{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":47,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":47,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"2d95964af09c","filters":{"venue":"ACM Transactions on Knowledge Discovery from Data"}},"results":[{"id":"W2180566385","doi":"10.1145/2733381","title":"Hierarchical Density Estimates for Data Clustering, Visualization, and Outlier Detection","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":857,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Cluster analysis; Computer science; Visualization; Outlier; Anomaly detection; Data mining; Hierarchy; Hierarchical clustering; Pattern recognition (psychology); CURE data clustering algorithm; Mathematics; Artificial intelligence; Correlation clustering","retraction":null,"screen_n_in":null,"score":{"opus":0.09123092616616002,"gpt":0.3467405532963631,"spread":0.255509627130203,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003245128,0.0001848864,0.0001845059,0.0001184139,0.0003682867,0.000391298,0.00241807,0.000103814,0.000005618718],"category_scores_gemma":[0.0001649733,0.0001810467,0.00003250396,0.0003055005,0.00008700784,0.002379086,0.0005098539,0.0001519665,0.00002577914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005027113,"about_ca_system_score_gemma":0.0001012621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001832148,"about_ca_topic_score_gemma":0.0007949124,"domain_scores_codex":[0.9983726,0.00004949764,0.0002716901,0.0009592543,0.0001504274,0.0001965007],"domain_scores_gemma":[0.9955046,0.000292947,0.00007826021,0.003856342,0.000116481,0.0001514134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003057305,0.001805542,0.0005945723,0.0001052967,0.0003625728,0.00000400909,0.001770696,0.0002885277,0.002929705,0.009771018,0.01653857,0.9655238],"study_design_scores_gemma":[0.0006803036,0.0001912795,0.0007163838,0.00003266206,0.0001031533,0.00001717929,0.0000833254,0.9418531,0.009978435,0.01727481,0.02869215,0.0003772346],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002812619,0.0001398208,0.9943002,0.0003343475,0.0003350331,0.0004047899,0.001274155,0.0003426009,0.0000563591],"genre_scores_gemma":[0.8109892,0.00006770592,0.1868007,0.000127153,0.0001353526,0.0001251697,0.001451569,0.00003053606,0.0002725915],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9651465,"threshold_uncertainty_score":0.738287,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045929671","doi":"10.1145/1376815.1376819","title":"Semantic text similarity using corpus-based word similarity and string similarity","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Topic Modeling","field":"Computer Science","cited_by":485,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Similarity (geometry); Semantic similarity; String metric; Artificial intelligence; Word (group theory); Natural language processing; Longest common subsequence problem; Focus (optics); String searching algorithm; String (physics); Representation (politics); Information retrieval; Matching (statistics); Pattern matching; Mathematics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.1204337695552436,"gpt":0.3074205502158795,"spread":0.186986780660636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004279114,0.000448995,0.0004991243,0.0002411639,0.0008887696,0.0003913397,0.003230168,0.0002317603,0.00004392673],"category_scores_gemma":[0.0001673055,0.0004738807,0.0001300574,0.0006018268,0.0002230122,0.003200896,0.0004491765,0.000779875,0.00002848651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001552863,"about_ca_system_score_gemma":0.000453603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009395767,"about_ca_topic_score_gemma":0.001253196,"domain_scores_codex":[0.996618,0.000222386,0.0005515344,0.001596256,0.0004451674,0.0005666909],"domain_scores_gemma":[0.9936689,0.0007663651,0.0001452886,0.005073285,0.0001057097,0.0002404396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001053573,0.01423526,0.08035918,0.00132997,0.002046416,0.001244942,0.009301427,0.1438239,0.0135037,0.005221042,0.003561208,0.7243194],"study_design_scores_gemma":[0.001520633,0.00007072123,0.00786985,0.0002232161,0.0001557927,0.00003782412,0.00005887906,0.9804195,0.00405095,0.003056296,0.00167967,0.0008566504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2578979,0.0004820103,0.7391785,0.000449269,0.000602322,0.000255162,0.0008822596,0.0002009372,0.00005164174],"genre_scores_gemma":[0.9141459,0.0001758536,0.08496581,0.000283262,0.0001203571,0.000007870697,0.0001857914,0.00003426243,0.00008088908],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8365957,"threshold_uncertainty_score":0.9997713,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3120491054","doi":"10.1145/3424672","title":"Knowledge Graph Embedding for Link Prediction","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":476,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Variety (cybernetics); Embedding; Link (geometry); Graph; Scale (ratio); Knowledge graph; Data science; Machine learning; Data mining; Artificial intelligence; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06056504407758513,"gpt":0.3279314449345395,"spread":0.2673664008569543,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002133534,0.0003577867,0.0003477269,0.0002117096,0.0005394758,0.000414845,0.003276558,0.0001848815,0.00003135046],"category_scores_gemma":[0.0001068433,0.0003702025,0.0002399618,0.00121148,0.00008668724,0.004089874,0.0002935379,0.0004600264,0.00009209829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007979282,"about_ca_system_score_gemma":0.0001961013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000742349,"about_ca_topic_score_gemma":0.000169494,"domain_scores_codex":[0.9971006,0.0001379858,0.0004704845,0.001565388,0.0002143044,0.0005112423],"domain_scores_gemma":[0.993304,0.00121803,0.0001063144,0.004986697,0.0002151427,0.0001698342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001508381,0.001734705,0.0001213666,0.0001072459,0.00050923,0.00003732799,0.001234431,0.008586855,0.005688496,0.009830159,0.01995179,0.9520476],"study_design_scores_gemma":[0.00508147,0.0005496453,0.001496757,0.0008657019,0.0004141126,0.00007229965,0.0003356835,0.4892126,0.04378241,0.1320297,0.3239738,0.002185876],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001027492,0.00301986,0.9866519,0.0007681875,0.003832516,0.0003725753,0.003594005,0.0003885637,0.0003448755],"genre_scores_gemma":[0.5396911,0.00286968,0.4436336,0.0005275857,0.001953292,0.0004599357,0.006690711,0.0001821905,0.003991902],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9498617,"threshold_uncertainty_score":0.999875,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2257550357","doi":"10.1145/2976744","title":"Scalable and Accurate Online Feature Selection for Big Data","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Feature selection; Pairwise comparison; Big data; Computer science; Scalability; Feature (linguistics); Benchmark (surveying); Curse of dimensionality; Selection (genetic algorithm); Artificial intelligence; Data mining; Dimensionality reduction; Set (abstract data type); Machine learning; Pattern recognition (psychology); Database","retraction":null,"screen_n_in":null,"score":{"opus":0.1056308529088211,"gpt":0.3196476373088136,"spread":0.2140167843999925,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001863645,0.0001957921,0.0001829068,0.0001166675,0.0002927425,0.0002974211,0.00261951,0.0001229315,0.00002182399],"category_scores_gemma":[0.0001322555,0.00013626,0.00003548318,0.0002859845,0.0000496266,0.004699399,0.0003098651,0.0001465811,0.00007797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000298951,"about_ca_system_score_gemma":0.0001168345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006390895,"about_ca_topic_score_gemma":0.001023407,"domain_scores_codex":[0.9983029,0.00006206945,0.0001918902,0.001045489,0.0001396306,0.0002580295],"domain_scores_gemma":[0.9959974,0.0005771026,0.00007009078,0.003176482,0.0000809767,0.00009792568],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001064902,0.0004711565,0.00007300702,0.00002677107,0.00008721461,8.305026e-7,0.00007678995,0.000009124652,0.01122647,0.00004088049,0.05770346,0.9301778],"study_design_scores_gemma":[0.008352399,0.0007258672,0.003849984,0.001645862,0.00047425,0.00004242178,0.0002922225,0.1570713,0.06797116,0.0151667,0.7423624,0.002045399],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009845309,0.0002938883,0.9651958,0.003746215,0.001318189,0.0002741167,0.01915984,0.000132878,0.00003376177],"genre_scores_gemma":[0.7429394,0.00363117,0.2164994,0.001007866,0.002167817,0.000192164,0.01975499,0.0001210668,0.01368622],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9281324,"threshold_uncertainty_score":0.5556521,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2038873345","doi":"10.1145/1857947.1857950","title":"Centralized and Distributed Anonymization for High-Dimensional Healthcare Data","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Tech University; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data anonymization; Scalability; Data sharing; Information privacy; Information sharing; Health care; Data mining; Data science; Computer security; Database; World Wide Web; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.06175333628821846,"gpt":0.3219685442326207,"spread":0.2602152079444023,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0004026245,0.0002735404,0.0002881897,0.0001350085,0.0004234759,0.0004214385,0.03897484,0.0002250201,0.00003187805],"category_scores_gemma":[0.005262586,0.0002623473,0.0000328211,0.0004515256,0.000170844,0.004624877,0.01800042,0.000491575,0.00002304526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004474717,"about_ca_system_score_gemma":0.0002294687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004180405,"about_ca_topic_score_gemma":0.001610173,"domain_scores_codex":[0.9972908,0.00008210045,0.0003737494,0.001582069,0.0002537421,0.0004175574],"domain_scores_gemma":[0.9677362,0.0008684548,0.000122868,0.03103032,0.0001105434,0.0001316327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004194097,0.002090731,0.00104003,0.0002225989,0.0005263324,0.00001871493,0.0001605154,0.00007400884,0.008612551,0.01200177,0.4874319,0.4874015],"study_design_scores_gemma":[0.004153802,0.0002283247,0.005488982,0.0001962024,0.0002006956,0.00002423026,0.00005714233,0.6566705,0.009264846,0.2888932,0.03359365,0.001228471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009220356,0.0002288647,0.8705069,0.02321884,0.001596704,0.0004541402,0.0943409,0.0004291876,0.000004130316],"genre_scores_gemma":[0.481996,0.0001574581,0.4657933,0.0001491906,0.000102005,0.0000451894,0.05169777,0.00002871009,0.00003046084],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6565965,"threshold_uncertainty_score":0.9999829,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096281132","doi":"10.1145/1460797.1460799","title":"Mining frequent cross-graph quasi-cliques","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Division of Information and Intelligent Systems","keywords":"Heuristics; Computer science; Clique; Data mining; Vertex (graph theory); Graph; Theoretical computer