{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":37,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":37,"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","author_layer_release":"2026-06-26"},"query_hash":"b4afff0fe0bd","filters":{"venue":"International Journal of Data Science and Analytics"}},"results":[{"id":"W4210299703","doi":"10.1007/s41060-021-00302-z","title":"Fake news detection based on news content and social contexts: a transformer-based approach","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":270,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Unavailability; Computer science; Exploit; Fake news; Economic shortage; Social media; Encoder; Transformer; Artificial intelligence; Machine learning; Computer security; World Wide Web; Internet privacy; Engineering","authors":[{"name":"Shaina Raza","is_ca":true},{"name":"Chen Ding","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1382122536767137,"gpt":0.3690256195116446,"spread":0.230813365834931,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002143511,0.00006907052,0.0001167094,0.0003758343,0.0007654658,0.0003623049,0.0007544495,0.00002271603,0.00006200732],"category_scores_gemma":[0.0003667338,0.00005854648,0.00003662957,0.0003319968,0.0004142373,0.001477328,0.00005433677,0.0001861867,7.22212e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001906543,"about_ca_system_score_gemma":0.0008015288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002485398,"about_ca_topic_score_gemma":0.0002050037,"domain_scores_codex":[0.9976373,0.00007025196,0.0003085533,0.0001371444,0.001691253,0.0001554893],"domain_scores_gemma":[0.9989906,0.00007514618,0.0002764025,0.00008934228,0.0004376649,0.0001308636],"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":[0.001115593,0.0009687634,0.00331207,0.00003602164,0.0001616216,0.00003664343,0.03476288,0.003945223,0.003086017,0.01965899,0.006387776,0.9265284],"study_design_scores_gemma":[0.006539668,0.001170135,0.006882081,0.00007495422,0.0001301231,0.00008834786,0.1597462,0.4524367,0.0005961716,0.0005001681,0.3712617,0.0005737023],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6890208,0.0001860603,0.1862271,0.08586822,0.002730922,0.0007780161,0.001107243,0.00005926183,0.03402242],"genre_scores_gemma":[0.9959363,0.0000497071,0.0004260537,0.00337452,0.0001465234,5.051063e-7,0.00001694818,0.000002673917,0.00004680231],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9259547,"threshold_uncertainty_score":0.5887421,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2541373928","doi":"10.1007/s41060-017-0053-2","title":"Entropy-based time-varying window width selection for nonlinear-type time–frequency analysis","year":2017,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Laser-Matter Interactions and Applications","field":"Physics and Astronomy","cited_by":59,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Spectral width; Window (computing); Dipole; Window function; Harmonics; Laser; Moment (physics); Rendering (computer graphics)","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.03444580523943833,"gpt":0.3619583317690687,"spread":0.3275125265296304,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005340498,0.00008322606,0.0001528476,0.000282736,0.0004659785,0.0006849333,0.001279946,0.00001492856,0.0001910127],"category_scores_gemma":[0.0001030017,0.00006934819,0.00008311865,0.0002685945,0.0001644,0.001716232,0.0001294998,0.00009959056,0.00001932843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004534402,"about_ca_system_score_gemma":0.0003180059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008170656,"about_ca_topic_score_gemma":0.000005460916,"domain_scores_codex":[0.9989495,0.000008309569,0.0002963374,0.0002051119,0.0004106118,0.0001301275],"domain_scores_gemma":[0.9976244,0.00006162257,0.0005445164,0.0003404121,0.001342566,0.00008650689],"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":[0.0002998636,0.002325153,0.5024601,0.00002780051,0.007792145,0.00001635654,0.0002250703,0.01445618,0.3083995,0.01308771,0.02372086,0.1271892],"study_design_scores_gemma":[0.0008347841,0.0001019318,0.006942988,0.00005013229,0.0008018273,0.00001136232,0.00003102926,0.9676428,0.006882905,0.002554078,0.01393491,0.0002112088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5722507,0.00003041431,0.406961,0.01333936,0.001069713,0.000383032,0.002762699,0.00003501252,0.003168003],"genre_scores_gemma":[0.9752458,0.000004900287,0.02360882,0.0001202586,0.0005899641,0.000001425911,0.0001840524,0.00000684949,0.0002379558],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9531867,"threshold_uncertainty_score":0.6604828,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4294084767","doi":"10.1007/s41060-022-00359-4","title":"Dbias: detecting biases and ensuring fairness in news articles","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":38,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Computer science; Python (programming language); Set (abstract data type); Extension (predicate logic); Open source; Information retrieval; Machine learning; Software; Programming language","authors":[{"name":"Shaina Raza","is_ca":true},{"name":"Deepak John Reji","is_ca":false},{"name":"Chen Ding","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2199598554541644,"gpt":0.4483360134583283,"spread":0.2283761580041639,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004838442,0.00004030372,0.00008777741,0.0002836681,0.000560033,0.0004490915,0.0008697519,0.00001584001,0.00001772812],"category_scores_gemma":[0.004754219,0.00003817739,0.00001366607,0.000425164,0.0004834511,0.002087133,0.0005298738,0.0002277308,1.846824e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001145996,"about_ca_system_score_gemma":0.0005152408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001643939,"about_ca_topic_score_gemma":0.002302342,"domain_scores_codex":[0.9983063,0.00007109878,0.0002293326,0.000125453,0.001116883,0.0001509496],"domain_scores_gemma":[0.9988517,0.0003288055,0.000179092,0.00007884903,0.0004572098,0.000104382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.000103862,0.0003628076,0.3281586,0.00001186808,0.000128972,0.0005024953,0.07728624,0.001370784,0.005421533,0.05133234,0.0007700886,0.5345504],"study_design_scores_gemma":[0.0033331,0.0006634171,0.1033906,0.0006195998,0.0001403467,0.000442265,0.6858562,0.04938977,0.001237854,0.08813731,0.06570004,0.001089553],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.987087,0.000160539,0.00007978946,0.01167185,0.0002739324,0.00002395121,0.00001878025,0.000003109696,0.0006810342],"genre_scores_gemma":[0.9983779,0.0006586176,0.0003806026,0.0003988842,0.000164514,1.865774e-7,7.940955e-7,0.000002072332,0.00001642398],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.60857,"threshold_uncertainty_score":0.5691587,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4286817176","doi":"10.1007/s41060-022-00343-y","title":"Semantic enhanced Markov model for sequential E-commerce product recommendation","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Markov chain; Stochastic matrix; Computer science; Context (archaeology); Markov model; Recommender system; Product (mathematics); Information retrieval; Data mining; Theoretical computer science; Artificial intelligence; Machine learning; Mathematics","authors":[{"name":"Mahreen Nasir","is_ca":true},{"name":"C. I. Ezeife","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08763348725034148,"gpt":0.362908129229054,"spread":0.2752746419787125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003137136,0.00007802886,0.0001354156,0.0003537929,0.0002664195,0.0003682573,0.003323146,0.00001054681,0.000009544943],"category_scores_gemma":[0.000161733,0.0000690825,0.00003844289,0.0003253738,0.00006998129,0.002879735,0.001405379,0.0001410374,3.059895e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000134245,"about_ca_system_score_gemma":0.0004068031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001346404,"about_ca_topic_score_gemma":0.000004756918,"domain_scores_codex":[0.9983062,0.00003648284,0.0004094368,0.0003039258,0.000792817,0.0001511308],"domain_scores_gemma":[0.9983556,0.00005786392,0.0004144222,0.0003573457,0.0007474295,0.00006734311],"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":[0.0000939217,0.0004453618,0.0005173179,0.00003731701,0.0002508997,0.00002342615,0.001503343,0.002114344,0.02504824,0.03124563,0.06347561,0.8752446],"study_design_scores_gemma":[0.0002834552,0.00009502756,0.00005508918,0.00001498928,0.00001313011,0.0001699198,0.00009132202,0.978408,0.001664578,0.002510914,0.01659187,0.0001017384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002800802,0.00003326123,0.9834898,0.01232795,0.0008979668,0.0001062846,0.00007860259,0.00001468337,0.0002506504],"genre_scores_gemma":[0.9058328,0.00007977527,0.09328049,0.0005340192,0.000153209,0.000004402285,0.00002380149,0.000004100676,0.00008738611],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9762936,"threshold_uncertainty_score":0.6175287,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2212891330","doi":"10.1007/s41060-018-0161-7","title":"Spectral ranking and unsupervised feature selection for point, collective, and contextual anomaly detection","year":2018,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Anomaly detection; Feature selection; Ranking (information retrieval); Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Computer science; Point (geometry); Anomaly (physics); Selection (genetic algorithm); Machine learning; Data mining; Mathematics; Physics; Linguistics","authors":[{"name":"Haofan Zhang","is_ca":true},{"name":"Ke Nian","is_ca":true},{"name":"Thomas F. Coleman","is_ca":true},{"name":"Yuying