemma":[0.0012568003,0.00085650553,0.021978484,0.0008058483,0.000044909444,0.0019531387,0.00019247357,0.87177956,0.08871832,0.002468179,0.008907709,0.0010380773],"about_ca_topic_score_codex":0.02177952,"about_ca_topic_score_gemma":0.0017089115,"teacher_disagreement_score":0.69564116,"about_ca_system_score_codex":0.0006727633,"about_ca_system_score_gemma":0.0009625536,"threshold_uncertainty_score":0.9994655},"labels":[],"label_agreement":null},{"id":"W2599038115","doi":"10.5430/air.v6n2p10","title":"Bio-inspired multiobjective clustering optimization: A survey and a proposal","year":2017,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Cluster analysis; Multi-objective optimization; Computer science; Data mining; Quality (philosophy); Mathematical optimization; Machine learning; Mathematics","score_opus":0.2304565960268817,"score_gpt":0.45474251321250253,"score_spread":0.22428591718562083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2599038115","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":[0.007960163,0.00007211878,0.9885258,0.0016209733,0.0002497733,0.00062044413,0.000006996422,0.00012237411,0.0008213332],"genre_scores_gemma":[0.85204476,0.00011823019,0.14730723,0.000014113367,0.00013536109,0.000088592256,0.000002938811,0.000025006097,0.0002637874],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996154,0.0006093868,0.00036398103,0.0009032758,0.001030174,0.0009391578],"domain_scores_gemma":[0.9963029,0.00069800986,0.00010966086,0.001492082,0.0011005596,0.0002967701],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0042840624,0.00018817975,0.00022534284,0.00036996434,0.0023066802,0.0022017115,0.0023540044,0.00011763374,0.000027933935],"category_scores_gemma":[0.0035211395,0.00018174737,0.0000405315,0.0006194078,0.000977917,0.0013860192,0.0029731898,0.00062135124,0.00013331202],"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":[0.0001824758,0.00021868071,0.0019352938,0.00005915604,0.000043083484,0.00015060471,0.002453359,0.03549354,0.0020016201,0.019198569,0.000034800116,0.93822885],"study_design_scores_gemma":[0.000054677887,0.00021494,0.0027572461,0.000039743893,8.1134937e-7,0.000018144052,0.00022591524,0.9750751,0.010581627,0.010779132,0.000038435508,0.0002142081],"about_ca_topic_score_codex":0.0017358634,"about_ca_topic_score_gemma":0.0013506506,"teacher_disagreement_score":0.9395816,"about_ca_system_score_codex":0.00016205339,"about_ca_system_score_gemma":0.00033250664,"threshold_uncertainty_score":0.9989922},"labels":[],"label_agreement":null},{"id":"W2606056073","doi":"10.1016/j.ijar.2017.04.004","title":"Collaborative fuzzy clustering algorithm: Some refinements","year":2017,"lang":"en","type":"article","venue":"International Journal of Approximate Reasoning","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":35,"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":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Cluster analysis; Partition (number theory); Computer science; Data mining; Fuzzy clustering; Fuzzy logic; Algorithm; Granular computing; Artificial intelligence; Mathematics; Rough set","score_opus":0.017989009181289577,"score_gpt":0.3372030557690087,"score_spread":0.3192140465877191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606056073","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":[0.008075875,0.00026838164,0.9828975,0.0022391824,0.0026477594,0.00012422679,0.000011944279,0.000052529427,0.0036825843],"genre_scores_gemma":[0.11067272,0.00034390687,0.88751954,0.0001138099,0.0009446238,0.0000096523845,0.0000024026378,0.000027933622,0.0003654256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99754393,0.000061658175,0.0005244153,0.00027901743,0.0012434869,0.0003475081],"domain_scores_gemma":[0.99683064,0.0000807038,0.0010849744,0.00054598995,0.0012895407,0.00016816155],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008376271,0.00018113572,0.00027367967,0.00028191652,0.000373542,0.0012922458,0.0038849262,0.000059719616,0.000009775346],"category_scores_gemma":[0.00052919314,0.00016460092,0.00010749612,0.000103644896,0.00009841732,0.003196925,0.0013978384,0.00037016775,0.000015195419],"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":[0.00011492429,0.00017255198,0.00052583485,0.00002346118,0.00052090664,0.001553418,0.0012435828,0.0026847383,0.0026974143,0.018192276,0.0002882236,0.97198266],"study_design_scores_gemma":[0.004458206,0.00041227267,0.0044458485,0.0012160762,0.000022756458,0.0017942295,0.00041858508,0.94360924,0.011935086,0.022794338,0.008186536,0.00070685166],"about_ca_topic_score_codex":0.00001967883,"about_ca_topic_score_gemma":0.0000021462897,"teacher_disagreement_score":0.9712758,"about_ca_system_score_codex":0.00028436462,"about_ca_system_score_gemma":0.0001903544,"threshold_uncertainty_score":0.99974453},"labels":[],"label_agreement":null},{"id":"W2612181456","doi":"10.1007/978-1-4899-7502-7_35-1","title":"Categorical Data Clustering","year":2016,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Machine Learning and Data Mining","topic":"Advanced Clustering Algorithms Research","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 Toronto","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Data mining; Domain (mathematical analysis); Cluster (spacecraft); Artificial intelligence; Machine learning; Mathematics","score_opus":0.05026195322463737,"score_gpt":0.32755562043522746,"score_spread":0.27729366721059007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612181456","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009620826,0.0043088575,0.61049,0.00046015164,0.00047624166,0.00018233687,0.0004557639,0.0002524805,0.38336456],"genre_scores_gemma":[0.0012080552,0.017311752,0.36540046,0.00005666138,0.0011993233,0.0000074553186,0.0020124465,0.00021805833,0.6125858],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99635607,0.000089650806,0.0006106719,0.0017380379,0.00070070423,0.0005048683],"domain_scores_gemma":[0.9946405,0.0008686422,0.0004335289,0.0037435847,0.000081881604,0.00023182998],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0011831787,0.00045233837,0.0006367969,0.00028996362,0.00022519393,0.00013013714,0.005330308,0.00024982085,0.00008041726],"category_scores_gemma":[0.0008277334,0.00038548178,0.000039615767,0.000080897036,0.00017421486,0.0011298328,0.021045286,0.0010247895,0.00004852023],"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":[0.000016882927,0.000011246673,0.00017189111,0.0001544722,0.00007598356,0.0001447196,0.00022935621,0.000039524533,0.000009831557,0.0038985705,0.0011015963,0.99414593],"study_design_scores_gemma":[0.00039375355,0.00012741784,0.000022827982,0.00033366255,0.00003079089,0.00013078225,0.000012365828,0.25862837,0.0000011228392,0.00095812394,0.7388423,0.00051847304],"about_ca_topic_score_codex":0.000046562185,"about_ca_topic_score_gemma":0.000029917534,"teacher_disagreement_score":0.9936274,"about_ca_system_score_codex":0.000040914732,"about_ca_system_score_gemma":0.00016491277,"threshold_uncertainty_score":0.9998597},"labels":[],"label_agreement":null},{"id":"W2623118547","doi":"10.5120/ijca2016912481","title":"A Survey on Unsupervised Clustering Algorithm based on K-Means Clustering","year":2016,"lang":"en","type":"article","venue":"International Journal of Computer Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Computer science; Cluster analysis; Data mining; Artificial intelligence","score_opus":0.030654955753429088,"score_gpt":0.32357217122990406,"score_spread":0.292917215476475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2623118547","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":[0.00022327068,0.000013155787,0.99460995,0.0036268176,0.00090424076,0.00022571543,0.00005886626,0.00008585764,0.0002521179],"genre_scores_gemma":[0.268149,0.000039255036,0.728701,0.001454976,0.0013521484,0.00006349248,0.000009367179,0.00004816223,0.00018260353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99716306,0.00017686268,0.000648913,0.00042312665,0.0012577426,0.00033031523],"domain_scores_gemma":[0.9966088,0.001091447,0.00034712197,0.0006599912,0.0010696646,0.00022298293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007637359,0.00023061,0.0002575776,0.00063924864,0.00011617993,0.0002615638,0.0029283962,0.000069375186,0.000026693004],"category_scores_gemma":[0.00006542481,0.00017354076,0.00016518346,0.00037140812,0.000067147645,0.0004846257,0.0004621276,0.00028977197,0.000101607424],"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":[0.000058315378,0.00022272165,0.00012643752,0.000004030814,0.00006910153,0.0000456541,0.000057911315,0.062147927,0.00028818875,0.00049248344,0.0003805244,0.9361067],"study_design_scores_gemma":[0.0015629752,0.0003677903,0.009178938,0.00022320461,0.0000033853091,0.00007669761,0.0000023918988,0.9796607,0.0004861171,0.00060411997,0.007604168,0.00022954236],"about_ca_topic_score_codex":0.000011354723,"about_ca_topic_score_gemma":0.000010502066,"teacher_disagreement_score":0.93587714,"about_ca_system_score_codex":0.0003832495,"about_ca_system_score_gemma":0.00016293392,"threshold_uncertainty_score":0.7076787},"labels":[],"label_agreement":null},{"id":"W27100606","doi":"10.1111/jgs.14068","title":"New data induced metric for density based clustering","year":2004,"lang":"en","type":"article","venue":"Journal of the American Geriatrics Society","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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":"Morris Kerzner Memorial Fund","keywords":"Cluster analysis; Metric (unit); Computer science; Data mining; Mathematics; Artificial intelligence; Business","score_opus":0.056767522146321144,"score_gpt":0.3413801901686271,"score_spread":0.28461266802230595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W27100606","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":[0.028751431,0.00010568683,0.96605563,0.004163214,0.00069360185,0.00018438259,0.0000061824085,0.00003175764,0.00000808169],"genre_scores_gemma":[0.18870965,0.000054702832,0.8100504,0.0006839827,0.00044976428,0.0000014621032,6.4561283e-7,0.000019360881,0.000030005574],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99791694,0.00008114582,0.0004488665,0.00032576884,0.0008062079,0.0004210874],"domain_scores_gemma":[0.9966313,0.00038787883,0.0010241843,0.0013648008,0.00036703274,0.00022475964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013299523,0.00016469933,0.00037057698,0.00013400544,0.00026313862,0.00019083438,0.0045361756,0.000046005534,9.962022e-7],"category_scores_gemma":[0.00067650893,0.00012086859,0.0003899244,0.0025829312,0.00007401536,0.0006204034,0.0017143071,0.00047204233,0.0000017070453],"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":[0.00027961354,0.00044839867,0.0011781601,0.00017397129,0.0006425041,0.00005122378,0.002337878,0.22009337,0.028692756,0.0004210014,0.019115489,0.72656566],"study_design_scores_gemma":[0.009373821,0.0021228094,0.019237531,0.00013848138,0.00024220654,0.000583862,0.0006826964,0.9311103,0.016710402,0.009419428,0.009086033,0.0012923804],"about_ca_topic_score_codex":0.00014446295,"about_ca_topic_score_gemma":0.000006862505,"teacher_disagreement_score":0.72527325,"about_ca_system_score_codex":0.0005057238,"about_ca_system_score_gemma":0.0012138503,"threshold_uncertainty_score":0.8429419},"labels":[],"label_agreement":null},{"id":"W2745587906","doi":"10.1007/978-3-319-65636-6_27","title":"Enhancing Ant Brood Clustering with Adaptive Radius of Perception and Non-parametric Estimation on Multi-core Architectures","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes on data engineering and communications technologies","topic":"Advanced Clustering Algorithms Research","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 Manitoba","funders":"","keywords":"Cluster analysis; Computer science; CUDA; Benchmark (surveying); Convergence (economics); Ant colony; Ant colony optimization algorithms; Data mining; Artificial intelligence; Machine learning; Parallel computing","score_opus":0.0583825477258629,"score_gpt":0.30550924447221084,"score_spread":0.24712669674634793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745587906","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":[0.00071756117,0.0015221968,0.99607074,0.00042170993,0.000033045308,0.00041533643,0.00009189921,0.00054078194,0.0001867092],"genre_scores_gemma":[0.46691856,0.001263178,0.53161854,0.000007629954,0.000008614863,0.000027340035,0.000062370396,0.000034040742,0.00005974002],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985512,0.000013790096,0.00026476744,0.000650391,0.00027383878,0.00024604774],"domain_scores_gemma":[0.9933921,0.0007887767,0.00025976863,0.0054334397,0.00008431594,0.000041599404],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018671769,0.00040071784,0.00041719395,0.00078548206,0.00031366118,0.00014549968,0.0029819226,0.00031707817,3.6456217e-7],"category_scores_gemma":[0.00072143297,0.00033030086,0.000029618479,0.00012306006,0.00035055532,0.00019225973,0.0030616417,0.0011443044,0.0000016935709],"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":[0.00003221717,0.000039793613,0.0000052162086,0.00022675999,0.000094714946,0.000007162997,0.00029450987,0.1244949,0.0012473735,0.0021554453,0.0000025069785,0.8713994],"study_design_scores_gemma":[0.00030058407,0.000541757,0.00025251476,0.0014347099,0.000028114457,0.000051517996,0.00002061647,0.99372905,0.0014291374,0.0015923834,0.00022018566,0.0003993955],"about_ca_topic_score_codex":0.00003155301,"about_ca_topic_score_gemma":0.00009221126,"teacher_disagreement_score":0.871,"about_ca_system_score_codex":0.00008380613,"about_ca_system_score_gemma":0.000039196344,"threshold_uncertainty_score":0.9999149},"labels":[],"label_agreement":null},{"id":"W2750557327","doi":"10.1016/j.ijar.2017.08.008","title":"Fuzzy C-Means clustering based on dual expression between cluster prototypes and reconstructed data","year":2017,"lang":"en","type":"article","venue":"International Journal of Approximate Reasoning","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":28,"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":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Dual (grammatical number); Cluster analysis; Cluster (spacecraft); Fuzzy logic; Fuzzy clustering; Computer science; Pattern recognition (psychology); Artificial intelligence; Data mining; Expression (computer science); Computer network; Art","score_opus":0.049615045357977505,"score_gpt":0.3513245074083753,"score_spread":0.3017094620503978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750557327","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":[0.050803203,0.000037047725,0.9440624,0.0021496187,0.0008068728,0.0002931703,0.000036952635,0.000053564312,0.0017571802],"genre_scores_gemma":[0.59920007,0.000027641643,0.4001798,0.000050972576,0.00047682234,0.000006306189,0.000008654803,0.000019613799,0.000030095069],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978154,0.00009651406,0.00046843366,0.00040115355,0.00094314455,0.00027536156],"domain_scores_gemma":[0.9974421,0.00023107203,0.0007512044,0.001006783,0.00040480483,0.00016398562],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001086902,0.0001768211,0.0002614965,0.00026792425,0.0003135631,0.0010881777,0.0033838144,0.000075016294,0.0000052866462],"category_scores_gemma":[0.0008960565,0.00014898044,0.000052113137,0.000054286393,0.000119114506,0.0020756386,0.0020243388,0.00044227927,0.0000032994485],"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":[0.0007885499,0.00018314415,0.024556097,0.00015446453,0.00031916297,0.0008082982,0.00082354795,0.010937278,0.003952329,0.0013978514,0.00025356526,0.9558257],"study_design_scores_gemma":[0.0018556841,0.00018472168,0.0077503715,0.0015749703,0.000010283437,0.0004856342,0.000036019792,0.98323804,0.0026312184,0.0014657789,0.00052473275,0.00024255499],"about_ca_topic_score_codex":0.000011356867,"about_ca_topic_score_gemma":0.0000028491713,"teacher_disagreement_score":0.97230077,"about_ca_system_score_codex":0.00009943127,"about_ca_system_score_gemma":0.00011840032,"threshold_uncertainty_score":0.9999488},"labels":[],"label_agreement":null},{"id":"W2754977413","doi":"","title":"Standardization and Weighting of Variables for the Fuzzy K-Means Clustering of Discontinuity Data","year":2000,"lang":"en","type":"article","venue":"4th North American Rock Mechanics Symposium","topic":"Advanced Clustering Algorithms Research","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 Toronto; Golder Associates (Canada)","funders":"","keywords":"Standardization; Weighting; Cluster analysis; Data mining; Computer science; Fuzzy logic; Discontinuity (linguistics); Fuzzy clustering; Mathematics; Artificial intelligence; Medicine","score_opus":0.018446712484574013,"score_gpt":0.2747637271969266,"score_spread":0.2563170147123526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754977413","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":[0.00375923,0.00009840623,0.9950038,0.00023501847,0.00009695734,0.0004225085,0.00022381094,0.000048623653,0.000111648464],"genre_scores_gemma":[0.833913,0.00064623595,0.16507044,0.000050056955,0.0000795698,0.000034145374,0.00003519835,0.000031290107,0.00014003382],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982235,0.000078783014,0.00041008426,0.0005070703,0.0004171073,0.00036347148],"domain_scores_gemma":[0.9977854,0.00040988522,0.0003078859,0.0012257079,0.00018649845,0.000084648455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005272072,0.00016472524,0.00033086317,0.00007475642,0.00023018804,0.000059975413,0.0015010098,0.00002565751,0.000004051604],"category_scores_gemma":[0.00009325477,0.0001314479,0.000042051244,0.00061527785,0.00005862374,0.00045760968,0.0010250295,0.00012296572,5.235186e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001318602,0.000083695304,0.0005519744,0.00024558115,0.00012656079,0.0000023379316,0.0018020001,0.6509325,0.003014849,0.0024051743,0.00005762278,0.34064585],"study_design_scores_gemma":[0.00028740749,0.00021626242,0.00009402809,0.000034953504,0.000023225679,0.0000072382504,0.00014442045,0.99613315,0.0009379291,0.0003861713,0.0015911375,0.00014406275],"about_ca_topic_score_codex":0.00019376949,"about_ca_topic_score_gemma":0.00028020373,"teacher_disagreement_score":0.8301538,"about_ca_system_score_codex":0.00003627615,"about_ca_system_score_gemma":0.00010069643,"threshold_uncertainty_score":0.536029},"labels":[],"label_agreement":null},{"id":"W2755594639","doi":"10.1109/trustcom/bigdatase/icess.2017.332","title":"A Data Science and Engineering Solution for Fast K-Means Clustering of Big Data","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Scalability; Computer science; Cluster analysis; Data mining; Science and engineering; Heuristic; Task (project management); Variety (cybernetics); Centroid; Data science; Database; Artificial intelligence; Engineering","score_opus":0.19239062046661298,"score_gpt":0.3746471718461937,"score_spread":0.18225655137958074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755594639","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":[0.00039675232,0.000030913914,0.99814326,0.00048466393,0.0003326189,0.00018499016,0.00008464579,0.000057172776,0.0002849881],"genre_scores_gemma":[0.17602095,0.000023490576,0.82371855,0.000011757424,0.00010223007,0.000006808843,0.000009848374,0.000009218367,0.00009716055],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983594,0.0000057268794,0.00015711303,0.0006992225,0.00042080984,0.00035775965],"domain_scores_gemma":[0.994667,0.000088821645,0.00008609359,0.0048742425,0.0001829537,0.000100871686],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0014409695,0.000088414425,0.000121986086,0.00012874271,0.00047084308,0.00045921904,0.008214709,0.00002386034,4.7444385e-7],"category_scores_gemma":[0.0013487866,0.00008319418,0.000007418833,0.00015600742,0.00026678512,0.0037435163,0.016968844,0.00007600075,0.0000010758293],"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":[0.0000070944016,0.000022092378,0.000059142752,0.00014445983,0.000011039848,0.0000029763714,0.00013048745,0.0011131301,0.0335121,0.0018640404,0.00013125331,0.9630022],"study_design_scores_gemma":[0.00022829595,0.000032568838,0.00091006927,0.00003509601,0.0000018765685,0.000011896667,0.000009732321,0.9954348,0.000933462,0.00005516647,0.002250067,0.00009693076],"about_ca_topic_score_codex":0.00008996149,"about_ca_topic_score_gemma":0.00008417168,"teacher_disagreement_score":0.9943217,"about_ca_system_score_codex":0.000036453377,"about_ca_system_score_gemma":0.0001513935,"threshold_uncertainty_score":0.9971513},"labels":[],"label_agreement":null},{"id":"W2762595523","doi":"10.1007/s10115-017-1110-9","title":"Subspace multi-clustering: a review","year":2017,"lang":"en","type":"review","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":41,"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":"Cluster analysis; Computer science; Clustering high-dimensional data; Correlation clustering; CURE data clustering algorithm; Data mining; Consensus clustering; Canopy clustering algorithm; Data stream clustering; Fuzzy clustering; Constrained clustering; Artificial intelligence; Brown clustering; Pattern recognition (psychology); Machine learning","score_opus":0.16548597611151802,"score_gpt":0.43143692051603333,"score_spread":0.2659509444045153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2762595523","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.3744906e-9,0.7794117,0.21129814,0.000018505965,0.0007915598,0.0012017007,0.000012505463,0.0001370238,0.007128883],"genre_scores_gemma":[3.0579693e-7,0.9936709,0.0022230966,0.000024874733,0.0001305864,0.0003933708,0.00003918504,0.000018781177,0.0034989382],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977045,0.00020708391,0.0010267644,0.0003372593,0.00032904168,0.0003953597],"domain_scores_gemma":[0.9969624,0.00011570372,0.00089534675,0.0014669839,0.00034567653,0.00021384294],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010331294,0.00041730228,0.001543763,0.00035877357,0.000339932,0.0010100277,0.001688456,0.00023296583,0.000002446397],"category_scores_gemma":[0.00023885477,0.00032651811,0.00020611346,0.00033153416,0.000056684552,0.004637249,0.0012359865,0.00039827908,0.0012825627],"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":[1.5081889e-7,0.0000062991544,5.121484e-8,0.120094225,0.000023798653,0.0000021621736,0.00020250266,9.0056443e-7,3.1073215e-9,0.00040927337,0.0012705325,0.8779901],"study_design_scores_gemma":[0.00014242216,0.000021016253,3.6238467e-7,0.073073626,0.000033239405,0.00023938963,0.000008027521,0.019675223,2.3812124e-8,7.340371e-7,0.9064887,0.0003171988],"about_ca_topic_score_codex":0.000010076367,"about_ca_topic_score_gemma":0.0000030618505,"teacher_disagreement_score":0.9052182,"about_ca_system_score_codex":0.00016093592,"about_ca_system_score_gemma":0.00033340885,"threshold_uncertainty_score":0.9999187},"labels":[],"label_agreement":null},{"id":"W2772904413","doi":"10.1109/tnnls.2017.2770167","title":"An Algorithm for Clustering Categorical Data With Set-Valued Features","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Science Foundation of Shanxi Province; Simon Fraser University; Kungliga Tekniska Högskolan; Shanxi Scholarship Council of China; National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Categorical variable; Data mining; Initialization; Algorithm; Set (abstract data type); CURE data clustering algorithm; Canopy clustering algorithm; Data set; Determining the number of clusters in a data set; Data stream clustering; Heuristic; Correlation clustering; Pattern recognition (psychology); Artificial intelligence; Machine learning","score_opus":0.04585140131797229,"score_gpt":0.32887373130401953,"score_spread":0.28302232998604726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772904413","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":[0.0013959636,0.00014517292,0.99660575,0.00016314845,0.00097598403,0.00045260627,0.000012417915,0.00023217384,0.000016799695],"genre_scores_gemma":[0.9650434,0.000032926295,0.033661235,0.000027026388,0.00035201243,0.00008735264,0.00001058355,0.000041767886,0.00074369286],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790317,0.00021471882,0.00021482306,0.00082542235,0.00032125373,0.00052063994],"domain_scores_gemma":[0.9977418,0.00023333628,0.00015737778,0.0015409478,0.000096933,0.0002295948],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000533518,0.00024579727,0.00029238354,0.00008850164,0.00223993,0.0014778845,0.0015572016,0.00011835211,9.2148525e-7],"category_scores_gemma":[0.000011919422,0.00019793911,0.00003891634,0.00011321766,0.00010838148,0.0012443851,0.000032091353,0.00083431974,0.0000011708055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027274094,0.000021496404,0.000010964772,0.000021743721,0.000025852776,0.000021689793,0.00011023912,0.72032434,0.000016184764,0.000017456083,0.00001917048,0.2793836],"study_design_scores_gemma":[0.0006577358,0.0006091114,0.00021813026,0.00005316704,0.000014872389,0.00023530544,0.000106194,0.99741095,0.000013841914,0.000003786263,0.0004193842,0.00025752748],"about_ca_topic_score_codex":0.00032516642,"about_ca_topic_score_gemma":0.00007320979,"teacher_disagreement_score":0.9636474,"about_ca_system_score_codex":0.00004161553,"about_ca_system_score_gemma":0.000028918954,"threshold_uncertainty_score":0.9995587},"labels":[],"label_agreement":null},{"id":"W2778728785","doi":"10.5430/air.v7n1p15","title":"Estimating the number of clusters using diversity","year":2017,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Outlier; Silhouette; Computer science; Pattern recognition (psychology); Entropy (arrow of time); Single-linkage clustering; Cluster (spacecraft); Ground truth; Artificial intelligence; Statistic; Mathematics; Data mining; Fuzzy clustering; Statistics; CURE data clustering algorithm; Physics","score_opus":0.36841764293722823,"score_gpt":0.505386192201522,"score_spread":0.1369685492642938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2778728785","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":[0.20526934,0.000013462201,0.79200244,0.0010691949,0.00031261248,0.00021349765,0.0000014598191,0.000030208654,0.0010877668],"genre_scores_gemma":[0.8881286,0.0000059581366,0.11161508,0.000011227035,0.00012529484,0.0000064020755,1.6936065e-7,0.000008900783,0.000098386685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99685085,0.0003088901,0.00031396202,0.0004373925,0.0013741208,0.0007147758],"domain_scores_gemma":[0.9965597,0.000642062,0.0001308901,0.0018606887,0.0006779163,0.0001287611],"candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0037966713,0.00011244369,0.0001635078,0.00012161362,0.004180655,0.0005990598,0.0052047027,0.00006361121,0.000037838414],"category_scores_gemma":[0.00182559,0.00008785894,0.0000746964,0.000454946,0.0012420313,0.00085703854,0.008622949,0.0005913157,0.0001628954],"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":[0.00005034647,0.00014964552,0.0040819217,0.000071079085,0.000045709006,0.000077377816,0.0050855475,0.049978584,0.0045674467,0.07877783,0.00003816965,0.85707635],"study_design_scores_gemma":[0.000016125068,0.000028448723,0.00036993148,0.000043652017,0.0000015995593,0.00001380259,0.00036421625,0.9120841,0.018623516,0.06834649,0.000016205406,0.00009191192],"about_ca_topic_score_codex":0.0025464098,"about_ca_topic_score_gemma":0.00007375716,"teacher_disagreement_score":0.8621055,"about_ca_system_score_codex":0.00012812897,"about_ca_system_score_gemma":0.00015396497,"threshold_uncertainty_score":0.99939513},"labels":[],"label_agreement":null},{"id":"W2783873704","doi":"10.1186/s12859-017-1996-y","title":"diceR: an R package for class discovery using an ensemble driven approach","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":62,"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 British Columbia; BC Cancer Agency","funders":"BC Cancer Foundation","keywords":"Computer science; Dicer; Cluster analysis; Context (archaeology); Data mining; Set (abstract data type); Class (philosophy); Permutation (music); Generalization; Cluster (spacecraft); Machine learning; Artificial intelligence; Data science; Biology; Mathematics","score_opus":0.08579926171176273,"score_gpt":0.34100829396308385,"score_spread":0.25520903225132113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783873704","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":[0.00971716,0.000007251685,0.9875722,0.000015776663,0.00023890716,0.00046764358,0.00002297247,0.00019676374,0.0017613602],"genre_scores_gemma":[0.04167516,0.0000025791826,0.95763844,0.00010534914,0.0002821751,0.000025535099,0.000030689425,0.00002479652,0.00021524125],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981972,0.000053307,0.00038404373,0.00030804626,0.00044245334,0.0006149227],"domain_scores_gemma":[0.99811447,0.000092479,0.00015912158,0.0012006456,0.00020363799,0.00022965096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042694015,0.0002005488,0.00021343192,0.00015692216,0.00037108263,0.00069007743,0.0013217861,0.00010849365,0.0000013783498],"category_scores_gemma":[0.0000757523,0.00017849273,0.00006904593,0.00036916032,0.00017265373,0.0052900505,0.0005214868,0.0001450506,0.000026332662],"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":[0.00046077234,0.0031970954,0.0016746548,0.0041618007,0.0002703121,0.00002035516,0.06685312,0.16525742,0.014700224,0.13561192,0.0018937242,0.6058986],"study_design_scores_gemma":[0.00047380972,0.00042859092,0.00007738776,0.000018714225,0.000005614143,0.000028602602,0.0005543471,0.99468917,0.0016741717,0.0011021408,0.00068316807,0.0002642801],"about_ca_topic_score_codex":0.000015498243,"about_ca_topic_score_gemma":0.000027274946,"teacher_disagreement_score":0.8294318,"about_ca_system_score_codex":0.000119649856,"about_ca_system_score_gemma":0.00020022994,"threshold_uncertainty_score":0.72787225},"labels":[],"label_agreement":null},{"id":"W2786121513","doi":"10.5539/mas.v12n2p116","title":"An Improved Version of K-medoid Algorithm using CRO","year":2018,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medoid; Cluster analysis; Computer science; Algorithm; k-means clustering; Disjoint sets; Data mining; DBSCAN; Cluster (spacecraft); Outlier; Correlation clustering; Artificial intelligence; CURE data clustering algorithm; Mathematics","score_opus":0.02065885472170116,"score_gpt":0.3194668025855861,"score_spread":0.2988079478638849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786121513","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":[0.029952075,0.00001060479,0.96823525,0.000025251627,0.00022259812,0.00019587392,0.000005196585,0.00012655997,0.0012265895],"genre_scores_gemma":[0.54518354,8.902844e-7,0.45467746,0.0000370847,0.000056624376,0.0000044080684,2.8885194e-7,0.000007825175,0.000031859916],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99725354,0.000023224587,0.00023424518,0.00085309666,0.0009738131,0.0006621119],"domain_scores_gemma":[0.99800503,0.000034115026,0.00011814791,0.0012154862,0.0003703329,0.00025686214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009136842,0.00015464757,0.00017754085,0.00028897118,0.0005359741,0.00019317266,0.0028683809,0.000054707223,0.000014284789],"category_scores_gemma":[0.0000308829,0.00014792038,0.000029411674,0.0014212272,0.0013515663,0.0011230824,0.001015196,0.00015311448,0.000019188534],"study_design_candidate":"bench_or_experimental","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":[0.0000068989125,0.000038624086,0.0000044606636,0.0000043141094,0.0000013781112,0.000001388818,0.00057898345,0.00052521477,0.7960718,0.00033075846,0.0000032312585,0.2024329],"study_design_scores_gemma":[0.00020408788,0.0001225144,0.000095155476,0.0000064568735,0.0000010828842,0.0000068985773,0.000031289757,0.76446277,0.23217367,0.002714641,0.000048739308,0.00013268353],"about_ca_topic_score_codex":0.00004667452,"about_ca_topic_score_gemma":0.0000024829242,"teacher_disagreement_score":0.7639376,"about_ca_system_score_codex":0.00016954295,"about_ca_system_score_gemma":0.00036351464,"threshold_uncertainty_score":0.6032018},"labels":[],"label_agreement":null},{"id":"W2788096725","doi":"10.1145/3178876.3185993","title":"ROSC","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"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; Spectral clustering; Similarity (geometry); Cluster analysis; Reachability; Data mining; Scale (ratio); Feature (linguistics); Competitor analysis; Artificial intelligence; Algorithm","score_opus":0.019395380790563112,"score_gpt":0.3199427341705084,"score_spread":0.30054735337994526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788096725","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":[0.0008879551,0.0000053199187,0.9456203,0.00057113316,0.00015496911,0.0000265823,7.009129e-8,0.0002105953,0.052523103],"genre_scores_gemma":[0.27744702,0.0000015661506,0.7094151,0.0003772222,0.00016397466,0.0000042235206,8.275622e-8,0.0000043800196,0.012586436],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994623,0.000010051474,0.000045963774,0.00015871681,0.00014840666,0.00017453385],"domain_scores_gemma":[0.9994933,0.000019761734,0.000006977424,0.0003624786,0.000064329564,0.00005313538],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007961683,0.000033993972,0.000032386914,0.000033759305,0.000062917235,0.000060979328,0.00057749875,0.000012942643,0.000078643185],"category_scores_gemma":[0.00002377225,0.000027803339,0.000010467108,0.00020869983,0.000047922138,0.00024434912,0.0003594681,0.000039532097,0.0010622198],"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":[0.0000027163308,0.00003305548,0.00012525616,0.000003827099,0.00000608352,0.000018508217,0.00035850581,0.000022828212,0.0061498783,0.15276599,0.0061688134,0.83434457],"study_design_scores_gemma":[0.00031822253,0.00032368308,0.0020830203,0.0000064358237,4.2705133e-7,0.000042693042,0.000017038727,0.75023717,0.08255911,0.024422117,0.13973927,0.000250806],"about_ca_topic_score_codex":0.0000080221635,"about_ca_topic_score_gemma":0.0000031786074,"teacher_disagreement_score":0.83409375,"about_ca_system_score_codex":0.000015121793,"about_ca_system_score_gemma":0.000016960228,"threshold_uncertainty_score":0.99971557},"labels":[],"label_agreement":null},{"id":"W2792821451","doi":"10.1007/s10898-018-0634-1","title":"A sampling-based exact algorithm for the solution of the minimax diameter clustering problem","year":2018,"lang":"en","type":"article","venue":"Journal of Global Optimization","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal; Polytechnique Montréal","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Cluster analysis; Minimax; Heuristic; Mathematical optimization; Algorithm; Set (abstract data type); Sampling (signal processing); Computer science; Statistics","score_opus":0.0290985115856251,"score_gpt":0.31785168437011047,"score_spread":0.28875317278448537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792821451","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":[0.00018915397,0.0000825817,0.9972866,0.0014817134,0.0005658559,0.00031772375,0.000008652609,0.000013607426,0.00005407835],"genre_scores_gemma":[0.04581221,0.000010460074,0.95379215,0.00012058824,0.00022722509,0.0000079568545,4.958748e-7,0.000008266016,0.000020667014],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986214,0.00008314684,0.00043348366,0.00014626129,0.00048376186,0.00023196227],"domain_scores_gemma":[0.9979709,0.00020628014,0.0005539366,0.00032389455,0.00089235464,0.000052627474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069972826,0.00010434856,0.00015588425,0.000047984813,0.00021833937,0.0000990923,0.0009510341,0.00005281977,0.000003982409],"category_scores_gemma":[0.00021026294,0.00006123064,0.0001445935,0.00053762534,0.0001270411,0.00041457464,0.00021297704,0.00011214476,6.555917e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040844378,0.000043537846,0.000060408547,0.00001519068,0.00002943633,5.364577e-7,0.00008030775,0.8507505,0.00014057885,0.00005466896,0.00016603204,0.14861794],"study_design_scores_gemma":[0.000598244,0.00036576475,0.00044501293,0.000083171886,0.000016663962,0.000037471764,0.000014054108,0.9968691,0.00078563,0.00033568472,0.00038254762,0.00006665386],"about_ca_topic_score_codex":0.000010248173,"about_ca_topic_score_gemma":0.0000080177215,"teacher_disagreement_score":0.14855129,"about_ca_system_score_codex":0.00022968173,"about_ca_system_score_gemma":0.00020340832,"threshold_uncertainty_score":0.24969131},"labels":[],"label_agreement":null},{"id":"W2801522993","doi":"10.1155/2018/6164534","title":"Application of Data Clustering to Railway Delay Pattern Recognition","year":2018,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Danmarks Tekniske Universitet","keywords":"Cluster analysis; Computer science; Data mining; Pattern recognition (psychology); Artificial intelligence; Transport engineering; Engineering","score_opus":0.04256832023106765,"score_gpt":0.33834660307763686,"score_spread":0.2957782828465692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801522993","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":[0.08095312,0.00002934228,0.9182538,0.00026438019,0.00025578545,0.00017704528,0.000024256695,0.000022651286,0.000019629506],"genre_scores_gemma":[0.59111166,0.000022300335,0.4086344,0.000051323503,0.00013750835,0.0000043857717,0.000024103927,0.000009766884,0.000004570926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837375,0.000035315443,0.0006387835,0.00027421617,0.0004905822,0.00018736093],"domain_scores_gemma":[0.99800515,0.00007285692,0.00048160128,0.00055109605,0.0007726773,0.00011662906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047182705,0.00010508356,0.00019751764,0.00024076412,0.000057607263,0.000025618658,0.001006808,0.00004210799,0.000006036499],"category_scores_gemma":[0.000049339167,0.00010272041,0.00004338712,0.0005034835,0.00003789511,0.0020036432,0.000046200083,0.0001462373,0.000013542766],"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":[0.0000816126,0.00004309903,0.0001459849,0.000036357458,0.00001619692,0.000009632479,0.0011936805,0.014950591,0.023420477,0.0000125369825,0.000014453595,0.9600754],"study_design_scores_gemma":[0.008045354,0.0062387963,0.19789532,0.0015126788,0.00014812578,0.00035452188,0.0012757444,0.60243034,0.1569096,0.008602299,0.015032515,0.0015547061],"about_ca_topic_score_codex":0.000013183097,"about_ca_topic_score_gemma":0.00010317073,"teacher_disagreement_score":0.95852065,"about_ca_system_score_codex":0.00005214904,"about_ca_system_score_gemma":0.00005511986,"threshold_uncertainty_score":0.41888168},"labels":[],"label_agreement":null},{"id":"W2804364458","doi":"10.1609/aaai.v32i1.12221","title":"Clustering - What Both Theoreticians and Practitioners Are Doing Wrong","year":2018,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Selection (genetic algorithm); Task (project management); Conceptual clustering; Correlation clustering; Machine learning; Implementation; Consensus clustering; Constrained clustering; CURE data clustering algorithm; Artificial intelligence; Data mining; Engineering","score_opus":0.0757605411064104,"score_gpt":0.3368907167482257,"score_spread":0.2611301756418153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804364458","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":[0.04613931,0.00030110832,0.9292779,0.010598608,0.0029553245,0.0016216136,0.000015901722,0.00037308573,0.008717125],"genre_scores_gemma":[0.9454822,0.0008916643,0.052778274,0.00027392726,0.00026323614,0.000087892324,0.0000010221694,0.000045113262,0.0001766576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99646276,0.00006766571,0.00070961856,0.0011980998,0.00092828245,0.00063355867],"domain_scores_gemma":[0.99681807,0.00026577382,0.0010101625,0.0007354099,0.0009988345,0.00017177868],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001230205,0.0004757962,0.0005104835,0.0002759078,0.00041004163,0.0020442447,0.0032901643,0.00028513547,0.00003359215],"category_scores_gemma":[0.0006699455,0.00039109087,0.00014512244,0.00051066576,0.0009767865,0.0017262867,0.0055122557,0.0012122025,0.00003663872],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026910976,0.0002717251,0.000098393604,0.0011733447,0.00013923609,0.000010407366,0.011773998,0.002900906,0.012449869,0.4435882,0.00012704536,0.5271978],"study_design_scores_gemma":[0.00004346682,0.00023098651,0.00010822178,0.005028245,0.000027182414,0.00002844481,0.0043228916,0.61763394,0.11135696,0.26040462,0.00012270885,0.0006923238],"about_ca_topic_score_codex":0.000040263265,"about_ca_topic_score_gemma":0.000017390068,"teacher_disagreement_score":0.8993429,"about_ca_system_score_codex":0.00016490053,"about_ca_system_score_gemma":0.00018691285,"threshold_uncertainty_score":0.9998541},"labels":[],"label_agreement":null},{"id":"W2805783523","doi":"10.1007/978-3-319-92058-0_8","title":"A Comparison of Knee Strategies for Hierarchical Spatial Clustering","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","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":"Brock University","funders":"","keywords":"Hierarchical clustering; Computer science; Cluster analysis; Medoid; Centroid; Dendrogram; Cluster (spacecraft); Data mining; Artificial intelligence; Complete linkage; Pattern recognition (psychology); Population","score_opus":0.04336293284831568,"score_gpt":0.3482684205343744,"score_spread":0.30490548768605874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805783523","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":[0.00013580428,0.00015778751,0.9962847,0.00020633137,0.0013422074,0.0006904067,0.000012092073,0.00012825473,0.0010423865],"genre_scores_gemma":[0.19732451,0.0000058723845,0.8017145,0.0001121591,0.0006481983,0.00002674483,0.000004582804,0.000043163298,0.0001202975],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955265,0.000038886268,0.00078509125,0.0015052457,0.0012564844,0.0008878143],"domain_scores_gemma":[0.99656296,0.00092571706,0.00037510434,0.0014133413,0.00052771176,0.00019514485],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084616727,0.00050613866,0.0008355509,0.00083754136,0.00025194863,0.00049044436,0.0036817358,0.00033401075,0.000026433456],"category_scores_gemma":[0.00014879237,0.0004809058,0.00017139828,0.00045469945,0.0015289679,0.00063747814,0.0026243145,0.00081599446,0.000013231993],"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":[0.000047559708,0.000055716406,0.00002209079,0.00023066858,0.000021306894,0.000020087535,0.002909911,0.06401666,0.00086629257,0.007063191,0.000014073094,0.92473245],"study_design_scores_gemma":[0.00034404427,0.0008313085,0.00002291944,0.00033883742,0.0000044327285,0.000022168566,0.0000012017732,0.8600181,0.003581599,0.13399744,0.00040941485,0.00042857075],"about_ca_topic_score_codex":0.000029246721,"about_ca_topic_score_gemma":0.00020691186,"teacher_disagreement_score":0.9243039,"about_ca_system_score_codex":0.00026685366,"about_ca_system_score_gemma":0.0009746122,"threshold_uncertainty_score":0.99976426},"labels":[],"label_agreement":null},{"id":"W2885148117","doi":"10.1142/s0219649218500338","title":"High-Dimensional Text Datasets Clustering Algorithm Based on Cuckoo Search and Latent Semantic Indexing","year":2018,"lang":"en","type":"article","venue":"Journal of Information & Knowledge Management","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Concordia University","keywords":"Computer science; Cluster analysis; Cuckoo search; Data mining; Search engine indexing; Document clustering; Clustering high-dimensional data; Curse of dimensionality; Spectral clustering; Artificial intelligence; Machine learning; Particle swarm optimization","score_opus":0.016741765429655938,"score_gpt":0.2882689026699501,"score_spread":0.27152713724029415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885148117","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":[0.001959572,0.000036327045,0.99506253,0.0005255831,0.0006738861,0.00023833559,0.000009082132,0.00003824191,0.0014564431],"genre_scores_gemma":[0.35980007,0.00004559239,0.6388693,0.00064805936,0.00036039072,0.000010314473,0.000025014411,0.00001794333,0.00022332495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782854,0.00009183825,0.0006581564,0.00017577563,0.0008860579,0.0003596182],"domain_scores_gemma":[0.9986027,0.00009286125,0.0002463877,0.00040753634,0.000460866,0.00018966985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013698934,0.00017952645,0.00021547228,0.00090981455,0.0002581233,0.00036052262,0.0007170047,0.00004710256,0.000022633738],"category_scores_gemma":[0.000041118277,0.00015196699,0.000052475905,0.0005009657,0.000081571925,0.002017281,0.00100907,0.0003083618,0.00018839004],"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":[0.000057777674,0.00010482452,0.00001944296,0.00015778889,0.000063949905,0.000049948903,0.0006897099,0.034065366,0.000018539631,0.0013400367,0.002003305,0.9614293],"study_design_scores_gemma":[0.0012882933,0.00045332967,0.0012950691,0.00029231206,0.000009419645,0.000062802406,0.0000861102,0.988217,0.00037459598,0.0001347886,0.0076245777,0.00016171818],"about_ca_topic_score_codex":0.0000053104654,"about_ca_topic_score_gemma":0.000002537737,"teacher_disagreement_score":0.9612676,"about_ca_system_score_codex":0.00022407957,"about_ca_system_score_gemma":0.00007110302,"threshold_uncertainty_score":0.6197034},"labels":[],"label_agreement":null},{"id":"W2885153817","doi":"10.5740/jaoacint.18-0161","title":"Log Transformation and the Effect on Estimation, Implication, and Interpretation of Mean and Measurement Uncertainty in Microbial Enumeration","year":2018,"lang":"en","type":"article","venue":"Journal of AOAC International","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Enumeration; Transformation (genetics); Interpretation (philosophy); Estimation; Statistics; Mathematics; Biological system; Applied mathematics; Econometrics; Biology; Computer science; Combinatorics; Economics; Genetics","score_opus":0.010492868194594974,"score_gpt":0.2946327197836856,"score_spread":0.2841398515890906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885153817","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":[0.4623282,0.000053342515,0.53481203,0.0024078013,0.00015343576,0.0001644538,0.0000015222594,0.0000037098696,0.00007550403],"genre_scores_gemma":[0.99415344,0.000031792337,0.005694048,0.000050489733,0.000058041922,0.000004996756,0.0000012287348,0.0000028640286,0.000003091279],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989128,0.00012931219,0.00037456994,0.00010555474,0.0004092124,0.0000685277],"domain_scores_gemma":[0.9989598,0.0001815821,0.00024624393,0.000079446014,0.0005041136,0.000028840665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014995392,0.00006908059,0.00012239287,0.00020288953,0.00005555743,0.00008445864,0.00018593391,0.0000273884,0.0000017397396],"category_scores_gemma":[0.0002604036,0.000047906004,0.00002150015,0.000097717995,0.000139868,0.00055876485,0.000043120748,0.00011652077,4.86076e-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":[0.002297433,0.000091723414,0.0014965122,0.0000956723,0.00015999471,0.000002779001,0.02093215,0.021664627,0.024386115,0.02083971,0.000087780165,0.9079455],"study_design_scores_gemma":[0.0030213324,0.00075207767,0.012257305,0.0001681172,0.00000900897,0.00012407025,0.000055603086,0.96785426,0.011397235,0.004227455,0.00006539276,0.000068111716],"about_ca_topic_score_codex":0.000019080639,"about_ca_topic_score_gemma":0.000029176683,"teacher_disagreement_score":0.94618964,"about_ca_system_score_codex":0.00010330477,"about_ca_system_score_gemma":0.00003316498,"threshold_uncertainty_score":0.19535501},"labels":[],"label_agreement":null},{"id":"W2889601666","doi":"10.5555/3327757.3327943","title":"Clustering Redemption–Beyond the Impossibility of Kleinberg’s Axioms","year":2018,"lang":"en","type":"article","venue":"Research Portal (King's College London)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Axiom; Cluster analysis; Impossibility; Consistency (knowledge bases); Mathematics; Theoretical computer science; Computer science; Algorithm; Discrete mathematics; Mathematical economics; Artificial intelligence","score_opus":0.04832968473082041,"score_gpt":0.3718895973347923,"score_spread":0.32355991260397193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889601666","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":[0.35645324,0.001250512,0.5452457,0.008152125,0.0028702796,0.0048893713,0.00017876067,0.00086309464,0.08009689],"genre_scores_gemma":[0.97754467,0.000068000416,0.017192092,0.000095726944,0.00059344305,0.00014312485,0.000005424358,0.000048970123,0.0043085385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924169,0.00083438976,0.00088119286,0.0011877978,0.0030105568,0.0016691721],"domain_scores_gemma":[0.99382615,0.001072739,0.00023656932,0.0027527364,0.0016998432,0.00041195832],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0066275946,0.00033087298,0.00046594924,0.00058725383,0.0012308739,0.00032019007,0.0038828608,0.00019445182,0.00025592878],"category_scores_gemma":[0.0011481337,0.00025638606,0.00020767606,0.0034614909,0.0018641803,0.0010566779,0.003787666,0.0011531098,0.00018711819],"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":[0.0025339085,0.0033144245,0.011963193,0.0021675066,0.0013318879,0.0041179005,0.022265527,0.003184815,0.11384495,0.31313807,0.045030147,0.47710767],"study_design_scores_gemma":[0.0039225128,0.0037292223,0.02112651,0.0005533525,0.000023916222,0.0008584598,0.0024499847,0.83170366,0.061819542,0.048852112,0.023285417,0.0016753088],"about_ca_topic_score_codex":0.00048446676,"about_ca_topic_score_gemma":0.0006490519,"teacher_disagreement_score":0.82851887,"about_ca_system_score_codex":0.00025339634,"about_ca_system_score_gemma":0.00074103015,"threshold_uncertainty_score":0.99998885},"labels":[],"label_agreement":null},{"id":"W2896348621","doi":"10.1007/978-3-030-01298-4_2","title":"A Self-representation Model for Robust Clustering of Categorical Sequences","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","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":"Université de Sherbrooke","funders":"","keywords":"Cluster analysis; Categorical variable; Computer science; Pattern recognition (psychology); Artificial intelligence; Pairwise comparison; Representation (politics); CURE data clustering algorithm; Similarity (geometry); Correlation clustering; Noise (video); Data mining; Subspace topology; Machine learning; Image (mathematics)","score_opus":0.05873108898476034,"score_gpt":0.32340882607728344,"score_spread":0.26467773709252307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896348621","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":[0.000024441184,0.00011396615,0.9975226,0.00024664035,0.0007444539,0.00070333,0.000007922679,0.00016848517,0.00046817726],"genre_scores_gemma":[0.017057857,0.000036220714,0.98202026,0.000106878826,0.00033465415,0.00003588349,0.000004266487,0.000037017075,0.0003669571],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995881,0.00002995962,0.0006222862,0.0015442381,0.001185534,0.0007369534],"domain_scores_gemma":[0.9969235,0.00060876104,0.0003518784,0.0012433846,0.0007027887,0.0001696746],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00082141627,0.00042542294,0.00057720114,0.0007863867,0.00022796754,0.0002925028,0.0034842738,0.00028009815,0.000006738113],"category_scores_gemma":[0.00015182824,0.00040093772,0.00014651503,0.0006468304,0.00073916384,0.0008079867,0.0019174828,0.0004689117,0.000009135413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010531902,0.000025247233,0.000003704341,0.00012375755,0.00001299452,0.00001337721,0.0014671844,0.8550413,0.0001118492,0.0016625905,0.000007881017,0.14151956],"study_design_scores_gemma":[0.00023531931,0.00022822822,0.000002076894,0.000118805845,0.00000594211,0.000039573933,3.329373e-7,0.87245965,0.0010808931,0.12543021,0.000049887385,0.0003490826],"about_ca_topic_score_codex":0.000024737094,"about_ca_topic_score_gemma":0.000074371324,"teacher_disagreement_score":0.14117049,"about_ca_system_score_codex":0.00045678808,"about_ca_system_score_gemma":0.0007619932,"threshold_uncertainty_score":0.99984425},"labels":[],"label_agreement":null},{"id":"W2905920056","doi":"10.32920/ryerson.14661465","title":"Kernel k-MACE: hypercube unsupervised clustering method","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Cluster analysis; Kernel (algebra); Pattern recognition (psychology); Computer science; Artificial intelligence; Kernel method; Initialization; Kernel embedding of distributions; Feature vector; Mace; Variable kernel density estimation; Mathematics; Support vector machine; Combinatorics","score_opus":0.0463775866907028,"score_gpt":0.3578731729497401,"score_spread":0.3114955862590373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905920056","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":[0.00096669653,0.00059620006,0.98740226,0.001379228,0.0015261358,0.0004641054,0.000008932286,0.00091542734,0.006741022],"genre_scores_gemma":[0.012913453,0.00020769762,0.98109555,0.0004898255,0.0002504331,0.0001304014,0.000019842253,0.00007694554,0.0048158295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99485344,0.0004468151,0.00059617724,0.0020381068,0.0011068757,0.0009585617],"domain_scores_gemma":[0.99545634,0.0003616395,0.00013562324,0.003214661,0.00045295362,0.00037878033],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009686983,0.0005864113,0.00075229135,0.00031153785,0.00019358523,0.0013611617,0.004192014,0.00047540237,0.00025715277],"category_scores_gemma":[0.00021501108,0.00058703416,0.00032285965,0.00063091447,0.000060889448,0.00054774195,0.020789064,0.001750721,0.00010368633],"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":[0.000012445278,0.00015262725,0.0000338203,0.00074321934,0.00021902753,0.0007330653,0.0020948607,0.18193837,0.0052365265,0.0010468232,0.00030304102,0.8074862],"study_design_scores_gemma":[0.00034014805,0.000030233297,0.00021837861,0.00018879506,0.000010427671,0.00013722888,0.00017189598,0.99168634,0.0037635216,0.0015358166,0.0012185437,0.0006986723],"about_ca_topic_score_codex":0.00034203508,"about_ca_topic_score_gemma":0.00006624873,"teacher_disagreement_score":0.809748,"about_ca_system_score_codex":0.00035894403,"about_ca_system_score_gemma":0.0005697752,"threshold_uncertainty_score":0.9996755},"labels":[],"label_agreement":null},{"id":"W2913182958","doi":"10.1109/hpcc/smartcity/dss.2018.00044","title":"Towards a New Approach for Empowering the MR-DBSCAN Clustering for Massive Data Using Quadtree","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"DBSCAN; Computer science; Quadtree; Cluster analysis; Scalability; Data mining; Noise (video); Node (physics); Unsupervised learning; Artificial intelligence; CURE data clustering algorithm; Correlation clustering; Database","score_opus":0.20291280341509466,"score_gpt":0.4207903255328411,"score_spread":0.21787752211774647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913182958","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":[0.0002574495,0.000038851907,0.9954835,0.0011638735,0.00040271232,0.0011227578,0.00002524529,0.0001826766,0.0013229211],"genre_scores_gemma":[0.014616812,0.000003051458,0.98250926,0.00019623117,0.0008493783,0.00008424555,0.000015668538,0.00003970711,0.0016856539],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976302,0.000040933228,0.0002869833,0.0009218514,0.0003739742,0.000746091],"domain_scores_gemma":[0.9970034,0.0002549967,0.00010010478,0.002251597,0.00021376138,0.00017618104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008378533,0.00021613375,0.00022414139,0.000099367455,0.000529701,0.0004710028,0.0041987034,0.00006843557,0.000012380345],"category_scores_gemma":[0.0003073655,0.0001577831,0.000075758515,0.0003900251,0.00012701511,0.0009373251,0.0036027527,0.00013837469,0.0000069634184],"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":[0.00017780933,0.00012733664,0.000027429003,0.00030973396,0.00023517982,0.0000060921693,0.004654013,0.03879702,0.0080535095,0.008441765,0.011535332,0.9276348],"study_design_scores_gemma":[0.00058535166,0.00012349461,0.000011993158,0.000019314697,0.000008439978,0.000020965355,0.0002487901,0.98385745,0.0020335566,0.0011191291,0.011747332,0.00022420302],"about_ca_topic_score_codex":0.00031280672,"about_ca_topic_score_gemma":0.000092277485,"teacher_disagreement_score":0.94506043,"about_ca_system_score_codex":0.00013128025,"about_ca_system_score_gemma":0.00034743155,"threshold_uncertainty_score":0.7802306},"labels":[],"label_agreement":null},{"id":"W2913529671","doi":"10.1109/ssci.2018.8628863","title":"Hybrid Metaheuristic Algorithm for Clustering","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Metaheuristic; Cluster analysis; Tabu search; Computer science; Parallel metaheuristic; Heuristics; Artificial intelligence; Data mining; Machine learning; Meta-optimization","score_opus":0.03140047396787493,"score_gpt":0.3250039390918261,"score_spread":0.2936034651239512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913529671","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":[0.000098089746,0.000029502904,0.99591637,0.00031525575,0.0005807091,0.00028011025,0.0000052932396,0.00036507874,0.002409616],"genre_scores_gemma":[0.014858544,0.0000037462512,0.9801895,0.00024758646,0.00039996378,0.00007081462,0.0000017495274,0.000019452213,0.0042086616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984873,0.0000284197,0.00019528929,0.0004833813,0.00028492807,0.0005207025],"domain_scores_gemma":[0.9987324,0.00018047976,0.000040693794,0.0006455997,0.00025955547,0.00014128888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033622424,0.00013662157,0.00015716827,0.00011745148,0.00022276753,0.00017988075,0.0010588167,0.000025858324,0.0000367712],"category_scores_gemma":[0.00010338685,0.00012254175,0.00006523721,0.00020721502,0.00009411544,0.0004335539,0.000665834,0.0000862962,0.0001941922],"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":[0.000003032876,0.0000192685,0.0000010654682,0.000010143022,0.000015983014,0.000010212419,0.000055844965,0.000047638514,0.00033982826,0.0019501903,0.0010394724,0.99650735],"study_design_scores_gemma":[0.0003201737,0.00021883471,0.000019603178,0.000006834984,0.0000025314898,0.00005229954,0.000005846816,0.96290374,0.010731341,0.005894582,0.019677345,0.00016684702],"about_ca_topic_score_codex":0.000013779409,"about_ca_topic_score_gemma":0.0000037785321,"teacher_disagreement_score":0.99634045,"about_ca_system_score_codex":0.000058356658,"about_ca_system_score_gemma":0.000047608548,"threshold_uncertainty_score":0.49971077},"labels":[],"label_agreement":null},{"id":"W2914448888","doi":"","title":"Proceedings of the 8th Conference on 8th WSEAS International Conference on Neural Networks - Volume 8","year":2007,"lang":"en","type":"article","venue":"","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":"University of Windsor","funders":"","keywords":"Volume (thermodynamics); Artificial neural network; Library science; Political science; Computer science; Artificial intelligence","score_opus":0.046595973343882394,"score_gpt":0.31942001435816136,"score_spread":0.272824041014279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914448888","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":[0.055846676,0.000008521818,0.7971388,0.0055861813,0.0012240846,0.00048098346,0.000004465942,0.00022669684,0.1394836],"genre_scores_gemma":[0.98619777,0.000008311872,0.008016563,0.00041855196,0.00012270019,0.000008717362,8.7388565e-7,0.000010836307,0.005215655],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790436,0.000017963293,0.00027834866,0.00046203515,0.0008812298,0.00045607137],"domain_scores_gemma":[0.9987407,0.000086795895,0.00014132418,0.0003657847,0.00053537905,0.0001300712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043361905,0.00017471024,0.00015824534,0.000113728085,0.000116663716,0.00019708811,0.0022705859,0.00007350371,0.00009770425],"category_scores_gemma":[0.0000904745,0.00012201153,0.00006585036,0.00041029823,0.00017539614,0.00038183416,0.0007369254,0.00044935461,0.000023611468],"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":[0.00015544704,0.00025015857,0.0030680865,0.000022681626,0.000038584487,0.00001556113,0.00056296756,0.0071616927,0.0022376503,0.84785557,0.0017992744,0.13683233],"study_design_scores_gemma":[0.000299362,0.00022844764,0.010757101,0.000058242542,0.0000013567455,0.000013016096,0.00008381806,0.9834626,0.0023334355,0.0022311695,0.00037812465,0.00015335501],"about_ca_topic_score_codex":0.000031130556,"about_ca_topic_score_gemma":0.000012475867,"teacher_disagreement_score":0.9763009,"about_ca_system_score_codex":0.00010178204,"about_ca_system_score_gemma":0.000060583618,"threshold_uncertainty_score":0.49754858},"labels":[],"label_agreement":null},{"id":"W2915001123","doi":"10.1609/aaai.v26i1.8282","title":"Weighted Clustering","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":48,"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 Waterloo","funders":"Strategic Research Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Research Foundation; Sino-Danish Center; Danmarks Grundforskningsfond; National Science Foundation","keywords":"Cluster analysis; Computer science; Correlation clustering; CURE data clustering algorithm; Generalization; Single-linkage clustering; Data mining; Canopy clustering algorithm; Artificial intelligence; Fuzzy clustering; Consensus clustering; Hierarchical clustering; Selection (genetic algorithm); Pattern recognition (psychology); Mathematics","score_opus":0.08640250646346599,"score_gpt":0.32819258052314715,"score_spread":0.24179007405968117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915001123","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":[0.03941091,0.000084361396,0.90882593,0.0119161075,0.0011446109,0.00047153208,0.000004925069,0.00030434076,0.037837286],"genre_scores_gemma":[0.9476122,0.0000515104,0.05074677,0.0002648389,0.00007486903,0.00002321172,3.4855518e-7,0.000016518989,0.0012097036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99777925,0.000023803761,0.00045730863,0.0005935858,0.00069283694,0.0004531937],"domain_scores_gemma":[0.9979678,0.00010448811,0.00020790893,0.0004883183,0.0011153328,0.0001161632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034886855,0.0002010141,0.00024243353,0.000108912,0.00022135703,0.00032181974,0.002284887,0.00008052471,0.00008754115],"category_scores_gemma":[0.00043629753,0.00016006414,0.00011589815,0.0011196337,0.00020211872,0.00064210367,0.0013977872,0.00039294816,0.00011868485],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024436898,0.00012183981,0.00003490793,0.000053280528,0.000016896085,0.0000060453463,0.0007185063,0.00014123516,0.105526514,0.6342413,0.000057670186,0.2590574],"study_design_scores_gemma":[0.000020416477,0.00006248121,0.0000497162,0.00014410654,0.000002970654,0.00001971321,0.00021840403,0.27829772,0.62283,0.09798437,0.0002148005,0.00015530715],"about_ca_topic_score_codex":0.000013063249,"about_ca_topic_score_gemma":0.0000063374023,"teacher_disagreement_score":0.90820134,"about_ca_system_score_codex":0.000071125396,"about_ca_system_score_gemma":0.00016696787,"threshold_uncertainty_score":0.65272266},"labels":[],"label_agreement":null},{"id":"W2918582631","doi":"10.1109/acssc.2018.8645076","title":"Kernel K-Mace Clustering","year":2018,"lang":"en","type":"article","venue":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Kernel (algebra); Cluster analysis; Variable kernel density estimation; Initialization; Mathematics; Kernel method; Computer science; Gaussian function; Kernel embedding of distributions; Algorithm; Pattern recognition (psychology); Artificial intelligence; Gaussian; Discrete mathematics","score_opus":0.05666554003204609,"score_gpt":0.3049090948370821,"score_spread":0.24824355480503602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918582631","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":[0.0062202793,0.0003525618,0.98350894,0.0006882933,0.0019853162,0.00036433278,0.00001094674,0.00041496678,0.0064543374],"genre_scores_gemma":[0.96437806,0.000110374145,0.03259153,0.0004502473,0.0007832801,0.00005327116,0.0000045203624,0.00004471297,0.0015840299],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964717,0.00029146334,0.00052519445,0.0011034446,0.00077593804,0.00083222747],"domain_scores_gemma":[0.99774635,0.00019738414,0.00022947775,0.0010374888,0.00036897924,0.0004203013],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061802013,0.00043781544,0.0005171791,0.0002890329,0.00046083075,0.0010177563,0.0014957907,0.00014749554,0.000022609736],"category_scores_gemma":[0.000035063287,0.00040481787,0.00007706427,0.00039276405,0.0003464475,0.00062339136,0.00091799797,0.00030477782,0.00039450626],"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":[0.00030921673,0.00048246296,0.00066027336,0.00082624913,0.00049412204,0.0004795357,0.005259965,0.0047459737,0.008868755,0.1316088,0.021663824,0.8246008],"study_design_scores_gemma":[0.00081774517,0.00094667776,0.00054503186,0.0005555625,0.00000743837,0.00013373395,0.00028527278,0.98271155,0.00051453355,0.00080699055,0.0120056365,0.00066981005],"about_ca_topic_score_codex":0.00014807918,"about_ca_topic_score_gemma":0.000017194861,"teacher_disagreement_score":0.9779656,"about_ca_system_score_codex":0.00011105831,"about_ca_system_score_gemma":0.00014660356,"threshold_uncertainty_score":0.9998404},"labels":[],"label_agreement":null},{"id":"W2923023146","doi":"10.1109/tbdata.2019.2907624","title":"Hierarchical Density-Based Clustering Using MapReduce","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":55,"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":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Cluster analysis; Scalability; Automatic summarization; Correlation clustering; Hierarchical clustering; CURE data clustering algorithm; Data mining; Canopy clustering algorithm; Constrained clustering; Artificial intelligence; Database","score_opus":0.1308743166587772,"score_gpt":0.3353534078399405,"score_spread":0.2044790911811633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923023146","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":[0.020743748,0.0000090006615,0.97663945,0.00037761865,0.001608636,0.00024081844,0.00008248052,0.00021964202,0.00007860237],"genre_scores_gemma":[0.7608311,0.000005505023,0.2385696,0.00021578021,0.00008346354,0.000006966994,0.000011642397,0.000025825779,0.00025007845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978163,0.000109767076,0.00022075792,0.0008498663,0.0005388349,0.00046443433],"domain_scores_gemma":[0.9966199,0.00019623208,0.000044475535,0.0029059546,0.00006183727,0.00017163814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030574144,0.00018548308,0.00018926158,0.00026992528,0.00022635177,0.00018458847,0.0023203027,0.00008562766,0.00002621226],"category_scores_gemma":[0.00000979668,0.0001913558,0.000054170214,0.00055869913,0.00006620746,0.0006934666,0.00007049834,0.0005235679,0.0002543227],"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":[0.00008229368,0.00025874423,0.000018378596,0.00008357862,0.000045292123,0.00006315371,0.00011422326,0.43440542,0.030753551,0.000037548063,0.000055793516,0.53408206],"study_design_scores_gemma":[0.00047845853,0.000077331315,0.000046474965,0.00005991929,0.000006060511,0.00004491842,0.0000066773623,0.978183,0.019963222,0.000058985166,0.0008576267,0.00021735726],"about_ca_topic_score_codex":0.00006764437,"about_ca_topic_score_gemma":0.00003557301,"teacher_disagreement_score":0.7400874,"about_ca_system_score_codex":0.0001275846,"about_ca_system_score_gemma":0.00019879956,"threshold_uncertainty_score":0.7803263},"labels":[],"label_agreement":null},{"id":"W2940105449","doi":"10.1002/9780470057339.vac028.pub2","title":"Clustering","year":2012,"lang":"en","type":"other","venue":"Encyclopedia