science; Combinatorics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05441437221485232,"gpt":0.3372334490668411,"spread":0.2828190768519887,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0002576771,0.0002756208,0.0002505935,0.0001684708,0.000452949,0.001006535,0.005477641,0.0001026359,0.00004795776],"category_scores_gemma":[0.00005580661,0.0002644818,0.0001054535,0.0006260281,0.00009412618,0.003962445,0.0001443991,0.0002720151,0.0002608568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005374472,"about_ca_system_score_gemma":0.0001393637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001861997,"about_ca_topic_score_gemma":0.0001473332,"domain_scores_codex":[0.997773,0.00006394223,0.0003992102,0.001140485,0.0002528578,0.0003705223],"domain_scores_gemma":[0.9936654,0.0003268954,0.00009917025,0.005683837,0.00007367355,0.0001510503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002053272,0.002114443,0.0001557253,0.000009258139,0.0001131277,0.00001316757,0.001102577,0.00008252992,0.0008425939,0.006032854,0.009839436,0.9796737],"study_design_scores_gemma":[0.00750963,0.003405138,0.0742887,0.001512422,0.0007096319,0.0001174993,0.001479837,0.3030951,0.05290907,0.1851049,0.3623514,0.007516745],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0124726,0.0004267137,0.9805956,0.001407867,0.0005238467,0.0001744676,0.003055715,0.0003446254,0.0009985437],"genre_scores_gemma":[0.6445814,0.0003035009,0.3506312,0.0006728818,0.0002588474,0.00006247532,0.002156517,0.00003104841,0.001302113],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.972157,"threshold_uncertainty_score":0.9999807,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2400248106","doi":"10.1145/2724720","title":"Improving Top-N Recommendation for Cold-Start Users via Cross-Domain Information","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Cold start (automotive); Computer science; Domain (mathematical analysis); Matrix decomposition; Cluster analysis; Precision and recall; Recommender system; Data mining; Artificial intelligence; Machine learning; Information retrieval; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.06982123719770345,"gpt":0.3200112914309484,"spread":0.2501900542332449,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007623043,0.0002310395,0.0002351574,0.00019464,0.0002783944,0.0009873555,0.002173366,0.0001270689,0.00001465929],"category_scores_gemma":[0.00008071058,0.0002173056,0.00008876645,0.0002998618,0.00003340177,0.01203333,0.0001596766,0.0001773848,0.00008282127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002067786,"about_ca_system_score_gemma":0.0002016056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006296077,"about_ca_topic_score_gemma":0.0003351189,"domain_scores_codex":[0.9983956,0.00009190167,0.0005134649,0.0005209323,0.0001864,0.0002917669],"domain_scores_gemma":[0.9968312,0.0002710605,0.0001982522,0.002375298,0.0001832672,0.0001409534],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001813303,0.0007228827,0.000662962,0.0001398778,0.0002323205,0.000001651015,0.00408406,0.00013171,0.001246136,0.004206349,0.04893838,0.9394524],"study_design_scores_gemma":[0.004506389,0.0007969041,0.0005047991,0.0001638063,0.00008993933,0.00001477182,0.0009350664,0.1508243,0.0314201,0.02232509,0.7870683,0.001350524],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002557953,0.00003905292,0.9915342,0.0008588435,0.00182409,0.0006651043,0.001846466,0.0002962637,0.000377968],"genre_scores_gemma":[0.6877248,0.00002662273,0.3066283,0.0005049883,0.0002562315,0.0004104264,0.004009229,0.00004018234,0.0003991507],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9381018,"threshold_uncertainty_score":0.9521092,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2069857456","doi":"10.1145/1993077.1993080","title":"Can the Utility of Anonymized Data be Used for Privacy Breaches?","year":2011,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Office of Integrative Activities; Office of International Science and Engineering; Division of Information and Intelligent Systems; Research Grants Council, University Grants Committee","keywords":"Data publishing; Computer science; Data anonymization; Adversary; Anonymity; Information privacy; k-anonymity; Closeness; Internet privacy; Data mining; Computer security; Data science; Publishing; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2143621106515954,"gpt":0.3377835758204947,"spread":0.1234214651688993,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001091633,0.0003306365,0.0004332962,0.0001431653,0.0003157541,0.000191133,0.1379265,0.0001796375,0.0001054385],"category_scores_gemma":[0.006944679,0.0002543618,0.0001117044,0.0006280677,0.0004210921,0.003849493,0.03717623,0.000430718,0.00001743121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004479426,"about_ca_system_score_gemma":0.0003441144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00151251,"about_ca_topic_score_gemma":0.001952232,"domain_scores_codex":[0.9968375,0.0002028703,0.0005793292,0.00158289,0.0003447333,0.0004527026],"domain_scores_gemma":[0.92076,0.001737767,0.0002320778,0.07709621,0.00009681802,0.00007714401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007105922,0.005684501,0.001756128,0.0002609449,0.001732018,0.00001208078,0.006062005,0.000002686864,0.002566603,0.001949057,0.579182,0.4000814],"study_design_scores_gemma":[0.006062807,0.0005008696,0.01124096,0.0003760942,0.0008645111,0.0000187789,0.001171553,0.3961843,0.09721239,0.4344465,0.05003959,0.001881621],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007253928,0.0002414425,0.9307585,0.009254766,0.0007614865,0.0007821707,0.05035718,0.0003787848,0.0002117048],"genre_scores_gemma":[0.7224647,0.00009986045,0.2735415,0.00009728933,0.00004282353,0.00007632699,0.003583652,0.00003068657,0.00006321892],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7152107,"threshold_uncertainty_score":0.9999909,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2602756700","doi":"10.1145/3046941","title":"An Influence Propagation View of PageRank","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Opinion Dynamics and Social Influence","field":"Physics and Astronomy","cited_by":82,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China; National Science Fund for Distinguished Young Scholars; Youth Innovation Promotion Association; National Science Foundation","keywords":"PageRank; Computer science; Ranking (information retrieval); Computation; Constraint (computer-aided design); Node (physics); Theoretical computer science; Data mining; Information retrieval; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04113487103308461,"gpt":0.345878011987555,"spread":0.3047431409544704,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013727,0.0001499187,0.0002124827,0.00003679169,0.0005175538,0.0002760403,0.001957895,0.00004763517,0.0001525846],"category_scores_gemma":[0.00001884316,0.0001438401,0.00006861816,0.00006452973,0.0001631119,0.002695205,0.00005466626,0.0001698442,0.00005577574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001470031,"about_ca_system_score_gemma":0.0001159904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001677692,"about_ca_topic_score_gemma":0.0001811374,"domain_scores_codex":[0.999001,0.00005231127,0.000267914,0.0003985611,0.0001290604,0.0001511102],"domain_scores_gemma":[0.9961578,0.00008279178,0.0001972143,0.003401404,0.00009480951,0.00006600426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001585767,0.003618301,0.05410367,0.0001180339,0.0005670246,0.000002356476,0.002544837,0.001917556,0.01421656,0.02231427,0.0002467643,0.900192],"study_design_scores_gemma":[0.005935146,0.0008841513,0.7445435,0.001949587,0.000879129,0.000001141107,0.002538935,0.05087984,0.0429886,0.1258054,0.02025862,0.003336003],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8142864,0.00006966068,0.1748541,0.000180548,0.0004775055,0.0002849894,0.008456795,0.00002699591,0.001363059],"genre_scores_gemma":[0.9980007,0.00003975412,0.0007789271,0.00001646533,0.0001231456,0.00002033627,0.0008648611,0.00001593207,0.0001399242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8968561,"threshold_uncertainty_score":0.586563,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3027864066","doi":"10.1145/3377939","title":"Story Forest","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Timeline; Computer science; Event (particle physics); Information retrieval; The Internet; Novelty; World Wide Web; Cluster analysis; Set (abstract data type); News aggregator; Graph; Data science; Artificial intelligence; History","retraction":null,"screen_n_in":null,"score":{"opus":0.06664237805374586,"gpt":0.3114345391788544,"spread":0.2447921611251086,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0001210553,0.0002262196,0.000257621,0.000106143,0.0002176148,0.0002156184,0.005876232,0.0000758915,0.00005461461],"category_scores_gemma":[0.0001133996,0.0002197622,0.0001137857,0.0006317184,0.00007222089,0.003915032,0.0003020019,0.0003907169,0.0004892565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005866664,"about_ca_system_score_gemma":0.0001077944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003863608,"about_ca_topic_score_gemma":0.0002811239,"domain_scores_codex":[0.9981965,0.00009602082,0.0002393066,0.0009877858,0.0002320595,0.0002483482],"domain_scores_gemma":[0.995061,0.0003462591,0.00007550845,0.00430856,0.00004851175,0.0001601719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001185077,0.001511925,0.0006964733,0.00005939703,0.000684283,0.0000717228,0.003272465,0.001935378,0.005527878,0.0104373,0.04901138,0.9266733],"study_design_scores_gemma":[0.002612652,0.0008706229,0.004697907,0.0002544108,0.0006033848,0.0000112368,0.0005607742,0.2985135,0.04590346,0.06312782,0.5796736,0.003170673],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001281829,0.0003572182,0.9932447,0.003050372,0.0002207741,0.0001441147,0.000643295,0.0005813295,0.000476389],"genre_scores_gemma":[0.8561631,0.0001285432,0.1419536,0.0007959017,0.0001525868,0.00002994107,0.0003889267,0.00003012964,0.0003573156],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9235026,"threshold_uncertainty_score":0.9995025,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1973522621","doi":"10.1145/2757281","title":"Refining Social Graph Connectivity via Shortcut Edge Addition","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":52,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Graph; Computation; Theoretical computer science; Algorithm; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.08509666336746628,"gpt":0.3278070009381637,"spread":0.2427103375706974,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002914757,0.0002877065,0.0003748217,0.0001585086,0.0003761527,0.0001712347,0.001102907,0.00008236161,0.000662064],"category_scores_gemma":[0.00001564481,0.0003002685,0.000205549,0.0004875426,0.0001058647,0.001326007,0.0001145437,0.0003934701,0.0001644124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008501604,"about_ca_system_score_gemma":0.0001253594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001199716,"about_ca_topic_score_gemma":0.001330096,"domain_scores_codex":[0.9982305,0.0001749625,0.0003349061,0.0007235213,0.0002275357,0.0003085707],"domain_scores_gemma":[0.9975376,0.0002892058,0.0001241657,0.001815959,0.000107294,0.0001258354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003682015,0.003766911,0.008584977,0.00001787253,0.001964874,0.00000673108,0.001417823,0.0003137023,0.001328566,0.004451393,0.129131,0.848648],"study_design_scores_gemma":[0.009899933,0.001120831,0.02709621,0.0006909956,0.006016416,0.000009991234,0.00589525,0.03997262,0.02797641,0.5094182,0.3643956,0.007507573],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04771097,0.00009028627,0.9375229,0.0001562939,0.0004231863,0.0001556772,0.008145196,0.0002206177,0.005574883],"genre_scores_gemma":[0.9878633,0.000003809336,0.002204892,0.00002975012,0.0007953213,0.00007107351,0.008639165,0.00003980699,0.0003528513],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9401523,"threshold_uncertainty_score":0.9999449,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1965792576","doi":"10.1145/1376815.1376816","title":"Joint cluster analysis of attribute data and relationship data","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining; Cluster analysis; Heuristic; Identification (biology); Tree (set theory); Machine