Li","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03377197851990105,"gpt":0.3192722043912278,"spread":0.2855002258713268,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008181686,0.00007703187,0.0001069089,0.0003209407,0.0003688577,0.0004636943,0.0006925369,0.00003552439,0.0000020021],"category_scores_gemma":[0.0001697432,0.00006614563,0.00001963607,0.0004629474,0.0003548201,0.002150467,0.0002423654,0.0001042358,2.51276e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007183621,"about_ca_system_score_gemma":0.0001852934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001635208,"about_ca_topic_score_gemma":0.00005325321,"domain_scores_codex":[0.999059,0.00001292721,0.0001975764,0.0002760756,0.0003334131,0.0001210624],"domain_scores_gemma":[0.9984183,0.00007029474,0.0001897928,0.0001388578,0.001098416,0.000084331],"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":[0.0003728135,0.0002131037,0.01375117,0.00002781986,0.0003124611,0.00001141652,0.001735319,0.00001525285,0.208609,0.05474149,0.004020802,0.7161893],"study_design_scores_gemma":[0.001775315,0.001497472,0.02529319,0.00007842285,0.00007850025,0.001897809,0.0004165907,0.8852018,0.05072303,0.01535224,0.01733571,0.000349915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1589325,0.00007176547,0.8386636,0.001898447,0.0001594432,0.0001051954,0.00001953324,0.00001934759,0.0001301594],"genre_scores_gemma":[0.952659,0.0001272411,0.04668503,0.0002088926,0.0002604692,0.000001633407,0.000001355666,0.000003169685,0.00005318006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8851866,"threshold_uncertainty_score":0.4471415,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411713554","doi":"10.1007/s41060-025-00856-2","title":"Toward sustainable smart cities: applications, challenges, and future directions","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Smart Cities and Technologies","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Architectural engineering; Environmental planning; Business; Geography; Engineering","authors":[{"name":"Amin Ullah","is_ca":false},{"name":"Irfan Ullah","is_ca":false},{"name":"Tariq Mahmood","is_ca":false},{"name":"Samra Nawazish","is_ca":false},{"name":"Zafar Ali","is_ca":false},{"name":"Amjad Rehman","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02942311108253774,"gpt":0.2831123824605666,"spread":0.2536892713780288,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003276089,0.0000522267,0.00008010553,0.0003514634,0.00007796747,0.0001319645,0.0006090394,0.00002718516,0.000004449989],"category_scores_gemma":[0.0000665412,0.00004456424,0.00001114456,0.0002260447,0.0002015868,0.0008047031,0.0002357451,0.0001029625,3.121543e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005744029,"about_ca_system_score_gemma":0.00009199921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006177604,"about_ca_topic_score_gemma":0.0000043701,"domain_scores_codex":[0.999424,0.00000248543,0.0001523932,0.00009585496,0.000226043,0.00009917766],"domain_scores_gemma":[0.9993703,0.00003517931,0.00003807388,0.0001490701,0.0003753715,0.00003194229],"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":[0.000007633563,0.00003433939,0.0008348323,0.0001086045,0.0002285648,0.00003777638,0.0004912202,0.00006935905,0.00008437498,0.3269563,0.005833062,0.665314],"study_design_scores_gemma":[0.0001178936,0.00001297984,0.001909984,0.00002932766,0.00002114409,0.00006837323,0.009222277,0.003872475,0.00006600359,0.006615147,0.9780055,0.00005887217],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.1279841,0.5805262,0.05875462,0.1246176,0.007494982,0.0007499836,0.0005129104,0.0006640307,0.09869545],"genre_scores_gemma":[0.7684473,0.2280265,0.002622701,0.0001740663,0.0004825697,0.000003758732,0.000008344819,0.000005849291,0.0002289515],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9721724,"threshold_uncertainty_score":0.1817277,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388304181","doi":"10.1007/s41060-023-00467-9","title":"Tackling cold-start with deep personalized transfer of user preferences for cross-domain recommendation","year":2023,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Bridge (graph theory); Cold start (automotive); Domain (mathematical analysis); Recommender system; Task (project management); Deep learning; Domain knowledge; Code (set theory); Transfer of learning; Quality (philosophy); Artificial intelligence; Machine learning; Engineering","authors":[{"name":"Sepehr Omidvar","is_ca":true},{"name":"Thomas Tran","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08551935414361735,"gpt":0.367103597124484,"spread":0.2815842429808667,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002255512,0.00007535856,0.000159184,0.0003569767,0.00009756526,0.0003747098,0.001803146,0.00002352714,0.000005869271],"category_scores_gemma":[0.00008315797,0.00005351792,0.00003392113,0.0004885642,0.0001949528,0.002777387,0.0001952129,0.0000708252,4.428927e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003509264,"about_ca_system_score_gemma":0.0002408011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001301619,"about_ca_topic_score_gemma":0.00001799756,"domain_scores_codex":[0.9985549,0.00001839593,0.0003925744,0.0002184275,0.0006785326,0.0001371487],"domain_scores_gemma":[0.9982377,0.0001101996,0.0002211872,0.0002016964,0.001163617,0.00006563099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008088915,0.0008674036,0.1362819,0.0004441098,0.001718235,0.0001368978,0.01130135,0.001006381,0.04269309,0.5168454,0.01879655,0.2690998],"study_design_scores_gemma":[0.007255695,0.002545363,0.02353417,0.001408224,0.0001552784,0.0005455073,0.003728948,0.6786541,0.03340212,0.02549145,0.2221707,0.001108462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1078916,0.00003141669,0.8895956,0.00187871,0.0002856955,0.0001003142,0.00007260539,0.00001745402,0.0001266007],"genre_scores_gemma":[0.9301793,0.0002422054,0.06931373,0.0001161424,0.00008520843,0.000002361282,0.00001866461,0.000004180969,0.00003818909],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8222877,"threshold_uncertainty_score":0.3613335,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4366003831","doi":"10.1007/s41060-023-00389-6","title":"Statistical power, accuracy, reproducibility and robustness of a graph clusterability test","year":2023,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland; University of Toronto","funders":"University of Toronto","keywords":"Statistical hypothesis testing; Statistic; Mathematics; Graph; Test statistic; Cluster analysis; Robustness (evolution); Computer science; Combinatorics; Statistics; Algorithm","authors":[{"name":"Pierre Miasnikof","is_ca":true},{"name":"Alexander Y. Shestopaloff","is_ca":true},{"name":"А. М. Райгородский","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05412285085499116,"gpt":0.381376137580153,"spread":0.3272532867251619,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003869958,0.00007263874,0.0001961027,0.0002553131,0.00006591366,0.000115777,0.0009124395,0.00001179511,0.0000408714],"category_scores_gemma":[0.001463938,0.00005840627,0.00003297489,0.0006008916,0.0005910999,0.000821996,0.0007148783,0.000121299,4.050468e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001851782,"about_ca_system_score_gemma":0.0001844418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004566166,"about_ca_topic_score_gemma":0.000006638425,"domain_scores_codex":[0.998343,0.0000274486,0.0004761671,0.0003836976,0.0006497111,0.0001199927],"domain_scores_gemma":[0.9975092,0.0005151119,0.0003310913,0.000593378,0.000964905,0.00008631509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005407488,0.0004488046,0.8934926,0.00002124716,0.0002480208,0.00001616136,0.0002035217,0.0006438497,0.00247601,0.008623743,0.006215223,0.08755672],"study_design_scores_gemma":[0.0008751815,0.0002952481,0.6101856,0.000179187,0.0002388531,0.0000593456,0.001186189,0.336679,0.001222814,0.04608247,0.002624823,0.000371234],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9522722,0.0000334111,0.04582906,0.001056964,0.0001335714,0.00005767365,0.000441808,0.000009469743,0.0001658235],"genre_scores_gemma":[0.9955401,0.0000512878,0.004234916,0.0000136035,0.0001211204,2.947799e-7,0.000029296,0.000002694199,0.000006709284],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3360352,"threshold_uncertainty_score":0.2381739,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2424687972","doi":"10.1007/s41060-016-0012-3","title":"Exact and approximate Boolean matrix decomposition with column-use condition","year":2016,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Univerzita Palackého v Olomouci","keywords":"Logical matrix; Matrix (chemical analysis); Complete Boolean algebra; Boolean function; Mathematics; Combinatorics; Discrete mathematics; Column (typography); Heuristic; Ideal (ethics); Maximum satisfiability problem; Heuristics; Boolean circuit; Algorithm; Two-element Boolean algebra; Algebra over a field; Pure mathematics; Mathematical optimization; Physics; Quantum mechanics","authors":[{"name":"Yuan Sun","is_ca":false},{"name":"Shiwei Ye","is_ca":false},{"name":"Yi Sun","is_ca":false},{"name":"Tsunehiko