of Environmetrics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 Waterloo","funders":"","keywords":"Principal component analysis; Cluster analysis; Ordination; Pattern recognition (psychology); Cluster (spacecraft); Artificial intelligence; Basis (linear algebra); Projection (relational algebra); Computer science; Group (periodic table); Subdivision; Object (grammar); Data mining; Projection pursuit; Mathematics; Geography; Machine learning; Algorithm","score_opus":0.014610352294990935,"score_gpt":0.2573610325764483,"score_spread":0.24275068028145738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940105449","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.106291e-7,0.0030042555,0.49485013,0.000016021831,0.0005855168,0.00013163302,0.000010775595,0.00013878192,0.50126207],"genre_scores_gemma":[0.00004812901,0.006504955,0.351467,0.000016010274,0.00045705703,0.000016319951,0.000006769467,0.00029964346,0.6411841],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978898,0.00005990651,0.00031228154,0.00047479608,0.0007106023,0.00055259763],"domain_scores_gemma":[0.99800617,0.00017630376,0.00031091733,0.0012927244,0.0000125514935,0.00020134763],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024408972,0.0003041954,0.0004119201,0.0011391952,0.00003026502,0.000021571774,0.0016507764,0.00031606545,0.0007358147],"category_scores_gemma":[0.00017991768,0.00030991196,0.000104666695,0.0010285327,0.00010458206,0.00018793979,0.0013671872,0.00038162456,0.0005258635],"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":[0.000002572213,0.00021450267,0.0005420366,0.00035584735,0.00008474465,0.000040888794,0.00018961853,0.0002977954,0.000027893568,0.0008352979,0.16545717,0.8319516],"study_design_scores_gemma":[0.0001468431,0.000037735612,0.0003242053,0.000047105914,0.000009105373,0.000007640962,0.0000033540155,0.0017897324,0.00002743238,0.000060849834,0.99722314,0.00032283296],"about_ca_topic_score_codex":0.00004146509,"about_ca_topic_score_gemma":0.0000038922385,"teacher_disagreement_score":0.831766,"about_ca_system_score_codex":0.00008141331,"about_ca_system_score_gemma":0.00003747498,"threshold_uncertainty_score":0.99993527},"labels":[],"label_agreement":null},{"id":"W2940228547","doi":"","title":"Formulation relaxée de la séparation équilibrée d’un graphe","year":2017,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"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":"Humanities; Combinatorics; Mathematics; Computer science; Philosophy","score_opus":0.026009490997036817,"score_gpt":0.29127812826218347,"score_spread":0.26526863726514666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940228547","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":[0.026519049,0.0013582823,0.9019238,0.019364273,0.0005262409,0.00073026004,0.000042961565,0.00037016056,0.049164988],"genre_scores_gemma":[0.52611804,0.0013301464,0.43400502,0.00008154794,0.00009579178,0.00016400867,0.00023666388,0.000089967536,0.037878823],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9822042,0.013098228,0.0009091931,0.0016356509,0.0011353956,0.0010173048],"domain_scores_gemma":[0.98542917,0.003895756,0.001171008,0.005693104,0.003318906,0.0004920583],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.014837188,0.0006290426,0.00058062543,0.00035158088,0.0018334248,0.002976745,0.0048404317,0.0008103294,0.00013354898],"category_scores_gemma":[0.004907533,0.00074230746,0.0003864882,0.0006136821,0.0008313959,0.0015193594,0.0046372996,0.001759948,0.00019695854],"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":[0.00002684491,0.00062706677,0.0012463501,0.00023019902,0.00012041992,0.000041656927,0.015486979,0.0026406369,0.00476318,0.6241306,0.00076320575,0.3499229],"study_design_scores_gemma":[0.0010322594,0.0000018603516,0.020877404,0.0022479924,0.000049332193,0.00012684938,0.000051282368,0.7875058,0.036707994,0.108659185,0.041853134,0.00088691706],"about_ca_topic_score_codex":0.0023313651,"about_ca_topic_score_gemma":0.00064352603,"teacher_disagreement_score":0.78486514,"about_ca_system_score_codex":0.00054337387,"about_ca_system_score_gemma":0.0009333694,"threshold_uncertainty_score":0.9995028},"labels":[],"label_agreement":null},{"id":"W2949559209","doi":"","title":"Efficient unimodality test in clustering by signature testing","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Unimodality; Signature (topology); Cluster analysis; Statistic; Hierarchical clustering; Statistical hypothesis testing; Test statistic; Mathematics; Computer science; Algorithm; Pattern recognition (psychology); Statistics; Data mining; Artificial intelligence","score_opus":0.06277861707316333,"score_gpt":0.22055729697849485,"score_spread":0.1577786799053315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949559209","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":[0.16417348,0.00006728757,0.83319944,0.000084279294,0.00030054498,0.00036437943,0.000021767111,0.00034890304,0.0014399232],"genre_scores_gemma":[0.9781838,0.000016848866,0.021043958,0.000060965172,0.00006410904,0.0000025706725,0.000009986415,0.00003362813,0.0005841004],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965895,0.00026205354,0.00032242594,0.0017797714,0.00024057449,0.0008057077],"domain_scores_gemma":[0.9967084,0.00084803096,0.00025992113,0.0016820041,0.00023868961,0.00026296743],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006993308,0.0004463692,0.00046403837,0.0003905319,0.00018231917,0.00019133695,0.003073967,0.00042963008,0.000005911847],"category_scores_gemma":[0.0005365114,0.0005379023,0.00011781816,0.0013846703,0.00014722513,0.00016789642,0.0066296817,0.0017836461,0.00004057776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007131439,0.00011891264,0.002178313,0.00013709045,0.000011711643,0.00029437622,0.00012180762,0.993976,0.00029233872,0.001127946,0.0000473682,0.0016870046],"study_design_scores_gemma":[0.0004519572,0.000050980005,0.0010571416,0.0002110724,0.000007238005,0.000007188791,0.00002341077,0.99156517,0.00013613437,0.005835509,0.000121900324,0.0005322906],"about_ca_topic_score_codex":0.00029850673,"about_ca_topic_score_gemma":0.00005287398,"teacher_disagreement_score":0.8140103,"about_ca_system_score_codex":0.00075935794,"about_ca_system_score_gemma":0.00021623416,"threshold_uncertainty_score":0.9997072},"labels":[],"label_agreement":null},{"id":"W2950793146","doi":"10.2298/csis180601007l","title":"Density-based clustering with constraints","year":2019,"lang":"en","type":"article","venue":"Computer Science and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"DBSCAN; Cluster analysis; Computer science; Benchmark (surveying); Data mining; Process (computing); Computation; Correlation clustering; Quality (philosophy); Constrained clustering; Algorithm; CURE data clustering algorithm; Machine learning","score_opus":0.01108352661053865,"score_gpt":0.23954492617872325,"score_spread":0.2284613995681846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950793146","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":[0.023173513,0.000009321041,0.9742392,0.00014801788,0.00053773663,0.0003349078,8.2841916e-7,0.00013537491,0.0014211361],"genre_scores_gemma":[0.9065706,0.0000016901469,0.0928972,0.00046643536,0.000029728204,0.000010536597,0.0000011245462,0.0000029158923,0.000019731557],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828273,0.000025397103,0.00020871183,0.00026357305,0.0008809531,0.00033865246],"domain_scores_gemma":[0.9986005,0.000051739975,0.00011169458,0.0004899262,0.000591342,0.00015478453],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00091643503,0.000114426744,0.00014299044,0.00034731353,0.0002284763,0.0012924371,0.00078922266,0.000029892435,0.0000015606003],"category_scores_gemma":[0.000015042964,0.00008952746,0.000012212772,0.0008550076,0.00030322594,0.007784335,0.00041505482,0.00010378257,0.00013711037],"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":[0.000026107744,0.000028440876,0.0037435626,0.0005228379,0.000018084802,0.00001612762,0.002997457,0.19364853,0.0008058899,0.03718786,0.00015478762,0.7608503],"study_design_scores_gemma":[0.0004073959,0.000141904,0.0014563381,0.00007824377,4.5978925e-7,0.00011304248,0.000053276846,0.9941713,0.00024940373,0.0000061563824,0.0031821467,0.00014032229],"about_ca_topic_score_codex":0.000007989466,"about_ca_topic_score_gemma":4.4928734e-7,"teacher_disagreement_score":0.8833971,"about_ca_system_score_codex":0.00009175334,"about_ca_system_score_gemma":0.00031736452,"threshold_uncertainty_score":0.9997443},"labels":[],"label_agreement":null},{"id":"W2950811391","doi":"10.3390/info10060208","title":"Latent Feature Group Learning for High-Dimensional Data Clustering","year":2019,"lang":"en","type":"article","venue":"Information","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Shenzhen University; China Postdoctoral Science Foundation","keywords":"Feature (linguistics); Pattern recognition (psychology); Cluster analysis; Artificial intelligence; Weighting; Computer science; Fitness function; Constraint (computer-aided design); Clustering high-dimensional data; Crossover; Data mining; Genetic algorithm; Mathematics; Machine learning","score_opus":0.02428100589534357,"score_gpt":0.2843044617072172,"score_spread":0.2600234558118736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950811391","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":[0.008351568,0.000013147387,0.98986185,0.00058468845,0.00048293415,0.0003418337,0.000008808043,0.00015467976,0.0002005197],"genre_scores_gemma":[0.5325799,0.0000059661147,0.4653778,0.00033828773,0.00010607483,0.000034815737,0.00069221866,0.000011793314,0.00085311226],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990748,0.00001803547,0.00016618284,0.00017536867,0.00032871196,0.0002368897],"domain_scores_gemma":[0.9991063,0.00008092047,0.00009113555,0.00056966126,0.00010441254,0.000047600286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003600717,0.000084268824,0.000088639994,0.00010108545,0.00011589814,0.00020189477,0.00080619956,0.000054618038,0.000008063303],"category_scores_gemma":[0.00007125323,0.000078099234,0.000018320974,0.00015791442,0.00000882899,0.004721535,0.0010208819,0.00018388023,0.00023735699],"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":[0.000056510333,0.000019163966,0.00023704581,0.0002065244,0.000026255637,0.0000016945854,0.00074706465,0.297761,0.0010393569,0.005531369,0.0020919614,0.6922821],"study_design_scores_gemma":[0.0004653926,0.00008054951,0.0013427928,0.000025094329,0.0000010321604,0.000010933435,0.00001393366,0.9796387,0.00012883743,0.00021718422,0.017972888,0.00010267231],"about_ca_topic_score_codex":0.000013288979,"about_ca_topic_score_gemma":0.0000022035692,"teacher_disagreement_score":0.6921794,"about_ca_system_score_codex":0.0000634417,"about_ca_system_score_gemma":0.000028203845,"threshold_uncertainty_score":0.34229988},"labels":[],"label_agreement":null},{"id":"W2951747536","doi":"10.1145/3321386","title":"Hierarchical Clustering","year":2019,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":207,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Engineering and Physical Sciences Research Council; Alan Turing Institute; National Science Foundation","keywords":"Cluster analysis; Hierarchical clustering; Granularity; Constrained clustering; Computer science; Correlation clustering; Data mining; Similarity (geometry); Hierarchy; Fuzzy clustering; Set (abstract data type); Function (biology); Canopy clustering algorithm; Mathematics; Artificial intelligence","score_opus":0.020996761164785226,"score_gpt":0.29897148618925345,"score_spread":0.27797472502446824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951747536","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":[0.34279487,0.00017251434,0.625608,0.026574442,0.0030733165,0.00015802715,4.2810714e-7,0.000033595577,0.0015847917],"genre_scores_gemma":[0.69528407,0.00001602953,0.3021037,0.00041753554,0.0002760451,6.433836e-7,1.7226872e-8,0.000010719092,0.0018912571],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989683,0.00007333234,0.00020204415,0.00009282117,0.0004773493,0.00018617418],"domain_scores_gemma":[0.99819446,0.00016122483,0.00014219909,0.0013403699,0.00009110627,0.000070633476],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00045158726,0.000056966095,0.00011647356,0.00006657489,0.000051806703,0.00007850627,0.0055552125,0.000025590387,0.000014839713],"category_scores_gemma":[0.00057122455,0.00003355165,0.00010241548,0.00021638443,0.000025363766,0.0003552454,0.0033453512,0.00041258297,0.00005258473],"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":[0.00026054637,0.0003397878,0.013953663,0.00019566616,0.00029855582,0.00039905251,0.004266337,0.104861386,0.114968956,0.008268516,0.012287892,0.73989964],"study_design_scores_gemma":[0.004037344,0.0012833405,0.06833528,0.00065900496,0.000019512003,0.006002082,0.00014906988,0.6501594,0.022148332,0.17329308,0.07318375,0.0007297871],"about_ca_topic_score_codex":0.0000011440685,"about_ca_topic_score_gemma":4.5252233e-7,"teacher_disagreement_score":0.73916984,"about_ca_system_score_codex":0.00006266297,"about_ca_system_score_gemma":0.00006907001,"threshold_uncertainty_score":0.9998252},"labels":[],"label_agreement":null},{"id":"W2952461389","doi":"10.1016/j.ins.2018.01.013","title":"RECOME: A new density-based clustering algorithm using relative KNN kernel density","year":2018,"lang":"en","type":"article","venue":"Information Sciences","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Beijing Municipal Natural Science Foundation; National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Pattern recognition (psychology); Jump; Single-linkage clustering; Merge (version control); Nearest-neighbor chain algorithm; Kernel density estimation; Algorithm; Graph; Kernel (algebra); Discontinuity (linguistics); k-nearest neighbors algorithm; Data mining; Artificial intelligence; Mathematics; Correlation clustering; CURE data clustering algorithm; Canopy clustering algorithm; Theoretical computer science; Combinatorics; Statistics; Physics","score_opus":0.06083948764184269,"score_gpt":0.3449632069298229,"score_spread":0.2841237192879802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952461389","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":[0.011351743,0.000007526458,0.98509467,0.00062020984,0.0006271563,0.00020143822,0.000002010236,0.00022503144,0.0018702216],"genre_scores_gemma":[0.12610897,0.000002182972,0.87292373,0.0006773551,0.00014702104,0.0000039864344,0.0000018234655,0.0000050234366,0.00012988805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976272,0.00008413636,0.00043199002,0.00034318527,0.000985797,0.00052771653],"domain_scores_gemma":[0.99841315,0.00017538213,0.00026212411,0.00044628032,0.0004834885,0.00021956906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012165476,0.00017499548,0.00017891299,0.0004645857,0.00094049843,0.00080196647,0.0012290444,0.00007858034,0.000020674359],"category_scores_gemma":[0.0003053697,0.0001596744,0.000057025278,0.001777117,0.00047677895,0.008486692,0.00065493636,0.00020585774,0.0003189331],"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":[0.00001928607,0.000025858935,0.0006004699,0.00002681724,0.000018070044,0.000009958166,0.0070147533,0.016704993,0.0004829939,0.0035425194,0.00035180588,0.9712025],"study_design_scores_gemma":[0.00030442912,0.00013666242,0.00096050155,0.00004430742,0.000002156897,0.00004707626,0.00014317493,0.99054843,0.002971367,0.0033776932,0.0012510415,0.00021318316],"about_ca_topic_score_codex":0.0003748323,"about_ca_topic_score_gemma":0.00004577764,"teacher_disagreement_score":0.9738434,"about_ca_system_score_codex":0.00021769734,"about_ca_system_score_gemma":0.0006214693,"threshold_uncertainty_score":0.77333814},"labels":[],"label_agreement":null},{"id":"W2954483433","doi":"","title":"Density-based clustering based on hierarchical density estimates","year":2013,"lang":"en","type":"article","venue":"ResearchOnline at James Cook University (James Cook University)","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":"University of Alberta","funders":"","keywords":"Cluster analysis; Partition (number theory); Hierarchical clustering; Single-linkage clustering; Hierarchy; Complete-linkage clustering; Measure (data warehouse); Hierarchical clustering of networks; Correlation clustering; Data mining; Cluster (spacecraft); Mathematics; CURE data clustering algorithm; Computer science; Stability (learning theory); Tree (set theory); Algorithm; Artificial intelligence; Machine learning; Combinatorics","score_opus":0.017394209216698518,"score_gpt":0.24577310594874077,"score_spread":0.22837889673204226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954483433","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":[0.12647595,0.000034781653,0.8566763,0.0073589147,0.00019237654,0.0013182969,0.000060023067,0.0011444615,0.006738886],"genre_scores_gemma":[0.5928719,0.00017724038,0.3354854,0.0017436722,0.00024086129,0.00000457944,0.0002175732,0.00017521366,0.06908354],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99371594,0.0007820453,0.0003194708,0.0016808682,0.0017385314,0.0017631487],"domain_scores_gemma":[0.99384266,0.0018415544,0.000191883,0.0019695244,0.000926396,0.0012279579],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00048626217,0.00064554624,0.00068455155,0.0022474078,0.0021241694,0.00051671197,0.0036315718,0.000358023,0.0004554763],"category_scores_gemma":[0.00039638803,0.00075766107,0.00037260447,0.0026010713,0.0014538021,0.001399507,0.0036621098,0.001458105,0.0007251458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010630218,0.0064244494,0.028639045,0.0017305803,0.00129158,0.040216155,0.0030483864,0.494416,0.026930595,0.02336365,0.02750792,0.3358014],"study_design_scores_gemma":[0.003257349,0.0006327038,0.0026276459,0.00018679132,0.000027522026,0.000032045857,0.00028913186,0.9131493,0.0026171787,0.00013098166,0.07621645,0.00083290006],"about_ca_topic_score_codex":0.0008107308,"about_ca_topic_score_gemma":0.00037949023,"teacher_disagreement_score":0.5211909,"about_ca_system_score_codex":0.00235635,"about_ca_system_score_gemma":0.001196594,"threshold_uncertainty_score":0.99948746},"labels":[],"label_agreement":null},{"id":"W2964040819","doi":"10.1609/aaai.v32i1.12221","title":"Clustering - What Both Theoreticians and Practitioners Are Doing Wrong","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Conceptual clustering; Machine learning; Selection (genetic algorithm); Correlation clustering; Artificial intelligence; Task (project management); Implementation; Consensus clustering; Constrained clustering; CURE data clustering algorithm; Data mining; Engineering; Software engineering","score_opus":0.016906449382870597,"score_gpt":0.3005511694067407,"score_spread":0.2836447200238701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964040819","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":[0.004556783,0.00010411861,0.98546,0.0016884293,0.0003191162,0.00011120874,3.4123227e-7,0.00021412453,0.0075459164],"genre_scores_gemma":[0.5444567,0.00016454588,0.45368707,0.0006445806,0.00021983651,0.000013262889,4.5070865e-7,0.000017922686,0.00079561153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987954,0.00007207471,0.00012794329,0.0003843824,0.00026444753,0.00035578618],"domain_scores_gemma":[0.99916106,0.00016722934,0.000059757615,0.0004114503,0.00008599098,0.000114484224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038046596,0.000111016016,0.00010588477,0.00009804005,0.00027046597,0.00076148816,0.00041110584,0.00004125009,0.000037910268],"category_scores_gemma":[0.00006240097,0.0000983624,0.000019211784,0.0002602537,0.0002101799,0.002487751,0.00067878474,0.0001353753,0.000052579257],"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":[0.000041164472,0.00006376741,0.000260627,0.000081362814,0.000046113004,0.00011925776,0.0063934997,0.000927277,0.0037342561,0.04246567,0.00038291336,0.9454841],"study_design_scores_gemma":[0.000540398,0.00025425942,0.0014402226,0.0002781236,0.0000043775344,0.00021579521,0.004063738,0.9751064,0.004947204,0.004873247,0.007803909,0.0004723365],"about_ca_topic_score_codex":0.000016740769,"about_ca_topic_score_gemma":0.000056200985,"teacher_disagreement_score":0.9741791,"about_ca_system_score_codex":0.000054871634,"about_ca_system_score_gemma":0.000024800049,"threshold_uncertainty_score":0.7343048},"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":"W2972986690","doi":"10.1016/j.ijar.2019.09.001","title":"A three-way cluster ensemble approach for large-scale data","year":2019,"lang":"en","type":"article","venue":"International Journal of Approximate Reasoning","topic":"Advanced Clustering Algorithms Research","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":"Saint Mary's University","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Data mining; Correlation clustering; SPARK (programming language); CURE data clustering algorithm; Cluster (spacecraft); k-medians clustering; Granularity; Fuzzy clustering; Single-linkage clustering; Data stream clustering; Scale (ratio); Constrained clustering; Artificial intelligence","score_opus":0.03398508273410222,"score_gpt":0.3263792715860228,"score_spread":0.2923941888519206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972986690","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":[0.007233102,0.00015462103,0.9894122,0.0006010856,0.00085100613,0.00028812696,0.00003091699,0.000041545678,0.0013874286],"genre_scores_gemma":[0.08309245,0.000026910951,0.9160165,0.00012683048,0.00044350067,0.0000110247165,0.00003367294,0.000028255166,0.00022081373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755377,0.000041228956,0.0005010313,0.00044530243,0.0010316201,0.00042704822],"domain_scores_gemma":[0.99765265,0.00022451619,0.00044052774,0.00077788724,0.00077260454,0.00013184057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016719585,0.00016774026,0.00028885202,0.00025132202,0.00007568358,0.00037967338,0.0043147025,0.000072469156,0.000013308348],"category_scores_gemma":[0.00022535527,0.00014417396,0.00012533281,0.00018657718,0.0000229937,0.0017339844,0.0016108997,0.00033472924,0.000016268454],"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":[0.002686101,0.0029397844,0.011705866,0.0007873567,0.002945073,0.00039299022,0.007500231,0.0827898,0.01779786,0.14485571,0.011687352,0.7139119],"study_design_scores_gemma":[0.0016677036,0.000108578606,0.00015833034,0.00012281463,0.0000075842427,0.0005105122,0.00012669439,0.9891623,0.00075228605,0.0025089413,0.0047085057,0.0001657451],"about_ca_topic_score_codex":0.000005613222,"about_ca_topic_score_gemma":0.0000029240719,"teacher_disagreement_score":0.9063725,"about_ca_system_score_codex":0.0001501998,"about_ca_system_score_gemma":0.00013461354,"threshold_uncertainty_score":0.8017862},"labels":[],"label_agreement":null},{"id":"W2979735657","doi":"10.1109/fuzz-ieee.2019.8858972","title":"Evidential clustering for categorical data","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Categorical variable; Cluster analysis; Outlier; Data mining; Computer science; Partition (number theory); Fuzzy clustering; Artificial intelligence; Pattern recognition (psychology); Fuzzy logic; Mathematics; Machine learning","score_opus":0.17710035093563814,"score_gpt":0.4150464112990636,"score_spread":0.23794606036342547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979735657","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":[0.000037418682,0.00020565762,0.9927396,0.0012278326,0.0033515447,0.0010853253,0.00005318973,0.00038597517,0.0009134602],"genre_scores_gemma":[0.035991736,0.00008466878,0.9553327,0.0001712264,0.000916337,0.00018043301,0.00025557686,0.00006447453,0.007002831],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996434,0.00006664214,0.00040491048,0.0017905169,0.0006487675,0.0006551881],"domain_scores_gemma":[0.9935334,0.00035552584,0.00013841948,0.0056078113,0.00020429962,0.00016054869],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.000728269,0.00031183573,0.00042263884,0.00018058256,0.000104350955,0.0007567617,0.010018335,0.00027498964,0.000022127278],"category_scores_gemma":[0.00025055607,0.00029649597,0.00011783947,0.00016551482,0.00003832711,0.0007396076,0.04611038,0.0007039353,0.00016091244],"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":[0.00011474449,0.0002767131,0.00006949652,0.003497307,0.00042463467,0.00012613369,0.00058548903,0.27434725,0.00047579172,0.0147565855,0.04810363,0.6572222],"study_design_scores_gemma":[0.0002893246,0.00004524186,0.000028788649,0.000045644076,0.0000082216875,0.000018999177,0.000006341727,0.9814995,0.000109773086,0.0056114933,0.011980076,0.00035662806],"about_ca_topic_score_codex":0.00013427807,"about_ca_topic_score_gemma":0.00003126038,"teacher_disagreement_score":0.70715225,"about_ca_system_score_codex":0.00018824406,"about_ca_system_score_gemma":0.00041161868,"threshold_uncertainty_score":0.99994874},"labels":[],"label_agreement":null},{"id":"W2980402111","doi":"10.1109/tfuzz.2019.2947231","title":"Hyperplane Division in Fuzzy C-Means: Clustering Big Data","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Fuzzy Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":35,"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; Alberta Innovates","keywords":"Cluster analysis; Disjoint sets; Hyperplane; Fuzzy clustering; Correlation clustering; Single-linkage clustering; CURE data clustering algorithm; Linear subspace; Computer science; Big data; Data mining; Division (mathematics); Clustering high-dimensional data; Data stream clustering; Mathematics; Canopy clustering algorithm; Data set; Artificial intelligence; Combinatorics","score_opus":0.06256838438048681,"score_gpt":0.29738658859684824,"score_spread":0.23481820421636143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980402111","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":[0.009305397,0.00015960942,0.9818919,0.00016392172,0.0054649315,0.00074034376,0.00006842927,0.00029988497,0.0019056319],"genre_scores_gemma":[0.99240494,0.000063266045,0.0054949573,0.000042098345,0.0001221133,0.00006280312,0.000010359572,0.000041373805,0.0017580674],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967108,0.00022431077,0.000520382,0.0010653174,0.0008242263,0.0006549933],"domain_scores_gemma":[0.9965902,0.0003033899,0.000093986986,0.0027621866,0.00007277685,0.00017747804],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000766605,0.00028324535,0.00039398044,0.00054885645,0.00015671209,0.0002973942,0.0023923288,0.00014635932,0.000007918052],"category_scores_gemma":[0.000011157289,0.00027398634,0.000061649705,0.0009257425,0.000037833288,0.0010281958,0.00006299819,0.000576756,0.000843645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045397377,0.00024394055,0.00015448924,0.00027502718,0.000043345928,0.000087687535,0.0004983974,0.7499884,0.0034497723,0.00008090007,0.00008030185,0.24505238],"study_design_scores_gemma":[0.0010905759,0.00022720541,0.00028843732,0.00043632503,0.0000046209357,0.00010217453,0.00018793775,0.99397874,0.00045598226,0.000060630515,0.0027447944,0.0004225841],"about_ca_topic_score_codex":0.0005980673,"about_ca_topic_score_gemma":0.00029401827,"teacher_disagreement_score":0.9830996,"about_ca_system_score_codex":0.00024047405,"about_ca_system_score_gemma":0.000094823496,"threshold_uncertainty_score":0.9999712},"labels":[],"label_agreement":null},{"id":"W2990431786","doi":"10.1016/j.dib.2019.104899","title":"Data on cut-edge for spatial clustering based on proximity graphs","year":2019,"lang":"en","type":"article","venue":"Data in Brief","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Cluster analysis; Data mining; Similarity (geometry); Computer science; Cluster (spacecraft); Single-linkage clustering; Enhanced Data Rates for GSM Evolution; Correlation clustering; Spatial analysis; Data point; CURE data clustering algorithm; Pattern recognition (psychology); Artificial intelligence; Mathematics; Image (mathematics); Statistics","score_opus":0.08391157172496429,"score_gpt":0.35313526980121274,"score_spread":0.26922369807624846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990431786","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":[0.0027515504,0.000009031634,0.99208206,0.00077354134,0.0006184654,0.0010432623,0.0021040025,0.00012355867,0.0004945315],"genre_scores_gemma":[0.57968855,0.000018516012,0.4095243,0.002419382,0.0004025619,0.00018001035,0.0072214087,0.000113607646,0.0004316891],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972965,0.00008580718,0.000255261,0.0013203813,0.00053376186,0.00050829054],"domain_scores_gemma":[0.9925788,0.00044185497,0.0000745773,0.006760161,0.00004627246,0.00009835498],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00096106913,0.00018166543,0.00021533424,0.00020315732,0.00008473612,0.00019510361,0.0064567034,0.000069085625,0.000015057787],"category_scores_gemma":[0.00042709426,0.0001774324,0.000023117618,0.00037229888,0.000045219946,0.0013016722,0.004322228,0.0003102612,0.00008469714],"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":[0.0009787988,0.0013022316,0.00309688,0.00075730577,0.000049798113,0.0001521446,0.00023205054,0.036220074,0.0009859648,0.0056606024,0.013647016,0.9369171],"study_design_scores_gemma":[0.0011315917,0.00026934297,0.0018716522,0.0000974004,0.0000014764578,0.0000026051994,0.0000033557037,0.9679796,0.00024136952,0.00031374692,0.027879788,0.00020806449],"about_ca_topic_score_codex":0.00021924886,"about_ca_topic_score_gemma":0.0004847018,"teacher_disagreement_score":0.93670905,"about_ca_system_score_codex":0.00007985314,"about_ca_system_score_gemma":0.00011079619,"threshold_uncertainty_score":0.99891883},"labels":[],"label_agreement":null},{"id":"W2990511412","doi":"10.1109/access.2020.2968290","title":"K-MACE and Kernel K-MACE Clustering","year":2020,"lang":"en","type":"preprint","venue":"IEEE Access","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mace; Cluster analysis; Estimator; Kernel (algebra); Computer science; Mathematics; Cluster (spacecraft); Algorithm; Artificial intelligence; Statistics; Combinatorics","score_opus":0.09332408950713195,"score_gpt":0.38665922038682365,"score_spread":0.2933351308796917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990511412","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":[0.00764856,0.0005770205,0.98467374,0.003063134,0.0018121457,0.0004983389,0.000016149428,0.0005588864,0.0011520061],"genre_scores_gemma":[0.80075705,0.0008383902,0.1944382,0.0012474802,0.0011593066,0.00025722285,0.000011730983,0.0001451339,0.0011455155],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966461,0.00012043722,0.00038421375,0.0015258021,0.00069112063,0.0006323241],"domain_scores_gemma":[0.99764013,0.00019050432,0.00021259725,0.0014241555,0.00015399628,0.00037859543],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00028576527,0.00043655076,0.00049789366,0.00018877287,0.00017768191,0.0018965203,0.0050636968,0.00026179926,0.00001053982],"category_scores_gemma":[0.000120739816,0.0004603548,0.00009514327,0.00040976168,0.00011463484,0.0009570471,0.01631198,0.0013379033,0.00005855629],"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":[0.00012570964,0.00018747493,0.001187522,0.0046025882,0.00042732843,0.0018641903,0.005283012,0.2285669,0.0057385927,0.0013489068,0.006482987,0.7441848],"study_design_scores_gemma":[0.00040454508,0.00004615288,0.0010811846,0.00026270092,0.000011295407,0.00005433242,0.000014313657,0.9806705,0.0036408652,0.01011421,0.0029801906,0.0007196754],"about_ca_topic_score_codex":0.00019420728,"about_ca_topic_score_gemma":0.000030688003,"teacher_disagreement_score":0.79310846,"about_ca_system_score_codex":0.00014938146,"about_ca_system_score_gemma":0.00019634393,"threshold_uncertainty_score":0.9997848},"labels":[],"label_agreement":null},{"id":"W2991006005","doi":"10.1007/978-981-15-0994-0_7","title":"A Hybridized Data Clustering for Breast Cancer Prognosis and Risk Exposure Using Fuzzy C-means and Cohort Intelligence","year":2019,"lang":"en","type":"book-chapter","venue":"Algorithms for intelligent systems","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":"University of Windsor","funders":"","keywords":"Cluster analysis; Breast cancer; Computer science; Artificial intelligence; Fuzzy logic; Fuzzy clustering; Machine learning; Metaheuristic; Data mining; Cancer; Medicine; Internal medicine","score_opus":0.09180944651642126,"score_gpt":0.34054516961173614,"score_spread":0.2487357230953149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991006005","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":[0.00010328385,0.009853423,0.97285485,0.00009259637,0.0024437602,0.0075741853,0.006481222,0.00022606926,0.0003706025],"genre_scores_gemma":[0.010145816,0.058277827,0.80196714,0.00015727048,0.005422966,0.004285327,0.0011348651,0.00161262,0.11699618],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937652,0.00009126001,0.0013456182,0.002802914,0.00089551165,0.0010995187],"domain_scores_gemma":[0.99454886,0.00092548097,0.00094406155,0.0023506938,0.0008077266,0.00042316728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017706404,0.0010232492,0.0014649278,0.00048068524,0.00050836394,0.0008816045,0.0025385884,0.0005153029,0.000008900361],"category_scores_gemma":[0.000112603215,0.0009916131,0.00022666839,0.00014926148,0.00027297984,0.00091678376,0.0028016611,0.0006657846,0.000012666142],"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":[0.00026896736,0.00008903482,0.0012313371,0.0052433335,0.0025521356,0.000040453077,0.00082843256,0.010954071,0.000069198235,0.00779117,0.00034764307,0.9705842],"study_design_scores_gemma":[0.00050864794,0.0003133878,0.000035069366,0.0018702477,0.00034048708,0.00051378726,0.00013160957,0.9740534,0.0000870989,0.0013744863,0.019584334,0.0011874462],"about_ca_topic_score_codex":0.0008031845,"about_ca_topic_score_gemma":0.00013010274,"teacher_disagreement_score":0.96939677,"about_ca_system_score_codex":0.00044455487,"about_ca_system_score_gemma":0.00038058968,"threshold_uncertainty_score":0.99925345},"labels":[],"label_agreement":null},{"id":"W2995714961","doi":"10.1109/cwit.2019.8929909","title":"Correct Number of Clusters (CNC) Description Length in Arbitrary Shape Clustering","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Cluster analysis; Computer science; Cluster (spacecraft); k-medians clustering; Determining the number of clusters in a data set; Compact space; Separable space; Context (archaeology); Data mining; Point (geometry); Algorithm; Correlation clustering; Mathematics; Artificial intelligence; CURE data clustering algorithm","score_opus":0.023176129352283057,"score_gpt":0.2908982372374981,"score_spread":0.267722107885215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995714961","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":[0.37242627,0.000020507556,0.603244,0.00014848013,0.0005896969,0.00032777057,0.0000010054135,0.00014159585,0.023100693],"genre_scores_gemma":[0.8681637,0.000022522081,0.12974271,0.00014574765,0.000025019468,0.000013553753,0.0000016434533,0.000018540399,0.0018665455],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981829,0.000090707246,0.0003649409,0.0004768005,0.0004353434,0.0004493417],"domain_scores_gemma":[0.99899244,0.00014036633,0.00008338068,0.0006236059,0.000071978735,0.000088207315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039152842,0.00016102007,0.00025864676,0.00020535222,0.00002986706,0.000073708536,0.0008664904,0.00008068046,0.00016786263],"category_scores_gemma":[0.00003609988,0.00015625703,0.00006446984,0.00060936116,0.000042551303,0.0011159229,0.0007109219,0.00028611426,0.0002749635],"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":[0.00032188915,0.00066655147,0.09115517,0.0008376791,0.000097571945,0.00017162829,0.0057755406,0.06218996,0.034185987,0.008698235,0.00056212203,0.7953377],"study_design_scores_gemma":[0.00065983745,0.00007961368,0.0065044286,0.000088541,0.000001006539,0.000048716363,0.0001376253,0.9896563,0.0018720452,0.0005442738,0.00020377479,0.00020379697],"about_ca_topic_score_codex":0.00016408213,"about_ca_topic_score_gemma":0.00005291155,"teacher_disagreement_score":0.9274664,"about_ca_system_score_codex":0.0001439151,"about_ca_system_score_gemma":0.00006865088,"threshold_uncertainty_score":0.6371976},"labels":[],"label_agreement":null},{"id":"W3011819927","doi":"10.1142/s0218488520500087","title":"Estimating and Controlling Overlap in Gaussian Mixtures for Clustering Methods Evaluation","year":2020,"lang":"en","type":"article","venue":"International Journal of Uncertainty Fuzziness and Knowledge-Based Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thales (Canada)","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Mixture model; Set (abstract data type); Artificial intelligence; Data set; Machine learning; Pattern recognition (psychology)","score_opus":0.05904577131457585,"score_gpt":0.40376231642250937,"score_spread":0.34471654510793354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011819927","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":[0.010162189,0.0023561113,0.9839873,0.0015864664,0.001472794,0.00035342778,0.0000059651325,0.000017014443,0.000058787504],"genre_scores_gemma":[0.85072047,0.000012798023,0.1485462,0.000073479845,0.00059054,0.000036843925,0.000002445783,0.000011830377,0.0000054196107],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798983,0.00034644242,0.0006678865,0.0002850915,0.00050039066,0.00021035687],"domain_scores_gemma":[0.99713534,0.0009476047,0.00039711376,0.00010485372,0.0012524854,0.00016262691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026884377,0.0001588064,0.00037296463,0.00029214312,0.00007971848,0.0003683765,0.00053081155,0.00006319893,0.0000012042318],"category_scores_gemma":[0.0012295274,0.00013339355,0.000072151466,0.00020416884,0.00004480786,0.00042254207,0.00014400546,0.00020631857,3.4922417e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003330014,0.000050661834,0.00058329524,0.0003021998,0.000093941024,0.000028057604,0.0015510202,0.7344235,0.004616914,0.001003475,0.00001660581,0.25699735],"study_design_scores_gemma":[0.0032887824,0.00016660812,0.00023648619,0.0004991713,0.000012476198,0.000055707955,0.00020436969,0.9942965,0.00020030276,0.0005829287,0.00032358227,0.00013308422],"about_ca_topic_score_codex":0.000042594045,"about_ca_topic_score_gemma":0.000020332322,"teacher_disagreement_score":0.84055823,"about_ca_system_score_codex":0.00018483466,"about_ca_system_score_gemma":0.00026424965,"threshold_uncertainty_score":0.54396313},"labels":[],"label_agreement":null},{"id":"W3016108274","doi":"10.1093/bioinformatics/btaa243","title":"Pooled variable scaling for cluster analysis","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":11,"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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; KU Leuven","keywords":"Cluster (spacecraft); Scaling; Variable (mathematics); Computer science; Statistics; Mathematics; Programming language","score_opus":0.03153041412441573,"score_gpt":0.292185891279953,"score_spread":0.2606554771555373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016108274","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":[0.00015854862,0.000017489565,0.9961986,0.0015552745,0.00007720642,0.0002535734,0.000012733486,0.0001871215,0.0015394803],"genre_scores_gemma":[0.01045589,0.0000036103263,0.9873155,0.001922062,0.00007499853,0.000023956753,0.000013354022,0.000008424033,0.00018221026],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988088,0.00001625923,0.00034093874,0.00017551938,0.00030615,0.00035234343],"domain_scores_gemma":[0.99901825,0.00016308791,0.00009580651,0.00039004727,0.00014291774,0.00018991291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028303463,0.00011319185,0.00021392516,0.0001383062,0.0001269803,0.00024355845,0.00082052883,0.00005380179,0.000008840074],"category_scores_gemma":[0.00023340822,0.00010259973,0.00011110835,0.0014080835,0.000021312171,0.0006977988,0.00042505827,0.00010148101,0.000068099565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011666185,0.00012391174,0.00033765685,0.0013363789,0.002149127,0.0000069662083,0.016631218,0.6278728,0.0006995457,0.051421262,0.010330017,0.28897446],"study_design_scores_gemma":[0.00035348622,0.000053621297,0.000023565277,0.000005394274,0.000050219667,0.0000014393595,0.0000639238,0.9888567,0.00034090303,0.00046192616,0.009654395,0.00013446689],"about_ca_topic_score_codex":0.0000028514487,"about_ca_topic_score_gemma":4.17578e-7,"teacher_disagreement_score":0.36098385,"about_ca_system_score_codex":0.00003953218,"about_ca_system_score_gemma":0.00006304022,"threshold_uncertainty_score":0.4183896},"labels":[],"label_agreement":null},{"id":"W3022527078","doi":"10.1142/s0129065702001060","title":"ON COMPUTING THE FUZZIFIER IN ↓FLVQ: A DATA DRIVEN APPROACH","year":2002,"lang":"en","type":"article","venue":"International Journal of Neural Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"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; Fuzzy clustering; Data mining; Computer science; Heuristic; Fuzzy logic; Correlation clustering; Set (abstract data type); Artificial intelligence; Algorithm","score_opus":0.11912871943748654,"score_gpt":0.3499688145090679,"score_spread":0.23084009507158137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022527078","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":[0.15014115,0.0009148311,0.8298403,0.008423209,0.0067220647,0.00041662637,0.000015673942,0.0000573008,0.0034688185],"genre_scores_gemma":[0.9955042,0.000016963302,0.0037002643,0.00013280081,0.00050385355,0.000001554371,0.0000012409881,0.000007715874,0.00013141014],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978226,0.00019713456,0.00047587563,0.00022509838,0.0010768707,0.00020243922],"domain_scores_gemma":[0.99854416,0.00036602837,0.00029789814,0.00049424224,0.00023458521,0.00006310346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006438309,0.00009874656,0.00016008833,0.00021475057,0.000054055814,0.00033492624,0.0046750116,0.000030769083,0.000004335792],"category_scores_gemma":[0.00019255019,0.000064311535,0.000047972062,0.00022876528,0.000037063288,0.00064707623,0.0007554367,0.00044872242,0.00001783777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006046814,0.00036704788,0.0011699675,0.000023548568,0.00015956913,0.0010666172,0.002020618,0.8747748,0.00030807062,0.007870962,0.0038443285,0.10833398],"study_design_scores_gemma":[0.00039255468,0.00007983138,0.0008840752,0.00008090919,0.0000010729576,0.0010609705,0.00007337726,0.99623704,0.0000046449186,0.00011157674,0.0010086856,0.0000652728],"about_ca_topic_score_codex":0.000031786814,"about_ca_topic_score_gemma":0.0000023089567,"teacher_disagreement_score":0.8453631,"about_ca_system_score_codex":0.00013262227,"about_ca_system_score_gemma":0.000018144077,"threshold_uncertainty_score":0.8687413},"labels":[],"label_agreement":null},{"id":"W3037218554","doi":"","title":"Statistical guarantees for local graph clustering","year":2020,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 Waterloo","funders":"","keywords":"PageRank; Cluster analysis; Computer science; Graph; Theoretical computer science; Cluster (spacecraft); Clustering coefficient; Path (computing); Mathematics; Algorithm; Artificial intelligence","score_opus":0.07959760419103978,"score_gpt":0.4021193523576084,"score_spread":0.3225217481665686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037218554","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":[0.0023426155,0.00049003714,0.98907197,0.007599811,0.00012221595,0.00018786664,0.0000046303244,0.00005220953,0.00012861966],"genre_scores_gemma":[0.7185916,0.00010919443,0.28050554,0.00014071002,0.00042574923,0.000009695871,0.0000020032003,0.000036253612,0.00017932542],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961278,0.00061822054,0.0005413266,0.00034768612,0.0016235613,0.0007413942],"domain_scores_gemma":[0.9960088,0.0021850578,0.0001704242,0.00023122304,0.0009485182,0.00045598313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00375259,0.00014983413,0.0003534206,0.00041406925,0.0003721083,0.00029015177,0.0016497961,0.00007167174,0.00003420198],"category_scores_gemma":[0.0040797396,0.00012585426,0.00013514938,0.00083494704,0.00021198622,0.0004775063,0.0008077099,0.002264995,0.000021033942],"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":[0.0011692832,0.00017355938,0.0013998282,0.0004959559,0.0001563398,0.0010041578,0.003039659,0.25597695,0.0056812344,0.0060587954,0.002874413,0.72196984],"study_design_scores_gemma":[0.0011230628,0.002350006,0.00038552357,0.0000642637,0.000003707228,0.00018755144,0.00018372356,0.9766591,0.00048494784,0.002508081,0.015911222,0.00013881845],"about_ca_topic_score_codex":0.000018913453,"about_ca_topic_score_gemma":0.0000041312346,"teacher_disagreement_score":0.721831,"about_ca_system_score_codex":0.00011370927,"about_ca_system_score_gemma":0.00023123213,"threshold_uncertainty_score":0.9840402},"labels":[],"label_agreement":null},{"id":"W3038456932","doi":"10.3390/a13070158","title":"Fuzzy C-Means Clustering Algorithm with Multiple Fuzzification Coefficients","year":2020,"lang":"en","type":"article","venue":"Algorithms","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":49,"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 Waterloo","funders":"National Foundation for Science and Technology Development","keywords":"Cluster analysis; Fuzzy clustering; Correlation clustering; CURE data clustering algorithm; Canopy clustering algorithm; Data mining; Computer science; FLAME clustering; Fuzzy set; Artificial intelligence; Algorithm; Data stream clustering; Fuzzy logic; Mathematics; Pattern recognition (psychology)","score_opus":0.02957732675180462,"score_gpt":0.27321826288198814,"score_spread":0.2436409361301835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038456932","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":[0.0005584008,0.00010817614,0.9943923,0.0022824528,0.00028363476,0.00052644097,0.000022832812,0.00080149586,0.0010242616],"genre_scores_gemma":[0.102658354,0.00003273985,0.89568067,0.00079337036,0.00036180022,0.0001014442,0.000028969034,0.000073574585,0.0002691075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964557,0.00010766596,0.00040766646,0.0011426145,0.0010315224,0.0008547754],"domain_scores_gemma":[0.9979031,0.00017559755,0.00015180411,0.0009335548,0.00029345969,0.0005424836],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002707788,0.0003711742,0.00035798576,0.000154597,0.00033861445,0.00033176542,0.0017603036,0.000110599736,0.000011749482],"category_scores_gemma":[0.00012181612,0.0003362516,0.00008415452,0.0014114283,0.00013677185,0.0009225229,0.0007882463,0.00045409944,0.00034332633],"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":[0.000030107898,0.00012467743,0.00016687156,0.000043751847,0.000054199252,0.00021243705,0.0017923552,0.022276288,0.0010167905,0.00022459842,0.0002106389,0.97384727],"study_design_scores_gemma":[0.001256782,0.0003931818,0.0005090293,0.0000328119,0.00000769391,0.00009380523,0.00015852108,0.9892045,0.0016587011,0.00013495315,0.0060848366,0.00046513422],"about_ca_topic_score_codex":0.00004954915,"about_ca_topic_score_gemma":0.0000086248765,"teacher_disagreement_score":0.9733822,"about_ca_system_score_codex":0.00013808362,"about_ca_system_score_gemma":0.000117748335,"threshold_uncertainty_score":0.9999089},"labels":[],"label_agreement":null},{"id":"W3039221356","doi":"10.1109/tcss.2020.3003538","title":"Discovering Density-Based Clustering Structures Using Neighborhood Distance Entropy Consistency","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Computational Social Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":12,"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 Waterloo","funders":"","keywords":"Cluster analysis; DBSCAN; Correlation clustering; CURE data clustering algorithm; Pattern recognition (psychology); Single-linkage clustering; Artificial intelligence; Outlier; Fuzzy clustering; Entropy (arrow of time); k-medians clustering; Mathematics; Computer science; Determining the number of clusters in a data set; Algorithm; Data mining; Physics","score_opus":0.042809567367067224,"score_gpt":0.29744679765202353,"score_spread":0.25463723028495633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039221356","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":[0.0071946513,0.000036889967,0.9904223,0.00070642214,0.0009033347,0.0003548614,0.00004953327,0.00028568052,0.000046289784],"genre_scores_gemma":[0.9571263,9.84048e-7,0.042307977,0.00024324395,0.0002505115,0.000024860585,0.000004661588,0.000029819443,0.000011631637],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757224,0.00018078955,0.00042176765,0.00057633326,0.00084164314,0.00040721564],"domain_scores_gemma":[0.99902177,0.00023483609,0.00016019795,0.00019270614,0.0001883589,0.00020211653],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00011165993,0.0002565676,0.00032578473,0.00010894066,0.0009346455,0.0003920175,0.00052285794,0.000090787784,0.0000074230893],"category_scores_gemma":[0.000011420379,0.00027957116,0.0001572866,0.00060676195,0.00010264876,0.00044727392,0.000013283901,0.00034932178,0.000016014195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000375616,0.000037009348,0.00002094088,0.00008411163,0.000045189372,0.000022447004,0.0006360715,0.9912072,0.0006877416,0.004469313,0.000005843868,0.0027466042],"study_design_scores_gemma":[0.0006210943,0.00007211929,0.00016771987,0.000041881838,0.00001112173,0.000015953376,0.00012844321,0.9974505,0.0004120671,0.0007330359,0.000064402775,0.00028168518],"about_ca_topic_score_codex":0.00009734211,"about_ca_topic_score_gemma":0.000012006258,"teacher_disagreement_score":0.9499317,"about_ca_system_score_codex":0.00035576656,"about_ca_system_score_gemma":0.00023839559,"threshold_uncertainty_score":0.99996567},"labels":[],"label_agreement":null},{"id":"W3042760544","doi":"10.4018/978-1-7998-3476-2.ch005","title":"Sequence Clustering Techniques in Educational Data Mining","year":2020,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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; Medical Council of Canada","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Sequence (biology); CURE data clustering algorithm; Correlation clustering; Clustering high-dimensional data; Data stream clustering; Artificial intelligence","score_opus":0.09898537637041742,"score_gpt":0.35664151093204677,"score_spread":0.25765613456162934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042760544","genre_codex":"other","genre_gemma":"methods","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":[0.000003492075,0.000205806,0.20476912,0.0009786574,0.00030965722,0.0003865711,0.00015870866,0.00033004305,0.79285794],"genre_scores_gemma":[0.010559164,0.000024638897,0.948152,0.0011110624,0.0008503152,0.000076095675,0.00005769815,0.00009986497,0.039069127],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969969,0.000031418156,0.00047691443,0.0013142565,0.00071120757,0.00046929842],"domain_scores_gemma":[0.99748814,0.000110639274,0.00018553928,0.0018952333,0.0001058208,0.00021462838],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024813082,0.0003986004,0.00040389516,0.00014603842,0.00008812837,0.00025259357,0.0044204164,0.00025581365,0.000013415157],"category_scores_gemma":[0.000103861836,0.00045517457,0.000061225335,0.00008206814,0.00012089631,0.0003893868,0.0054750447,0.00056889805,0.00009097996],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001144946,0.000009017138,0.00001089267,0.00009424451,0.000027853683,0.00032276646,0.00012216922,0.000043254626,0.00009799113,0.78793186,0.0010877033,0.2102408],"study_design_scores_gemma":[0.00052751356,0.00024657554,0.000054115444,0.0022175228,0.000020992931,0.0006546639,0.000024446954,0.15075454,0.00026171625,0.76381683,0.079270944,0.0021501598],"about_ca_topic_score_codex":0.00006822984,"about_ca_topic_score_gemma":0.00012522662,"teacher_disagreement_score":0.7537888,"about_ca_system_score_codex":0.00063112186,"about_ca_system_score_gemma":0.00081974897,"threshold_uncertainty_score":0.99979},"labels":[],"label_agreement":null},{"id":"W3089543401","doi":"10.1007/978-3-030-58942-4_9","title":"An Ising Framework for Constrained Clustering on Special Purpose Hardware","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":17,"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 Toronto","funders":"","keywords":"Computer science; Cluster analysis; Heuristic; Benchmark (surveying); Theoretical computer science; Constraint programming; Partition (number theory); Constrained clustering; Constraint (computer-aided design); Machine learning; Artificial intelligence; Correlation clustering; Mathematical optimization; CURE data clustering algorithm","score_opus":0.036714655109650836,"score_gpt":0.3189121647864331,"score_spread":0.28219750967678225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089543401","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":[0.000009618885,0.000060900667,0.99278426,0.0015111065,0.002938145,0.000999395,0.000030414933,0.0003256289,0.0013405395],"genre_scores_gemma":[0.011891617,0.000011459167,0.9811046,0.0019855702,0.00478739,0.000028590874,0.000010286935,0.000082896724,0.00009759535],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943506,0.000050748222,0.00059381546,0.0025247114,0.0014040411,0.0010760789],"domain_scores_gemma":[0.9959757,0.0011795223,0.0002745013,0.0017753432,0.00032564643,0.00046930317],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007160239,0.0007094335,0.0007266429,0.000749456,0.0005135641,0.0012708963,0.004977867,0.00045842788,0.000024358642],"category_scores_gemma":[0.00046569336,0.00071303366,0.0001891829,0.00065992074,0.00077924796,0.00083080033,0.0016350107,0.0015917579,0.000042551834],"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":[0.000038110215,0.000025801,0.0000015444707,0.00006944768,0.000009681122,0.00016712042,0.00076768064,0.1040198,0.00014663332,0.03862844,0.000009389316,0.85611635],"study_design_scores_gemma":[0.0003288382,0.0007289062,0.0000066557686,0.000609739,0.0000039295915,0.0000496323,5.624149e-7,0.74895334,0.00097347243,0.24584465,0.0018257278,0.00067452015],"about_ca_topic_score_codex":0.0000036261429,"about_ca_topic_score_gemma":0.000020092213,"teacher_disagreement_score":0.8554418,"about_ca_system_score_codex":0.00054653455,"about_ca_system_score_gemma":0.0006580691,"threshold_uncertainty_score":0.9997659},"labels":[],"label_agreement":null},{"id":"W3090078726","doi":"10.20382/jocg.v11i1a11","title":"An improved cost function for hierarchical cluster trees","year":2019,"lang":"en","type":"article","venue":"Journal of Computational Geometry (Carleton University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Ohio State University; National Science Foundation","keywords":"Hierarchical clustering; Cluster analysis; Granularity; Tree (set theory); Function (biology); Mathematics; Graph; Similarity (geometry); Tree structure; Computer science; Set (abstract data type); Hierarchical clustering of networks; Data mining; Algorithm; Correlation clustering; Combinatorics; CURE data clustering algorithm; Artificial intelligence; Statistics","score_opus":0.012001304747632493,"score_gpt":0.26031672254219884,"score_spread":0.24831541779456634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090078726","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":[0.101082444,0.000014302942,0.8973471,0.00051056745,0.0004936161,0.00025214057,0.000009540297,0.00003300637,0.00025728834],"genre_scores_gemma":[0.78172344,0.000005835636,0.21662253,0.00022921528,0.00022820801,6.022067e-7,0.000012668402,0.000015357888,0.0011621425],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985156,0.00011354666,0.00028298618,0.00027430305,0.00053759007,0.00027599253],"domain_scores_gemma":[0.99789333,0.00053358567,0.00028408275,0.00023416014,0.00082582596,0.00022903494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042227007,0.00013461639,0.0002437565,0.0011052651,0.00012965636,0.00012801151,0.00092409,0.00008266805,0.000026453421],"category_scores_gemma":[0.00005326219,0.0001357151,0.00017025508,0.0009378103,0.000051086827,0.0015691805,0.0001650254,0.0003103836,0.000010727583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010395618,0.00029813868,0.001046842,0.000048552887,0.0001835622,0.000045351113,0.0001905847,0.86390436,0.0021820448,0.016849315,0.00035321928,0.11385845],"study_design_scores_gemma":[0.0035983336,0.0020372656,0.00921838,0.000030395502,0.00002149704,0.00010519125,0.00014114633,0.95423245,0.0001519749,0.006785677,0.023434946,0.00024272873],"about_ca_topic_score_codex":0.000002927521,"about_ca_topic_score_gemma":0.0000017301169,"teacher_disagreement_score":0.68072456,"about_ca_system_score_codex":0.00023243578,"about_ca_system_score_gemma":0.0002623531,"threshold_uncertainty_score":0.5534301},"labels":[],"label_agreement":null},{"id":"W3092332002","doi":"10.1109/tcyb.2020.3023373","title":"A <i>Group</i>-Based Distance Learning Method for Semisupervised Fuzzy Clustering","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":12,"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":"China Electronics Technology Group Corporation; Higher Education Discipline Innovation Project; Academy of Finland; National Natural Science Foundation of China","keywords":"Cluster analysis; Pairwise comparison; Artificial intelligence; Constrained clustering; Fuzzy clustering; Computer science; Machine learning; Fuzzy logic; Artificial neural network; Distance measures; Data mining; Mathematics; CURE data clustering algorithm","score_opus":0.03472825080664537,"score_gpt":0.306341575228065,"score_spread":0.2716133244214196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092332002","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":[0.00018300104,0.00003925502,0.9963542,0.0019613993,0.00027675752,0.00047071217,0.000022446555,0.0004999051,0.000192272],"genre_scores_gemma":[0.2904064,0.000018177898,0.70821303,0.00079263904,0.000072579845,0.00015266362,0.0000031462384,0.000050031816,0.00029132282],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785036,0.00014316951,0.00031605494,0.00069897756,0.00045529808,0.00053613004],"domain_scores_gemma":[0.9984171,0.00062114326,0.00007365901,0.0004570504,0.0001296129,0.0003014478],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026053164,0.00025843916,0.0002671946,0.00009806659,0.0003281912,0.00018080906,0.00082965026,0.00010428314,0.000012315265],"category_scores_gemma":[0.000038365128,0.000280814,0.00017307336,0.000609455,0.000050139635,0.00023323827,0.000011260637,0.0005592567,0.000029550423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096180505,0.000080893464,0.000001968533,0.00010696192,0.0000248728,0.000010676568,0.00066251046,0.8101059,0.009814783,0.00020743693,0.000037241618,0.17885053],"study_design_scores_gemma":[0.001137144,0.0005067732,0.000004458279,0.000042784966,0.000013381921,0.000005099485,0.00004544594,0.9654485,0.024146173,0.00021083742,0.00814106,0.00029835574],"about_ca_topic_score_codex":0.0000148986,"about_ca_topic_score_gemma":0.000022133827,"teacher_disagreement_score":0.2902234,"about_ca_system_score_codex":0.00011227245,"about_ca_system_score_gemma":0.00006475958,"threshold_uncertainty_score":0.9999644},"labels":[],"label_agreement":null},{"id":"W3094325709","doi":"10.18280/ria.340408","title":"An Improved Deep Learning Algorithm for Risk Prediction of Corporate Internet Reporting","year":2020,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Autoregressive model; Autoregressive–moving-average model; Time series; The Internet; Index (typography); Data mining; Algorithm; Deep learning; Econometrics; Mathematics","score_opus":0.0884579502347997,"score_gpt":0.3171150574558491,"score_spread":0.22865710722104943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094325709","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":[0.0101720225,0.00007617024,0.9886023,0.00013461341,0.0002229599,0.0004343812,0.000015450245,0.00025246252,0.00008965215],"genre_scores_gemma":[0.6218004,0.000041315485,0.37767866,0.000029073912,0.00015001126,0.000051299892,0.000017643459,0.000026016958,0.00020554753],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973097,0.00012469038,0.0012046371,0.00072317064,0.00022886648,0.00040893376],"domain_scores_gemma":[0.9969255,0.00020976222,0.0017034838,0.0005417533,0.00040151543,0.00021800402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011657869,0.00017538725,0.00030877866,0.000096281125,0.00016101463,0.000109221015,0.00086528657,0.00008476684,0.000018156321],"category_scores_gemma":[0.0014445254,0.00018399414,0.00012162002,0.00061839353,0.00008799058,0.00055039185,0.00026465332,0.00037814424,0.00002476204],"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":[0.000018982017,0.000059959544,0.0005519998,0.0000694395,0.000019658453,0.000010447953,0.0029438261,0.12565018,0.020154996,0.00020807955,0.000014364741,0.85029805],"study_design_scores_gemma":[0.000061251056,0.00086924515,0.000055628716,0.00003268167,0.000007161181,0.000014508437,0.0005002199,0.8857001,0.11153949,0.0006736912,0.0004088279,0.00013720845],"about_ca_topic_score_codex":0.00003998428,"about_ca_topic_score_gemma":0.0000027236422,"teacher_disagreement_score":0.85016084,"about_ca_system_score_codex":0.00005120407,"about_ca_system_score_gemma":0.000049302867,"threshold_uncertainty_score":0.7503063},"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":"W3097529996","doi":"10.1016/j.patcog.2020.107748","title":"Projected fuzzy C-means clustering with locality preservation","year":2020,"lang":"en","type":"article","venue":"Pattern Recognition","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":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Locality; Cluster analysis; Fuzzy clustering; Computer science; Fuzzy logic; Data mining; Curse of dimensionality; Clustering high-dimensional data; Partition (number theory); Benchmark (surveying); Pattern recognition (psychology); Artificial intelligence; Projection (relational algebra); Mathematics; Algorithm","score_opus":0.07571112933585794,"score_gpt":0.28262663107455643,"score_spread":0.2069155017386985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097529996","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":[0.032354407,0.000007529086,0.9635194,0.0025252688,0.000063566295,0.00040860873,0.000013092158,0.00042646876,0.0006816349],"genre_scores_gemma":[0.9030904,0.000009808156,0.09516636,0.0012427613,0.00021243647,0.00013121385,0.00008106105,0.000030489953,0.00003546061],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839824,0.000115193434,0.0002090221,0.00051767565,0.00044032204,0.000319565],"domain_scores_gemma":[0.99917954,0.00005954807,0.00008930621,0.00029971934,0.00022503192,0.00014687394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015758148,0.00014905728,0.00013899221,0.0000653215,0.00010703659,0.00017214105,0.00045261008,0.000052813975,0.000022932018],"category_scores_gemma":[0.00008133744,0.00013585208,0.000029799636,0.00053771015,0.00003267021,0.0011495204,0.0002915154,0.00023384504,0.0001599383],"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":[0.00006104759,0.00005820984,0.0020555512,0.00020650137,0.000026389116,0.000047014582,0.0014077195,0.0016045418,0.0014654938,0.0000065729655,0.00007932073,0.9929816],"study_design_scores_gemma":[0.00081638875,0.0003757213,0.005133337,0.00009039596,0.0000065537697,0.00002613006,0.00007468246,0.9879408,0.004305622,0.0005803211,0.00033887726,0.0003111971],"about_ca_topic_score_codex":0.0000777817,"about_ca_topic_score_gemma":0.000052814117,"teacher_disagreement_score":0.9926704,"about_ca_system_score_codex":0.00006456055,"about_ca_system_score_gemma":0.000044327204,"threshold_uncertainty_score":0.5539887},"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":"W3105265316","doi":"10.1007/s10955-020-02651-8","title":"Correction To: Clustering in the Three and Four Color Cyclic Particle Systems in One Dimension","year":2020,"lang":"en","type":"article","venue":"Journal of Statistical Physics","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":"University of Alberta","funders":"","keywords":"Dimension (graph theory); Cluster analysis; Mathematics; Statistical physics; Particle system; Particle (ecology); Computer science; Combinatorics; Physics; Statistics; Computer graphics (images); Geology","score_opus":0.0678446815159414,"score_gpt":0.31649388882122165,"score_spread":0.24864920730528023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105265316","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":[0.103622146,0.00003218926,0.89451444,0.001477976,0.00020870451,0.0001228591,0.0000014880775,0.0000059175636,0.000014257543],"genre_scores_gemma":[0.9680873,0.000007766063,0.031578302,0.00020119613,0.000114178205,0.000003925287,1.2660995e-7,0.0000050589974,0.0000021328897],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989121,0.00011324241,0.000283707,0.00012940365,0.0003771023,0.00018447841],"domain_scores_gemma":[0.99899197,0.00065225427,0.000077257886,0.00009666362,0.00006468595,0.000117171585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003765357,0.000064616404,0.00017183849,0.00002724907,0.000037765803,0.00010515474,0.00025476256,0.000015836877,5.000093e-7],"category_scores_gemma":[0.0003514845,0.00004884989,0.000013404281,0.0003817272,0.000027964086,0.00025975727,0.00016030954,0.00031832137,0.0000047596545],"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":[0.0005336947,0.00055055827,0.004510336,0.00024558674,0.000041028907,0.001211146,0.010327503,0.45659804,0.025527876,0.029458119,0.0012939262,0.46970218],"study_design_scores_gemma":[0.0003818712,0.00044728752,0.02199728,0.00008505274,0.0000025080215,0.000039736668,0.00011778243,0.97402054,0.00012078245,0.002698786,0.000030425148,0.00005792923],"about_ca_topic_score_codex":0.000037554066,"about_ca_topic_score_gemma":0.000028541608,"teacher_disagreement_score":0.8644652,"about_ca_system_score_codex":0.00006532155,"about_ca_system_score_gemma":0.000029061292,"threshold_uncertainty_score":0.19920409},"labels":[],"label_agreement":null},{"id":"W3107330311","doi":"10.1007/s10489-020-02108-1","title":"Improving cluster recovery with feature rescaling factors","year":2021,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Advanced Clustering Algorithms Research","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":"Université du Québec à Montréal","funders":"","keywords":"Cluster analysis; Normalization (sociology); Computer science; Data mining; Preprocessor; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Data pre-processing; Machine