learning; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1540393998356944,"gpt":0.3374659296680593,"spread":0.1834265298323649,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004265724,0.00025256,0.0005923204,0.0003726126,0.0003128995,0.00008344376,0.003680263,0.00006380738,0.0004219112],"category_scores_gemma":[0.00005348241,0.0002443412,0.000121538,0.001220822,0.0001855284,0.002065541,0.001111756,0.0003093673,0.00002601295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002190926,"about_ca_system_score_gemma":0.0001055807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00121993,"about_ca_topic_score_gemma":0.001299662,"domain_scores_codex":[0.9976367,0.0001624783,0.0005974874,0.001149845,0.0002259426,0.000227586],"domain_scores_gemma":[0.986357,0.0007765085,0.0002055939,0.01250095,0.00006924662,0.00009073617],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002603028,0.004562328,0.739602,0.00006616323,0.02723509,0.000009455821,0.00156919,0.002690768,0.0004094742,0.001364267,0.1356031,0.08662786],"study_design_scores_gemma":[0.002083088,0.0001106053,0.3737023,0.0002162885,0.02407516,0.000004068892,0.0007328013,0.5546895,0.0008371073,0.005674841,0.03628045,0.001593761],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09494489,0.0003875556,0.8141442,0.0002572213,0.00008240924,0.0001997846,0.08961523,0.00005537998,0.0003133407],"genre_scores_gemma":[0.898113,0.0001050399,0.007239299,0.000020576,0.0001193664,0.000008927831,0.09404662,0.0000228407,0.0003243665],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8069049,"threshold_uncertainty_score":0.9963944,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2724995883","doi":"10.1145/3080574","title":"Mining Community Structures in Multidimensional Networks","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Relevance (law); Identification (biology); Set (abstract data type); Data mining; Node (physics); Function (biology); Machine learning; Feature (linguistics); Artificial intelligence; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.06927095770474913,"gpt":0.3432355618617533,"spread":0.2739646041570042,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002699007,0.0002366691,0.0003163606,0.0001002345,0.001070641,0.0002616713,0.002574512,0.00006535163,0.0004004307],"category_scores_gemma":[0.00002436867,0.0002310276,0.0001121887,0.0001081213,0.0001419975,0.001022345,0.0003250817,0.0006925988,0.00001709593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003662075,"about_ca_system_score_gemma":0.00005237741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006324115,"about_ca_topic_score_gemma":0.006171139,"domain_scores_codex":[0.9986789,0.0002039255,0.0003016838,0.0004249495,0.0001236869,0.0002668216],"domain_scores_gemma":[0.9940179,0.0005477341,0.0001508756,0.005182915,0.00003522127,0.00006534984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003706893,0.004092699,0.1904051,0.00002284242,0.001501451,0.00001269469,0.001975687,0.01771205,0.0007908805,0.004668862,0.01102931,0.7674177],"study_design_scores_gemma":[0.004907799,0.0001948734,0.612514,0.0008766637,0.0008468434,0.000002194603,0.003147614,0.2836301,0.004982361,0.07225421,0.01410323,0.002540137],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5843973,0.0001259744,0.4112223,0.0001119057,0.0003713024,0.0002027715,0.001712806,0.00006569144,0.001789946],"genre_scores_gemma":[0.9904635,0.00001157047,0.00705247,0.00002032762,0.0002278707,0.00002209355,0.002001588,0.00002564753,0.0001749506],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7648776,"threshold_uncertainty_score":0.9560212,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2405494619","doi":"10.1145/2983533","title":"Structural Analysis of User Choices for Mobile App Recommendation","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Computer science; Mobile apps; App store; Variety (cybernetics); Recommender system; World Wide Web; Margin (machine learning); Focus (optics); Taxonomy (biology); Data science; Human–computer interaction; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.05976271325554005,"gpt":0.3313509147680883,"spread":0.2715882015125483,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002458964,0.0001697929,0.0003392482,0.0003504629,0.0001252054,0.0001342368,0.002275645,0.00007735258,0.0001079239],"category_scores_gemma":[0.00002861985,0.00011652,0.0001794781,0.0006481597,0.00003565233,0.002727094,0.0001020782,0.00006304806,0.00001003778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005117532,"about_ca_system_score_gemma":0.00004669107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002623748,"about_ca_topic_score_gemma":0.0008108974,"domain_scores_codex":[0.9985726,0.00008040207,0.0004023005,0.0006417609,0.0001181798,0.0001847375],"domain_scores_gemma":[0.9963124,0.0007535935,0.0001765218,0.002617705,0.00008801372,0.00005172679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004939041,0.0002957832,0.0012294,0.00003441428,0.001733833,2.755784e-7,0.0003939413,0.0000417689,0.002664299,0.001481985,0.003562809,0.9885121],"study_design_scores_gemma":[0.007133161,0.001898118,0.05084994,0.0008072035,0.00516641,0.000007127373,0.000639175,0.1621597,0.1757234,0.02592453,0.5662169,0.003474256],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0150475,0.00007162162,0.9777194,0.000347857,0.0005684756,0.000357523,0.005647428,0.0001263437,0.0001138559],"genre_scores_gemma":[0.9662873,0.00007953702,0.03199461,0.00003311884,0.00006105348,0.0001602973,0.0008113271,0.00001431124,0.0005584374],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9850379,"threshold_uncertainty_score":0.4751548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2020791430","doi":"10.1145/1552303.1552306","title":"Link spam target detection using page farms","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"PageRank; Computer science; Backlink; Web page; Spamdexing; HITS algorithm; Information retrieval; Ranking (information retrieval); Link analysis; Search engine; Precision and recall; Data mining; World Wide Web; Web search engine; Static web page; Web search query; Web development","retraction":null,"screen_n_in":null,"score":{"opus":0.05779916987046218,"gpt":0.2945533312560526,"spread":0.2367541613855904,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002713544,0.0002785377,0.000235811,0.0002332523,0.000488733,0.0005919617,0.002636426,0.00016915,0.00004022597],"category_scores_gemma":[0.00006658066,0.0002762036,0.0001170533,0.0007371004,0.00003989708,0.004181034,0.00008185375,0.0004503764,0.0001735314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000133321,"about_ca_system_score_gemma":0.00009877011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000302772,"about_ca_topic_score_gemma":0.0002219758,"domain_scores_codex":[0.9979715,0.0001232977,0.0003228016,0.0009670948,0.0002683499,0.0003469131],"domain_scores_gemma":[0.9959709,0.0001933399,0.0001011979,0.00355343,0.00005980282,0.0001213286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001206466,0.0008594718,0.00008298398,0.00001757072,0.0001434447,0.00002141496,0.001112949,0.002800131,0.05362551,0.0002861228,0.0004991576,0.9404306],"study_design_scores_gemma":[0.001912311,0.0008371077,0.005347279,0.0002392601,0.0002382529,0.00006133546,0.0001487858,0.7392189,0.1797284,0.03806785,0.03254469,0.001655867],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02672342,0.0002901456,0.9687198,0.000560198,0.002444731,0.0001890964,0.000386925,0.0003541911,0.0003314641],"genre_scores_gemma":[0.966371,0.00006263352,0.03245252,0.0002101632,0.0004634196,0.000006834159,0.0001708532,0.0000210877,0.0002414727],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9396476,"threshold_uncertainty_score":0.999969,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3039137796","doi":"10.1145/3394053","title":"Internal Evaluation of Unsupervised Outlier Detection","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Outlier; Anomaly detection; Computer science; Cluster analysis; Data mining; Artificial intelligence; Domain (mathematical analysis); Pattern recognition (psychology); Binary number; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1100711224031969,"gpt":0.3275591643988292,"spread":0.2174880419956323,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002969287,0.0001534508,0.0001739446,0.0001006733,0.0001392987,0.0001162039,0.002318597,0.00007887397,0.000122459],"category_scores_gemma":[0.00007509893,0.0001515665,0.00009180734,0.0005632376,0.00004761198,0.001528809,0.0001327994,0.0002097652,0.0001211563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006210299,"about_ca_system_score_gemma":0.0001159603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001415572,"about_ca_topic_score_gemma":0.0001075203,"domain_scores_codex":[0.9984031,0.0001248339,0.0003400802,0.0006422192,0.0003548666,0.0001349506],"domain_scores_gemma":[0.9973517,0.0001240356,0.0001119491,0.00214071,0.0001810349,0.0000905405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005553005,0.0004450823,0.00005806295,0.00001732877,0.0001186204,5.280273e-7,0.0008607258,0.0004566259,0.02280034,0.0004733574,0.0005580741,0.9741557],"study_design_scores_gemma":[0.001273032,0.0003459083,0.002381554,0.00006201524,0.0002579307,0.000003723004,0.0002320781,0.6556272,0.324532,0.006137423,0.008700502,0.0004466434],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01930838,0.0001076833,0.9780458,0.0007170492,0.0002364153,0.0003209901,0.0005167158,0.0001998348,0.0005471258],"genre_scores_gemma":[0.986863,0.00003857337,0.01263024,0.0001312207,0.00008374235,0.000073489,0.0001066259,0.00001428828,0.00005885168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9737091,"threshold_uncertainty_score":0.6180704,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2214080290","doi":"10.1145/2700409","title":"Classification with Streaming Features: An Emerging-Pattern Mining Approach","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Streaming data; Feature selection; Data mining; Benchmark (surveying); Classifier (UML); Curse of dimensionality; Feature (linguistics); Machine learning; Artificial intelligence; Feature vector; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.1110131822858443,"gpt":0.3239055552908267,"spread":0.2128923730049824,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002823343,0.0002583999,0.000204905,0.0001506265,0.000305398,0.0006896158,0.00408963,0.00008465454,0.000006092324],"category_scores_gemma":[0.00003102262,0.0002229078,0.00003379272,0.0006023531,0.00007497743,0.004448361,0.0001492353,0.0002624347,0.00005466597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007163878,"about_ca_system_score_gemma":0.0002262979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004466119,"about_ca_topic_score_gemma":0.0005469379,"domain_scores_codex":[0.997856,0.00008783719,0.0002636352,0.001176781,0.0003220275,0.0002937622],"domain_scores_gemma":[0.9941777,0.0001458333,0.0001142054,0.005239149,0.00009999767,0.0002231195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002530569,0.001397221,0.000352817,0.00001382769,0.0001150014,0.00000449387,0.004822991,0.000445183,0.0001374331,0.0006365609,0.003538706,0.9885104],"study_design_scores_gemma":[0.002300377,0.0005671641,0.01248366,0.000233874,0.0002511609,0.00005479934,0.01166748,0.9490593,0.000846795,0.0009757802,0.02008865,0.001470974],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01198396,0.0001176583,0.9838828,0.0004278727,0.0002481344,0.0001946484,0.002129228,0.0002348712,0.0007808366],"genre_scores_gemma":[0.6339324,0.00002204554,0.3589927,0.00008992276,0.0001823147,0.0001092064,0.00618889,0.00003852311,0.0004439837],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9870395,"threshold_uncertainty_score":0.9089915,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2055028639","doi":"10.1145/1460797.1460801","title":"On domination game analysis for microeconomic data mining","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National University of Singapore","keywords":"Nash equilibrium; Game theory; Dimension (graph theory); Product (mathematics); Commodity; Computer science; Point (geometry); Best response; Space (punctuation); Mathematical