Kameda","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02182951033062821,"gpt":0.3398350894567677,"spread":0.3180055791261395,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008743068,0.00006800986,0.00009408638,0.0002348026,0.0001089638,0.0006498958,0.001087561,0.00001488606,0.000004243842],"category_scores_gemma":[0.0001487222,0.00004040332,0.00001145659,0.0001872847,0.0002501267,0.004932373,0.0003365715,0.00008136428,0.000001402775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003605966,"about_ca_system_score_gemma":0.0001302665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001133421,"about_ca_topic_score_gemma":0.000003424805,"domain_scores_codex":[0.9987486,0.00002213327,0.0001984017,0.0002166675,0.0006981124,0.0001161137],"domain_scores_gemma":[0.9988134,0.0001020894,0.0002452579,0.000213292,0.0005157458,0.0001102047],"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":[0.0002018958,0.0003803363,0.09349795,0.00003503725,0.0003583928,0.0006943867,0.0007502618,0.000569386,0.03075271,0.07222739,0.003654578,0.7968777],"study_design_scores_gemma":[0.002998012,0.0008974992,0.06576397,0.0006960465,0.00007949986,0.004500992,0.0001620906,0.903047,0.002194612,0.005156609,0.01399702,0.0005067137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2535025,0.00005372925,0.7414649,0.004621658,0.0001994554,0.00003349662,0.00003615284,0.00001428401,0.00007384675],"genre_scores_gemma":[0.9567117,0.0002288848,0.04271202,0.0001617384,0.0001097059,1.8112e-7,0.000004099356,0.00000287484,0.00006878142],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9024776,"threshold_uncertainty_score":0.626696,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399281748","doi":"10.1007/s41060-024-00567-0","title":"Automatic user story generation: a comprehensive systematic literature review","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Persona Design and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Systematic review; Computer science; MEDLINE; Political science","authors":[{"name":"Carlos Alberto dos Santos","is_ca":true},{"name":"Kévin Bouchard","is_ca":true},{"name":"Bianca Minetto Napoleão","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07858855502867235,"gpt":0.361042526757811,"spread":0.2824539717291386,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001397074,0.00008483297,0.0001797961,0.0003228132,0.0001018693,0.001144136,0.002651076,0.00001904681,0.0000061125],"category_scores_gemma":[0.0002342916,0.00005965167,0.00004164305,0.0008696752,0.0001247772,0.003690555,0.0003476496,0.0001722472,0.00001342373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000730657,"about_ca_system_score_gemma":0.0004451047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.649812e-7,"about_ca_topic_score_gemma":5.147364e-7,"domain_scores_codex":[0.9982346,0.00004747711,0.0003602784,0.0002475899,0.001009464,0.0001005838],"domain_scores_gemma":[0.9980706,0.0001244783,0.0001744353,0.0004330398,0.001097712,0.00009971415],"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":[0.00000423761,0.0003061513,0.00005658157,0.0360172,0.001016006,0.00205414,0.003332474,0.0000920852,0.02531839,0.3811288,0.3914966,0.1591773],"study_design_scores_gemma":[0.000107434,0.00003651497,0.00006219005,0.0325749,0.00009518296,0.002171071,0.00005904778,0.9319782,0.00006950412,0.0003644025,0.0323364,0.0001451914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002800189,0.3566393,0.5902638,0.04694586,0.002407491,0.0004377311,0.0001268706,0.00009669145,0.0002820127],"genre_scores_gemma":[0.5938241,0.2093185,0.1765543,0.01706657,0.002333886,0.00001988946,0.00009608194,0.00002870379,0.0007578978],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9318861,"threshold_uncertainty_score":0.9998928,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399483161","doi":"10.1007/s41060-024-00558-1","title":"Deep learning-based approach for COVID-19 spread prediction","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Kungliga Tekniska Högskolan; Lunds Universitet; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Autoregressive integrated moving average; Computer science; Deep learning; Autoencoder; Coronavirus disease 2019 (COVID-19); Econometrics; Artificial intelligence; Key (lock); Machine learning; Infectious disease (medical specialty); Time series; Disease; Mathematics; Computer security; Medicine","authors":[{"name":"Silvino Pedro Cumbane","is_ca":false},{"name":"Győző Gidófalvi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3625657137010542,"gpt":0.4922212792509322,"spread":0.129655565549878,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004529536,0.00008764458,0.000181231,0.0002727573,0.0001579867,0.0002157926,0.000973697,0.00003588931,0.00001425228],"category_scores_gemma":[0.02361378,0.00005996273,0.00006158466,0.0002906708,0.0003535175,0.0007201701,0.0002649608,0.0001880707,9.730262e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000228502,"about_ca_system_score_gemma":0.0004515238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001076028,"about_ca_topic_score_gemma":0.000005448938,"domain_scores_codex":[0.9983678,0.00003545691,0.0004215471,0.0002762976,0.000751823,0.0001470118],"domain_scores_gemma":[0.9968361,0.002088781,0.0002085424,0.0001566174,0.0005615231,0.0001484863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009681008,0.001792819,0.08097985,0.002404846,0.002987355,0.0004642351,0.003007237,0.2155443,0.002607749,0.2737746,0.2165759,0.1988929],"study_design_scores_gemma":[0.000268174,0.0001273099,0.0002834917,0.00005034252,0.00008997403,0.00004579258,0.0001968279,0.9180226,0.00002038644,0.02013876,0.06068501,0.00007129231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001793399,0.0004059541,0.9904011,0.006704583,0.0003079255,0.00008646295,0.0001185194,0.00002895775,0.000153097],"genre_scores_gemma":[0.9263335,0.000447989,0.07088716,0.001537787,0.0006402764,0.000003908362,0.00005218799,0.000009677257,0.00008752377],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9245401,"threshold_uncertainty_score":0.9846107,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2419390560","doi":"10.1007/s41060-016-0011-4","title":"Similarity-based probabilistic category-based location recommendation utilizing temporal and geographical influence","year":2016,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dynamic time warping; Computer science; Similarity (geometry); Probabilistic logic; Matching (statistics); Component (thermodynamics); Data mining; Information retrieval; Pattern recognition (psychology); Artificial intelligence; Mathematics; Statistics; Image (mathematics)","authors":[{"name":"Dequan Zhou","is_ca":true},{"name":"Seyyed Mohammadreza Rahimi","is_ca":true},{"name":"Xin Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06415753661921661,"gpt":0.369871203293933,"spread":0.3057136666747163,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004786806,0.00008718051,0.0001377166,0.000489731,0.0004200997,0.000330212,0.0009067236,0.00005207121,0.00005252802],"category_scores_gemma":[0.003001741,0.00006452123,0.00003165006,0.0006980058,0.001656623,0.001923375,0.00009343593,0.0001196738,0.000001755983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001662246,"about_ca_system_score_gemma":0.001661233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008208881,"about_ca_topic_score_gemma":0.001561295,"domain_scores_codex":[0.9979626,0.000123231,0.0004317749,0.0002923151,0.001013488,0.0001765794],"domain_scores_gemma":[0.9965067,0.0004317324,0.0003505963,0.000214002,0.002309002,0.0001879624],"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":[0.0002423986,0.0007943946,0.536534,0.00008789447,0.0002045782,0.00002744045,0.001586307,0.003212649,0.002624674,0.03607256,0.0009131837,0.4177],"study_design_scores_gemma":[0.00600454,0.0008168072,0.2213021,0.001566278,0.0008146503,0.00003912255,0.007833702,0.5753283,0.001223599,0.03307183,0.1503913,0.001607763],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7119695,0.0001201385,0.1915588,0.09500986,0.0004217358,0.0002781379,0.0001658179,0.00004010132,0.0004359295],"genre_scores_gemma":[0.9977275,0.00009027234,0.001407357,0.0005893914,0.000147086,0.000001093693,0.00002499468,0.000003214432,0.000009153716],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5721156,"threshold_uncertainty_score":0.6103895,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3176378653","doi":"10.1007/s41060-021-00256-2","title":"Biased resampling strategies for imbalanced spatio-temporal forecasting","year":2021,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Resampling; Computer science; Relevance (law); Set (abstract data type); Machine learning; Sampling (signal processing); Data mining; Artificial intelligence","authors":[{"name":"Mariana Oliveira","is_ca":false},{"name":"Nuno Moniz","is_ca":false},{"name":"Luı́s Torgo","is_ca":true},{"name":"Vı́tor Santos Costa","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1650942241800284,"gpt":0.3802273601920618,"spread":0.2151331360120333,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001650562,0.00007778443,0.0001395321,0.0002581402,0.0001332268,0.001061767,0.002842216,0.00002488462,0.000003165519],"category_scores_gemma":[0.001370822,0.0000689747,0.00003019238,0.0004916397,0.0001663551,0.005578002,0.0006216498,0.0001040612,4.974691e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006990581,"about_ca_system_score_gemma":0.001329964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006099111,"about_ca_topic_score_gemma":0.00001364882,"domain_scores_codex":[0.9982839,0.00001675596,0.000425506,0.0003033975,0.0008088168,0.0001616847],"domain_scores_gemma":[0.9961807,0.000181934,0.0004403588,0.0004802408,0.002635545,0.00008128054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001059401,0.0003321528,0.009123576,0.0000686392,0.000245157,0.0003325022,0.0008456529,0.0009987568,0.06140479,0.6227474,0.01453423,0.2892612],"study_design_scores_gemma":[0.0006972843,0.0001056386,0.00169026,0.0001738578,0.00002138369,0.0004401463,0.0006401135,0.9134382,0.01352726,0.0472549,0.02178048,0.0002304953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004744981,0.00005346779,0.991873,0.002640508,0.0003612337,0.00004176874,0.0001168831,0.00001938852,0.0001487135],"genre_scores_gemma":[0.5396745,0.00006519698,0.4597986,0.0002656903,0.0001140965,7.942325e-7,0.00006586199,0.000002891362,0.00001236561],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9124394,"threshold_uncertainty_score":0.9999752,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2767552437","doi":"10.1007/s41060-017-0079-5","title":"Discovering