{"meta":{"query_hash":"cffdf243d9d7","filters":{"venue":"Annals of Data Science"},"cohort_total":6,"direct_labels_cover":0,"predictions_cover":6,"exported":6,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/cffdf243d9d7","api":"https://metacan.xera.ac/api/v1/cohort?venue=Annals+of+Data+Science"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1660101840212524,"score_gpt":0.43717033546384587,"score_spread":0.2711601514425935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2937573193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042079963,0.000028428798,0.9523593,0.0007509041,0.000015117424,0.00027838844,0.0033496292,0.000021532207,0.0011167378],"genre_scores_gemma":[0.97094244,0.000043996177,0.028245337,0.000079674915,0.000009101366,0.000009075147,0.00060343323,0.0000037163857,0.00006321289],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990694,0.000020320314,0.00029510143,0.0002483656,0.000250858,0.00011595329],"domain_scores_gemma":[0.9983554,0.0003385356,0.0002055384,0.0007399014,0.00026532335,0.00009532894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006479141,0.000061002815,0.00013061191,0.000059673483,0.00007647125,0.000023086595,0.0005329904,0.000023200952,0.000098269564],"category_scores_gemma":[0.0010490735,0.00005592096,0.000013847255,0.00061246316,0.00031954402,0.00054729317,0.00019510929,0.00003714518,0.00003274773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036017927,0.000051174506,0.00018538027,0.000022286371,0.0000035779312,1.3067273e-8,0.00002708054,4.2731344e-7,0.01986326,0.9677841,0.0011581713,0.010900912],"study_design_scores_gemma":[0.0003287467,0.00007009941,0.13643964,0.00008773158,0.00004045081,0.000003258492,0.00013568133,0.015969196,0.01506961,0.8251187,0.0065173125,0.00021957418],"about_ca_topic_score_codex":0.000018134595,"about_ca_topic_score_gemma":6.175773e-7,"teacher_disagreement_score":0.9288625,"about_ca_system_score_codex":0.000004428471,"about_ca_system_score_gemma":0.00014809752,"threshold_uncertainty_score":0.22803906},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.31340056802892574,"score_gpt":0.39623512387785315,"score_spread":0.0828345558489274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031211888","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09002329,0.0028260548,0.8613955,0.036845934,0.00064353383,0.0002806904,0.001556837,0.00045353777,0.0059746206],"genre_scores_gemma":[0.87322277,0.00007980827,0.123693556,0.0026816966,0.00010851223,0.0000020612165,0.00016951714,0.000009658178,0.000032436204],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958841,0.0001609867,0.0004594604,0.0015943251,0.0010387321,0.0008623778],"domain_scores_gemma":[0.9959987,0.0005678062,0.0002950239,0.0026886095,0.00011691812,0.00033294974],"candidate_categories":["sts","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0093594445,0.00020069256,0.00024735936,0.00016070089,0.0022968329,0.0005790708,0.0153958835,0.00004699187,0.000016316366],"category_scores_gemma":[0.0020066805,0.00018412927,0.000030820232,0.0020071086,0.0013908446,0.009391739,0.011093044,0.00024880958,0.000015178186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049929662,0.00038502953,0.004754774,0.0001345092,0.000098447556,0.000048587277,0.027249536,0.00306303,0.03623821,0.1618094,0.5850586,0.18110995],"study_design_scores_gemma":[0.000389556,0.0007707864,0.0004249324,0.000489011,0.000026671698,0.000038220096,0.0020182906,0.8872532,0.0068183127,0.00327939,0.09746616,0.0010254221],"about_ca_topic_score_codex":0.000073288036,"about_ca_topic_score_gemma":0.000008740576,"teacher_disagreement_score":0.8841902,"about_ca_system_score_codex":0.0000100976495,"about_ca_system_score_gemma":0.00069834787,"threshold_uncertainty_score":0.99900204},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.17834760593036078,"score_gpt":0.36096779761130454,"score_spread":0.18262019168094376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220667573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9975207,0.00035814784,0.00063035346,0.00013610652,0.000037726408,0.00033460848,0.0008556555,0.00006624376,0.000060498896],"genre_scores_gemma":[0.99608773,0.00024710386,0.0024995673,0.00013717906,0.000011673837,0.000021575714,0.00077705126,0.00001636748,0.0002017588],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997984,0.000036869682,0.00022752245,0.00046217148,0.00090051134,0.00038892898],"domain_scores_gemma":[0.9985742,0.0002534307,0.00033990777,0.0005522593,0.00017353572,0.00010663939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001644839,0.00013508818,0.00026809337,0.00016630994,0.0006529954,0.000024472316,0.0007178938,0.000019922494,0.000023672523],"category_scores_gemma":[0.00044416016,0.00010134325,0.000043399326,0.00088140444,0.00021880293,0.0008732052,0.00011867595,0.00023539641,4.845931e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022795892,0.00017322681,0.98647135,0.000007481902,0.00010366398,0.000005253092,0.008340093,0.0037249315,0.00017077637,0.00003177913,0.00019041955,0.00055308966],"study_design_scores_gemma":[0.0044444916,0.0015096547,0.23772508,0.00012408009,0.00040195897,0.000010555168,0.0050577256,0.746854,0.0030457908,0.00011708625,0.00035631302,0.00035328264],"about_ca_topic_score_codex":0.00005526189,"about_ca_topic_score_gemma":0.00018282217,"teacher_disagreement_