economics; Economics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07051834428210217,"gpt":0.3199586946775136,"spread":0.2494403503954114,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004074712,0.0002361388,0.000299319,0.0004667643,0.0002051458,0.0007781206,0.008054944,0.00006041589,0.00004441971],"category_scores_gemma":[0.00007240747,0.0002355513,0.0001137986,0.0006892997,0.00003098208,0.007757449,0.0002791572,0.0001235036,0.0001492839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006325784,"about_ca_system_score_gemma":0.00005548295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003846171,"about_ca_topic_score_gemma":0.0002209533,"domain_scores_codex":[0.9977795,0.00005193988,0.0003433026,0.001384209,0.0001508264,0.0002902158],"domain_scores_gemma":[0.9912363,0.0005368976,0.0001195355,0.008002349,0.00003409537,0.00007080908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009616176,0.001059067,0.00003071685,0.00001303333,0.001006317,0.000004474022,0.0002748016,0.0009493079,0.0001984321,0.003060273,0.01889881,0.9744086],"study_design_scores_gemma":[0.002378332,0.0003820418,0.004677538,0.00008602093,0.001470639,0.000001193107,0.0001513968,0.9291766,0.001341032,0.009165676,0.05022168,0.000947855],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004477437,0.0001030416,0.9809259,0.00142801,0.0005887669,0.0002954917,0.01178427,0.0001065445,0.0002905362],"genre_scores_gemma":[0.7845188,0.0001540163,0.1729331,0.0008776998,0.0002621493,0.00003804383,0.03901297,0.00002821637,0.002175006],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9734607,"threshold_uncertainty_score":0.9973119,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3212326024","doi":"10.1145/3487046","title":"Scalable Mining of High-Utility Sequential Patterns With Three-Tier MapReduce Model","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Brandon University","funders":"Narodowe Centrum Badań i Rozwoju; Høgskulen på Vestlandet","keywords":"Computer science; Scalability; Correctness; Data mining; Completeness (order theory); Computation; Scale (ratio); Database; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.05944832735846505,"gpt":0.2862248184868035,"spread":0.2267764911283385,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002332727,0.0002215253,0.0002920259,0.00007448958,0.0002218647,0.0002669857,0.002829822,0.00007829855,0.000088574],"category_scores_gemma":[0.00002368875,0.0002041556,0.00006445876,0.0005086859,0.00009732098,0.002242213,0.0003366554,0.00021597,0.00003197923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003604956,"about_ca_system_score_gemma":0.0004455495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005649258,"about_ca_topic_score_gemma":0.001460945,"domain_scores_codex":[0.9979524,0.00008305995,0.0003386633,0.001062411,0.0002806316,0.0002828116],"domain_scores_gemma":[0.9941846,0.0001985655,0.0001023266,0.005270162,0.0001403234,0.0001040683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008769757,0.005021908,0.001922575,0.0001748807,0.0007962728,0.00004354091,0.002023834,0.009585463,0.004917977,0.003611839,0.003961254,0.9678528],"study_design_scores_gemma":[0.00117364,0.0001012972,0.005739976,0.0003121736,0.0002336891,0.00001746587,0.0002960164,0.9467992,0.03906717,0.004753268,0.0008834617,0.0006225994],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1002246,0.00009536712,0.8859698,0.0003272422,0.0002481706,0.0001162853,0.01277734,0.00007420725,0.0001670779],"genre_scores_gemma":[0.7326949,0.00002942583,0.2648723,0.0000337865,0.00004594239,0.00003376244,0.001805941,0.00001882624,0.0004650713],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9672301,"threshold_uncertainty_score":0.8325223,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4205969642","doi":"10.1145/3495011","title":"sGrapp: Butterfly Approximation in Streaming Graphs","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Bipartite graph; Theoretical computer science; Streaming algorithm; Graph; Mathematics; Upper and lower bounds","retraction":null,"screen_n_in":null,"score":{"opus":0.03476832363944742,"gpt":0.2913620502884173,"spread":0.2565937266489698,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002256185,0.0002023542,0.0002481447,0.0003061828,0.0003551564,0.0001093617,0.001379138,0.00002358271,0.001126247],"category_scores_gemma":[0.000003673132,0.0002257189,0.0001273008,0.0007959368,0.00003814382,0.0007656152,0.0001792552,0.000431032,0.00002576198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007732025,"about_ca_system_score_gemma":0.00005864246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001566408,"about_ca_topic_score_gemma":0.0005287711,"domain_scores_codex":[0.9984317,0.0001691283,0.0003416925,0.0006127123,0.0002002421,0.0002445356],"domain_scores_gemma":[0.997589,0.000216258,0.00009572983,0.002037128,0.00001923953,0.00004262576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002677615,0.007529104,0.04894419,0.00003366795,0.001095388,0.00001129101,0.002732551,0.009087197,0.002555304,0.01147544,0.01077843,0.9054897],"study_design_scores_gemma":[0.007640392,0.0007592749,0.0461773,0.0004702766,0.001854393,0.000006436608,0.0163635,0.2165303,0.01449753,0.593302,0.09747471,0.004923868],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3186788,0.0001851852,0.6689944,0.0002014534,0.0002913198,0.0004384066,0.008857011,0.0001474101,0.002206017],"genre_scores_gemma":[0.9912899,0.000008632991,0.002261842,0.0000254105,0.00007788634,0.0002037571,0.005833315,0.00002754909,0.0002717487],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9005658,"threshold_uncertainty_score":0.9997869,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2786524829","doi":"10.1145/3047010","title":"ATR-Vis","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Dalhousie University","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo; Natural Sciences and Engineering Research Council of Canada; International Development Research Centre","keywords":"Computer science; Variety (cybernetics); Terminology; Task (project management); Information retrieval; Set (abstract data type); Visualization; Data science; World Wide Web; Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04897813893720501,"gpt":0.2997655827834099,"spread":0.2507874438462049,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002023382,0.0001742626,0.0001929757,0.0001550685,0.0003495961,0.0004488364,0.003781453,0.00007617232,0.0002364659],"category_scores_gemma":[0.0000605429,0.0001565866,0.00009409136,0.0007084415,0.00008617219,0.00308878,0.0001827066,0.0001444941,0.001269106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004108521,"about_ca_system_score_gemma":0.0001074311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000228331,"about_ca_topic_score_gemma":0.001341757,"domain_scores_codex":[0.9983811,0.00009083856,0.0002704878,0.0008031609,0.0002235664,0.0002308127],"domain_scores_gemma":[0.9948745,0.0001875574,0.00006324652,0.00468438,0.0001013105,0.00008905334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007747742,0.001807982,0.001829456,0.00002185711,0.0007347607,0.00001446275,0.002476252,0.0001878308,0.002598868,0.007778014,0.05139454,0.9310785],"study_design_scores_gemma":[0.002873043,0.0008774126,0.02049639,0.0003060813,0.0007580318,0.00001034054,0.0004210156,0.5091985,0.02839396,0.0309367,0.4031799,0.002548569],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003678093,0.0001326935,0.9919854,0.0008256544,0.0009220093,0.00008480417,0.0005920965,0.0001337894,0.001645449],"genre_scores_gemma":[0.9743229,0.00008205503,0.02201365,0.0002858128,0.0003390208,0.00001008691,0.0006383606,0.00001756246,0.002290571],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9706448,"threshold_uncertainty_score":0.9995085,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2895492593","doi":"10.1145/3237191","title":"Enumerating Trillion Subgraphs On Distributed Systems","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"Chongqing Research Program of Basic Research and Frontier Technology","keywords":"Enumeration; Computer science; Scalability; Theoretical computer science; Graph; Algorithm; Combinatorics; Mathematics; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.04566446021945211,"gpt":0.2890463675566758,"spread":0.2433819073372237,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004173035,0.0002992696,0.0002822831,0.0002296304,0.0006710373,0.0006479366,0.003627982,0.0001168218,0.00003939848],"category_scores_gemma":[0.00008256097,0.000264526,0.000114295,0.0009657373,0.0001500362,0.002271482,0.0001264033,0.0003185312,0.0005212574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004894494,"about_ca_system_score_gemma":0.000078823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001025526,"about_ca_topic_score_gemma":0.00007370039,"domain_scores_codex":[0.9976575,0.000266492,0.0003729606,0.001033786,0.0002839442,0.0003853411],"domain_scores_gemma":[0.9947031,0.0006028771,0.0001094744,0.004350277,0.00009966771,0.0001345708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009215315,0.007623262,0.0005006992,0.0001796143,0.001741012,0.0001251127,0.006778107,0.003133512,0.008384954,0.1452656,0.01882765,0.806519],"study_design_scores_gemma":[0.008786706,0.004692369,0.005574602,0.002483286,0.0006424485,0.00009477085,0.002122678,0.6988614,0.07799484,0.09197768,0.1012723,0.005496949],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01782889,0.0002766194,0.972838,0.000190587,0.003285536,0.0002437996,0.004623828,0.0002586752,0.0004540221],"genre_scores_gemma":[0.9947717,0.00004707919,0.003372099,0.00008162457,0.0003519586,0.0000306867,0.001052542,0.000022456,0.0002699124],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9769428,"threshold_uncertainty_score":0.9999807,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2504431993","doi":"10.1145/2948068","title":"The Convergence Behavior of Naive Bayes on Large Sparse Datasets","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Naive Bayes classifier; Computer science; Machine learning; Missing data; Bayes' theorem; Artificial intelligence; Convergence (economics); Data mining; Bayesian probability; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.05267241250637728,"gpt":0.3180910509676954,"spread":0.2654186384613181,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003985704,0.0002252012,0.0002082974,0.0001054803,0.0003257267,0.0001497741,0.00716618,0.00008459675,0.00008766792],"category_scores_gemma":[0.0002119865,0.000138702,0.00006730847,0.0003405692,0.0002152511,0.002663482,0.0003387483,0.0001821051,0.0003999763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006625922,"about_ca_system_score_gemma":0.000146029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005219463,"about_ca_topic_score_gemma":0.0002123773,"domain_scores_codex":[0.9979154,0.000157279,0.0004140522,0.0008604411,0.0003308211,0.000321951],"domain_scores_gemma":[0.9897711,0.001223949,0.0001862768,0.00865044,0.0000859293,0.00008229438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002863266,0.004466416,0.001416089,0.00003639912,0.0002943533,0.00002310288,0.0005697454,0.000003496656,0.039795,0.06181991,0.1256411,0.765648],"study_design_scores_gemma":[0.002299,0.0005847816,0.02056398,0.0006308384,0.0002110732,0.00001063036,0.0002140488,0.002315516,0.6187772,0.009784552,0.343364,0.001244325],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002477889,0.000121114,0.925047,0.0008988146,0.0007544235,0.0003304932,0.07009839,0.0001645097,0.0001073568],"genre_scores_gemma":[0.9836447,0.0008412626,0.01224919,0.00012187,0.00005436516,0.0001614189,0.002341851,0.00002537274,0.0005599458],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9811668,"threshold_uncertainty_score":0.9982055,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1993150471","doi":"10.1145/1870096.1870099","title":"Discovering Knowledge-Sharing Communities in Question-Answering Forums","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Computer science; Cluster analysis; Transaction data; Question answering; Set (abstract data type); Information retrieval; Identification (biology); Focus (optics); Function (biology); Database transaction; Data mining; Artificial