learning","score_opus":0.018261338284883202,"score_gpt":0.2635628413197893,"score_spread":0.2453015030349061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107330311","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":[0.0043842564,0.00014240394,0.99112993,0.00038394166,0.00020206481,0.00018026211,0.0000017183027,0.00022025016,0.0033551955],"genre_scores_gemma":[0.36471355,0.000054428947,0.6320445,0.00064332446,0.0001125887,0.000045967383,0.000009252081,0.000045202032,0.0023311789],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978024,0.000042691154,0.0002134927,0.0008266573,0.0005356722,0.0005791044],"domain_scores_gemma":[0.9982721,0.00029450248,0.00008793604,0.0009915616,0.00019202745,0.00016185726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021628603,0.00023437194,0.00022227562,0.00009919641,0.00020513972,0.00032393564,0.0010074683,0.00011080775,0.000024435394],"category_scores_gemma":[0.00010676487,0.0001946536,0.000054426855,0.0008731091,0.00008057587,0.0006012007,0.0008052512,0.00052746455,0.000076707394],"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":[0.000083290855,0.000099986166,0.00015336153,0.00011835087,0.000070421214,0.00023721326,0.0015097994,0.028680924,0.02135261,0.020533875,0.00028357792,0.9268766],"study_design_scores_gemma":[0.00027943478,0.0002018477,0.00027791664,0.00013078102,0.000011708267,0.00017301686,0.001092589,0.20618552,0.7785538,0.007684405,0.004430748,0.0009782773],"about_ca_topic_score_codex":0.000021231723,"about_ca_topic_score_gemma":0.000014145091,"teacher_disagreement_score":0.9258983,"about_ca_system_score_codex":0.00012566194,"about_ca_system_score_gemma":0.00018210009,"threshold_uncertainty_score":0.79377437},"labels":[],"label_agreement":null},{"id":"W3111477678","doi":"10.17605/osf.io/pejaq","title":"FOCAL3D Simulated Data","year":2020,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.059571032367751214,"score_gpt":0.32486404666885876,"score_spread":0.2652930143011075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111477678","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":[0.003662488,0.00000247772,0.83352345,0.0038894047,0.00033771107,0.00070392457,0.000023266371,0.0007976973,0.15705955],"genre_scores_gemma":[0.6048224,0.00014716137,0.222648,0.0030186458,0.00052230165,0.00011262859,0.000116499854,0.00018219613,0.16843018],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936098,0.000539385,0.0005418315,0.0037664275,0.00082639983,0.0007161447],"domain_scores_gemma":[0.98810315,0.00065129914,0.000164326,0.0102771325,0.00019491086,0.00060915225],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0028079294,0.00031204632,0.00038102997,0.000105978324,0.00023663387,0.00036208832,0.0099054845,0.00018287638,0.068278626],"category_scores_gemma":[0.0057275677,0.00034709912,0.00009813282,0.00078946905,0.00014445277,0.0013649564,0.020570604,0.00081811805,0.7160811],"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":[0.00027806003,0.0007347584,0.004023169,0.00035660053,0.00048712382,0.00078023836,0.00609948,0.16022108,0.021609245,0.006087396,0.109075226,0.6902476],"study_design_scores_gemma":[0.0006400225,0.0000022241059,0.00090875145,0.000028151098,0.000011024498,0.000030275778,0.00003566144,0.8397022,0.005244067,0.0027688243,0.1502171,0.00041172188],"about_ca_topic_score_codex":0.000066153334,"about_ca_topic_score_gemma":0.0000050010362,"teacher_disagreement_score":0.6898359,"about_ca_system_score_codex":0.00014026134,"about_ca_system_score_gemma":0.00021688204,"threshold_uncertainty_score":0.9998981},"labels":[],"label_agreement":null},{"id":"W3119850208","doi":"10.1007/978-3-030-73050-5_43","title":"An Efficient K-Means Clustering Algorithm for Analysing COVID-19","year":2021,"lang":"en","type":"preprint","venue":"Advances in intelligent systems and computing","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Cluster analysis; Centroid; Computer science; Coronavirus disease 2019 (COVID-19); Pandemic; Similarity (geometry); Quality (philosophy); Data mining; Health care; k-means clustering; Algorithm; Artificial intelligence; Medicine; Economics; Disease; Economic growth","score_opus":0.04157513408384758,"score_gpt":0.38017399012812736,"score_spread":0.33859885604427975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119850208","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":[0.003349957,0.018191125,0.9740079,0.000077021636,0.0028183707,0.0011983316,0.00001940843,0.00028136012,0.00005651757],"genre_scores_gemma":[0.2964081,0.0011756365,0.70137966,0.00012711523,0.00055082625,0.0001844379,0.00005972024,0.00007121811,0.000043293017],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99453545,0.00041594368,0.0012528601,0.0020964695,0.0006980361,0.0010012272],"domain_scores_gemma":[0.9964126,0.0008348769,0.0005636296,0.0013499289,0.00032914814,0.00050985214],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019870496,0.00059705426,0.0010147062,0.0006114393,0.00048927683,0.0013966217,0.0017202096,0.0002764326,0.0000017953951],"category_scores_gemma":[0.00024376046,0.0006333387,0.00020008946,0.00067001494,0.000120162076,0.0004939851,0.0029774723,0.00084603316,0.0000013173889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004175972,0.000059986363,0.00008717532,0.00082013156,0.00002906515,0.000061205385,0.0016982225,0.7012416,0.000014501142,0.00042578933,0.0000011209,0.295557],"study_design_scores_gemma":[0.00031558666,0.00010032398,0.000014739233,0.0011453476,0.0000134919965,0.000101675796,0.002570732,0.9927713,0.00008643411,0.00044088968,0.0017836884,0.0006557732],"about_ca_topic_score_codex":0.0004909638,"about_ca_topic_score_gemma":0.00013188383,"teacher_disagreement_score":0.29490122,"about_ca_system_score_codex":0.0007987482,"about_ca_system_score_gemma":0.000355988,"threshold_uncertainty_score":0.99964005},"labels":[],"label_agreement":null},{"id":"W3120082291","doi":"10.1109/ieem45057.2020.9309941","title":"Business Applications for Current Developments in Big Data Clustering: An Overview","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Western University","funders":"","keywords":"Big data; Cluster analysis; Headline; Computer science; Data science; Raw data; Currency; Data mining; Business; Artificial intelligence","score_opus":0.4828641149166046,"score_gpt":0.44616679371825857,"score_spread":0.03669732119834601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120082291","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":[0.000049309703,0.00035042578,0.9970054,0.0015590249,0.00013869675,0.0006452767,0.00001719119,0.00013096727,0.00010371377],"genre_scores_gemma":[0.014694221,0.00039268393,0.98309624,0.0006924957,0.00028830534,0.00056541833,0.00015776577,0.00002658939,0.00008627644],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985587,0.000025379248,0.00022874342,0.0006595358,0.0002329257,0.0002947129],"domain_scores_gemma":[0.99869335,0.000053461143,0.000038125578,0.0009344207,0.000119685654,0.00016095085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020140434,0.00010910723,0.00013449148,0.00007288475,0.00007406447,0.0001281743,0.002592084,0.000024493034,0.0000027682077],"category_scores_gemma":[0.00006978492,0.000105054394,0.000010990993,0.00079178624,0.000017745988,0.0007156102,0.0023825292,0.00009807914,0.000029236879],"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":[0.000004024622,0.000058594167,0.00007239321,0.00014510876,0.0000027409408,0.0000011890169,0.0001531073,0.00060129794,0.00007533223,0.0011895457,0.000114828494,0.99758184],"study_design_scores_gemma":[0.00044493316,0.000023002944,0.0023808891,0.000025999485,0.0000010465307,0.000002406976,0.000014708665,0.7430906,0.00007813044,0.00046927205,0.25327834,0.00019065612],"about_ca_topic_score_codex":0.000014813667,"about_ca_topic_score_gemma":0.00007599904,"teacher_disagreement_score":0.99739116,"about_ca_system_score_codex":0.000050448005,"about_ca_system_score_gemma":0.00017414863,"threshold_uncertainty_score":0.481678},"labels":[],"label_agreement":null},{"id":"W3122289361","doi":"10.18280/ria.340604","title":"Big Data Clustering Using Improvised Fuzzy C-Means Clustering","year":2020,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"MNIST database; Computer science; Cluster analysis; Artificial intelligence; Fuzzy clustering; Data mining; Convolutional neural network; Big data; Rand index; Fuzzy logic; Encoder; Pattern recognition (psychology); Deep learning; Machine learning","score_opus":0.21354878917626946,"score_gpt":0.34659951147689494,"score_spread":0.13305072230062548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122289361","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":[0.0022186118,0.00018735543,0.99277496,0.0018531319,0.00085550494,0.00041093092,0.0000192127,0.00043887494,0.0012414145],"genre_scores_gemma":[0.6852574,0.00009303216,0.31238225,0.0006679005,0.0010641911,0.000021105301,0.000021084139,0.00008909997,0.00040399827],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962105,0.000117634976,0.0007267574,0.0014957731,0.00051384943,0.0009354573],"domain_scores_gemma":[0.99644107,0.00020055298,0.00018716129,0.0025590903,0.00015985173,0.00045225964],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005994876,0.00034838179,0.00039045516,0.00016799221,0.00038981508,0.00044942528,0.0046212315,0.00011529435,0.000032770775],"category_scores_gemma":[0.00041340932,0.000377442,0.00010050159,0.001344869,0.00012813651,0.0011307412,0.005482259,0.0005134648,0.00040088268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023813956,0.000049519076,0.000034872417,0.00017580975,0.00002266691,0.000113002054,0.001933121,0.5459468,0.03620133,0.00015625448,0.000082500155,0.41526031],"study_design_scores_gemma":[0.00008609824,0.000116471136,0.000006213606,0.00009461932,0.000007888014,0.00007216537,0.00041616298,0.98365945,0.01127768,0.00018880323,0.0036534097,0.00042106543],"about_ca_topic_score_codex":0.000086355045,"about_ca_topic_score_gemma":0.000031142303,"teacher_disagreement_score":0.6830387,"about_ca_system_score_codex":0.00013676847,"about_ca_system_score_gemma":0.00015110099,"threshold_uncertainty_score":0.99986774},"labels":[],"label_agreement":null},{"id":"W3126183644","doi":"10.1007/s11634-022-00514-6","title":"Determinantal consensus clustering","year":2022,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"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 Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Cluster analysis; Point process; Single-linkage clustering; Mathematics; Computer science; Kernel (algebra); Similarity (geometry); Consensus clustering; Data mining; Artificial intelligence; Correlation clustering; CURE data clustering algorithm; Combinatorics; Statistics","score_opus":0.053565366313241526,"score_gpt":0.36025569701971255,"score_spread":0.306690330706471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126183644","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":[0.011081129,0.0013447038,0.98640764,0.00052613486,0.00009652943,0.000103774284,0.00005829574,0.000047707497,0.0003340819],"genre_scores_gemma":[0.93380857,0.00062707346,0.065186545,0.000041686155,0.000015832082,0.00005068858,0.00014611761,0.00000566454,0.00011784994],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844915,0.00013059586,0.00025018287,0.00065160927,0.00031407716,0.00020438866],"domain_scores_gemma":[0.99842274,0.00012433672,0.000109506145,0.0012719334,0.000023916187,0.00004754801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054850226,0.00008563674,0.00016542169,0.00035174473,0.00024564355,0.000082248494,0.0012653265,0.000015692127,0.000014584888],"category_scores_gemma":[0.00005678923,0.00008972069,0.000024991961,0.001626731,0.000060126844,0.0007518104,0.002097455,0.00016773632,0.0000026692712],"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":[0.000018820405,0.00008613971,0.011633455,0.000020920503,0.00006165215,0.000042302767,0.00023300051,0.022836113,0.0012320436,0.0026855622,0.00003614254,0.96111387],"study_design_scores_gemma":[0.00014640059,0.000020847858,0.013683039,0.0000023836928,0.000020800491,0.000017578981,0.00020922121,0.97436863,0.000028153954,0.0005126451,0.010879119,0.00011118691],"about_ca_topic_score_codex":0.000024295667,"about_ca_topic_score_gemma":0.0003516591,"teacher_disagreement_score":0.96100265,"about_ca_system_score_codex":0.00008235084,"about_ca_system_score_gemma":0.00002479426,"threshold_uncertainty_score":0.36587036},"labels":[],"label_agreement":null},{"id":"W3130186424","doi":"10.1109/icjece.2020.3018433","title":"Evaluation of Dimensionality Reduction Techniques for Load Profiling Application in Smart Grid Environment","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Electrical and Computer Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"University of Regina","keywords":"Profiling (computer programming); Dimensionality reduction; Computer science; Smart grid; Grid; Reduction (mathematics); Artificial intelligence; Engineering; Mathematics; Operating system; Electrical engineering","score_opus":0.01787113559275199,"score_gpt":0.2570653424765557,"score_spread":0.23919420688380372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130186424","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":[0.039578937,0.00076287973,0.95925826,0.00015676416,0.00009483139,0.00013708296,8.250701e-7,0.00000527924,0.000005116559],"genre_scores_gemma":[0.7238501,0.000022652179,0.2759738,0.0000076752485,0.00012098134,0.000016302622,0.0000013634033,0.0000049207083,0.0000022041536],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991437,0.000039075756,0.00023408675,0.0001344149,0.00029311673,0.00015555703],"domain_scores_gemma":[0.9992979,0.000057976533,0.000063561354,0.000099153345,0.0003569049,0.00012446579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008841865,0.000057552992,0.000118937576,0.00015603777,0.000028759492,0.00002304375,0.000120665114,0.000033864937,5.422736e-7],"category_scores_gemma":[0.00008779496,0.000059374725,0.000029295357,0.0002283502,0.000010427427,0.00014103772,0.000024276516,0.0001276136,8.7215554e-8],"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":[0.0000067894516,0.00004010639,0.0003160449,0.00004975155,0.000031116637,0.000016202774,0.00012758024,0.1470969,0.023810804,0.0033809822,0.000023966251,0.82509977],"study_design_scores_gemma":[0.00019843494,0.00008972198,0.002037644,0.000034981942,0.000006599784,0.0001176283,0.0000018539218,0.9666184,0.029217562,0.0012137496,0.00040130946,0.00006208831],"about_ca_topic_score_codex":0.000067591434,"about_ca_topic_score_gemma":0.000028456574,"teacher_disagreement_score":0.82503766,"about_ca_system_score_codex":0.00040002173,"about_ca_system_score_gemma":0.0005548038,"threshold_uncertainty_score":0.2421231},"labels":[],"label_agreement":null},{"id":"W3131740359","doi":"10.1016/j.datak.2021.101876","title":"Generation of Gaussian sets for clustering methods assessment","year":2021,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Advanced Clustering Algorithms Research","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":"Thales (Canada)","funders":"","keywords":"Cluster analysis; Computer science; Generator (circuit theory); Fuzzy clustering; Curse of dimensionality; Rand index; Mixture model; Data mining; Homogeneity (statistics); Artificial intelligence; Gaussian; Pattern recognition (psychology); Set (abstract data type); Hierarchical clustering; Maximization; Sensitivity (control systems); Algorithm; Machine learning; Mathematics; Mathematical optimization; Power (physics); Engineering","score_opus":0.1936835263463012,"score_gpt":0.47320929907024467,"score_spread":0.27952577272394347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131740359","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":[0.0001948376,0.00061440235,0.99776083,0.00009415736,0.0007885281,0.000162281,0.00006508901,0.00011120674,0.00020865806],"genre_scores_gemma":[0.0050805747,0.000026765223,0.9942734,0.0000067981764,0.00018882786,0.000042689026,0.00022989693,0.000025186535,0.00012581483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998595,0.00007410645,0.0002960792,0.00053847226,0.0001716829,0.00032467692],"domain_scores_gemma":[0.9980086,0.00026985034,0.000053638218,0.0013796162,0.00019230753,0.00009599596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008492214,0.00014491705,0.00022370921,0.000121965444,0.000070843715,0.000110934525,0.0011701754,0.000053957658,0.0000062972676],"category_scores_gemma":[0.00033894446,0.0001598471,0.000042356718,0.00042816153,0.000012089749,0.00067586766,0.0018962169,0.0001530196,0.0000033815977],"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":[0.0000013168949,0.000060051174,0.000006575892,0.00031777244,0.00005050607,0.000010506339,0.00025921786,0.009881406,0.15209857,0.0029831014,0.00032775934,0.8340032],"study_design_scores_gemma":[0.0002312273,0.00002428617,0.00010660747,0.000048728092,0.0000057815246,0.000017365202,0.000013080421,0.9521344,0.036181763,0.000040099952,0.011044156,0.00015254444],"about_ca_topic_score_codex":0.0000024531196,"about_ca_topic_score_gemma":0.000010880634,"teacher_disagreement_score":0.94225293,"about_ca_system_score_codex":0.000098338256,"about_ca_system_score_gemma":0.00016697761,"threshold_uncertainty_score":0.6518375},"labels":[],"label_agreement":null},{"id":"W3139417388","doi":"10.1016/j.neucom.2021.02.062","title":"Automatic determining optimal parameters in multi-kernel collaborative fuzzy clustering based on dimension constraint","year":2021,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Clustering Algorithms Research","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":"McMaster University","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Kernel (algebra); Computer science; Kernel embedding of distributions; Kernel method; Kernel principal component analysis; Variable kernel density estimation; Fuzzy clustering; Dimensionality reduction; Constrained clustering; Constraint (computer-aided design); Dimension (graph theory); Artificial intelligence; Data mining; Mathematics; Pattern recognition (psychology); CURE data clustering algorithm; Support vector machine","score_opus":0.03790629680017404,"score_gpt":0.31660966168509636,"score_spread":0.2787033648849223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139417388","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":[0.34324366,0.00001324056,0.6555785,0.00025699293,0.00025688723,0.00024939788,0.0000014274873,0.00024128536,0.0001586142],"genre_scores_gemma":[0.5445552,9.5336713e-7,0.45501557,0.00037141517,0.000014992553,0.000013798233,0.0000013013992,0.00001926644,0.0000074992677],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968788,0.0004289726,0.00049426866,0.00093465165,0.0005168779,0.00074644637],"domain_scores_gemma":[0.9977987,0.0010700787,0.00016332764,0.0006367116,0.00016598638,0.00016519829],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047324615,0.00028734765,0.00037894628,0.00028078226,0.00022291346,0.00032188397,0.0006131765,0.000080213904,0.000003098185],"category_scores_gemma":[0.00053253846,0.00031397355,0.00007102001,0.0011438542,0.0000787786,0.0002881116,0.00086476625,0.0005525976,0.000017992497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000781729,0.00009620518,0.00030655105,0.000046807738,0.000005462686,0.0012634844,0.0007671782,0.8681625,0.0035001626,0.00003642561,0.0000032371547,0.12580419],"study_design_scores_gemma":[0.0013519765,0.00015587767,0.002642457,0.00036482132,0.0000020983089,0.00008115668,0.00019162071,0.9881529,0.0067435256,0.000018282704,0.000015828433,0.0002794061],"about_ca_topic_score_codex":0.0000064284886,"about_ca_topic_score_gemma":0.000013050687,"teacher_disagreement_score":0.20131154,"about_ca_system_score_codex":0.00019308164,"about_ca_system_score_gemma":0.0002718763,"threshold_uncertainty_score":0.9999312},"labels":[],"label_agreement":null},{"id":"W3146117809","doi":"10.18280/isi.260106","title":"Parallelization of the K-Means++ Clustering Algorithm","year":2021,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Cluster analysis; Parallel computing; Initialization; SIMD; CUDA; Parallel algorithm; Graphics processing unit; Graphics; Algorithm; Throughput; Parallel programming model; Programming paradigm; Operating system","score_opus":0.01641005298293848,"score_gpt":0.2551106498400835,"score_spread":0.23870059685714504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3146117809","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":[0.0025583883,0.000080780126,0.99365604,0.00014049771,0.00040502308,0.00015735827,0.0000059563836,0.000100742014,0.002895201],"genre_scores_gemma":[0.47420865,0.000072003706,0.52494085,0.00025847903,0.00007423452,0.000047550773,0.000028731527,0.000014859166,0.00035463038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986143,0.000093335824,0.0004495591,0.00013502453,0.00045747703,0.00025027047],"domain_scores_gemma":[0.998548,0.000057182107,0.00021987093,0.0005879402,0.00053716515,0.00004987214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002776458,0.000111220674,0.00014019129,0.00010011863,0.0002239329,0.00020976525,0.0006432539,0.00006364338,0.000011107341],"category_scores_gemma":[0.00027777068,0.00009242404,0.00006970858,0.0009016155,0.00009143694,0.0027850983,0.0006071706,0.00012691533,0.000022604647],"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":[0.0000035779012,0.000019823598,0.00019788732,0.00022083928,0.000022333003,0.000003900841,0.0045979447,0.03653458,0.00058893446,0.005027459,0.00008840173,0.9526943],"study_design_scores_gemma":[0.00028919862,0.000027206257,0.0033078634,0.0001418609,0.000003333472,0.000091946546,0.00032742866,0.97618294,0.0119978655,0.004902655,0.002583723,0.00014396082],"about_ca_topic_score_codex":0.000022055176,"about_ca_topic_score_gemma":0.000007612124,"teacher_disagreement_score":0.95255035,"about_ca_system_score_codex":0.00017023469,"about_ca_system_score_gemma":0.00016257715,"threshold_uncertainty_score":0.3768943},"labels":[],"label_agreement":null},{"id":"W3174452951","doi":"10.1109/access.2021.3091397","title":"Automatic Data Clustering Framework Using Nature-Inspired Binary Optimization Algorithms","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Computer science; Distortion (music); Correlation clustering; CURE data clustering algorithm; Algorithm; Binary number; Canopy clustering algorithm; Data mining; Artificial intelligence; Mathematics","score_opus":0.10296852308607309,"score_gpt":0.4151459321661608,"score_spread":0.31217740908008773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174452951","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":[0.0074645868,0.00045027694,0.98882556,0.0004414607,0.0020413164,0.00019874958,0.00001568731,0.0004578277,0.00010453666],"genre_scores_gemma":[0.075806744,0.0000659112,0.92323047,0.0004024517,0.00034047107,0.000013818159,0.0000379291,0.00004350153,0.00005871966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971046,0.00016574375,0.0003795779,0.0010379191,0.00073193,0.0005802525],"domain_scores_gemma":[0.99634004,0.00026778007,0.00015123619,0.0027977857,0.00027352155,0.00016961116],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00038035004,0.00023967732,0.00028285602,0.00019815621,0.00033452903,0.0011995095,0.0046958886,0.00025651284,0.000050524905],"category_scores_gemma":[0.0003953196,0.00025628565,0.000048301536,0.0016991723,0.000058213096,0.0039213984,0.00487672,0.0007009175,0.000016494598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036740353,0.00007970182,0.000079847305,0.000114505136,0.000041627158,0.00049257645,0.0001451461,0.9068492,0.00077452534,0.00009176975,0.00011963187,0.09120781],"study_design_scores_gemma":[0.0002293936,0.000017579681,0.00018609915,0.00021608558,0.000008975295,0.00012456228,0.00001694582,0.9954374,0.002648624,0.00066626584,0.00014921799,0.0002988778],"about_ca_topic_score_codex":0.00003319266,"about_ca_topic_score_gemma":0.000006335709,"teacher_disagreement_score":0.09090893,"about_ca_system_score_codex":0.00017569479,"about_ca_system_score_gemma":0.0003001275,"threshold_uncertainty_score":0.9999889},"labels":[],"label_agreement":null},{"id":"W3182227316","doi":"10.18280/ria.350302","title":"Minimization of the Number of Iterations in K-Medoids Clustering with Purity Algorithm","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; k-medoids; Minification; Algorithm; Medoid; k-means clustering; Mathematics; Computer science; Mathematical optimization; Correlation clustering; CURE data clustering algorithm; Statistics","score_opus":0.028706898763195963,"score_gpt":0.3027406127607996,"score_spread":0.2740337139976036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182227316","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":[0.030090827,0.000051900417,0.9681724,0.00038192215,0.000130232,0.0001502469,0.0000045003835,0.000017616574,0.0010003824],"genre_scores_gemma":[0.7801068,0.00003817465,0.21891874,0.000022750488,0.000020397638,0.00001921946,0.0000024424085,0.000010163189,0.0008613407],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986638,0.000111899804,0.00041981516,0.0003052044,0.00028208035,0.00021722006],"domain_scores_gemma":[0.9986002,0.00016956462,0.00012886766,0.0007420863,0.000319867,0.00003945386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022523466,0.00009740498,0.00017767539,0.000068080546,0.000073009294,0.000038371505,0.0006018743,0.00004615466,0.000043493914],"category_scores_gemma":[0.00014920038,0.00007947376,0.000052888645,0.0014346968,0.00011280769,0.00027525524,0.00039579978,0.0001645248,0.000009949947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012504372,0.00039715966,0.0058165384,0.00019568138,0.000020863761,0.000041304087,0.005859905,0.74350137,0.009583665,0.0044731353,0.000018058041,0.23007981],"study_design_scores_gemma":[0.00004456182,0.000019139638,0.0006290266,0.00015266154,0.0000019266977,0.000048882943,0.00031778708,0.81267715,0.18535396,0.00059686,0.00008270228,0.00007533822],"about_ca_topic_score_codex":0.0000319267,"about_ca_topic_score_gemma":0.00007009373,"teacher_disagreement_score":0.7500159,"about_ca_system_score_codex":0.000053131804,"about_ca_system_score_gemma":0.00013885224,"threshold_uncertainty_score":0.32408455},"labels":[],"label_agreement":null},{"id":"W3184306616","doi":"10.3390/math9141680","title":"Self-Expressive Kernel Subspace Clustering Algorithm for Categorical Data with Embedded Feature Selection","year":2021,"lang":"en","type":"article","venue":"Mathematics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Kernel (algebra); Categorical variable; Computer science; Pattern recognition (psychology); Artificial intelligence; Variable kernel density estimation; Mathematics; Kernel method; Data mining; Algorithm; Machine learning; Support vector machine","score_opus":0.03362400087073737,"score_gpt":0.31652423611581404,"score_spread":0.2829002352450767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184306616","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":[0.00018172253,0.00010392736,0.9979718,0.00055568793,0.00013919626,0.00041763196,0.000022253304,0.00036392623,0.00024387435],"genre_scores_gemma":[0.00094739685,0.000021818296,0.99662226,0.000048815044,0.000161496,0.00007841879,0.000043987202,0.00004576784,0.0020300609],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99791646,0.00005354837,0.00021755512,0.0007377316,0.00054886995,0.000525861],"domain_scores_gemma":[0.99751884,0.00032575533,0.00013683332,0.0014379577,0.0004308871,0.0001497369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029114145,0.00023665979,0.0003058304,0.000074145704,0.00023266861,0.00035489714,0.0013275804,0.00011729937,0.00000528743],"category_scores_gemma":[0.00016425192,0.00020289744,0.000044428773,0.0006502276,0.000032332147,0.0006483552,0.0012836531,0.00031255433,0.000015475933],"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":[0.00015150719,0.0060863392,0.00011714457,0.008969345,0.0023622112,0.0027654283,0.04988223,0.02939373,0.01740696,0.036128733,0.03938473,0.80735165],"study_design_scores_gemma":[0.00058331294,0.00009402674,0.0000075598473,0.00005246871,0.000021865731,0.0005483988,0.00031126977,0.98801583,0.0051640724,0.0020467762,0.0028886837,0.00026575135],"about_ca_topic_score_codex":0.0000030198107,"about_ca_topic_score_gemma":0.000018824987,"teacher_disagreement_score":0.9586221,"about_ca_system_score_codex":0.0001442308,"about_ca_system_score_gemma":0.00022971681,"threshold_uncertainty_score":0.82739174},"labels":[],"label_agreement":null},{"id":"W3185688577","doi":"","title":"CANUCS: The CAnadian NIRISS Unbiased Cluster Survey","year":2017,"lang":"en","type":"article","venue":"JWST Proposal. Cycle 1","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cluster (spacecraft); Computer science","score_opus":0.03733052967814782,"score_gpt":0.32608347648642094,"score_spread":0.2887529468082731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185688577","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":[0.19116889,0.00048185623,0.4762704,0.21593106,0.009605465,0.0069878614,0.00039346647,0.0016329883,0.09752801],"genre_scores_gemma":[0.97792983,0.000008178882,0.017273266,0.00073715573,0.00020460827,0.00006217277,0.000009007137,0.000037261252,0.003738538],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99727166,0.00032788015,0.00024102088,0.0005989391,0.00063716836,0.0009233569],"domain_scores_gemma":[0.99600685,0.00015562786,0.0001530304,0.0029345062,0.00028742754,0.00046255937],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016528856,0.00021847645,0.00020365763,0.00011972316,0.0025411304,0.001772546,0.004697322,0.000115831535,0.000033204335],"category_scores_gemma":[0.0007360054,0.00015872739,0.000065035194,0.00022101388,0.0003793325,0.00084851444,0.0011272151,0.000499869,0.00043259902],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017918633,0.0004106072,0.08961783,0.00018900106,0.0003618865,0.0012608471,0.0068488093,0.0059260167,0.0008607086,0.025758633,0.06389883,0.8046876],"study_design_scores_gemma":[0.0013604864,0.00017590976,0.59905946,0.000066551256,0.0000091293,0.00008994632,0.000055876695,0.34241787,0.001450736,0.0072715892,0.047094632,0.0009477816],"about_ca_topic_score_codex":0.45193607,"about_ca_topic_score_gemma":0.7851688,"teacher_disagreement_score":0.80373985,"about_ca_system_score_codex":0.00038335266,"about_ca_system_score_gemma":0.0014276707,"threshold_uncertainty_score":0.9992637},"labels":[],"label_agreement":null},{"id":"W3189005758","doi":"10.6084/m9.figshare.c.5127031.v1","title":"Supplementary material from \"Multivariate phenotypic divergence along an urbanization gradient\"","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Multivariate statistics; Divergence (linguistics); Multivariate analysis; Urbanization; Geography; Mathematics; Biology; Statistics; Ecology","score_opus":0.05498864000589632,"score_gpt":0.28979764688820386,"score_spread":0.23480900688230755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3189005758","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013855025,0.00003988199,0.1326713,0.001087112,0.0005786016,0.0006544914,0.8504284,0.0006203647,0.000064834414],"genre_scores_gemma":[0.62975496,0.0000015917803,0.063545816,0.000753508,0.00075842696,0.00011307929,0.3050035,0.00004201766,0.000027084254],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984774,0.00008130393,0.00019103006,0.00056283845,0.0003559639,0.00033147342],"domain_scores_gemma":[0.99912816,0.000050301423,0.00007054132,0.0004056391,0.00010174381,0.00024361648],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000028771949,0.00014997408,0.0001254464,0.000036394234,0.00015102171,0.00022336244,0.0012045329,0.00004634049,0.08058231],"category_scores_gemma":[0.00020998389,0.00015627037,0.000029164297,0.0003426491,0.0000058984074,0.0008277916,0.0010131012,0.0001233208,0.0005097499],"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":[0.000536258,0.0008965723,0.0047644246,0.00092527637,0.00041786008,0.0016315833,0.041926198,0.025562475,0.058778096,0.0020947054,0.5366018,0.3258648],"study_design_scores_gemma":[0.0011719147,0.00038116678,0.017255777,0.00027037488,0.000008529444,0.0000056558415,0.00009294352,0.90567887,0.032164592,0.0009726279,0.04118615,0.00081137643],"about_ca_topic_score_codex":0.00022413471,"about_ca_topic_score_gemma":0.000021194855,"teacher_disagreement_score":0.8801164,"about_ca_system_score_codex":0.000055030734,"about_ca_system_score_gemma":0.00004530654,"threshold_uncertainty_score":0.92025816},"labels":[],"label_agreement":null},{"id":"W3198815918","doi":"10.3390/a14090258","title":"A Novel Semi-Supervised Fuzzy C-Means Clustering Algorithm Using Multiple Fuzzification Coefficients","year":2021,"lang":"en","type":"article","venue":"Algorithms","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Foundation for Science and Technology Development","keywords":"Cluster analysis; Fuzzy clustering; Computer science; Artificial intelligence; Data mining; Pattern recognition (psychology); Fuzzy logic; Fuzzy set; Correlation clustering; Mathematics; Algorithm; Machine learning","score_opus":0.05065401274004585,"score_gpt":0.3084842384201754,"score_spread":0.2578302256801296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198815918","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":[0.002140587,0.00031016732,0.99465126,0.00032931266,0.0012064886,0.0004034323,0.00005701091,0.0005075596,0.0003942022],"genre_scores_gemma":[0.024460338,0.000053538053,0.9739863,0.0002532777,0.00035158306,0.000057984067,0.000059720656,0.0000820246,0.00069523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954057,0.00016286282,0.000651175,0.0014344122,0.0011853878,0.0011604741],"domain_scores_gemma":[0.99670076,0.00029046476,0.00017590934,0.0016926539,0.0007370749,0.0004031372],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005540406,0.0004496832,0.00047123837,0.0002993948,0.0005695595,0.0005303819,0.0015422213,0.00020705695,0.000024532226],"category_scores_gemma":[0.00027899977,0.00050118734,0.00018885954,0.0019340146,0.00012512889,0.0010884331,0.0015723538,0.000519705,0.00011886639],"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":[0.000008477387,0.00047809273,0.00007442886,0.00006118785,0.000082373685,0.0003316407,0.0010860354,0.068848975,0.06861692,0.00015077993,0.000043922417,0.86021715],"study_design_scores_gemma":[0.0015048571,0.00005506271,0.00020874498,0.000087144566,0.000013567653,0.0006399539,0.00024413182,0.9853602,0.009431403,0.00017791812,0.0017105112,0.00056649075],"about_ca_topic_score_codex":0.00016182095,"about_ca_topic_score_gemma":0.00002489645,"teacher_disagreement_score":0.91651124,"about_ca_system_score_codex":0.0004333813,"about_ca_system_score_gemma":0.00036379957,"threshold_uncertainty_score":0.999744},"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":"W3205343175","doi":"10.1093/nsr/nwab183","title":"Massive data clustering by multi-scale psychological observations","year":2021,"lang":"en","type":"article","venue":"National Science Review","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":10,"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 Ottawa","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Cluster analysis; Scale (ratio); Psychology; Computer science; Artificial intelligence; Geography; Cartography","score_opus":0.30351777484378367,"score_gpt":0.4854582473962416,"score_spread":0.18194047255245793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205343175","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":[0.00004822161,0.014462912,0.9700185,0.01376061,0.00020795826,0.0002184033,0.00005046773,0.000085173575,0.0011477679],"genre_scores_gemma":[0.0025705183,0.016797211,0.9752948,0.004196888,0.0000652909,0.000059459995,0.00008931349,0.000008056234,0.0009184441],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967153,0.00009276261,0.00029629708,0.0009514572,0.0015652878,0.00037890466],"domain_scores_gemma":[0.9975723,0.0001559618,0.00009161707,0.0010456784,0.0009550931,0.00017932299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017110308,0.000110642584,0.00017364523,0.0000624955,0.00037291212,0.00022683611,0.0034865513,0.000034006644,0.000058845497],"category_scores_gemma":[0.002008619,0.00009673364,0.000036630536,0.0026052592,0.000235615,0.0018581407,0.0024462685,0.000203141,0.0001002076],"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":[0.0000021371818,0.000885917,0.00031397346,0.00073948345,0.000024954385,0.000084127045,0.00011612982,0.0010369956,0.06223418,0.018097503,0.045176525,0.87128806],"study_design_scores_gemma":[0.00040029798,0.000039197967,0.005356292,0.0009873931,0.0000074787945,0.00019279138,0.000013311934,0.8537035,0.0009471293,0.0018845486,0.13600338,0.0004646916],"about_ca_topic_score_codex":0.0000032721528,"about_ca_topic_score_gemma":0.0000069625517,"teacher_disagreement_score":0.8708234,"about_ca_system_score_codex":0.00019759593,"about_ca_system_score_gemma":0.00050865853,"threshold_uncertainty_score":0.6478938},"labels":[],"label_agreement":null},{"id":"W3211395167","doi":"10.1109/access.2021.3126854","title":"KNN-SC: Novel Spectral Clustering Algorithm Using k-Nearest Neighbors","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Institute for Information and Communications Technology Promotion; National Research Foundation of Korea","keywords":"Cluster analysis; Spectral clustering; CURE data clustering algorithm; Computer science; Correlation clustering; k-nearest neighbors algorithm; Pattern recognition (psychology); Nearest-neighbor chain algorithm; Canopy clustering algorithm; Graph; Algorithm; Noise (video); Artificial intelligence; Data mining; Theoretical computer science","score_opus":0.08371092394036551,"score_gpt":0.3714442137006123,"score_spread":0.2877332897602468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211395167","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":[0.020195682,0.000111165136,0.9763848,0.00032167294,0.001750138,0.00015571155,0.000012668714,0.0002697151,0.000798458],"genre_scores_gemma":[0.16891293,0.000043048574,0.82886165,0.00044271722,0.0009124139,0.000023257477,0.000006086439,0.00007342902,0.0007244577],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970606,0.000072401584,0.0003594222,0.0008891533,0.0007248846,0.00089355157],"domain_scores_gemma":[0.99810314,0.00013696849,0.00010997451,0.0011005632,0.0002840685,0.00026525703],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00024503501,0.00027646607,0.00030303854,0.00019244247,0.0003155506,0.0012324356,0.0022926973,0.00010706392,0.00004633653],"category_scores_gemma":[0.00007560486,0.00029778833,0.00011144673,0.0013194657,0.00008586234,0.0022672077,0.0017565773,0.00044323548,0.000045280194],"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":[0.000028496588,0.00062885456,0.0011992268,0.0002115099,0.00020739374,0.0035461022,0.00119172,0.21017812,0.13067588,0.001803252,0.00038917942,0.64994025],"study_design_scores_gemma":[0.00054150977,0.000028571401,0.0012763677,0.00006651792,0.00000566764,0.00037313945,0.000023683322,0.94450283,0.05140375,0.0005530468,0.00083598273,0.00038890901],"about_ca_topic_score_codex":0.00021812826,"about_ca_topic_score_gemma":0.00006782902,"teacher_disagreement_score":0.73432475,"about_ca_system_score_codex":0.0002674706,"about_ca_system_score_gemma":0.00031644764,"threshold_uncertainty_score":0.9999474},"labels":[],"label_agreement":null},{"id":"W4205263674","doi":"10.1007/978-0-387-39940-9_3579","title":"Semi-Supervised Clustering","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Advanced Clustering Algorithms Research","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 Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence","score_opus":0.024568357284607774,"score_gpt":0.2700766950451616,"score_spread":0.2455083377605538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205263674","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005301947,0.0029793333,0.3492713,0.0000692301,0.0015754449,0.00079985015,0.0003962092,0.00030948193,0.64459383],"genre_scores_gemma":[0.00031788636,0.005009428,0.06454829,0.00006646862,0.0014866475,0.00006706257,0.00041931216,0.00018757908,0.92789733],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99558574,0.00008290058,0.0010819501,0.0011643693,0.0014123503,0.00067267666],"domain_scores_gemma":[0.99558073,0.0002509112,0.00053551194,0.0029964172,0.0002995551,0.00033685396],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063011865,0.0006494812,0.0009909682,0.0005160358,0.000119962395,0.0001298553,0.0026671074,0.00034610069,0.000061033617],"category_scores_gemma":[0.00009451006,0.00065655675,0.00021243139,0.00016722931,0.00010662423,0.00082272774,0.0016263511,0.0007853728,0.000283637],"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":[0.00010793555,0.00028047638,0.000024795394,0.006785666,0.0006800254,0.0027974038,0.0016927184,0.009766266,0.00123352,0.18812153,0.032333244,0.7561764],"study_design_scores_gemma":[0.0007019339,0.00023893973,0.000008269419,0.0024578753,0.000036372534,0.0001915731,0.000024989411,0.11777089,0.000051061117,0.0009301784,0.8764175,0.0011704038],"about_ca_topic_score_codex":0.00009709379,"about_ca_topic_score_gemma":0.000020879845,"teacher_disagreement_score":0.84408426,"about_ca_system_score_codex":0.00020216953,"about_ca_system_score_gemma":0.00030004227,"threshold_uncertainty_score":0.99958855},"labels":[],"label_agreement":null},{"id":"W4205661532","doi":"10.1109/ijcnn.2006.1716671","title":"Refining Spherical K-Means for Clustering Documents","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Convexity; Cluster analysis; Mathematical optimization; Constraint (computer-aided design); Set (abstract data type); Maximization; Mathematics; Algorithm; Computer science; Function (biology); Linear programming; Optimization problem; Artificial intelligence","score_opus":0.06047978020347221,"score_gpt":0.318466311927053,"score_spread":0.25798653172358077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205661532","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":[0.022102125,0.000030997984,0.9342531,0.015306575,0.002779726,0.00061980734,0.000013699482,0.000500158,0.024393793],"genre_scores_gemma":[0.8932073,0.00001791967,0.09591331,0.0011631261,0.002349334,0.00025254153,0.000010980603,0.000049041475,0.0070364345],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973721,0.000023309229,0.0004733776,0.00062345533,0.0007923574,0.00071541814],"domain_scores_gemma":[0.9987541,0.00016419617,0.0002432478,0.00025625108,0.0004868872,0.00009535819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047101168,0.0002860482,0.00024043336,0.0000855447,0.00034446863,0.00071349146,0.0017870131,0.00007565182,0.000027584043],"category_scores_gemma":[0.000065490705,0.00022095146,0.000125975,0.00032066068,0.000109603425,0.0006908954,0.0004235298,0.0004111863,0.000048112037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005448988,0.000302798,0.0011586113,0.00008817424,0.00016405304,0.000049034148,0.00046585884,0.48981214,0.018080447,0.2769196,0.06153065,0.15088372],"study_design_scores_gemma":[0.0005521818,0.00019856267,0.0006032663,0.000119710494,0.0000049675623,0.000054624736,0.000019965308,0.9748298,0.00088251807,0.014516045,0.00793141,0.0002869593],"about_ca_topic_score_codex":0.00007648235,"about_ca_topic_score_gemma":0.000021169271,"teacher_disagreement_score":0.8711052,"about_ca_system_score_codex":0.00018250955,"about_ca_system_score_gemma":0.000043242737,"threshold_uncertainty_score":0.9010139},"labels":[],"label_agreement":null},{"id":"W4206148502","doi":"10.36227/techrxiv.16926754","title":"Unified Embedding and Clustering","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Cluster analysis; Embedding; Computer science; Correlation clustering; Manifold (fluid mechanics); Clustering high-dimensional data; CURE data clustering algorithm; Space (punctuation); Artificial intelligence; Mathematics; Data mining; Algorithm; Pattern recognition (psychology); Engineering","score_opus":0.0380694894070643,"score_gpt":0.3374502951707269,"score_spread":0.2993808057636626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206148502","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":[0.0055226535,0.00052537717,0.988919,0.00049740454,0.0005990681,0.00016516334,8.074352e-7,0.00034928956,0.003421221],"genre_scores_gemma":[0.15364723,0.00017255922,0.84407693,0.00010273138,0.0000748968,0.000031726548,0.0000055093496,0.000024185336,0.0018642237],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793047,0.00010986227,0.00027358744,0.00091306726,0.00037256506,0.00040043538],"domain_scores_gemma":[0.99845815,0.000115584444,0.000080099635,0.0010929778,0.00012954614,0.00012364384],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00040063864,0.0002337109,0.0003142501,0.00015477062,0.00012438979,0.0010218117,0.0010967215,0.0001777874,0.00002160282],"category_scores_gemma":[0.0000869284,0.00023755262,0.000058133915,0.00019534404,0.000045959416,0.0003263822,0.01472687,0.00067950547,0.000007162973],"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":[0.0000047535027,0.000056480952,0.00009887358,0.00088219065,0.0001257206,0.00052755885,0.0027369969,0.14372037,0.0014813463,0.0040523917,0.00010364112,0.84620965],"study_design_scores_gemma":[0.00012153347,0.000011843325,0.00023496238,0.00015536646,0.000002381182,0.00005171988,0.0001276867,0.9966022,0.0005199823,0.0016415195,0.00024640193,0.00028443738],"about_ca_topic_score_codex":0.00007527049,"about_ca_topic_score_gemma":0.000016036944,"teacher_disagreement_score":0.8528818,"about_ca_system_score_codex":0.00009146264,"about_ca_system_score_gemma":0.00014158754,"threshold_uncertainty_score":0.99324185},"labels":[],"label_agreement":null},{"id":"W4210265465","doi":"10.36227/techrxiv.16926754.v1","title":"Unified Embedding and Clustering","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Cluster analysis; Embedding; Computer science; Correlation clustering; Clustering high-dimensional data; CURE data clustering algorithm; Manifold (fluid mechanics); Artificial intelligence; Space (punctuation); Data mining; Mathematics; Algorithm; Engineering","score_opus":0.0380694894070643,"score_gpt":0.3374502951707269,"score_spread":0.2993808057636626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210265465","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":[0.0055226535,0.00052537717,0.988919,0.00049740454,0.0005990681,0.00016516334,8.074352e-7,0.00034928956,0.003421221],"genre_scores_gemma":[0.15364723,0.00017255922,0.84407693,0.00010273138,0.0000748968,0.000031726548,0.0000055093496,0.000024185336,0.0018642237],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793047,0.00010986227,0.00027358744,0.00091306726,0.00037256506,0.00040043538],"domain_scores_gemma":[0.99845815,0.000115584444,0.000080099635,0.0010929778,0.00012954614,0.00012364384],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00040063864,0.0002337109,0.0003142501,0.00015477062,0.00012438979,0.0010218117,0.0010967215,0.0001777874,0.00002160282],"category_scores_gemma":[0.0000869284,0.00023755262,0.000058133915,0.00019534404,0.000045959416,0.0003263822,0.01472687,0.00067950547,0.000007162973],"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":[0.0000047535027,0.000056480952,0.00009887358,0.00088219065,0.0001257206,0.00052755885,0.0027369969,0.14372037,0.0014813463,0.0040523917,0.00010364112,0.84620965],"study_design_scores_gemma":[0.00012153347,0.000011843325,0.00023496238,0.00015536646,0.000002381182,0.00005171988,0.0001276867,0.9966022,0.0005199823,0.0016415195,0.00024640193,0.00028443738],"about_ca_topic_score_codex":0.00007527049,"about_ca_topic_score_gemma":0.000016036944,"teacher_disagreement_score":0.8528818,"about_ca_system_score_codex":0.00009146264,"about_ca_system_score_gemma":0.00014158754,"threshold_uncertainty_score":0.99324185},"labels":[],"label_agreement":null},{"id":"W4210362242","doi":"10.1287/ijoc.2021.1137","title":"Efficient Algebraic Multigrid Methods for Multilevel Overlapping Coclustering of User-Item Relationships","year":2022,"lang":"en","type":"article","venue":"INFORMS journal on computing","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Toronto Metropolitan University","funders":"","keywords":"Bipartite graph; Computer science; Theoretical computer science; Scalability; Feature (linguistics); Graph; Algorithm","score_opus":0.07169727211548858,"score_gpt":0.38226519267080344,"score_spread":0.31056792055531485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210362242","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":[0.12505499,0.00006226478,0.8731662,0.00013887578,0.0009916142,0.00035863405,0.0000044595754,0.00009621667,0.00012673401],"genre_scores_gemma":[0.43682098,0.0000015244896,0.56290084,0.000088722394,0.00009717385,0.000013278612,0.0000013206794,0.000018896462,0.000057260288],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99698293,0.00029996524,0.0009795771,0.00033740397,0.0007657872,0.0006343254],"domain_scores_gemma":[0.99501675,0.0032644991,0.0007592206,0.00045471665,0.00031030588,0.00019453009],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004727277,0.0002206869,0.00035891833,0.00059287937,0.0017205885,0.00021139039,0.0013870705,0.000052988205,0.000008047709],"category_scores_gemma":[0.0013391932,0.00020796429,0.00021584699,0.00065458985,0.00004545843,0.00032060058,0.0015417456,0.0012594062,0.0000033484253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003093441,0.000045479086,0.00011117658,0.00003685425,0.000028641969,0.000007783833,0.0016283782,0.71011525,0.0009024041,0.0020929559,0.00001726054,0.2849829],"study_design_scores_gemma":[0.0011175245,0.00031052076,0.0023308655,0.00012395387,0.000004109587,0.00032832872,0.00036953037,0.9909808,0.00072842586,0.00052000105,0.002951341,0.00023462127],"about_ca_topic_score_codex":0.0000042992656,"about_ca_topic_score_gemma":2.3084692e-7,"teacher_disagreement_score":0.311766,"about_ca_system_score_codex":0.00048545923,"about_ca_system_score_gemma":0.00017929416,"threshold_uncertainty_score":0.999579},"labels":[],"label_agreement":null},{"id":"W4211047464","doi":"10.1007/978-1-4471-7452-3_9","title":"Clustering I: Basic Clustering Models and Algorithms","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Clustering Algorithms Research","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":"Concordia University","funders":"","keywords":"Cluster analysis; Correlation clustering; Fuzzy clustering; Learning vector quantization; Artificial intelligence; Computer science; CURE data clustering algorithm; Pattern recognition (psychology); Canopy clustering algorithm; Conceptual clustering; Competitive learning; Unsupervised learning; Machine learning; Determining the number of clusters in a data set; Single-linkage clustering; Consensus clustering; Artificial neural network; Data mining","score_opus":0.05182116940461246,"score_gpt":0.2868308259429649,"score_spread":0.23500965653835243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211047464","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014849771,0.0004937653,0.64652,0.0002103583,0.0004756137,0.00040980696,0.000008754771,0.0003581592,0.35152203],"genre_scores_gemma":[0.0003394828,0.00068990246,0.29192445,0.00026599932,0.00023944935,0.000018210289,0.0000087258695,0.00015435844,0.70635945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959906,0.00003199893,0.0005808521,0.0016147562,0.0009439701,0.0008378771],"domain_scores_gemma":[0.99723375,0.00023423578,0.00021459437,0.0017889886,0.00018678485,0.00034162],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042139157,0.00073202903,0.00079068873,0.000479193,0.0001936181,0.0005212736,0.001749208,0.0004651045,0.00010741607],"category_scores_gemma":[0.000016299686,0.0007247358,0.00016909614,0.00009000787,0.00013725957,0.0012241874,0.005009198,0.0009392601,0.00034470562],"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":[0.00002105653,0.000019591753,0.0000012873456,0.00058373046,0.0001698479,0.0002636516,0.00044350539,0.038477056,0.00008202938,0.13548848,0.00051681563,0.82393295],"study_design_scores_gemma":[0.0004349066,0.0001226627,0.0000029272849,0.000308823,0.000010487931,0.00021209991,0.000008165553,0.9563927,0.000025381929,0.022666514,0.018993456,0.0008218768],"about_ca_topic_score_codex":0.00003200927,"about_ca_topic_score_gemma":0.00003748354,"teacher_disagreement_score":0.91791564,"about_ca_system_score_codex":0.00025226382,"about_ca_system_score_gemma":0.00018469346,"threshold_uncertainty_score":0.99952036},"labels":[],"label_agreement":null},{"id":"W4211218449","doi":"10.1007/978-1-4471-7452-3_10","title":"Clustering II: Topics in Clustering","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Clustering Algorithms Research","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":"Concordia University","funders":"","keywords":"Cluster analysis; Computer science; Correlation clustering; CURE data clustering algorithm; Single-linkage clustering; Fuzzy clustering; Consensus clustering; Hierarchical clustering; Data mining; Brown clustering; Artificial intelligence","score_opus":0.03726779996790174,"score_gpt":0.2929327815631323,"score_spread":0.25566498159523054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211218449","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006709102,0.00013797649,0.49545535,0.00044790396,0.0006510215,0.0003263244,0.000002293671,0.0002017266,0.50277066],"genre_scores_gemma":[0.00023498519,0.00013615286,0.12925945,0.00023421527,0.00024494296,0.000011516189,0.0000050044873,0.000074437776,0.8697993],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970039,0.000021124099,0.00055947516,0.0010340866,0.0006812523,0.0007001289],"domain_scores_gemma":[0.9979305,0.000096481024,0.00014536148,0.0015816357,0.00009645873,0.00014951972],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029593334,0.00047736565,0.0005698577,0.0005355948,0.00011377196,0.00019064372,0.0020577912,0.00040513815,0.00021615089],"category_scores_gemma":[0.000026562513,0.000492192,0.0001430311,0.000113662914,0.000054715823,0.00051486207,0.0053945365,0.0009739635,0.00046756817],"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":[0.000028225635,0.00005224739,0.000027296834,0.0005982897,0.0000857219,0.0006811578,0.0009569875,0.020288428,0.000095798365,0.2233231,0.0008390323,0.7530237],"study_design_scores_gemma":[0.0006689749,0.00021094197,0.000047682,0.00058686984,0.000004319452,0.00009474275,0.00000884078,0.69932693,0.000057972793,0.010142433,0.28780228,0.0010480148],"about_ca_topic_score_codex":0.000036843376,"about_ca_topic_score_gemma":0.00028964027,"teacher_disagreement_score":0.7519757,"about_ca_system_score_codex":0.0004458612,"about_ca_system_score_gemma":0.00019535344,"threshold_uncertainty_score":0.999753},"labels":[],"label_agreement":null},{"id":"W4212923685","doi":"10.2139/ssrn.4038110","title":"A Process Convolution Model for Crash Count Data on a Network","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","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":"McGill University; HEC Montréal","funders":"","keywords":"Count data; Crash; Computer science; Process (computing); Statistics; Convolution (computer science); Econometrics; Mathematics; Artificial intelligence; Programming language; Artificial neural network","score_opus":0.04158118083929049,"score_gpt":0.3369409990319969,"score_spread":0.29535981819270646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212923685","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":[0.0018330087,0.00062186475,0.9954491,0.0014174596,0.00023163621,0.00029283503,0.00001894957,0.000070455324,0.000064666376],"genre_scores_gemma":[0.9737336,0.00044052448,0.022245143,0.00047778696,0.0005984913,0.0001992434,0.000034917604,0.00004778898,0.0022224945],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961031,0.00009155185,0.00022274596,0.0004593236,0.00072371826,0.0023995673],"domain_scores_gemma":[0.99885595,0.00009067089,0.0001416982,0.0006928909,0.00013276651,0.00008600878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030810093,0.00012930905,0.00014377561,0.00009240143,0.00097057014,0.00011232556,0.0028220636,0.00002758137,0.000003817139],"category_scores_gemma":[0.00007645389,0.00012810493,0.00004749388,0.0003840861,0.000025351217,0.0005448876,0.00082969863,0.0018366898,0.000004538088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000964788,0.00010873458,0.000015670603,0.00000875065,0.000052893593,0.000004354019,0.00016536377,0.8334133,0.0000252818,0.13011459,0.00088610715,0.035108447],"study_design_scores_gemma":[0.0005551235,0.00041005146,0.000004085367,0.0000058435603,0.000003882947,0.0002381928,0.000096974174,0.723074,0.0000035869546,0.27415386,0.0013470771,0.000107316795],"about_ca_topic_score_codex":0.000005144965,"about_ca_topic_score_gemma":0.00005532792,"teacher_disagreement_score":0.97320396,"about_ca_system_score_codex":0.0017240165,"about_ca_system_score_gemma":0.0047271587,"threshold_uncertainty_score":0.8385777},"labels":[],"label_agreement":null},{"id":"W4220790596","doi":"10.1109/bigcomp54360.2022.00017","title":"The Border K-Means Clustering Algorithm for One Dimensional Data","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Cluster analysis; Computer science; Algorithm; Canopy clustering algorithm; CURE data clustering algorithm; Focus (optics); Data mining; Flexibility (engineering); Data stream clustering; Centroid; Cluster (spacecraft); Algorithm design; Correlation clustering; Artificial intelligence; Mathematics","score_opus":0.0641923449340145,"score_gpt":0.3551603780778739,"score_spread":0.2909680331438594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220790596","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":[0.00002015017,0.00013661069,0.9936944,0.0046055145,0.00053553993,0.00037042453,0.000067835506,0.00016612181,0.00040336794],"genre_scores_gemma":[0.00065521226,0.000011726899,0.9898779,0.000499895,0.00013112875,0.00023207258,0.000045903453,0.000022723627,0.00852348],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978507,0.00008569745,0.0002053335,0.00059519755,0.0007463087,0.00051675166],"domain_scores_gemma":[0.99736655,0.00062249566,0.000049131926,0.0017790749,0.00009364177,0.000089110035],"candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0010559112,0.00011300414,0.000111087575,0.000055800017,0.001592226,0.00020753333,0.003965507,0.00001724854,0.00006790701],"category_scores_gemma":[0.000077591,0.00008930976,0.000037396538,0.00035356477,0.000057781508,0.00044272054,0.010457776,0.00025282646,0.000013490293],"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":[0.000008217275,0.00005551193,0.0000013101399,0.0000041391254,0.000026929269,0.000006455598,0.00006818361,0.011281365,0.00009997058,0.0022019139,0.0033925697,0.9828534],"study_design_scores_gemma":[0.00029648404,0.00008392861,0.000017787122,0.0000018206396,0.0000016558696,0.000025311212,0.000054251486,0.8387662,0.000052482068,0.0012285465,0.15935877,0.000112761234],"about_ca_topic_score_codex":0.000037171267,"about_ca_topic_score_gemma":0.00002815323,"teacher_disagreement_score":0.9827407,"about_ca_system_score_codex":0.00010122676,"about_ca_system_score_gemma":0.00012151703,"threshold_uncertainty_score":0.9997076},"labels":[],"label_agreement":null},{"id":"W4230355264","doi":"10.1007/978-1-4939-7131-2_100724","title":"Network Dataset","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.04994951798517892,"score_gpt":0.309039389115118,"score_spread":0.2590898711299391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230355264","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.5740982e-8,0.000105958294,0.5173813,0.00017900475,0.00033764003,0.00009992375,0.000103610655,0.00016159896,0.48163092],"genre_scores_gemma":[8.373138e-7,0.000041787505,0.21991833,0.00058961054,0.00089006656,0.000004623558,0.00028472886,0.000031667503,0.77823836],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981784,0.000011103218,0.00020921568,0.00066540926,0.0004981619,0.00043767816],"domain_scores_gemma":[0.9977913,0.00008669913,0.00008247063,0.0017933225,0.00009674115,0.0001494849],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00021556778,0.00025020642,0.00023269714,0.00008112779,0.000110599896,0.00016176008,0.002139173,0.00018539475,0.0019507285],"category_scores_gemma":[0.000012331091,0.00022539089,0.0000482943,0.000049039616,0.000119337674,0.00025846384,0.0023070714,0.00035494188,0.0061204284],"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":[0.0000018869254,0.000002579741,8.250027e-8,0.000009643613,0.00001943913,0.00006638512,0.000010846968,0.00005879309,5.966759e-7,0.22997884,0.73827887,0.03157202],"study_design_scores_gemma":[0.000057383608,0.00005895423,4.947286e-7,0.000036441503,0.0000021973067,0.000023767081,2.1759887e-7,0.007309661,0.0000043276277,0.14745672,0.84481484,0.00023502312],"about_ca_topic_score_codex":0.000004475462,"about_ca_topic_score_gemma":0.000008782833,"teacher_disagreement_score":0.297463,"about_ca_system_score_codex":0.00006643839,"about_ca_system_score_gemma":0.000083344086,"threshold_uncertainty_score":0.9989616},"labels":[],"label_agreement":null},{"id":"W4231076572","doi":"10.1007/978-0-387-39940-9_2216","title":"Clustering Index","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","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":"University of Waterloo","funders":"","keywords":"Cluster analysis; Index (typography); Computer science; Artificial intelligence; World Wide Web","score_opus":0.021481385931594668,"score_gpt":0.27206912690312873,"score_spread":0.2505877409715341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231076572","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000013271166,0.0018910182,0.46515048,0.000042205884,0.0011844273,0.0005055045,0.00019989893,0.00019307632,0.53083205],"genre_scores_gemma":[0.0006041509,0.0040620137,0.049004287,0.00004898315,0.0012995955,0.00004989852,0.0002289946,0.00014781811,0.94455427],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99603724,0.00006307893,0.0009591337,0.0010156522,0.0013377671,0.0005871238],"domain_scores_gemma":[0.9960061,0.00020213696,0.0005940878,0.00265546,0.00025901615,0.00028322992],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005649916,0.0005590327,0.00085439533,0.0005430186,0.00009947266,0.00011310146,0.0024065024,0.00032474395,0.00004130666],"category_scores_gemma":[0.00008220298,0.0005659894,0.00017002948,0.00014933769,0.00010407185,0.00074185565,0.0015781145,0.0007763022,0.00021875638],"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":[0.0000668008,0.0001574015,0.000043425032,0.0033402895,0.00039531456,0.0017464014,0.00070503826,0.007197471,0.00019216251,0.16404687,0.017724268,0.8043845],"study_design_scores_gemma":[0.00050541136,0.00018143772,0.000025770474,0.0017897746,0.000021455566,0.0001689996,0.000014818258,0.074799016,0.000014542761,0.001288807,0.92025363,0.00093634473],"about_ca_topic_score_codex":0.00010181321,"about_ca_topic_score_gemma":0.00002465029,"teacher_disagreement_score":0.90252936,"about_ca_system_score_codex":0.00018465825,"about_ca_system_score_gemma":0.00028034335,"threshold_uncertainty_score":0.99967915},"labels":[],"label_agreement":null},{"id":"W4231833091","doi":"10.1109/ijcnn.2006.1716663","title":"Fuzzy Clustering of Open-Source Software Quality Data: A Case Study of Mozilla","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":4,"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":"Mozilla Foundation","keywords":"Computer science; Data mining; Software quality; Fuzzy logic; Software; Cluster analysis; Software metric; Ranking (information retrieval); Artificial intelligence; Software development; Operating system","score_opus":0.16967533549687067,"score_gpt":0.38844686424841907,"score_spread":0.2187715287515484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231833091","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":[0.8832261,0.000029868337,0.1105867,0.0010974853,0.0007831111,0.0011162163,0.000044624514,0.00016667717,0.0029492395],"genre_scores_gemma":[0.98699075,0.000009022757,0.011944523,0.000096112875,0.00034834113,0.00004334859,0.0000072412918,0.000024676836,0.0005360004],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967443,0.00009941207,0.00091070076,0.0007528268,0.0010587013,0.00043406474],"domain_scores_gemma":[0.99720347,0.00027311806,0.00070591987,0.00085153634,0.00088803045,0.00007790699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012432397,0.00027521775,0.00044051267,0.00014296653,0.00021042289,0.0004444922,0.0052120415,0.000060340608,0.000010515954],"category_scores_gemma":[0.00014320573,0.00021371047,0.00006279637,0.00053932605,0.00016587172,0.0011345367,0.0036927538,0.00041851684,0.000005236235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001036784,0.003464135,0.012248135,0.00034546747,0.00052045146,0.00085108343,0.0054002968,0.74292797,0.0078216875,0.041732613,0.012509981,0.17114139],"study_design_scores_gemma":[0.0017248936,0.0007507158,0.003165535,0.0002640251,0.000019456049,0.0009646516,0.0013294447,0.9844977,0.0007201344,0.0058248895,0.00026948043,0.00046904833],"about_ca_topic_score_codex":0.003370122,"about_ca_topic_score_gemma":0.00038196638,"teacher_disagreement_score":0.24156974,"about_ca_system_score_codex":0.00007876809,"about_ca_system_score_gemma":0.00007187416,"threshold_uncertainty_score":0.9685357},"labels":[],"label_agreement":null},{"id":"W4232476000","doi":"10.1007/978-1-4614-6170-8_100950","title":"Clustering Objective Function","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence","score_opus":0.02291046649971108,"score_gpt":0.2636089981528809,"score_spread":0.24069853165316984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232476000","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.18276304e-7,0.00004302777,0.5420766,0.000069853704,0.00042042378,0.000118935066,8.655632e-7,0.0002863017,0.4569839],"genre_scores_gemma":[0.00054268463,0.00003180122,0.06377174,0.00023787442,0.0003710704,0.00001514867,0.0000048287434,0.000057608042,0.9349672],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980318,0.00001345548,0.00025321596,0.00076935696,0.0005659645,0.0003662232],"domain_scores_gemma":[0.99840796,0.00012260795,0.00012302902,0.00102154,0.00018578282,0.00013909698],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002210004,0.0003225716,0.00030753794,0.00025905267,0.00013030748,0.00016843487,0.00096576,0.0002544249,0.00021714444],"category_scores_gemma":[0.000023772924,0.00030826678,0.000123171,0.00005329959,0.00006010514,0.00024130555,0.0012077899,0.0005407555,0.0012382796],"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":[0.000012319052,0.0000044903713,3.5122403e-7,0.000049528782,0.000063637446,0.000025793435,0.000063768144,0.0008753808,0.00004887431,0.42016035,0.0011929693,0.57750255],"study_design_scores_gemma":[0.00046439684,0.0005067765,0.00002748208,0.00021378962,0.000018243436,0.00008969961,0.0000059121003,0.3658348,0.00015340083,0.11452501,0.517067,0.0010934623],"about_ca_topic_score_codex":0.000009760911,"about_ca_topic_score_gemma":0.0000192613,"teacher_disagreement_score":0.5764091,"about_ca_system_score_codex":0.00021973075,"about_ca_system_score_gemma":0.0000721154,"threshold_uncertainty_score":0.99993694},"labels":[],"label_agreement":null},{"id":"W4234033320","doi":"10.1145/564410.564412","title":"Document clustering with committees","year":2002,"lang":"en","type":"article","venue":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Document clustering; Similarity (geometry); Set (abstract data type); Information retrieval; Task (project management); Data mining; Fuzzy clustering; Space (punctuation); Group (periodic table); Cluster (spacecraft); Artificial intelligence; Image (mathematics)","score_opus":0.06517323618068653,"score_gpt":0.3218864163618488,"score_spread":0.25671318018116224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234033320","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":[0.86046886,0.00012933699,0.030018793,0.024288986,0.0010157241,0.0031853528,0.000071686896,0.00035060785,0.080470614],"genre_scores_gemma":[0.9693052,0.00016434875,0.028963657,0.00018109831,0.000034151686,0.00006906697,0.000005796364,0.000010228593,0.0012664058],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961586,0.0000285128,0.0006155774,0.0003354813,0.0023022182,0.000559585],"domain_scores_gemma":[0.99703014,0.00027910183,0.00024265591,0.0002723508,0.0019951484,0.00018060884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011490377,0.00022013162,0.00021508486,0.0007302774,0.00028686662,0.0007046328,0.0026224798,0.00008714126,0.000073838004],"category_scores_gemma":[0.0010961256,0.00015781159,0.00002870219,0.00086165254,0.00026893656,0.0031469916,0.0020758486,0.00065595494,0.000059529793],"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":[0.0040006903,0.0018787187,0.04467971,0.0017148987,0.0005787025,0.000037123045,0.08228683,0.0024649494,0.0029202101,0.4443112,0.01290504,0.40222192],"study_design_scores_gemma":[0.0138755515,0.006699432,0.088372596,0.005158703,0.000010708253,0.00031118438,0.01872851,0.57903206,0.13862889,0.049451843,0.09639509,0.00333544],"about_ca_topic_score_codex":0.000024767603,"about_ca_topic_score_gemma":0.000006565279,"teacher_disagreement_score":0.5765671,"about_ca_system_score_codex":0.0003035808,"about_ca_system_score_gemma":0.00014745498,"threshold_uncertainty_score":0.679479},"labels":[],"label_agreement":null},{"id":"W4235761050","doi":"10.1007/978-1-4614-6170-8_100658","title":"Cluster Analysis","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Cluster (spacecraft); Computer science; Operating system","score_opus":0.022553855722679404,"score_gpt":0.2845981466991351,"score_spread":0.26204429097645565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235761050","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.765838e-8,0.000035933004,0.5397511,0.00037362808,0.00008871929,0.000072434064,0.0000016041108,0.00017005373,0.45950642],"genre_scores_gemma":[0.00013562101,0.00002800106,0.13424549,0.00057571655,0.00014124246,0.0000064739147,0.0000096133335,0.000030901563,0.864827],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99779403,0.000022490702,0.0003048813,0.0008031862,0.00070518407,0.0003702117],"domain_scores_gemma":[0.99757254,0.00017774507,0.00012329407,0.0017753185,0.00016969361,0.000181424],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002819967,0.00030900983,0.00050163915,0.00071236066,0.00008100526,0.00019733232,0.001794327,0.0002476946,0.0006466793],"category_scores_gemma":[0.00002165201,0.0002714932,0.000359125,0.00020261543,0.00006857225,0.00014049008,0.0013055828,0.00041969898,0.0016113285],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029097346,0.000005360813,0.0000025508857,0.000025205787,0.000781327,0.00003472373,0.00004033589,0.0019899567,0.000002594816,0.80515116,0.00664677,0.18531707],"study_design_scores_gemma":[0.00015554279,0.000056437068,0.000011953022,0.000019934609,0.00011845239,0.0000111299605,4.508112e-7,0.3228227,0.000018353318,0.035817362,0.64044,0.00052773213],"about_ca_topic_score_codex":0.000009929195,"about_ca_topic_score_gemma":0.000026370664,"teacher_disagreement_score":0.76933384,"about_ca_system_score_codex":0.00010446561,"about_ca_system_score_gemma":0.000050809776,"threshold_uncertainty_score":0.9999737},"labels":[],"label_agreement":null},{"id":"W4236921545","doi":"10.1109/ijcnn.2006.1716710","title":"PARTCAT: A Subspace Clustering Algorithm for High Dimensional Categorical Data","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Subspace topology; Dimension (graph theory); Data mining; Similarity (geometry); Algorithm; Clustering high-dimensional data; Artificial neural network; Cluster (spacecraft); Artificial intelligence; Pattern recognition (psychology); Mathematics; Machine learning","score_opus":0.08700548172302576,"score_gpt":0.3200420799469654,"score_spread":0.23303659822393963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236921545","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":[0.0073307464,0.00004794984,0.96847945,0.018740296,0.002694737,0.00081398664,0.000087559194,0.00036375478,0.0014415061],"genre_scores_gemma":[0.88534874,0.000025162153,0.10774924,0.0007499927,0.0033028265,0.00020598012,0.00012379423,0.000052551186,0.0024417283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644053,0.000035674446,0.0005390928,0.001045252,0.0010900458,0.0008493939],"domain_scores_gemma":[0.9979443,0.0002657383,0.00028706994,0.0006574048,0.000706267,0.00013923302],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007108852,0.00037339143,0.00032135847,0.00013084877,0.00042036356,0.0006787482,0.0035965487,0.00010504021,0.000023259312],"category_scores_gemma":[0.00007272784,0.00028466334,0.000093789495,0.00040797298,0.00016870102,0.0009756375,0.0013278272,0.0005292122,0.000053766365],"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":[0.00036278623,0.000545853,0.00018976117,0.00006492181,0.00023009411,0.00008751153,0.000254928,0.16231738,0.004513971,0.3456495,0.1495404,0.33624288],"study_design_scores_gemma":[0.00058951654,0.00015744794,0.00053537183,0.000055928736,0.000009000386,0.000122053774,0.0000105483105,0.9707219,0.0005703593,0.024962252,0.0019371912,0.00032840198],"about_ca_topic_score_codex":0.00017037982,"about_ca_topic_score_gemma":0.000036947797,"teacher_disagreement_score":0.87801796,"about_ca_system_score_codex":0.00016951462,"about_ca_system_score_gemma":0.00009322597,"threshold_uncertainty_score":0.99996054},"labels":[],"label_agreement":null},{"id":"W4237407686","doi":"10.1007/3-540-36175-8_8","title":"Automatic Extraction of Clusters from Hierarchical Clustering Representations","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":95,"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":"Computer science; Hierarchical clustering; Hierarchical clustering of networks; Cluster analysis; Single-linkage clustering; Reachability; Brown clustering; Data mining; Dendrogram; Complete-linkage clustering; Correlation clustering; Set (abstract data type); Representation (politics); Cluster (spacecraft); Canopy clustering algorithm; Artificial intelligence; Theoretical computer science","score_opus":0.026161983350778222,"score_gpt":0.31537102485687596,"score_spread":0.2892090415060977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237407686","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":[0.0002858869,0.00018003954,0.9952002,0.00066721754,0.0014687295,0.00043856868,0.00001029075,0.00016143819,0.0015875848],"genre_scores_gemma":[0.038610235,0.00004466335,0.96040446,0.0003730589,0.00021354797,0.000017240827,0.000008433371,0.000046218345,0.0002821273],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99533343,0.000100465535,0.00081314874,0.0015728527,0.001505216,0.00067487964],"domain_scores_gemma":[0.99593055,0.001304684,0.00041512767,0.0018676665,0.00026125502,0.0002207232],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007286563,0.00045602204,0.0005996617,0.0010530507,0.00023224857,0.00032427922,0.0028116445,0.0003020854,0.000052031854],"category_scores_gemma":[0.00026763455,0.00046063281,0.0001534375,0.0007846955,0.000818199,0.0008884198,0.0016344396,0.0011224748,0.000024497025],"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":[0.0000064667825,0.000039292165,0.000020723515,0.000065385626,0.000022074533,0.000096228534,0.0008742849,0.16849391,0.00084836944,0.0012244217,0.000012112645,0.8282967],"study_design_scores_gemma":[0.00028401692,0.000099099736,0.0001644526,0.0003773059,0.000006783099,0.000077159566,5.24834e-7,0.92206126,0.0016567917,0.0746761,0.00019305521,0.0004034753],"about_ca_topic_score_codex":0.000082394414,"about_ca_topic_score_gemma":0.000080845355,"teacher_disagreement_score":0.82789326,"about_ca_system_score_codex":0.0004660099,"about_ca_system_score_gemma":0.00040744952,"threshold_uncertainty_score":0.9997845},"labels":[],"label_agreement":null},{"id":"W4238474289","doi":"10.7287/peerj.preprints.1693","title":"A comparison of clustering methods for biogeography with fossil datasets","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Advanced Clustering Algorithms Research","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":"Royal Ontario Museum","funders":"","keywords":"Cluster analysis; Hierarchical clustering; Euclidean distance; Set (abstract data type); Complete-linkage clustering; Computer science; Similarity (geometry); Data mining; Cluster (spacecraft); Range (aeronautics); Single-linkage clustering; Complete linkage; Data set; Mathematics; Statistics; Fuzzy clustering; Artificial intelligence; CURE data clustering algorithm; Biology; Engineering","score_opus":0.08915802525528156,"score_gpt":0.4734502304649979,"score_spread":0.38429220520971635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238474289","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":[0.00006155218,0.0005016388,0.9967587,0.0003610515,0.0003552242,0.0009148954,0.00035967428,0.00021430498,0.0004729692],"genre_scores_gemma":[0.0073873317,0.000018347077,0.9920472,0.000019704934,0.00006119064,0.00027989713,0.00005499706,0.000032810465,0.00009852275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99717605,0.00017968459,0.0005592757,0.0010713796,0.00043531597,0.00057826506],"domain_scores_gemma":[0.99612844,0.00073768164,0.0004013435,0.00224723,0.00031305192,0.00017226647],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009087656,0.00036589275,0.00076071755,0.00046677003,0.000105776206,0.0001719957,0.002944149,0.00020042935,0.000007912459],"category_scores_gemma":[0.00010655124,0.00024883726,0.000181054,0.0003780433,0.00019000033,0.0002826406,0.005587041,0.00036188026,0.0000026935231],"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":[0.00012513554,0.00018014685,0.0005402131,0.0010786364,0.00029555045,0.000004921713,0.00038156225,0.0034405682,0.0022372347,0.0023318934,0.0009149746,0.9884692],"study_design_scores_gemma":[0.0011333149,0.00056729617,0.00024837375,0.0006930047,0.000031459484,0.0000139724625,0.000043151038,0.934174,0.033874646,0.014353983,0.014107969,0.0007588068],"about_ca_topic_score_codex":0.000053125816,"about_ca_topic_score_gemma":0.000034669232,"teacher_disagreement_score":0.98771036,"about_ca_system_score_codex":0.000062048835,"about_ca_system_score_gemma":0.0001803414,"threshold_uncertainty_score":0.99999636},"labels":[],"label_agreement":null},{"id":"W4239679132","doi":"10.4018/9781591405573.ch031","title":"Clustering Analysis and Algorithms","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Cluster analysis; Computer science; Single-linkage clustering; Cluster (spacecraft); Data mining; Similarity (geometry); Set (abstract data type); Pattern recognition (psychology); Artificial intelligence; Consensus clustering; Data set; Clustering high-dimensional data; Correlation clustering; CURE data clustering algorithm; Image (mathematics)","score_opus":0.03173086598057796,"score_gpt":0.2837229048107496,"score_spread":0.2519920388301716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239679132","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":[0.0000037346824,0.00027556386,0.503048,0.00002113533,0.00016547061,0.00014653512,0.000027502578,0.00019380437,0.49611828],"genre_scores_gemma":[0.022488743,0.00014838993,0.5382017,0.00056505617,0.0006307055,0.00007119741,0.000009279522,0.00017709691,0.43770784],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99712986,0.000030514459,0.00042933397,0.001147471,0.0006555855,0.0006072417],"domain_scores_gemma":[0.9978528,0.000055681223,0.00021749947,0.0013428375,0.00016649847,0.00036469213],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022911566,0.0005240989,0.0007283708,0.00034827707,0.00016613248,0.00028013036,0.0013797199,0.00036617936,0.00003091265],"category_scores_gemma":[0.000016978836,0.00053346803,0.000285807,0.00012752612,0.00017695075,0.00017798175,0.002227164,0.0004505912,0.000109221946],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010695667,0.0000068705044,0.000014998428,0.000046323217,0.00078031555,0.000310554,0.00013995072,0.000054461612,0.000006778955,0.6489707,0.0000775366,0.34958076],"study_design_scores_gemma":[0.00083312695,0.00036648766,0.00042053644,0.000272522,0.0006639728,0.00041243283,0.000008519497,0.09762388,0.00012189031,0.8735757,0.023396105,0.002304837],"about_ca_topic_score_codex":0.00016444475,"about_ca_topic_score_gemma":0.00014015238,"teacher_disagreement_score":0.34727594,"about_ca_system_score_codex":0.00025453558,"about_ca_system_score_gemma":0.00011546626,"threshold_uncertainty_score":0.9997117},"labels":[],"label_agreement":null},{"id":"W4239884948","doi":"10.1007/978-1-4939-7131-2_100253","title":"Data Reduction Method","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Reduction (mathematics); Computer science; Mathematics; Geometry","score_opus":0.14797980495840338,"score_gpt":0.40624248348071534,"score_spread":0.258262678522312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239884948","genre_codex":"methods","genre_gemma":"other","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":[1.7871724e-8,0.000059001683,0.5930123,0.0002508794,0.00043490343,0.0000955922,0.000017975042,0.00019967233,0.40592965],"genre_scores_gemma":[3.2802137e-7,0.000039970437,0.49552923,0.000027135073,0.000388948,0.0000017710494,0.000030576542,0.000019964631,0.5039621],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978149,0.000026556192,0.00022832684,0.001096041,0.0005584317,0.0002757641],"domain_scores_gemma":[0.99550366,0.00006989238,0.00010448776,0.0040270733,0.00018099215,0.00011391809],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005736862,0.00022301386,0.00022400626,0.00017870107,0.00009369943,0.00015732546,0.00404347,0.0002009098,0.00091282977],"category_scores_gemma":[0.00003817464,0.00020422618,0.000042658034,0.000057014437,0.00008726145,0.0006733071,0.004764772,0.0003822485,0.00164777],"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":[0.0000036708395,0.000007290149,1.3430744e-8,0.000024422778,0.000053695177,0.000028010827,0.000060705723,0.000016784998,0.00008068246,0.21140009,0.065467626,0.722857],"study_design_scores_gemma":[0.00006758905,0.000056589575,2.5146775e-7,0.000037239828,0.0000054031116,0.00014498808,0.000002549097,0.08199737,0.00016999528,0.09949686,0.8177597,0.0002614827],"about_ca_topic_score_codex":0.000009329595,"about_ca_topic_score_gemma":0.0000045818233,"teacher_disagreement_score":0.75229204,"about_ca_system_score_codex":0.00009085613,"about_ca_system_score_gemma":0.00012417386,"threshold_uncertainty_score":0.9994846},"labels":[],"label_agreement":null},{"id":"W4240667868","doi":"10.7287/peerj.preprints.1693v1","title":"A comparison of clustering methods for biogeography with fossil datasets","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Ontario Museum","funders":"","keywords":"Cluster analysis; Hierarchical clustering; Euclidean distance; Complete-linkage clustering; Set (abstract data type); Computer science; Similarity (geometry); Data mining; Cluster (spacecraft); Single-linkage clustering; Complete linkage; Range (aeronautics); Data set; Mathematics; Fuzzy clustering; Artificial intelligence; CURE data clustering algorithm; Biology; Engineering","score_opus":0.08915802525528156,"score_gpt":0.4734502304649979,"score_spread":0.38429220520971635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240667868","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":[0.00006155218,0.0005016388,0.9967587,0.0003610515,0.0003552242,0.0009148954,0.00035967428,0.00021430498,0.0004729692],"genre_scores_gemma":[0.0073873317,0.000018347077,0.9920472,0.000019704934,0.00006119064,0.00027989713,0.00005499706,0.000032810465,0.00009852275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99717605,0.00017968459,0.0005592757,0.0010713796,0.00043531597,0.00057826506],"domain_scores_gemma":[0.99612844,0.00073768164,0.0004013435,0.00224723,0.00031305192,0.00017226647],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009087656,0.00036589275,0.00076071755,0.00046677003,0.000105776206,0.0001719957,0.002944149,0.00020042935,0.000007912459],"category_scores_gemma":[0.00010655124,0.00024883726,0.000181054,0.0003780433,0.00019000033,0.0002826406,0.005587041,0.00036188026,0.0000026935231],"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":[0.00012513554,0.00018014685,0.0005402131,0.0010786364,0.00029555045,0.000004921713,0.00038156225,0.0034405682,0.0022372347,0.0023318934,0.0009149746,0.9884692],"study_design_scores_gemma":[0.0011333149,0.00056729617,0.00024837375,0.0006930047,0.000031459484,0.0000139724625,0.000043151038,0.934174,0.033874646,0.014353983,0.014107969,0.0007588068],"about_ca_topic_score_codex":0.000053125816,"about_ca_topic_score_gemma":0.000034669232,"teacher_disagreement_score":0.98771036,"about_ca_system_score_codex":0.000062048835,"about_ca_system_score_gemma":0.0001803414,"threshold_uncertainty_score":0.99999636},"labels":[],"label_agreement":null},{"id":"W4241307588","doi":"10.1007/978-1-4939-7131-2_100106","title":"Cluster Description","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Cluster (spacecraft); Computer science; Programming language","score_opus":0.04605066862676165,"score_gpt":0.2856856847795797,"score_spread":0.23963501615281801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241307588","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.568774e-7,0.000044297285,0.5269192,0.00019741926,0.00035104484,0.000120192824,0.0000013742682,0.00021974037,0.4721461],"genre_scores_gemma":[0.000033079188,0.00003775631,0.18005076,0.00033819882,0.00036315198,0.000007258301,0.0000046544637,0.000037344824,0.8191278],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981656,0.000014205265,0.00024405874,0.0006560392,0.0005720377,0.000348065],"domain_scores_gemma":[0.9983464,0.000055003115,0.00009095748,0.0011339702,0.00023493773,0.0001387686],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002046675,0.00027002278,0.00022475142,0.00021907792,0.00009649697,0.00024217292,0.001306611,0.00026116552,0.0013361439],"category_scores_gemma":[0.00001974881,0.00024418224,0.000101007136,0.00004306599,0.00011748626,0.0005003797,0.0011885857,0.00035496734,0.0054978696],"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":[0.000015680609,0.000020189376,7.9666734e-7,0.000075651085,0.00008351836,0.000089768975,0.00033523023,0.000043089858,0.00009289391,0.61639696,0.11249064,0.27035558],"study_design_scores_gemma":[0.00020244246,0.00015084654,0.000003556715,0.00008894176,0.000004759888,0.00006107849,0.0000018936622,0.03709198,0.00011321984,0.20102756,0.76079214,0.00046156126],"about_ca_topic_score_codex":0.000004322512,"about_ca_topic_score_gemma":0.000010047955,"teacher_disagreement_score":0.64830154,"about_ca_system_score_codex":0.0001718023,"about_ca_system_score_gemma":0.00007711744,"threshold_uncertainty_score":0.99957675},"labels":[],"label_agreement":null},{"id":"W4241938281","doi":"10.1145/376284.375672","title":"Data bubbles","year":2001,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cluster analysis; Computer science; Data mining; CURE data clustering algorithm; Data stream clustering; Canopy clustering algorithm; Hierarchical clustering; Correlation clustering; Set (abstract data type); Data set; Data compression; Key (lock); Constrained clustering; Determining the number of clusters in a data set; Fuzzy clustering; Algorithm; Artificial intelligence","score_opus":0.123803096386827,"score_gpt":0.366511782884858,"score_spread":0.24270868649803096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241938281","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":[0.015085021,0.00015959123,0.9793649,0.0024989839,0.00052847486,0.00012862992,0.000008645049,0.0003343661,0.001891403],"genre_scores_gemma":[0.07812442,0.00045341285,0.9138129,0.00035889167,0.0004240146,0.000024056437,0.000025812751,0.00003255143,0.006743989],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983473,0.00005282237,0.00017574486,0.0006360096,0.00035203993,0.00043607948],"domain_scores_gemma":[0.9951127,0.00025814588,0.000046995086,0.0043864106,0.00006503283,0.00013070786],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003168061,0.00012148369,0.00013533368,0.00009631546,0.0001231608,0.00014925378,0.0068877744,0.00005068796,0.000053846634],"category_scores_gemma":[0.00053305074,0.000111964524,0.000025659067,0.00050688634,0.000045019035,0.0010793585,0.0053141345,0.00019924244,0.0002467739],"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":[0.000007884198,0.00003175601,0.00073152286,0.000005157086,0.000009954611,0.00008758646,0.000056276578,0.00007121411,0.00040487407,0.0004059025,0.003807564,0.9943803],"study_design_scores_gemma":[0.00052808353,0.00017625747,0.003346164,0.000033208365,0.000003970431,0.00019441632,0.000027846763,0.43123528,0.00052226207,0.024606079,0.53887224,0.00045415363],"about_ca_topic_score_codex":0.00010035999,"about_ca_topic_score_gemma":0.00006600292,"teacher_disagreement_score":0.99392617,"about_ca_system_score_codex":0.000041703326,"about_ca_system_score_gemma":0.000060517916,"threshold_uncertainty_score":0.99848545},"labels":[],"label_agreement":null},{"id":"W4243066799","doi":"10.1007/978-1-4939-7131-2_100110","title":"Clustering Evaluation","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence","score_opus":0.0745023061247611,"score_gpt":0.3441617868366472,"score_spread":0.2696594807118861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243066799","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.1500323e-7,0.00007035243,0.5074308,0.00009400257,0.00031284383,0.00019441181,9.386874e-7,0.00016445294,0.4917318],"genre_scores_gemma":[0.00007808785,0.000031216674,0.18579124,0.000105592735,0.00037801245,0.000018932236,0.0000068623463,0.00003932439,0.8135507],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99762195,0.000022591541,0.0002507194,0.00066118385,0.0011367108,0.00030681584],"domain_scores_gemma":[0.9980968,0.000063803695,0.00010803916,0.0011463147,0.00047227734,0.00011273881],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006270806,0.0002478556,0.00020889223,0.00021737989,0.000102792714,0.00017840428,0.0012267234,0.00020180175,0.0024632355],"category_scores_gemma":[0.00004377576,0.00023727604,0.00008082477,0.00004700615,0.00007594451,0.00034080524,0.0012968419,0.00028367786,0.0025008877],"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":[0.000004606277,0.000007353892,1.7469755e-7,0.00004159674,0.000052027408,0.000026203592,0.00020969688,0.0004594336,0.00004138054,0.06073092,0.006465278,0.93196136],"study_design_scores_gemma":[0.00020356265,0.000099440374,0.0000026231796,0.00009693308,0.000008748008,0.00003398614,0.0000020948105,0.76139694,0.000089900386,0.083871245,0.15382011,0.00037438257],"about_ca_topic_score_codex":0.000003516798,"about_ca_topic_score_gemma":0.000015499523,"teacher_disagreement_score":0.9315869,"about_ca_system_score_codex":0.00028271467,"about_ca_system_score_gemma":0.00016739122,"threshold_uncertainty_score":0.99844867},"labels":[],"label_agreement":null},{"id":"W4244787383","doi":"10.23952/jano.3.2021.1.09","title":"A survey of clustering methods via optimization methodology","year":2021,"lang":"en","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Department of Education of Guangdong Province; Shenzhen University; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Data mining; Artificial intelligence","score_opus":0.0701899445410024,"score_gpt":0.37791770589676704,"score_spread":0.30772776135576463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244787383","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":[0.000079184225,0.0002286534,0.99910545,0.0001555385,0.00016735146,0.00005962584,8.5372767e-7,0.000013761769,0.00018960198],"genre_scores_gemma":[0.020876398,0.00020557667,0.9787909,0.0000650522,0.000033742992,0.000001933279,0.00000383729,0.000011675353,0.000010906198],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982097,0.0005597142,0.00056672853,0.00021371935,0.0002747092,0.00017542855],"domain_scores_gemma":[0.99775434,0.000807577,0.0004541659,0.0001994866,0.00066844915,0.0001159911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018040801,0.00010862164,0.0004062779,0.00015709549,0.00005973853,0.000052893487,0.00027637466,0.00008437516,0.00001930535],"category_scores_gemma":[0.0005374097,0.00009852369,0.00004773794,0.00074063224,0.000047993923,0.00028780656,0.00027655563,0.0002034968,2.8961884e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056784706,0.000039374576,0.000017374425,0.000016999431,0.000026367388,0.000006708357,0.00014423284,0.8890353,0.0021564025,0.00016692189,0.0000036186916,0.10832993],"study_design_scores_gemma":[0.00042922332,0.00011580192,0.00040534028,0.000013013049,0.00000975359,0.0001061522,0.000021656653,0.9933997,0.0049281754,0.00045365078,0.000026173877,0.00009140279],"about_ca_topic_score_codex":0.000008803737,"about_ca_topic_score_gemma":6.95465e-7,"teacher_disagreement_score":0.108238526,"about_ca_system_score_codex":0.00003928849,"about_ca_system_score_gemma":0.00010476174,"threshold_uncertainty_score":0.40176797},"labels":[],"label_agreement":null},{"id":"W4246424543","doi":"10.1007/978-1-4939-7131-2_100111","title":"Clustering Objective Function","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence","score_opus":0.028964105373926644,"score_gpt":0.2778500299480699,"score_spread":0.24888592457414327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246424543","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.421412e-7,0.00004680009,0.537232,0.000046063924,0.00053153496,0.00012923338,0.0000015461271,0.00028769902,0.4617247],"genre_scores_gemma":[0.00016383173,0.000033813012,0.07991423,0.0001672907,0.0005614887,0.000013288956,0.0000044795997,0.00005475879,0.9190868],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979911,0.000009924896,0.00024469913,0.0008057142,0.00056910614,0.00037946948],"domain_scores_gemma":[0.99836385,0.000078956764,0.00011606723,0.0010237717,0.000282739,0.00013462608],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00018615338,0.00031835464,0.0002660138,0.0002645867,0.0001490822,0.00018047907,0.0010022564,0.0002596233,0.001015931],"category_scores_gemma":[0.000020475893,0.00030315583,0.000112586764,0.00006644668,0.000107631524,0.00043810174,0.001473332,0.00044602389,0.002637367],"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":[0.0000656492,0.000026556687,0.0000010100413,0.00012811722,0.0002916635,0.00014529096,0.0006722821,0.00041460156,0.0002064861,0.27856794,0.012528067,0.70695233],"study_design_scores_gemma":[0.00056746433,0.0010287968,0.000030812364,0.00030731902,0.0000249653,0.00014229663,0.000022784701,0.21639556,0.0004217028,0.25739735,0.5222041,0.0014568402],"about_ca_topic_score_codex":0.000008027773,"about_ca_topic_score_gemma":0.00002567496,"teacher_disagreement_score":0.7054955,"about_ca_system_score_codex":0.00025685786,"about_ca_system_score_gemma":0.000100754965,"threshold_uncertainty_score":0.99994206},"labels":[],"label_agreement":null},{"id":"W4246517075","doi":"10.17771/pucrio.acad.54595","title":"A MODEL-BASED FRAMEWORK FOR SEMI-SUPERVISED CLUSTERING AND COMMUNITY DETECTION","year":2021,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Pontifícia Universidade Católica do Rio de Janeiro; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Centre interuniversitaire de recherche sur les reseaux d'entreprise, la logistique et le transport; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Cluster analysis; Computer science; Focus (optics); Data mining; Perspective (graphical); Machine learning; Artificial intelligence; Stochastic block model","score_opus":0.05005488187165928,"score_gpt":0.34649199057940594,"score_spread":0.29643710870774664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246517075","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":[0.01435167,0.00014735953,0.9838884,0.000070104994,0.0003871924,0.00049241615,0.000008257169,0.00025352117,0.00040108783],"genre_scores_gemma":[0.18787129,0.000029931858,0.8092413,0.00013857077,0.00006331664,0.00032395718,0.00015168251,0.000056575536,0.0021233996],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828434,0.00020129616,0.00027493612,0.00051404967,0.00033691069,0.00038846798],"domain_scores_gemma":[0.9976851,0.0007876415,0.00009963856,0.00094253017,0.00034880513,0.00013628474],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046207284,0.0002856916,0.00033080616,0.0001950622,0.00068970665,0.00037338966,0.0007929333,0.00039435356,0.0000057730945],"category_scores_gemma":[0.00040491842,0.00030706712,0.00010743384,0.00034367817,0.000025861536,0.00028301112,0.00028126457,0.0012714984,0.0000017702346],"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":[0.00024146514,0.00026589597,0.000006227791,0.0035809705,0.000109994515,0.000013903347,0.0067320354,0.116331026,0.014196284,0.0017273431,0.000027639644,0.85676724],"study_design_scores_gemma":[0.0003467048,0.000119872326,0.000030064306,0.00028393284,0.000009638241,0.000003909775,0.00065914757,0.9775998,0.011932669,0.0086668525,0.000038321978,0.00030908306],"about_ca_topic_score_codex":0.00009041054,"about_ca_topic_score_gemma":0.0010188571,"teacher_disagreement_score":0.86126876,"about_ca_system_score_codex":0.00012949453,"about_ca_system_score_gemma":0.00020309968,"threshold_uncertainty_score":0.99993813},"labels":[],"label_agreement":null},{"id":"W4247582225","doi":"10.32920/ryerson.14648265.v1","title":"k-MACE Clustering for Gaussian Clusters","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Clustering Algorithms Research","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":"Toronto Metropolitan University","funders":"","keywords":"Mace; Cluster analysis; Preprocessor; Computer science; Mathematics; Gaussian; Cluster (spacecraft); Algorithm; Covariance; Statistics; Artificial intelligence; Physics; Medicine","score_opus":0.04531905812185061,"score_gpt":0.34262640442645365,"score_spread":0.29730734630460304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247582225","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":[0.00025276403,0.00027437284,0.9884274,0.0036753032,0.0021166343,0.00094754086,0.000011790078,0.0005985951,0.0036955855],"genre_scores_gemma":[0.018991213,0.00009540407,0.9731421,0.00049719145,0.00032357802,0.00047080603,0.000044868295,0.000073113915,0.0063617155],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99628574,0.00010544482,0.00048542666,0.0015892215,0.00062563055,0.0009085502],"domain_scores_gemma":[0.996707,0.00027426126,0.00017265487,0.0022266577,0.00032414153,0.00029528147],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00050675916,0.00045579925,0.00054079894,0.00025352347,0.0002112543,0.0012500433,0.0030755568,0.00035222713,0.000035528334],"category_scores_gemma":[0.00016625768,0.00046371156,0.0003208443,0.0003177779,0.000065691194,0.00045908353,0.0113416575,0.00079844217,0.000021809557],"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":[0.00006702549,0.0002651396,0.000025272864,0.0034655365,0.0004468278,0.00038787207,0.00391742,0.38036928,0.0014057794,0.0068412377,0.0038852224,0.5989234],"study_design_scores_gemma":[0.00044172644,0.000056661218,0.00003908014,0.00023358632,0.000008237099,0.00003990262,0.00014574535,0.99063003,0.0013871526,0.0014451535,0.0049790703,0.0005936712],"about_ca_topic_score_codex":0.00007816118,"about_ca_topic_score_gemma":0.00010669214,"teacher_disagreement_score":0.6102607,"about_ca_system_score_codex":0.00034173176,"about_ca_system_score_gemma":0.00044933858,"threshold_uncertainty_score":0.99978673},"labels":[],"label_agreement":null},{"id":"W4247791306","doi":"10.1137/1.9781611976335.ch11","title":"Chapter 11: Graph-Based Clustering Algorithms","year":2020,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Cluster analysis; Hypergraph; Computer science; Clustering coefficient; Graph; Null graph; Voltage graph; Butterfly graph; Strength of a graph; Theoretical computer science; Algorithm; Mathematics; Line graph; Combinatorics; Artificial intelligence","score_opus":0.09129902419943707,"score_gpt":0.27567703356965967,"score_spread":0.18437800937022258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247791306","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":[0.0000069960547,0.000057011046,0.9171643,0.00041166274,0.00030808215,0.0019444266,0.00011803582,0.00032886228,0.07966061],"genre_scores_gemma":[0.0004672532,0.000032964806,0.9323723,0.0006896563,0.0015171771,0.0004215889,0.000054264314,0.0002983769,0.064146444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970392,0.0000046128985,0.00068266166,0.0009914351,0.00069154246,0.0005905282],"domain_scores_gemma":[0.99805325,0.00035308604,0.00042012104,0.0007171581,0.000113971604,0.0003423831],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043006794,0.000689482,0.0008551779,0.00009744264,0.00040791888,0.00031487306,0.0009908156,0.00079997664,0.00001440677],"category_scores_gemma":[0.0000224047,0.00066433713,0.00067883905,0.00004566681,0.0003095915,0.00007316825,0.00090113503,0.000900395,0.000015511969],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027604154,0.000026419948,4.9171028e-8,0.000671834,0.0002815418,0.000008259772,0.0010609955,0.00013311233,0.0005334389,0.895341,0.0010740504,0.10084173],"study_design_scores_gemma":[0.005925278,0.0004886606,7.305567e-8,0.0008339833,0.00026128758,0.0000308958,0.00023000212,0.26775917,0.0047243317,0.5718686,0.1454057,0.0024719918],"about_ca_topic_score_codex":0.0000020365455,"about_ca_topic_score_gemma":0.0000016619573,"teacher_disagreement_score":0.32347235,"about_ca_system_score_codex":0.000092958086,"about_ca_system_score_gemma":0.00015937276,"threshold_uncertainty_score":0.9995808},"labels":[],"label_agreement":null},{"id":"W4248125270","doi":"10.1137/1.9781611976335.ch18","title":"Chapter 18: Evaluation of Clustering Algorithms","year":2020,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Cluster analysis; Computer science; Correlation clustering; Data mining; CURE data clustering algorithm; Determining the number of clusters in a data set; Single-linkage clustering; Set (abstract data type); Fuzzy clustering; Cluster (spacecraft); Canopy clustering algorithm; Clustering high-dimensional data; Algorithm; Artificial intelligence","score_opus":0.19723447155785484,"score_gpt":0.32563627083338675,"score_spread":0.1284017992755319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248125270","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":[0.00003087582,0.00013820788,0.71865225,0.00016354957,0.0003363793,0.0033483438,0.000114271126,0.0001778329,0.2770383],"genre_scores_gemma":[0.0032019732,0.00007659361,0.93540436,0.00018931268,0.0016955002,0.0005709181,0.000059054608,0.00027626654,0.058526047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99732697,0.0000066100138,0.0006569688,0.00063140935,0.0010577525,0.00032027232],"domain_scores_gemma":[0.9982911,0.00023604483,0.00051149377,0.00052197906,0.00027833748,0.00016108298],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001084555,0.00041395848,0.00067807146,0.00006370582,0.00017909532,0.000110625886,0.0006273754,0.0005481141,0.000024741601],"category_scores_gemma":[0.000043166634,0.0004010312,0.00039682243,0.000030004514,0.00020091217,0.00006525173,0.0007875711,0.00055484334,0.000006320487],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020135267,0.000019117953,1.9728773e-8,0.00052356475,0.0003450167,6.890887e-7,0.002010078,0.00016816874,0.000789414,0.6110082,0.00049043936,0.38462514],"study_design_scores_gemma":[0.0039037,0.00027972698,7.1403946e-8,0.0005179666,0.00038312457,0.000011936655,0.00025941324,0.4146385,0.0039684945,0.56179756,0.01330697,0.00093253213],"about_ca_topic_score_codex":0.0000011534823,"about_ca_topic_score_gemma":7.84623e-7,"teacher_disagreement_score":0.41447031,"about_ca_system_score_codex":0.00010432757,"about_ca_system_score_gemma":0.00018537958,"threshold_uncertainty_score":0.99984413},"labels":[],"label_agreement":null},{"id":"W4249726331","doi":"10.1137/1.9781611976335.ch7","title":"Chapter 7: Hierarchical Clustering Techniques","year":2020,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Hierarchical clustering; Hierarchical clustering of networks; Computer science; Partition (number theory); Cluster analysis; Hierarchical database model; Single-linkage clustering; Algorithm; Set (abstract data type); Data mining; Hierarchical control system; Pattern recognition (psychology); Canopy clustering algorithm; Artificial intelligence; Mathematics; Correlation clustering; Combinatorics","score_opus":0.08103529639172104,"score_gpt":0.2813290510848872,"score_spread":0.20029375469316618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249726331","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":[0.0000027895785,0.000036523612,0.6645698,0.0005235089,0.00013268222,0.0017105564,0.000056449462,0.00047584248,0.33249184],"genre_scores_gemma":[0.00021393115,0.00005501532,0.911392,0.0004973198,0.0014116403,0.00032400832,0.00002013994,0.00018318363,0.08590277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99767643,0.0000035006046,0.00056476484,0.0007878656,0.0005150761,0.0004523661],"domain_scores_gemma":[0.9984734,0.00028286153,0.00028054015,0.0005594829,0.00007239504,0.0003313234],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036514824,0.00052206754,0.0007038638,0.00006393774,0.00031222941,0.00025304483,0.0008555496,0.0007684707,0.000012822574],"category_scores_gemma":[0.00003122235,0.00048924156,0.0004504127,0.00002433373,0.00028313886,0.00006302492,0.0014541082,0.0011504199,0.000011143106],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000140477005,0.000008130427,4.970116e-9,0.00024222111,0.00011454617,0.0000028304455,0.00069090293,0.0000020780867,0.00042966814,0.79919344,0.00057582284,0.19872631],"study_design_scores_gemma":[0.0011062456,0.0002694765,1.20760335e-8,0.00039092064,0.00007763765,0.000030882587,0.00006874146,0.019546999,0.0030951991,0.7512191,0.2232115,0.0009832861],"about_ca_topic_score_codex":6.732164e-7,"about_ca_topic_score_gemma":4.6970084e-7,"teacher_disagreement_score":0.24682218,"about_ca_system_score_codex":0.000081482234,"about_ca_system_score_gemma":0.00012266224,"threshold_uncertainty_score":0.9997559},"labels":[],"label_agreement":null},{"id":"W4250669299","doi":"10.1007/978-1-4939-7131-2_100425","title":"Graph Clustering","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence","score_opus":0.03630852760864116,"score_gpt":0.29069633507219084,"score_spread":0.25438780746354966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250669299","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.4931887e-7,0.000067960056,0.51774186,0.00010168882,0.0003198661,0.00009893538,0.0000017236673,0.0002937851,0.48137394],"genre_scores_gemma":[0.000021690144,0.0000743102,0.20073588,0.00016568248,0.00030776826,0.0000070621504,0.00000277229,0.000049273625,0.79863554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978844,0.000010357769,0.00027509057,0.00077095197,0.00061231694,0.00044691772],"domain_scores_gemma":[0.9980603,0.0000691059,0.00010079975,0.0014028625,0.00018636356,0.00018059224],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001867677,0.00033135738,0.0002913581,0.00031645084,0.00012448459,0.00020637063,0.0019406393,0.00024258459,0.0011528964],"category_scores_gemma":[0.000015093062,0.00031022634,0.00013981701,0.000069253656,0.0001465562,0.0003192764,0.0021126412,0.0004164524,0.0024828645],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012039084,0.000019543684,6.836628e-7,0.00014426309,0.00015939043,0.00035560178,0.00038054667,0.00018700653,0.000084531515,0.56055987,0.02504972,0.41304684],"study_design_scores_gemma":[0.00025462604,0.00021898159,0.0000030105787,0.00019418544,0.000006645984,0.00012772036,0.000003598587,0.05513223,0.00017807647,0.25845048,0.6845502,0.00088026345],"about_ca_topic_score_codex":0.0000059045647,"about_ca_topic_score_gemma":0.000019445852,"teacher_disagreement_score":0.6595005,"about_ca_system_score_codex":0.00010345967,"about_ca_system_score_gemma":0.0000747465,"threshold_uncertainty_score":0.999935},"labels":[],"label_agreement":null},{"id":"W4251878303","doi":"10.1137/1.9781611976335.ch10","title":"Chapter 10: Search-Based Clustering Algorithms","year":2020,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Cluster analysis; Algorithm; Artificial intelligence","score_opus":0.11434634602538142,"score_gpt":0.286528705407464,"score_spread":0.1721823593820826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251878303","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":[0.000005150583,0.000057235262,0.82716143,0.00050315174,0.00021281363,0.0020556576,0.00012793088,0.00037846906,0.16949816],"genre_scores_gemma":[0.0003024094,0.000025857915,0.8135575,0.00047806877,0.0014688892,0.00029707098,0.00005616262,0.00027761672,0.18353643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996898,0.000005897641,0.0006496272,0.001001258,0.0008025179,0.0006426767],"domain_scores_gemma":[0.99804205,0.00039903767,0.0003030494,0.0007294014,0.00014396178,0.00038252518],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053885917,0.000659998,0.00082848466,0.00008843566,0.000417967,0.0003618371,0.0010455766,0.0007777222,0.000045949404],"category_scores_gemma":[0.000025955855,0.0006368785,0.00058632845,0.000040927607,0.00035125416,0.000074632415,0.0011544521,0.0010557311,0.00004769149],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057076963,0.000030918156,1.7753209e-8,0.0008692698,0.00036107804,0.000010768485,0.0014540444,0.00024160392,0.00050383114,0.7656181,0.0016185825,0.22923474],"study_design_scores_gemma":[0.005779896,0.0006726279,4.5918302e-8,0.0008047543,0.00019919658,0.000027913671,0.00025725304,0.58920294,0.004782095,0.2222855,0.1736934,0.0022943867],"about_ca_topic_score_codex":0.0000016330789,"about_ca_topic_score_gemma":6.175401e-7,"teacher_disagreement_score":0.5889613,"about_ca_system_score_codex":0.00012848961,"about_ca_system_score_gemma":0.000225609,"threshold_uncertainty_score":0.9996083},"labels":[],"label_agreement":null},{"id":"W4252408959","doi":"10.1007/978-1-4939-7131-2_100104","title":"Cluster Analysis","year":2018,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Cluster (spacecraft); Computer science; Operating system","score_opus":0.028849627619853005,"score_gpt":0.3001337533546835,"score_spread":0.2712841257348305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252408959","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.9884964e-7,0.000039769617,0.52886915,0.00024361048,0.000115183546,0.000080093974,0.0000030013252,0.00017309998,0.4704757],"genre_scores_gemma":[0.000037847163,0.000029641425,0.16430137,0.0003936376,0.00021720982,0.000005590835,0.000008807147,0.00002905241,0.83497685],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99775255,0.000016295511,0.00029403876,0.0008434062,0.00070932606,0.0003843985],"domain_scores_gemma":[0.99755317,0.00011155014,0.000115924486,0.0017794614,0.00026463257,0.00017525555],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00023512366,0.00030473399,0.00043026617,0.00072839967,0.00009341723,0.00021228308,0.0018660212,0.00025305155,0.0033013832],"category_scores_gemma":[0.00001848496,0.00026673064,0.0003265453,0.00025587072,0.00012705401,0.00026403044,0.0016111042,0.00034226288,0.0035824475],"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":[0.000019747456,0.0000406238,0.000009006396,0.000079634636,0.0045213625,0.00024988013,0.00056342717,0.0010427267,0.000013771677,0.676443,0.092109,0.22490782],"study_design_scores_gemma":[0.00019574982,0.00012157792,0.000013726663,0.000029798044,0.00016805476,0.000018465935,0.0000019125132,0.19935212,0.00005445203,0.08668022,0.7126361,0.00072778104],"about_ca_topic_score_codex":0.000008076822,"about_ca_topic_score_gemma":0.00003574416,"teacher_disagreement_score":0.62052715,"about_ca_system_score_codex":0.00012326671,"about_ca_system_score_gemma":0.00007239087,"threshold_uncertainty_score":0.9999785},"labels":[],"label_agreement":null},{"id":"W4253573012","doi":"10.1137/1.9781611976335.ch2","title":"Chapter 2: Data Types","year":2020,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Data type; Unstructured data; Cluster analysis; Information retrieval; Data mining; Artificial intelligence; Big data; Programming language","score_opus":0.18043614749240725,"score_gpt":0.302795166268206,"score_spread":0.12235901877579877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253573012","genre_codex":"other","genre_gemma":"methods","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":[0.0000034657396,0.00017016297,0.45782164,0.0007709811,0.0003357431,0.0021161116,0.00048083515,0.00036503503,0.53793603],"genre_scores_gemma":[0.0001683396,0.00009930709,0.7592717,0.00047975226,0.0019733685,0.00012447734,0.00016257037,0.00020444917,0.23751608],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979653,0.0000020559612,0.00041613652,0.00083674,0.00044342128,0.00033637125],"domain_scores_gemma":[0.9980916,0.00025945695,0.0002558793,0.0011374917,0.00006240655,0.00019316205],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034629655,0.00039801447,0.000553336,0.00003350584,0.00023177947,0.00022047576,0.0015972869,0.00052014587,0.000015143377],"category_scores_gemma":[0.0000312866,0.00036275154,0.00021194032,0.000019206675,0.00019417737,0.00008155675,0.0024011538,0.0006982326,0.000031803294],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000078458625,0.0000066702255,5.413559e-9,0.0001654562,0.00017397516,0.0000016059308,0.00045877468,0.0000020336524,0.00008418173,0.88523275,0.0030898824,0.110776834],"study_design_scores_gemma":[0.0011652024,0.00011221492,1.0438744e-8,0.00018037182,0.000111440546,0.000011554058,0.000070775764,0.022181856,0.00035298578,0.5585996,0.41652998,0.0006839858],"about_ca_topic_score_codex":7.093401e-7,"about_ca_topic_score_gemma":4.927336e-7,"teacher_disagreement_score":0.4134401,"about_ca_system_score_codex":0.000037532707,"about_ca_system_score_gemma":0.000118230586,"threshold_uncertainty_score":0.99988246},"labels":[],"label_agreement":null},{"id":"W4254373892","doi":"10.1007/978-1-4614-6170-8_100953","title":"Graph Clustering","year":2014,"lang":"en","type":"book-chapter","venue":"","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":"University of Calgary","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence","score_opus":0.02848160426955035,"score_gpt":0.2753965071202259,"score_spread":0.24691490285067555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254373892","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.098773e-8,0.00006123138,0.5303565,0.00015536358,0.00024604597,0.00008926441,9.2066887e-7,0.00028781226,0.46880278],"genre_scores_gemma":[0.000078049,0.000071007984,0.16801186,0.0002449142,0.00020267903,0.000008263735,0.0000030572155,0.00005298207,0.8313272],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997927,0.000014269994,0.00028518372,0.0007343092,0.0006087428,0.0004304855],"domain_scores_gemma":[0.99807686,0.00010984047,0.000107175714,0.0013995821,0.00011965912,0.00018689015],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022367552,0.00033597878,0.00033949254,0.00030939738,0.00010804963,0.00019184945,0.0018660587,0.00023746151,0.00022614124],"category_scores_gemma":[0.000017658733,0.00031573858,0.00015369087,0.000054904365,0.000079336576,0.00017011519,0.0017134366,0.0005100349,0.0011168587],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019296328,0.000002807023,2.0957165e-7,0.00004958334,0.000029968824,0.00005375035,0.000029696284,0.00038461693,0.000017299728,0.6626981,0.0019656555,0.33476642],"study_design_scores_gemma":[0.00024301429,0.00012245541,0.0000031418103,0.0001562196,0.000005629368,0.000092611655,0.0000010221548,0.11745675,0.000072195544,0.13218814,0.74889195,0.0007668454],"about_ca_topic_score_codex":0.0000072635967,"about_ca_topic_score_gemma":0.000014361642,"teacher_disagreement_score":0.7469263,"about_ca_system_score_codex":0.000087819906,"about_ca_system_score_gemma":0.000052549225,"threshold_uncertainty_score":0.9999295},"labels":[],"label_agreement":null},{"id":"W4281975883","doi":"10.1145/3805034","title":"Streaming Hierarchical Clustering Based on Point-Set Kernel","year":2022,"lang":"en","type":"preprint","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"State Key Laboratory of Novel Software Technology; Nanjing University; National Natural Science Foundation of China","keywords":"Hierarchical clustering; Cluster analysis; Computer science; Data mining; Single-linkage clustering; Brown clustering; Tree (set theory); Consensus clustering; Correlation clustering; Hierarchical clustering of networks; CURE data clustering algorithm; Scalability; Kernel (algebra); Tree structure; Constrained clustering; Artificial intelligence; Mathematics; Algorithm; Database; Binary tree","score_opus":0.07734526681048454,"score_gpt":0.3535982704819712,"score_spread":0.27625300367148664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281975883","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":[0.0012679024,0.00018135423,0.9770254,0.0012663078,0.0029646347,0.0006946734,0.015346482,0.0005050921,0.00074818905],"genre_scores_gemma":[0.61897045,0.0003504675,0.36034438,0.00067186996,0.0008721789,0.0009623643,0.013910856,0.00038374704,0.0035337035],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99318516,0.0006159127,0.0007285065,0.0033244956,0.001233428,0.00091251987],"domain_scores_gemma":[0.98299664,0.0022263443,0.00021714186,0.014140242,0.00008985901,0.00032974168],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00070927443,0.00080463546,0.0007222937,0.0007342101,0.0007524445,0.001117058,0.015223838,0.00032993368,0.00039372497],"category_scores_gemma":[0.00029067448,0.00086370966,0.00031083543,0.00071031175,0.00017588827,0.0017131012,0.00629926,0.0039671496,0.0001945419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040064214,0.0022305262,0.00003715876,0.00034975112,0.000398753,0.00028046654,0.0012783553,0.5905523,0.00016991487,0.00013936317,0.001121284,0.40304148],"study_design_scores_gemma":[0.0010509464,0.00026300322,0.00032107218,0.0005240484,0.000057740857,0.000007303931,0.0001385141,0.98849374,0.00033412813,0.0034224214,0.004437756,0.00094933016],"about_ca_topic_score_codex":0.00044571806,"about_ca_topic_score_gemma":0.0004940313,"teacher_disagreement_score":0.61770254,"about_ca_system_score_codex":0.0008173398,"about_ca_system_score_gemma":0.0008914137,"threshold_uncertainty_score":0.9999199},"labels":[],"label_agreement":null},{"id":"W4285364251","doi":"10.1609/aaai.v26i1.8282","title":"Weighted Clustering","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Strategic Research Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Research Foundation; Sino-Danish Center; Danmarks Grundforskningsfond; National Science Foundation","keywords":"Cluster analysis; Computer science; Generalization; CURE data clustering algorithm; Correlation clustering; Data mining; Single-linkage clustering; Artificial intelligence; Consensus clustering; Hierarchical clustering; Canopy clustering algorithm; Fuzzy clustering; Selection (genetic algorithm); Pattern recognition (psychology); Mathematics","score_opus":0.02217365358364736,"score_gpt":0.2965578701439754,"score_spread":0.274384216560328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285364251","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":[0.0007678947,0.00007279417,0.9715784,0.0012712519,0.00019117014,0.000028880217,2.0842165e-7,0.0002615845,0.025827803],"genre_scores_gemma":[0.05126296,0.000018402532,0.93375087,0.00038498148,0.000058079087,0.000007453164,0.0000010316674,0.000008445613,0.014507755],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991028,0.00003246864,0.00009626789,0.00028580622,0.0002297167,0.0002529461],"domain_scores_gemma":[0.9992126,0.000051783158,0.000012277262,0.00052926573,0.000109000044,0.00008502711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000082714396,0.00006220186,0.00007292348,0.00004169102,0.00007099658,0.0001350982,0.00047672942,0.000024505109,0.00011452168],"category_scores_gemma":[0.000032146192,0.00005813002,0.000028233704,0.00042667915,0.000014240093,0.00032729504,0.00086938613,0.00009640674,0.0001969109],"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":[0.0000030775018,0.00008205457,0.00011228194,0.000031628806,0.000026906027,0.00093441934,0.00034486467,0.00097261555,0.018789107,0.056427814,0.0010758478,0.9211994],"study_design_scores_gemma":[0.00023287714,0.000018782208,0.00033050045,0.000009987618,5.5575794e-7,0.0001607213,0.000025538928,0.932656,0.04288972,0.004188845,0.01933305,0.00015340715],"about_ca_topic_score_codex":0.000005406942,"about_ca_topic_score_gemma":0.000010207872,"teacher_disagreement_score":0.9316834,"about_ca_system_score_codex":0.00003517666,"about_ca_system_score_gemma":0.00006316959,"threshold_uncertainty_score":0.2530957},"labels":[],"label_agreement":null},{"id":"W4285464664","doi":"10.32920/ryerson.14661465.v1","title":"Kernel k-MACE: hypercube unsupervised clustering method","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Cluster analysis; Kernel (algebra); Pattern recognition (psychology); Computer science; Artificial intelligence; Kernel method; Initialization; Kernel embedding of distributions; Feature vector; Mace; Variable kernel density estimation; Mathematics; Support vector machine; Combinatorics","score_opus":0.0463775866907028,"score_gpt":0.3578731729497401,"score_spread":0.3114955862590373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285464664","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":[0.00096669653,0.00059620006,0.98740226,0.001379228,0.0015261358,0.0004641054,0.000008932286,0.00091542734,0.006741022],"genre_scores_gemma":[0.012913453,0.00020769762,0.98109555,0.0004898255,0.0002504331,0.0001304014,0.000019842253,0.00007694554,0.0048158295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99485344,0.0004468151,0.00059617724,0.0020381068,0.0011068757,0.0009585617],"domain_scores_gemma":[0.99545634,0.0003616395,0.00013562324,0.003214661,0.00045295362,0.00037878033],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009686983,0.0005864113,0.00075229135,0.00031153785,0.00019358523,0.0013611617,0.004192014,0.00047540237,0.00025715277],"category_scores_gemma":[0.00021501108,0.00058703416,0.00032285965,0.00063091447,0.000060889448,0.00054774195,0.020789064,0.001750721,0.00010368633],"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":[0.000012445278,0.00015262725,0.0000338203,0.00074321934,0.00021902753,0.0007330653,0.0020948607,0.18193837,0.0052365265,0.0010468232,0.00030304102,0.8074862],"study_design_scores_gemma":[0.00034014805,0.000030233297,0.00021837861,0.00018879506,0.000010427671,0.00013722888,0.00017189598,0.99168634,0.0037635216,0.0015358166,0.0012185437,0.0006986723],"about_ca_topic_score_codex":0.00034203508,"about_ca_topic_score_gemma":0.00006624873,"teacher_disagreement_score":0.809748,"about_ca_system_score_codex":0.00035894403,"about_ca_system_score_gemma":0.0005697752,"threshold_uncertainty_score":0.9996755},"labels":[],"label_agreement":null},{"id":"W4285781363","doi":"10.1002/widm.1343","title":"Density‐based clustering","year":2019,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Cluster analysis; Artificial intelligence","score_opus":0.06673601290054507,"score_gpt":0.3667671650858934,"score_spread":0.30003115218534837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285781363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042607516,0.025625624,0.92201144,0.00060308276,0.0018624732,0.0010120642,0.000082919505,0.00027652868,0.005918353],"genre_scores_gemma":[0.6197993,0.005663145,0.3584121,0.0005886046,0.0009509553,0.0002115989,0.0007197741,0.00018294789,0.013471547],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969705,0.00025850654,0.0005830735,0.0013590276,0.00025306587,0.00057583046],"domain_scores_gemma":[0.99610555,0.00030845174,0.00018078218,0.0031443934,0.00006590065,0.00019491774],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012614767,0.0003697553,0.00064107816,0.00021829629,0.00026689708,0.000580901,0.0028156743,0.000088943394,0.00002057156],"category_scores_gemma":[0.00012919359,0.0003118947,0.000106272084,0.0004833117,0.00011612133,0.0032793113,0.015987229,0.00029751405,0.00039361793],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064549014,0.00022501152,0.0020308855,0.0013738865,0.000054090717,0.0000754631,0.002631999,0.00009062741,0.0010146779,0.00023642399,0.01032604,0.9818764],"study_design_scores_gemma":[0.00091261644,0.00036855426,0.00076262304,0.004225052,0.000028729604,0.0001698976,0.00043279282,0.94368577,0.00017753014,0.00018897792,0.048179116,0.00086835766],"about_ca_topic_score_codex":0.000003631454,"about_ca_topic_score_gemma":0.000045052937,"teacher_disagreement_score":0.981008,"about_ca_system_score_codex":0.00008435822,"about_ca_system_score_gemma":0.00013629267,"threshold_uncertainty_score":0.9999333},"labels":[],"label_agreement":null},{"id":"W4286239843","doi":"10.5281/zenodo.6866942","title":"Datasets for Data-Centric Classification and Clustering","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Data science; Artificial intelligence","score_opus":0.09582514426084024,"score_gpt":0.30527602719829605,"score_spread":0.2094508829374558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286239843","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":[0.0007037469,0.00011904964,0.992782,0.0015234379,0.00014097326,0.0006709935,0.0015329752,0.0006622702,0.001864527],"genre_scores_gemma":[0.74698925,0.00042283104,0.19075435,0.00094120303,0.0005800194,0.0000033198642,0.055059407,0.0035463553,0.0017032826],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979551,0.000282957,0.0002018117,0.00071418093,0.00046121862,0.00038476216],"domain_scores_gemma":[0.9982431,0.00006532464,0.00009012907,0.001271662,0.0001821605,0.00014760601],"candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012044739,0.0001048689,0.00010490991,0.00024040027,0.0035837896,0.0009050377,0.0034739277,0.000022319586,0.00045663],"category_scores_gemma":[0.00047191457,0.00012270984,0.000017033732,0.00066376623,0.000075959346,0.0007629738,0.013030421,0.00024786618,0.00021961353],"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":[0.00005854415,0.00013478633,0.0000023185341,0.00009224469,0.000028551514,0.000015308295,0.0005712313,0.00086287624,0.002679906,0.0071217823,0.10790813,0.88052434],"study_design_scores_gemma":[0.0003284358,0.00011529506,0.00011612852,0.000003269376,0.00000261082,0.00011334676,0.00009785257,0.37233943,0.000023198243,0.00017515969,0.62659097,0.000094314826],"about_ca_topic_score_codex":0.0000071509317,"about_ca_topic_score_gemma":1.999428e-7,"teacher_disagreement_score":0.88043,"about_ca_system_score_codex":0.00018241112,"about_ca_system_score_gemma":0.000006480007,"threshold_uncertainty_score":0.9977134},"labels":[],"label_agreement":null},{"id":"W4292397078","doi":"10.1007/s11222-022-10128-9","title":"A joint latent factor analyzer and functional subspace model for clustering multivariate functional data","year":2022,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Advanced Clustering Algorithms Research","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":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Functional principal component analysis; Principal component analysis; Multivariate statistics; Univariate; Cluster analysis; Subspace topology; Initialization; Projection pursuit; Mathematics; Computer science; Model selection; Multivariate normal distribution; Artificial intelligence; Pattern recognition (psychology); Statistics","score_opus":0.1475347888853481,"score_gpt":0.3320264717340741,"score_spread":0.18449168284872602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292397078","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":[0.00393213,0.000072160794,0.9946311,0.00020781353,0.00026161488,0.00018072521,0.0006527814,0.0000540427,0.0000076149063],"genre_scores_gemma":[0.41190207,0.000005176646,0.5875529,0.00007556886,0.000062861676,0.000013494133,0.00010329712,0.000013518369,0.00027112756],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850565,0.000046207962,0.0002120576,0.0005800465,0.00034875967,0.0003072588],"domain_scores_gemma":[0.9990819,0.00027950812,0.000092107926,0.0003408257,0.00010003079,0.000105618914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038452315,0.00012944533,0.00015266504,0.000090560934,0.000772324,0.000182992,0.0002699121,0.000018468796,0.000010298889],"category_scores_gemma":[0.000076029595,0.00013570621,0.000016381127,0.00012714548,0.00003943965,0.0001732804,0.0032381983,0.00020476268,5.6929855e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052362408,0.000056616595,0.00024912757,0.00008838626,0.000073166164,0.00001514026,0.0009476707,0.85715103,0.0007743359,0.013969868,0.0007857938,0.12583649],"study_design_scores_gemma":[0.0005411027,0.000060537663,0.004637509,0.0000070792257,0.000005774601,0.000033757402,0.000045464218,0.991131,0.000005979831,0.003200314,0.00017385515,0.00015760976],"about_ca_topic_score_codex":0.000023494664,"about_ca_topic_score_gemma":0.000008586118,"teacher_disagreement_score":0.40796992,"about_ca_system_score_codex":0.00006308306,"about_ca_system_score_gemma":0.00008136852,"threshold_uncertainty_score":0.59401697},"labels":[],"label_agreement":null},{"id":"W4292585402","doi":"10.48550/arxiv.1607.06187","title":"Exploring Differences in Interpretation of Words Essential in Medical\\n Expert-Patient Communication","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Jaccard index; Context (archaeology); Interpretation (philosophy); Quality of life (healthcare); Sample (material); Medicine; Psychology; Computer science; Artificial intelligence; Nursing","score_opus":0.14636189583854994,"score_gpt":0.2538733988732508,"score_spread":0.10751150303470083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292585402","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":[0.5136646,0.00006753094,0.485552,0.000113514136,0.00018317274,0.00014603259,0.0000016859519,0.000034728506,0.0002367038],"genre_scores_gemma":[0.99653566,0.0011854535,0.0021965527,0.000011428128,0.000015594855,0.000010229791,0.0000035269422,0.00000975009,0.0000317973],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980859,0.00037303098,0.0003605157,0.00063611526,0.00026388082,0.00028054332],"domain_scores_gemma":[0.99819946,0.00032785084,0.00023299314,0.0010321307,0.000107911015,0.000099662044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034293195,0.00018381102,0.00032472174,0.0006281322,0.000036788024,0.000034215787,0.0022237485,0.00015957601,0.000017667742],"category_scores_gemma":[0.00015559867,0.00018605441,0.000071886905,0.0006143829,0.00016426967,0.0007210994,0.0036614863,0.00054783124,0.0000059618324],"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":[0.00073588773,0.0016954528,0.031807877,0.00079413195,0.00021695331,0.0013591336,0.07517241,0.23488395,0.00085754244,0.08392013,0.000023422022,0.5685331],"study_design_scores_gemma":[0.00057641196,0.00005328773,0.0036369707,0.0016044838,0.0000024465796,0.0000014684507,0.0005435906,0.97814935,0.0007259522,0.0144377705,0.000007470174,0.00026079974],"about_ca_topic_score_codex":0.0004351136,"about_ca_topic_score_gemma":0.00027994943,"teacher_disagreement_score":0.7432654,"about_ca_system_score_codex":0.00035092834,"about_ca_system_score_gemma":0.00017201074,"threshold_uncertainty_score":0.7587079},"labels":[],"label_agreement":null},{"id":"W4293863504","doi":"10.1109/siu55565.2022.9864873","title":"Semantic Segmentation with the Mixup Data Augmentation Method","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Image segmentation; Computer vision; Natural language processing","score_opus":0.07743756159890856,"score_gpt":0.37187996519312605,"score_spread":0.29444240359421747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293863504","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":[0.0002334729,0.0011372684,0.98596233,0.011075978,0.000010374967,0.00076243357,0.00004493135,0.00016076957,0.00061243057],"genre_scores_gemma":[0.58939713,0.00020660502,0.4060856,0.00036305218,0.000023007771,0.0029963455,0.00038837292,0.000021249038,0.00051864935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977662,0.0004738153,0.00028629036,0.0006247203,0.0005797268,0.0002692765],"domain_scores_gemma":[0.99609077,0.00036944824,0.00025953967,0.0029427544,0.00025419466,0.00008328963],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00096381654,0.00017166095,0.00015204445,0.00014484515,0.0034284093,0.0005447028,0.004850241,0.000026754145,0.00004496382],"category_scores_gemma":[0.0000093753615,0.00014275321,0.000018549801,0.0013319631,0.00026385917,0.00082094455,0.0037879522,0.000548635,0.000008424166],"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":[0.000012096815,0.00015374795,0.00005136634,0.000039583618,0.000031063406,8.2128537e-7,0.0019342594,0.0016832714,0.0024172906,0.018299919,0.0003056102,0.97507095],"study_design_scores_gemma":[0.00035904348,0.000088528875,0.00016784822,0.000017731763,0.00003649028,0.00006377462,0.004705007,0.96311426,0.00023246833,0.0040123546,0.02696001,0.0002424798],"about_ca_topic_score_codex":0.00007427583,"about_ca_topic_score_gemma":0.000044665772,"teacher_disagreement_score":0.9748285,"about_ca_system_score_codex":0.00010128636,"about_ca_system_score_gemma":0.00038371957,"threshold_uncertainty_score":0.997869},"labels":[],"label_agreement":null},{"id":"W4294311511","doi":"10.1109/tetci.2022.3201620","title":"Viewpoint-Based Kernel Fuzzy Clustering With Weight Information Granules","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Emerging Topics in Computational Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":71,"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":"Anhui Provincial Key Research and Development Plan; Natural Science Foundation of Anhui Province; Central University Basic Research Fund of China; National Natural Science Foundation of China","keywords":"Cluster analysis; Fuzzy clustering; Mathematics; Artificial intelligence; Data mining; Pattern recognition (psychology); FLAME clustering; Correlation clustering; CURE data clustering algorithm; Computer science","score_opus":0.025033645151595774,"score_gpt":0.2962129579615027,"score_spread":0.2711793128099069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294311511","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":[0.000630437,0.000021932441,0.994786,0.0032927815,0.0005831601,0.0002535157,0.000012020403,0.00016416314,0.00025598827],"genre_scores_gemma":[0.6831065,0.000013509285,0.31543478,0.0010899075,0.000027240712,0.0002153843,0.000008785523,0.000015661923,0.00008828114],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787265,0.00012690612,0.00043652748,0.0003625549,0.00086633407,0.00033500153],"domain_scores_gemma":[0.99904495,0.00026919952,0.000107613916,0.0003501435,0.00015051861,0.00007757283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033539216,0.00018830657,0.0001605984,0.0005909022,0.0005051771,0.00011129319,0.00082069694,0.000034497698,0.0000599798],"category_scores_gemma":[0.000008386002,0.00019985266,0.00006285319,0.0011163566,0.000070847294,0.0009696419,0.000026169277,0.00061970577,0.000027146642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003208557,0.000082028426,0.0000059351164,0.000022312393,0.000008546014,0.000012634309,0.0004520409,0.84415627,0.0000037013024,0.005422325,0.000005860921,0.14979625],"study_design_scores_gemma":[0.0002514929,0.00018806472,0.00007269561,0.0000428814,0.0000025572078,0.000028326722,0.00012487674,0.98585546,0.0008717747,0.011258804,0.0010723441,0.00023074094],"about_ca_topic_score_codex":0.00005970981,"about_ca_topic_score_gemma":0.000031050444,"teacher_disagreement_score":0.68247604,"about_ca_system_score_codex":0.00037201418,"about_ca_system_score_gemma":0.00017237592,"threshold_uncertainty_score":0.8149755},"labels":[],"label_agreement":null},{"id":"W4308319351","doi":"10.1007/s11721-022-00219-8","title":"Blending