{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":6,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":6,"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":"cffdf243d9d7","filters":{"venue":"Annals of Data Science"}},"results":[{"id":"W4289225573","doi":"10.1007/s40745-022-00432-6","title":"Forecasting Directional Movement of Stock Prices using Deep Learning","year":2022,"lang":"en","type":"article","venue":"Annals of Data Science","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":66,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Stock market; Computer science; Deep learning; Artificial intelligence; Stock market prediction; Word2vec; Machine learning; Stock (firearms); Sentiment analysis; Binary classification; Econometrics; Support vector machine; Economics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.609124789376396,"gpt":0.5163442024371268,"spread":0.09278058693926927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03551867,0.0001206024,0.0003049671,0.0007205129,0.001002682,0.0001090875,0.004279354,0.00001793784,0.0005330131],"category_scores_gemma":[0.02415333,0.000106064,0.00007007003,0.00429244,0.000600697,0.001832032,0.00497979,0.0002221691,0.000001511491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003906317,"about_ca_system_score_gemma":0.000359566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001911508,"about_ca_topic_score_gemma":0.00001134747,"domain_scores_codex":[0.9931129,0.000461034,0.0009026147,0.0008662941,0.004237912,0.0004193028],"domain_scores_gemma":[0.9937217,0.002974151,0.001217216,0.00117126,0.0008049736,0.0001106664],"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":[0.0001108544,0.0002014642,0.08964239,0.00002107399,0.0000291141,0.000005521533,0.001320243,0.07717986,0.0357974,0.0009731023,0.0008432002,0.7938758],"study_design_scores_gemma":[0.0001568708,0.000297523,0.03190312,0.00003288119,0.00001124485,0.00002858115,0.002036156,0.9414012,0.0116208,0.006838891,0.005456664,0.0002160582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9467461,0.0002603604,0.04678619,0.0001753328,0.0005572816,0.000199832,0.0001319504,0.00002266609,0.005120267],"genre_scores_gemma":[0.8796946,0.000005660424,0.1200111,0.0001022207,0.00004042004,0.000005549203,0.000007139396,0.000008339839,0.0001249926],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8642213,"threshold_uncertainty_score":0.9931365,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220667573","doi":"10.1007/s40745-022-00381-0","title":"A Machine Learning Model for Predicting Individual Substance Abuse with Associated Risk-Factors","year":2022,"lang":"en","type":"article","venue":"Annals of Data Science","topic":"Substance Abuse Treatment and Outcomes","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Machine learning; Decision tree; Naive Bayes classifier; Artificial intelligence; Random forest; Support vector machine; Substance abuse; Logistic regression; Computer science; CHAID; Vulnerability (computing); Psychology; Psychiatry; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.1783476059303608,"gpt":0.3609677976113045,"spread":0.1826201916809438,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001644839,0.0001350882,0.0002680934,0.0001663099,0.0006529954,0.00002447232,0.0007178938,0.00001992249,0.00002367252],"category_scores_gemma":[0.0004441602,0.0001013432,0.00004339933,0.0008814044,0.0002188029,0.0008732052,0.0001186759,0.0002353964,4.845931e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003919214,"about_ca_system_score_gemma":0.0002171724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005526189,"about_ca_topic_score_gemma":0.0001828222,"domain_scores_codex":[0.997984,0.00003686968,0.0002275225,0.0004621715,0.0009005113,0.000388929],"domain_scores_gemma":[0.9985742,0.0002534307,0.0003399078,0.0005522593,0.0001735357,0.0001066394],"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":[0.0002279589,0.0001732268,0.9864714,0.000007481902,0.000103664,0.000005253092,0.008340093,0.003724932,0.0001707764,0.00003177913,0.0001904196,0.0005530897],"study_design_scores_gemma":[0.004444492,0.001509655,0.2377251,0.0001240801,0.000401959,0.00001055517,0.005057726,0.746854,0.003045791,0.0001170863,0.000356313,0.0003532826],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975207,0.0003581478,0.0006303535,0.0001361065,0.00003772641,0.0003346085,0.0008556555,0.00006624376,0.0000604989],"genre_scores_gemma":[0.9960877,0.0002471039,0.002499567,0.0001371791,0.00001167384,0.00002157571,0.0007770513,0.00001636748,0.0002017588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7487463,"threshold_uncertainty_score":0.5022379,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4295631129","doi":"10.1007/s40745-022-00446-0","title":"Impact