intelligence; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.05505658305164102,"gpt":0.3200791919554526,"spread":0.2650226089038116,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0007541249,0.000386086,0.0004108023,0.0004170522,0.000537783,0.000904344,0.006632241,0.0001892592,0.00003992235],"category_scores_gemma":[0.00009476159,0.0003820719,0.000115033,0.0006400475,0.0001233732,0.00479089,0.0006715427,0.001065157,0.0002110661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001221583,"about_ca_system_score_gemma":0.0001542525,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004609925,"about_ca_topic_score_gemma":0.04109391,"domain_scores_codex":[0.997538,0.0001526818,0.0005840641,0.0009061241,0.0002391549,0.0005799856],"domain_scores_gemma":[0.9928135,0.00077612,0.0001090275,0.006101391,0.00005618123,0.0001437555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004013876,0.01266615,0.0924859,0.001056603,0.001389587,0.000195397,0.1777443,0.01553939,0.05489288,0.1526833,0.004981777,0.4859633],"study_design_scores_gemma":[0.006587896,0.0005311692,0.02474916,0.005993009,0.0002010722,0.0001269095,0.01473823,0.7858169,0.02391736,0.02642878,0.1049685,0.005941045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.266786,0.0005761108,0.7243754,0.0002730661,0.00447211,0.0002779344,0.0005851359,0.0003483371,0.002305943],"genre_scores_gemma":[0.9870062,0.000146369,0.01135276,0.00003342347,0.0002329919,0.00008046989,0.0003622983,0.00004675918,0.0007386671],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7702776,"threshold_uncertainty_score":0.9998631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386497976","doi":"10.1145/3622940","title":"Discovering Interesting Patterns from Hypergraphs","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Hypergraph; Data mining; Computer science; Theoretical computer science; Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.07976721731493004,"gpt":0.3152483108612908,"spread":0.2354810935463608,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001784589,0.0002676104,0.0002392392,0.0002125737,0.0003794886,0.0007632081,0.005608071,0.00007553591,0.00005317451],"category_scores_gemma":[0.00007505007,0.000259243,0.00009454446,0.0008407405,0.0000527856,0.003305503,0.0006782473,0.0003165875,0.0009672329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004261708,"about_ca_system_score_gemma":0.00007908837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001690724,"about_ca_topic_score_gemma":0.0008285621,"domain_scores_codex":[0.9977459,0.00006013424,0.0003523463,0.001214921,0.0002411923,0.0003854932],"domain_scores_gemma":[0.9936139,0.00078367,0.00008274014,0.00536118,0.00003165882,0.0001268561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001708128,0.0006436243,0.001733323,0.0000253585,0.0003151542,0.00003847947,0.002225944,0.0004784999,0.00239864,0.001366978,0.006386356,0.9843706],"study_design_scores_gemma":[0.002427894,0.0002290162,0.07162513,0.00137981,0.0003279841,0.000014695,0.002454008,0.8276272,0.01294179,0.02799422,0.0502274,0.002750898],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1279754,0.00008236289,0.8534598,0.0005801893,0.0009639037,0.0001350487,0.01607302,0.0005542049,0.0001760652],"genre_scores_gemma":[0.9473358,0.0002203319,0.04453597,0.000111669,0.0002590898,0.00009260102,0.006855067,0.00004801966,0.0005413988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9816197,"threshold_uncertainty_score":0.999986,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1993625478","doi":"10.1145/1409620.1409623","title":"On disclosure risk analysis of anonymized itemsets in the presence of prior knowledge","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Hacker; Computer science; Heuristics; Context (archaeology); Set (abstract data type); Function (biology); Data mining; Benchmark (surveying); Information retrieval; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.05564791742840004,"gpt":0.3095288978769892,"spread":0.2538809804485891,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009458709,0.0003307804,0.0007112728,0.0008995895,0.0002369065,0.00008015874,0.05363472,0.0001881308,0.00003981543],"category_scores_gemma":[0.009050614,0.000245792,0.0002514653,0.004344023,0.0004497386,0.001973043,0.006864571,0.0006666633,0.00003284671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006737896,"about_ca_system_score_gemma":0.0002216696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006936886,"about_ca_topic_score_gemma":0.002103097,"domain_scores_codex":[0.9965252,0.0006299415,0.0007768251,0.00116728,0.0005311152,0.0003696233],"domain_scores_gemma":[0.9646866,0.004813937,0.0003663938,0.02997398,0.0001063747,0.00005273159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00295063,0.04991819,0.1146678,0.00069422,0.01728505,0.0002922313,0.04018926,0.0110603,0.00685975,0.007807199,0.2797651,0.4685103],"study_design_scores_gemma":[0.006983507,0.00115464,0.3052278,0.001091557,0.003302871,0.0000195079,0.001285285,0.5499222,0.03118277,0.09408648,0.003546676,0.002196695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4329037,0.0009632585,0.5506737,0.0013856,0.0004474733,0.0005512838,0.01246373,0.0001642159,0.0004470032],"genre_scores_gemma":[0.9751831,0.0008281052,0.02331271,0.00001999353,0.00001805824,0.00004580383,0.0005120702,0.00001704684,0.00006311235],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5422794,"threshold_uncertainty_score":0.9999994,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388421529","doi":"10.1145/3631609","title":"Laplacian Change Point Detection for Single and Multi-view Dynamic Graphs","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Canadian Institute for Advanced Research; McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Anomaly detection; Laplacian matrix; Snapshot (computer storage); Laplace operator; Embedding; Theoretical computer science; Graph; Algorithm; Data mining; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.09321852727549758,"gpt":0.335970799174395,"spread":0.2427522718988974,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001606441,0.0002168513,0.0002615508,0.00020649,0.000294201,0.0001351634,0.0005313893,0.00005152387,0.0000774448],"category_scores_gemma":[0.000008750712,0.0002185579,0.0001410436,0.0004790481,0.00005456562,0.0006474492,0.000074742,0.0001515457,0.00005431413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000359563,"about_ca_system_score_gemma":0.00001651481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004873243,"about_ca_topic_score_gemma":0.003308335,"domain_scores_codex":[0.9987683,0.00005374531,0.0002373311,0.0005968026,0.00008222154,0.0002615509],"domain_scores_gemma":[0.9982471,0.0002588322,0.0000709272,0.001316878,0.00003936082,0.00006694474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000500851,0.0005948372,0.0003898399,0.00003795674,0.0003533073,8.120145e-7,0.000379046,0.00001545882,0.003246224,0.0001702065,0.0006220647,0.9941401],"study_design_scores_gemma":[0.009509834,0.00149519,0.03230828,0.001606702,0.004630535,0.000007846293,0.004856789,0.6067781,0.03953386,0.1530823,0.1410304,0.00516016],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05113339,0.0004360422,0.9386553,0.000243597,0.0003607133,0.0008211762,0.007877279,0.0003360357,0.0001364671],"genre_scores_gemma":[0.9925874,0.0001200221,0.002842207,0.00002228388,0.0001200703,0.0003211847,0.003605565,0.00004176113,0.0003394359],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.98898,"threshold_uncertainty_score":0.8912533,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3163912335","doi":"10.1145/3448021","title":"Similarity Embedding Networks for Robust Human Activity Recognition","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Computer science; Embedding; Pattern recognition (psychology); Similarity (geometry); Pairwise comparison; Activity recognition; Cluster analysis; Convolutional neural network; Deep learning; Machine learning; Generalization; Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1595380997247741,"gpt":0.343239936842662,"spread":0.1837018371178879,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005357775,0.0003652805,0.0004743884,0.0001624049,0.0007746984,0.0009140321,0.002319765,0.0002399358,0.0001216892],"category_scores_gemma":[0.000237235,0.0004153155,0.0002494878,0.0006500361,0.00006524276,0.005439603,0.0002922073,0.0005293016,0.0001016116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001809431,"about_ca_system_score_gemma":0.0002608363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002233065,"about_ca_topic_score_gemma":0.003145875,"domain_scores_codex":[0.9968407,0.0003772203,0.0004411715,0.001580082,0.0002846534,0.0004762025],"domain_scores_gemma":[0.9933999,0.001754562,0.0001926524,0.004151868,0.0003368975,0.0001641234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001065686,0.002286644,0.0001031023,0.00009290996,0.000487347,0.00002795106,0.0004422146,0.001656079,0.004421028,0.0001089033,0.004391157,0.9858761],"study_design_scores_gemma":[0.005971317,0.0004454757,0.003483176,0.001203792,0.0006981003,0.00009736064,0.00065202,0.8867067,0.06420445,0.01357922,0.01990236,0.003056095],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01317972,0.0001949828,0.9781402,0.0005543531,0.001924555,0.0005150008,0.004792968,0.0003150057,0.0003831655],"genre_scores_gemma":[0.9676756,0.00006027318,0.0277437,0.0001741879,0.0004428651,0.0001868176,0.003076734,0.00004993406,0.0005898722],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.98282,"threshold_uncertainty_score":0.9998299,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3011191765","doi":"10.1145/3380928","title":"Continuous Influence Maximization","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Maximization; Computer science; Benchmark (surveying); Mathematical optimization; Product (mathematics); Function (biology); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04107850160594025,"gpt":0.291683042845804,"spread":0.2506045412398638,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005888738,0.0001957936,0.0002545568,0.00005110533,0.0001532374,0.0001660945,0.001343951,0.00003772815,0.0007697274],"category_scores_gemma":[0.00001747044,0.0001978903,0.00009920794,0.0004007712,0.00005185266,0.001015736,0.00009347358,0.0002288495,0.0002676182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001843756,"about_ca_system_score_gemma":0.00005631896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003438765,"about_ca_topic_score_gemma":0.00005808832,"domain_scores_codex":[0.9987658,0.00006299142,0.0002770284,0.0005761653,0.0001301593,0.0001879038],"domain_scores_gemma":[0.997926,0.0001631705,0.00008436337,0.001667766,0.00005855365,0.0001001759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004430906,0.002973827,0.04091348,0.00005839509,0.002336318,0.00001189409,0.002935169,0.01683095,0.008597204,0.005833457,0.04973526,0.8693309],"study_design_scores_gemma":[0.008153361,0.001112345,0.03485236,0.0008486583,0.004612334,0.000003164554,0.003751653,0.3152237,0.08678443,0.09504409,0.4429159,0.006698043],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05628267,0.00008864502,0.9383768,0.0005560277,0.00008491256,0.0001966516,0.002939262,0.0001702141,0.001304808],"genre_scores_gemma":[0.9926208,0.00001625906,0.004185059,0.0001679816,0.0002576445,0.00002613808,0.002502604,0.00002696629,0.0001966059],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9363381,"threshold_uncertainty_score":0.8427975,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3209720970","doi":"10.1145/3473910","title":"Semi-Supervised Ensemble Learning for Dealing with Inaccurate and Incomplete Supervision","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IBM (Canada); University of Alberta","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Classifier (UML); Ensemble learning; Supervised learning; Noise (video); Semi-supervised learning; Labeled data; Data