co-location patterns with aggregated spatial transactions and dependency rules","year":2017,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"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; Canadian Institutes of Health Research","keywords":"Association rule learning; Computer science; Data mining; Dependency (UML); Database transaction; Contrast (vision); Spatial analysis; Common spatial pattern; Spatial ecology; Artificial intelligence; Statistics; Mathematics","authors":[{"name":"Mohomed Shazan Mohomed Jabbar","is_ca":true},{"name":"Colin Bellinger","is_ca":true},{"name":"Osmar R. Zai͏̈ane","is_ca":true},{"name":"Álvaro Osornio-Vargas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04159857979522947,"gpt":0.3375766672262661,"spread":0.2959780874310367,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005124322,0.00006711558,0.00008582325,0.0001486122,0.000403188,0.001501568,0.00262541,0.00001489248,0.00000273707],"category_scores_gemma":[0.00009626222,0.00005044471,0.000009515407,0.00008571192,0.0002807338,0.00578009,0.0002478261,0.00009930476,0.000001088285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002543804,"about_ca_system_score_gemma":0.0002407012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002159625,"about_ca_topic_score_gemma":0.0001227683,"domain_scores_codex":[0.9988567,0.000006305784,0.0001922564,0.0002288781,0.0006142946,0.0001016273],"domain_scores_gemma":[0.9986041,0.00003060927,0.0003289706,0.0005061144,0.0004343633,0.00009590817],"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":[0.00001286693,0.000101335,0.01484475,0.000008954562,0.00009098656,0.00005715596,0.0005197781,0.0001232755,0.0007316926,0.004160285,0.00004417479,0.9793047],"study_design_scores_gemma":[0.0009392012,0.0001744783,0.1357998,0.0003147508,0.0000655547,0.0009374031,0.000404034,0.8568245,0.001436118,0.0009534326,0.001871109,0.0002795861],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1206986,0.00002915414,0.8770397,0.001851383,0.0001271691,0.00002681381,0.0001445879,0.000005585465,0.00007694092],"genre_scores_gemma":[0.9684333,0.0003188883,0.03109491,0.00004241846,0.00008107307,5.254981e-7,0.0000128046,0.000002475016,0.00001366789],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9790252,"threshold_uncertainty_score":0.999535,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405127663","doi":"10.1007/s41060-024-00693-9","title":"AI-generated or AI touch-up? Identifying AI contribution in text data","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Data science","authors":[{"name":"Ahmad Hashemi","is_ca":true},{"name":"Wei Shi","is_ca":true},{"name":"Jean‐Pierre Corriveau","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1328814845314103,"gpt":0.4163926192477443,"spread":0.283511134716334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002457926,0.00008843244,0.0001407652,0.000586313,0.00008115689,0.001960539,0.00537567,0.00003217892,0.00001620163],"category_scores_gemma":[0.0007696345,0.00006657324,0.00001844594,0.0009105675,0.0001231802,0.01058305,0.001964043,0.0003027001,0.000007035448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001378837,"about_ca_system_score_gemma":0.001077169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005273513,"about_ca_topic_score_gemma":0.00009221342,"domain_scores_codex":[0.9976621,0.00002925122,0.0005110237,0.0004502166,0.00115148,0.0001959815],"domain_scores_gemma":[0.9981402,0.00009069626,0.0001319104,0.0006504382,0.0008866827,0.0001000395],"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":[0.0001290393,0.000329383,0.00792354,0.00009015176,0.0004779492,0.00369309,0.00175369,0.007831796,0.02882719,0.1875456,0.06692675,0.6944718],"study_design_scores_gemma":[0.0002399028,0.00002397339,0.00024207,0.000194893,0.00001295298,0.0002847341,0.00004188548,0.9852044,0.0004505363,0.002179276,0.01103944,0.0000859136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01205629,0.0004814158,0.9612123,0.02372802,0.002307516,0.00004391217,0.000119657,0.00001793004,0.00003293567],"genre_scores_gemma":[0.9901226,0.0003641199,0.007090835,0.001942814,0.0003550848,2.177152e-7,0.00004356187,0.000003561781,0.00007724706],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9780663,"threshold_uncertainty_score":0.9990755,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4382794929","doi":"10.1007/s41060-023-00422-8","title":"Cluster weighted model based on TSNE algorithm for high-dimensional data","year":2023,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster (spacecraft); Computer science; Algorithm; Data mining","authors":[{"name":"Kehinde Olobatuyi","is_ca":true},{"name":"Matthew R. P. Parker","is_ca":true},{"name":"Oludare Ariyo","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08185738340875104,"gpt":0.3724881720827192,"spread":0.2906307886739682,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.003839335,0.0001100716,0.0001686965,0.0005616972,0.0001392087,0.0003689481,0.005860405,0.00003676356,0.000002922641],"category_scores_gemma":[0.0003456966,0.00008211021,0.00003132134,0.0005976085,0.0001611984,0.002802604,0.001540749,0.0001444625,0.000003700518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004339138,"about_ca_system_score_gemma":0.0006767726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000420053,"about_ca_topic_score_gemma":0.000001584926,"domain_scores_codex":[0.9975087,0.00002921008,0.0003639176,0.0004782914,0.001399924,0.0002199478],"domain_scores_gemma":[0.9974326,0.0002874603,0.0002386227,0.0009251062,0.0009633036,0.0001528836],"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":[0.00003677659,0.0001321379,0.00001669569,0.00000580587,0.00007049762,0.00006212903,0.00005836314,0.005220727,0.0005260946,0.03223272,0.03452467,0.9271134],"study_design_scores_gemma":[0.0005849409,0.00007195515,0.00005121017,0.0000418016,0.00001756698,0.00003082314,0.000003851295,0.9752182,0.000169787,0.02242375,0.001287626,0.00009847228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004751802,0.00001817526,0.9889569,0.009227345,0.0006667166,0.0000591531,0.0005264778,0.00001553597,0.00005449947],"genre_scores_gemma":[0.03424178,0.00004858513,0.9630077,0.002200768,0.0002790581,6.558564e-7,0.0001314818,0.000006267538,0.00008370639],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9699975,"threshold_uncertainty_score":0.9995184,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4383645786","doi":"10.1007/s41060-023-00409-5","title":"Applications of the discrete-time Fourier transform to data analysis","year":2023,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Scientific Research and Discoveries","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Probability mass function; Probability-generating function; Random variable; Characteristic function (probability theory); Fourier transform; Discrete-time stochastic process; Discrete Fourier transform (general); Mathematics; Random function; Discrete-time Fourier transform; Function (biology); Applied mathematics; Variable (mathematics); Discrete time and continuous time; Fourier analysis; Probability density function; Algorithm; Stochastic process; Mathematical analysis; Fractional Fourier transform; Statistics; Continuous-time stochastic process","authors":[{"name":"Dayne Sorvisto","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05059634054103507,"gpt":0.391844785633456,"spread":0.3412484450924209,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001479371,0.00004401854,0.0001026773,0.0003707338,0.0001141972,0.0002242927,0.00364153,0.000006043323,0.0001034157],"category_scores_gemma":[0.0001175529,0.00002686419,0.00004648984,0.002220643,0.0003255701,0.001277004,0.0009480502,0.00006263979,0.000009105075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001091632,"about_ca_system_score_gemma":0.0003306675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005096008,"about_ca_topic_score_gemma":0.00001468853,"domain_scores_codex":[0.9983279,0.00001025092,0.0002419966,0.000182815,0.001118,0.0001189965],"domain_scores_gemma":[0.9985587,0.00006205138,0.0001313729,0.0006696894,0.0004765741,0.0001016076],"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":[0.0001353436,0.0004902402,0.1910058,0.00002217922,0.004340836,0.00001253787,0.001723232,0.003942534,0.01353086,0.030973,0.1327139,0.6211095],"study_design_scores_gemma":[0.0008529476,0.00009538094,0.04588292,0.00009115585,0.0009795587,0.000009355646,0.005208021,0.7212819,0.004873785,0.02105261,0.1993009,0.0003715115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2795372,0.0001045592,0.6390911,0.04069035,0.0008598106,0.0006291659,0.02333411,0.00001787889,0.01573584],"genre_scores_gemma":[0.9977549,0.00001695202,0.001354674,0.00003961364,0.0001461369,8.200311e-7,0.0001739167,0.000002021994,0.0005109829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7182177,"threshold_uncertainty_score":0.676693,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4206899722","doi":"10.1007/s41060-021-00296-8","title":"The validation of chest tube management after lung resection surgery using a random forest classifier","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital; University of Ottawa; Dalhousie University","funders":"Department of Medicine, Ottawa Hospital; Ontario Medical Association; Ontario Ministry of Health and Long-Term Care","keywords":"Random forest; Classifier (UML); Lung; Medicine; Chest