of COVID-19 on Stock Indices Volatility: Long-Memory Persistence, Structural Breaks, or Both?","year":2022,"lang":"en","type":"article","venue":"Annals of Data Science","topic":"Market Dynamics and Volatility","field":"Economics, Econometrics and Finance","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Volatility (finance); Econometrics; Economics; Autoregressive conditional heteroskedasticity; Long memory; Financial economics; Markov chain; Portfolio; Stock market; Stock (firearms); Stochastic volatility; Coronavirus disease 2019 (COVID-19); Statistics; Mathematics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.230385761088309,"gpt":0.3825578848856986,"spread":0.1521721237973896,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00357785,0.0001466956,0.000406425,0.0004286757,0.0003956182,0.00005903187,0.00234787,0.00003446523,0.002328613],"category_scores_gemma":[0.001032156,0.0001340327,0.0001200271,0.001162694,0.0006201034,0.001106348,0.001083762,0.0001853348,0.000002753032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000110027,"about_ca_system_score_gemma":0.0005865517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002463774,"about_ca_topic_score_gemma":0.0001634518,"domain_scores_codex":[0.9979544,0.00004518982,0.0006354184,0.0007598969,0.0002451163,0.0003599494],"domain_scores_gemma":[0.9972966,0.0001835951,0.0007388967,0.001492761,0.00006936586,0.0002187285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003554494,0.0001872924,0.9900205,0.00009517906,0.00005723157,0.000004789787,0.0006790588,0.00035128,0.00002950107,0.002489087,0.001842937,0.00388769],"study_design_scores_gemma":[0.0003059749,0.0006792179,0.7718546,0.0000077042,0.000004828771,0.000008167231,0.0002392619,0.2220266,0.00001118939,0.003214696,0.001426329,0.0002214445],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9846795,0.0003281743,0.0001477721,0.0003558531,0.0001548153,0.0002141914,0.01150679,0.00001129876,0.002601598],"genre_scores_gemma":[0.9991598,0.00005286067,0.000190054,0.0002519024,0.00001637988,0.000004633094,0.0001361495,0.000007258656,0.0001810224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2216753,"threshold_uncertainty_score":0.9985834,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3031211888","doi":"10.1007/s40745-020-00291-z","title":"Empowering Data Mining Sciences by Habitual Domains Theory, Part II: Reaching Wonderful Solutions","year":2020,"lang":"en","type":"article","venue":"Annals of Data Science","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Management science; Computer science; Restructuring; Operations research; Decision analysis; Data science; Mathematics; Engineering; Political science; Mathematical economics","retraction":null,"screen_n_in":null,"score":{"opus":0.3134005680289257,"gpt":0.3962351238778531,"spread":0.0828345558489274,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.009359444,0.0002006926,0.0002473594,0.0001607009,0.002296833,0.0005790708,0.01539588,0.00004699187,0.00001631637],"category_scores_gemma":[0.00200668,0.0001841293,0.00003082023,0.002007109,0.001390845,0.009391739,0.01109304,0.0002488096,0.00001517819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001009765,"about_ca_system_score_gemma":0.0006983479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007328804,"about_ca_topic_score_gemma":0.000008740576,"domain_scores_codex":[0.9958841,0.0001609867,0.0004594604,0.001594325,0.001038732,0.0008623778],"domain_scores_gemma":[0.9959987,0.0005678062,0.0002950239,0.00268861,0.0001169181,0.0003329497],"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":[0.00004992966,0.0003850295,0.004754774,0.0001345092,0.00009844756,0.00004858728,0.02724954,0.00306303,0.03623821,0.1618094,0.5850586,0.1811099],"study_design_scores_gemma":[0.000389556,0.0007707864,0.0004249324,0.000489011,0.0000266717,0.0000382201,0.002018291,0.8872532,0.006818313,0.00327939,0.09746616,0.001025422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09002329,0.002826055,0.8613955,0.03684593,0.0006435338,0.0002806904,0.001556837,0.0004535378,0.005974621],"genre_scores_gemma":[0.8732228,0.00007980827,0.1236936,0.002681697,0.0001085122,0.000002061216,0.0001695171,0.000009658178,0.0000324362],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8841902,"threshold_uncertainty_score":0.999002,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401478708","doi":"10.1007/s40745-024-00570-z","title":"Non-negative