mining; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.05977660722155591,"gpt":0.3027910564366063,"spread":0.2430144492150504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002754138,0.0002089412,0.000227423,0.00007963314,0.0005407056,0.0005617004,0.001211698,0.00007216357,0.00002432308],"category_scores_gemma":[0.0001910885,0.0001867083,0.00004144433,0.0002710907,0.00004044614,0.002090459,0.0001875627,0.0003228738,0.00002749107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002854566,"about_ca_system_score_gemma":0.0001374797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002163272,"about_ca_topic_score_gemma":0.0005946452,"domain_scores_codex":[0.9982226,0.0001513577,0.0002477473,0.0009679057,0.0001689834,0.000241372],"domain_scores_gemma":[0.9965711,0.0008309593,0.00007348633,0.002291062,0.0001355013,0.00009794674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002385264,0.0004968649,0.002124008,0.0001663596,0.0002203455,0.0000225124,0.002054342,0.002982656,0.02252673,0.005456049,0.0003800954,0.9633315],"study_design_scores_gemma":[0.002941854,0.000413971,0.007561781,0.0004318697,0.0001733744,0.00004588313,0.0008076325,0.9162698,0.009669797,0.002754476,0.05805703,0.0008724777],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03968042,0.0006353926,0.9573585,0.001162243,0.0001706511,0.0001629343,0.0004672075,0.0001412969,0.0002213956],"genre_scores_gemma":[0.9102501,0.0004119892,0.08588918,0.00009828782,0.00006424505,0.00003004622,0.002840803,0.0000277228,0.0003876642],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.962459,"threshold_uncertainty_score":0.7613743,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3119526997","doi":"10.1145/3428077","title":"Context-Based Evaluation of Dimensionality Reduction Algorithms—Experiments and Statistical Significance Analysis","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IBM (Canada); University of Alberta","funders":"","keywords":"Dimensionality reduction; Computer science; Data mining; Curse of dimensionality; Algorithm; Redundancy (engineering); Context (archaeology); Generalizability theory; Parametric statistics; Machine learning; Reduction (mathematics); Artificial intelligence; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.1002620059718009,"gpt":0.3783655596835932,"spread":0.2781035537117924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004869869,0.0001423872,0.0002541722,0.0001355528,0.0001619404,0.0001146936,0.0005295743,0.00006915176,0.0002058587],"category_scores_gemma":[0.0001296544,0.0001389177,0.00006735561,0.0006325153,0.00008992623,0.001107052,0.00006821756,0.0001223444,0.0000182194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005812615,"about_ca_system_score_gemma":0.0003229595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002122728,"about_ca_topic_score_gemma":0.0001374244,"domain_scores_codex":[0.9978405,0.0004226117,0.0003244652,0.0007724981,0.0005045613,0.000135429],"domain_scores_gemma":[0.9973373,0.0004042173,0.000102102,0.001723261,0.0003536638,0.00007941038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002325973,0.004277564,0.0003810038,0.00007062621,0.001802395,0.0000114739,0.001016702,0.006813079,0.06351519,0.001132279,0.001924673,0.9188224],"study_design_scores_gemma":[0.00196696,0.0001006187,0.008935197,0.0001395186,0.001592957,0.000002967795,0.000702903,0.7074727,0.2732742,0.005008413,0.0003953952,0.0004081913],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0746853,0.0005412615,0.9209868,0.0002660854,0.0003584555,0.0001598806,0.002922523,0.00003007842,0.00004960396],"genre_scores_gemma":[0.9573767,0.00004292977,0.04000604,0.00003967493,0.00002105435,0.00003527327,0.002422917,0.000006506322,0.00004890792],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9184142,"threshold_uncertainty_score":0.5664899,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4317209824","doi":"10.1145/3580367","title":"Differentially Private Release of Heterogeneous Network for Managing Healthcare Data","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Concordia University","funders":"","keywords":"Flexibility (engineering); Computer science; Health care; Scalability; Variety (cybernetics); Data sharing; Data science; Enhanced Data Rates for GSM Evolution; Big data; Information exchange; Private information retrieval; Information sharing; Data mining; Computer security; World Wide Web; Database; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.09979903213826967,"gpt":0.3332541246626596,"spread":0.23345509252439,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005383591,0.0003248335,0.0004326373,0.0002562562,0.0003546084,0.0002648185,0.08199511,0.0001645016,0.00001209401],"category_scores_gemma":[0.002564168,0.0003263587,0.00009877373,0.001156016,0.0001294121,0.002623698,0.04028656,0.000354948,0.00007579925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006544717,"about_ca_system_score_gemma":0.0001637322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002299672,"about_ca_topic_score_gemma":0.000766352,"domain_scores_codex":[0.9965449,0.000136736,0.0005864924,0.001732139,0.0003340227,0.0006657352],"domain_scores_gemma":[0.9498137,0.001055512,0.0002005362,0.04875202,0.00007020216,0.0001080949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002777313,0.0008178037,0.0004181078,0.0005959899,0.000854411,0.00005664916,0.0001907871,0.002014829,0.0007570342,0.002523889,0.2832617,0.7082311],"study_design_scores_gemma":[0.001049062,0.000204361,0.0007853986,0.0005074403,0.0001510667,0.00000676834,0.00004579326,0.6728387,0.0034879,0.3075603,0.01267839,0.0006847488],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007168433,0.0006564875,0.9493866,0.01007921,0.00158875,0.0005752866,0.02955222,0.0009772334,0.00001577128],"genre_scores_gemma":[0.5809961,0.001886667,0.3927747,0.0001807401,0.0002739936,0.0001243439,0.02353205,0.00009784979,0.0001335458],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7075463,"threshold_uncertainty_score":0.9999188,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4225986943","doi":"10.1145/3502726","title":"On the Robustness of Metric Learning: An Adversarial Perspective","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Science Foundation","keywords":"Robustness (evolution); Pairwise comparison; Computer science; Metric (unit); Adversarial system; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.04692128029731266,"gpt":0.309908607807081,"spread":0.2629873275097683,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009261291,0.0002917069,0.0003291103,0.0004022509,0.001256691,0.000188141,0.007974978,0.00006977667,0.0004969681],"category_scores_gemma":[0.0008027835,0.0002458874,0.0001454602,0.001789494,0.0001436572,0.002013296,0.0008124592,0.001448514,0.00003293797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003022416,"about_ca_system_score_gemma":0.0003151656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005903402,"about_ca_topic_score_gemma":0.00010148,"domain_scores_codex":[0.9962942,0.00121517,0.0003509263,0.001114546,0.0006933879,0.0003317745],"domain_scores_gemma":[0.9924831,0.002639567,0.0002366613,0.00443688,0.000117608,0.00008614439],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002589897,0.001145714,0.00004432381,0.000005832664,0.0002114782,0.000008411846,0.003144259,0.949181,0.00007939462,0.03019459,0.0005748522,0.01515115],"study_design_scores_gemma":[0.001968458,0.001285568,0.000665868,0.00004306127,0.0002233083,0.00001183923,0.01045502,0.9680746,0.0006083731,0.01115512,0.004719716,0.0007890845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01792742,0.0001342951,0.9765602,0.001121076,0.002161028,0.0003199448,0.0006358135,0.0001608647,0.0009793086],"genre_scores_gemma":[0.9923961,0.00001324233,0.006515086,0.00008091056,0.0001807444,0.00005504578,0.0002281117,0.00003779393,0.0004929465],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9744687,"threshold_uncertainty_score":0.9999993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399815117","doi":"10.1145/3673761","title":"Learning Individual Treatment Effects under Heterogeneous Interference in Networks","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Weighting; Benchmark (surveying); Interference (communication); Computer science; Generalization; Regression; Spillover effect; Observational study; Range (aeronautics); Confounding; Sample (material); Process (computing); Machine learning; Artificial intelligence; Mathematics; Statistics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.169365479198976,"gpt":0.4090027000751428,"spread":0.2396372208761667,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000187644,0.0003606812,0.00036565,0.0002312582,0.0001025863,0.0002648745,0.0009986944,0.0001726746,0.0001142737],"category_scores_gemma":[0.0001294815,0.0003118894,0.00009673797,0.0003604781,0.00008045635,0.0009977834,0.000111167,0.0006170847,0.00008598671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003590089,"about_ca_system_score_gemma":0.0001148158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001253133,"about_ca_topic_score_gemma":0.001631974,"domain_scores_codex":[0.9981499,0.0001980032,0.0003645425,0.0007879877,0.0001420923,0.0003575266],"domain_scores_gemma":[0.9952724,0.002961618,0.00004923349,0.001622576,0.00001990836,0.00007424213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002828134,0.003189795,0.0003974202,0.0003837962,0.001477694,0.0003710874,0.004720545,0.01538155,0.001305671,0.006385251,0.001235515,0.9648688],"study_design_scores_gemma":[0.003558624,0.005103437,0.0009495682,0.007596092,0.002090263,0.0001060408,0.001710208,0.1474994,0.0678888,0.7527413,0.007065408,0.003690782],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06544109,0.001317562,0.9307624,0.00008087479,0.0005373316,0.0004265149,0.0006345331,0.0005805491,0.0002191558],"genre_scores_gemma":[0.9910362,0.0005540623,0.006857961,0.00003149366,0.00009440262,0.000161344,0.0006290935,0.00007110985,0.0005643214],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9611781,"threshold_uncertainty_score":0.9999333,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4306407742","doi":"10.1145/3563947","title":"Lifelong Online Learning from Accumulated Knowledge","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; Université Laval","funders":"Universidade de Macau","keywords":"Computer science; Lifelong learning; Task (project management); Artificial intelligence; Machine learning; Process (computing); Transfer of learning; Knowledge base; Online learning; Multi-task learning; Knowledge transfer; Knowledge management","retraction":null,"screen_n_in":null,"score":{"opus":0.09332883032205538,"gpt":0.3227769710322922,"spread":0.2294481407102368,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004398712,0.0003755304,0.0003847052,0.0003266533,0.001377958,0.0005350257,0.005736408,0.00009982175,0.001115048],"category_scores_gemma":[0.0002037506,0.0004123793,0.0001581805,0.001207543,0.00007289518,0.002599806,0.0009377652,0.001403582,0.0006234057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002044702,"about_ca_system_score_gemma":0.0003118377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004789385,"about_ca_topic_score_gemma":0.0004833263,"domain_scores_codex":[0.996394,0.0006919604,0.0005413843,0.001423309,0.0004655769,0.0004837603],"domain_scores_gemma":[0.994554,0.001340409,0.0001890495,0.003627887,0.00008430141,0.0002043478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003212774,0.00555113,0.001289318,0.00002850123,0.0008688688,0.0001054908,0.01791124,0.08472993,0.003565111,0.00123891,0.008201253,0.876189],"study_design_scores_gemma":[0.002535203,0.0002931133,0.007699175,0.00009282937,0.0001448323,0.00001122162,0.002938116,0.6534315,0.000564508,0.002024127,0.3291465,0.001118856],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05493166,0.001334938,0.9360772,0.0007937452,0.002323293,0.000273716,0.002583859,0.0006593003,0.001022338],"genre_scores_gemma":[0.9690897,0.0001168301,0.01868297,0.0003405742,0.0002507444,0.00005368877,0.006518397,0.00006485706,0.004882248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9173942,"threshold_uncertainty_score":0.9999221,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220966911","doi":"10.1145/3502727","title":"Stochastic Variational Optimization of a Hierarchical Dirichlet Process Latent Beta-Liouville Topic Model","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Dirichlet process; Hierarchical Dirichlet process; Topic model; Computer science; Measure (data warehouse); Dirichlet distribution; Inference; Prior