tube; Resection; Radiology; Computer science; Surgery; Artificial intelligence; Internal medicine","authors":[{"name":"William Klement","is_ca":true},{"name":"Sébastien Gilbert","is_ca":true},{"name":"Virginia Ferreira Resende","is_ca":true},{"name":"Donna E. Maziak","is_ca":true},{"name":"Andrew Seely","is_ca":true},{"name":"Farid M. Shamji","is_ca":true},{"name":"Sudhir Sundaresan","is_ca":true},{"name":"Patrick J. Villeneuve","is_ca":true},{"name":"Nathalie Japkowicz","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06469924393754112,"gpt":0.3353173416258536,"spread":0.2706180976883125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004385635,0.00006161583,0.0001075256,0.0004477857,0.0002783116,0.0003447919,0.002584406,0.00001192542,0.000005350845],"category_scores_gemma":[0.0002764622,0.00004633648,0.00003685725,0.0006886004,0.000226083,0.002597259,0.00133667,0.0001342291,2.33647e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001787525,"about_ca_system_score_gemma":0.000261765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009001536,"about_ca_topic_score_gemma":0.000003214176,"domain_scores_codex":[0.9976914,0.00007025553,0.0004712612,0.0002041662,0.001440519,0.0001224236],"domain_scores_gemma":[0.9980155,0.0002058629,0.0005463561,0.0005048538,0.0006847146,0.00004267342],"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":[0.002615894,0.001501239,0.2198666,0.0002519252,0.001694323,0.0006440362,0.002229173,0.01190244,0.03465063,0.176042,0.05904172,0.4895601],"study_design_scores_gemma":[0.0007703405,0.00008666329,0.02565075,0.000123039,0.00007182959,0.0004006737,0.0005152845,0.9340694,0.005826499,0.004627405,0.0276407,0.0002174426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07681984,0.0001872887,0.9178229,0.003625313,0.001131881,0.0001353314,0.00009518071,0.00001482015,0.0001674427],"genre_scores_gemma":[0.9859686,0.0003388344,0.01348836,0.0000921491,0.00006797112,0.000003387521,0.00001418819,0.000003028336,0.00002341983],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9221669,"threshold_uncertainty_score":0.4802513,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3212301104","doi":"10.1007/s41060-021-00294-w","title":"Personalized multi-faceted trust modeling to determine trust links in social media and its potential for misinformation management","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Access Control and Trust","field":"Social Sciences","cited_by":4,"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":"Misinformation; Computer science; Social media; Popularity; Context (archaeology); Set (abstract data type); Cluster analysis; Data science; Internet privacy; Recommender system; World Wide Web; Computer security; Artificial intelligence; Psychology","authors":[{"name":"Alexandre Parmentier","is_ca":true},{"name":"Robin Cohen","is_ca":true},{"name":"Xueguang Ma","is_ca":true},{"name":"Gaurav Sahu","is_ca":true},{"name":"Queenie Chen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09913148508559601,"gpt":0.3803917413536482,"spread":0.2812602562680522,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002228623,0.00006421145,0.0001292911,0.0004492975,0.0005860121,0.0002772468,0.0009800592,0.00002854465,0.00003145497],"category_scores_gemma":[0.0004111984,0.00006054483,0.00002818608,0.0003359461,0.0001246405,0.001638483,0.000406464,0.0001509086,4.682271e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001422327,"about_ca_system_score_gemma":0.0002012138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003673507,"about_ca_topic_score_gemma":0.00009752274,"domain_scores_codex":[0.9982013,0.00002975246,0.0003415216,0.0001579911,0.001093952,0.000175468],"domain_scores_gemma":[0.9991227,0.0000504295,0.0001863717,0.0000555806,0.0004823703,0.0001025363],"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":[0.002621019,0.001016974,0.005819055,0.0001110135,0.0006915441,0.0003920297,0.1032558,0.05156044,0.002300816,0.1428805,0.002641928,0.6867089],"study_design_scores_gemma":[0.00183977,0.00003320949,0.001104797,0.00001685247,0.00004309816,0.00001353126,0.01154622,0.9794602,0.00000559111,0.0006394871,0.005193384,0.0001038188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9280087,0.0002642911,0.05031428,0.01851699,0.001342496,0.0004640995,0.0005436868,0.00001292285,0.0005324882],"genre_scores_gemma":[0.9962676,0.0001468692,0.00289013,0.0003226579,0.000272923,0.000003296744,0.0000210279,0.000003078377,0.00007243489],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9278998,"threshold_uncertainty_score":0.4507191,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389455239","doi":"10.1007/s41060-023-00464-y","title":"Enhancing e-commerce recommendations with a novel scale-aware spectral graph wavelets framework","year":2023,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Wavelet; Embedding; Graph; Smoothing; Collaborative filtering; Eigenvalues and eigenvectors; Scale (ratio); Recommender system; Artificial intelligence; Machine learning; Theoretical computer science; Data mining; Computer vision","authors":[{"name":"Osama Alshareet","is_ca":true},{"name":"Anjali Awasthi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06010432902480681,"gpt":0.3485235941154597,"spread":0.2884192650906529,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001833111,0.0001085377,0.0001749935,0.0006963122,0.0001872051,0.0006634089,0.00334531,0.00003404489,0.000005773813],"category_scores_gemma":[0.0001525505,0.00008072901,0.00003533926,0.001367675,0.0001611085,0.003354137,0.0007848194,0.0002469578,0.000003274628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006534794,"about_ca_system_score_gemma":0.0002945628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003155361,"about_ca_topic_score_gemma":0.00004634588,"domain_scores_codex":[0.998007,0.00001926794,0.000415198,0.0003112801,0.0010174,0.0002298371],"domain_scores_gemma":[0.9981276,0.0001596708,0.0003328717,0.0004852297,0.0007527025,0.0001418904],"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":[0.0001323546,0.0009598559,0.03815224,0.0001046853,0.001196404,0.000851586,0.008993173,0.0004903002,0.02298912,0.360591,0.06214184,0.5033975],"study_design_scores_gemma":[0.004141048,0.002347104,0.06854971,0.005638433,0.0002405554,0.009067506,0.005812185,0.6464441,0.03049863,0.09466843,0.1298996,0.002692663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01280191,0.00002033656,0.9693669,0.01688018,0.0005910033,0.00005048939,0.00005443476,0.00004970649,0.0001850196],"genre_scores_gemma":[0.737325,0.0003432253,0.2614559,0.0005862783,0.0002323516,0.000001088626,0.00001348669,0.000006883326,0.00003586894],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.724523,"threshold_uncertainty_score":0.6397267,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2754529182","doi":"10.1007/s41060-017-0072-z","title":"Visual analytics of high-frequency lake monitoring data","year":2017,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ministry of the Environment, Conservation and Parks; University of Saskatchewan; Nipissing University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canada Foundation for Innovation","keywords":"Visual analytics; Analytics; Data science; Computer science; Remote sensing; Visualization; Geography; Data mining","authors":[{"name":"Mark P. Wachowiak","is_ca":true},{"name":"April L. James","is_ca":true},{"name":"Renata Wachowiak-Smolíková","is_ca":true},{"name":"Dan Walters","is_ca":true},{"name":"Krystopher J. Chutko","is_ca":true},{"name":"James A. Rusak","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1201980088890202,"gpt":0.4235599393987042,"spread":0.303361930509684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.002588758,0.000129037,0.0002671003,0.0004852097,0.0002923499,0.001487711,0.01806101,0.00003894287,0.00001151492],"category_scores_gemma":[0.002245907,0.0001089289,0.00003406319,0.0003886538,0.0006391804,0.01140904,0.005481088,0.0001708855,0.000003674725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004061135,"about_ca_system_score_gemma":0.0007149347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005535097,"about_ca_topic_score_gemma":0.00004363926,"domain_scores_codex":[0.9967439,0.00002291978,0.0006887252,0.0004348735,0.001898356,0.0002111907],"domain_scores_gemma":[0.994212,0.00008604674,0.001237195,0.002300279,0.001971869,0.0001925653],"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":[0.0000672504,0.001437474,0.3335275,0.0001072827,0.001409645,0.0008468797,0.0007100698,0.0007183083,0.0108746,0.2679347,0.009920569,0.3724457],"study_design_scores_gemma":[0.001689425,0.0002518031,0.0708575,0.0004844577,0.0002332364,0.0003296788,0.0003333885,0.9024308,0.00334313,0.006408236,0.01305937,0.00057893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09437887,0.0003429318,0.8887761,0.0082365,0.005060019,0.0001195167,0.001718379,0.00003654274,0.001331186],"genre_scores_gemma":[0.9606281,0.0008863022,0.03785054,0.0001035208,0.0004179081,7.05965e-8,0.00006424281,0.000005602044,0.00004369256],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9017125,"threshold_uncertainty_score":0.9995489,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399799131","doi":"10.1007/s41060-024-00580-3","title":"Implicitly adaptive optimal proposal in variational inference for Bayesian learning","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Inference; Bayesian inference; Bayesian probability; Computer science; Machine learning; Artificial intelligence","authors":[{"name":"Mostafa Bakhouya","is_ca":false},{"name":"Hassan Ramchoun","is_ca":false},{"name":"Mohammed Hadda","is_ca":false},{"name":"Tawfik