Sparse Matrix Factorization for Soft Clustering of Territory Risk Analysis","year":2024,"lang":"en","type":"article","venue":"Annals of Data Science","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"","keywords":"Cluster analysis; Fuzzy logic; Data mining; Computer science; Fuzzy clustering; Sparse matrix; Matrix decomposition; Machine learning; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1723067282531261,"gpt":0.3603478806697574,"spread":0.1880411524166313,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001436907,0.0000872478,0.0003436183,0.0007815791,0.00008938267,0.00009141415,0.0009134922,0.00003484923,0.00009190074],"category_scores_gemma":[0.0003973282,0.00008723118,0.0001293935,0.001936982,0.0001951446,0.001666902,0.0002633321,0.00005066611,0.00002118961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001169717,"about_ca_system_score_gemma":0.00004955773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00325346,"about_ca_topic_score_gemma":0.0003252923,"domain_scores_codex":[0.9986739,0.000006782213,0.0005225815,0.0005267447,0.0000877564,0.0001822118],"domain_scores_gemma":[0.9986302,0.0001370476,0.0003617808,0.0007183611,0.00009721198,0.0000554581],"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":[0.0002256024,0.0006556275,0.7845061,0.001758325,0.006872267,0.000008352972,0.0077411,0.05175099,0.006818397,0.04560703,0.01332375,0.08073242],"study_design_scores_gemma":[0.00008652551,0.00006762001,0.03945966,0.00003194869,0.0001756876,1.891224e-7,0.00009967507,0.9488738,0.002390115,0.004042258,0.004603504,0.0001690841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08158536,0.0009867051,0.8875992,0.0002252145,0.0003700654,0.0001836414,0.02853388,0.00001877031,0.000497101],"genre_scores_gemma":[0.994386,0.0004828293,0.00448118,0.00002074234,0.00006119295,0.000004327041,0.0004853422,0.000006024783,0.00007242515],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9128006,"threshold_uncertainty_score":0.491828,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2937573193","doi":"10.1007/s40745-019-00216-5","title":"A New Family of Lifetime Distributions: Theory, Application and Characterizations","year":2019,"lang":"en","type":"article","venue":"Annals of Data Science","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Mathematics; Order statistic; Applied mathematics; Poisson distribution; Statistics; Estimator; Exponential family; Negative binomial distribution; Hazard","retraction":null,"screen_n_in":null,"score":{"opus":0.1660101840212524,"gpt":0.4371703354638459,"spread":0.2711601514425935,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006479141,0.00006100281,0.0001306119,0.00005967348,0.00007647125,0.0000230866,0.0005329904,0.00002320095,0.00009826956],"category_scores_gemma":[0.001049074,0.00005592096,0.00001384726,0.0006124632,0.000319544,0.0005472932,0.0001951093,0.00003714518,0.00003274773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004428471,"about_ca_system_score_gemma":0.0001480975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001813459,"about_ca_topic_score_gemma":6.175773e-7,"domain_scores_codex":[0.9990694,0.00002032031,0.0002951014,0.0002483656,0.000250858,0.0001159533],"domain_scores_gemma":[0.9983554,0.0003385356,0.0002055384,0.0007399014,0.0002653234,0.00009532894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003601793,0.00005117451,0.0001853803,0.00002228637,0.000003577931,1.306727e-8,0.00002708054,4.273134e-7,0.01986326,0.9677841,0.001158171,0.01090091],"study_design_scores_gemma":[0.0003287467,0.00007009941,0.1364396,0.00008773158,0.00004045081,0.000003258492,0.0001356813,0.0159692,0.01506961,0.8251187,0.006517312,0.0002195742],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04207996,0.0000284288,0.9523593,0.0007509041,0.00001511742,0.0002783884,0.003349629,0.00002153221,0.001116738],"genre_scores_gemma":[0.9709424,0.00004399618,0.02824534,0.00007967492,0.000009101366,0.000009075147,0.0006034332,0.000003716386,0.00006321289],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9288625,"threshold_uncertainty_score":0.2280391,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}