probability; Parametric statistics; Bayesian inference; Posterior probability; Mathematics; Bayesian probability; Applied mathematics; Artificial intelligence; Data mining; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04890874881870901,"gpt":0.3044790594634345,"spread":0.2555703106447255,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003895146,0.0001792017,0.0002581106,0.0001827246,0.0003898547,0.00008887001,0.002619837,0.00005751662,0.0001254563],"category_scores_gemma":[0.00004735011,0.0001774103,0.00008688738,0.0005522099,0.00004750236,0.001113881,0.0002850353,0.0004107635,0.000004564876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000690711,"about_ca_system_score_gemma":0.0003559192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002774527,"about_ca_topic_score_gemma":0.00001335641,"domain_scores_codex":[0.9980469,0.0002525247,0.0003601518,0.0007135252,0.0004115695,0.00021531],"domain_scores_gemma":[0.9974003,0.0003598307,0.0001157108,0.001965271,0.00007810251,0.00008071945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004676621,0.0007779908,0.000006229852,0.00001696267,0.00008472484,0.000001549354,0.00111712,0.9653277,0.0000610475,0.01323663,0.0001918596,0.01913139],"study_design_scores_gemma":[0.0004508341,0.00007737064,0.00006011016,0.0000161612,0.00005949457,0.000003567656,0.00001903762,0.9572123,0.0001174792,0.04174845,0.00005026381,0.0001849586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007537141,0.0001397633,0.9948135,0.0007832203,0.0004282722,0.0002509056,0.00258155,0.00005919693,0.0001898567],"genre_scores_gemma":[0.5385419,0.00001192953,0.4602747,0.0001076336,0.00004253527,0.00009208557,0.0006249801,0.00001666074,0.0002876177],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5377881,"threshold_uncertainty_score":0.7234583,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391026313","doi":"10.1145/3641108","title":"Interpreting Deep Forest through Feature Contribution and MDI Feature Importance","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Interpretability; Categorical variable; Feature (linguistics); Random forest; Computer science; Tree (set theory); Artificial intelligence; Variety (cybernetics); Feature model; Data mining; Layer (electronics); Machine learning; Pattern recognition (psychology); Mathematics; Software","retraction":null,"screen_n_in":null,"score":{"opus":0.03162727012661239,"gpt":0.3094050055243785,"spread":0.2777777353977661,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003044838,0.0003225614,0.0002719224,0.0001199791,0.0003850106,0.001292059,0.002409063,0.0002065807,0.00002853731],"category_scores_gemma":[0.0002130553,0.0002915953,0.00009749954,0.0007291168,0.0001302163,0.006327083,0.0002630649,0.0006720266,0.0002104385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001409752,"about_ca_system_score_gemma":0.000133543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001410208,"about_ca_topic_score_gemma":0.00289075,"domain_scores_codex":[0.9976599,0.0001014449,0.0002892234,0.001268745,0.0002382861,0.0004424221],"domain_scores_gemma":[0.9962873,0.0007559645,0.00006697805,0.002690597,0.00009427701,0.0001048305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004845089,0.00159066,0.004888052,0.000591853,0.001503027,0.000805142,0.02378074,0.001678158,0.009720583,0.1771602,0.07676279,0.7010343],"study_design_scores_gemma":[0.0006630708,0.00040895,0.002410416,0.001911589,0.0003410976,0.0001394918,0.00189166,0.5436649,0.03332398,0.1370238,0.2763359,0.001885208],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008634987,0.008707508,0.9740537,0.004713938,0.001665415,0.0003145796,0.001048774,0.0003638333,0.0004972343],"genre_scores_gemma":[0.9754582,0.0006251948,0.02189193,0.0002971851,0.0002111549,0.00004452325,0.0006619935,0.00003575359,0.0007740653],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9668232,"threshold_uncertainty_score":0.9999536,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2791982474","doi":"10.1145/3023363","title":"Visual Analysis of Brain Networks Using Sparse Regression Models","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Army Research Office; National Institute of Biomedical Imaging and Bioengineering; DoD Alzheimer's Disease Neuroimaging Initiative; Defense Threat Reduction Agency; Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health; National Natural Science Foundation of China","keywords":"Visual analytics; Computer science; Discriminative model; Visualization; Artificial intelligence; Machine learning; Intersection (aeronautics); Human–computer interaction","retraction":null,"screen_n_in":null,"score":{"opus":0.09753420314028476,"gpt":0.3740269390566549,"spread":0.2764927359163701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003019046,0.0002072955,0.0003704246,0.000506204,0.0002288245,0.0002405243,0.002815192,0.0001021671,0.0001002847],"category_scores_gemma":[0.00005799852,0.0001841209,0.0001432212,0.00253303,0.0001438186,0.003128313,0.0002793374,0.000142958,0.00002453889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004199309,"about_ca_system_score_gemma":0.0001216229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001951061,"about_ca_topic_score_gemma":0.0004840494,"domain_scores_codex":[0.9981413,0.000149109,0.0004342823,0.0007522238,0.0002807606,0.0002423202],"domain_scores_gemma":[0.9958083,0.0003055561,0.0001778083,0.003456026,0.0001474691,0.0001048487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004194923,0.008234859,0.001585734,0.00009120104,0.009920169,0.00003076947,0.005710226,0.6115114,0.005851765,0.02379965,0.02646744,0.3063773],"study_design_scores_gemma":[0.0002471993,0.00005651241,0.0001694924,0.00007731325,0.000528978,5.802211e-7,0.0000603823,0.9961469,0.00106088,0.0006744854,0.0007730899,0.0002041823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008855609,0.0001106292,0.9886715,0.0001200935,0.0004394872,0.00008018603,0.001517902,0.00006838386,0.0001362018],"genre_scores_gemma":[0.9728773,0.00007781191,0.02445918,0.0002473757,0.0001253142,0.000002154344,0.001888979,0.00001909093,0.0003028544],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9642123,"threshold_uncertainty_score":0.7508233,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408221131","doi":"10.1145/3721983","title":"SED2AM: Solving Multi-Trip Time-Dependent Vehicle Routing Problem Using Deep Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Smart Parking Systems Research","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"National Research Council Canada; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Vehicle routing problem; Computer science; Routing (electronic design automation); Artificial intelligence; Reinforcement; Mathematical optimization; Machine learning; Mathematics; Engineering; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.04577542143170239,"gpt":0.3068384094486623,"spread":0.2610629880169599,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000648618,0.0003723897,0.0003956702,0.0003871805,0.0005628671,0.0004154977,0.001495642,0.0001783062,0.0001625558],"category_scores_gemma":[0.000153267,0.0004083715,0.0001099839,0.0006335167,0.00005278358,0.001258114,0.0002086543,0.0008489722,0.0004159987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006060851,"about_ca_system_score_gemma":0.000161879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005649583,"about_ca_topic_score_gemma":0.0004061587,"domain_scores_codex":[0.9974098,0.0001805008,0.0006323584,0.0007394305,0.0003785205,0.0006594099],"domain_scores_gemma":[0.9971582,0.0005315887,0.00006946154,0.002044558,0.00008554073,0.0001106622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004730753,0.0001910545,0.00118794,0.0002534302,0.0005918757,0.00001168034,0.0009142538,0.931405,0.04156744,0.00001241007,0.0003453953,0.02347224],"study_design_scores_gemma":[0.001009894,0.00002723444,0.0002605358,0.0007102435,0.000120671,0.000002839489,0.0004104542,0.9825137,0.01224628,0.00002371706,0.002275222,0.0003991825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03606544,0.0008615599,0.9587902,0.00003335871,0.0008935205,0.0006405949,0.00015437,0.0005642659,0.001996735],"genre_scores_gemma":[0.9896431,0.00007387958,0.00546591,0.00001298159,0.0001374647,0.00006211149,0.0003804405,0.00009589556,0.004128198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9535777,"threshold_uncertainty_score":0.9998368,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313437244","doi":"10.1145/3578586","title":"Summarizing User-item Matrix By Group Utility Maximization","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Greedy algorithm; Computer science; Selection (genetic algorithm); Population; Similarity (geometry); Group (periodic table); Maximization; Data mining; Preference; Cluster analysis; Information retrieval; Theoretical computer science; Artificial intelligence; Algorithm; Mathematical optimization; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.06137206547769925,"gpt":0.3151175045849592,"spread":0.2537454391072599,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004998756,0.0002575461,0.0002751549,0.0002159661,0.0003379282,0.0006082453,0.003637698,0.0001394252,0.00004269315],"category_scores_gemma":[0.00005160278,0.0002489365,0.00009790914,0.001018721,0.00003837823,0.003631687,0.0003231495,0.0002617297,0.0002322959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007104188,"about_ca_system_score_gemma":0.00005920758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006806146,"about_ca_topic_score_gemma":0.0004006017,"domain_scores_codex":[0.9977576,0.0001853391,0.0004268434,0.00100748,0.0002658734,0.0003568468],"domain_scores_gemma":[0.9950407,0.0005075544,0.0001035117,0.004199936,0.00004613778,0.0001021917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006147296,0.001436214,0.003845223,0.0001665085,0.0003750433,0.00002557997,0.001170985,0.00005919486,0.002822097,0.005100809,0.4041354,0.5808014],"study_design_scores_gemma":[0.001756895,0.0002844136,0.009898155,0.0004600436,0.0001485736,0.00001417715,0.0004702568,0.2840926,0.01313772,0.01717846,0.6707206,0.001838109],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002948778,0.0003343076,0.9903732,0.000678908,0.00118214,0.0003184865,0.002613311,0.001098498,0.0004523624],"genre_scores_gemma":[0.9570478,0.0006031288,0.03360219,0.0001482927,0.0001511471,0.0001294219,0.00534713,0.0000634964,0.002907392],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.956771,"threshold_uncertainty_score":0.9999963,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4319349118","doi":"10.1145/3563040","title":"DeltaShield: Information Theory for Human- Trafficking Detection","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Science Foundation","keywords":"Computer science; Interpretability; Scalability; Spotting; Domain (mathematical analysis); Law enforcement; Laptop; Information retrieval; Data mining; Matching (statistics); Artificial intelligence; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.05985050683720564,"gpt":0.3110097719310146,"spread":0.2511592650938089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006332241,0.0001864712,0.0001557928,0.0003763043,0.0006806618,0.0005933723,0.002010606,0.0001313036,0.00001615228],"category_scores_gemma":[0.0001544485,0.0001884134,0.0001036413,0.0008425924,0.00003364773,0.006602312,0.00008667887,0.000229214,0.0003382978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007100953,"about_ca_system_score_gemma":0.00005987423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009401159,"about_ca_topic_score_gemma":0.0004845151,"domain_scores_codex":[0.9986272,0.00009537957,0.0003150055,0.0004896586,0.0001946755,0.0002780675],"domain_scores_gemma":[0.996879,0.0007663606,0.0000954904,0.002125558,0.00007054691,0.00006303997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008668934,0.0001351518,0.000008893056,0.00003999065,0.0001042914,9.80983e-7,0.002211351,0.0014339,0.002689994,0.003465039,0.001486737,0.988337],"study_design_scores_gemma":[0.005684058,0.001329409,0.006331579,0.0004413805,0.0004941474,0.0000232048,0.002527423,0.4810002,0.1280696,0.2296849,0.141801,0.002613155],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0232463,0.00003823528,0.9724162,0.0001899207,0.002057566,0.0003279022,0.0008128742,0.000727051,0.0001839567],"genre_scores_gemma":[0.9949484,0.00003112354,0.003158568,0.0001020658,0.0001910333,0.0001110334,0.001203721,0.00001859898,0.0002353959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9857239,"threshold_uncertainty_score":0.7683275,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4366087542","doi":"10.1145/3592857","title":"Modeling