Masrour","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03728472567215683,"gpt":0.3491551834299391,"spread":0.3118704577577822,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001553628,0.00009391477,0.0001300068,0.0005476767,0.00008729446,0.001065545,0.002512532,0.00003079258,0.000006512694],"category_scores_gemma":[0.0005762473,0.00007446546,0.00002933446,0.0006854925,0.0001581905,0.004948841,0.0005289675,0.000233522,0.000001996786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009033743,"about_ca_system_score_gemma":0.001917492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001022036,"about_ca_topic_score_gemma":0.00000845814,"domain_scores_codex":[0.9982666,0.00001630313,0.0003812542,0.0003392201,0.0008007734,0.0001958162],"domain_scores_gemma":[0.9984753,0.0002261404,0.0001641337,0.0001683054,0.0008701469,0.00009595374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003148948,0.00007391284,0.001908695,0.00002744202,0.00006701115,0.0001301362,0.0007065898,0.002351837,0.0008142507,0.8463666,0.0003080408,0.147214],"study_design_scores_gemma":[0.0001942264,0.0001618269,0.001684711,0.0001528006,0.000009394729,0.0001578731,0.00009244921,0.9732369,0.0001070079,0.0224605,0.00163922,0.0001030973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001670116,0.0001403949,0.9933643,0.004119809,0.0003933649,0.00005360111,0.00003036286,0.00001241964,0.0002156178],"genre_scores_gemma":[0.8336244,0.00009990035,0.1659929,0.00009176401,0.0001612754,0.000001160636,0.000005015157,0.000003321618,0.00002028799],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.970885,"threshold_uncertainty_score":0.9999714,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4205284473","doi":"10.1007/s41060-021-00304-x","title":"Knowledgebase approximation using association rule aggregation","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":2,"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":"Association rule learning; Pooling; Computer science; Set (abstract data type); Data mining; Knowledge extraction; Association (psychology); Artificial intelligence","authors":[{"name":"Pouya Mehrannia","is_ca":true},{"name":"Behzad Moshiri","is_ca":true},{"name":"Otman Basir","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06659777893143116,"gpt":0.3312128219549486,"spread":0.2646150430235174,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002954429,0.00005277718,0.00008510775,0.0003456527,0.0002860051,0.0004132168,0.002288772,0.00001319256,0.00001196432],"category_scores_gemma":[0.0004407142,0.00004672721,0.00002245033,0.0006033251,0.00005254254,0.003517236,0.001078229,0.0001395511,0.000001538885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004096956,"about_ca_system_score_gemma":0.0004289908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001058734,"about_ca_topic_score_gemma":0.00000124944,"domain_scores_codex":[0.9978796,0.00004315782,0.0002899319,0.0001835934,0.001486511,0.0001172259],"domain_scores_gemma":[0.9982864,0.00006079673,0.0005201632,0.0002280801,0.0008443679,0.00006020077],"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":[0.00005892367,0.000859945,0.02931056,0.00001936711,0.0002994846,0.0002118632,0.00286049,0.02093817,0.01074167,0.06869116,0.009409418,0.856599],"study_design_scores_gemma":[0.0002646486,0.00005211691,0.0009796575,0.0000105993,0.00001477509,0.000152978,0.0001501263,0.9870358,0.0001790322,0.003950051,0.007133523,0.000076752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2527859,0.0004504388,0.7325172,0.008302239,0.003814348,0.0001299741,0.000128049,0.00003110443,0.00184071],"genre_scores_gemma":[0.9341813,0.00007879467,0.06513415,0.0003423949,0.0002186501,4.196565e-7,0.00001415813,0.000002602524,0.00002755816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9660976,"threshold_uncertainty_score":0.4253145,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396953092","doi":"10.1007/s41060-024-00552-7","title":"Feature extraction for exoplanet detection","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Stellar, planetary, and galactic studies","field":"Physics and Astronomy","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Vector Institute; Dalhousie University","funders":"","keywords":"Exoplanet; Computer science; Feature (linguistics); Extraction (chemistry); Feature extraction; Artificial intelligence; Computer vision; Chromatography; Chemistry; Stars","authors":[{"name":"João Pimentel","is_ca":true},{"name":"Joana Amorim","is_ca":true},{"name":"Frank Rudzicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03634748418262827,"gpt":0.3383414768702387,"spread":0.3019939926876105,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004708635,0.00005348429,0.00007197946,0.0001521707,0.00008075248,0.0002544311,0.0003285279,0.00001268834,0.00001857852],"category_scores_gemma":[0.00005124666,0.00004030374,0.00002449737,0.0001177364,0.00007983726,0.0009838664,0.00005309037,0.00009905367,0.0000025596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002030045,"about_ca_system_score_gemma":0.0001051412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001447684,"about_ca_topic_score_gemma":0.000005130692,"domain_scores_codex":[0.9993195,0.000004253931,0.0001193827,0.0001284937,0.0003482201,0.00008012612],"domain_scores_gemma":[0.9993635,0.0001286158,0.00008342963,0.00007906301,0.000304965,0.00004044014],"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":[0.0001108404,0.00008489469,0.17047,0.00003479453,0.0008104728,0.00004735285,0.0003532621,0.0001513419,0.002850984,0.004329307,0.03949549,0.7812613],"study_design_scores_gemma":[0.0008544859,0.0002686176,0.07155485,0.0002234146,0.0004672464,0.0005711533,0.001108616,0.1526305,0.00327536,0.005807361,0.7628958,0.0003426297],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.248306,0.008391714,0.643953,0.02826371,0.02976282,0.0006085944,0.001951743,0.00007996245,0.03868249],"genre_scores_gemma":[0.9973882,0.0001351862,0.001006422,0.00003973346,0.001236715,3.000323e-7,0.00004509967,0.000002691661,0.0001456812],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7809187,"threshold_uncertainty_score":0.2453485,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401900459","doi":"10.1007/s41060-024-00624-8","title":"A nearest neighbor-based approach for improving the reliability of multiclass probabilistic classifiers","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"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","keywords":"Probabilistic logic; Probabilistic classification; k-nearest neighbors algorithm; Reliability (semiconductor); Artificial intelligence; Computer science; Benchmark (surveying); Multiclass classification; Machine learning; Multivariate statistics; Class (philosophy); Pattern recognition (psychology); Support vector machine; Data mining; Naive Bayes classifier","authors":[{"name":"Hyukjun Gweon","is_ca":true},{"name":"Jiaxuan Lu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05976447993703259,"gpt":0.3409420003058778,"spread":0.2811775203688452,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00366928,0.0000716389,0.0001071359,0.0002076174,0.0001091834,0.0006113321,0.003030501,0.00002348657,0.000001089302],"category_scores_gemma":[0.002753324,0.00004324158,0.00004235343,0.0004799801,0.0004481551,0.001735257,0.0003511246,0.0001793932,3.790369e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007124379,"about_ca_system_score_gemma":0.000858118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002438153,"about_ca_topic_score_gemma":0.000002444588,"domain_scores_codex":[0.9983611,0.00003813604,0.0003755935,0.0003103542,0.0007933027,0.0001215104],"domain_scores_gemma":[0.9976903,0.0004831797,0.0002543633,0.0005447681,0.0009614111,0.00006602827],"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":[0.0001589841,0.0006567154,0.007396546,0.000651634,0.0001769226,0.00002639642,0.001306347,0.04273214,0.01688494,0.2491875,0.003157773,0.6776641],"study_design_scores_gemma":[0.0001539189,0.00006578201,0.001281296,0.00003554012,0.00002452341,0.00001994086,0.00008165255,0.9938179,0.0001304901,0.0006849658,0.00365354,0.00005048317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005766807,0.0001086369,0.9880603,0.005395249,0.0003652295,0.00009804415,0.00008280197,0.00001256817,0.000110368],"genre_scores_gemma":[0.914734,0.00001536292,0.08501385,0.00009924276,0.0001020955,0.000001496812,0.00001895978,0.000002977125,0.00001203093],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9510857,"threshold_uncertainty_score":0.589509,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387403737","doi":"10.1007/s41060-023-00465-x","title":"Theoretical and practical data science and analytics: challenges and solutions","year":2023,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":1,"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":"Big data; Data science; Cloud computing; Analytics; Computer science; Data analysis; Business intelligence; The Internet; Focus (optics); Knowledge management; World Wide Web; Data mining","authors":[{"name":"Carson K. Leung","is_ca":true},{"name":"Gabriella Pasi","is_ca":false},{"name":"Li