score":0.7487463,"about_ca_system_score_codex":0.00003919214,"about_ca_system_score_gemma":0.00021717245,"threshold_uncertainty_score":0.5022379},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.609124789376396,"score_gpt":0.5163442024371268,"score_spread":0.09278058693926927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289225573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9467461,0.0002603604,0.046786193,0.00017533283,0.0005572816,0.00019983198,0.0001319504,0.000022666092,0.0051202667],"genre_scores_gemma":[0.8796946,0.0000056604244,0.12001109,0.00010222072,0.000040420044,0.0000055492033,0.0000071393956,0.000008339839,0.00012499264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99311286,0.000461034,0.00090261473,0.00086629414,0.0042379117,0.0004193028],"domain_scores_gemma":[0.9937217,0.0029741514,0.0012172161,0.0011712596,0.0008049736,0.00011066644],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03551867,0.000120602424,0.00030496708,0.00072051294,0.0010026816,0.000109087545,0.0042793537,0.000017937837,0.0005330131],"category_scores_gemma":[0.02415333,0.00010606399,0.000070070026,0.00429244,0.000600697,0.0018320315,0.00497979,0.00022216912,0.000001511491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110854424,0.0002014642,0.08964239,0.000021073985,0.000029114099,0.0000055215332,0.0013202426,0.07717986,0.0357974,0.00097310235,0.0008432002,0.79387575],"study_design_scores_gemma":[0.0001568708,0.00029752302,0.031903118,0.00003288119,0.000011244852,0.000028581146,0.0020361564,0.9414012,0.011620803,0.006838891,0.005456664,0.0002160582],"about_ca_topic_score_codex":0.00019115079,"about_ca_topic_score_gemma":0.000011347467,"teacher_disagreement_score":0.86422133,"about_ca_system_score_codex":0.000039063172,"about_ca_system_score_gemma":0.00035956595,"threshold_uncertainty_score":0.9931365},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.23038576108830897,"score_gpt":0.3825578848856986,"score_spread":0.15217212379738962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295631129","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9846795,0.00032817433,0.00014777211,0.00035585306,0.0001548153,0.00021419142,0.01150679,0.000011298755,0.002601598],"genre_scores_gemma":[0.99915975,0.000052860672,0.00019005395,0.00025190235,0.000016379878,0.0000046330942,0.00013614954,0.0000072586563,0.00018102238],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979544,0.000045189816,0.0006354184,0.00075989694,0.00024511633,0.00035994942],"domain_scores_gemma":[0.99729663,0.00018359507,0.00073889666,0.0014927613,0.00006936586,0.00021872853],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035778503,0.00014669563,0.00040642495,0.00042867567,0.0003956182,0.000059031874,0.0023478705,0.000034465233,0.0023286133],"category_scores_gemma":[0.0010321564,0.0001340327,0.00012002712,0.0011626942,0.00062010344,0.0011063481,0.0010837618,0.00018533478,0.000002753032],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035544942,0.00018729237,0.9900205,0.000095179064,0.000057231566,0.0000047897865,0.00067905884,0.00035128003,0.000029501072,0.002489087,0.0018429374,0.0038876904],"study_design_scores_gemma":[0.0003059749,0.0006792179,0.7718546,0.0000077042,0.000004828771,0.000008167231,0.00023926188,0.22202662,0.000011189387,0.0032146962,0.0014263287,0.00022144453],"about_ca_topic_score_codex":0.002463774,"about_ca_topic_score_gemma":0.00016345181,"teacher_disagreement_score":0.22167534,"about_ca_system_score_codex":0.00011002704,"about_ca_system_score_gemma":0.0005865517,"threshold_uncertainty_score":0.9985834},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1723067282531261,"score_gpt":0.3603478806697574,"score_spread":0.18804115241663133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401478708","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08158536,0.0009867051,0.88759923,0.00022521448,0.00037006545,0.00018364137,0.028533882,0.000018770312,0.00049710105],"genre_scores_gemma":[0.99438596,0.0004828293,0.0044811796,0.000020742342,0.00006119295,0.0000043270406,0.00048534223,0.0000060247826,0.00007242515],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986739,0.000006782213,0.0005225815,0.0005267447,0.0000877564,0.00018221184],"domain_scores_gemma":[0.99863017,0.00013704757,0.00036178084,0.0007183611,0.00009721198,0.0000554581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014369066,0.0000872478,0.00034361833,0.00078157906,0.000089382665,0.00009141415,0.0009134922,0.00003484923,0.000091900736],"category_scores_gemma":[0.00039732823,0.00008723118,0.0001293935,0.0019369823,0.0001951446,0.0016669024,0.0002633321,0.000050666105,0.000021189606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022560236,0.00065562746,0.78450614,0.001758325,0.0068722675,0.000008352972,0.0077411,0.051750988,0.006818397,0.04560703,0.013323749,0.08073242],"study_design_scores_gemma":[0.000086525506,0.000067620014,0.03945966,0.000031948694,0.0001756876,1.8912243e-7,0.00009967507,0.94887376,0.0023901146,0.0040422585,0.0046035037,0.00016908409],"about_ca_topic_score_codex":0.0032534602,"about_ca_topic_score_gemma":0.00032529232,"teacher_disagreement_score":0.91280055,"about_ca_system_score_codex":0.000011697169,"about_ca_system_score_gemma":0.00004955773,"threshold_uncertainty_score":0.49182802},"labels":[],"label_agreement":null}]}