multiple algorithmic granular components: a recipe for clustering","year":2022,"lang":"en","type":"article","venue":"Swarm Intelligence","topic":"Advanced Clustering Algorithms Research","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":"University of Manitoba","funders":"","keywords":"Cluster analysis; Computer science; DBSCAN; Algorithm; Swarm intelligence; Canopy clustering algorithm; Correlation clustering; Data mining; Artificial intelligence; Particle swarm optimization","score_opus":0.05911746107355961,"score_gpt":0.31609172751656583,"score_spread":0.25697426644300625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308319351","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":[0.0019371511,0.00026208014,0.994693,0.00049381325,0.0012784149,0.0008073416,0.00002858057,0.0003556804,0.00014395807],"genre_scores_gemma":[0.48555622,0.000049062335,0.5121625,0.00030101967,0.00015122094,0.0009792781,0.000022492695,0.00005608961,0.0007221082],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969549,0.00014918037,0.00044776226,0.0008609425,0.00074022973,0.0008469668],"domain_scores_gemma":[0.99809986,0.0005599554,0.0001353877,0.0008824853,0.00014403656,0.00017829209],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00088958646,0.0002502164,0.0002697966,0.0003051113,0.0009575281,0.00015957667,0.002572289,0.00004300069,0.00004369295],"category_scores_gemma":[0.00021508244,0.0002851306,0.00014777598,0.00083551306,0.00007916512,0.0006499026,0.0024177507,0.00048603633,0.00004472984],"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":[0.00012737038,0.00026646114,0.00012832491,0.00014388589,0.00005314159,0.00013364445,0.0027083596,0.25628304,0.011678714,0.004295852,0.00022471597,0.72395647],"study_design_scores_gemma":[0.00026060292,0.00025276403,0.000025494588,0.000026106456,0.0000035177115,0.000099490346,0.00029926663,0.9596167,0.015985977,0.0052808775,0.017804712,0.00034445198],"about_ca_topic_score_codex":0.00008674428,"about_ca_topic_score_gemma":0.00000605636,"teacher_disagreement_score":0.723612,"about_ca_system_score_codex":0.00043161487,"about_ca_system_score_gemma":0.000078293655,"threshold_uncertainty_score":0.99996006},"labels":[],"label_agreement":null},{"id":"W4310371105","doi":"10.3390/e24121749","title":"Nonparametric Clustering of Mixed Data Using Modified Chi-Squared Tests","year":2022,"lang":"en","type":"article","venue":"Entropy","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Nonparametric statistics; Cluster analysis; Benchmark (surveying); Computer science; Sample space; Data mining; Cluster (spacecraft); Algorithm; Continuous variable; Parametric statistics; Mathematics; Hierarchical clustering; Product (mathematics); Statistics; Artificial intelligence","score_opus":0.09565957577078021,"score_gpt":0.3471802942440409,"score_spread":0.2515207184732607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310371105","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":[0.067347616,0.00016759781,0.93138516,0.000092556824,0.0005314564,0.00021414222,0.000042736276,0.000108872315,0.000109839624],"genre_scores_gemma":[0.69315594,0.000004978735,0.30662954,0.00002218097,0.000050707702,0.000013706283,0.000015618412,0.00001770117,0.000089623754],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976361,0.00018716682,0.00031595113,0.00059366814,0.00081515184,0.00045196273],"domain_scores_gemma":[0.99760735,0.00018094541,0.00015688245,0.0018897575,0.00006255047,0.000102496204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005143511,0.00013948313,0.00023185981,0.0003667849,0.00026920388,0.00007768341,0.003216822,0.00002594213,0.000043181026],"category_scores_gemma":[0.00023474856,0.00015271796,0.000044958048,0.0015823754,0.000048442278,0.00048217352,0.0068719494,0.00030013753,0.0000075390094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000740023,0.000350061,0.0005597937,0.00008736317,0.00007708443,0.00015098036,0.00060129777,0.88145095,0.038496125,0.003386964,0.00044441363,0.07432095],"study_design_scores_gemma":[0.00053819764,0.0001020301,0.00059738784,0.000008859203,0.0000042504125,0.00004670821,0.00004552769,0.9963041,0.0013765382,0.00036343906,0.0004589667,0.00015398493],"about_ca_topic_score_codex":0.00011190344,"about_ca_topic_score_gemma":0.0000031417017,"teacher_disagreement_score":0.62580836,"about_ca_system_score_codex":0.00016150158,"about_ca_system_score_gemma":0.00011821535,"threshold_uncertainty_score":0.8565393},"labels":[],"label_agreement":null},{"id":"W4312723533","doi":"10.1109/access.2022.3228238","title":"Piecemeal Clustering: a Self-Driven Data Clustering Algorithm","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland; Equinor","keywords":"Cluster analysis; CURE data clustering algorithm; Computer science; Canopy clustering algorithm; Correlation clustering; Data stream clustering; Fuzzy clustering; Data mining; Determining the number of clusters in a data set; Single-linkage clustering; Clustering high-dimensional data; Algorithm; Constrained clustering; Data set; Affinity propagation; Artificial intelligence","score_opus":0.09243514291304206,"score_gpt":0.3723603590328441,"score_spread":0.27992521611980203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312723533","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":[0.0012051952,0.00010886309,0.9936555,0.00067993946,0.002121792,0.0004440976,0.00009136987,0.0009212908,0.0007719781],"genre_scores_gemma":[0.17616822,0.0001015288,0.8196465,0.0011787242,0.0009822876,0.00048486915,0.00010522725,0.00014866874,0.0011839753],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99567056,0.0002495928,0.00044832384,0.0013749088,0.001304678,0.00095191976],"domain_scores_gemma":[0.99597096,0.00017294203,0.00017860041,0.0032999895,0.00011166723,0.00026584996],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007466099,0.00030794204,0.0003272224,0.00033029713,0.0008845487,0.00084089115,0.01372373,0.000057943595,0.00009937617],"category_scores_gemma":[0.000039612903,0.0003451648,0.000068684094,0.0012594447,0.000056190922,0.0030520407,0.025775675,0.00074705266,0.000059821108],"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":[0.000044052438,0.00047674403,0.00026530822,0.00014521358,0.00018322557,0.0010361935,0.0017115927,0.24459676,0.0008676101,0.00013160321,0.008828526,0.74171317],"study_design_scores_gemma":[0.00063053163,0.00012068812,0.00015845461,0.000012065056,0.0000072067937,0.00025196507,0.000043411917,0.9646284,0.00020151709,0.00023279748,0.0333133,0.00039967278],"about_ca_topic_score_codex":0.00018358442,"about_ca_topic_score_gemma":0.000053085852,"teacher_disagreement_score":0.7413135,"about_ca_system_score_codex":0.00039053895,"about_ca_system_score_gemma":0.00023081183,"threshold_uncertainty_score":0.99990004},"labels":[],"label_agreement":null},{"id":"W4319653775","doi":"10.48550/arxiv.2302.03391","title":"Sparse and geometry-aware generalisation of the mutual information for joint discriminative clustering and feature selection","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre hospitalier de l'Université Laval","funders":"Agence Nationale de la Recherche","keywords":"Cluster analysis; Discriminative model; Feature selection; Pattern recognition (psychology); Computer science; Scalability; Selection (genetic algorithm); Feature (linguistics); Artificial intelligence; Relevance (law); Clustering high-dimensional data; Data mining; Machine learning; Mathematics","score_opus":0.12688043526973647,"score_gpt":0.22954914912027388,"score_spread":0.10266871385053741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319653775","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":[0.1689353,0.0000088184215,0.8299785,0.00027499185,0.00022729523,0.00045939133,0.00003595746,0.00006565975,0.000014085177],"genre_scores_gemma":[0.9894201,0.000081873135,0.009871056,0.000018495715,0.00003766495,0.0000049186015,0.000019930396,0.000010532371,0.0005354012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907166,0.00007642689,0.00014285136,0.00040514645,0.00011129836,0.00019260608],"domain_scores_gemma":[0.9990226,0.000095710806,0.00023461392,0.00033833797,0.000250373,0.000058375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024719656,0.00016014242,0.00017928402,0.00029957423,0.00019704687,0.000105584506,0.00040443093,0.00015445387,5.825269e-7],"category_scores_gemma":[0.00010481387,0.00014769926,0.00006229532,0.00049989426,0.00010369847,0.0007477067,0.0020646476,0.00031904463,0.0000010305788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009683635,0.000035309047,0.002059688,0.0013524421,0.00014390497,0.000007584633,0.005079534,0.9504946,0.0005086615,0.017009811,0.0003133826,0.022898274],"study_design_scores_gemma":[0.00033472662,0.00005607482,0.00977891,0.000098962664,0.000020778303,0.0000050344606,0.00028513875,0.9822691,0.0006688188,0.00627465,0.000055167486,0.00015263632],"about_ca_topic_score_codex":0.00011008763,"about_ca_topic_score_gemma":0.00009002114,"teacher_disagreement_score":0.8204848,"about_ca_system_score_codex":0.00017036253,"about_ca_system_score_gemma":0.00007040907,"threshold_uncertainty_score":0.6023001},"labels":[],"label_agreement":null},{"id":"W4319660509","doi":"10.1016/j.eswa.2023.119655","title":"Rule-based fuzzy neural networks realized with the aid of linear function Prototype-driven fuzzy clustering and layer Reconstruction-based network design strategy","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":7,"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":"Fuzzy clustering; Fuzzy logic; Centroid; Computer science; Cluster analysis; Euclidean distance; Neuro-fuzzy; Artificial neural network; Data mining; Artificial intelligence; Fuzzy classification; Fuzzy number; Defuzzification; Mathematics; Fuzzy set; Pattern recognition (psychology); Fuzzy control system","score_opus":0.035932059205595356,"score_gpt":0.2865825160744831,"score_spread":0.25065045686888776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319660509","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":[0.0009007388,0.00020706172,0.99442834,0.00048906123,0.00010267566,0.003350201,0.0000045877296,0.00040735002,0.00010997848],"genre_scores_gemma":[0.8126925,0.000021950294,0.17502987,0.00010748202,0.00050109724,0.011406447,0.00003093163,0.000076490775,0.00013317459],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978867,0.0002761973,0.0003630368,0.0005831672,0.00042071278,0.0004701707],"domain_scores_gemma":[0.99796027,0.00042818213,0.00026666868,0.0009217366,0.00028465132,0.00013849945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047685156,0.00024726434,0.00029427907,0.00013795441,0.00058219087,0.00016303861,0.00053254847,0.00009829895,0.0000017720578],"category_scores_gemma":[0.0000085783395,0.00016540913,0.000038364506,0.0015199875,0.00020604543,0.00023914334,0.00009620071,0.0002581781,0.0000063964058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022793341,0.000019275694,0.00019324372,0.00005456285,0.000034730798,0.0000029803869,0.00008726514,0.98765475,0.00025738316,0.00047400256,0.00012489012,0.010869005],"study_design_scores_gemma":[0.0009098827,0.00040454138,0.00024523906,0.00012663027,0.000010247025,0.00003771319,0.00016136587,0.99708176,0.00008439438,0.000068762856,0.00066366565,0.0002058138],"about_ca_topic_score_codex":0.00015628159,"about_ca_topic_score_gemma":0.00004282815,"teacher_disagreement_score":0.81939846,"about_ca_system_score_codex":0.00006545617,"about_ca_system_score_gemma":0.0001773563,"threshold_uncertainty_score":0.6745189},"labels":[],"label_agreement":null},{"id":"W4320007135","doi":"10.18280/mmep.090622","title":"Block-Based K-Medoids Partitioning Method with Standardized Data to Improve Clustering Accuracy","year":2022,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medoid; Cluster analysis; Block (permutation group theory); Computer science; k-medoids; Data mining; Algorithm; Correlation clustering; CURE data clustering algorithm; Pattern recognition (psychology); Mathematics; Artificial intelligence","score_opus":0.055049099934319605,"score_gpt":0.304892631881267,"score_spread":0.24984353194694736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320007135","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":[0.0015208329,0.000063518666,0.9969485,0.0005187256,0.000072981515,0.0004190152,0.000023481096,0.00039529928,0.000037656864],"genre_scores_gemma":[0.13582452,0.000003105274,0.86374485,0.000049003767,0.000028981776,0.00025224514,0.0000071771337,0.000041249597,0.000048870304],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977189,0.000057919904,0.00032816594,0.0007078114,0.0006320441,0.0005551654],"domain_scores_gemma":[0.99809533,0.00050034194,0.000056238234,0.0010380397,0.00006106256,0.00024900254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001313722,0.00022792954,0.0003091984,0.00016450476,0.00033976347,0.00029246658,0.0010179003,0.00003345562,0.000009053847],"category_scores_gemma":[0.00012347967,0.00020788614,0.00002848347,0.00046081256,0.00001995198,0.00034395492,0.0016096273,0.00042970726,0.0000039786155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014782829,0.000033498727,6.6155457e-7,0.0002495631,0.00002015665,0.000011954063,0.0004485154,0.99331826,0.00097532646,0.0011451734,0.00000955234,0.0037725794],"study_design_scores_gemma":[0.0004670879,0.0001956856,5.2145566e-7,0.00014340758,0.000009680561,0.000052552245,0.000026087617,0.9959164,0.0004425522,0.0013392805,0.0011165596,0.00029016242],"about_ca_topic_score_codex":0.000012234606,"about_ca_topic_score_gemma":6.480831e-7,"teacher_disagreement_score":0.13430369,"about_ca_system_score_codex":0.00009764108,"about_ca_system_score_gemma":0.00006316728,"threshold_uncertainty_score":0.8477351},"labels":[],"label_agreement":null},{"id":"W4323896842","doi":"10.1109/tbdata.2023.3255003","title":"Approximate Clustering Ensemble Method for Big Data","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Disjoint sets; Big data; Correlation clustering; Data mining; Component (thermodynamics); Cluster (spacecraft); Artificial intelligence; Mathematics; Combinatorics","score_opus":0.3223194882196442,"score_gpt":0.40855782386772044,"score_spread":0.08623833564807626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323896842","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":[0.000027131908,0.00002267105,0.9919521,0.0010292026,0.0034740928,0.00050481904,0.0021749793,0.00072843005,0.00008653119],"genre_scores_gemma":[0.012512303,0.00021687409,0.98350835,0.00019174349,0.00061895564,0.00020418725,0.00060568424,0.000085204396,0.0020567265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968954,0.00011629894,0.00032595257,0.0014279581,0.00052342797,0.0007109929],"domain_scores_gemma":[0.9923183,0.0006626186,0.000067871035,0.0066926153,0.00008279897,0.00017582893],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0014296513,0.00023312964,0.00025445168,0.00040706282,0.00045593447,0.00028688493,0.0064266487,0.000095419186,0.0000036500642],"category_scores_gemma":[0.00006414986,0.00023470646,0.000051869913,0.0013412362,0.000049327806,0.0011139091,0.00037285726,0.0003228488,0.00017148569],"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":[0.000027028322,0.00006260298,1.3618165e-7,0.00007701516,0.000044798955,0.000016329592,0.00009016671,0.019021807,0.003919291,0.00002023402,0.002516015,0.9742046],"study_design_scores_gemma":[0.0005331994,0.00007432282,0.000004529643,0.000039797535,0.00001456356,0.000030896474,0.000026228246,0.9536978,0.007975087,0.0003906713,0.036959633,0.00025329704],"about_ca_topic_score_codex":0.00007104708,"about_ca_topic_score_gemma":0.00023800308,"teacher_disagreement_score":0.9739513,"about_ca_system_score_codex":0.000064243446,"about_ca_system_score_gemma":0.00013509406,"threshold_uncertainty_score":0.99894905},"labels":[],"label_agreement":null},{"id":"W4360979800","doi":"10.1007/s00453-023-01113-3","title":"Preface to the Special Issue on the 17th Algorithms and Data Structures Symposium (WADS 2021)","year":2023,"lang":"en","type":"article","venue":"Algorithmica","topic":"Advanced Clustering Algorithms Research","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":"University of Alberta; University of Waterloo; Dalhousie University","funders":"Division of Mathematical Sciences; Dalhousie University; Fields Institute for Research in Mathematical Sciences; Pacific Institute for the Mathematical Sciences","keywords":"Theory of computation; Computer science; Algorithm; Data science","score_opus":0.04072615141270493,"score_gpt":0.3320292424290909,"score_spread":0.29130309101638596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360979800","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":[0.0060076443,0.0004015922,0.52549356,0.43969986,0.00947975,0.00474186,0.00080018275,0.0014133923,0.011962175],"genre_scores_gemma":[0.063608535,0.0037876922,0.658513,0.024067182,0.15522365,0.0016223588,0.00064935506,0.0008985656,0.09162966],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963492,0.0002443983,0.00029356848,0.0012105352,0.0010615893,0.00084068946],"domain_scores_gemma":[0.99522257,0.00086934346,0.000075925054,0.0034810808,0.00010968514,0.0002413743],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011072744,0.00032267658,0.00024763597,0.00017653902,0.0007561496,0.0006493942,0.0056659123,0.00009326141,0.000106720705],"category_scores_gemma":[0.0003132476,0.00019135047,0.000047425336,0.0015203526,0.00019604,0.00044724476,0.005715918,0.0005830028,0.0010838361],"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":[0.00001843824,0.00002980594,0.000007824448,0.000014509103,0.00006398911,0.000076455064,0.0018115432,0.002002683,0.0002290347,0.00419736,0.18519469,0.8063537],"study_design_scores_gemma":[0.00028262415,0.00021911236,0.0010235626,0.000028354485,0.000010288703,0.000047163274,0.0002601177,0.39202297,0.00170388,0.0036553568,0.6003704,0.0003761548],"about_ca_topic_score_codex":0.0000748991,"about_ca_topic_score_gemma":0.000020563646,"teacher_disagreement_score":0.8059775,"about_ca_system_score_codex":0.00007047262,"about_ca_system_score_gemma":0.00010566287,"threshold_uncertainty_score":0.9997139},"labels":[],"label_agreement":null},{"id":"W4375858861","doi":"10.32473/flairs.36.133230","title":"Biogeography-based optimization for feature selection","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Cluster analysis; Data mining; Computer science; Cluster (spacecraft); Selection (genetic algorithm); Feature selection; Biogeography; Feature (linguistics); Machine learning; Artificial intelligence; Ecology; Biology","score_opus":0.13065043082825348,"score_gpt":0.38871743987603846,"score_spread":0.258067009047785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375858861","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":[0.009455058,0.000017718798,0.97035784,0.017142462,0.0009523315,0.0010153692,0.000050630963,0.0003057502,0.00070282444],"genre_scores_gemma":[0.7509341,0.00017019153,0.24669243,0.00013735163,0.0005785044,0.0005112389,0.000029575096,0.000041813757,0.0009047543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99645764,0.000028244674,0.00039192813,0.0006402828,0.0018130054,0.0006688824],"domain_scores_gemma":[0.99369574,0.000523844,0.00018207781,0.00023419429,0.0052504805,0.00011365754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024156729,0.00018232121,0.00018371434,0.00039032908,0.0006222587,0.00060361385,0.0033431596,0.000147894,0.000025702335],"category_scores_gemma":[0.0012980569,0.000153489,0.0003141644,0.0037113565,0.00039629015,0.0007351465,0.0008564305,0.0005657099,0.000020449308],"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":[0.00022001012,0.00025436762,0.0013469037,0.0003557919,0.00024176297,9.339437e-7,0.0023281693,0.15230006,0.16488247,0.57057273,0.016716104,0.09078072],"study_design_scores_gemma":[0.000046346864,0.00008612353,0.000082691484,0.0000707466,0.000002643204,0.0000011781431,0.0004667092,0.76033014,0.19914109,0.038951255,0.00070255896,0.0001185114],"about_ca_topic_score_codex":0.000045486653,"about_ca_topic_score_gemma":0.000005800894,"teacher_disagreement_score":0.7414791,"about_ca_system_score_codex":0.00022999075,"about_ca_system_score_gemma":0.0003421664,"threshold_uncertainty_score":0.62591},"labels":[],"label_agreement":null},{"id":"W4375869758","doi":"10.48550/arxiv.1907.01136","title":"Finding Outliers in Gaussian Model-Based Clustering","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Outlier; Cluster analysis; Gaussian; Computer science; Mixture model; Pattern recognition (psychology); Artificial intelligence; Statistics; Econometrics; Mathematics; Data mining; Physics","score_opus":0.10265674291270344,"score_gpt":0.2399083167034491,"score_spread":0.13725157379074565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375869758","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":[0.053008735,0.000024098134,0.9434557,0.00011632438,0.00048620385,0.00043203187,0.000009545909,0.0002494962,0.0022178784],"genre_scores_gemma":[0.96437156,0.000027427173,0.033538677,0.00007448226,0.00003277198,0.0000026387024,0.000008808257,0.000039348633,0.0019042863],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969784,0.00014735751,0.0002713679,0.0016035956,0.0002060842,0.0007931829],"domain_scores_gemma":[0.9975037,0.00013396994,0.00019616493,0.0018509168,0.00009190318,0.00022333559],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004154032,0.0004022283,0.0004462003,0.0008734269,0.00012140046,0.00019031948,0.0030394811,0.00035907197,0.00000987588],"category_scores_gemma":[0.000048770027,0.0005070314,0.00018394334,0.00087129325,0.00009608081,0.00051613624,0.004231671,0.0012697983,0.00010009005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002387364,0.000040667812,0.0010071441,0.0001381818,0.00001639204,0.00034965857,0.0002231544,0.993827,0.000026984964,0.0031065478,0.000012946079,0.0012274532],"study_design_scores_gemma":[0.0007371702,0.00003311237,0.00033309532,0.00025215588,0.0000075500143,0.0000021457195,0.00004935201,0.9915909,0.00007993886,0.0063625667,0.000035965586,0.0005160319],"about_ca_topic_score_codex":0.00011472354,"about_ca_topic_score_gemma":0.00009395246,"teacher_disagreement_score":0.9113628,"about_ca_system_score_codex":0.0010284279,"about_ca_system_score_gemma":0.0005089207,"threshold_uncertainty_score":0.99973816},"labels":[],"label_agreement":null},{"id":"W4377249775","doi":"10.1007/978-3-031-33271-5_19","title":"Interpretable Clustering via Soft Clustering Trees","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"University of Toronto","funders":"","keywords":"Cluster analysis; Computer science; Interpretability; Constrained clustering; Correlation clustering; Artificial intelligence; Data mining; CURE data clustering algorithm; Fuzzy clustering; Brown clustering; Conceptual clustering; Machine learning; Consensus clustering; Partition (number theory); Pattern recognition (psychology); Mathematics","score_opus":0.025300078755108986,"score_gpt":0.2867354810263392,"score_spread":0.26143540227123024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377249775","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":[0.000011388324,0.00021343211,0.99162054,0.0005354758,0.003496115,0.0005351475,0.000006748957,0.0009089608,0.0026721791],"genre_scores_gemma":[0.04789105,0.00012861965,0.9413759,0.00091981393,0.0011492831,0.00006373769,0.000010150626,0.00025856658,0.008202887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928058,0.000055149223,0.0008703488,0.0026897707,0.0018673555,0.0017115779],"domain_scores_gemma":[0.995515,0.00091369974,0.00032643724,0.0025454299,0.00031555918,0.00038389213],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0013946517,0.00089724147,0.00089174137,0.0017981394,0.00048102392,0.0011967004,0.006874169,0.00044875834,0.00003252057],"category_scores_gemma":[0.00021721485,0.0008963079,0.00022712808,0.001369835,0.0007981681,0.0014024551,0.009660272,0.0017022381,0.00026654365],"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":[0.000007703464,0.000011795776,0.0000065935337,0.000063713494,0.000015223425,0.00024841016,0.000552229,0.32385975,0.00034422794,0.0002927563,0.000008739163,0.67458886],"study_design_scores_gemma":[0.0002716456,0.00018103087,0.000034942386,0.00080991234,0.0000051913785,0.00017986081,3.5839312e-7,0.95474607,0.00050293066,0.041722376,0.00065748696,0.00088819914],"about_ca_topic_score_codex":0.00007337851,"about_ca_topic_score_gemma":0.00064356206,"teacher_disagreement_score":0.67370063,"about_ca_system_score_codex":0.00083587616,"about_ca_system_score_gemma":0.000480482,"threshold_uncertainty_score":0.99984014},"labels":[],"label_agreement":null},{"id":"W4378087396","doi":"10.3390/app13106342","title":"VSFCM: A Novel Viewpoint-Driven Subspace Fuzzy C-Means Algorithm","year":2023,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"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":"Anhui Provincial Key Research and Development Plan; National Key Research and Development Program of China; Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Initialization; Cluster analysis; Computer science; Subspace topology; Fuzzy clustering; Data mining; Pattern recognition (psychology); Correlation clustering; Algorithm; Artificial intelligence; Fuzzy logic","score_opus":0.04843435855030365,"score_gpt":0.31999287265577925,"score_spread":0.2715585141054756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378087396","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":[0.002437109,0.00005035298,0.9749071,0.0040581655,0.0004734029,0.0003864281,0.000008676337,0.0010576867,0.016621077],"genre_scores_gemma":[0.07693704,0.000087803244,0.9196597,0.00072335964,0.0002530825,0.00020916932,0.0000055507608,0.000033669367,0.0020906671],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99618274,0.00003785696,0.0002849085,0.001081286,0.0013270739,0.0010861284],"domain_scores_gemma":[0.99850255,0.00031161756,0.00010048629,0.0007472918,0.00008720831,0.00025082994],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001252437,0.00024310796,0.00026185825,0.00044323085,0.0007417726,0.00044880676,0.00311907,0.000078460725,0.000014390977],"category_scores_gemma":[0.00006938929,0.0002128048,0.00007464713,0.004798206,0.0005755863,0.00065591256,0.001401592,0.00028591932,0.0012523946],"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":[0.0000068600793,0.00015955514,0.00008384945,0.000047921338,0.000037793554,0.00008987837,0.0033688548,0.031251967,0.048825156,0.21528165,0.004001438,0.69684505],"study_design_scores_gemma":[0.00051693537,0.00013330953,0.00078593846,0.000028152963,0.0000035120113,0.000038965194,0.00055469543,0.9630873,0.004591187,0.017102502,0.012623853,0.00053361384],"about_ca_topic_score_codex":0.00003156327,"about_ca_topic_score_gemma":0.000016964266,"teacher_disagreement_score":0.93183535,"about_ca_system_score_codex":0.00007799427,"about_ca_system_score_gemma":0.00021415408,"threshold_uncertainty_score":0.99952525},"labels":[],"label_agreement":null},{"id":"W4384438355","doi":"10.1007/s10489-023-04827-7","title":"A three-way adaptive density peak clustering (3W-ADPC) method","year":2023,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Advanced Clustering Algorithms Research","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":"","keywords":"Cluster analysis; Computer science; Cluster (spacecraft); Process (computing); Algorithm; Data mining; Boundary (topology); Correlation clustering; Artificial intelligence; Mathematics","score_opus":0.06696534723128361,"score_gpt":0.3432592515649392,"score_spread":0.2762939043336556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384438355","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":[0.0006228261,0.000038620296,0.99311864,0.0002904807,0.00032747892,0.0004398271,0.0000023165576,0.0010234967,0.004136294],"genre_scores_gemma":[0.25092784,0.00005523944,0.7479633,0.00026170802,0.00013677799,0.00017027419,0.0000035532717,0.000045976583,0.00043533993],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99675375,0.000066320885,0.00039342412,0.0010695186,0.00076049264,0.0009564801],"domain_scores_gemma":[0.9976096,0.00062004756,0.00011111625,0.0012452143,0.00016759634,0.00024638054],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010826621,0.0003109666,0.0003310631,0.00030607,0.00032927305,0.00019126794,0.0021811877,0.000121778954,0.000031923893],"category_scores_gemma":[0.00011839216,0.00031107303,0.000096615055,0.0020827584,0.00013216694,0.00048595894,0.0025872919,0.0005312378,0.0020750652],"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":[0.000037406546,0.000033264518,0.000013313303,0.000031765463,0.00003680124,0.00010717437,0.0013189461,0.023472939,0.005925154,0.066582695,0.00025192648,0.9021886],"study_design_scores_gemma":[0.00008776103,0.000084788226,0.00050061126,0.000028597895,0.000004049185,0.00003847302,0.0002570507,0.91195405,0.03650697,0.04929131,0.00085801113,0.00038833648],"about_ca_topic_score_codex":0.0001296193,"about_ca_topic_score_gemma":0.00008120699,"teacher_disagreement_score":0.9018003,"about_ca_system_score_codex":0.00017009363,"about_ca_system_score_gemma":0.000084375184,"threshold_uncertainty_score":0.99993414},"labels":[],"label_agreement":null},{"id":"W4384937323","doi":"10.1016/j.neucom.2023.126547","title":"On k-means iterations and Gaussian clusters","year":2023,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Innovate UK; Royal Society","keywords":"Cluster analysis; Computer science; Set (abstract data type); k-means clustering; Algorithm; Gaussian; Data set; Data mining; Determining the number of clusters in a data set; Pattern recognition (psychology); Correlation clustering; Artificial intelligence; CURE data clustering algorithm","score_opus":0.02419776443647915,"score_gpt":0.3013819124988729,"score_spread":0.2771841480623938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384937323","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":[0.095371336,0.000007347748,0.8973298,0.0034736204,0.00036634374,0.00020184077,0.0000012030727,0.000951862,0.0022966214],"genre_scores_gemma":[0.9472908,0.000007486073,0.050980248,0.00094091473,0.00013927181,0.000013552203,0.0000023689347,0.000025897853,0.0005994582],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871105,0.000066628265,0.0001432697,0.00043601886,0.00026619542,0.00037681093],"domain_scores_gemma":[0.9991041,0.00037769068,0.000034604145,0.00034415218,0.000028687124,0.00011080503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019022501,0.00010951926,0.0000931899,0.00022949983,0.00034039913,0.00025619662,0.00041774003,0.000027811202,0.0000016101628],"category_scores_gemma":[0.0000931241,0.00010847599,0.00002543611,0.0007445742,0.000031669806,0.00022120772,0.0005956709,0.0002142871,0.00012241212],"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":[0.000009743366,0.00005904935,0.00035683217,0.000076218144,0.00001793665,0.00044557895,0.0034685114,0.24353182,0.002720138,0.054410875,0.0019837734,0.6929195],"study_design_scores_gemma":[0.00019321706,0.00007771552,0.0029009797,0.000026426793,5.862894e-7,0.000028971837,0.00001723245,0.99351674,0.00013851225,0.0018808333,0.0011116075,0.000107173604],"about_ca_topic_score_codex":0.0000029731036,"about_ca_topic_score_gemma":0.000001141993,"teacher_disagreement_score":0.8519195,"about_ca_system_score_codex":0.000021912207,"about_ca_system_score_gemma":0.000018354709,"threshold_uncertainty_score":0.44235227},"labels":[],"label_agreement":null},{"id":"W4385232475","doi":"10.1109/tpami.2023.3298629","title":"Knowledge-Induced Multiple Kernel Fuzzy Clustering","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Cluster analysis; Fuzzy clustering; Computer science; Data mining; Artificial intelligence; Fuzzy logic; Knowledge extraction; Kernel (algebra); Domain knowledge; Correlation clustering; Data stream clustering; Pattern recognition (psychology); CURE data clustering algorithm; Machine learning; Mathematics","score_opus":0.050388673218625786,"score_gpt":0.3325815652432935,"score_spread":0.28219289202466774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385232475","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":[0.0054591573,0.00004653858,0.9931574,0.00031557,0.00032229768,0.00014757992,0.000016462282,0.00039515636,0.00013984246],"genre_scores_gemma":[0.99535686,0.0002632869,0.003313513,0.00010786125,0.000029151954,0.00005370545,0.0000040273276,0.00002209608,0.00084947166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789953,0.000108428976,0.00037871246,0.0007634001,0.0003652181,0.0004847268],"domain_scores_gemma":[0.99851114,0.00035035002,0.00007017523,0.00074611173,0.000103609964,0.00021862076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036587403,0.00026222933,0.0003392578,0.0010971138,0.00034157268,0.00019479258,0.0007602882,0.00007904584,0.000038863727],"category_scores_gemma":[0.000015041175,0.0002445687,0.00023676641,0.0032314993,0.000055324814,0.00040705828,0.00004007398,0.000403095,0.00031321959],"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":[0.000006830305,0.00008163256,0.00014412437,0.000023037028,0.00024197211,0.00002579441,0.0005831296,0.08465973,0.0012403415,0.000011579665,0.0000041694707,0.91297764],"study_design_scores_gemma":[0.00011392908,0.00009196986,0.00092702085,0.000022972332,0.00006721761,0.000010752265,0.00006883255,0.93827754,0.05994895,0.000148445,0.00006202668,0.0002603573],"about_ca_topic_score_codex":0.0007286051,"about_ca_topic_score_gemma":0.0015322365,"teacher_disagreement_score":0.9898977,"about_ca_system_score_codex":0.00006739905,"about_ca_system_score_gemma":0.000026551337,"threshold_uncertainty_score":0.99732226},"labels":[],"label_agreement":null},{"id":"W4385768263","doi":"10.24963/ijcai.2023/225","title":"Optimal Decision Trees For Interpretable Clustering with Constraints","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"Vector Institute; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Cluster analysis; Interpretability; Constrained clustering; Computer science; Conceptual clustering; Data mining; Artificial intelligence; Machine learning; Correlation clustering; CURE data clustering algorithm","score_opus":0.02759134347042677,"score_gpt":0.32498078392234264,"score_spread":0.29738944045191584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385768263","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":[0.008974811,0.00000667875,0.98832786,0.00025329317,0.00014464394,0.0002764096,0.0000036065849,0.0005413124,0.0014713705],"genre_scores_gemma":[0.23648278,0.0000050412464,0.7613086,0.000047090987,0.000028095908,0.00007232095,0.0000021365065,0.000015627249,0.002038326],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998639,0.0000145945705,0.00015471064,0.00041615518,0.0002993438,0.0004761873],"domain_scores_gemma":[0.9989077,0.00042450015,0.000028837374,0.00042933412,0.00010032514,0.00010933475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030019385,0.00011984942,0.00014248767,0.00017820107,0.00013352424,0.00020090482,0.0007586493,0.000035836674,0.000025663685],"category_scores_gemma":[0.00008876282,0.00009147217,0.000039773502,0.0005541965,0.00008609347,0.0005020284,0.00062967266,0.00008883191,0.000090767855],"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":[0.00009606812,0.00002395257,0.000061512714,0.000027367183,0.000027556493,0.00005551075,0.0004527439,0.15055539,0.0013791646,0.0020960022,0.00091729156,0.8443074],"study_design_scores_gemma":[0.0005713517,0.0002318264,0.00021621819,0.000054616634,0.0000012441044,0.000039194987,0.00011109075,0.99535024,0.0014913189,0.0005297547,0.0012599516,0.00014319197],"about_ca_topic_score_codex":0.0000063128496,"about_ca_topic_score_gemma":0.000025463421,"teacher_disagreement_score":0.84479487,"about_ca_system_score_codex":0.000046071207,"about_ca_system_score_gemma":0.00005711453,"threshold_uncertainty_score":0.37301266},"labels":[],"label_agreement":null},{"id":"W4385832543","doi":"10.1007/978-3-031-39821-6_28","title":"Subspace Clustering Technique Using Multi-objective Functions for Multi-class Categorical Data","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"Concordia University","funders":"","keywords":"Cluster analysis; Computer science; Categorical variable; Data mining; CURE data clustering algorithm; Correlation clustering; Fuzzy clustering; Clustering high-dimensional data; Entropy (arrow of time); Artificial intelligence; Class (philosophy); Pattern recognition (psychology); Subspace topology; Data stream clustering; Machine learning","score_opus":0.1494450529088616,"score_gpt":0.3744778443600943,"score_spread":0.2250327914512327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385832543","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":[0.000005137924,0.00012076118,0.99455726,0.00030441256,0.0024242233,0.0018164708,0.00008571025,0.0006244136,0.000061592866],"genre_scores_gemma":[0.0027830412,0.0000211881,0.9949578,0.00012528179,0.0004820544,0.00011897092,0.000038667404,0.00013027288,0.0013427193],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934358,0.00007085139,0.0006528588,0.003316471,0.0011599327,0.0013640873],"domain_scores_gemma":[0.9940539,0.0011219878,0.00032163347,0.0035877405,0.00061039807,0.00030433043],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0017875845,0.00074496237,0.0007296997,0.0014616337,0.0007608847,0.0007101475,0.0073141796,0.0005248633,0.0000027093372],"category_scores_gemma":[0.0006189643,0.0007435839,0.0001549736,0.0015419632,0.0007836796,0.0012917357,0.009865188,0.001515809,0.000037595655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003087067,0.00013300804,0.000019685112,0.00025303115,0.00006960675,0.00036819413,0.0008135913,0.64378464,0.002528592,0.0015337389,0.000035172103,0.35042986],"study_design_scores_gemma":[0.000519464,0.00014068092,0.000029853718,0.00026862297,0.000012086122,0.00020274297,0.0000011708877,0.9921186,0.0008636048,0.0046543474,0.0004007683,0.00078806747],"about_ca_topic_score_codex":0.00013201286,"about_ca_topic_score_gemma":0.0006564335,"teacher_disagreement_score":0.3496418,"about_ca_system_score_codex":0.0011879934,"about_ca_system_score_gemma":0.0010802349,"threshold_uncertainty_score":0.9995015},"labels":[],"label_agreement":null},{"id":"W4386124589","doi":"10.2139/ssrn.4551320","title":"Approximation Schemes for Min-Sum K-Clustering","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Clustering Algorithms Research","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":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Mathematics; Combinatorics; Statistics","score_opus":0.04373845239734463,"score_gpt":0.33118047490163116,"score_spread":0.2874420225042865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386124589","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":[0.0010812167,0.0012392973,0.9929864,0.0021706142,0.0014231256,0.0006398658,0.000007517959,0.00037701725,0.00007499309],"genre_scores_gemma":[0.114492424,0.008918988,0.84677684,0.00016108066,0.0041010464,0.0009728307,0.00009584744,0.0004340365,0.024046883],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941625,0.00010464338,0.00055637467,0.00079905835,0.00073483284,0.0036425872],"domain_scores_gemma":[0.9980608,0.00019188531,0.0004073015,0.000838125,0.00034903878,0.00015284667],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0031677105,0.00037264585,0.00040620132,0.00046613274,0.0003956751,0.0006346451,0.0026598317,0.000273606,0.0000020689604],"category_scores_gemma":[0.0002933561,0.0003757614,0.0002939404,0.00033083287,0.00004698168,0.00049490354,0.002456627,0.004399025,0.000048406604],"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":[0.00008362524,0.000112137335,0.000037070145,0.0006447636,0.0006887741,0.000028051358,0.0007690576,0.033101,0.0008228961,0.13890743,0.0003817214,0.8244235],"study_design_scores_gemma":[0.000469479,0.00016059072,0.000014758147,0.00014345262,0.000013186443,0.00020581546,0.00015769254,0.48515144,0.00030247626,0.5110181,0.0019990064,0.00036401334],"about_ca_topic_score_codex":0.000023108976,"about_ca_topic_score_gemma":0.00013950333,"teacher_disagreement_score":0.8240595,"about_ca_system_score_codex":0.0022825105,"about_ca_system_score_gemma":0.0034346578,"threshold_uncertainty_score":0.9998694},"labels":[],"label_agreement":null},{"id":"W4386283145","doi":"10.18280/mmep.100420","title":"Performance Evaluation of Some Clustering Algorithms under Different Validity Indices","year":2023,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Computer science; Algorithm; Data mining; Artificial intelligence","score_opus":0.12362484919823169,"score_gpt":0.3054019343034031,"score_spread":0.18177708510517143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386283145","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":[0.35935003,0.000054999604,0.6400937,0.000045128847,0.00007223682,0.00015213806,7.961885e-7,0.00020535913,0.000025615787],"genre_scores_gemma":[0.9292715,0.00012583473,0.07042907,0.0000032496273,0.000036735088,0.00007019936,0.00000226439,0.000021522457,0.000039579405],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981986,0.00003627137,0.0003263088,0.00031389127,0.00074727746,0.00037764298],"domain_scores_gemma":[0.9992118,0.00020382155,0.000059763977,0.00032634477,0.00009244125,0.00010581695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012637096,0.000170914,0.00024885772,0.00021153534,0.00008232903,0.000079399004,0.00033315382,0.00006954613,0.0000029174264],"category_scores_gemma":[0.000045091263,0.00014758135,0.000039618473,0.0003344398,0.000033175736,0.00036954504,0.0003316586,0.00018357618,0.000012969033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.8784293e-7,0.000021748623,0.000010292325,0.00049518765,0.000013491407,5.2535387e-7,0.00049925694,0.9888915,0.00042004086,0.0016980753,8.5364417e-7,0.007948147],"study_design_scores_gemma":[0.00022666036,0.000053552845,0.00018194207,0.0002803712,0.000010896434,0.0000068146483,0.000014785544,0.98273087,0.00094040245,0.015392126,0.0000031847394,0.00015839942],"about_ca_topic_score_codex":0.0000030196288,"about_ca_topic_score_gemma":1.1544656e-7,"teacher_disagreement_score":0.56992155,"about_ca_system_score_codex":0.000054359218,"about_ca_system_score_gemma":0.000018442704,"threshold_uncertainty_score":0.6018193},"labels":[],"label_agreement":null},{"id":"W4386846972","doi":"10.14293/p2199-8442.1.sop-.pquwpp.v1","title":"A study on density based spatial clustering of applications with noise","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"DBSCAN; Cluster analysis; Computer science; Outlier; Noise (video); Data mining; Pattern recognition (psychology); Presentation (obstetrics); Artificial intelligence; Image (mathematics); Correlation clustering; CURE data clustering algorithm","score_opus":0.0700196497098633,"score_gpt":0.34811029555545936,"score_spread":0.27809064584559606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386846972","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":[0.009230902,0.0000019841148,0.98776734,0.00026781295,0.00012682173,0.0017720591,0.000010317313,0.00046683275,0.00035594436],"genre_scores_gemma":[0.7703806,0.0000012299051,0.22834781,0.000034281325,0.00006513458,0.0007267066,0.0000075594116,0.00003705766,0.00039963317],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974784,0.00010256168,0.00031370722,0.0009518562,0.00084397505,0.0003094857],"domain_scores_gemma":[0.99708027,0.0002362833,0.00017296722,0.0021244409,0.0002710233,0.000115005896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037056318,0.00025612544,0.00036123223,0.000320564,0.00010043527,0.00011147218,0.0016564899,0.00009572509,0.000004132172],"category_scores_gemma":[0.000034892728,0.00021765003,0.00006690766,0.00045572332,0.00006183455,0.00006817988,0.003497661,0.0005560218,0.000049312643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014618436,0.001520152,0.0040863687,0.00047630715,0.00018448077,0.00020490025,0.0012193505,0.9289686,0.00028524263,0.00039575965,0.000048231894,0.0624644],"study_design_scores_gemma":[0.0007192799,0.00060064875,0.022104142,0.00014343759,0.000013382645,0.0000034197108,0.00012180987,0.97381705,0.0016329701,0.0004636993,0.000026313275,0.00035384778],"about_ca_topic_score_codex":0.0007522313,"about_ca_topic_score_gemma":0.0006889866,"teacher_disagreement_score":0.7611497,"about_ca_system_score_codex":0.00012859463,"about_ca_system_score_gemma":0.00026586096,"threshold_uncertainty_score":0.88755107},"labels":[],"label_agreement":null},{"id":"W4387790211","doi":"10.2139/ssrn.4602038","title":"Parsimonious Bayesian Model-Based Clustering with Dissimilarities","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","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":"University of Manitoba","funders":"","keywords":"Cluster analysis; Bayesian probability; Computer science; Artificial intelligence; Econometrics; Data mining; Statistics; Mathematics","score_opus":0.025785571967865857,"score_gpt":0.2935396233393311,"score_spread":0.26775405137146524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387790211","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":[0.00091120426,0.00071455527,0.9937561,0.0030407573,0.0004707643,0.00034493522,0.000014541788,0.000589312,0.00015783026],"genre_scores_gemma":[0.768192,0.0026985097,0.2228821,0.00018420076,0.00062241545,0.0001664407,0.000027898059,0.00029943898,0.0049269754],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9921095,0.00018691021,0.00054071273,0.0010275345,0.0012660993,0.004869271],"domain_scores_gemma":[0.9975731,0.0001413458,0.0003638956,0.0013314176,0.00027986232,0.0003103828],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001970081,0.00059403706,0.00056984514,0.00056625303,0.0005473869,0.0008958422,0.0034869062,0.00030450072,0.000002635146],"category_scores_gemma":[0.00007149052,0.00052580377,0.0002379933,0.00046254424,0.00014359466,0.0004547293,0.0021324316,0.008623779,0.00001320533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054908676,0.00004597559,0.00006862401,0.00010131877,0.00018471495,0.00014255788,0.00023294908,0.9635465,0.000011329304,0.0057989825,0.000037266575,0.02977488],"study_design_scores_gemma":[0.00048369734,0.0002494438,0.000020778898,0.00026722293,0.00001829399,0.00025836148,0.00016197143,0.76214105,0.00004893261,0.23582812,0.000039793253,0.0004823287],"about_ca_topic_score_codex":0.000079079044,"about_ca_topic_score_gemma":0.0011610609,"teacher_disagreement_score":0.77087396,"about_ca_system_score_codex":0.002784204,"about_ca_system_score_gemma":0.010286387,"threshold_uncertainty_score":0.9997194},"labels":[],"label_agreement":null},{"id":"W4388305482","doi":"10.1080/00401706.2023.2262896","title":"Post-Shrinkage Strategies in Statistical and Machine Learning for High Dimensional DataPost-Shrinkage Strategies in Statistical and Machine Learning for High Dimensional Data, Syed Ejaz Ahmed, Feryaal Ahmed, and Bahadir Yüzbaşı, New York: Chapman and Hall/CRC Press, 2023, 408 pp., ISBN 9780367763442","year":2023,"lang":"en","type":"article","venue":"Technometrics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 Windsor","funders":"","keywords":"Shrinkage; Statistical learning; Statistical analysis; Computer science; Artificial intelligence; Mathematics; Machine learning; Statistics","score_opus":0.05985652472270515,"score_gpt":0.317590329561149,"score_spread":0.2577338048384439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388305482","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":[0.1703913,0.007874745,0.81400245,0.0010851617,0.00022584682,0.0020457306,0.0037797783,0.00057000533,0.000024949213],"genre_scores_gemma":[0.73952806,0.0015378195,0.25486162,0.000052020798,0.00009531171,0.000119329234,0.0032326984,0.000110837784,0.0004622873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948819,0.00017966074,0.0008396135,0.0018982029,0.0009086359,0.0012919883],"domain_scores_gemma":[0.99427205,0.004102068,0.00022413618,0.0007506054,0.0001701201,0.0004810342],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017954318,0.000628577,0.00087424985,0.0016236253,0.0005202155,0.00092986936,0.0009712747,0.0003048123,0.000016405002],"category_scores_gemma":[0.0024591994,0.00061657064,0.000028843328,0.0020554066,0.0005616774,0.0016102523,0.0036160534,0.0013513278,0.000003967665],"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":[0.0017907463,0.0007791828,0.0148131605,0.002847446,0.0003231098,0.0015229383,0.0012281113,0.020032538,0.004755553,0.33309996,0.0014415577,0.6173657],"study_design_scores_gemma":[0.004805257,0.0014294467,0.046432495,0.0001558924,0.00003794543,0.00010088672,0.00039897987,0.9223546,0.00010421828,0.02244292,0.00086388463,0.00087349664],"about_ca_topic_score_codex":0.0029756145,"about_ca_topic_score_gemma":0.00072525674,"teacher_disagreement_score":0.90232205,"about_ca_system_score_codex":0.00011389038,"about_ca_system_score_gemma":0.00031076756,"threshold_uncertainty_score":0.99962854},"labels":[],"label_agreement":null},{"id":"W4388517820","doi":"10.1109/fuzz52849.2023.10309720","title":"Incremental Cluster Validity Index for Predicting Early Signs of Change in Data Streams","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data stream mining; Cluster analysis; Outlier; Data mining; Data stream; Index (typography); Change detection; STREAMS; Cluster (spacecraft); Artificial intelligence","score_opus":0.3202045578532634,"score_gpt":0.4126508453781036,"score_spread":0.09244628752484019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388517820","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":[0.32960138,0.0000067621854,0.6685381,0.00047258992,0.00018319605,0.0007310947,0.00009523696,0.00020894209,0.00016272088],"genre_scores_gemma":[0.96506524,0.0000065061854,0.034459576,0.0000485192,0.000099160716,0.00009280033,0.00003721843,0.000013636046,0.00017732913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837595,0.00006282596,0.0002595558,0.0004704019,0.0004151821,0.0004160613],"domain_scores_gemma":[0.99855494,0.0003476388,0.0000637721,0.00090430136,0.000060911017,0.00006844406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010141204,0.00010038488,0.00015481056,0.00022962506,0.000055668603,0.000056326116,0.0016572134,0.000052386633,0.000007918776],"category_scores_gemma":[0.00016508275,0.000095118485,0.000025546931,0.0007564669,0.00003659576,0.0010909466,0.0031253616,0.00012859306,0.000011778176],"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":[0.00015460832,0.00042893132,0.32135677,0.00052637135,0.00008230709,0.00006130446,0.008090971,0.0027199073,0.0073230257,0.0013546076,0.0019244547,0.6559768],"study_design_scores_gemma":[0.0006854208,0.00017150989,0.02707445,0.000034741104,0.0000012350529,0.0000015457174,0.00010693928,0.9695589,0.0017489018,0.00039512926,0.0001120924,0.00010914553],"about_ca_topic_score_codex":0.00085634994,"about_ca_topic_score_gemma":0.00039986378,"teacher_disagreement_score":0.96683896,"about_ca_system_score_codex":0.00005698672,"about_ca_system_score_gemma":0.00004080851,"threshold_uncertainty_score":0.38955396},"labels":[],"label_agreement":null},{"id":"W4390419450","doi":"10.2478/ecce-2023-0005","title":"Optimized Centroid-Based Clustering of Dense Nearly-square Point Clouds by the Hexagonal Pattern","year":2023,"lang":"en","type":"article","venue":"Electrical Control and Communication Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Northwestern Polytechnic","funders":"","keywords":"Centroid; Cluster analysis; Euclidean distance; Hexagonal crystal system; Hexagonal lattice; Square lattice; Combinatorics; Euclidean geometry; Algorithm; Square (algebra); Unit square; Computer science; Mathematics; Partition (number theory); Data mining; Geometry; Artificial intelligence; Physics; Crystallography; Statistical physics","score_opus":0.009776132249794716,"score_gpt":0.2415935204913045,"score_spread":0.2318173882415098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390419450","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":[0.0057290546,0.0015254063,0.98901296,0.003206606,0.000036746012,0.000228026,0.000005078585,0.00023455755,0.000021556882],"genre_scores_gemma":[0.9871162,0.0001541188,0.012431854,0.00015492202,0.00001980983,0.00007289026,0.000007524324,0.000017569293,0.000025113135],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864733,0.00015990171,0.00029186028,0.00021521389,0.00031005288,0.00037561843],"domain_scores_gemma":[0.99804157,0.0009523062,0.00007798924,0.00073441915,0.00009560689,0.0000980857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005401589,0.00014165665,0.00021996775,0.00011611882,0.00016625001,0.000100303165,0.000973137,0.000053181953,0.0000028535205],"category_scores_gemma":[0.00017452544,0.00011662423,0.000066588014,0.0006843138,0.000043237735,0.00015848149,0.00031983174,0.00035513914,0.00000502147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009737775,0.000091346825,0.00019887314,0.00007156686,0.00009209712,0.000008520438,0.00050724106,0.7512808,0.019949775,0.0010842247,0.0002769804,0.22634119],"study_design_scores_gemma":[0.0012261326,0.0000718607,0.0012083598,0.000029265393,0.000005053048,0.0000073837355,0.000008287957,0.9962103,0.0006679664,0.00008559092,0.00035886848,0.00012095853],"about_ca_topic_score_codex":0.000042442472,"about_ca_topic_score_gemma":0.0000013189245,"teacher_disagreement_score":0.98138714,"about_ca_system_score_codex":0.000057820853,"about_ca_system_score_gemma":0.000035456596,"threshold_uncertainty_score":0.4755798},"labels":[],"label_agreement":null},{"id":"W4390444745","doi":"10.18280/ts.400626","title":"Enhanced Cross-Validation Methods Leveraging Clustering Techniques","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Computer science; Cross-validation; Data mining; Artificial intelligence","score_opus":0.060675995641990804,"score_gpt":0.4088140946180655,"score_spread":0.34813809897607473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390444745","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":[0.01660023,0.000013262759,0.9801568,0.00032008052,0.0002088174,0.0003093621,0.0000019667566,0.0014364873,0.00095304096],"genre_scores_gemma":[0.43385834,0.00001604946,0.5651343,0.000100494726,0.00015927834,0.00015188998,0.000009801478,0.000025231655,0.00054463005],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99775755,0.00019314374,0.00035953318,0.00055934006,0.0005574186,0.00057298486],"domain_scores_gemma":[0.99902093,0.00021600822,0.0000899118,0.0004272664,0.0001335245,0.00011234237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016641616,0.00018779344,0.00018267996,0.00031987173,0.00027868315,0.00041450272,0.00091766694,0.000059442293,0.00007587608],"category_scores_gemma":[0.000060585524,0.0001924066,0.00007323067,0.0009257982,0.00005631044,0.0008813514,0.0007154077,0.00020156542,0.000097760974],"study_design_candidate":"bench_or_experimental","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":[0.00001192396,0.0000266659,0.000039292165,0.000046338773,0.000020345891,0.000023205568,0.0010328728,0.015120158,0.27228776,0.0006169722,0.00008916109,0.7106853],"study_design_scores_gemma":[0.00026854675,0.000078638506,0.00087698596,0.000038490194,0.000002080934,0.000008029339,0.0000324704,0.48846692,0.50681365,0.0014939818,0.0017020673,0.00021814319],"about_ca_topic_score_codex":0.000012327744,"about_ca_topic_score_gemma":9.108824e-7,"teacher_disagreement_score":0.71046716,"about_ca_system_score_codex":0.00015257297,"about_ca_system_score_gemma":0.000047830817,"threshold_uncertainty_score":0.78461134},"labels":[],"label_agreement":null},{"id":"W4390597136","doi":"10.5383/juspn.16.01.006","title":"An Enhanced Fuzzy Clustering to Pattern Recognition for Cloud Computing, by using Model Aggregation and Model Selection","year":2022,"lang":"en","type":"article","venue":"Journal of Ubiquitous Systems and Pervasive Networks","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Cluster analysis; Cloud computing; Computer science; Fuzzy clustering; Data mining; Fuzzy logic; Adaptive resonance theory; Artificial intelligence; Machine learning; Model selection","score_opus":0.03468317124047883,"score_gpt":0.30431706792857116,"score_spread":0.26963389668809234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390597136","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":[0.26076877,0.00036822067,0.7379676,0.000054341042,0.00046707946,0.0003379131,0.000011518748,0.000020853775,0.000003695929],"genre_scores_gemma":[0.9465711,0.00007009928,0.05253658,0.00013000972,0.0006137473,0.000024463936,0.0000054514444,0.000025734584,0.000022830525],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827445,0.00017495076,0.00048965943,0.00033835496,0.00037751536,0.00034509518],"domain_scores_gemma":[0.9986546,0.00010875333,0.00045016923,0.00014298008,0.00043851044,0.00020498529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009415849,0.00016473282,0.00030308578,0.00017168606,0.0006164529,0.00029220743,0.00029217472,0.00007153559,4.525088e-7],"category_scores_gemma":[0.000022515322,0.00016983812,0.000051576553,0.00021700413,0.000017210657,0.0005626314,0.00024365724,0.00033872036,7.4906936e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055347853,0.000025696016,0.000021558306,0.00005185877,0.000018224806,0.0000025786721,0.0012424912,0.87017936,0.0049254512,0.000006171597,0.00013273105,0.12333852],"study_design_scores_gemma":[0.00057124277,0.00077303813,0.0000067152478,0.00015510732,0.000013642427,0.0004137278,0.0003326315,0.99702704,0.00024201997,0.00024775972,0.000026486847,0.00019056012],"about_ca_topic_score_codex":0.00005959126,"about_ca_topic_score_gemma":0.000016752301,"teacher_disagreement_score":0.6858023,"about_ca_system_score_codex":0.00020448091,"about_ca_system_score_gemma":0.00007772155,"threshold_uncertainty_score":0.69257975},"labels":[],"label_agreement":null},{"id":"W4392136634","doi":"10.31234/osf.io/fq6e9","title":"Ensemble clustering: A practical tutorial","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"Cluster analysis; Computer science; Consensus clustering; Data mining; Ensemble learning; Machine learning; Clustering high-dimensional data; CURE data clustering algorithm; Correlation clustering; Robustness (evolution); Stability (learning theory); Artificial intelligence","score_opus":0.062162072007400676,"score_gpt":0.38882062716574867,"score_spread":0.32665855515834796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392136634","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":[0.00013472863,0.00014537731,0.95323145,0.0060053915,0.00978237,0.00043954235,0.000004751224,0.0013275582,0.028928803],"genre_scores_gemma":[0.0268653,0.000041800224,0.95446706,0.00018712439,0.0024915482,0.00020302809,0.000006517573,0.000072279094,0.015665347],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964511,0.000117554104,0.00039860804,0.0013908813,0.0009615847,0.0006802995],"domain_scores_gemma":[0.99741536,0.00028410283,0.000081902275,0.0017711675,0.00017679595,0.00027067825],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00055402564,0.00037656125,0.000378215,0.00026488653,0.00008414228,0.0013818556,0.0017489014,0.00039810815,0.00005154054],"category_scores_gemma":[0.00029158272,0.00034020861,0.0001890654,0.0003422749,0.00006555476,0.00024533932,0.026295658,0.002335288,0.0012046568],"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":[0.00013494017,0.000550583,0.000004911688,0.0032451143,0.00064748205,0.0067051467,0.0030023137,0.027811846,0.0030521948,0.4072348,0.086713776,0.4608969],"study_design_scores_gemma":[0.00017074107,0.00007920876,0.0000032258988,0.00012757193,0.000011143958,0.00018745943,0.000012364261,0.8471207,0.00091783766,0.11981051,0.03109957,0.00045966462],"about_ca_topic_score_codex":0.000076816694,"about_ca_topic_score_gemma":0.000020373418,"teacher_disagreement_score":0.8193089,"about_ca_system_score_codex":0.00032108623,"about_ca_system_score_gemma":0.0009052492,"threshold_uncertainty_score":0.9999664},"labels":[],"label_agreement":null},{"id":"W4392197543","doi":"10.28924/2291-8639-22-2024-36","title":"Impact of Dataset Scaling on Hierarchical Clustering: A Comparative Analysis of Distance-Based and Ratio-Based Methods","year":2024,"lang":"en","type":"article","venue":"International Journal of Analysis and Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hierarchical clustering; Mathematics; Cluster analysis; Scaling; Multidimensional scaling; Data mining; Statistics; Computer science; Geometry","score_opus":0.0474050211507275,"score_gpt":0.4728101699367248,"score_spread":0.42540514878599733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392197543","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":[0.019153243,0.00018936089,0.9796399,0.0003892033,0.000018949424,0.00006635984,0.0005151662,0.00000665151,0.000021204623],"genre_scores_gemma":[0.8616068,0.000033600496,0.1381777,0.000020437448,0.000029184454,0.000008746221,0.00011671394,0.0000029618004,0.0000038728426],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846846,0.00013280891,0.0005661257,0.00024471513,0.0004906732,0.00009719146],"domain_scores_gemma":[0.9979972,0.0008876648,0.00032123592,0.00026169672,0.00042918246,0.00010301871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006403553,0.00010785455,0.00044802632,0.0016792341,0.00004701576,0.00014910907,0.0005227072,0.000029640889,0.000014615137],"category_scores_gemma":[0.000042927182,0.00008288149,0.00033108663,0.002114389,0.00013878365,0.00018823556,0.000102296624,0.00017073269,2.6731115e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021696638,0.00042258133,0.0045473482,0.000046549474,0.017227627,0.000016990261,0.00047827608,0.8256523,0.006033589,0.012497868,0.000053962718,0.13280591],"study_design_scores_gemma":[0.00020156891,0.00013069782,0.011530941,0.00003774221,0.00074165664,0.000003490413,0.000018673913,0.98538345,0.0011330635,0.00039793874,0.0003514818,0.00006928622],"about_ca_topic_score_codex":0.000043080174,"about_ca_topic_score_gemma":0.00001985491,"teacher_disagreement_score":0.84245354,"about_ca_system_score_codex":0.00007659424,"about_ca_system_score_gemma":0.0001266594,"threshold_uncertainty_score":0.3379809},"labels":[],"label_agreement":null},{"id":"W4392715283","doi":"10.1016/j.ijar.2024.109169","title":"An auto-weighted enhanced horizontal collaborative fuzzy clustering algorithm with knowledge adaption mechanism","year":2024,"lang":"en","type":"article","venue":"International Journal of Approximate Reasoning","topic":"Advanced Clustering Algorithms Research","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 Alberta","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Fuzzy clustering; Partition (number theory); Fuzzy logic; Entropy (arrow of time); Machine learning; Artificial intelligence; Mathematics","score_opus":0.010357393417794491,"score_gpt":0.3068244848556005,"score_spread":0.296467091437806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392715283","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":[0.01197745,0.00049217924,0.98421556,0.00021991268,0.0016015571,0.00016995546,0.0000140565335,0.00021526201,0.001094046],"genre_scores_gemma":[0.42126048,0.000105322026,0.5779465,0.000011438328,0.00054067845,0.00001546228,0.000007087939,0.000035521447,0.000077543555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735683,0.00014272264,0.00052241643,0.0004638463,0.0011265789,0.0003875916],"domain_scores_gemma":[0.9976514,0.00013777029,0.00029673995,0.0002661124,0.0014233864,0.00022456353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076221884,0.00026728798,0.00030120378,0.00060291,0.00013361339,0.0010183925,0.0014380099,0.00009158978,0.000014599991],"category_scores_gemma":[0.000045071014,0.00021810229,0.00009645771,0.000711916,0.00006454115,0.0028897896,0.00030650612,0.0005485183,0.00001678105],"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":[0.00022944916,0.00024980542,0.000004360461,0.00005648609,0.0005858684,0.0015694471,0.005891718,0.0023290268,0.059363272,0.044421427,0.000028706923,0.8852704],"study_design_scores_gemma":[0.00071683154,0.00078007946,0.000025584957,0.0008975425,0.00001507166,0.0014307643,0.0004793664,0.96073145,0.029121459,0.0051566907,0.00037727144,0.00026791557],"about_ca_topic_score_codex":0.000010019387,"about_ca_topic_score_gemma":0.0000090412,"teacher_disagreement_score":0.9584024,"about_ca_system_score_codex":0.0006084222,"about_ca_system_score_gemma":0.000504565,"threshold_uncertainty_score":0.98203826},"labels":[],"label_agreement":null},{"id":"W4392738528","doi":"10.1080/03610918.2024.2328166","title":"An ensemble approach to determine the number of latent dimensions and assess its reliability","year":2024,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Advanced Clustering Algorithms Research","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":"Polytechnique Montréal","funders":"","keywords":"Reliability (semiconductor); Computer science; Statistics; Reliability engineering; Mathematics; Engineering; Physics","score_opus":0.19477715379534086,"score_gpt":0.47886232169168147,"score_spread":0.28408516789634064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392738528","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":[0.04331762,0.00015444415,0.9556466,0.00031365827,0.0000419615,0.00029706568,0.000018819359,0.000050439656,0.00015943473],"genre_scores_gemma":[0.6130561,0.000042248575,0.38681927,0.000021103724,0.0000035865573,0.000019783818,0.000020750856,0.0000049978776,0.000012097238],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889624,0.00026222834,0.00029494436,0.000250815,0.0001852629,0.00011052561],"domain_scores_gemma":[0.99739575,0.0015945468,0.00004776822,0.000669581,0.00023033068,0.00006201051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050001335,0.00008298371,0.00010842125,0.000108057815,0.00017396263,0.00016966359,0.0004050858,0.000033362292,8.71481e-7],"category_scores_gemma":[0.00016867132,0.000071278824,0.000009697203,0.00049670774,0.000094843264,0.00031104285,0.00043040028,0.00015800582,0.0000031385644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044491485,0.00010580911,0.000549592,0.000059467002,0.0000056180097,6.9044273e-7,0.0021345646,0.7308962,0.00014463531,0.08756313,0.000010135918,0.17852572],"study_design_scores_gemma":[0.00010467936,0.00002903179,0.012844547,0.000029868646,0.0000044494573,0.0000054625725,0.00004552503,0.96928483,0.000018950428,0.017450133,0.00010890532,0.0000736161],"about_ca_topic_score_codex":0.000021555461,"about_ca_topic_score_gemma":0.000009261632,"teacher_disagreement_score":0.5697385,"about_ca_system_score_codex":0.000043250348,"about_ca_system_score_gemma":0.000043656462,"threshold_uncertainty_score":0.2906666},"labels":[],"label_agreement":null},{"id":"W4393552393","doi":"10.5281/zenodo.6577860","title":"SpatialSort: Supporting Datasets","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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; Terry Fox Research Institute; BC Cancer Agency","funders":"","keywords":"Computer