Wang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3191882207103572,"gpt":0.4219101829844512,"spread":0.102721962274094,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005424612,0.0001205274,0.0001710823,0.0008017202,0.0003752279,0.001415003,0.001630574,0.00003631356,0.00002539932],"category_scores_gemma":[0.005080902,0.00009213175,0.000009380713,0.0009268844,0.003941243,0.01271949,0.004993259,0.0001921754,0.000008296313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002293207,"about_ca_system_score_gemma":0.0003086271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002652632,"about_ca_topic_score_gemma":0.00002969003,"domain_scores_codex":[0.9974537,0.000007745575,0.0003317515,0.0005136828,0.001408462,0.0002846282],"domain_scores_gemma":[0.9975371,0.0001872245,0.0002413675,0.0004778081,0.001477329,0.00007914899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004870268,0.0001085008,0.003671026,0.00007466173,0.00008397916,0.0001588572,0.000112954,0.000007550621,0.0009005658,0.8339181,0.005106027,0.1558091],"study_design_scores_gemma":[0.0005870019,0.00005294261,0.04549097,0.0002892972,0.0003047831,0.00100209,0.002539941,0.8197637,0.00004234971,0.038215,0.09128378,0.000428208],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5969964,0.009123111,0.01362766,0.3599603,0.004238997,0.0005688345,0.001139311,0.000170848,0.01417458],"genre_scores_gemma":[0.9835437,0.0141153,0.001118553,0.0006497852,0.0005199765,2.748211e-7,0.00003672258,0.000006137217,0.000009559733],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8197561,"threshold_uncertainty_score":0.9996216,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408166864","doi":"10.1007/s41060-025-00737-8","title":"Enhanced anomaly detection through a Bayesian framework with a novel network merging structure learning approach","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"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; Research Manitoba","keywords":"Anomaly detection; Bayesian network; Anomaly (physics); Computer science; Artificial intelligence; Bayesian probability; Machine learning; Physics","authors":[{"name":"Ashani Wickramasinghe","is_ca":true},{"name":"Saman Muthukumarana","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02783018688427642,"gpt":0.3090371544783123,"spread":0.2812069675940359,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008074862,0.0001145703,0.0001626882,0.0002270328,0.0002325827,0.0006841927,0.002488231,0.00004992187,0.000002048241],"category_scores_gemma":[0.0002700914,0.00008670562,0.00002389696,0.001134096,0.0002063735,0.002808435,0.0005196418,0.0004359631,2.197302e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006444445,"about_ca_system_score_gemma":0.0004737079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001563613,"about_ca_topic_score_gemma":0.000009755759,"domain_scores_codex":[0.9982889,0.00002316182,0.0003072849,0.0003608094,0.0008055153,0.00021433],"domain_scores_gemma":[0.9983767,0.00008268917,0.0002962502,0.0003251291,0.0008473003,0.00007197387],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002126267,0.0003006881,0.004164698,0.00005354077,0.0007684881,0.00007196117,0.003505856,0.3320589,0.03889861,0.3633652,0.000411586,0.2561878],"study_design_scores_gemma":[0.0003176071,0.00009859866,0.0005158194,0.0002797959,0.00003499729,0.0001580957,0.0001881534,0.9840598,0.001669391,0.01177981,0.0007480165,0.0001499846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009411202,0.0001089618,0.9888303,0.0006898997,0.0004215653,0.00002961688,0.000005328699,0.00001556527,0.0004875631],"genre_scores_gemma":[0.730105,0.00006536747,0.2693959,0.000276658,0.0001330354,2.021606e-7,0.000001809844,0.000002471018,0.00001956264],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7206938,"threshold_uncertainty_score":0.6597686,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410728601","doi":"10.1007/s41060-025-00799-8","title":"A data-driven approach for predicting crime occurrence using machine learning models","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Crime Patterns and Interventions","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence","authors":[{"name":"Faisal Tareque Shohan","is_ca":true},{"name":"Abu Ubaida Akash","is_ca":true},{"name":"Muhammad Ibrahim","is_ca":false},{"name":"Mohammad Shafiul Alam","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3388764596217803,"gpt":0.4783996502889309,"spread":0.1395231906671506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002903221,0.00006234704,0.0001218218,0.0003179208,0.0004871565,0.000455816,0.002616234,0.0000246188,0.00001625473],"category_scores_gemma":[0.001298008,0.00005508192,0.00003761023,0.0003316448,0.0003913524,0.003258864,0.0007925255,0.0001626505,1.999495e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009012336,"about_ca_system_score_gemma":0.0006469128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004197486,"about_ca_topic_score_gemma":0.0001125207,"domain_scores_codex":[0.9984983,0.00003793562,0.0003502526,0.0002489559,0.0006985058,0.000166055],"domain_scores_gemma":[0.9982739,0.000111247,0.000278743,0.0002327826,0.001025728,0.0000775763],"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":[0.0004727865,0.002913767,0.3160058,0.0004083999,0.002828607,0.00008194404,0.0170816,0.1416015,0.006759717,0.2008257,0.04182116,0.269199],"study_design_scores_gemma":[0.0001966973,0.00002171739,0.0001428115,0.0001028821,0.00007024498,0.000008386055,0.001757178,0.98682,0.00001416979,0.000540175,0.01026997,0.00005580455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04132342,0.0005160219,0.9500831,0.001405795,0.0008882392,0.0001470894,0.002042722,0.00001450108,0.003579054],"genre_scores_gemma":[0.9728684,0.0003036898,0.02618156,0.0001174217,0.0002624271,4.615467e-7,0.0001427345,0.000002659018,0.000120667],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.931545,"threshold_uncertainty_score":0.4861657,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406609300","doi":"10.1007/s41060-025-00717-y","title":"Supervised graph embedding for classification using discriminating frequent patterns","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"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 Dhaka; University Grants Commission of Bangladesh; University of Manitoba","keywords":"Pattern recognition (psychology); Artificial intelligence; Embedding; Computer science; Graph; Machine learning; Theoretical computer science","authors":[{"name":"Md. Tanvir Alam","is_ca":false},{"name":"Chowdhury Farhan Ahmed","is_ca":false},{"name":"Md. Samiullah","is_ca":false},{"name":"Carson K. Leung","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1214151811224538,"gpt":0.4118745984518881,"spread":0.2904594173294343,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000997276,0.00008011644,0.0001161471,0.0005171829,0.0001786247,0.0004455252,0.002837175,0.00002134329,7.092131e-7],"category_scores_gemma":[0.0002830932,0.00006718653,0.00004033469,0.000584332,0.0001446849,0.003731158,0.0005666717,0.0001129279,8.799462e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008535914,"about_ca_system_score_gemma":0.0001977528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004841449,"about_ca_topic_score_gemma":0.000003121501,"domain_scores_codex":[0.9985591,0.00001559265,0.0003793727,0.0002801639,0.0006013841,0.0001644189],"domain_scores_gemma":[0.9981257,0.000154653,0.0002916209,0.0003252983,0.001036908,0.00006583959],"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":[0.00004572167,0.0002044023,0.02282669,0.00005408243,0.0002149249,0.00005362419,0.0005828348,0.009635101,0.1023237,0.2605093,0.0009598847,0.6025898],"study_design_scores_gemma":[0.0002664328,0.00002455245,0.002014123,0.0001493792,0.00001725999,0.00003417482,0.0001778626,0.9865249,0.0007788611,0.00949673,0.0004397754,0.00007597564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04760826,0.0001084065,0.9496217,0.001829638,0.0007160056,0.00005366922,0.00002451014,0.000007342125,0.00003040389],"genre_scores_gemma":[0.8394482,0.0001879551,0.1599156,0.0003365253,0.00009792449,5.179459e-7,0.00000618243,0.00000251389,0.00000458502],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9768898,"threshold_uncertainty_score":0.5272225,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416940015","doi":"10.1007/s41060-025-00885-x","title":"Sequential Bayesian estimation of the F1 score using the Dirichlet-multinomial model","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Imbalanced Data Classification Techniques","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":"Western University; University of Manitoba","funders":"","keywords":"Benchmark (surveying); Metric (unit); Bayesian probability; Sample (material); Point estimation; Sample size determination; Bayesian inference; Prior probability; Class (philosophy)","authors":[{"name":"Surani Matharaarachchi","is_ca":true},{"name":"Maxime Turgeon","is_ca":true},{"name":"Saman Muthukumarana","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0841653532904757,"gpt":0.3783429684597155,"spread":0.2941776151692398,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001345326,0.00006034591,0.00008920796,0.0002210985,0.0001639889,0.0002985689,0.005112322,0.0000212716,8.938595e-7],"category_scores_gemma":[0.000529138,0.00003516991,0.00003052485,0.0006140284,0.0004593029,0.002279053,0.001238432,0.0001315897,1.398461e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009048893,"about_ca_system_score_gemma":0.0008571147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001680259,"about_ca_topic_score_gemma":0.000003436624,"domain_scores_codex":[0.9985131,0.00002869056,0.0003734988,0.0001687349,0.0008238802,0.00009206664],"domain_scores_gemma":[0.9980291,0.00006625673,0.0004499058,0.0006145455,0.0008124092,0.00002776375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005759231,0.0003008887,0.008895353,0.00003909379,0.0002569002,0.00001364405,0.001031861,0.1359005,0.1141678,0.4787115,0.007291285,0.2533336],"study_design_scores_gemma":[0.0001042734,0.000006354243,0.0009801657,0.0000644358,0.00001692318,0.00002514321,0.00002513477,0.9864206,0.00774842,0.004370196,0.0002033753,0.00003492231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01384,0.00002472846,0.9815343,0.004035373,0.0003492076,0.00005013507,0.00004151595,0.00000591308,0.0001188541],"genre_scores_gemma":[0.8990269,0.00003298972,0.1005598,0.0003168555,0.00004137453,2.313166e-7,0.000002765982,0.000001403404,0.00001771148],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8851869,"threshold_uncertainty_score":0.9500051,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403155585","doi":"10.1007/s41060-024-00653-3","title":"A