Regime Shifts in Multiple Time Series","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Series (stratigraphy); Computer science; Time series; Dependency (UML); Representation (politics); Grid; Machine learning; Artificial intelligence; Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.06498033503273945,"gpt":0.2730715737043471,"spread":0.2080912386716076,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003291663,0.0002200222,0.0002932345,0.0003160526,0.0002753528,0.0003721284,0.002932492,0.00008369961,0.00006788974],"category_scores_gemma":[0.0001071478,0.0002128397,0.0001020944,0.001458704,0.00004459436,0.004178651,0.0003260307,0.0002492899,0.001152842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005019762,"about_ca_system_score_gemma":0.00008493378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005174461,"about_ca_topic_score_gemma":0.001966986,"domain_scores_codex":[0.9980708,0.0000777739,0.0003765421,0.0008727149,0.000213101,0.00038909],"domain_scores_gemma":[0.9964082,0.0002876419,0.00004988098,0.003136647,0.00003804085,0.0000795884],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003305908,0.001520724,0.0008326042,0.00009962261,0.0006977587,0.0001886649,0.008966154,0.4890836,0.004387558,0.002290863,0.005519859,0.486082],"study_design_scores_gemma":[0.0003171043,0.0000335074,0.000404985,0.00008170404,0.00002400872,0.000001281834,0.000194944,0.9946985,0.0002336305,0.002177953,0.00156534,0.0002670656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06159198,0.0002271703,0.9346733,0.0009737907,0.0004517477,0.0001688905,0.001039175,0.0004177961,0.0004561362],"genre_scores_gemma":[0.978622,0.0001614069,0.01740594,0.00004156605,0.00009881467,0.0000266214,0.0009835234,0.00003403601,0.002626055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9172674,"threshold_uncertainty_score":0.9996248,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2257410811","doi":"10.1145/3365672","title":"A New Smooth Approximation to the Zero One Loss with a Probabilistic Interpretation","year":2019,"lang":"en","type":"preprint","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hinge loss; Algorithm; Computer science; Probabilistic logic; Maxima and minima; Artificial intelligence; Mathematics; Benchmark (surveying); Mathematical optimization; Machine learning; Pattern recognition (psychology); Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.04480686181851787,"gpt":0.2922726434183354,"spread":0.2474657815998175,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0004609571,0.0004188118,0.000379028,0.0002267016,0.00022436,0.001255494,0.006803858,0.0001882208,0.00003136076],"category_scores_gemma":[0.0003629158,0.0003082326,0.00008558171,0.0005408399,0.0000505459,0.001637547,0.0007644881,0.001000757,0.0006361347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001809906,"about_ca_system_score_gemma":0.0007572056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000941722,"about_ca_topic_score_gemma":0.001414735,"domain_scores_codex":[0.9967644,0.0003044241,0.0004525921,0.001712724,0.0004800878,0.0002858095],"domain_scores_gemma":[0.989122,0.0005833429,0.0002854643,0.009694532,0.0001784569,0.0001361549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005399165,0.001166482,0.0001980154,0.0004341621,0.0005047378,0.000002845518,0.009378181,0.1168347,0.0000756471,0.004556789,0.008698326,0.8576102],"study_design_scores_gemma":[0.001401752,0.000552158,0.009106469,0.002373026,0.0006351771,0.000006401184,0.0001667692,0.9250674,0.0002666601,0.0217589,0.03709082,0.001574481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009343374,0.0001421213,0.9888692,0.004504033,0.00128721,0.001387173,0.00217579,0.0002348971,0.0004652418],"genre_scores_gemma":[0.8307936,0.00006072625,0.157434,0.0002786436,0.0002909056,0.0002854885,0.009030242,0.00006118257,0.001765192],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8560357,"threshold_uncertainty_score":0.999937,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3044604502","doi":"10.1145/3480243","title":"Time-Aware Graph Embedding: A Temporal Smoothness and Task-Oriented Approach","year":2021,"lang":"en","type":"preprint","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Embedding; Computer science; Granularity; Theoretical computer science; Graph embedding; Graph; Smoothing; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.03824167191490641,"gpt":0.2946700430901839,"spread":0.2564283711752775,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0002520662,0.0008635396,0.0008942301,0.0003964718,0.0004419841,0.001038798,0.00631435,0.0005277201,0.00002939178],"category_scores_gemma":[0.00004214874,0.0008714191,0.0002902765,0.001113468,0.0003243934,0.003187618,0.002556949,0.001797947,0.00002873371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009247145,"about_ca_system_score_gemma":0.0002864378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001221333,"about_ca_topic_score_gemma":0.0001103002,"domain_scores_codex":[0.994463,0.000330068,0.0006740644,0.003404497,0.0004937968,0.0006345611],"domain_scores_gemma":[0.9893352,0.0004983218,0.0002989398,0.009411076,0.0001679248,0.0002885812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001222489,0.0199816,0.001739596,0.002994747,0.008175198,0.001171597,0.02127901,0.2325454,0.002408377,0.003428422,0.03721682,0.6678367],"study_design_scores_gemma":[0.003293894,0.0002635574,0.001330862,0.002326077,0.0007215805,0.0001079774,0.001089039,0.9544118,0.001067163,0.01633748,0.01412804,0.004922511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01073022,0.003150501,0.9775425,0.0002466028,0.002084466,0.0006665132,0.00501364,0.0004405235,0.0001250171],"genre_scores_gemma":[0.6974429,0.001964672,0.2731691,0.0002599502,0.0004452027,0.000372873,0.02511768,0.0002093933,0.001018181],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7218664,"threshold_uncertainty_score":0.9999982,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07734526681048454,"gpt":0.3535982704819712,"spread":0.2762530036714866,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007092744,0.0008046355,0.0007222937,0.0007342101,0.0007524445,0.001117058,0.01522384,0.0003299337,0.000393725],"category_scores_gemma":[0.0002906745,0.0008637097,0.0003108354,0.0007103118,0.0001758883,0.001713101,0.00629926,0.00396715,0.0001945419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008173398,"about_ca_system_score_gemma":0.0008914137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004457181,"about_ca_topic_score_gemma":0.0004940313,"domain_scores_codex":[0.9931852,0.0006159127,0.0007285065,0.003324496,0.001233428,0.0009125199],"domain_scores_gemma":[0.9829966,0.002226344,0.0002171419,0.01414024,0.00008985901,0.0003297417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004006421,0.002230526,0.00003715876,0.0003497511,0.000398753,0.0002804665,0.001278355,0.5905523,0.0001699149,0.0001393632,0.001121284,0.4030415],"study_design_scores_gemma":[0.001050946,0.0002630032,0.0003210722,0.0005240484,0.00005774086,0.000007303931,0.0001385141,0.9884937,0.0003341281,0.003422421,0.004437756,0.0009493302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001267902,0.0001813542,0.9770254,0.001266308,0.002964635,0.0006946734,0.01534648,0.0005050921,0.000748189],"genre_scores_gemma":[0.6189705,0.0003504675,0.3603444,0.00067187,0.0008721789,0.0009623643,0.01391086,0.000383747,0.003533704],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6177025,"threshold_uncertainty_score":0.9999199,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2325563383","doi":"10.1145/2297456.2297460","title":"The Latent Maximum Entropy Principle","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Statistical Mechanics and Entropy","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Principle of maximum entropy; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04418102761629817,"gpt":0.3089701903070841,"spread":0.2647891626907859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001528767,0.00018535,0.0001521948,0.00002394457,0.0004349946,0.0001737415,0.001028811,0.00003480863,0.0009448302],"category_scores_gemma":[0.00002027352,0.0001285593,0.00008548411,0.0001129739,0.00005098597,0.0005700155,0.00009299676,0.0002407856,0.0008741162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000332476,"about_ca_system_score_gemma":0.00004296779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001693797,"about_ca_topic_score_gemma":0.00001424297,"domain_scores_codex":[0.9987931,0.00006058747,0.0002278566,0.0003176842,0.0001569935,0.0004437474],"domain_scores_gemma":[0.9974007,0.0004812649,0.00005324579,0.001884763,0.00002739722,0.0001526564],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001823301,0.002312027,0.005740006,0.00001127564,0.0007423863,0.000001424076,0.0003832528,0.00004099327,0.0005643795,0.5820554,0.009639564,0.398327],"study_design_scores_gemma":[0.002410419,0.0001828995,0.01186143,0.0000974979,0.0006741635,0.000001748065,0.0008698421,0.01735332,0.007239579,0.1686675,0.7894835,0.001158092],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02055435,0.0003623116,0.9673218,0.0003781989,0.002093089,0.0002324222,0.007676215,0.00003956582,0.001342109],"genre_scores_gemma":[0.9953382,0.00004806185,0.001588501,0.00003395521,0.0005593525,0.0000456838,0.0009954231,0.00002862757,0.001362206],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9747838,"threshold_uncertainty_score":0.9999685,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413592351","doi":"10.1145/3762667","title":"ORIC V2: Improved Feature Interaction Detection Model through Online Random Interaction Chains for Click-Through Rate Prediction","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Petro-Canada","funders":"National Natural Science Foundation of China","keywords":"Feature (linguistics); Random forest; Computer science; Pattern recognition (psychology); Artificial intelligence; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.0650397683175733,"gpt":0.3459675967337768,"spread":0.2809278284162035,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004049081,0.0004523412,0.0004885676,0.0003016577,0.0005588497,0.0005554679,0.001898918,0.0003263949,0.000006489574],"category_scores_gemma":[0.0001199553,0.0004199628,0.0002648173,0.0007598414,0.00004354718,0.008134626,0.0001741419,0.0006882851,0.00001229811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004146592,"about_ca_system_score_gemma":0.0001820026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006389639,"about_ca_topic_score_gemma":0.002262642,"domain_scores_codex":[0.9971393,0.0002340719,0.0006900277,0.001376691,0.0001723278,0.0003875445],"domain_scores_gemma":[0.9956956,0.0006606352,0.0002955851,0.003071484,0.0002157073,0.00006102305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003829096,0.005334775,0.00004721415,0.0005995732,0.001921533,0.000004515759,0.005332298,0.005942837,0.04117299,0.004456988,0.04804499,0.8833132],"study_design_scores_gemma":[0.00298523,0.0002953544,0.0001058217,0.0004044995,0.0002272188,0.000008492936,0.0003848712,0.8918769,0.03767873,0.01080473,0.05477266,0.0004554891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001939569,0.0002557578,0.9842138,0.002250025,0.006161646,0.001336922,0.002762795,0.0006733954,0.0004060902],"genre_scores_gemma":[0.9031737,0.001030679,0.0874735,0.0005886611,0.0005298284,0.0007388378,0.003062974,0.00006665194,0.003335166],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9012341,"threshold_uncertainty_score":0.9998252,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}