science","score_opus":0.03703822458885673,"score_gpt":0.296882333592253,"score_spread":0.2598441090033963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393552393","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003954554,0.000066743225,0.04015364,0.0004446146,0.00037073685,0.0005807182,0.9550293,0.0010006907,0.0023496118],"genre_scores_gemma":[0.000035885212,0.00016008371,0.001929365,0.00018306548,0.0002007719,2.3138392e-7,0.9961226,0.0010864029,0.0002815918],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948579,0.0008455108,0.0005724752,0.0012734154,0.0014813402,0.0009693438],"domain_scores_gemma":[0.9960871,0.00008613915,0.00040133644,0.0026631362,0.0003972384,0.00036505848],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0018772867,0.00035202492,0.00035742542,0.00065485324,0.0043319007,0.0022574628,0.0090255765,0.00013973471,0.124336064],"category_scores_gemma":[0.0015509382,0.00040793212,0.000099509765,0.0012324078,0.00016941602,0.0006943097,0.020537028,0.0013457482,0.0074799866],"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":[0.000011279088,0.000103180195,1.9986405e-8,0.000114420895,0.0000357549,0.00020018265,0.0000922096,0.00014399267,0.00004443273,0.0001755528,0.90308076,0.095998235],"study_design_scores_gemma":[0.0002993701,0.00025667401,0.0000053667527,0.000025462528,0.000011495668,0.00037165103,0.000041801075,0.0014269958,0.00003446278,0.00012904899,0.99699026,0.00040738625],"about_ca_topic_score_codex":0.00009193216,"about_ca_topic_score_gemma":9.67796e-7,"teacher_disagreement_score":0.116856076,"about_ca_system_score_codex":0.0004721511,"about_ca_system_score_gemma":0.000022947579,"threshold_uncertainty_score":0.9998373},"labels":[],"label_agreement":null},{"id":"W4393622469","doi":"10.5281/zenodo.7812052","title":"Data from: The problem with missingness in mixed-type datasets and what we can do about it","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 Guelph","funders":"","keywords":"Missing data; Type (biology); Statistics; Computer science; Mathematics; Data science; Biology; Ecology","score_opus":0.0762632156264673,"score_gpt":0.30655359672369104,"score_spread":0.23029038109722372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393622469","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002533614,0.0009399967,0.0029076233,0.0055213314,0.00020049833,0.0007643105,0.9891305,0.00039476808,0.00011561914],"genre_scores_gemma":[0.000023828687,0.0059424313,0.0021245175,0.00018014557,0.00014497108,1.9210982e-7,0.9906659,0.0007576192,0.00016035668],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958328,0.0007079891,0.00036801246,0.0014327144,0.0009844485,0.0006740452],"domain_scores_gemma":[0.99535584,0.00022705318,0.00019148449,0.0036387101,0.00033810275,0.00024878583],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0013977158,0.00032866103,0.000307308,0.00032434784,0.0015588476,0.007680814,0.009705938,0.00013705416,0.00045258526],"category_scores_gemma":[0.00059903256,0.0002615055,0.000017537344,0.0017122069,0.00035159747,0.00173393,0.0183198,0.0010030627,0.0042213476],"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":[0.000031636384,0.000048028316,1.6499325e-7,0.000115649564,0.000038384023,0.00015686576,0.00032472744,0.000061880724,0.000012868402,0.000025016552,0.8921778,0.10700698],"study_design_scores_gemma":[0.00042752855,0.00014118005,0.00007049214,0.0006829295,0.000014180448,0.00010640761,0.00040064397,0.0024938541,0.000004725029,0.00011673051,0.9952249,0.0003164599],"about_ca_topic_score_codex":0.0004967874,"about_ca_topic_score_gemma":0.0001392203,"teacher_disagreement_score":0.10669052,"about_ca_system_score_codex":0.00017011423,"about_ca_system_score_gemma":0.000040180486,"threshold_uncertainty_score":0.9999837},"labels":[],"label_agreement":null},{"id":"W4393700520","doi":"10.5281/zenodo.7812051","title":"Data from: The problem with missingness in mixed-type datasets and what we can do about it","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 Guelph","funders":"","keywords":"Missing data; Type (biology); Computer science; Data type; Data science; Data mining; Statistics; Mathematics; Machine learning; Geology; Programming language","score_opus":0.0762632156264673,"score_gpt":0.30655359672369104,"score_spread":0.23029038109722372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393700520","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002533614,0.0009399967,0.0029076233,0.0055213314,0.00020049833,0.0007643105,0.9891305,0.00039476808,0.00011561914],"genre_scores_gemma":[0.000023828687,0.0059424313,0.0021245175,0.00018014557,0.00014497108,1.9210982e-7,0.9906659,0.0007576192,0.00016035668],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958328,0.0007079891,0.00036801246,0.0014327144,0.0009844485,0.0006740452],"domain_scores_gemma":[0.99535584,0.00022705318,0.00019148449,0.0036387101,0.00033810275,0.00024878583],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0013977158,0.00032866103,0.000307308,0.00032434784,0.0015588476,0.007680814,0.009705938,0.00013705416,0.00045258526],"category_scores_gemma":[0.00059903256,0.0002615055,0.000017537344,0.0017122069,0.00035159747,0.00173393,0.0183198,0.0010030627,0.0042213476],"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":[0.000031636384,0.000048028316,1.6499325e-7,0.000115649564,0.000038384023,0.00015686576,0.00032472744,0.000061880724,0.000012868402,0.000025016552,0.8921778,0.10700698],"study_design_scores_gemma":[0.00042752855,0.00014118005,0.00007049214,0.0006829295,0.000014180448,0.00010640761,0.00040064397,0.0024938541,0.000004725029,0.00011673051,0.9952249,0.0003164599],"about_ca_topic_score_codex":0.0004967874,"about_ca_topic_score_gemma":0.0001392203,"teacher_disagreement_score":0.10669052,"about_ca_system_score_codex":0.00017011423,"about_ca_system_score_gemma":0.000040180486,"threshold_uncertainty_score":0.9999837},"labels":[],"label_agreement":null},{"id":"W4393758208","doi":"10.5281/zenodo.5061257","title":"GVI: Sample data for computing VGVI. Vancouver, BC and Manchester.","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sample (material); Computer science; Geography; Physics","score_opus":0.0718370294873503,"score_gpt":0.3051840397421036,"score_spread":0.23334701025475332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393758208","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000558241,0.00018665036,0.39572632,0.00021518662,0.00036485938,0.00053607975,0.6023547,0.00037705415,0.00023354313],"genre_scores_gemma":[0.000024970293,0.00037525402,0.04813209,0.00015971393,0.00039002328,1.3556377e-7,0.94978786,0.00087155675,0.00025840406],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99598783,0.00040510148,0.00044877842,0.0016214871,0.00074372155,0.00079305633],"domain_scores_gemma":[0.99499804,0.00034128863,0.00024507384,0.0033057514,0.0007903088,0.00031952886],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001305661,0.0003451602,0.00040966654,0.00031845964,0.0024990211,0.0027181695,0.0071015568,0.00017915411,0.00081729895],"category_scores_gemma":[0.0025698992,0.00038892118,0.00005983488,0.0007129693,0.00019961828,0.00078416057,0.023815352,0.0006988072,0.0006497751],"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":[0.000013949901,0.00006880694,7.6265856e-8,0.00036171277,0.000048729697,0.00003473579,0.00008805548,0.000056028115,0.000026425414,0.00008879027,0.88172626,0.1174864],"study_design_scores_gemma":[0.0005620851,0.00017682915,0.000007885815,0.00012780036,0.000017598531,0.000118934884,0.00008487963,0.023333348,0.000022591445,0.00017955391,0.9749832,0.00038528827],"about_ca_topic_score_codex":0.00007411916,"about_ca_topic_score_gemma":0.000007859862,"teacher_disagreement_score":0.34759423,"about_ca_system_score_codex":0.00020787102,"about_ca_system_score_gemma":0.000026124215,"threshold_uncertainty_score":0.9998563},"labels":[],"label_agreement":null},{"id":"W4396712800","doi":"10.1109/tfuzz.2024.3397808","title":"CBCG: A Clustering Algorithm Based on Bidirectional Conical Information Granularity","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Fuzzy Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Natural Science Foundation of Hunan Province","keywords":"Cluster analysis; Data mining; Granularity; Fuzzy clustering; Computer science; Sorting; Cluster (spacecraft); Algorithm; Fuzzy logic; Single-linkage clustering; Correlation clustering; CURE data clustering algorithm; k-medians clustering; FLAME clustering; Complete-linkage clustering; Pattern recognition (psychology); Artificial intelligence","score_opus":0.020597308030298498,"score_gpt":0.2820249380215247,"score_spread":0.26142762999122615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396712800","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":[0.000118178985,0.00006406373,0.99098116,0.0005062846,0.005357161,0.0004748175,0.00008499214,0.0010372136,0.0013761554],"genre_scores_gemma":[0.96074355,0.000022035814,0.037520573,0.00022645306,0.00024886354,0.00041123698,0.000012361933,0.000040613268,0.00077428785],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973902,0.00018783261,0.0004661849,0.00050455873,0.0009988181,0.00045236596],"domain_scores_gemma":[0.99854517,0.00041132397,0.00005321175,0.00063251855,0.00015292877,0.000204851],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005831952,0.0002603242,0.00024559005,0.00067915575,0.00035860264,0.0008427314,0.0005370506,0.00016496894,0.000015092801],"category_scores_gemma":[0.000012044972,0.00024830693,0.0001729886,0.0009819202,0.00006445954,0.0013300843,0.0000075435405,0.0007042703,0.0005660527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036094672,0.00013078733,9.7315e-7,0.00023398249,0.000054140306,0.00005205262,0.00022794618,0.6539913,0.0001425947,0.0006750309,0.00023319382,0.34422192],"study_design_scores_gemma":[0.00041049693,0.00023687752,0.000016997921,0.00027151077,0.000007710476,0.00009763125,0.000031397987,0.98796904,0.0007196657,0.00009172773,0.009895905,0.0002510371],"about_ca_topic_score_codex":0.00016036048,"about_ca_topic_score_gemma":0.000014101233,"teacher_disagreement_score":0.9606254,"about_ca_system_score_codex":0.0004774212,"about_ca_system_score_gemma":0.00022253364,"threshold_uncertainty_score":0.9999969},"labels":[],"label_agreement":null},{"id":"W4396844948","doi":"10.1186/s13104-024-06791-y","title":"An inversion-based clustering approach for complex clusters","year":2024,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 Regina","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Similarity measure; Profiling (computer programming); Feature (linguistics); Similarity (geometry); Ranking (information retrieval); Artificial intelligence; Inversion (geology); Machine learning; Pattern recognition (psychology)","score_opus":0.30026848375425247,"score_gpt":0.4587841597762987,"score_spread":0.15851567602204625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396844948","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":[0.001147383,0.00025102825,0.9954252,0.00090882706,0.00022187777,0.0010059719,0.000020601037,0.0006151304,0.0004039752],"genre_scores_gemma":[0.32513973,0.00000631942,0.6739201,0.000069181784,0.00024444368,0.00029036653,0.00004030929,0.000046351703,0.00024323774],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99538445,0.0005153974,0.00029161913,0.0011629221,0.0014041826,0.0012414302],"domain_scores_gemma":[0.9944246,0.0034488898,0.000026046839,0.0012542009,0.0004204335,0.00042584247],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0031707948,0.00023018048,0.00023742669,0.0008700475,0.00059518847,0.0013392523,0.0024405227,0.000119441786,0.000019566576],"category_scores_gemma":[0.0007835893,0.0002110977,0.00013938107,0.001527808,0.00030143565,0.0010161335,0.0009064553,0.00059431157,0.000072745876],"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":[0.00039371906,0.00061056804,0.0005339387,0.004741553,0.00009617981,0.00012912026,0.0021735544,0.41756284,0.040659998,0.009742873,0.0064259972,0.5169296],"study_design_scores_gemma":[0.00044679907,0.00037657592,0.00013972755,0.00007653889,0.0000020422658,0.000007847152,0.00012299755,0.9924547,0.0018124607,0.0010921417,0.003218952,0.00024922198],"about_ca_topic_score_codex":0.00012150395,"about_ca_topic_score_gemma":0.000035470104,"teacher_disagreement_score":0.57489187,"about_ca_system_score_codex":0.00034015288,"about_ca_system_score_gemma":0.00057697686,"threshold_uncertainty_score":0.99969745},"labels":[],"label_agreement":null},{"id":"W4398203199","doi":"10.1016/j.ins.2024.120761","title":"An axiomatic framework for three-way clustering","year":2024,"lang":"en","type":"article","venue":"Information Sciences","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":17,"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":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Axiom; Axiomatic system; Data mining; Mathematics; Artificial intelligence","score_opus":0.054430876012930327,"score_gpt":0.39105383680820793,"score_spread":0.3366229607952776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398203199","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":[0.0016241189,0.00006505802,0.994776,0.0009538096,0.00079701253,0.00026593325,0.0000042747115,0.0004611233,0.0010526889],"genre_scores_gemma":[0.38113794,0.0000035871287,0.6184922,0.00018441235,0.000080342565,0.00007599273,0.0000021030935,0.000003918948,0.00001948689],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858004,0.000017715918,0.00028163413,0.00021936269,0.00056313607,0.00033808695],"domain_scores_gemma":[0.9990818,0.000343568,0.000053009488,0.00033133815,0.00009535597,0.0000949287],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010394268,0.00009700357,0.00008836205,0.0003318278,0.0003708108,0.0022657462,0.0013029969,0.000048374943,0.000010089743],"category_scores_gemma":[0.00018298898,0.00007805887,0.0000405183,0.0010686086,0.00012433421,0.009953756,0.00018549344,0.00010730756,0.000162798],"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":[0.0000015685526,0.0000052141977,0.000010751286,0.00010343476,0.0000038092376,0.0000010273404,0.0022973532,0.018627375,0.000059680337,0.20309055,0.000055891825,0.77574337],"study_design_scores_gemma":[0.000042088435,0.00011920494,0.00015018143,0.000073667085,7.776214e-7,0.0000142152085,0.00013866721,0.9167971,0.000229297,0.07903678,0.0032917499,0.00010628253],"about_ca_topic_score_codex":0.000012279707,"about_ca_topic_score_gemma":0.000009530579,"teacher_disagreement_score":0.8981697,"about_ca_system_score_codex":0.00005336169,"about_ca_system_score_gemma":0.00012071521,"threshold_uncertainty_score":0.99877},"labels":[],"label_agreement":null},{"id":"W4399424565","doi":"10.48550/arxiv.2406.02465","title":"An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Danmarks Grundforskningsfond; Government of Canada; Canadian Institute for Advanced Research","keywords":"Cluster analysis; Computer science; Artificial intelligence; Encoder; Empirical research; Pattern recognition (psychology); Data mining; Machine learning; Mathematics; Statistics","score_opus":0.07352471772403338,"score_gpt":0.27488410284662,"score_spread":0.20135938512258664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399424565","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":[0.37429366,0.000027771744,0.62424123,0.000053690852,0.00018357848,0.0005799247,0.000049596147,0.00041580014,0.00015474485],"genre_scores_gemma":[0.94610953,0.000027107546,0.05359545,0.000024785359,0.000048520764,0.000004028914,0.00004710909,0.000044705088,0.00009876205],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99655735,0.0003459649,0.00030833643,0.0019287564,0.00035475296,0.0005048085],"domain_scores_gemma":[0.9964011,0.00013227884,0.00015833792,0.0027764519,0.00019988844,0.0003319468],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046707984,0.00044532152,0.00052083755,0.0005625113,0.0001480232,0.00021082078,0.003736449,0.00020709695,0.000012517896],"category_scores_gemma":[0.000018776243,0.00044409456,0.00010901752,0.001238418,0.00015972425,0.0005808286,0.0079419,0.0010844625,0.000042365198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019746347,0.0012034863,0.0065711197,0.00083542865,0.00060813146,0.0038858645,0.009629204,0.9715337,0.00009694042,0.00071834883,0.00012007944,0.004600236],"study_design_scores_gemma":[0.00074172573,0.00071316207,0.00066188636,0.0001449297,0.00009087961,0.000012456705,0.0009683644,0.9922704,0.00007177748,0.0037687253,0.000060837625,0.0004948474],"about_ca_topic_score_codex":0.00050690246,"about_ca_topic_score_gemma":0.00037259748,"teacher_disagreement_score":0.5718159,"about_ca_system_score_codex":0.00037471682,"about_ca_system_score_gemma":0.00048164828,"threshold_uncertainty_score":0.9998011},"labels":[],"label_agreement":null},{"id":"W4399995656","doi":"10.1109/tpami.2024.3418776","title":"Simplex Clustering via sBeta With Applications to Online Adjustment of Black-Box Predictions","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Institut National de la Recherche Scientifique","funders":"Compute Canada","keywords":"Cluster analysis; Computer science; Artificial intelligence; Simplex; Black box; Combinatorics; Algorithm; Pattern recognition (psychology); Mathematics","score_opus":0.02565515967990565,"score_gpt":0.32014705448452946,"score_spread":0.2944918948046238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399995656","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":[0.00047353064,0.00013758556,0.9979854,0.0006310732,0.00008471088,0.00034711324,0.00015050691,0.00016406343,0.000026016713],"genre_scores_gemma":[0.96048987,0.00026173214,0.038655743,0.000145781,0.000032299406,0.00013064998,0.00001061037,0.000019194304,0.00025412842],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982361,0.00004529202,0.000391873,0.0006532543,0.00040062613,0.00027285726],"domain_scores_gemma":[0.9988046,0.00015020397,0.000051746796,0.0006721905,0.00011964025,0.0002016132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014065744,0.00021430702,0.0002868161,0.0008676077,0.00013975502,0.00010459097,0.00049504207,0.000044360542,0.00006253181],"category_scores_gemma":[0.0000017624028,0.00017715449,0.00014875861,0.002465971,0.00009530698,0.00028407396,0.000023152215,0.0002846244,0.00002448335],"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":[0.000006735309,0.00012264372,0.000013217939,0.000049271188,0.00035801646,0.000004630294,0.00029732697,0.36272985,0.00035496277,0.000042898027,0.0000020020334,0.63601846],"study_design_scores_gemma":[0.000051691284,0.00027096437,0.00021964153,0.00006260769,0.00025041556,0.000017567832,0.000059620408,0.9793497,0.019050919,0.00010675386,0.0003740661,0.00018610462],"about_ca_topic_score_codex":0.00055395777,"about_ca_topic_score_gemma":0.001262166,"teacher_disagreement_score":0.9600163,"about_ca_system_score_codex":0.00007629463,"about_ca_system_score_gemma":0.00003610398,"threshold_uncertainty_score":0.72241503},"labels":[],"label_agreement":null},{"id":"W4400811537","doi":"10.1109/csci62032.2023.00024","title":"Three-Way Clustering: An Advanced Soft Clustering Approach","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":4,"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 Regina","funders":"","keywords":"Cluster analysis; Computer science; Data mining; Artificial intelligence","score_opus":0.054600297286088305,"score_gpt":0.32227804524714937,"score_spread":0.2676777479610611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400811537","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":[0.0036284053,0.000029860588,0.9859632,0.00039260997,0.00045986945,0.0004043,0.0000025292943,0.0029122806,0.0062069157],"genre_scores_gemma":[0.13164473,0.000022986755,0.86422837,0.00022304115,0.00021882808,0.00018079406,0.000020490488,0.000085803396,0.0033749833],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99642503,0.00006889122,0.00038369614,0.0011530275,0.0008051215,0.001164239],"domain_scores_gemma":[0.9975681,0.00013822263,0.00007817721,0.0016852402,0.00013323188,0.0003970531],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00067132147,0.00033020246,0.0003164502,0.00039919076,0.000360555,0.00040335435,0.0024342302,0.000119229604,0.000028252083],"category_scores_gemma":[0.00008667849,0.00031150345,0.000094779985,0.001733764,0.00009064578,0.0017918341,0.0026844847,0.0003760261,0.00045065643],"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":[0.000027180224,0.00009992852,0.00008567762,0.00009752291,0.000024995315,0.000091364454,0.0007717701,0.18197545,0.0037020512,0.0019047821,0.00031437134,0.8109049],"study_design_scores_gemma":[0.00052848144,0.00016065424,0.0011286853,0.000017542889,0.0000016965504,0.000056250006,0.00016195804,0.99387056,0.00047875135,0.0015572202,0.0016236446,0.00041455598],"about_ca_topic_score_codex":0.000052563377,"about_ca_topic_score_gemma":0.00013263637,"teacher_disagreement_score":0.81189513,"about_ca_system_score_codex":0.00012758389,"about_ca_system_score_gemma":0.00006741324,"threshold_uncertainty_score":0.9999337},"labels":[],"label_agreement":null},{"id":"W4400929535","doi":"10.24132/csrn.3401.27","title":"LVCluster: Bounded Clustering using Laguerre Voronoi Diagram","year":2024,"lang":"en","type":"article","venue":"Computer Science Research Notes","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Voronoi diagram; Laguerre polynomials; Bounded function; Cluster analysis; Centroidal Voronoi tessellation; Power diagram; Computer science; Diagram; Weighted Voronoi diagram; Mathematics; Artificial intelligence; Mathematical analysis; Geometry","score_opus":0.1833181193907332,"score_gpt":0.46084896332075936,"score_spread":0.27753084393002614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400929535","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":[0.01509224,0.0013300126,0.9784576,0.0013698152,0.0020058546,0.0005265561,0.000003489866,0.0008695889,0.0003448397],"genre_scores_gemma":[0.5961885,0.000069898895,0.4025108,0.00006166833,0.00090607395,0.000042309042,0.0000013876179,0.000045427994,0.00017395683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9908359,0.0003868303,0.00048554834,0.0021105362,0.0035425762,0.0026386185],"domain_scores_gemma":[0.9950234,0.0014207122,0.000048113914,0.0019036544,0.0008393977,0.0007646736],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0068076705,0.00036610765,0.00034369034,0.002025336,0.0017430247,0.0072301044,0.00612832,0.00012586868,0.000018928085],"category_scores_gemma":[0.00055993523,0.0003326006,0.00014376594,0.007460297,0.0020314818,0.0045405477,0.008006232,0.0012866057,0.00031845437],"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":[0.0000061395017,0.00006624131,0.00005789395,0.00017459567,0.000020230607,0.00040246057,0.0013998352,0.011065423,0.008102566,0.0128940325,0.000119243494,0.9656913],"study_design_scores_gemma":[0.00016518902,0.00020586651,0.00027852386,0.0003114984,0.0000020348946,0.00021458433,0.000021184242,0.98660564,0.0044840225,0.004947655,0.0023775848,0.0003862108],"about_ca_topic_score_codex":0.0002207761,"about_ca_topic_score_gemma":0.00003292727,"teacher_disagreement_score":0.9755402,"about_ca_system_score_codex":0.0010507022,"about_ca_system_score_gemma":0.0017522061,"threshold_uncertainty_score":0.9999126},"labels":[],"label_agreement":null},{"id":"W4400985398","doi":"10.54254/2755-2721/79/20241631","title":"Analysis of clustering algorithms in Iris and breast cancer datasets","year":2024,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cluster analysis; DBSCAN; Expansive; Computer science; Noise (video); Data mining; Domain (mathematical analysis); Data science; Artificial intelligence; CURE data clustering algorithm; Correlation clustering; Mathematics; Image (mathematics)","score_opus":0.009490061202234312,"score_gpt":0.2762931799248556,"score_spread":0.26680311872262125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400985398","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":[0.019364843,0.0006000987,0.9796378,0.0001183469,0.00004737516,0.000061446204,0.0000889443,0.00006547214,0.000015655687],"genre_scores_gemma":[0.9272415,0.00005940539,0.072604634,0.00001479626,0.000021196878,0.000021210682,0.000025728434,0.000008063948,0.000003488783],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992049,0.000005133058,0.0001637545,0.00029339443,0.00018045321,0.00015239327],"domain_scores_gemma":[0.9996566,0.0001531704,0.000015924372,0.000101732425,0.000017385466,0.000055163193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012513102,0.00009486371,0.00016417398,0.00046674226,0.000022576458,0.00008575358,0.00014115925,0.000025870864,0.0000029274995],"category_scores_gemma":[0.0000029406779,0.00009739173,0.000019134073,0.0009809296,0.0000220113,0.00018301806,0.00024393034,0.00010513806,5.5272835e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001878405,0.00000572845,0.00013162944,0.00007867425,0.00010411299,0.000010183142,0.00019953791,0.91463476,0.00031138104,0.0042554904,0.0000027003148,0.080263935],"study_design_scores_gemma":[0.00010621469,0.0000044139056,0.031050561,0.000040407554,0.00001704539,0.000015496837,0.000010443202,0.96831566,0.000018139872,0.0002733752,0.000053194904,0.000095028234],"about_ca_topic_score_codex":0.00004980391,"about_ca_topic_score_gemma":0.000007247311,"teacher_disagreement_score":0.9078766,"about_ca_system_score_codex":0.00003246427,"about_ca_system_score_gemma":0.00002291064,"threshold_uncertainty_score":0.39715192},"labels":[],"label_agreement":null},{"id":"W4401011434","doi":"10.1016/b978-0-443-24010-2.00005-6","title":"Clustering","year":2024,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Advanced Clustering Algorithms Research","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":"University of Calgary","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence","score_opus":0.024099824071557665,"score_gpt":0.2847893070594668,"score_spread":0.26068948298790917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401011434","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.962872e-7,0.0020421436,0.033650126,0.00020169854,0.0012541441,0.00034903162,0.000010359817,0.00064777443,0.9618445],"genre_scores_gemma":[0.00002432612,0.0000968875,0.032049447,0.00015790109,0.0004836906,0.000038857226,0.000003549216,0.00013337402,0.967012],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972695,0.000014107261,0.0004169039,0.0010180259,0.00072703155,0.00055439206],"domain_scores_gemma":[0.99800426,0.00008125143,0.00010660382,0.0014821509,0.00010619275,0.00021954966],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002628005,0.0004921398,0.00045229704,0.00035448006,0.00012129402,0.0004057903,0.0018045444,0.00029657985,0.00008430057],"category_scores_gemma":[0.000011963307,0.00047530417,0.00025076247,0.00003603704,0.000116338844,0.00014822836,0.0026395305,0.0010748403,0.002620249],"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":[0.0000015844457,0.0000015851285,2.4596101e-8,0.00015138484,0.00005339555,0.00036218908,0.00013621601,0.000023808772,0.000016443973,0.034412418,0.00008876797,0.9647522],"study_design_scores_gemma":[0.00008492013,0.000048913775,2.744335e-7,0.00057933317,0.000014612757,0.00011683536,0.0000012690778,0.013008251,0.000033629116,0.08581142,0.89983493,0.00046559583],"about_ca_topic_score_codex":2.3361358e-7,"about_ca_topic_score_gemma":0.0000069060206,"teacher_disagreement_score":0.96428657,"about_ca_system_score_codex":0.0002488547,"about_ca_system_score_gemma":0.00014696737,"threshold_uncertainty_score":0.99976987},"labels":[],"label_agreement":null},{"id":"W4401331642","doi":"10.1109/fuzz-ieee60900.2024.10611833","title":"Generalized Deep Embedded Fuzzy C-Means for Clustering High-Dimensional Data","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Cluster analysis; Fuzzy clustering; Fuzzy logic; Artificial intelligence; Data mining; Clustering high-dimensional data; Pattern recognition (psychology)","score_opus":0.06002803338243091,"score_gpt":0.35236343863696323,"score_spread":0.29233540525453233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401331642","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":[0.00072228716,0.00037690645,0.9942088,0.0017979217,0.0012286244,0.00035159668,0.000042037627,0.0007534203,0.00051837426],"genre_scores_gemma":[0.018093288,0.000015974756,0.976605,0.0003270634,0.00034891552,0.0000702659,0.000099153665,0.000039857354,0.0044004894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975963,0.0000495138,0.00027821475,0.0010118894,0.00049256283,0.00057152245],"domain_scores_gemma":[0.9977729,0.00031756074,0.000024774394,0.0016175911,0.00010192652,0.000165255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005240155,0.00019467012,0.00020116896,0.00017501871,0.00017197228,0.0004939942,0.0022169743,0.00006807503,0.000061632556],"category_scores_gemma":[0.00008836994,0.0001665226,0.00006330602,0.00043171845,0.00004536668,0.0011372467,0.0028687303,0.00018121483,0.00014147624],"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":[0.00007022587,0.00010647343,0.0000035419835,0.0003917899,0.00022539697,0.00026973768,0.0006127349,0.10361579,0.0133689,0.12497027,0.020945711,0.73541945],"study_design_scores_gemma":[0.00042561753,0.00005610341,0.000010620514,0.00003336583,0.0000056263307,0.000050290353,0.000009605543,0.9812037,0.00090048177,0.007545457,0.00953454,0.0002246109],"about_ca_topic_score_codex":0.00005077729,"about_ca_topic_score_gemma":0.00006234579,"teacher_disagreement_score":0.8775879,"about_ca_system_score_codex":0.000088444,"about_ca_system_score_gemma":0.00012828919,"threshold_uncertainty_score":0.67905945},"labels":[],"label_agreement":null},{"id":"W4401769675","doi":"10.18280/isi.290405","title":"Distributed K-means Clustering Using Topological Relationships","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Topology (electrical circuits); Computer science; Mathematics; Artificial intelligence; Combinatorics","score_opus":0.054677586115813914,"score_gpt":0.30345414908231905,"score_spread":0.24877656296650513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401769675","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":[0.014045292,0.00015025263,0.98237795,0.00016783201,0.00054008176,0.00019951275,0.000020553978,0.0008209391,0.001677577],"genre_scores_gemma":[0.85641325,0.00001262688,0.14333501,0.000037027206,0.00007541907,0.000025864556,0.000043804976,0.000009529822,0.000047485737],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984574,0.000106330794,0.00046235934,0.00021091403,0.0003611483,0.00040186555],"domain_scores_gemma":[0.9991032,0.00019595359,0.00007634363,0.00035771506,0.00015617292,0.00011063918],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00062175776,0.00015853082,0.00014407442,0.00030532846,0.00046537755,0.0010599857,0.00049982284,0.00011945575,0.000015623555],"category_scores_gemma":[0.00039839812,0.00014700532,0.00006474859,0.0010098233,0.000116768395,0.006184316,0.00039423158,0.00036920002,0.0001629961],"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":[0.000031282085,0.000042313583,0.0007837618,0.0012748229,0.00011220616,0.00012999406,0.017114505,0.3200623,0.0008946883,0.14529718,0.00041437655,0.5138425],"study_design_scores_gemma":[0.00009509596,0.00003740348,0.0009167294,0.00016817854,0.000003958292,0.00018521979,0.00028204705,0.9838196,0.0001824554,0.010957798,0.0031722956,0.00017922484],"about_ca_topic_score_codex":0.000032484346,"about_ca_topic_score_gemma":0.0000048333795,"teacher_disagreement_score":0.84236795,"about_ca_system_score_codex":0.0006161702,"about_ca_system_score_gemma":0.00011121447,"threshold_uncertainty_score":0.999977},"labels":[],"label_agreement":null},{"id":"W4401831247","doi":"10.18280/ria.380412","title":"A Comprehensive Study of Ensemble Models to Improve the Performance of Cluster Algorithms","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster (spacecraft); Computer science; Algorithm","score_opus":0.0697253121005116,"score_gpt":0.32701849358913027,"score_spread":0.2572931814886187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401831247","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":[0.31661835,0.00026036118,0.6812968,0.0002999673,0.0003796463,0.00073894276,0.000003819567,0.00006614014,0.0003359268],"genre_scores_gemma":[0.9836961,0.00005121693,0.015097462,0.00004615145,0.000053217485,0.00008910299,4.6072452e-7,0.000020464993,0.00094582123],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978156,0.00010166266,0.0006063786,0.00059230794,0.000486094,0.00039796095],"domain_scores_gemma":[0.9977638,0.00047240677,0.000088811204,0.001214109,0.00036601955,0.00009486762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042073833,0.00018727402,0.00029548572,0.0002199835,0.00012073939,0.000094199604,0.0014876575,0.000047983674,0.000010133175],"category_scores_gemma":[0.00003083903,0.00014013599,0.00009138951,0.001333199,0.000106315085,0.00043363962,0.00090639695,0.00027483964,0.00009891441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022713966,0.00021546998,0.000009351114,0.00022956153,0.00003902445,0.000011967906,0.015830314,0.7447338,0.01619356,0.0012545626,0.00006567547,0.221394],"study_design_scores_gemma":[0.000042453772,0.0009703982,0.000014499065,0.00013126808,0.000006784564,0.000016497359,0.0021760082,0.90715617,0.08833687,0.0005979846,0.00041633123,0.00013475832],"about_ca_topic_score_codex":0.00009632307,"about_ca_topic_score_gemma":0.000007635008,"teacher_disagreement_score":0.6670778,"about_ca_system_score_codex":0.000054654512,"about_ca_system_score_gemma":0.000072776405,"threshold_uncertainty_score":0.571458},"labels":[],"label_agreement":null},{"id":"W4401835829","doi":"10.18280/ria.380416","title":"Optimizing the Evaluation of K-means Clustering Using the Weight Product","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Product (mathematics); k-means clustering; Computer science; Mathematics; Statistics","score_opus":0.13743874341883913,"score_gpt":0.37872133203304276,"score_spread":0.24128258861420362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401835829","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":[0.0045550903,0.0027527907,0.98801893,0.0020373624,0.0008301556,0.0005060206,0.0000012723541,0.00009737512,0.0012010288],"genre_scores_gemma":[0.9542206,0.00009485838,0.044974033,0.00002778935,0.00022261956,0.000044640896,6.9178924e-7,0.000020759424,0.00039400154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782646,0.00025253132,0.00039605793,0.00047762942,0.00069912977,0.00034820213],"domain_scores_gemma":[0.99805474,0.00039017625,0.00008028461,0.0011139874,0.0003200418,0.0000407964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031245179,0.0001402453,0.00013212209,0.00011601986,0.00032624483,0.0002647303,0.001343534,0.000032111802,0.000041115116],"category_scores_gemma":[0.00024332423,0.000085914515,0.00009440732,0.001185119,0.00017167564,0.00042764485,0.0005393513,0.0003021086,0.000052923115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017414727,0.000012747394,0.0000023960351,0.000048518898,0.000014766468,0.000003502427,0.0037777165,0.76413685,0.0070747114,0.002125169,0.000024023593,0.22277784],"study_design_scores_gemma":[0.000013170488,0.000022589384,0.000004354844,0.00017951935,0.000018030221,0.000056068075,0.0004985462,0.940035,0.056151282,0.0015896846,0.0013325758,0.00009917145],"about_ca_topic_score_codex":0.000034723525,"about_ca_topic_score_gemma":0.0000096922795,"teacher_disagreement_score":0.94966555,"about_ca_system_score_codex":0.0001430678,"about_ca_system_score_gemma":0.00016492158,"threshold_uncertainty_score":0.35034922},"labels":[],"label_agreement":null},{"id":"W4402654931","doi":"10.1007/978-3-031-70239-6_27","title":"SERIEMA: A Framework to Enhance Clustering Stability, Compactness, and Separation by Fusing Multimodal Data","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Compact space; Cluster analysis; Stability (learning theory); Separation (statistics); Artificial intelligence; Data mining; Machine learning; Mathematics","score_opus":0.03724753028036763,"score_gpt":0.3658450307763174,"score_spread":0.32859750049594977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402654931","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":[0.00032999273,0.0009457316,0.9941105,0.0018377308,0.001409979,0.00071136944,0.00006327953,0.0002718678,0.00031954455],"genre_scores_gemma":[0.108213075,0.00006014789,0.89034986,0.0006010678,0.0004095879,0.000016440943,0.000023909768,0.00006584477,0.00026005236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939335,0.000047879712,0.00059192686,0.0031668656,0.0013337862,0.00092605053],"domain_scores_gemma":[0.9953801,0.0007787968,0.00015889334,0.003082634,0.00023058656,0.00036899635],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0013113068,0.0006317195,0.0006185465,0.0005717136,0.0003551044,0.0018094061,0.004804259,0.0003351875,0.000012312415],"category_scores_gemma":[0.00027222946,0.00062339386,0.000050307863,0.0009782364,0.00064262544,0.0016263615,0.012084419,0.0014461271,0.00004624552],"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":[0.000025101655,0.000041965075,0.000022047172,0.00036343228,0.000024174273,0.00013254448,0.002870025,0.059400767,0.0024481162,0.0018534361,0.000054710774,0.9327637],"study_design_scores_gemma":[0.00008080672,0.00013189694,0.0000166035,0.0009483145,0.000005502766,0.000067876346,6.9772784e-7,0.95219,0.002080182,0.042450033,0.0013726283,0.0006555047],"about_ca_topic_score_codex":0.0000750909,"about_ca_topic_score_gemma":0.0002187171,"teacher_disagreement_score":0.93210816,"about_ca_system_score_codex":0.0005100823,"about_ca_system_score_gemma":0.00038232628,"threshold_uncertainty_score":0.99962175},"labels":[],"label_agreement":null},{"id":"W4402728512","doi":"10.3390/math12182884","title":"Imputing Missing Data in One-Shot Devices Using Unsupervised Learning Approach","year":2024,"lang":"en","type":"article","venue":"Mathematics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Oakland University","keywords":"Computer science; Cluster analysis; Missing data; Imputation (statistics); Data mining; Reliability (semiconductor); Crash; DBSCAN; Mobile device; Sampling (signal processing); Machine learning; Artificial intelligence; Fuzzy clustering","score_opus":0.29114768685540554,"score_gpt":0.4016962559138063,"score_spread":0.11054856905840077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402728512","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":[0.02627852,0.000639917,0.9711728,0.00012341609,0.000090168716,0.00015444739,0.0000015517359,0.00031283728,0.0012263452],"genre_scores_gemma":[0.18633474,0.000008097636,0.8134569,0.000016469938,0.00006941231,0.0000031002055,0.000006555484,0.000030085464,0.00007464291],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980277,0.000086172375,0.00036269988,0.0005856244,0.00047613838,0.00046167313],"domain_scores_gemma":[0.99849904,0.00035964276,0.00005608866,0.0009690393,0.000037622536,0.00007855533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013408222,0.00016108046,0.00022818151,0.00024965213,0.00015242351,0.00077764917,0.0016468714,0.000063239124,0.0000051296142],"category_scores_gemma":[0.00027186802,0.00015659542,0.000029078044,0.0009527805,0.000037186586,0.000931698,0.0018451585,0.00046603938,0.000019475452],"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":[0.0000063329758,0.0007105575,0.00075587747,0.011079506,0.00017858812,0.00055997435,0.041811418,0.17860247,0.025645813,0.017632287,0.00004468032,0.7229725],"study_design_scores_gemma":[0.00009144147,0.000011348996,0.000026274476,0.0005720161,0.000005555389,0.00006067988,0.00034154562,0.9960562,0.00025553294,0.0022145961,0.00018822157,0.00017660674],"about_ca_topic_score_codex":0.000025042853,"about_ca_topic_score_gemma":0.0000028573513,"teacher_disagreement_score":0.8174537,"about_ca_system_score_codex":0.00011837462,"about_ca_system_score_gemma":0.00011852149,"threshold_uncertainty_score":0.7498889},"labels":[],"label_agreement":null},{"id":"W4403170718","doi":"10.1007/s00357-024-09493-z","title":"Mixed-Type Distance Shrinkage and Selection for Clustering via Kernel Metric Learning","year":2024,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","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":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"University of British Columbia","keywords":"Cluster analysis; Shrinkage; Selection (genetic algorithm); Mathematics; Kernel (algebra); Artificial intelligence; Metric (unit); Pattern recognition (psychology); Type (biology); Statistics; Computer science; Combinatorics; Geology; Engineering","score_opus":0.04542069984512903,"score_gpt":0.3289202876242669,"score_spread":0.28349958777913786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403170718","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":[0.0072160005,0.0012154287,0.9902298,0.00059986924,0.00050836,0.00009857723,3.1385656e-7,0.00006112916,0.000070506416],"genre_scores_gemma":[0.8892338,0.00021719925,0.10985783,0.000009029581,0.0002004097,0.0000057707207,6.5299344e-7,0.000013413461,0.0004618576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989573,0.00006211611,0.0003079694,0.00020710258,0.00029629047,0.00016922758],"domain_scores_gemma":[0.9990738,0.0002766084,0.00017341567,0.0000933591,0.00030702993,0.00007578929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075670634,0.00008384466,0.00012923001,0.00036694607,0.00012366395,0.0002952709,0.0002494611,0.000048921,0.0000015248296],"category_scores_gemma":[0.00026728588,0.00007526204,0.000049232665,0.00085396867,0.000023538576,0.0008602858,0.0000635217,0.0003073739,0.000003951629],"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":[0.000048393224,0.000028108414,0.0003118636,0.00022550773,0.00004706786,0.000008781315,0.00037386644,0.009022033,0.057373703,0.004867884,0.00017613491,0.92751664],"study_design_scores_gemma":[0.00016214541,0.00023058942,0.0037502497,0.000075513584,0.000009140526,0.00015469531,0.000036498124,0.9805384,0.0015903487,0.001294729,0.012076724,0.000080941485],"about_ca_topic_score_codex":0.0000015926535,"about_ca_topic_score_gemma":0.0000028285485,"teacher_disagreement_score":0.9715164,"about_ca_system_score_codex":0.00018256462,"about_ca_system_score_gemma":0.000072012976,"threshold_uncertainty_score":0.3069097},"labels":[],"label_agreement":null},{"id":"W4403344678","doi":"10.1287/ijoc.2024.0938","title":"A Column Generation Algorithm with Dynamic Constraint Aggregation for Minimum Sum-of-Squares Clustering","year":2025,"lang":"en","type":"preprint","venue":"INFORMS journal on computing","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Column (typography); Column generation; Cluster analysis; Constraint (computer-aided design); Explained sum of squares; Mathematical optimization; Algorithm; Computer science; Least-squares function approximation; Mathematics; Combinatorics; Artificial intelligence; Statistics","score_opus":0.030440264737981348,"score_gpt":0.32754724705520116,"score_spread":0.2971069823172198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403344678","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":[0.012061733,0.00012266966,0.98448646,0.00032106118,0.0017050083,0.00094056985,0.000044325345,0.00012414622,0.00019404259],"genre_scores_gemma":[0.16079949,0.000054249704,0.8383048,0.00014064519,0.00043828232,0.000037009588,0.000042315714,0.000030148049,0.00015304965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966164,0.00008320825,0.001183803,0.00058224157,0.0008967577,0.00063755445],"domain_scores_gemma":[0.99623716,0.00051151204,0.0013058669,0.0006515065,0.0011136676,0.00018028518],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012363093,0.0004373915,0.0006305508,0.000750123,0.0004958796,0.0008791163,0.0014435626,0.00026595345,0.0000021363028],"category_scores_gemma":[0.00021179208,0.00038078387,0.00023382643,0.00040523402,0.00012121309,0.000522879,0.0013345975,0.0013128187,0.0000016959553],"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":[0.000023109353,0.0000287453,0.000009791868,0.00021709185,0.00008765915,0.00001987131,0.0005473088,0.3805687,0.00006982532,0.00018582794,0.000026307647,0.61821574],"study_design_scores_gemma":[0.0011314388,0.00061735074,0.000052274074,0.0022453656,0.000017291146,0.000253269,0.000105335224,0.99302256,0.0010257851,0.00087243976,0.00025887508,0.00039803836],"about_ca_topic_score_codex":0.000020370291,"about_ca_topic_score_gemma":0.000025074036,"teacher_disagreement_score":0.6178177,"about_ca_system_score_codex":0.00064589584,"about_ca_system_score_gemma":0.001078693,"threshold_uncertainty_score":0.9998644},"labels":[],"label_agreement":null},{"id":"W4403730407","doi":"10.23952/jnva.8.2024.6.09","title":"Solving net-constrained clustering problem","year":2024,"lang":"en","type":"article","venue":"Journal of Nonlinear and Variational Analysis","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Net (polyhedron); Computer science; Mathematics; Artificial intelligence","score_opus":0.01568507956756476,"score_gpt":0.2976116037681624,"score_spread":0.28192652420059766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403730407","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":[0.001988653,0.00048753264,0.99527234,0.0018456111,0.00012263264,0.00002904238,0.0000050285207,0.000026745493,0.00022242437],"genre_scores_gemma":[0.22502488,0.0000960875,0.774108,0.00006269432,0.0004297204,0.0000012643659,0.0000034722957,0.000007476017,0.00026638515],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987772,0.000046777783,0.0003908755,0.0001832823,0.00044185613,0.00016001091],"domain_scores_gemma":[0.99918526,0.00023458856,0.00011563732,0.00011409541,0.00024249026,0.00010790337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007103969,0.00008976424,0.00021525516,0.00062195485,0.00008986512,0.0003417811,0.0002949226,0.000036942012,0.000030821277],"category_scores_gemma":[0.000063916064,0.0000713561,0.0001794793,0.0011769114,0.000024957368,0.00066158327,0.00015330089,0.0002269584,0.0000042415554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059250324,0.00022893248,0.0015865524,0.00029305203,0.008060945,0.0007597311,0.0029308207,0.5157647,0.005355881,0.036048293,0.00021071934,0.42870113],"study_design_scores_gemma":[0.0001318487,0.000052518244,0.0015988974,0.000035301666,0.00013307342,0.00015925754,0.000016777767,0.99436575,0.000025345398,0.0023913302,0.0010116436,0.00007825595],"about_ca_topic_score_codex":0.00001021563,"about_ca_topic_score_gemma":0.0000057322027,"teacher_disagreement_score":0.47860107,"about_ca_system_score_codex":0.000051815685,"about_ca_system_score_gemma":0.0001622874,"threshold_uncertainty_score":0.3295803},"labels":[],"label_agreement":null},{"id":"W4403793086","doi":"10.1007/s11634-024-00608-3","title":"A sparse exponential family latent block model for co-clustering","year":2024,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Clustering Algorithms Research","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":"University of Calgary","funders":"Amirkabir University of Technology","keywords":"Exponential family; Cluster analysis; Exponential function; Block (permutation group theory); Computer science; Mathematics; Statistics; Combinatorics","score_opus":0.1106521907296518,"score_gpt":0.39391825692417415,"score_spread":0.2832660661945223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403793086","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":[0.0022305192,0.0028941708,0.99399394,0.00036081244,0.000094320094,0.00018180233,0.00008897216,0.000083191815,0.00007227846],"genre_scores_gemma":[0.8218928,0.0037611085,0.17349073,0.00003380478,0.000057944257,0.000112837246,0.00035370537,0.000013561958,0.00028351418],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982603,0.00003571996,0.0003125142,0.0008694025,0.0002675817,0.00025447074],"domain_scores_gemma":[0.9986327,0.00012867272,0.000059234302,0.0010667623,0.00004788631,0.00006468582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004919061,0.00012530062,0.00020139824,0.00041148707,0.00009624384,0.00031526433,0.00091973704,0.00004483496,0.0000014169848],"category_scores_gemma":[0.000042703323,0.00011687625,0.000054126383,0.0010137138,0.00005205139,0.0020079971,0.00046189365,0.00011662819,0.0000059200315],"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":[0.000038133374,0.000105328814,0.0005508971,0.00024046545,0.00027288412,0.000015273032,0.0005921093,0.27290946,0.00873776,0.009510467,0.0001898523,0.70683736],"study_design_scores_gemma":[0.00013958453,0.000013853992,0.00091816095,0.000027814547,0.000061204046,0.0000020176017,0.000038909388,0.9932954,0.00007059254,0.0015430724,0.0037534337,0.00013600617],"about_ca_topic_score_codex":0.00001096731,"about_ca_topic_score_gemma":0.00017188226,"teacher_disagreement_score":0.8205032,"about_ca_system_score_codex":0.00006436358,"about_ca_system_score_gemma":0.0000412907,"threshold_uncertainty_score":0.4766075},"labels":[],"label_agreement":null},{"id":"W4403821441","doi":"10.48550/arxiv.2410.00802","title":"A practical guide to fitting correlation functions from lattice data","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Science and Technology Facilities Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Correlation; Statistical physics; Lattice (music); Computer science; Mathematics; Physics; Geometry","score_opus":0.20254420063618953,"score_gpt":0.3094327341186903,"score_spread":0.1068885334825008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403821441","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":[0.0061520506,0.000050094255,0.98738354,0.0015596626,0.001491074,0.0003265361,0.00013346472,0.0005127899,0.0023907577],"genre_scores_gemma":[0.55092627,0.000053337175,0.43005073,0.0002307355,0.00056044,0.0000040465966,0.000254103,0.000061363935,0.017858967],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99691314,0.00017581905,0.00025392347,0.0020176133,0.00022441741,0.00041506402],"domain_scores_gemma":[0.99541175,0.00073453755,0.00012987031,0.0032182417,0.00021855393,0.00028705716],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00048430753,0.00026552845,0.00024566738,0.0003138976,0.0002002787,0.00038997323,0.0027392346,0.00024001954,0.000039290066],"category_scores_gemma":[0.0006836541,0.00031949993,0.00008305263,0.0009975999,0.000057020457,0.0007580948,0.02256455,0.0014089752,0.0016633539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005497724,0.00013725253,0.0003125635,0.00014527049,0.00030386166,0.002029766,0.00048723278,0.91748613,0.00006336597,0.046234865,0.022486975,0.010257724],"study_design_scores_gemma":[0.00014919051,0.000029216942,0.00017579804,0.00018470394,0.00007333144,0.000009574116,0.00010249433,0.97126627,0.000011392338,0.01798195,0.009703246,0.00031284822],"about_ca_topic_score_codex":0.00060792593,"about_ca_topic_score_gemma":0.000104348735,"teacher_disagreement_score":0.5573328,"about_ca_system_score_codex":0.00041587616,"about_ca_system_score_gemma":0.00049003534,"threshold_uncertainty_score":0.99992573},"labels":[],"label_agreement":null},{"id":"W4404308404","doi":"10.48550/arxiv.2410.17976","title":"metasnf: Meta Clustering with Similarity Network Fusion in R","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Campbell Family Mental Health Research Institute; University of Toronto; Hospital for Sick Children; Natural Sciences and Engineering Research Council of Canada; Fondation Brain Canada; Centre for Addiction and Mental Health Foundation; Canada Research Chairs","keywords":"Similarity (geometry); Cluster analysis; Artificial intelligence; Fusion; Computer science; Pattern recognition (psychology); Philosophy; Linguistics","score_opus":0.12070957064102666,"score_gpt":0.22956725980234727,"score_spread":0.1088576891613206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404308404","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":[0.024941977,0.0006513669,0.9707259,0.00036455234,0.00058699393,0.00052709295,0.00001236044,0.0004703017,0.0017194841],"genre_scores_gemma":[0.950698,0.00027946098,0.046756733,0.00008110718,0.00012892441,0.0000073910246,0.000009365676,0.00005322436,0.0019857655],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965424,0.00027140658,0.00027243048,0.0018724853,0.00025377193,0.0007875113],"domain_scores_gemma":[0.99755996,0.00018444136,0.0001478256,0.0017507939,0.00013638286,0.00022061793],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0007183972,0.00049260113,0.00069329044,0.00047242682,0.00014789628,0.0002829981,0.0024700642,0.0002960544,0.000025306546],"category_scores_gemma":[0.000027011085,0.0004654359,0.000263483,0.0018339789,0.00012486872,0.00039702468,0.012818404,0.0019329381,0.00006615416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043155156,0.000042765663,0.00016217401,0.00020196068,0.00041572828,0.002358767,0.00013162034,0.9845035,0.000008598924,0.010692132,0.00006593966,0.0013736405],"study_design_scores_gemma":[0.00032692627,0.000067604575,0.00022514288,0.00021976799,0.00023948438,0.000017621864,0.000023657223,0.9424015,0.000035349854,0.055411518,0.000527512,0.00050388445],"about_ca_topic_score_codex":0.0003424168,"about_ca_topic_score_gemma":0.0008809965,"teacher_disagreement_score":0.92575604,"about_ca_system_score_codex":0.00046273766,"about_ca_system_score_gemma":0.00027804347,"threshold_uncertainty_score":0.99977976},"labels":[],"label_agreement":null},{"id":"W4404851989","doi":"10.1016/j.nepr.2024.104219","title":"Latent cluster analysis: Another method in search of a research question?","year":2024,"lang":"en","type":"editorial","venue":"Nurse Education in Practice","topic":"Advanced Clustering Algorithms Research","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":"Canadian Journal of Communication (Canada)","funders":"","keywords":"Cluster (spacecraft); Information retrieval; Psychology; Computer science","score_opus":0.03807364250420745,"score_gpt":0.5090188835520983,"score_spread":0.4709452410478909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404851989","genre_codex":"editorial","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008307269,0.0024668127,0.21608001,0.016087139,0.75196105,0.0016391355,0.00003335998,0.00014770111,0.011501701],"genre_scores_gemma":[0.00095206173,0.0010320084,0.67809176,0.00019157384,0.27026388,0.001195163,0.00015564272,0.00017949623,0.04793839],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9889918,0.0048158965,0.0009093058,0.0013416221,0.0032220162,0.00071934867],"domain_scores_gemma":[0.98352015,0.011666649,0.00027956365,0.0016650966,0.0027375913,0.00013092809],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.015929725,0.00028638085,0.0005683334,0.005328807,0.00006834801,0.0004214115,0.0018659441,0.0006687033,0.000036324134],"category_scores_gemma":[0.009461953,0.0002953004,0.00012829085,0.00944429,0.0001403139,0.0013539046,0.0005490247,0.004241825,0.00020751478],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023123149,0.0019539248,0.00020747296,0.0007025247,0.00045730863,0.00007211694,0.009359154,0.01122353,0.00003235929,0.007346107,0.9203099,0.04810436],"study_design_scores_gemma":[0.00068703643,0.0002406868,0.00051721017,0.0014281044,0.00022026902,0.000016580281,0.003315971,0.11191042,0.00010129009,0.0041523934,0.8768306,0.0005794631],"about_ca_topic_score_codex":0.0043461756,"about_ca_topic_score_gemma":0.00042064278,"teacher_disagreement_score":0.48169717,"about_ca_system_score_codex":0.0015631875,"about_ca_system_score_gemma":0.0069452985,"threshold_uncertainty_score":0.99994993},"labels":[],"label_agreement":null},{"id":"W4404973628","doi":"10.3390/a17120551","title":"Ellipsoidal K-Means: An Automatic Clustering Approach for Non-Uniform Data Distributions","year":2024,"lang":"en","type":"article","venue":"Algorithms","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"King Abdulaziz City for Science and Technology","keywords":"Cluster analysis; Ellipsoid; Computer science; Mathematics; Artificial intelligence; Physics","score_opus":0.06264586508325108,"score_gpt":0.3495320024963194,"score_spread":0.2868861374130683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404973628","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":[0.00011540686,0.00020081326,0.9960382,0.00041281807,0.00073190674,0.000715383,0.00040408436,0.0010433511,0.00033805583],"genre_scores_gemma":[0.008879453,0.0000293009,0.98882496,0.000040400035,0.0005301538,0.0002445596,0.00081861136,0.00005436451,0.00057821325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969481,0.00005074867,0.00040150955,0.0012303037,0.0005382094,0.0008311162],"domain_scores_gemma":[0.99689585,0.00024551977,0.0000505238,0.0024020835,0.00012005633,0.0002859473],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00089486514,0.00029135452,0.000283492,0.00021275243,0.00039677645,0.0009648855,0.0035246355,0.00011617756,0.000009393639],"category_scores_gemma":[0.00009161141,0.00027221334,0.000090819216,0.0008555767,0.0001050356,0.0027968057,0.0018322113,0.0003636691,0.00006698927],"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":[0.000003738455,0.00015456001,0.0000021513524,0.0003908374,0.000080801714,0.00006380571,0.0005343822,0.010741594,0.00018003721,0.0016472581,0.0010563233,0.9851445],"study_design_scores_gemma":[0.0002767728,0.00016277935,0.000020601845,0.00006528891,0.000015473292,0.00016317618,0.00008930602,0.9911536,0.00012285434,0.0013077232,0.0062776785,0.000344756],"about_ca_topic_score_codex":0.000040309427,"about_ca_topic_score_gemma":0.000010045449,"teacher_disagreement_score":0.98479974,"about_ca_system_score_codex":0.00019736186,"about_ca_system_score_gemma":0.00022378161,"threshold_uncertainty_score":0.999973},"labels":[],"label_agreement":null},{"id":"W4405631822","doi":"10.1016/j.rines.2024.100051","title":"Spatial characterisation of groundwater systems using fuzzy c-mean clustering: A multi-parameter approach in crystalline aquifers","year":2024,"lang":"en","type":"article","venue":"Results in Earth Sciences","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Energy","funders":"","keywords":"Aquifer; Groundwater; Cluster analysis; Fuzzy logic; Environmental science; Groundwater resources; Water resource management; Hydrology (agriculture); Geology; Data mining; Soil science; Computer science; Geotechnical engineering; Artificial intelligence","score_opus":0.07866996826638287,"score_gpt":0.33222634178589294,"score_spread":0.2535563735195101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405631822","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":[0.39186537,0.00014419571,0.60692316,0.00006877248,0.00040033658,0.00034007538,0.000007843886,0.00006408657,0.00018612904],"genre_scores_gemma":[0.872521,0.000020663787,0.12726556,0.000007890371,0.000067615314,0.000017535383,0.0000037597613,0.000010154861,0.00008583361],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968629,0.00021591582,0.00072778447,0.00085520523,0.000761533,0.000576683],"domain_scores_gemma":[0.99910855,0.00022683441,0.00012382667,0.00039799899,0.00006181161,0.00008099502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021949192,0.0001923013,0.00029820623,0.00087345217,0.0000878713,0.0005279515,0.00092278945,0.000089942485,0.0000013392819],"category_scores_gemma":[0.000116744326,0.00016052922,0.000052037616,0.0017162886,0.00030125992,0.0013072934,0.0004283049,0.00027995827,0.000005520768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001029211,0.0003074772,0.0021845547,0.00056163984,0.000017340211,0.00012734783,0.010107878,0.924258,0.014330301,0.00048536906,0.0000017623214,0.047515396],"study_design_scores_gemma":[0.0004868833,0.00014433442,0.0062632887,0.00033398205,0.0000012502002,0.000034523728,0.00025776876,0.99180275,0.0003712038,0.000068638336,0.000051627383,0.00018371899],"about_ca_topic_score_codex":0.0019499973,"about_ca_topic_score_gemma":0.0004134695,"teacher_disagreement_score":0.4806556,"about_ca_system_score_codex":0.00009339977,"about_ca_system_score_gemma":0.00017195304,"threshold_uncertainty_score":0.65461916},"labels":[],"label_agreement":null},{"id":"W4405765923","doi":"10.4230/lipics.esa.2022.56","title":"Improved Polynomial-Time Approximations for Clustering with Minimum Sum of Radii or Diameters","year":2022,"lang":"en","type":"preprint","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Algorithm; Mathematics; Combinatorics; Computer science; Statistics","score_opus":0.026285380078038455,"score_gpt":0.2950712382600269,"score_spread":0.26878585818198847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405765923","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":[0.009968891,0.00003944248,0.9780298,0.00041468075,0.0012511669,0.006051362,0.0034130192,0.00035967064,0.00047197056],"genre_scores_gemma":[0.025734626,0.00004354654,0.96502584,0.00029429712,0.00024619862,0.0041940436,0.0015216849,0.00022783794,0.0027119508],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945722,0.000093996845,0.0020365487,0.0008784428,0.0010002506,0.0014185121],"domain_scores_gemma":[0.99420106,0.000795919,0.0015670988,0.002457453,0.000623672,0.0003547681],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011382449,0.0008763144,0.0013232898,0.0008774255,0.0005857344,0.00066203246,0.0041060303,0.00039944847,0.000053227577],"category_scores_gemma":[0.00030844632,0.0007595661,0.0005493798,0.0006297855,0.0002829505,0.001480557,0.005703037,0.001171825,0.000010205649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016183557,0.0062713204,0.00084009906,0.09050906,0.009942262,0.000110591754,0.1430764,0.359467,0.0066401013,0.0030140264,0.02235442,0.34159115],"study_design_scores_gemma":[0.004350034,0.0012280716,0.00002206096,0.00035656392,0.000069536036,0.00005907971,0.0008700626,0.9772381,0.0012507556,0.0001924291,0.013387298,0.00097599666],"about_ca_topic_score_codex":0.000044899,"about_ca_topic_score_gemma":0.000026268708,"teacher_disagreement_score":0.6177711,"about_ca_system_score_codex":0.0006388776,"about_ca_system_score_gemma":0.0007585934,"threshold_uncertainty_score":0.99948555},"labels":[],"label_agreement":null},{"id":"W4406141871","doi":"10.1137/1.9781611978322.102","title":"The Johnson-Lindenstrauss Lemma for Clustering and Subspace Approximation: From Coresets to Dimension Reduction","year":2025,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Advanced Clustering Algorithms Research","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":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Lemma (botany); Dimensionality reduction; Subspace topology; Dimension (graph theory); Mathematics; Reduction (mathematics); Cluster analysis; Combinatorics; Pure mathematics; Computer science; Mathematical analysis; Artificial intelligence; Geometry; Statistics","score_opus":0.06832685645952044,"score_gpt":0.29021760091077076,"score_spread":0.22189074445125032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406141871","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":[0.0002625176,0.00015958164,0.9777785,0.0011271744,0.0006839934,0.0053906552,0.00016360988,0.00016224533,0.014271725],"genre_scores_gemma":[0.0005554715,0.00016540408,0.8516513,0.00011239827,0.0013776887,0.0011641708,0.00007295499,0.00011463706,0.14478596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981011,0.0000060457996,0.00046475118,0.00066723244,0.00037180493,0.0003890464],"domain_scores_gemma":[0.998055,0.0008665976,0.00027075497,0.00051514874,0.00014614992,0.0001463659],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00059472234,0.00036903596,0.00045428678,0.000054013275,0.00085370085,0.00042642228,0.0004592596,0.0005114095,8.2160886e-7],"category_scores_gemma":[0.00005506875,0.00029928182,0.00019888704,0.00003747457,0.00018081006,0.000059211514,0.0007389396,0.0004559301,0.000001216083],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001712899,0.00002060337,3.7787245e-8,0.00056615844,0.00035409498,6.2302377e-7,0.0033663716,0.00012387651,0.0015168197,0.50239295,0.010596561,0.4808906],"study_design_scores_gemma":[0.005055205,0.0004249499,3.554798e-7,0.0014734166,0.0002817646,0.000026592084,0.001260203,0.17786402,0.0064345705,0.6581044,0.1476488,0.0014257072],"about_ca_topic_score_codex":0.0000042330107,"about_ca_topic_score_gemma":0.000005245304,"teacher_disagreement_score":0.4794649,"about_ca_system_score_codex":0.00010839037,"about_ca_system_score_gemma":0.00012690725,"threshold_uncertainty_score":0.99994594},"labels":[],"label_agreement":null},{"id":"W4406170506","doi":"10.1109/tfuzz.2025.3526978","title":"A Vertical Federated Multiview Fuzzy Clustering Method for Incomplete Data","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Fuzzy Systems","topic":"Advanced Clustering Algorithms Research","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 Alberta","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Cluster analysis; Raw data; Flexibility (engineering); Data mining; Process (computing); Fuzzy clustering; Fuzzy logic; Machine learning; Distributed computing; Artificial intelligence","score_opus":0.08335018997250195,"score_gpt":0.3831114108535232,"score_spread":0.29976122088102125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406170506","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":[0.000055771674,0.00020469159,0.9937898,0.0008011583,0.0025099686,0.0013002433,0.00012620937,0.00046173198,0.0007504501],"genre_scores_gemma":[0.5225237,0.00005397061,0.4731409,0.00035155175,0.00015828022,0.0010173196,0.000022955583,0.000070258524,0.0026610799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968017,0.00039459005,0.0005906155,0.0010883218,0.0004644246,0.00066039833],"domain_scores_gemma":[0.9966081,0.0011165428,0.000057955378,0.0017886626,0.00024496933,0.00018378742],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010680392,0.0003029543,0.000493058,0.00037155463,0.00064341835,0.0005323559,0.0019092272,0.00014884607,0.000002571233],"category_scores_gemma":[0.00006160759,0.00029398178,0.00011896419,0.0009731278,0.000055806075,0.0006722924,0.00006401339,0.0004185595,0.000053051364],"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":[0.0002803182,0.00055159186,0.0000037537195,0.0015820966,0.00056707626,0.000046428806,0.00038572756,0.3070723,0.01035637,0.0027214854,0.0012233092,0.6752095],"study_design_scores_gemma":[0.0010616543,0.00012399325,0.000010958431,0.00033476044,0.000026776099,0.00003490655,0.000063958,0.98979425,0.0018148342,0.00023154964,0.00622948,0.0002728563],"about_ca_topic_score_codex":0.00033718557,"about_ca_topic_score_gemma":0.00019319117,"teacher_disagreement_score":0.682722,"about_ca_system_score_codex":0.00026952502,"about_ca_system_score_gemma":0.00021115386,"threshold_uncertainty_score":0.99995124},"labels":[],"label_agreement":null},{"id":"W4406266350","doi":"10.1109/vtc2024-fall63153.2024.10757898","title":"A Robust Clustering Scheme for Vehicular Communication Networks","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","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":"Polytechnique Montréal","funders":"","keywords":"Computer science; Scheme (mathematics); Cluster analysis; Computer network; Distributed computing; Artificial intelligence; Mathematics","score_opus":0.052503773740987955,"score_gpt":0.31585285650315836,"score_spread":0.2633490827621704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406266350","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":[0.00015047543,0.0012377745,0.9950552,0.0015525372,0.00020706971,0.00025987448,6.5895637e-7,0.0005889187,0.00094748585],"genre_scores_gemma":[0.05967794,0.000083169485,0.9381617,0.00010967989,0.0000952795,0.00013483729,0.0000057409347,0.000020759846,0.0017109094],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999007,0.000032811044,0.00015166639,0.00032737598,0.0001728092,0.0003083601],"domain_scores_gemma":[0.99885696,0.00025442304,0.000015540285,0.00072448695,0.0000791751,0.00006943931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003877456,0.00009620599,0.00009690679,0.000086565924,0.00014869569,0.000451119,0.00094141765,0.000055023356,0.000009241173],"category_scores_gemma":[0.00003710876,0.00008760357,0.00006007201,0.00037773707,0.000030480056,0.0005609631,0.00074900256,0.00019191144,0.000026753223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008044501,0.000035477755,0.000007784357,0.0001669031,0.00005242465,0.00001999413,0.00031404957,0.64216006,0.00063191104,0.063009895,0.0025684533,0.29102498],"study_design_scores_gemma":[0.0001095882,0.0000347014,0.000010010172,0.00006702914,0.0000014387589,0.000015747222,0.000013290532,0.9853109,0.00016438095,0.0011970496,0.012965602,0.00011024694],"about_ca_topic_score_codex":0.000012385814,"about_ca_topic_score_gemma":0.00001115695,"teacher_disagreement_score":0.34315085,"about_ca_system_score_codex":0.00008141532,"about_ca_system_score_gemma":0.00003607634,"threshold_uncertainty_score":0.43501508},"labels":[],"label_agreement":null},{"id":"W4407352320","doi":"10.2139/ssrn.5131398","title":"Fast Online $\\Ell_0$ Elastic Net Subspace Clustering Via a Novel Dictionary Update Strategy","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","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":"University of Alberta","funders":"","keywords":"Elastic net regularization; Subspace topology; Cluster analysis; Computer science; Net (polyhedron); Artificial intelligence; Pattern recognition (psychology); Mathematics; Feature selection","score_opus":0.017270484703722992,"score_gpt":0.298309612447457,"score_spread":0.281039127743734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407352320","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":[0.001842748,0.0027874897,0.9907318,0.0020020704,0.0015689221,0.00038169182,0.0000628612,0.00029307327,0.0003293877],"genre_scores_gemma":[0.6208747,0.037993006,0.29988602,0.00080655934,0.0054575168,0.00021387353,0.0003780224,0.0003932178,0.033997063],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99217343,0.00021594742,0.00084707636,0.0012446841,0.0010987117,0.004420122],"domain_scores_gemma":[0.99729365,0.00018746461,0.0005286904,0.0012348059,0.00042814907,0.00032723046],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0015107414,0.0007046811,0.0006685666,0.0007567716,0.0005209428,0.0006090726,0.003771417,0.00041560267,0.000016902552],"category_scores_gemma":[0.000089174275,0.0007181611,0.00033570497,0.0007520671,0.000119824406,0.00064040814,0.0045776106,0.011639733,0.000038117272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010752406,0.00040897357,0.00004353048,0.00018201275,0.0006680768,0.00010019297,0.00021483446,0.75930864,0.0005438469,0.017616918,0.00010514376,0.2207003],"study_design_scores_gemma":[0.0009878669,0.00035275417,0.00022323635,0.000378439,0.00004729834,0.0020698225,0.00021516277,0.9004484,0.000033794076,0.093461454,0.0010595218,0.0007222656],"about_ca_topic_score_codex":0.00016434454,"about_ca_topic_score_gemma":0.0012922888,"teacher_disagreement_score":0.6908457,"about_ca_system_score_codex":0.0035067706,"about_ca_system_score_gemma":0.008438903,"threshold_uncertainty_score":0.999527},"labels":[],"label_agreement":null},{"id":"W4407641753","doi":"10.32388/6yejp9","title":"Review of: \"Fixed-Sized Clusters k-Means\"","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Mathematics","score_opus":0.03736909423499118,"score_gpt":0.3719601192432709,"score_spread":0.3345910250082797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407641753","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.6973573e-9,0.4479843,0.43844858,0.072615,0.0019332289,0.0011382437,0.000057629186,0.00020703995,0.03761596],"genre_scores_gemma":[3.4573805e-8,0.48756126,0.11752495,0.020441324,0.000089793764,0.00012720963,0.00010311382,0.000023772638,0.37412855],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99489737,0.00039036156,0.0012767096,0.0012285031,0.0014785881,0.0007284531],"domain_scores_gemma":[0.9942789,0.0006063982,0.00051054347,0.0032545181,0.0011298187,0.00021981199],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017136977,0.0005857797,0.0018950874,0.00035542765,0.00008753277,0.000072258226,0.005279462,0.0002539457,0.0005335329],"category_scores_gemma":[0.001408834,0.00049525005,0.00058448175,0.0018447287,0.00012495629,0.0002943898,0.003247035,0.0009665338,0.0001974047],"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":[0.0000010433916,0.000021248927,6.659238e-8,0.13306062,0.000048518756,0.0000117773225,0.0000046072155,0.000006137436,8.842919e-7,0.000339279,0.70214766,0.16435814],"study_design_scores_gemma":[0.0001995027,0.000043589076,4.2689962e-7,0.19153056,0.000054558277,0.000017335307,8.7269916e-7,0.002893465,0.00002052972,0.00012879228,0.8047509,0.00035947817],"about_ca_topic_score_codex":0.000092656206,"about_ca_topic_score_gemma":0.000017111419,"teacher_disagreement_score":0.3365126,"about_ca_system_score_codex":0.00024957905,"about_ca_system_score_gemma":0.0012985739,"threshold_uncertainty_score":0.9997499},"labels":[],"label_agreement":null},{"id":"W4407827487","doi":"10.1109/tcyb.2025.3537108","title":"Automated Cluster Elimination Guided by High-Density Points","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Chengdu Science and Technology Program; Fundamental Research Funds for the Central Universities; Guangxi Key Research and Development Program; National Natural Science Foundation of China","keywords":"Cluster (spacecraft); Computer science; Operating system","score_opus":0.013430609403275243,"score_gpt":0.295411280232498,"score_spread":0.2819806708292228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407827487","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":[0.010381249,0.00001689973,0.9820243,0.004841376,0.00094568107,0.0002793079,0.00001535285,0.0009678353,0.00052798784],"genre_scores_gemma":[0.91604483,0.000037158115,0.076597765,0.00073061883,0.000017215112,0.000041775766,0.0000045979846,0.000020529622,0.006505502],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981939,0.00012909695,0.00032154933,0.00050572935,0.0004663535,0.00038338092],"domain_scores_gemma":[0.9985115,0.0002139787,0.00006086981,0.000861061,0.00024621066,0.000106362524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023890796,0.0002004156,0.00018594982,0.00027572556,0.0002661632,0.00015521856,0.0008733415,0.00014269646,0.000020563466],"category_scores_gemma":[0.00003272666,0.00021315037,0.000070716356,0.000782974,0.000080590515,0.00028572648,0.000022953327,0.00034011368,0.00014944185],"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":[0.00013420523,0.0011959041,0.000015027702,0.00016258175,0.00029574812,0.000055690125,0.0009985395,0.23284444,0.017504428,0.0052596796,0.07732394,0.6642098],"study_design_scores_gemma":[0.0007450253,0.000090751346,0.00037621343,0.0000431904,0.000013618217,0.000009672713,0.000008103583,0.87352526,0.12246601,0.0016289008,0.0008910178,0.0002022122],"about_ca_topic_score_codex":0.00012669164,"about_ca_topic_score_gemma":0.000036678113,"teacher_disagreement_score":0.9056636,"about_ca_system_score_codex":0.0002579342,"about_ca_system_score_gemma":0.000079097146,"threshold_uncertainty_score":0.86920196},"labels":[],"label_agreement":null},{"id":"W4407937849","doi":"10.1109/tpami.2025.3545573","title":"Gauging-: A Non-Parametric Hierarchical Clustering Algorithm","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cluster analysis; Artificial intelligence; Hierarchical clustering; Algorithm; Pattern recognition (psychology); Parametric statistics; Data mining; Mathematics; Statistics","score_opus":0.017910348891412187,"score_gpt":0.3089522056968399,"score_spread":0.2910418568054277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407937849","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":[0.000360235,0.000105413215,0.99813044,0.0006080218,0.0002791956,0.00017204121,0.000015963638,0.000135246,0.00019346148],"genre_scores_gemma":[0.9320175,0.00030782569,0.06626255,0.00051296374,0.000016275128,0.000049925384,0.0000022150837,0.000012452414,0.0008182681],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977448,0.00010344906,0.00044276225,0.00083044753,0.00041956606,0.00045895393],"domain_scores_gemma":[0.99850184,0.00035705423,0.00006953127,0.00078043615,0.0001033185,0.00018782547],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034089023,0.0002792597,0.0004166602,0.0020308958,0.00033531894,0.0002744802,0.00086659146,0.00008980843,0.0000640205],"category_scores_gemma":[0.000013268379,0.0002587305,0.00026524163,0.0045816856,0.00010961669,0.00035037252,0.000040672447,0.00062123046,0.000030411864],"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":[0.0000064849824,0.00010738677,0.0000615908,0.000021368962,0.00033185005,0.000021112171,0.00010436413,0.060603037,0.00008403469,0.000026530402,0.0000024149838,0.9386298],"study_design_scores_gemma":[0.00012004688,0.000093989875,0.0005679784,0.000039077597,0.0001284371,0.000012814667,0.000019961659,0.96950066,0.028842188,0.00037843175,0.00006609859,0.00023033161],"about_ca_topic_score_codex":0.000836284,"about_ca_topic_score_gemma":0.00022302484,"teacher_disagreement_score":0.9383995,"about_ca_system_score_codex":0.00009529044,"about_ca_system_score_gemma":0.00004572442,"threshold_uncertainty_score":0.99998647},"labels":[],"label_agreement":null},{"id":"W4408062361","doi":"10.5220/0013105300003893","title":"Data Clustering Using Mother Tree Optimization","year":2025,"lang":"en","type":"article","venue":"","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":"University of Regina","funders":"","keywords":"Computer science; Cluster analysis; Tree (set theory); Data mining; Artificial intelligence; Mathematics","score_opus":0.08909702423773201,"score_gpt":0.3795694031184865,"score_spread":0.2904723788807545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408062361","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":[0.00007134527,0.000039026647,0.98747116,0.0004730275,0.00018997512,0.0000976883,0.0000020494522,0.00019197604,0.011463758],"genre_scores_gemma":[0.0049239835,0.000008258526,0.9912926,0.00020221483,0.00002722215,0.0000025210957,0.0000038444946,0.000007732292,0.0035316022],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990377,0.000033053548,0.0001344233,0.00039869378,0.00017518607,0.00022095523],"domain_scores_gemma":[0.9985276,0.000050239298,0.000023617924,0.0013105364,0.00005092601,0.000037100002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020047273,0.00007814171,0.00008354527,0.00013980686,0.000102456164,0.00017841117,0.0017149338,0.000032497428,0.000021837332],"category_scores_gemma":[0.00005544501,0.00007354187,0.000012721094,0.00053522666,0.000022592838,0.0008604062,0.0025691157,0.00007919881,0.000009067661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024428684,0.00001601618,0.000035177523,0.000014060792,0.000011209736,0.000004689308,0.000029252684,0.8678541,0.00041438808,0.0014290935,0.00020198972,0.12998755],"study_design_scores_gemma":[0.00015213092,0.0000058732735,0.00003421167,0.000020312636,0.0000014744865,0.0000041033845,0.000011436697,0.9978955,0.00025163687,0.00024494107,0.0013046872,0.000073714444],"about_ca_topic_score_codex":0.000046169385,"about_ca_topic_score_gemma":0.000029554869,"teacher_disagreement_score":0.13004136,"about_ca_system_score_codex":0.000066494766,"about_ca_system_score_gemma":0.00006719694,"threshold_uncertainty_score":0.3202219},"labels":[],"label_agreement":null},{"id":"W4408609303","doi":"10.1109/tsmc.2025.3547350","title":"An Adaptive Federated Fuzzy C-Means Clustering With Nonindependently and Identically Distributed Data","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"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":"National Natural Science Foundation of China","keywords":"Independent and identically distributed random variables; Computer science; Cluster analysis; Fuzzy logic; Fuzzy clustering; Data mining; Artificial intelligence; Mathematics; Statistics; Random variable","score_opus":0.026326408643167022,"score_gpt":0.2855842154885161,"score_spread":0.25925780684534905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408609303","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":[0.005641279,0.00036066215,0.9913209,0.00008932592,0.0007932033,0.0008476743,0.00018220567,0.00026401522,0.00050073984],"genre_scores_gemma":[0.994852,0.000072628114,0.0034599747,0.000023521141,0.000044134722,0.00009262581,0.000017220318,0.00003174256,0.0014061445],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99695647,0.00031513025,0.00051063206,0.0010864486,0.0006173859,0.00051394803],"domain_scores_gemma":[0.9978415,0.00017261633,0.00012378015,0.0013129993,0.0002464829,0.00030266066],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005151845,0.0003515346,0.0004525404,0.00027897148,0.0005290319,0.0016229444,0.0009813185,0.00016393022,9.249055e-7],"category_scores_gemma":[0.000005532926,0.000313368,0.000026103593,0.0005537176,0.00015667234,0.00076270604,0.000053427735,0.0004126245,0.000008797131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011410483,0.0014539757,0.00060467015,0.0028820497,0.002019535,0.00085420586,0.0029863252,0.8981973,0.0052972795,0.018108957,0.00035498635,0.066099696],"study_design_scores_gemma":[0.0010407472,0.00052444235,0.00027863635,0.0006018071,0.000043749224,0.0002827811,0.0011507176,0.99523455,0.00014245826,0.00003303785,0.00031026814,0.0003567883],"about_ca_topic_score_codex":0.00080541405,"about_ca_topic_score_gemma":0.00054181874,"teacher_disagreement_score":0.9892107,"about_ca_system_score_codex":0.00013829487,"about_ca_system_score_gemma":0.000121441684,"threshold_uncertainty_score":0.9999318},"labels":[],"label_agreement":null},{"id":"W4408793869","doi":"10.1109/swc62898.2024.00216","title":"Clustering Algorithms with Balanced Weights for Geographic Data Processing","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 New Brunswick","funders":"Chinese Academy of Sciences","keywords":"Computer science; Cluster analysis; Data mining; Algorithm; Artificial intelligence","score_opus":0.04745828689423992,"score_gpt":0.3390360936300708,"score_spread":0.2915778067358309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408793869","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":[0.00021417707,0.00084878027,0.9957711,0.0008300812,0.00026792678,0.00041819343,0.00001717957,0.0010040515,0.00062850455],"genre_scores_gemma":[0.046200696,0.000037180744,0.95196676,0.00009085346,0.00021784514,0.000108607135,0.000029091474,0.00004234179,0.0013066133],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99763775,0.00002185754,0.0002100668,0.0010756159,0.00045972128,0.00059499225],"domain_scores_gemma":[0.9982841,0.00016657886,0.000031668726,0.0012526171,0.00012682349,0.00013821079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004149833,0.00020624168,0.00018441204,0.00025765144,0.0002288801,0.0009565755,0.0021915676,0.000054482993,0.0000071769164],"category_scores_gemma":[0.000023848836,0.00014805402,0.00003727135,0.00089914154,0.000075802294,0.0020781874,0.001202419,0.00020414198,0.000018158504],"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":[0.000019295703,0.000032459324,0.00004646785,0.00048425587,0.000054151482,0.000092896866,0.00023452802,0.00089155894,0.00033952025,0.0021581356,0.0002749106,0.9953718],"study_design_scores_gemma":[0.0002893795,0.00011966087,0.000086350316,0.00021739006,0.000006304705,0.00009236725,0.00002269617,0.98799556,0.00045873137,0.0011903847,0.0092687905,0.00025239252],"about_ca_topic_score_codex":0.000018981189,"about_ca_topic_score_gemma":0.00002323335,"teacher_disagreement_score":0.99511945,"about_ca_system_score_codex":0.0000460925,"about_ca_system_score_gemma":0.00017050031,"threshold_uncertainty_score":0.92242795},"labels":[],"label_agreement":null},{"id":"W4409363136","doi":"10.1609/aaai.v39i20.35385","title":"ICE-T: Interactions-aware Cross-column Contrastive Embedding for Heterogeneous Tabular Datasets","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Mitacs","keywords":"Column (typography); Computer science; Embedding; Artificial intelligence","score_opus":0.06925681773120876,"score_gpt":0.4013077380625092,"score_spread":0.33205092033130046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409363136","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":[0.021607801,0.00003784843,0.9725189,0.0021179153,0.0010671725,0.0011873855,0.00010316912,0.00015293514,0.0012068562],"genre_scores_gemma":[0.98701966,0.00001783125,0.011808418,0.0003060412,0.000065689645,0.00018391295,0.0000052405753,0.00001692124,0.0005762945],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755424,0.00002074074,0.00063336414,0.00077445287,0.0004593152,0.00055787346],"domain_scores_gemma":[0.99740046,0.000398376,0.00033152083,0.0004948088,0.0012726791,0.00010217962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004988272,0.00027567052,0.0003333418,0.00023096982,0.0004975112,0.00064424716,0.002775413,0.0000928157,0.000031146606],"category_scores_gemma":[0.0010386256,0.00023650353,0.0001578558,0.0007787852,0.00036522865,0.00097068463,0.00096436037,0.00040448617,0.000032763244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006739877,0.0005739104,0.00025137322,0.00045301148,0.00020679586,0.0000058783744,0.0013480771,0.0075076614,0.07822114,0.59842795,0.001140125,0.3111901],"study_design_scores_gemma":[0.000060587394,0.00013145324,0.00003520874,0.00031124018,0.000010692251,0.000005456627,0.00021107923,0.518326,0.4274079,0.05259284,0.0007202779,0.00018729565],"about_ca_topic_score_codex":0.00002545241,"about_ca_topic_score_gemma":0.000014748065,"teacher_disagreement_score":0.96541184,"about_ca_system_score_codex":0.00015662445,"about_ca_system_score_gemma":0.00017672316,"threshold_uncertainty_score":0.96443343},"labels":[],"label_agreement":null},{"id":"W4409885889","doi":"10.1007/s10586-024-04981-8","title":"SPINEX-clustering: similarity-based predictions with explainable neighbors exploration for clustering problems","year":2025,"lang":"en","type":"article","venue":"Cluster Computing","topic":"Advanced Clustering Algorithms Research","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 Manitoba","funders":"Clemson University","keywords":"Computer science; Cluster analysis; Similarity (geometry); Data mining; Artificial intelligence; Information retrieval; Image (mathematics)","score_opus":0.03347734993308603,"score_gpt":0.3032434677044574,"score_spread":0.2697661177713714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409885889","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":[0.0008481216,0.00007454455,0.991018,0.0034598147,0.0007769466,0.0017871902,0.0000070245246,0.000914254,0.0011141287],"genre_scores_gemma":[0.305872,0.0000035688877,0.6916,0.0009096939,0.00024127541,0.00039778213,0.000032448825,0.000065420056,0.00087781803],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99655586,0.00013514685,0.0006497647,0.0011213378,0.00049817923,0.0010397155],"domain_scores_gemma":[0.99748474,0.0005128468,0.00022922586,0.0010825648,0.00050263695,0.00018799973],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078604656,0.00043540922,0.00043091417,0.00059062673,0.0011003774,0.0007116463,0.0013060534,0.00015403875,0.00000310399],"category_scores_gemma":[0.00016625291,0.00042330104,0.00013061802,0.0013901492,0.00011622209,0.0013686825,0.0011742845,0.00042919745,0.000007001765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007017176,0.00010330585,0.00015418621,0.0005872401,0.000049860715,0.000009529666,0.00070178224,0.97563213,0.00025691692,0.0012713331,0.00036057035,0.020802999],"study_design_scores_gemma":[0.0022548633,0.00036065132,0.00014348082,0.0006312245,0.000019007955,0.000016786964,0.00017565048,0.9890886,0.0007609709,0.0013884229,0.0047365567,0.0004237797],"about_ca_topic_score_codex":0.000029420467,"about_ca_topic_score_gemma":0.00007952616,"teacher_disagreement_score":0.30502385,"about_ca_system_score_codex":0.00039143531,"about_ca_system_score_gemma":0.00031233032,"threshold_uncertainty_score":0.9998219},"labels":[],"label_agreement":null},{"id":"W4410398281","doi":"10.32473/flairs.38.1.138970","title":"Flexible Dirichlet Mixture Model for Multi-modal data Clustering","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Advanced Clustering Algorithms Research","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":"Concordia University","funders":"","keywords":"Modal; Cluster analysis; Latent Dirichlet allocation; Mixture model; Computer science; Dirichlet distribution; Data mining; Mathematics; Artificial intelligence; Topic model; Materials science","score_opus":0.3601967099388323,"score_gpt":0.46848168253118033,"score_spread":0.10828497259234804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410398281","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":[0.0015104585,0.00007421227,0.98502517,0.009911838,0.00088402315,0.00087774725,0.00009887792,0.0001169069,0.0015007964],"genre_scores_gemma":[0.5616374,0.0002532886,0.42975354,0.00024254563,0.00032349167,0.00029065952,0.000016696566,0.000031645115,0.0074507003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99566674,0.000027950924,0.000676033,0.0011043546,0.0016852437,0.0008396778],"domain_scores_gemma":[0.9939089,0.0005311086,0.00019579368,0.000901266,0.0043289815,0.00013395671],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0031512985,0.00025931833,0.00029597455,0.00023740708,0.00065914553,0.0008450337,0.012231864,0.00017237541,0.000012420605],"category_scores_gemma":[0.0023248943,0.00021790045,0.00023105853,0.0013653807,0.000582255,0.0014313832,0.008736842,0.00091347174,0.000010675614],"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":[0.00020710207,0.0003752105,0.00019083392,0.0005111713,0.00031002075,8.1816e-7,0.0039007154,0.016169045,0.10418768,0.74418706,0.0117922425,0.11816808],"study_design_scores_gemma":[0.000082355815,0.000031622574,0.000018761302,0.00020010359,0.000005706021,0.0000018570305,0.0007792484,0.8340309,0.08647263,0.07717104,0.0010454896,0.00016028289],"about_ca_topic_score_codex":0.00007856959,"about_ca_topic_score_gemma":0.000036097794,"teacher_disagreement_score":0.81786186,"about_ca_system_score_codex":0.00036949367,"about_ca_system_score_gemma":0.00074315444,"threshold_uncertainty_score":0.99928033},"labels":[],"label_agreement":null},{"id":"W4410920770","doi":"10.1007/s11634-025-00637-6","title":"Mixed-type kernel-based quantification of similarity for clustering","year":2025,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus","funders":"University of British Columbia","keywords":"Kernel (algebra); Similarity (geometry); Cluster analysis; Artificial intelligence; Computer science; Pattern recognition (psychology); Type (biology); Mathematics; Data mining; Combinatorics; Geology","score_opus":0.09468252969729223,"score_gpt":0.3986018150346892,"score_spread":0.303919285337397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410920770","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":[0.001399341,0.0009905266,0.99657315,0.00060580217,0.00009909812,0.00018657742,0.00003814236,0.000026328491,0.000081055594],"genre_scores_gemma":[0.7883241,0.00067489065,0.21051128,0.000028321303,0.000008981265,0.00003427511,0.00035672757,0.000003904143,0.000057506222],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998602,0.00007170324,0.00038115468,0.0006155725,0.00017309554,0.00015652893],"domain_scores_gemma":[0.9977986,0.0003435829,0.0001736069,0.0014637832,0.00019165743,0.000028728302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007282557,0.00009228375,0.00023367858,0.0004744635,0.00008273157,0.00006631353,0.0010203299,0.000050514136,0.0000012482006],"category_scores_gemma":[0.0003614655,0.00009222626,0.00003814689,0.002260755,0.00007912428,0.00092275743,0.00030661013,0.00007833189,5.714208e-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":[0.00009822736,0.00023047617,0.022337018,0.00044094995,0.00017757098,6.462937e-7,0.0000657501,0.06547756,0.009222901,0.036211815,0.00007663969,0.8656604],"study_design_scores_gemma":[0.00022086574,0.000017078946,0.030201219,0.000027051085,0.00005896796,8.6290655e-8,0.000042685348,0.9622673,0.0017152996,0.0019789254,0.0033902777,0.00008026157],"about_ca_topic_score_codex":0.000019052015,"about_ca_topic_score_gemma":0.0005105329,"teacher_disagreement_score":0.8967897,"about_ca_system_score_codex":0.000045725214,"about_ca_system_score_gemma":0.00006128224,"threshold_uncertainty_score":0.37608778},"labels":[],"label_agreement":null},{"id":"W4410944754","doi":"10.21203/rs.3.rs-6795375/v1","title":"Introduction of a Method to Choose the Number of Clusters of a Mixed Dataset under Kproto","year":2025,"lang":"en","type":"preprint","venue":"Research Square","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":"Statistics Canada","funders":"","keywords":"Computer science; Chemistry; Statistics; Mathematics","score_opus":0.0772401653793962,"score_gpt":0.48828246581726664,"score_spread":0.41104230043787043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410944754","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":[0.0030017863,0.00012973377,0.9835107,0.0076648733,0.00028995838,0.0033393712,0.0017823381,0.000038625567,0.00024266918],"genre_scores_gemma":[0.050220247,0.00018531978,0.94322926,0.00008454475,0.0005949236,0.0020111043,0.00071406196,0.000069138274,0.0028914036],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99260277,0.0023727757,0.00078089425,0.001073338,0.0024847328,0.00068551657],"domain_scores_gemma":[0.9923361,0.0014606962,0.0002864301,0.0038532657,0.0018850359,0.00017849515],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.006982376,0.00026261757,0.0006536917,0.0008002912,0.00012528752,0.00008732996,0.004276535,0.00022685196,0.0000654997],"category_scores_gemma":[0.0014736734,0.00020662067,0.00017695471,0.002406719,0.00036237357,0.00019495627,0.01318891,0.0015552513,0.000021238571],"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":[0.001520321,0.0017337471,0.0004976484,0.025105309,0.0012165431,0.000040539675,0.0084114345,0.23549768,0.011353176,0.040118773,0.12156569,0.5529391],"study_design_scores_gemma":[0.004453763,0.0019848412,0.013598633,0.008199877,0.0001309315,0.00010255573,0.0062677334,0.44809756,0.30345508,0.11427077,0.09717132,0.0022669462],"about_ca_topic_score_codex":0.0012809332,"about_ca_topic_score_gemma":0.000039298648,"teacher_disagreement_score":0.5506722,"about_ca_system_score_codex":0.00029847198,"about_ca_system_score_gemma":0.0009770255,"threshold_uncertainty_score":0.9947922},"labels":[],"label_agreement":null},{"id":"W4411086763","doi":"10.1109/tpami.2025.3577171","title":"A Clustering Validity Index With Multi-Granularity Fusion for Multiple Fuzzy Clustering Algorithms","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":3,"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":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Cluster analysis; Granularity; Computer science; Fuzzy clustering; Artificial intelligence; Data mining; Pattern recognition (psychology); Fuzzy logic; Index (typography); Fusion; Fuzzy set; Algorithm","score_opus":0.04519106119666905,"score_gpt":0.3254033522786221,"score_spread":0.28021229108195306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411086763","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":[0.0014031078,0.00005874009,0.9971983,0.00029458717,0.000254603,0.00053563307,0.000055413784,0.00018123437,0.000018386965],"genre_scores_gemma":[0.8819436,0.00013337453,0.117216416,0.00023126682,0.000016690927,0.00015598789,0.0000065777635,0.000019305662,0.00027681835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974834,0.00012326306,0.00047880362,0.001002335,0.00039767456,0.0005145546],"domain_scores_gemma":[0.99825525,0.00042493822,0.00011761223,0.000807789,0.00021554717,0.00017886364],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049032655,0.0003671119,0.00050083315,0.00090277905,0.00059066765,0.00027949217,0.0007482633,0.00011963139,0.0000113978585],"category_scores_gemma":[0.00001948437,0.00031805842,0.00026884777,0.001682444,0.0001101659,0.00047369764,0.000052316154,0.0004659502,0.0000038952544],"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":[0.00008447042,0.00022078534,0.001346546,0.00010736231,0.0003641346,0.000011688216,0.00023973298,0.25265115,0.00035401733,0.000005147993,9.267856e-7,0.744614],"study_design_scores_gemma":[0.00055892224,0.00019285643,0.0016067392,0.00009407516,0.00018179884,0.0000111334875,0.0000575279,0.96743053,0.02942112,0.00008531206,0.000035461188,0.00032452436],"about_ca_topic_score_codex":0.0018247912,"about_ca_topic_score_gemma":0.0069286656,"teacher_disagreement_score":0.88054043,"about_ca_system_score_codex":0.00011922162,"about_ca_system_score_gemma":0.00004725002,"threshold_uncertainty_score":0.99992716},"labels":[],"label_agreement":null},{"id":"W4411635074","doi":"10.1016/j.patcog.2025.111953","title":"WANN-DPC: Density peaks finding clustering based on Weighted Adaptive Nearest Neighbors","year":2025,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":7,"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":"Natural Science Basic Research Program of Shaanxi Province; China Postdoctoral Science Foundation; Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China","keywords":"Cluster analysis; Pattern recognition (psychology); Artificial intelligence; k-nearest neighbors algorithm; Computer science; Mathematics; Algorithm","score_opus":0.03834201504974158,"score_gpt":0.2962184310452347,"score_spread":0.25787641599549316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411635074","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":[0.038755406,0.0000112310145,0.95640343,0.00077925826,0.0006206159,0.00033553876,0.000019446987,0.00030654616,0.0027685114],"genre_scores_gemma":[0.962768,0.000006847315,0.035795696,0.0009983543,0.00010672538,0.00007176438,0.000036663172,0.000022776978,0.00019315083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978267,0.00019868238,0.0002855429,0.0007104118,0.0004594818,0.0005191809],"domain_scores_gemma":[0.99861735,0.00037771338,0.00010484201,0.00055835414,0.00022123902,0.00012051947],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033741022,0.00024478536,0.00022456136,0.0004480863,0.0003338896,0.00023946607,0.0005985913,0.000114354705,0.00004587113],"category_scores_gemma":[0.00010840311,0.00025543902,0.00009175268,0.00067086157,0.00005127695,0.00044222534,0.00040509665,0.00043935163,0.0002471041],"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":[0.00006831443,0.00010640684,0.0015009767,0.00007018148,0.000026363556,0.00009625518,0.00018181575,0.0018189298,0.00036732282,0.000030409386,0.00012699624,0.995606],"study_design_scores_gemma":[0.0007716785,0.00017158157,0.011787243,0.0004531905,0.000008711261,0.0000073641804,0.000033411092,0.9780821,0.006953774,0.0013210651,0.00011984802,0.0002899822],"about_ca_topic_score_codex":0.00010062603,"about_ca_topic_score_gemma":0.000113855465,"teacher_disagreement_score":0.995316,"about_ca_system_score_codex":0.00030096504,"about_ca_system_score_gemma":0.00008851302,"threshold_uncertainty_score":0.9999898},"labels":[],"label_agreement":null},{"id":"W4411655587","doi":"10.18280/ria.390201","title":"Exploring Swarm Intelligence for Enhanced Clustering in Artificial Intelligence: A PSO-Kmeans Hybrid Approach","year":2025,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"k-means clustering; Swarm intelligence; Cluster analysis; Particle swarm optimization; Artificial intelligence; Computer science; Pattern recognition (psychology); Machine learning","score_opus":0.16023196000590909,"score_gpt":0.34934451377614545,"score_spread":0.18911255377023636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411655587","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":[0.0058176555,0.0002781172,0.9848318,0.0008788395,0.0013793482,0.0016430009,0.000010987695,0.0004027835,0.0047574434],"genre_scores_gemma":[0.81876343,0.0003764924,0.17810142,0.00013888215,0.00018991431,0.0013619192,0.000012439261,0.00005829413,0.0009971979],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937991,0.00018788691,0.0017876044,0.0019932587,0.0005639571,0.0016681982],"domain_scores_gemma":[0.99614096,0.0010570069,0.0002512697,0.001860686,0.00042494133,0.000265138],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018562296,0.00061804184,0.0007573675,0.001144347,0.00049443555,0.0004976136,0.0032637038,0.00016350647,0.000033193963],"category_scores_gemma":[0.00092616864,0.0006902386,0.0003128036,0.0029885347,0.00028965087,0.0014084436,0.0013166936,0.00084964384,0.00027111606],"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":[0.00008229878,0.00031361522,0.0000073535043,0.00030427793,0.000021432092,0.000023334143,0.0024088884,0.4538046,0.0038734532,0.029130949,0.000020886544,0.5100089],"study_design_scores_gemma":[0.000035440396,0.00012453397,0.0000051559728,0.00029279405,0.0000066969965,0.000016379867,0.0019124681,0.64270735,0.3337289,0.020310592,0.0004234735,0.00043619817],"about_ca_topic_score_codex":0.00008112257,"about_ca_topic_score_gemma":0.000053640553,"teacher_disagreement_score":0.8129458,"about_ca_system_score_codex":0.0005414119,"about_ca_system_score_gemma":0.0002629804,"threshold_uncertainty_score":0.9995549},"labels":[],"label_agreement":null},{"id":"W4412421561","doi":"10.1016/j.patcog.2025.112128","title":"Gauging- <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si3.svg\"> <mml:mi>β</mml:mi> </mml:math> : Border-aware hierarchical clustering based on density and proximity","year":2025,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"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","keywords":"Cluster analysis; Computer science; Scalable Vector Graphics; Hierarchical clustering; Mathematics; Artificial intelligence; World Wide Web","score_opus":0.024043183018317774,"score_gpt":0.27805980188601126,"score_spread":0.2540166188676935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412421561","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":[0.6045185,0.00002037715,0.3936929,0.00066072546,0.00030721375,0.00008717439,0.0000240183,0.00018111861,0.00050799403],"genre_scores_gemma":[0.98491555,0.00004187143,0.013341203,0.0011698733,0.00016720095,0.00019068268,0.00008898559,0.000046670055,0.000037958027],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745667,0.00015890364,0.0003648977,0.0008065791,0.00061511964,0.0005978523],"domain_scores_gemma":[0.9984247,0.00043059135,0.00017640534,0.0006637169,0.000111585854,0.00019298325],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058537174,0.0002591925,0.00017677198,0.00020955152,0.00048730712,0.0003855652,0.00051714637,0.00024907364,0.0000325899],"category_scores_gemma":[0.00026173666,0.0003196268,0.00013772016,0.00033549915,0.0001573896,0.0005241829,0.00085128384,0.0006410169,0.00022452924],"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":[0.00045238345,0.00037499296,0.00022943651,0.0013296645,0.00013240341,0.00051336014,0.0008486323,0.0015023951,0.0009060661,0.0798822,0.00016151105,0.91366696],"study_design_scores_gemma":[0.00063571,0.0003922422,0.0007743453,0.0005979816,0.000026461159,0.000078965844,0.000052541513,0.98765236,0.008222136,0.0011328354,0.00015330629,0.0002811258],"about_ca_topic_score_codex":0.00013554377,"about_ca_topic_score_gemma":0.0002329714,"teacher_disagreement_score":0.98614997,"about_ca_system_score_codex":0.000043972384,"about_ca_system_score_gemma":0.00016844107,"threshold_uncertainty_score":0.99992555},"labels":[],"label_agreement":null},{"id":"W4413324958","doi":"10.1016/j.neucom.2025.131324","title":"S2F: Border peeling clustering from cluster skeletons to final clusters","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","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":"University of Alberta","funders":"Yangzhou University; Ministry of Education of the People's Republic of China; Ministry of Education; Natural Science Foundation of Yangzhou City","keywords":"Cluster (spacecraft); Cluster analysis; Computer science; Artificial intelligence; Computer network","score_opus":0.022156098549891222,"score_gpt":0.3391739224309043,"score_spread":0.31701782388101307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413324958","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":[0.050830465,0.00004710462,0.93765044,0.0057494445,0.00134043,0.00051620766,0.0000037552547,0.0006275624,0.0032345816],"genre_scores_gemma":[0.42406908,0.0000058371456,0.5655187,0.007956952,0.00045833972,0.000053783046,0.000005394364,0.0000621308,0.0018697835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961793,0.00020444211,0.0006043496,0.0013147186,0.0006044516,0.0010927741],"domain_scores_gemma":[0.9974092,0.0008369407,0.000111275906,0.0011656076,0.00019481985,0.00028213862],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004574707,0.00038271188,0.00038782324,0.0005434522,0.00060504413,0.00060306716,0.002229515,0.000115476985,0.000014189029],"category_scores_gemma":[0.00032488987,0.0004202483,0.00013763495,0.0015192569,0.000050287665,0.00047958962,0.0044197026,0.0007069052,0.00013425942],"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":[0.000049644197,0.00008156168,0.0004960279,0.0000811964,0.000051586645,0.00011220593,0.0012517953,0.3887246,0.004584993,0.0005074998,0.0016831689,0.60237575],"study_design_scores_gemma":[0.0008146704,0.00007385503,0.0026167578,0.00023452162,0.0000075727335,0.000017764398,0.000059270562,0.97244084,0.0010223731,0.0005012206,0.02181216,0.00039901168],"about_ca_topic_score_codex":0.00014308555,"about_ca_topic_score_gemma":0.00003671898,"teacher_disagreement_score":0.60197675,"about_ca_system_score_codex":0.00020651515,"about_ca_system_score_gemma":0.00015463296,"threshold_uncertainty_score":0.99982494},"labels":[],"label_agreement":null},{"id":"W4413359139","doi":"10.1109/access.2025.3600986","title":"Deep Clustering With Self-Supervision Using Pairwise Similarities","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Cluster analysis; Pairwise comparison; Artificial intelligence","score_opus":0.03610949039550173,"score_gpt":0.3456854684973579,"score_spread":0.30957597810185616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413359139","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":[0.028344862,0.00018567275,0.96911937,0.00036738507,0.00043781998,0.00021372191,7.29963e-7,0.0004129815,0.0009174414],"genre_scores_gemma":[0.61229336,0.00006419699,0.3864908,0.0006821804,0.00011283566,0.00003727735,9.2698093e-7,0.000029260926,0.00028916268],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983138,0.00007517643,0.00020932013,0.0005117513,0.00041670405,0.00047324918],"domain_scores_gemma":[0.998789,0.00013593891,0.00004898578,0.0007558961,0.0001787645,0.000091386624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021968853,0.0001874662,0.00019939155,0.0002700362,0.0003083844,0.0007434185,0.0019126551,0.00006857811,0.000006483762],"category_scores_gemma":[0.000021488384,0.00016401277,0.000039816685,0.0008112458,0.000056455625,0.0019375171,0.001150021,0.0002359255,0.000006008928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009711902,0.00024061059,0.0031558922,0.0007419331,0.00016559285,0.00040536118,0.001940665,0.6738139,0.0023903705,0.0014236862,0.00025884443,0.31536603],"study_design_scores_gemma":[0.00041468846,0.000044087752,0.00045200266,0.00015482814,0.0000068747186,0.000022387658,0.000033539738,0.9935929,0.0037225094,0.00078027917,0.0005714883,0.00020437878],"about_ca_topic_score_codex":0.000093181465,"about_ca_topic_score_gemma":0.0000546616,"teacher_disagreement_score":0.5839485,"about_ca_system_score_codex":0.00017189508,"about_ca_system_score_gemma":0.00013718531,"threshold_uncertainty_score":0.7168802},"labels":[],"label_agreement":null},{"id":"W4414183863","doi":"10.3390/app151810052","title":"AutoProPos: An Extension of Prototype Scattering and Positive Sampling Clustering for an Unknown Number of Clusters","year":2025,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Silhouette; Cluster analysis; Pattern recognition (psychology); Subspace topology; Extension (predicate logic); Autoencoder; Image (mathematics); Parametric statistics; Binary number","score_opus":0.047046133104338805,"score_gpt":0.3798647348832161,"score_spread":0.3328186017788773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414183863","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":[0.24333493,0.000024460925,0.75468004,0.0001173778,0.00009529134,0.00079940906,0.0000031469929,0.000052864634,0.00089251203],"genre_scores_gemma":[0.64548683,0.0000033396007,0.3543714,0.000044618744,0.000012416693,0.000055508113,0.0000010497956,0.0000053274343,0.000019478211],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983499,0.00003860158,0.00030634925,0.00064163713,0.00032382918,0.0003396808],"domain_scores_gemma":[0.99904406,0.00018660465,0.000129323,0.00039795818,0.00016094832,0.00008109353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083917665,0.00013750246,0.00024154899,0.00019091656,0.00030795677,0.000117643634,0.0008463756,0.000052403546,0.000001082],"category_scores_gemma":[0.0000394177,0.00012298564,0.000028364733,0.0006444662,0.0005131726,0.00066442875,0.00058634585,0.00008839345,4.9464467e-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":[0.00022931182,0.00019350839,0.0004953432,0.000517133,0.000031773507,0.0000014697364,0.004357269,0.018223016,0.37095836,0.06342648,0.0000042696975,0.5415621],"study_design_scores_gemma":[0.00066282053,0.0007363016,0.0031300923,0.00027793788,0.000009516003,0.000015266414,0.00077478174,0.8896386,0.089492336,0.014921621,0.000048623406,0.000292084],"about_ca_topic_score_codex":0.00005926263,"about_ca_topic_score_gemma":0.000019693334,"teacher_disagreement_score":0.8714156,"about_ca_system_score_codex":0.000031426705,"about_ca_system_score_gemma":0.00011451343,"threshold_uncertainty_score":0.50152093},"labels":[],"label_agreement":null},{"id":"W4414633048","doi":"10.48550/arxiv.2504.15781","title":"Interacting Immediate Neighbour Interpolation for Geoscientific Data","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Resources Canada","keywords":"Interpolation (computer graphics); Curvature; Multivariate interpolation; Range (aeronautics); Trilinear interpolation; Grid; Function (biology); Nearest-neighbor interpolation","score_opus":0.15263742288790713,"score_gpt":0.40201059623415186,"score_spread":0.24937317334624473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414633048","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":[0.0211827,0.00016836468,0.9679986,0.0011899172,0.0073869475,0.0007688417,0.0004013651,0.0002986181,0.00060464686],"genre_scores_gemma":[0.55226195,0.000099331766,0.43058842,0.0005707844,0.0013108198,0.00042122632,0.0019260485,0.00008008265,0.012741336],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99643666,0.00011447749,0.00056660565,0.0018220054,0.0004185224,0.00064175087],"domain_scores_gemma":[0.994584,0.00076194963,0.00036509847,0.0038109096,0.0003424119,0.00013559373],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0011011545,0.0003329996,0.00036819762,0.00040637373,0.0002678225,0.00057486945,0.006124008,0.00020841205,0.000014801152],"category_scores_gemma":[0.0014537547,0.0003474666,0.00012491988,0.00042818463,0.00007078473,0.0010578958,0.018774,0.0009895503,0.00007485729],"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":[0.00028603952,0.00081107335,0.0553527,0.004919894,0.00090542116,0.00014672652,0.0076467446,0.01492279,0.011801293,0.004693938,0.029426793,0.86908656],"study_design_scores_gemma":[0.00029495,0.0000301912,0.0032998873,0.00048953696,0.000015538453,0.000004299598,0.00005507731,0.98131007,0.0007496881,0.0017480989,0.011640552,0.00036213596],"about_ca_topic_score_codex":0.00017138069,"about_ca_topic_score_gemma":0.000046921923,"teacher_disagreement_score":0.9663873,"about_ca_system_score_codex":0.00019997006,"about_ca_system_score_gemma":0.00039503764,"threshold_uncertainty_score":0.9998977},"labels":[],"label_agreement":null},{"id":"W4415092883","doi":"10.1007/978-3-032-08649-5_4","title":"Pairwise Clustering on Numerical Datasets by Translation","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","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":"University of Windsor","funders":"","keywords":"Pairwise comparison; Cluster analysis; Partition (number theory); Categorical variable; Parameterized complexity; Constrained clustering; Set (abstract data type); Computation; Similarity (geometry)","score_opus":0.05057951670700949,"score_gpt":0.3428955448297427,"score_spread":0.2923160281227332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415092883","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":[0.0000011069467,0.0002460418,0.9072669,0.0014870906,0.00017887643,0.00032686314,0.000085315856,0.00010313449,0.09030468],"genre_scores_gemma":[0.00838107,0.004857659,0.977915,0.0033122564,0.00006096394,0.000109672736,0.00091412134,0.000025682479,0.004423602],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980643,0.000043697604,0.00058964686,0.0003908842,0.00062339555,0.00028812332],"domain_scores_gemma":[0.9966418,0.00039395664,0.00018548204,0.0024829158,0.00017601188,0.00011980167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081254204,0.00023195818,0.00023387566,0.0009571788,0.00046778008,0.0006101686,0.0039063427,0.00011959448,0.000005023132],"category_scores_gemma":[0.000050048486,0.000241691,0.000036618112,0.000552618,0.00046919502,0.005529328,0.0027462845,0.0006007783,0.00004658934],"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":[0.0000037334366,0.000016625225,0.0000016340186,0.000030178277,0.0000036439276,4.907487e-7,0.0003907122,0.0012397927,0.0000029010241,0.07181577,0.0014699097,0.9250246],"study_design_scores_gemma":[0.00020249106,0.000048636408,0.000028749273,0.00017755783,0.0000015148261,0.0000062210966,0.0000031646912,0.75433886,0.000009889047,0.0013447324,0.24364546,0.00019274467],"about_ca_topic_score_codex":0.000009700084,"about_ca_topic_score_gemma":0.0000032150379,"teacher_disagreement_score":0.92483187,"about_ca_system_score_codex":0.00022938744,"about_ca_system_score_gemma":0.00023225206,"threshold_uncertainty_score":0.9855873},"labels":[],"label_agreement":null},{"id":"W4415826823","doi":"10.1016/j.neucom.2025.131886","title":"Evidential clustering with view-weight learning for proximity data","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Clustering Algorithms Research","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":"Simon Fraser University","funders":"Agence Nationale de la Recherche","keywords":"Cluster analysis; Interpretability; Categorical variable; Constraint (computer-aided design); Conceptual clustering; Matching (statistics); Constrained clustering; Relational database","score_opus":0.04372034419290236,"score_gpt":0.342046180839285,"score_spread":0.2983258366463826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415826823","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":[0.0035301698,0.00009260064,0.9936606,0.0007384938,0.00041266542,0.0006239255,0.0000011496936,0.00043712658,0.0005032205],"genre_scores_gemma":[0.37518337,0.000013553373,0.6231614,0.00037809266,0.0003573237,0.00006088045,0.00001232741,0.00004223659,0.00079085643],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975928,0.00012644578,0.0003004937,0.0010253005,0.0003546677,0.0006002912],"domain_scores_gemma":[0.99795395,0.00052358466,0.00011853324,0.0011624177,0.00015902834,0.000082509105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006356807,0.00020124676,0.00023866593,0.00017619325,0.000571535,0.0004160651,0.0025733113,0.00004828034,0.0000013327804],"category_scores_gemma":[0.0003107313,0.00018527571,0.000040546754,0.00068666774,0.000047053578,0.0010061847,0.004032575,0.00044393688,0.0000058948513],"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":[0.000057074223,0.000061720675,0.00095103116,0.00042207548,0.00004781609,0.000046157405,0.0002161316,0.08241938,0.0015372584,0.0011067371,0.00028426864,0.9128503],"study_design_scores_gemma":[0.0006070166,0.00010705458,0.0006457483,0.00019696564,0.0000076128294,0.000028504286,0.000010208239,0.97906756,0.0007330084,0.00020762756,0.01820874,0.00017992401],"about_ca_topic_score_codex":0.000011054417,"about_ca_topic_score_gemma":0.000009587068,"teacher_disagreement_score":0.91267043,"about_ca_system_score_codex":0.00005760323,"about_ca_system_score_gemma":0.00013713446,"threshold_uncertainty_score":0.75553244},"labels":[],"label_agreement":null},{"id":"W4416221854","doi":"10.1016/j.compind.2025.104410","title":"Integrating static and dynamic hierarchical clustering and its application to retail segmentation","year":2025,"lang":"en","type":"article","venue":"Computers in Industry","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Ministerio de Ciencia e Innovación","keywords":"Cluster analysis; Profiling (computer programming); Hierarchical clustering; Variety (cybernetics); Big data; Key (lock); Identification (biology); Market segmentation; Dynamic data","score_opus":0.016353627886842876,"score_gpt":0.32588103996101325,"score_spread":0.3095274120741704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416221854","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":[0.18253592,0.00006029726,0.8151263,0.0016986565,0.00012020272,0.00030090287,8.943688e-7,0.00006015434,0.00009667051],"genre_scores_gemma":[0.68294984,0.000012127288,0.31643742,0.00040355936,0.000015109093,0.00006616344,0.000002241521,0.000007289804,0.000106233],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883413,0.000076598175,0.00023206692,0.00045543176,0.00015567313,0.00024608348],"domain_scores_gemma":[0.9993755,0.00021262137,0.00003866109,0.0002344969,0.000039862265,0.00009881119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002663762,0.00012035698,0.0001397829,0.00030100383,0.00009976075,0.00014871506,0.00036832213,0.00012058097,6.6072056e-7],"category_scores_gemma":[0.0000742813,0.00012944694,0.000009315039,0.00061044534,0.0000373482,0.00028702183,0.00090272084,0.0005890895,0.0000018950265],"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":[0.0000088868865,0.000019796473,0.0010794143,0.000103249455,0.000008417608,0.000011306049,0.0011899807,0.008414617,0.002946707,0.002822942,0.00002229729,0.9833724],"study_design_scores_gemma":[0.00029716935,0.00004157613,0.00489319,0.00020751964,0.0000012658285,0.000012412276,0.00014507015,0.99226236,0.00031550642,0.0016493949,0.00006112372,0.0001134078],"about_ca_topic_score_codex":0.00001229313,"about_ca_topic_score_gemma":0.00001792443,"teacher_disagreement_score":0.98384774,"about_ca_system_score_codex":0.00016644102,"about_ca_system_score_gemma":0.000047560632,"threshold_uncertainty_score":0.5278693},"labels":[],"label_agreement":null},{"id":"W4416455941","doi":"10.7717/peerj-cs.3309","title":"The Silhouette coefficient and the Davies-Bouldin index are more informative than Dunn index, Calinski-Harabasz index, Shannon entropy, and Gap statistic for unsupervised clustering internal evaluation of two convex clusters","year":2025,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Silhouette; Cluster analysis; Rand index; Pattern recognition (psychology); Ground truth; Consensus clustering; Euclidean distance; Correlation clustering","score_opus":0.0262903710357365,"score_gpt":0.34893061353911187,"score_spread":0.32264024250337536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416455941","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":[0.081946395,0.0002704879,0.91311824,0.0023275998,0.0007179963,0.0014980839,0.000025494754,0.000053847376,0.00004187218],"genre_scores_gemma":[0.9855249,0.00003389925,0.013746827,0.00041464382,0.000054060947,0.0001538978,0.0000027836547,0.000011685013,0.000057312463],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955573,0.00034758187,0.00068574393,0.00078495784,0.0018968808,0.00072754914],"domain_scores_gemma":[0.99579775,0.0014820119,0.0004086071,0.000841974,0.0012950607,0.00017457324],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005510658,0.00032125096,0.00043145774,0.00042202682,0.0010936175,0.0010818699,0.0023594939,0.00006137125,0.0000012605693],"category_scores_gemma":[0.0005196544,0.00021222112,0.00007342413,0.0012284308,0.0024837726,0.0010058586,0.0031929354,0.00040394522,9.752703e-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":[0.0006152953,0.000107096545,0.0075294343,0.00039880743,0.00016266944,0.000008967187,0.020460391,0.40238497,0.00030904004,0.011363533,0.00015221171,0.5565076],"study_design_scores_gemma":[0.0040600034,0.000116484385,0.026874881,0.00022896563,0.000021530144,0.000024550498,0.0005193836,0.964752,0.0003373733,0.002775573,0.00007492906,0.0002143312],"about_ca_topic_score_codex":0.00016934567,"about_ca_topic_score_gemma":0.00012050995,"teacher_disagreement_score":0.9035785,"about_ca_system_score_codex":0.0002783602,"about_ca_system_score_gemma":0.00048639672,"threshold_uncertainty_score":0.9999551},"labels":[],"label_agreement":null},{"id":"W4416959460","doi":"10.1016/j.patcog.2025.112829","title":"Fast online ℓ0 elastic net subspace clustering via a novel dictionary update strategy","year":2025,"lang":"en","type":"article","venue":"Pattern Recognition","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":"University of Alberta","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Cluster analysis; Subspace topology; Block (permutation group theory); Piecewise; Diagonal; Data stream clustering; Adaptability; Norm (philosophy); Convergence (economics); Elastic net regularization","score_opus":0.03269478410830945,"score_gpt":0.3017830425501344,"score_spread":0.26908825844182493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416959460","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":[0.024699623,0.000058526915,0.97260046,0.0010361274,0.0006052784,0.00024614393,0.00008218298,0.00030461414,0.00036703591],"genre_scores_gemma":[0.92984486,0.00009215945,0.06790096,0.0008634511,0.00027500378,0.000104514525,0.00033736802,0.000037371577,0.0005443297],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818957,0.00007303016,0.00031592458,0.00060856243,0.00034254935,0.00047034005],"domain_scores_gemma":[0.99903774,0.00013333728,0.00009576865,0.00042963398,0.00019149005,0.00011203344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017529273,0.0002190651,0.00019185377,0.0003086664,0.00019056408,0.0001922565,0.00055895926,0.000092814,0.000050311304],"category_scores_gemma":[0.000038604026,0.00023573628,0.0000639012,0.0006093578,0.00004877561,0.00066929177,0.00054335326,0.0003648265,0.00020748061],"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":[0.000018610901,0.00018746457,0.00026107326,0.00008835684,0.000036232665,0.000030742776,0.00007546316,0.0057988768,0.003327476,0.000016056158,0.000081403094,0.9900783],"study_design_scores_gemma":[0.0008281511,0.00011267471,0.01007458,0.00023501823,0.000012685671,0.00008187173,0.000058643785,0.98519766,0.0010535002,0.0016810489,0.0003688213,0.00029536098],"about_ca_topic_score_codex":0.00008874115,"about_ca_topic_score_gemma":0.00016503134,"teacher_disagreement_score":0.98978287,"about_ca_system_score_codex":0.00015200763,"about_ca_system_score_gemma":0.0000698383,"threshold_uncertainty_score":0.9613046},"labels":[],"label_agreement":null},{"id":"W4416963394","doi":"10.1109/cisp-bmei68103.2025.11259320","title":"Clustering Through Classifying: A Novel Neural-Based Approach","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 Lethbridge","funders":"","keywords":"Cluster analysis; Focus (optics); Correlation clustering; CURE data clustering algorithm; Data stream clustering; Conceptual clustering; Canopy clustering algorithm; Encoding (memory); Object (grammar)","score_opus":0.08079583600671128,"score_gpt":0.3511631127687199,"score_spread":0.27036727676200867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416963394","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":[0.000116833326,0.00058303174,0.9175854,0.0053232657,0.0017323942,0.0009622942,0.0000083724535,0.00058009056,0.07310835],"genre_scores_gemma":[0.25432685,0.000034449637,0.7256012,0.0027264487,0.00016079699,0.00013267506,0.0000051738293,0.00005584082,0.016956586],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931383,0.00023248448,0.0010503496,0.0023474786,0.0012535196,0.0019778614],"domain_scores_gemma":[0.99580675,0.0005271742,0.00022037367,0.0026817964,0.00044411045,0.0003197922],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007482721,0.0007966336,0.0007816764,0.0005614952,0.00088214024,0.0014336951,0.003912164,0.00038715548,0.000078696445],"category_scores_gemma":[0.00027725112,0.0007955029,0.00035412915,0.0037948263,0.0005133336,0.0015901453,0.0040963837,0.0013551614,0.0000779234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015685511,0.0014396259,0.00011648873,0.0015389053,0.00019378516,0.00006819989,0.0010594975,0.6634231,0.004201763,0.02115905,0.0009994241,0.30564332],"study_design_scores_gemma":[0.0023584766,0.00017104215,0.00017791652,0.00026191576,0.000023960843,0.000029612494,0.00018505553,0.9853594,0.0021004898,0.0004874016,0.008131083,0.00071368803],"about_ca_topic_score_codex":0.0001769638,"about_ca_topic_score_gemma":0.000015046047,"teacher_disagreement_score":0.32193625,"about_ca_system_score_codex":0.00060846854,"about_ca_system_score_gemma":0.000970995,"threshold_uncertainty_score":0.9996029},"labels":[],"label_agreement":null},{"id":"W49490112","doi":"","title":"On the Complexity of Minimum Sum-of-Squares Clustering","year":2007,"lang":"fr","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Conceptual clustering; Mathematics; Confusion; Explained sum of squares; Computer science; Artificial intelligence; Combinatorics; Correlation clustering; Statistics; Psychology; CURE data clustering algorithm","score_opus":0.05104021855297638,"score_gpt":0.3008957281111915,"score_spread":0.2498555095582151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W49490112","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":[0.05170485,0.0031937836,0.9268346,0.014902755,0.0006423677,0.0009984971,0.00008360725,0.00023233997,0.0014072421],"genre_scores_gemma":[0.7666052,0.00020818024,0.23005812,0.00075646426,0.00017663024,0.00007287399,0.0000045972597,0.00007297186,0.0020449543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99467397,0.0004603391,0.0012316217,0.00075323693,0.0012729021,0.0016079408],"domain_scores_gemma":[0.9941393,0.0019009408,0.00067891105,0.0023293537,0.0005263901,0.0004250636],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0036543934,0.0005287238,0.0007183403,0.0006377809,0.00036482036,0.0001820998,0.002737572,0.0003971706,0.000083122315],"category_scores_gemma":[0.0010022392,0.00047352278,0.0003501759,0.0016651533,0.0018393951,0.000548558,0.0017016897,0.0010771155,0.00002383324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046130436,0.000982952,0.0016298246,0.0005627148,0.00016361316,0.00024676856,0.0025005334,0.022818903,0.021835998,0.75257576,0.0016118188,0.19460982],"study_design_scores_gemma":[0.00066113536,0.0009691489,0.015701696,0.00073715363,0.00002700098,0.00017880765,0.0003546109,0.8309388,0.110790685,0.037114713,0.0019334984,0.0005927459],"about_ca_topic_score_codex":0.012871668,"about_ca_topic_score_gemma":0.0049386187,"teacher_disagreement_score":0.8081199,"about_ca_system_score_codex":0.00063400913,"about_ca_system_score_gemma":0.0003996991,"threshold_uncertainty_score":0.99977165},"labels":[],"label_agreement":null},{"id":"W565269975","doi":"10.1609/aaai.v29i1.9594","title":"SoF: Soft-Cluster Matrix Factorization for Probabilistic Clustering","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":7,"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 Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Baidu","keywords":"Cluster analysis; Non-negative matrix factorization; Probabilistic logic; Algorithm; Computer science; Mathematics; Fuzzy clustering; Correlation clustering; Data mining; Pattern recognition (psychology); Matrix decomposition; Artificial intelligence","score_opus":0.1442253030763614,"score_gpt":0.3621481781069662,"score_spread":0.2179228750306048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W565269975","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":[0.0055837994,0.0000139765625,0.9887096,0.0025921108,0.00069140276,0.0010569135,0.000006604226,0.00015222898,0.0011933285],"genre_scores_gemma":[0.9495,0.000005555571,0.04934507,0.00011239535,0.00013900064,0.00013841444,0.0000012283979,0.000027043156,0.0007312656],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755794,0.000022430862,0.00056773506,0.0006069412,0.0007317634,0.0005131832],"domain_scores_gemma":[0.99687356,0.0001901739,0.00033473372,0.00039531183,0.0020228324,0.00018341841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078032754,0.0002530946,0.00027884686,0.00015411015,0.00019712934,0.00037383244,0.002246971,0.00010805509,0.000008589263],"category_scores_gemma":[0.002196689,0.00019734938,0.00009716394,0.0007847266,0.00020812832,0.00090161257,0.0008124951,0.00026027748,0.00004892289],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036304622,0.0002848627,0.000114777606,0.00035592823,0.000034472094,7.559729e-7,0.0045369333,0.013915732,0.024340576,0.7602262,0.00039512978,0.19543158],"study_design_scores_gemma":[0.000069211856,0.0002827723,0.000011949832,0.00012281549,0.000006306556,0.0000053602535,0.00027264204,0.7435699,0.06896058,0.1862791,0.0002111445,0.00020818674],"about_ca_topic_score_codex":0.000022640152,"about_ca_topic_score_gemma":0.000007839186,"teacher_disagreement_score":0.9439162,"about_ca_system_score_codex":0.00017461769,"about_ca_system_score_gemma":0.00023306713,"threshold_uncertainty_score":0.80476743},"labels":[],"label_agreement":null},{"id":"W632121358","doi":"10.1007/s10115-015-0851-6","title":"On strategies for building effective ensembles of relative clustering validity criteria","year":2015,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","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":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Measure (data warehouse); Data mining; Set (abstract data type); Partition (number theory); Complementarity (molecular biology); Consensus clustering; Stability (learning theory); Variety (cybernetics); Machine learning; Artificial intelligence; Mathematics; Fuzzy clustering; CURE data clustering algorithm","score_opus":0.06181771647573652,"score_gpt":0.357017140401257,"score_spread":0.29519942392552045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W632121358","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":[0.016492497,0.00016483449,0.9745897,0.000017674725,0.00055584015,0.00059819495,0.0000102322665,0.00006760026,0.0075034453],"genre_scores_gemma":[0.98634577,0.000006751727,0.013393821,0.000008417455,0.000058505786,0.00012299583,0.0000031103543,0.0000049691057,0.000055684282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907625,0.000109964494,0.00032427377,0.00012845572,0.00018780425,0.00017325886],"domain_scores_gemma":[0.9985195,0.0004888867,0.00015958372,0.00020228892,0.00054308225,0.00008668181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008216946,0.00011045772,0.0002008773,0.0001926438,0.00009577546,0.00023862028,0.00021583193,0.00005922846,2.5568437e-7],"category_scores_gemma":[0.00027931845,0.000095826064,0.000030347652,0.00019452452,0.000035197027,0.00465257,0.00016844024,0.00007696984,0.000011752716],"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":[0.00026972528,0.00008882697,0.00007553841,0.0032089546,0.00010330462,0.0000017875425,0.07651583,0.023316473,0.0016873197,0.7712,0.0019820165,0.1215502],"study_design_scores_gemma":[0.0010059719,0.0007093091,0.00014795637,0.00032119715,0.000003919751,0.000015734413,0.0018065613,0.9790575,0.0017183134,0.006533852,0.0085010035,0.00017867451],"about_ca_topic_score_codex":0.000015783038,"about_ca_topic_score_gemma":0.0000018527362,"teacher_disagreement_score":0.9698532,"about_ca_system_score_codex":0.00009050864,"about_ca_system_score_gemma":0.00008313302,"threshold_uncertainty_score":0.39076737},"labels":[],"label_agreement":null},{"id":"W65834064","doi":"","title":"Clustering in the Presence of Background Noise","year":2014,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Robustness (evolution); Computer science; Centroid; CURE data clustering algorithm; Data mining; Cluster (spacecraft); Correlation clustering; Noise (video); Algorithm; Constrained clustering; Canopy clustering algorithm; Artificial intelligence","score_opus":0.05514190194778961,"score_gpt":0.34961984386203676,"score_spread":0.29447794191424714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W65834064","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":[0.03359577,0.000014924416,0.9333991,0.0033029062,0.00025405342,0.00011941877,0.0000014895453,0.000053224823,0.029259142],"genre_scores_gemma":[0.9850756,0.0000175884,0.014209034,0.00014295806,0.00005652789,0.00001537423,0.0000034718948,0.0000071046975,0.00047234993],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830806,0.00030050726,0.0002373465,0.00029567245,0.00064658053,0.00021181772],"domain_scores_gemma":[0.99886745,0.0005044312,0.00011552535,0.0003414567,0.00013616105,0.000034997036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008788844,0.00011305284,0.00012485778,0.00018395172,0.00006891834,0.00016099148,0.0019169473,0.000032945856,0.00005326893],"category_scores_gemma":[0.0004309884,0.00008726597,0.000037287726,0.00023134661,0.00005870351,0.00032125736,0.00041814058,0.00053393614,0.000034452143],"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":[0.00009826154,0.00019697745,0.00987826,0.00005180586,0.000031323547,0.000042155552,0.0036903752,0.23252851,0.007557661,0.4098033,0.000030898354,0.33609048],"study_design_scores_gemma":[0.00028139286,0.0001251178,0.0052371793,0.0000721268,5.468239e-7,0.000013299883,0.00009921116,0.9899597,0.00018512341,0.0026546272,0.0012814018,0.00009023531],"about_ca_topic_score_codex":0.00015393624,"about_ca_topic_score_gemma":0.000054709493,"teacher_disagreement_score":0.9514798,"about_ca_system_score_codex":0.000042177617,"about_ca_system_score_gemma":0.000029472783,"threshold_uncertainty_score":0.35621968},"labels":[],"label_agreement":null},{"id":"W6920510158","doi":"10.60692/pgp62-5kc97","title":"A unified view of density-based methods for semi-supervised clustering and classification","year":2019,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Core (optical fiber); Bridge (graph theory); Fraction (chemistry); Labeled data; Conceptual clustering; Correlation clustering; Data stream clustering; Pattern recognition (psychology)","score_opus":0.07282835786029025,"score_gpt":0.31763390026555316,"score_spread":0.24480554240526292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920510158","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":[0.052753087,0.000004195269,0.94578534,0.000058928326,0.00018825053,0.00079459377,0.000010190984,0.00014158626,0.00026380815],"genre_scores_gemma":[0.7048281,1.4453991e-7,0.29499653,0.000049492075,0.000009552002,0.00006610985,0.0000052890773,0.0000063696725,0.000038461236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868053,0.00013301319,0.0005182844,0.00021393513,0.00022970584,0.0002245429],"domain_scores_gemma":[0.9986401,0.00007102655,0.0002605969,0.00059782166,0.00035302495,0.000077424855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095536234,0.00013745074,0.00027014507,0.00026971972,0.00007941248,0.00015867993,0.00037377057,0.000083149665,0.0000017275844],"category_scores_gemma":[0.00003720623,0.00012259299,0.000054625656,0.00031580398,0.000024004681,0.00089755194,0.00016979237,0.00007392326,0.00004322113],"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":[0.00076463906,0.000027628621,0.03966091,0.034624245,0.00029765378,0.000003482674,0.16811697,0.026773235,0.007433597,0.019352365,0.000040568044,0.7029047],"study_design_scores_gemma":[0.0009995427,0.000068876776,0.0036575927,0.00017436694,0.000005288345,0.000010715595,0.0009654766,0.9899916,0.0037836852,0.0000072261478,0.00020226256,0.00013338149],"about_ca_topic_score_codex":0.0000023494365,"about_ca_topic_score_gemma":6.6386264e-8,"teacher_disagreement_score":0.96321833,"about_ca_system_score_codex":0.00008909922,"about_ca_system_score_gemma":0.000056607994,"threshold_uncertainty_score":0.4999197},"labels":[],"label_agreement":null},{"id":"W6920973824","doi":"10.6084/m9.figshare.25807416","title":"Additional file 1 of An inversion-based clustering approach for complex clusters","year":2024,"lang":"en","type":"article","venue":"Open MIND","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 Regina","funders":"","keywords":"Cluster analysis; Table (database); Data file; File format; Code (set theory); Cluster (spacecraft)","score_opus":0.0896934857428779,"score_gpt":0.3483930517080126,"score_spread":0.2586995659651347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920973824","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":[0.000035378693,0.0000046996965,0.8825308,0.00011929297,0.00006612969,0.00050776923,0.111894086,0.000014136571,0.004827669],"genre_scores_gemma":[0.0009282355,1.2395662e-7,0.9759431,0.000054952245,0.00005635132,0.00031951148,0.021052126,0.000015844622,0.001629778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986829,0.000048216672,0.00019540121,0.0005146589,0.00029544465,0.00026336775],"domain_scores_gemma":[0.99821913,0.0010974167,0.000049128623,0.0004271073,0.00008977861,0.00011743342],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019252776,0.000116610325,0.00015675568,0.00014482765,0.00011413987,0.0003705965,0.0014769869,0.00004829456,0.16709606],"category_scores_gemma":[0.000124479,0.000114145325,0.00006343604,0.00034831354,0.00007739055,0.00075036695,0.00074333604,0.000110040775,0.00010433143],"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":[0.000028481205,0.000077217854,8.878407e-8,0.00008438444,0.00001894595,0.000011745942,0.0001845008,0.0141085945,0.00022507,0.00001211815,0.45064783,0.53460103],"study_design_scores_gemma":[0.00017076592,0.0001042742,0.000005526573,0.00008315696,0.0000015809628,0.00000634149,0.000049136663,0.7170342,0.00025103518,0.00004140583,0.28215307,0.00009946197],"about_ca_topic_score_codex":0.000009200937,"about_ca_topic_score_gemma":0.000007132454,"teacher_disagreement_score":0.7029256,"about_ca_system_score_codex":0.00007708359,"about_ca_system_score_gemma":0.00026526983,"threshold_uncertainty_score":0.8336653},"labels":[],"label_agreement":null},{"id":"W6924105539","doi":"10.15468/dl.pr7yrs","title":"Occurrence Download","year":2023,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Set (abstract data type); Confidentiality","score_opus":0.025895767468059317,"score_gpt":0.2681033199922915,"score_spread":0.24220755252423215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6924105539","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010285716,0.0000088215465,0.003245115,0.00028945232,0.0009718312,0.00029306303,0.99467397,0.00047534588,0.000032090087],"genre_scores_gemma":[4.2501955e-7,0.00007082805,0.0000680346,0.0002104497,0.0000017610247,0.000007458267,0.9996406,1.664391e-8,4.2973548e-7],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976091,0.000080730584,0.00038346645,0.0004018877,0.0010019565,0.00052286015],"domain_scores_gemma":[0.99792165,0.000053910248,0.0002320729,0.0011892972,0.0003659219,0.0002371642],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00041019547,0.00029439665,0.00027475832,0.00018774187,0.00034885574,0.00044164155,0.0025157663,0.00029829697,0.00008019208],"category_scores_gemma":[0.00029552032,0.00031230995,0.00013284208,0.0010654804,0.00014967848,0.0023608718,0.0025249482,0.00044837012,0.599503],"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":[0.000008117486,0.00001551933,0.00002550071,0.000116813804,0.000017457282,0.000010476607,0.000028514345,0.00008996815,2.0386125e-8,2.8223147e-7,0.9915692,0.008118103],"study_design_scores_gemma":[0.00023299335,0.00003787557,0.00003953277,0.0000034418074,0.0000066351017,0.000007767382,0.000030478253,0.000024220097,0.00000199236,0.000005658721,0.99930453,0.00030485625],"about_ca_topic_score_codex":0.00053005427,"about_ca_topic_score_gemma":0.0000115634275,"teacher_disagreement_score":0.59942275,"about_ca_system_score_codex":0.0005169186,"about_ca_system_score_gemma":0.00024029124,"threshold_uncertainty_score":0.9999329},"labels":[],"label_agreement":null},{"id":"W6925415964","doi":"10.18712/nsd-nsd2584-2-v3","title":"Travel and Holiday Survey 2017, 2nd quarter, Person File + Wood Firing + Health & Vaccination","year":2022,"lang":"en","type":"dataset","venue":"NSD – Norsk senter for forskningsdata","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); The Internet; Norwegian; Vaccination; Work (physics); National Health Interview Survey","score_opus":0.06840023896232364,"score_gpt":0.3445974789706527,"score_spread":0.276197240008329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6925415964","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000383749,0.00046460456,0.12315599,0.0007307118,0.0009673087,0.0011419124,0.8733777,0.00011284953,0.000010587924],"genre_scores_gemma":[0.000059765345,0.00027961223,0.013374666,0.00034853883,0.00022239888,0.00042251448,0.9841389,0.00007664469,0.0010769664],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99457806,0.00042388463,0.0007063659,0.0019137379,0.0010539936,0.0013239697],"domain_scores_gemma":[0.9956629,0.00081598264,0.00070237025,0.0022055774,0.00019801265,0.00041512478],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020783483,0.00069168565,0.0008646818,0.0006881716,0.0009723809,0.00070724636,0.0032788578,0.00025627558,0.0026860302],"category_scores_gemma":[0.00044000812,0.00074912695,0.00018326088,0.0005927873,0.000059626585,0.0015180118,0.0022157894,0.0010900693,0.00003238057],"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":[0.000043646338,0.000108129716,0.00001463994,0.000494264,0.00006788749,0.00002067233,0.00044340274,0.000024087192,0.0000029772407,0.000009318458,0.98297757,0.01579343],"study_design_scores_gemma":[0.0017576253,0.0010996694,0.0028800794,0.00019393471,0.000021871874,0.00018505527,0.0002375097,0.023811009,0.000014301438,0.00012633525,0.968682,0.0009906217],"about_ca_topic_score_codex":0.003214375,"about_ca_topic_score_gemma":0.001537164,"teacher_disagreement_score":0.11076123,"about_ca_system_score_codex":0.00048156746,"about_ca_system_score_gemma":0.00029730948,"threshold_uncertainty_score":0.999496},"labels":[],"label_agreement":null},{"id":"W6929161022","doi":"10.4224/40000433","title":"Guide des règles de l'art sur les coupe-feu et les pare-feu et leur effet sur la transmission acoustique","year":2007,"lang":"en","type":"report","venue":"NPARC","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Terminology; Context (archaeology); Jurisdiction; Best practice; Fire safety; Fire protection","score_opus":0.05981230376779776,"score_gpt":0.3696977348816851,"score_spread":0.30988543111388733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929161022","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":[0.0020518308,0.002207438,0.9035717,0.00111905,0.00034712232,0.000570495,0.00007478051,0.00070864527,0.0893489],"genre_scores_gemma":[0.018500343,0.035620593,0.76779443,0.000473636,0.0007894917,0.00030901178,0.00026816432,0.00052379706,0.1757205],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9924607,0.00096771214,0.0010228041,0.0014656885,0.0026172267,0.0014658684],"domain_scores_gemma":[0.99373096,0.0024944348,0.0003831863,0.0014520803,0.0013623289,0.00057699776],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006686095,0.00085565593,0.0009955394,0.0005513414,0.00039297435,0.0005082183,0.0024809127,0.0010970826,0.00012226158],"category_scores_gemma":[0.0016856948,0.000795947,0.00037000424,0.0006112366,0.00042385343,0.0007323527,0.00089347473,0.002298073,0.000040294843],"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":[0.00006761833,0.00029075157,0.00083302456,0.0016487632,0.00015528413,0.0020042353,0.0008187385,0.0043001706,0.015501832,0.00077960506,0.06718767,0.9064123],"study_design_scores_gemma":[0.0007155249,0.0002385754,0.0028493032,0.0019717182,0.000040212482,0.0011399777,0.00003829149,0.030289449,0.004947794,0.0021841102,0.954459,0.0011260195],"about_ca_topic_score_codex":0.0019558063,"about_ca_topic_score_gemma":0.0006810679,"teacher_disagreement_score":0.9052863,"about_ca_system_score_codex":0.0007951949,"about_ca_system_score_gemma":0.0036465374,"threshold_uncertainty_score":0.99944913},"labels":[],"label_agreement":null},{"id":"W6929807060","doi":"10.5061/dryad.bk3j9kd6f","title":"Data from: Integrating over uncertainty in spatial scale of response within multispecies occupancy models yields more accurate assessments of community composition","year":2019,"lang":"en","type":"dataset","venue":"Open MIND","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Scale (ratio); Bayesian probability; Occupancy; Range (aeronautics); Spatial ecology; Selection (genetic algorithm)","score_opus":0.22259440158859317,"score_gpt":0.46460979305338657,"score_spread":0.2420153914647934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929807060","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09974284,0.000017372437,0.06593535,0.000031485015,0.00021051428,0.0007203614,0.8333066,0.0000020873854,0.000033402506],"genre_scores_gemma":[0.043753505,0.000019281759,0.11658443,0.000022803484,0.000025906369,0.000021646429,0.8394832,0.000018525992,0.00007067959],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99583024,0.0015151285,0.0009074311,0.0006449052,0.0007856093,0.00031670817],"domain_scores_gemma":[0.99327844,0.0014300195,0.0008487147,0.004140127,0.00022475497,0.00007794666],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002282334,0.00032822104,0.00078648335,0.00027450663,0.000116029514,0.00028000365,0.009079391,0.0002798907,0.00014370722],"category_scores_gemma":[0.00029354534,0.00031202202,0.00004831744,0.0004331169,0.00019822814,0.001871556,0.011576828,0.0014410355,0.000021151198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014331437,0.0058701867,0.00076554087,0.001401028,0.0007179984,0.00029011737,0.02178231,0.36898363,0.02533978,0.000014565519,0.3752515,0.18525192],"study_design_scores_gemma":[0.0016026241,0.00031231652,0.0017120299,0.0014894393,0.000024128714,0.0000041641106,0.0007784666,0.988483,0.0015807417,0.00010963584,0.0034716597,0.0004317568],"about_ca_topic_score_codex":0.02990011,"about_ca_topic_score_gemma":0.0093964115,"teacher_disagreement_score":0.61949944,"about_ca_system_score_codex":0.00021307661,"about_ca_system_score_gemma":0.00056182896,"threshold_uncertainty_score":0.9999332},"labels":[],"label_agreement":null},{"id":"W6929870454","doi":"10.5061/dryad.rfj6q579r","title":"Source pool diversity and proximity shape the compositional uniqueness of insular mammal assemblages worldwide","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Concordia University; Université de Sherbrooke","funders":"","keywords":"Ectotherm; Population; Variation (astronomy); Range (aeronautics); Natural (archaeology); Lacertidae","score_opus":0.031747393981363045,"score_gpt":0.2536503977295346,"score_spread":0.22190300374817157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929870454","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007495462,0.0005497266,0.25890598,0.0025197868,0.00028816596,0.0015803588,0.72691655,0.0008015411,0.0009424585],"genre_scores_gemma":[0.021793684,0.00064245355,0.0036496962,0.00037543604,0.0003005976,3.4121783e-7,0.97177887,0.0009167738,0.0005421455],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99678224,0.00088761566,0.0002871794,0.00067458476,0.00096667814,0.00040171313],"domain_scores_gemma":[0.99747354,0.000136619,0.00021314785,0.0010741486,0.00092651724,0.00017603165],"candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009855502,0.00022806306,0.00027580032,0.000261476,0.0042898566,0.0007897682,0.0036824285,0.00012410228,0.0007461739],"category_scores_gemma":[0.0005151085,0.00021026276,0.0000678869,0.00081158744,0.0004117437,0.0004542272,0.025950242,0.000736255,0.00019551058],"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":[0.000060159153,0.0002656948,0.0000042662,0.00045379213,0.00014821388,0.000109779714,0.00060285215,0.0003611088,0.0010175406,0.00077534636,0.9364929,0.05970831],"study_design_scores_gemma":[0.0003240499,0.0001369677,0.0006201269,0.000102921316,0.000019519255,0.00024038159,0.00007408771,0.0054709828,0.00039568203,0.00014660168,0.9922245,0.00024414202],"about_ca_topic_score_codex":0.00007079377,"about_ca_topic_score_gemma":0.0000010021317,"teacher_disagreement_score":0.25525627,"about_ca_system_score_codex":0.00015926278,"about_ca_system_score_gemma":0.000018076109,"threshold_uncertainty_score":0.9970064},"labels":[],"label_agreement":null},{"id":"W6930383710","doi":"10.5281/zenodo.12342515","title":"bankamp katalog 2017 pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Subpoena; Paraphernalia; Pretext; Fusible alloy; Limiting","score_opus":0.033752732861100324,"score_gpt":0.2736382651706521,"score_spread":0.23988553230955179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930383710","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.651525e-7,0.0006752172,0.16079667,0.00053164636,0.00044958259,0.0004131729,0.00020202187,0.0031803327,0.8337506],"genre_scores_gemma":[0.00015522771,0.00033212753,0.008926955,0.00010282291,0.00057850033,1.233642e-7,0.00087894895,0.009409393,0.9796159],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968646,0.00027171188,0.00026472972,0.0010963565,0.0008137193,0.0006888777],"domain_scores_gemma":[0.9976595,0.000021667964,0.00013373757,0.0016214635,0.00027121158,0.0002924114],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005884187,0.00031628064,0.00027578406,0.0008076488,0.0007929396,0.0022775198,0.004636527,0.0002087461,0.040379945],"category_scores_gemma":[0.00033761744,0.00032916365,0.000097388525,0.0009420396,0.00021920209,0.00029727476,0.006424828,0.0007700571,0.36303478],"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":[0.0000038206813,0.000037313777,1.6986768e-8,0.00017410614,0.00005442765,0.00013602397,0.00019257468,0.0000097943475,0.00010672787,0.00424702,0.91004646,0.08499169],"study_design_scores_gemma":[0.00020635556,0.00011944467,0.0000027844276,0.00018616942,0.000008185617,0.00025630152,0.00002345378,0.0019061238,0.00004166631,0.0008695291,0.99604124,0.00033875814],"about_ca_topic_score_codex":0.00002675866,"about_ca_topic_score_gemma":6.2661275e-7,"teacher_disagreement_score":0.32265484,"about_ca_system_score_codex":0.0002268746,"about_ca_system_score_gemma":0.000010119228,"threshold_uncertainty_score":0.999916},"labels":[],"label_agreement":null},{"id":"W6931096469","doi":"10.5281/zenodo.4699907","title":"+27733404752 REVENGE SPELL, INSTANT DEATH SPELLS IN AUSTRALIA, CANADA, MALTA,AUSTRIA, BAHAMAS, BAHRAIN, BARBADOS, BELGIUM, BHUTAN, BRUNEI.","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Spell; MAGIC (telescope); Instant; Harm; Wife","score_opus":0.04873091082236333,"score_gpt":0.2688419079113559,"score_spread":0.2201109970889926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931096469","genre_codex":"other","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":[0.18241784,0.0026012904,0.33830392,0.02279288,0.002811516,0.00544519,0.0021408715,0.003263479,0.440223],"genre_scores_gemma":[0.8439545,0.0009056775,0.040658433,0.0013823101,0.00080249546,2.4256715e-7,0.001369085,0.0036449176,0.107282355],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99500793,0.00075459236,0.0006281223,0.0011679712,0.0012503151,0.0011910846],"domain_scores_gemma":[0.9968808,0.00010085973,0.0001597441,0.0014354046,0.00088793936,0.0005352028],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011483689,0.00033303472,0.0003752188,0.00039691065,0.00068878714,0.0011893389,0.0029315818,0.00013355349,0.007953468],"category_scores_gemma":[0.0010759104,0.0003885451,0.00007885619,0.0023415822,0.00013301034,0.00074791134,0.0037865317,0.00090359204,0.0067455913],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032679256,0.0016465023,0.00025501792,0.00090646517,0.0003720178,0.013385948,0.0049766544,0.007890988,0.04146584,0.059312213,0.5227232,0.3467384],"study_design_scores_gemma":[0.0010387407,0.00016296818,0.0021010228,0.000120901335,0.0000065994395,0.00047201433,0.00021972082,0.0052629663,0.0033533494,0.00060425716,0.9861598,0.0004976587],"about_ca_topic_score_codex":0.015345982,"about_ca_topic_score_gemma":0.0028220986,"teacher_disagreement_score":0.66153663,"about_ca_system_score_codex":0.0012283657,"about_ca_system_score_gemma":0.00014790514,"threshold_uncertainty_score":0.99985665},"labels":[],"label_agreement":null},{"id":"W6931585265","doi":"10.5281/zenodo.7629517","title":"Fig. 78. Mesoscutum pubescence. A in Revision of the Nearctic species of the Lasioglossum (Dialictus) gemmatum species complex (Hymenoptera: Halictidae)","year":2023,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Nearctic ecozone; Dorsum; Species complex; Scale (ratio)","score_opus":0.04716349607864643,"score_gpt":0.260761916863621,"score_spread":0.21359842078497457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931585265","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00087827444,0.0005353243,0.01891282,0.0067652026,0.0017983859,0.0041282945,0.0008941236,0.002557928,0.96352965],"genre_scores_gemma":[0.10580333,0.0025799938,0.0064848606,0.00031800658,0.0009820537,8.571307e-7,0.0002708573,0.014842262,0.8687178],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960418,0.00080172694,0.0005564058,0.00067060627,0.0013478704,0.000581632],"domain_scores_gemma":[0.99695563,0.00008483436,0.00045637772,0.0019771862,0.00041639208,0.000109604145],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008751659,0.0002961034,0.00044019724,0.00051525317,0.0007449916,0.00045747892,0.0058523663,0.00014791008,0.0040046643],"category_scores_gemma":[0.00113396,0.00021532521,0.0001652848,0.0024682537,0.00079372735,0.00022687354,0.00797919,0.00066870055,0.00089146104],"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":[0.00004535846,0.00029171057,0.000074640426,0.0009621174,0.00013689272,0.000029665362,0.0037072974,0.00036460982,0.00385975,0.019415246,0.9189378,0.052174907],"study_design_scores_gemma":[0.0003496373,0.00009320619,0.004246858,0.0007590465,0.000008463621,0.000023448105,0.00016187102,0.0019021902,0.00050084235,0.00017115728,0.9915718,0.0002115076],"about_ca_topic_score_codex":0.0001643598,"about_ca_topic_score_gemma":0.000015181309,"teacher_disagreement_score":0.10492506,"about_ca_system_score_codex":0.00027900594,"about_ca_system_score_gemma":0.000024056615,"threshold_uncertainty_score":0.99988645},"labels":[],"label_agreement":null},{"id":"W6931742362","doi":"10.5281/zenodo.5708940","title":"Automated Risk of Bias Tool for Prevalence Studies","year":2021,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Calgary; McGill University Health Centre; University of Waterloo; University of Toronto","funders":"","keywords":"Checklist; Risk assessment; MEDLINE; Data collection; Risk factor; Seroprevalence","score_opus":0.07633642572904348,"score_gpt":0.3219613033725742,"score_spread":0.24562487764353075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931742362","genre_codex":"methods","genre_gemma":"other","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":[0.00016641933,0.0071479627,0.8079588,0.0004990645,0.00074801757,0.003002628,0.0019616492,0.009232933,0.16928253],"genre_scores_gemma":[0.002469401,0.014631993,0.24091433,0.00015224284,0.00091710093,0.0000022115282,0.002141864,0.020643465,0.71812737],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970191,0.0006291134,0.00037654763,0.00080839684,0.0006759208,0.00049093494],"domain_scores_gemma":[0.99685115,0.00017154525,0.00040137582,0.0012509243,0.0012077141,0.00011727445],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010964317,0.00025709294,0.00040204517,0.00045367793,0.0007882208,0.00044282989,0.002711175,0.00013723521,0.0027672714],"category_scores_gemma":[0.0037650028,0.0002600137,0.000116079944,0.0008852057,0.0002503087,0.00016921487,0.003836057,0.00032082724,0.00062248314],"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":[0.000022071341,0.00013493997,0.0000018553178,0.002322792,0.00039367029,0.000023433797,0.00078124355,0.00023216491,0.0005071891,0.0017845444,0.8155448,0.17825134],"study_design_scores_gemma":[0.00046873325,0.00025012527,0.000050392297,0.0005009315,0.000024007248,0.00004094621,0.0000739409,0.015634311,0.00040956546,0.00017408222,0.9820886,0.00028435665],"about_ca_topic_score_codex":0.000014656252,"about_ca_topic_score_gemma":3.963124e-7,"teacher_disagreement_score":0.5670445,"about_ca_system_score_codex":0.00016441666,"about_ca_system_score_gemma":0.000015963324,"threshold_uncertainty_score":0.9999852},"labels":[],"label_agreement":null},{"id":"W6931817005","doi":"10.5683/sp3/xy4jjv","title":"Environics Focus Ontario 1996-1","year":2009,"lang":"en","type":"dataset","venue":"Borealis","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Innovative Research Group (Canada)","funders":"","keywords":"Focus (optics); Public opinion; Field (mathematics); Focus group; Government (linguistics)","score_opus":0.019977066730199833,"score_gpt":0.27927511177958914,"score_spread":0.2592980450493893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931817005","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.1229161e-7,0.00033484958,0.029317977,0.00035464077,0.00010752965,0.00022621118,0.96863693,0.00012730963,0.0008943351],"genre_scores_gemma":[5.507259e-7,0.0003370354,0.020504426,0.0002473179,0.00021183636,0.00003199256,0.97821045,0.000018054287,0.00043833762],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971075,0.00008086259,0.0003354256,0.00085099344,0.0008922224,0.00073301786],"domain_scores_gemma":[0.99665177,0.00009101065,0.00016152527,0.002778272,0.00006342201,0.00025398476],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026259074,0.00038959025,0.00040407619,0.00022739469,0.00015321019,0.00027708456,0.0035003207,0.00034755783,0.000068044596],"category_scores_gemma":[0.0000647441,0.00038218335,0.00013650351,0.0002332609,0.00007427218,0.00031749165,0.0010871056,0.0010132553,0.00013137473],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031241843,0.00004678505,3.99528e-7,0.000011510955,0.000016569904,0.00023733453,0.000039430182,0.00005592498,3.9731057e-7,0.00006896828,0.9220416,0.077477954],"study_design_scores_gemma":[0.00019359209,0.00016486993,0.00019671557,0.00003595483,0.0000106447,0.000055208777,0.0000010837291,0.0005013146,0.00001573187,0.0014547302,0.99696434,0.00040581077],"about_ca_topic_score_codex":0.7085854,"about_ca_topic_score_gemma":0.7967724,"teacher_disagreement_score":0.08818709,"about_ca_system_score_codex":0.00081117614,"about_ca_system_score_gemma":0.0005817253,"threshold_uncertainty_score":0.999863},"labels":[],"label_agreement":null},{"id":"W6958204250","doi":"10.6084/m9.figshare.12441566.v1","title":"Additional file 5 of Developing a framework to inform scale-up success for population health interventions: a critical interpretive synthesis of the literature","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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; University of Ottawa; University of Calgary; Government of New Brunswick; University of New Brunswick","funders":"","keywords":"Population; Population health; Visualization; Qualitative research; Public health; Health professionals; MEDLINE","score_opus":0.04939400675366261,"score_gpt":0.3808540122971685,"score_spread":0.33146000554350585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958204250","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000028928457,0.000026923759,0.092339136,0.0029255839,0.00003052059,0.00033122092,0.9042956,0.000029267998,0.000018840003],"genre_scores_gemma":[0.036665827,7.778794e-7,0.8055409,0.0023220559,0.00015856972,0.004557612,0.150653,0.000028352188,0.00007289046],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9989387,0.0000521787,0.00031556637,0.00021641613,0.00029255488,0.00018459553],"domain_scores_gemma":[0.99367845,0.005385672,0.00014697046,0.00022815111,0.00046296703,0.000097811506],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000045257166,0.00008781788,0.00018002732,0.00007145861,0.000109704764,0.00006973231,0.00074717996,0.00005969986,0.19368711],"category_scores_gemma":[0.054258354,0.00007271032,0.00014306704,0.0008214162,0.000012061534,0.0003438644,0.00058154773,0.0001684882,0.000033070082],"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":[0.000022902133,0.000019502777,0.0000029333132,0.002394023,0.000014366334,5.1147924e-7,0.0017608842,0.00008852018,0.0000010717703,0.001131085,0.9686573,0.025906883],"study_design_scores_gemma":[0.0002294783,0.0009963783,0.020717483,0.6995926,0.000009621501,0.000025054213,0.00048683916,0.11343296,0.0019418972,0.0078033535,0.15389338,0.0008709809],"about_ca_topic_score_codex":0.0000017691633,"about_ca_topic_score_gemma":0.000004353407,"teacher_disagreement_score":0.81476396,"about_ca_system_score_codex":0.00007983948,"about_ca_system_score_gemma":0.00016391622,"threshold_uncertainty_score":0.95370805},"labels":[],"label_agreement":null},{"id":"W6977015603","doi":"10.6084/m9.figshare.25807416.v1","title":"Additional file 1 of An inversion-based clustering approach for complex clusters","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 Regina","funders":"","keywords":"Cluster analysis; Table (database); Data file; File format; Code (set theory); Cluster (spacecraft)","score_opus":0.08145911007452508,"score_gpt":0.3101200265644326,"score_spread":0.22866091648990752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977015603","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.3504953e-7,0.000009612827,0.16137053,0.00003887806,0.000025351997,0.00023500077,0.8372968,0.00019885873,0.00082472456],"genre_scores_gemma":[0.00014725658,3.067632e-8,0.39966834,0.00008818455,0.00006843367,0.0009025506,0.598856,0.000015263835,0.00025394384],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987406,0.000033968943,0.00016580026,0.00043609185,0.00033945878,0.00028406302],"domain_scores_gemma":[0.9975976,0.0017018318,0.000047462137,0.00038700594,0.00014609456,0.00012005222],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000041096497,0.0001273068,0.00013210099,0.00017015391,0.00010140559,0.00014694489,0.00081583456,0.00006106253,0.81346434],"category_scores_gemma":[0.00068129564,0.00012798673,0.00009623054,0.0003794888,0.000015642134,0.00047472087,0.00036607496,0.00013100513,0.000281239],"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":[0.000005054407,0.000023125938,6.6106205e-9,0.00047177175,0.000007628619,0.0000068446902,0.00003469289,0.00861281,0.000017186556,0.0000041386006,0.9603686,0.030448185],"study_design_scores_gemma":[0.000085893014,0.00006366864,0.0000076291235,0.00059258536,6.088662e-7,0.0000050341705,0.000011088385,0.6538115,0.00005814051,0.000024768933,0.34524426,0.00009478702],"about_ca_topic_score_codex":0.000001562343,"about_ca_topic_score_gemma":0.0000015478017,"teacher_disagreement_score":0.8131831,"about_ca_system_score_codex":0.00008034159,"about_ca_system_score_gemma":0.00020532936,"threshold_uncertainty_score":0.5219147},"labels":[],"label_agreement":null},{"id":"W6978058864","doi":"10.6084/m9.figshare.24892825.v1","title":"Additional file 1 of Geospatial analysis and participant characteristics associated with colorectal cancer screening participation in Alberta, Canada: a population-based cross-sectional study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; Alberta Health Services","funders":"","keywords":"Colorectal cancer screening; Geospatial analysis; Cancer screening; Colorectal cancer; Data collection","score_opus":0.049989912967286894,"score_gpt":0.32920261522279964,"score_spread":0.27921270225551276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6978058864","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2194801,6.155129e-7,0.00011667891,0.000013198373,0.000009817396,0.00017548606,0.78017247,0.000028379378,0.000003275877],"genre_scores_gemma":[0.6260592,2.2646201e-8,0.0002476682,0.000007658545,0.000013308583,0.0010968394,0.37252563,0.000005637731,0.000044031967],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984797,0.000079688885,0.0003057029,0.00030803183,0.0005452538,0.00028159472],"domain_scores_gemma":[0.99691683,0.00241491,0.00020714954,0.00012652481,0.0002543523,0.00008024882],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007391256,0.00010380656,0.0002141511,0.00021095277,0.00012006013,0.00007105663,0.00016967369,0.00004022514,0.25798967],"category_scores_gemma":[0.0032226397,0.000102500635,0.000026556256,0.0016482552,0.0000092286,0.00017274624,0.0001158468,0.00011599325,0.00000834516],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004590044,0.00013799095,0.8760652,0.000027195321,0.00027177724,0.000047440273,0.0002185091,0.09107045,0.0000015735399,6.4674657e-7,0.030099383,0.0020139273],"study_design_scores_gemma":[0.00015101615,0.000042217616,0.5854925,0.00010283907,0.0000068273034,1.504718e-7,0.0000052395403,0.41407028,0.000004137459,8.8646965e-7,0.000056975652,0.000066915316],"about_ca_topic_score_codex":0.14907324,"about_ca_topic_score_gemma":0.8176392,"teacher_disagreement_score":0.6685659,"about_ca_system_score_codex":0.00016625662,"about_ca_system_score_gemma":0.0006666924,"threshold_uncertainty_score":0.85659313},"labels":[],"label_agreement":null},{"id":"W6986648496","doi":"","title":"¿Qué forma de educación lingüística quieren los padres inmigrantes? Una investigación sobre los deseos educativos de los miembros de la comunidad árabe de Ontario","year":2010,"lang":"en","type":"article","venue":"Dialnet (Universidad de la Rioja)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Arabic; Heritage language; Value (mathematics); Second language; English language; English as a second language","score_opus":0.010879139164801465,"score_gpt":0.2992022145775078,"score_spread":0.2883230754127063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986648496","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":[0.77306145,0.00012713818,0.21631739,0.0011171683,0.0003051799,0.0005973786,0.000059943217,0.00039025367,0.008024065],"genre_scores_gemma":[0.766404,0.000069069945,0.22942953,0.00082271907,0.00034492763,0.0000786043,0.000027326778,0.000101223086,0.0027226056],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947952,0.0009802937,0.0004131122,0.00093336107,0.0007180977,0.0021599608],"domain_scores_gemma":[0.9944065,0.0021076126,0.00027577276,0.0015091355,0.00027434234,0.0014266295],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016718373,0.0006237506,0.0005724946,0.00075361505,0.0007567239,0.000803642,0.0034060783,0.0007016419,0.00014820554],"category_scores_gemma":[0.0011061311,0.0007158604,0.00025798185,0.0012518164,0.001146505,0.001266443,0.0011637349,0.0023617947,0.00007355866],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009495813,0.0042713336,0.20197855,0.0015946077,0.0011369511,0.005084205,0.14947538,0.011908822,0.28454077,0.1269227,0.037323486,0.17481361],"study_design_scores_gemma":[0.009218791,0.001127485,0.29964152,0.0016523427,0.00035833882,0.0044222106,0.005134385,0.39046273,0.06078988,0.11939741,0.10302008,0.0047748485],"about_ca_topic_score_codex":0.024664152,"about_ca_topic_score_gemma":0.025511017,"teacher_disagreement_score":0.3785539,"about_ca_system_score_codex":0.0021166175,"about_ca_system_score_gemma":0.0071904543,"threshold_uncertainty_score":0.9999398},"labels":[],"label_agreement":null},{"id":"W6999392703","doi":"","title":"Clustering Oligarchies","year":2013,"lang":"en","type":"article","venue":"CaltechAUTHORS (California Institute of Technology)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Robustness (evolution); Initialization; Set (abstract data type); Data set; Data point","score_opus":0.015206979535115283,"score_gpt":0.2641469856410328,"score_spread":0.2489400061059175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6999392703","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":[0.05056873,0.00018502514,0.94095427,0.0048265764,0.0005277954,0.00051587867,0.000012021651,0.0012747379,0.0011349744],"genre_scores_gemma":[0.42435998,0.000061346065,0.57500064,0.000075492564,0.000043998254,0.00020044585,0.0000032433936,0.00002745449,0.00022742651],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976063,0.000024211766,0.00055126037,0.00063361257,0.0004364607,0.0007481725],"domain_scores_gemma":[0.9979248,0.00003280967,0.00018359484,0.0014005286,0.0002718819,0.00018637808],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027653237,0.00028631385,0.00041359436,0.0010868323,0.00021230066,0.000087307795,0.0025849112,0.00032344903,0.00003007542],"category_scores_gemma":[0.00036747538,0.00026667962,0.00010910165,0.0017809308,0.0007550038,0.0008186964,0.0021756103,0.00061948545,0.00052009383],"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":[0.000009038437,0.0001340144,0.00042298934,0.00019998959,0.00006739315,0.00006953841,0.0001328384,0.0026845087,0.039734326,0.068017595,0.0007020361,0.8878257],"study_design_scores_gemma":[0.0013331549,0.0005294169,0.00061068375,0.0004242598,0.000017256987,0.00036204682,0.00018886499,0.52809966,0.19230027,0.15930702,0.115508944,0.0013184253],"about_ca_topic_score_codex":0.00006376426,"about_ca_topic_score_gemma":0.000008121339,"teacher_disagreement_score":0.88650733,"about_ca_system_score_codex":0.00010548975,"about_ca_system_score_gemma":0.00010192095,"threshold_uncertainty_score":0.99997854},"labels":[],"label_agreement":null},{"id":"W7017732879","doi":"","title":"Canada – Manitoba Province – Winnipeg – Main Street Looking South from City Hall – Canadian Dog Train and Remains of Old Fort Garry","year":2013,"lang":"en","type":"article","venue":"Digital USD (University of San Diego)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Sinkhole; Settlement (finance)","score_opus":0.010670402446127408,"score_gpt":0.18015374946761437,"score_spread":0.16948334702148696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017732879","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":[0.974325,0.000033747212,0.021599922,0.00026676024,0.000054000746,0.00029665008,0.0006204816,0.00003357064,0.0027698623],"genre_scores_gemma":[0.99239033,0.000002579216,0.0069135027,0.00004996215,0.000016265834,3.7939125e-7,0.000029887786,0.0000103954735,0.00058670295],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984852,0.000025600491,0.00014965233,0.00044044715,0.000424533,0.00047456048],"domain_scores_gemma":[0.9987768,0.000087726534,0.00012553246,0.00046760234,0.00012474845,0.0004176075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008304492,0.00016662241,0.00026157597,0.00017088262,0.0001703937,0.000099357734,0.00093330775,0.000070006274,0.000034888195],"category_scores_gemma":[0.000037575413,0.00020620506,0.00005246067,0.00024156606,0.00022421424,0.0012696191,0.0005177273,0.00016604061,0.0000029259077],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000991262,0.000353515,0.40283465,0.0007182154,0.0006680878,0.00338526,0.015178286,0.0013034375,0.002097993,0.0096561285,0.010167461,0.55353785],"study_design_scores_gemma":[0.0023214228,0.00037240173,0.90661085,0.00041228934,0.000036970407,0.000028300714,0.024600247,0.05362087,0.00056290836,0.006121023,0.0039022837,0.0014104627],"about_ca_topic_score_codex":0.9699764,"about_ca_topic_score_gemma":0.9965665,"teacher_disagreement_score":0.55212736,"about_ca_system_score_codex":0.00039558328,"about_ca_system_score_gemma":0.0010591196,"threshold_uncertainty_score":0.8408798},"labels":[],"label_agreement":null},{"id":"W7023682103","doi":"","title":"Ottawa Senators HOT TAKES Heading Into The 2023-24 NHL Regular Season","year":2023,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Heading (navigation); Favourite; Taste; White (mutation); Code (set theory); Begging","score_opus":0.008605565159378567,"score_gpt":0.2199428136018655,"score_spread":0.2113372484424869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023682103","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000090080475,0.00049093063,0.00024839104,0.0011490169,0.000777849,0.0005376078,0.000025497797,0.00088917935,0.9958725],"genre_scores_gemma":[0.00006992832,0.00025739483,0.01319213,0.00020719461,0.0002416918,0.0000424224,0.00002293638,0.00023848026,0.98572785],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970468,0.00016781212,0.00063843833,0.00043565148,0.0011166546,0.00059459766],"domain_scores_gemma":[0.9975673,0.0003670027,0.00052115176,0.0011557426,0.00020452005,0.00018428682],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00068492425,0.00042797843,0.00044493942,0.00018106107,0.00021885657,0.00024040707,0.0018222547,0.0003603833,0.022252144],"category_scores_gemma":[0.00034652062,0.00035522907,0.00019227159,0.00006340366,0.00022224865,0.000001260122,0.000468735,0.0005811334,0.012907054],"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":[0.000011464136,0.00001363029,9.059938e-7,0.0002472127,0.00005908011,0.000042971962,0.00044865138,0.0014506943,6.138923e-7,0.00014266215,0.9847815,0.0128005985],"study_design_scores_gemma":[0.0002587162,0.000090490736,0.000005037604,0.00034832724,0.000013073304,0.00005910711,0.00017304458,0.0021982968,0.000028479855,0.000040888594,0.99641275,0.0003717663],"about_ca_topic_score_codex":0.0054292846,"about_ca_topic_score_gemma":0.0025576141,"teacher_disagreement_score":0.012943739,"about_ca_system_score_codex":0.00016444449,"about_ca_system_score_gemma":0.0000733328,"threshold_uncertainty_score":0.99988997},"labels":[],"label_agreement":null},{"id":"W7024212856","doi":"","title":"The Relevance of International Law Standards to Religious Leaders","year":2023,"lang":"en","type":"other","venue":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Economic and Social Research Council","keywords":"Relevance (law); Accountability; Human rights; International law; Reflexivity; Legitimacy; Norm (philosophy); International human rights law; Plea; Normative; Section (typography)","score_opus":0.03779702065530324,"score_gpt":0.30623318522100945,"score_spread":0.2684361645657062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024212856","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008395865,0.0040050005,0.5141312,0.08102465,0.002009149,0.005417302,0.0069093634,0.001530118,0.37657735],"genre_scores_gemma":[0.052873492,0.041138407,0.07580191,0.000058482623,0.00022093965,1.2518404e-7,0.000088964305,0.00037149366,0.8294462],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99520767,0.0004973758,0.00024656445,0.0007388936,0.0026028112,0.00070667296],"domain_scores_gemma":[0.9946929,0.0011978395,0.0005484247,0.0016561951,0.0016301491,0.00027449123],"candidate_categories":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0017843719,0.0003045225,0.00070075406,0.0010930885,0.00082165113,0.000025670424,0.007859095,0.00041840263,0.00021968367],"category_scores_gemma":[0.00025775682,0.00033505057,0.0003945949,0.0019057507,0.004019405,0.000336817,0.004296927,0.0012194847,0.00003699089],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0043916856,0.001357184,0.0004795955,0.0016571325,0.003403265,0.0011029347,0.06836838,0.011191643,0.0013740656,0.032568254,0.76094466,0.11316122],"study_design_scores_gemma":[0.001981351,0.00069200015,0.00032214512,0.001244001,0.000078810845,0.00000803691,0.066631906,0.005602374,0.000087364286,0.00037782209,0.9225125,0.00046169627],"about_ca_topic_score_codex":0.017510043,"about_ca_topic_score_gemma":0.033465058,"teacher_disagreement_score":0.45286882,"about_ca_system_score_codex":0.00050190446,"about_ca_system_score_gemma":0.0007402136,"threshold_uncertainty_score":0.9999102},"labels":[],"label_agreement":null},{"id":"W7027101180","doi":"","title":"Big Data Clustering: Models and Applications","year":2023,"lang":"en","type":"dissertation","venue":"MacSphere (McMaster University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Cluster analysis; Heuristic; Categorization; Big data; Identification (biology); Conceptual clustering; Similarity (geometry)","score_opus":0.07643698189621714,"score_gpt":0.2879257419409178,"score_spread":0.21148876004470066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7027101180","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029918147,0.00017644596,0.8300162,0.00008585288,0.00045880437,0.00048663258,0.000068219975,0.0004763217,0.16820163],"genre_scores_gemma":[0.00050141505,0.00045644992,0.02539443,0.000031056574,0.0002495265,0.000011815583,0.000602139,0.000081870414,0.9726713],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976146,0.00006762889,0.0001994628,0.0012410978,0.0004227227,0.00045444886],"domain_scores_gemma":[0.99769753,0.00010594233,0.00014329595,0.0017196505,0.00012533957,0.00020821135],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013521072,0.00031610808,0.00029771475,0.0003791068,0.00028444937,0.0002713367,0.0035299168,0.00024152432,0.00035777656],"category_scores_gemma":[0.000012198771,0.00038031285,0.000049362738,0.0011913416,0.00005876787,0.00093571935,0.0029994189,0.00044582508,0.00011655717],"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":[0.000018859591,0.000019428991,0.0000039057695,0.00018670919,0.000050468752,0.00007577927,0.00034220953,0.001208978,0.000029456825,0.0018319053,0.00028403057,0.99594826],"study_design_scores_gemma":[0.0006576063,0.000055721077,0.00012571926,0.000173333,0.000050530012,0.000015905838,0.0019033833,0.47384393,0.00003934234,0.0030009293,0.5193919,0.0007417251],"about_ca_topic_score_codex":0.00013222435,"about_ca_topic_score_gemma":0.00115167,"teacher_disagreement_score":0.99520653,"about_ca_system_score_codex":0.00012492255,"about_ca_system_score_gemma":0.00016994735,"threshold_uncertainty_score":0.9998649},"labels":[],"label_agreement":null},{"id":"W7027250496","doi":"","title":"A clustering algorithm to find groups with homogeneous preferences","year":2003,"lang":"en","type":"article","venue":"Consultation of the Doctoral Thesis Database (TESEO) (Ministerio de Educación, Cultura y Deporte)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Homogeneous; Cluster analysis; Information system; Field (mathematics); Feature (linguistics)","score_opus":0.03423239114366127,"score_gpt":0.2914982224660955,"score_spread":0.25726583132243425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7027250496","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":[0.4671525,0.00020682788,0.5290068,0.0008521995,0.00072919286,0.0011633615,0.00019984893,0.00017373184,0.00051554973],"genre_scores_gemma":[0.62871706,0.000035448345,0.36923993,0.00027857095,0.00009025584,0.00022873179,0.00004122018,0.00004378717,0.0013249775],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99601203,0.00047278663,0.00077584485,0.0009495702,0.0009781242,0.00081163156],"domain_scores_gemma":[0.9962342,0.00049897225,0.00053917797,0.001674261,0.0006357748,0.00041764262],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007703249,0.0004838327,0.00050207484,0.00020679519,0.0004477825,0.00042875521,0.0019118121,0.000111659465,0.00007345281],"category_scores_gemma":[0.0012886628,0.00033348304,0.00013898785,0.001346426,0.00029207158,0.0008969765,0.0006651916,0.0003468125,0.000040945204],"study_design_candidate":"bench_or_experimental","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":[0.0007155144,0.002174175,0.007894753,0.0010517468,0.0010208167,0.00086545566,0.03986474,0.008567318,0.21847148,0.004460248,0.002344126,0.7125696],"study_design_scores_gemma":[0.012444138,0.0042424984,0.0935935,0.004859597,0.0007315582,0.013850334,0.021511303,0.11820025,0.6203522,0.003541845,0.09718473,0.009488054],"about_ca_topic_score_codex":0.00014214742,"about_ca_topic_score_gemma":0.00011255673,"teacher_disagreement_score":0.70308155,"about_ca_system_score_codex":0.00023005414,"about_ca_system_score_gemma":0.00061344064,"threshold_uncertainty_score":0.9999117},"labels":[],"label_agreement":null},{"id":"W7033311453","doi":"","title":"Predicting the performance of tubular daylighting devices","year":2013,"lang":"en","type":"article","venue":"NPARC","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Daylighting; Daylight; Illuminance; Roof; Solar energy; Efficient energy use; Skylight; Glazing","score_opus":0.013944177839396353,"score_gpt":0.25477907981208553,"score_spread":0.24083490197268917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033311453","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":[0.9380554,0.000052553267,0.05433257,0.00091567985,0.00010584097,0.00017615528,3.4657782e-7,0.00008815197,0.0062732967],"genre_scores_gemma":[0.926083,0.000009224858,0.07357679,0.000051407857,0.00005324309,0.000027084154,1.8554827e-7,0.000006028377,0.00019302433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989589,0.00004374842,0.0001735659,0.00018653537,0.00036545735,0.00027182177],"domain_scores_gemma":[0.99909973,0.0001661519,0.000077084645,0.00048347493,0.00012773965,0.000045809058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032598426,0.00007218491,0.000088251036,0.000041895033,0.00016615058,0.00008248781,0.0010937604,0.00002370319,0.000044405384],"category_scores_gemma":[0.00006720835,0.000047665068,0.00002481709,0.00028208102,0.00006267541,0.0005942657,0.00051301025,0.00015032639,0.00005775041],"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":[0.000005152354,0.0000669492,0.038297147,0.00026834512,0.000053589647,0.000007478612,0.0043796585,0.0045224116,0.29493025,0.0060439464,0.00050475815,0.65092033],"study_design_scores_gemma":[0.000081607446,0.000060003335,0.009532179,0.00004279143,0.0000012188042,0.000010996291,0.000056393554,0.9524603,0.036392327,0.00074711756,0.0005448412,0.000070209666],"about_ca_topic_score_codex":0.000018346325,"about_ca_topic_score_gemma":0.0000011699166,"teacher_disagreement_score":0.9479379,"about_ca_system_score_codex":0.00001867465,"about_ca_system_score_gemma":0.0000292919,"threshold_uncertainty_score":0.20324971},"labels":[],"label_agreement":null},{"id":"W7033425217","doi":"","title":"Quelle politique pour répondre aux discriminations à l'université ?","year":2024,"lang":"fr","type":"article","venue":"Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B))","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Social power; Limiting","score_opus":0.019022440958892668,"score_gpt":0.24884224754802545,"score_spread":0.22981980658913279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033425217","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08198637,0.016141897,0.34993848,0.21965407,0.0023655111,0.0034087868,0.0027530736,0.002399577,0.32135224],"genre_scores_gemma":[0.5072721,0.0060177795,0.007129162,0.0024260383,0.000675899,0.00002325469,0.000392859,0.0003931275,0.47566974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9910779,0.0009977164,0.00072129373,0.0026597073,0.0013889081,0.0031544445],"domain_scores_gemma":[0.9924491,0.0019431789,0.00043895948,0.0019831837,0.00090407673,0.0022815235],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["metaepi_narrow","open_science"],"category_scores_codex":[0.00093494984,0.0016213681,0.0013832514,0.002661885,0.0041486095,0.006193182,0.006948123,0.0010420909,0.00085087755],"category_scores_gemma":[0.00035096786,0.0017945123,0.001017165,0.005323706,0.0026600452,0.0066324156,0.013311257,0.0021703956,0.00040607387],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012077581,0.00029404895,0.00045842936,0.0006079413,0.00079245935,0.010477988,0.11564345,0.0024563915,0.00017726635,0.8201887,0.013224041,0.03447151],"study_design_scores_gemma":[0.004521082,0.000536198,0.0020669128,0.0011240292,0.00067873736,0.0029651807,0.013439362,0.07997254,0.000669723,0.029434063,0.8621024,0.0024897878],"about_ca_topic_score_codex":0.0049931807,"about_ca_topic_score_gemma":0.00046716645,"teacher_disagreement_score":0.8488783,"about_ca_system_score_codex":0.00670389,"about_ca_system_score_gemma":0.0032967178,"threshold_uncertainty_score":0.9996534},"labels":[],"label_agreement":null},{"id":"W7038497428","doi":"","title":"Hybrid Fall Rye in Canada","year":2022,"lang":"en","type":"other","venue":"University Library (University of Saskatchewan)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.006230477434639576,"score_gpt":0.16334215867167887,"score_spread":0.15711168123703928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7038497428","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012514494,0.0007728569,0.06983134,0.0045061265,0.0012909416,0.0015018991,0.0022477792,0.0016434299,0.90569115],"genre_scores_gemma":[0.0136837335,0.00023407192,0.040224615,0.000090838104,0.00003239372,7.3126124e-8,0.000113216985,0.00013176189,0.9454893],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997976,0.00017342837,0.000106605796,0.0006893583,0.00058884895,0.00046576723],"domain_scores_gemma":[0.99859476,0.000084414045,0.00021143068,0.0008735293,0.000018766234,0.00021708308],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0000594536,0.0002640671,0.00044903468,0.0008663448,0.00014962691,0.00001850645,0.0036448329,0.000104480765,0.0055103665],"category_scores_gemma":[0.0000035467824,0.00041293056,0.00011271224,0.00086688617,0.00013058526,0.0009882112,0.003630726,0.000601643,0.0000318189],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019267124,0.000295298,0.011213058,0.0005485063,0.00037801216,0.024252912,0.012232089,0.0016226412,0.000015600192,0.001099184,0.9149468,0.033203233],"study_design_scores_gemma":[0.0010395538,0.00005880188,0.00060496933,0.00008889526,0.000012738849,0.000014358417,0.03625294,0.0026525112,0.000014776092,0.00015736656,0.9585281,0.0005749974],"about_ca_topic_score_codex":0.92173576,"about_ca_topic_score_gemma":0.92389464,"teacher_disagreement_score":0.043581296,"about_ca_system_score_codex":0.0009576122,"about_ca_system_score_gemma":0.004023486,"threshold_uncertainty_score":0.9998323},"labels":[],"label_agreement":null},{"id":"W70833783","doi":"","title":"Central clustering of categorical data with automated feature weighting","year":2013,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"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; Weighting; Artificial intelligence; Data mining; Kernel (algebra); Pattern recognition (psychology); Feature (linguistics); Clustering high-dimensional data; Machine learning; Mathematics","score_opus":0.12553371645470476,"score_gpt":0.35394447805044793,"score_spread":0.22841076159574317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W70833783","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":[0.0029916172,0.000008706082,0.9873973,0.0055941655,0.000586588,0.00029580444,0.000015031932,0.00034687103,0.0027638911],"genre_scores_gemma":[0.8759317,0.00001790449,0.12355095,0.00012721088,0.000115245246,0.000026110178,0.00002958971,0.000016279724,0.00018503348],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720204,0.000076505974,0.0005123416,0.00075997843,0.0009387027,0.00051040953],"domain_scores_gemma":[0.9976496,0.00015727241,0.00023941425,0.0010414243,0.00072857353,0.00018370042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024533915,0.00023967875,0.000258221,0.00024203495,0.00010127968,0.00042007677,0.0029891813,0.0000879519,0.0002297644],"category_scores_gemma":[0.00024700345,0.0001965759,0.0000447906,0.00041319584,0.00017839759,0.0014701353,0.0012096242,0.00042044072,0.00020191519],"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":[0.000103684346,0.0004135435,0.0001179716,0.000046781977,0.00013402803,0.00013466491,0.0010009921,0.026280345,0.021456758,0.28895134,0.0006255986,0.6607343],"study_design_scores_gemma":[0.000046414967,0.0001490548,0.0005011721,0.00010999586,0.0000026043929,0.000047063135,0.00015682775,0.9700027,0.019674145,0.008955808,0.00013427863,0.00021994892],"about_ca_topic_score_codex":0.00031782806,"about_ca_topic_score_gemma":0.00005266486,"teacher_disagreement_score":0.94372237,"about_ca_system_score_codex":0.0001332399,"about_ca_system_score_gemma":0.00018719814,"threshold_uncertainty_score":0.8016133},"labels":[],"label_agreement":null},{"id":"W7095231604","doi":"","title":"Algorithm for Minimum Sum-of-Squares Clustering","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Context (archaeology); Fuzzy clustering; Sequence (biology); Field (mathematics); Fuzzy logic","score_opus":0.046744747967012674,"score_gpt":0.3169603332495066,"score_spread":0.27021558528249395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095231604","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":[0.0017239321,0.00008246918,0.9964102,0.00019367896,0.00024498397,0.00026739543,0.000005478276,0.00017589398,0.0008960065],"genre_scores_gemma":[0.02791562,0.000027679629,0.96926725,0.000060702645,0.00008298762,0.00005144929,0.0000017632948,0.000016091226,0.0025764855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858713,0.000025163117,0.00026213314,0.00036700565,0.00034130007,0.00041727832],"domain_scores_gemma":[0.9988468,0.00025032024,0.00006130875,0.00054524734,0.00018772202,0.00010856463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018465907,0.0001279835,0.00020040883,0.00014268768,0.00015304769,0.000030145735,0.00093177176,0.000051905026,0.000012238724],"category_scores_gemma":[0.000059160677,0.00011754472,0.000088705965,0.00031283003,0.00009354077,0.0004062413,0.0004966899,0.00008654436,0.000015936495],"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":[0.000009207069,0.000074222386,0.00005363315,0.00005006258,0.000022880859,0.000032773914,0.0006325518,0.0010681194,0.0023554415,0.0009330997,0.000659769,0.99410826],"study_design_scores_gemma":[0.00053347176,0.00021024715,0.0001986674,0.000014619259,0.0000012305975,0.00007543553,0.000036272704,0.9762011,0.018366018,0.00091791194,0.003269862,0.0001751521],"about_ca_topic_score_codex":0.00003207275,"about_ca_topic_score_gemma":0.000005273335,"teacher_disagreement_score":0.9939331,"about_ca_system_score_codex":0.000039945695,"about_ca_system_score_gemma":0.00007667212,"threshold_uncertainty_score":0.47933346},"labels":[],"label_agreement":null},{"id":"W7133093713","doi":"","title":"Optimal and Greedy Algorithms for Clustering with Applications to Data Science","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"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 Toronto","funders":"","keywords":"Cluster analysis; Constrained clustering; Correlation clustering; Scalability; Class (philosophy); Heuristic; Bounding overwatch; CURE data clustering algorithm; Clustering high-dimensional data","score_opus":0.12314620837366497,"score_gpt":0.4590791525163828,"score_spread":0.33593294414271785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133093713","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":[0.0034587448,0.00019917617,0.989775,0.001060955,0.00055333343,0.0042202165,0.00013585377,0.0003215517,0.00027515195],"genre_scores_gemma":[0.0047147367,0.00019832957,0.9768134,0.00006793395,0.0004351909,0.0020972907,0.0003801674,0.00018740313,0.015105565],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99239933,0.000046601646,0.00053359475,0.0036999309,0.0016718304,0.0016486841],"domain_scores_gemma":[0.9932569,0.0005087644,0.00031124396,0.0038568636,0.0011666446,0.0008995304],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0017772646,0.00067825214,0.00062081916,0.001001276,0.0018320039,0.0015810732,0.006737921,0.00019871889,0.000008321525],"category_scores_gemma":[0.00037563048,0.00069042324,0.00004892282,0.004438348,0.00062636967,0.001745666,0.005440958,0.0005954309,0.00010993065],"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":[0.0004547205,0.00018200863,0.000019678171,0.0017184432,0.0001643464,0.000057068508,0.031449936,0.061207373,0.0064854547,0.0008995365,0.00037965068,0.8969818],"study_design_scores_gemma":[0.0006904766,0.0006890484,0.000514354,0.00043049673,0.000047675316,0.000060401588,0.00683982,0.9836214,0.0009889967,0.000056042114,0.005153757,0.0009075355],"about_ca_topic_score_codex":0.00037104115,"about_ca_topic_score_gemma":0.0004204306,"teacher_disagreement_score":0.922414,"about_ca_system_score_codex":0.00029420824,"about_ca_system_score_gemma":0.0014017145,"threshold_uncertainty_score":0.9995547},"labels":[],"label_agreement":null},{"id":"W7160045919","doi":"10.20894/ijcoa.101.014.001.001","title":"A Multiview Point Perspective on Clustering Algorithms for Similarity Evaluation","year":2025,"lang":"","type":"article","venue":"International Journal of Computing Algorithm","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Cluster analysis; Viewpoints; Similarity (geometry); Correlation clustering; Fuzzy clustering; Set (abstract data type); Perspective (graphical); Pattern recognition (psychology); Single-linkage clustering","score_opus":0.056779147601151984,"score_gpt":0.43804825507439044,"score_spread":0.38126910747323844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160045919","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":[0.00084508606,0.0020190154,0.9690796,0.009310139,0.016390866,0.0013329926,0.00007316866,0.000073271374,0.0008758189],"genre_scores_gemma":[0.24151483,0.00034379677,0.75298095,0.0012413354,0.0034099792,0.00003450646,0.000011386406,0.000074296426,0.00038889868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9908641,0.00086073123,0.0023185525,0.0011858327,0.003785333,0.0009854253],"domain_scores_gemma":[0.9779383,0.002511452,0.0019014854,0.00074883626,0.01657553,0.00032442025],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0077683846,0.00071566907,0.0010746715,0.0019204204,0.0005420532,0.0011807922,0.004102644,0.0003083783,0.00003347099],"category_scores_gemma":[0.0039658714,0.0007382318,0.00090448675,0.0010771243,0.00026337776,0.0011537794,0.0015956315,0.0015679488,0.000016328991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002845973,0.0006913991,0.000017471633,0.00007310359,0.0011990916,0.00013402908,0.0022174004,0.108202554,0.000088323,0.00305394,0.0004554022,0.8835827],"study_design_scores_gemma":[0.006280878,0.0010666738,0.00047285788,0.002974858,0.00015953156,0.00043333168,0.000900215,0.9720129,0.0010647567,0.0118094515,0.0022843818,0.0005401801],"about_ca_topic_score_codex":0.00011051954,"about_ca_topic_score_gemma":0.00000755708,"teacher_disagreement_score":0.8830425,"about_ca_system_score_codex":0.0068038944,"about_ca_system_score_gemma":0.0020891237,"threshold_uncertainty_score":0.99985605},"labels":[],"label_agreement":null},{"id":"W7160145418","doi":"10.20894/ijcoa.101.014.001.21985","title":"A Multiview Point Perspective on Clustering Algorithms for Similarity Evaluation","year":2025,"lang":"","type":"article","venue":"International Journal of Computing Algorithm","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Cluster analysis; Viewpoints; Similarity (geometry); Correlation clustering; Fuzzy clustering; Set (abstract data type); Perspective (graphical); Pattern recognition (psychology); Single-linkage clustering","score_opus":0.056779147601151984,"score_gpt":0.43804825507439044,"score_spread":0.38126910747323844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160145418","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":[0.00084508606,0.0020190154,0.9690796,0.009310139,0.016390866,0.0013329926,0.00007316866,0.000073271374,0.0008758189],"genre_scores_gemma":[0.24151483,0.00034379677,0.75298095,0.0012413354,0.0034099792,0.00003450646,0.000011386406,0.000074296426,0.00038889868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9908641,0.00086073123,0.0023185525,0.0011858327,0.003785333,0.0009854253],"domain_scores_gemma":[0.9779383,0.002511452,0.0019014854,0.00074883626,0.01657553,0.00032442025],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0077683846,0.00071566907,0.0010746715,0.0019204204,0.0005420532,0.0011807922,0.004102644,0.0003083783,0.00003347099],"category_scores_gemma":[0.0039658714,0.0007382318,0.00090448675,0.0010771243,0.00026337776,0.0011537794,0.0015956315,0.0015679488,0.000016328991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002845973,0.0006913991,0.000017471633,0.00007310359,0.0011990916,0.00013402908,0.0022174004,0.108202554,0.000088323,0.00305394,0.0004554022,0.8835827],"study_design_scores_gemma":[0.006280878,0.0010666738,0.00047285788,0.002974858,0.00015953156,0.00043333168,0.000900215,0.9720129,0.0010647567,0.0118094515,0.0022843818,0.0005401801],"about_ca_topic_score_codex":0.00011051954,"about_ca_topic_score_gemma":0.00000755708,"teacher_disagreement_score":0.8830425,"about_ca_system_score_codex":0.0068038944,"about_ca_system_score_gemma":0.0020891237,"threshold_uncertainty_score":0.99985605},"labels":[],"label_agreement":null},{"id":"W74666794","doi":"10.1007/978-3-642-22185-9_31","title":"User Centric Homogeneity-Based Clustering Approach for Intelligence Computation","year":2011,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Advanced Clustering Algorithms Research","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":"Toronto Metropolitan University","funders":"","keywords":"Cluster analysis; Homogeneity (statistics); Computer science; Computation; Data mining; Hierarchical clustering; Software; Information retrieval; Artificial intelligence; Machine learning; Algorithm","score_opus":0.0925614050617813,"score_gpt":0.3398276076177767,"score_spread":0.2472662025559954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W74666794","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":[0.0000029462603,0.00019517756,0.9651475,0.0001671038,0.00020011622,0.00086365273,0.00001635219,0.00012784389,0.03327934],"genre_scores_gemma":[0.008624857,0.00053416874,0.989777,0.00034280604,0.00003039136,0.00010836754,0.000090817135,0.00001628665,0.0004752769],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977035,0.000041709376,0.00078600313,0.0004951518,0.0005535593,0.00042010625],"domain_scores_gemma":[0.9963941,0.00034443915,0.00038107732,0.001955191,0.0007658927,0.00015930804],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013353452,0.0002942867,0.00030437208,0.0015156331,0.0006279026,0.0006390794,0.0044099814,0.0001553399,0.0000028114441],"category_scores_gemma":[0.00006480646,0.00031228628,0.000071677416,0.0006979719,0.0007925227,0.005087262,0.003033511,0.00045520594,0.000020850466],"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":[0.0000074195023,0.00003681749,0.000011118629,0.00012874675,0.0000066655616,3.3049577e-7,0.0008985738,0.03765314,0.0000021336693,0.1721678,0.00004025831,0.789047],"study_design_scores_gemma":[0.00023395206,0.00007626058,0.00009188455,0.00010305776,0.0000038010207,0.000013492327,0.0000097806615,0.9802963,0.00003777504,0.005945737,0.012856521,0.00033144516],"about_ca_topic_score_codex":0.00001188164,"about_ca_topic_score_gemma":0.000004025743,"teacher_disagreement_score":0.94264317,"about_ca_system_score_codex":0.00028343528,"about_ca_system_score_gemma":0.0003977023,"threshold_uncertainty_score":0.99993294},"labels":[],"label_agreement":null},{"id":"W75896675","doi":"","title":"Characterization of Linkage-based Clustering","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":41,"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 Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Correlation clustering; Conceptual clustering; CURE data clustering algorithm; Canopy clustering algorithm; Artificial intelligence; Data mining; Fuzzy clustering; Constrained clustering; Data stream clustering; Machine learning","score_opus":0.014460533485080477,"score_gpt":0.2774060828660243,"score_spread":0.26294554938094383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W75896675","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":[0.13992614,6.3690754e-7,0.85849744,0.0003075089,0.00024493705,0.000075355594,9.288398e-7,0.000119660865,0.00082738645],"genre_scores_gemma":[0.6992436,7.693253e-7,0.30026793,0.00007452426,0.000039678227,0.000006848937,0.0000025846286,0.000006453255,0.0003575949],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924797,0.000017447503,0.0001501725,0.00019179698,0.00022184306,0.00017077147],"domain_scores_gemma":[0.99924886,0.000047198828,0.000053337826,0.0004830826,0.00010713004,0.000060374638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017477067,0.000065261534,0.00008570266,0.00010424291,0.000040602867,0.0000481588,0.00059127883,0.00004540333,0.000044457225],"category_scores_gemma":[0.00004499862,0.000059925762,0.000026939695,0.00026922728,0.00003595322,0.0003188607,0.00022706862,0.00016138988,0.000022226108],"study_design_candidate":"bench_or_experimental","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":[0.0000018871253,0.000020139454,0.000097678676,0.000016706304,0.0000015641245,0.0000021774126,0.00004356595,0.00022622499,0.93910164,0.0013487323,0.0000013624816,0.0591383],"study_design_scores_gemma":[0.00015546473,0.000029057675,0.0030423068,0.000006870727,3.7859323e-7,0.000003007882,0.0000012435759,0.6695462,0.32647556,0.000101627396,0.00057136145,0.00006692666],"about_ca_topic_score_codex":0.000008214774,"about_ca_topic_score_gemma":0.00001014001,"teacher_disagreement_score":0.66932,"about_ca_system_score_codex":0.000008915013,"about_ca_system_score_gemma":0.000046814966,"threshold_uncertainty_score":0.24437016},"labels":[],"label_agreement":null},{"id":"W958955349","doi":"10.1017/cbo9781139031998.014","title":"Statistics of large-scale structure","year":2012,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Scale (ratio); Statistics; Geography; Mathematics; Cartography","score_opus":0.018915480158652145,"score_gpt":0.23660011701962425,"score_spread":0.2176846368609721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W958955349","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012347426,0.00015827995,0.4704156,0.00000472211,0.0002052109,0.00020152977,0.0016403068,0.00008757764,0.5272744],"genre_scores_gemma":[0.00047823944,0.00007334642,0.06445789,0.00001696004,0.00009365982,2.262312e-7,0.00004437414,0.000036830876,0.9347985],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99829316,0.000039442326,0.00019929762,0.00047677758,0.0005321909,0.00045912227],"domain_scores_gemma":[0.99807864,0.00009516892,0.00025699515,0.0010508613,0.00028632378,0.00023202451],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009653813,0.00030525148,0.00040360418,0.00019851132,0.00012900948,0.000034565124,0.0015406756,0.00029837765,0.000009450025],"category_scores_gemma":[0.000009537526,0.00035755988,0.000104475264,0.000015797612,0.0002019205,0.00016765302,0.0017358636,0.00057709,0.0000088661445],"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":[0.000017281141,0.000009920142,0.0000012076256,0.00014453463,0.0000672814,0.00010734778,0.00014920316,0.000020231013,0.00012369301,0.9832823,0.0056263893,0.010450562],"study_design_scores_gemma":[0.0005214336,0.00006903611,0.000023134264,0.000103555525,0.00005789481,0.000026109143,0.000018410512,0.0044495077,0.0015272504,0.00014435241,0.9925746,0.0004847412],"about_ca_topic_score_codex":0.000024767995,"about_ca_topic_score_gemma":0.0000025111083,"teacher_disagreement_score":0.9869482,"about_ca_system_score_codex":0.00017310807,"about_ca_system_score_gemma":0.00013320168,"threshold_uncertainty_score":0.99988765},"labels":[],"label_agreement":null}]}