comparative exploration of two diffusion generative models on tabular data synthesis","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Privacy-Preserving Technologies in Data","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":"Cape Breton University","funders":"","keywords":"Generative grammar; Diffusion; Computer science; Artificial intelligence; Physics","authors":[{"name":"Neetu Kumari","is_ca":true},{"name":"Enayat Rajabi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2532926116103552,"gpt":0.4105372524801282,"spread":0.157244640869773,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001950689,0.0001055673,0.0001980747,0.0006089266,0.00008166103,0.0005837109,0.03588823,0.00002768314,0.000003666237],"category_scores_gemma":[0.005206475,0.00007913583,0.0000213757,0.0007207877,0.0003867409,0.01491961,0.03905484,0.000198979,0.000002933446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008070161,"about_ca_system_score_gemma":0.0004100995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001613536,"about_ca_topic_score_gemma":0.000009425318,"domain_scores_codex":[0.997507,0.00004190389,0.0004212708,0.0004753003,0.001423654,0.0001308428],"domain_scores_gemma":[0.9952033,0.0003507971,0.0002810938,0.003389961,0.0007122568,0.00006254591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000094777,0.0008448978,0.0002070302,0.00006007803,0.0008383262,0.0004981951,0.001776923,0.007166541,0.0381496,0.4651186,0.1501028,0.3351422],"study_design_scores_gemma":[0.0001124272,0.00005668104,0.00001359201,0.0002097992,0.00002079412,0.00002962158,0.0001319262,0.9199682,0.006541333,0.07188743,0.0009525336,0.00007560068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0101805,0.0003843566,0.970907,0.01706245,0.0005613082,0.00005482144,0.0005341006,0.0000310647,0.0002844437],"genre_scores_gemma":[0.8059487,0.0008694009,0.19294,0.00009305272,0.0001024767,6.198457e-7,0.00003720347,0.00000295474,0.000005676799],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9128017,"threshold_uncertainty_score":0.9988582,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4412623152","doi":"10.1007/s41060-025-00870-4","title":"Impact of hotel responses to online reviews on customer loyalty and acquisition: a longitudinal sentiment analysis with booking","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Digital Marketing and Social Media","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Advertising; Loyalty; Loyalty business model; Sentiment analysis; Marketing; Business; Computer science; Artificial intelligence; Service quality; Service (business)","authors":[{"name":"Seynabou Diouf","is_ca":true},{"name":"Haïfa Nakouri","is_ca":true},{"name":"Bob-Antoine J. Ménélas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06655442216595538,"gpt":0.4502535513002822,"spread":0.3836991291343268,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002793361,0.00006911369,0.0002275052,0.0006875727,0.0001445408,0.0002298946,0.00060836,0.00001960195,0.0000159312],"category_scores_gemma":[0.001488471,0.00004796848,0.00005931899,0.001196301,0.0004803167,0.0006554443,0.0001578432,0.00008062812,6.227806e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001302679,"about_ca_system_score_gemma":0.0005485681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001718803,"about_ca_topic_score_gemma":0.0002112387,"domain_scores_codex":[0.9984128,0.00007214485,0.0003072525,0.0001737503,0.0009084787,0.0001255505],"domain_scores_gemma":[0.9984187,0.0002306204,0.0002647345,0.0001405729,0.0008097275,0.0001356478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009142426,0.0004716016,0.9079522,0.0000199602,0.001481434,0.00006605961,0.002852448,0.0002217576,0.0003095132,0.002652594,0.003418192,0.07963997],"study_design_scores_gemma":[0.0005295453,0.0003993168,0.9829352,0.0008855259,0.0006476921,0.00001019551,0.002177663,0.000605239,0.00004225742,0.0002849691,0.01129405,0.0001883293],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9949408,0.0002017179,0.0005451967,0.00223122,0.0001200498,0.00006228212,0.00009839254,0.00000274262,0.001797584],"genre_scores_gemma":[0.9980503,0.0006535616,0.0007455065,0.0002119803,0.0001065619,2.430276e-7,0.000004711272,0.000001490118,0.0002256007],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07945164,"threshold_uncertainty_score":0.2216879,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2997087822","doi":"10.1007/s41060-020-00227-z","title":"A consistently oriented basis for eigenanalysis","year":2020,"lang":"en","type":"preprint","venue":"International Journal of Data Science and Analytics","topic":"Scientific Research and Discoveries","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of Technology Sydney; York University; Massachusetts Institute of Technology","keywords":"Python (programming language); Interpretability; Eigenvalues and eigenvectors; Computer science; Algorithm; Basis (linear algebra); Artificial intelligence; Implementation; Machine learning; Mathematics; Programming language","authors":[{"name":"Jay N. Damask","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1137284844806762,"gpt":0.4019434110814905,"spread":0.2882149266008143,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001365839,0.0001242785,0.0002742726,0.0003743663,0.0001294255,0.0008991176,0.002435081,0.00002497962,0.00009194735],"category_scores_gemma":[0.000757354,0.0000964905,0.0001462008,0.0003507375,0.0005179704,0.001007602,0.00181491,0.0002314943,0.000002556771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000547068,"about_ca_system_score_gemma":0.001847322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000635839,"about_ca_topic_score_gemma":0.000005286366,"domain_scores_codex":[0.9974748,0.00001766133,0.0004726332,0.0004069089,0.001434646,0.0001933609],"domain_scores_gemma":[0.9962281,0.0001254768,0.0005310965,0.0003873302,0.002485055,0.0002429151],"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":[0.001674166,0.002039254,0.1520254,0.0004244349,0.0177653,0.0003048907,0.004260291,0.003482048,0.01975705,0.220421,0.2888958,0.2889503],"study_design_scores_gemma":[0.004546766,0.0006060553,0.005821839,0.001312568,0.002871394,0.00006450352,0.01814558,0.5602477,0.01167889,0.1260586,0.2667943,0.001851818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2032092,0.0008981019,0.7192615,0.03396328,0.006462378,0.0007829805,0.0277574,0.00002389189,0.007641289],"genre_scores_gemma":[0.9902094,0.00009243815,0.008312015,0.0001452282,0.0007877527,0.000002227428,0.0003254263,0.000006376216,0.0001191278],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7870002,"threshold_uncertainty_score":0.8670212,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4417145987","doi":"10.1007/s41060-025-00934-5","title":"A novel multilevel taxonomical approach for describing high-dimensional unlabeled movement data","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Linnéuniversitetet","keywords":"Anomaly detection; Movement (music); Outlier; Scale (ratio); Variable (mathematics); Face (sociological concept)","authors":[{"name":"Yashar Tavakoli","is_ca":true},{"name":"Lourdes Peña‐Castillo","is_ca":true},{"name":"Amílcar Soares","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.302275681033034,"gpt":0.3948436289704082,"spread":0.09256794793737422,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002382872,0.00009446447,0.0001973133,0.0002887714,0.0001343451,0.0001954994,0.002350614,0.00003809801,0.000012052],"category_scores_gemma":[0.002624577,0.00006962068,0.00003022556,0.0002339803,0.0001878517,0.00101002,0.001348464,0.0001354546,3.862798e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008627784,"about_ca_system_score_gemma":0.0003865622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001834823,"about_ca_topic_score_gemma":0.000002762604,"domain_scores_codex":[0.9983567,0.00001205321,0.0005146132,0.0003309886,0.0006295729,0.0001560606],"domain_scores_gemma":[0.9979181,0.0003873817,0.0003065313,0.0004792083,0.0008285826,0.00008022084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002586009,0.002919931,0.002160582,0.00007026908,0.001041385,0.00002326438,0.00005340014,0.0008381208,0.03814352,0.8168468,0.07092278,0.06672136],"study_design_scores_gemma":[0.001767539,0.00005392543,0.001096585,0.0001070371,0.0001467606,0.00003550246,0.0001307169,0.9793202,0.0005722831,0.01395434,0.00267133,0.0001437675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02422377,0.00003304535,0.9725649,0.001650746,0.0003157231,0.0001181975,0.0009508702,0.000005215193,0.0001375615],"genre_scores_gemma":[0.3801676,0.00001610418,0.6189521,0.0005463641,0.0001333184,0.000001199089,0.0001178745,0.000003322324,0.00006218832],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9784821,"threshold_uncertainty_score":0.4368065,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399847064","doi":"10.1007/s41060-024-00589-8","title":"Twin neural network improved k-nearest neighbor regression","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Regional Municipality of Waterloo; Perimeter Institute; University of Waterloo","funders":"Mitacs","keywords":"Artificial neural network; Regression; k-nearest neighbors algorithm; Artificial intelligence; Pattern recognition (psychology); Computer science; Statistics; Mathematics","authors":[{"name":"Sebastian J. Wetzel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04646352333519553,"gpt":0.3408537908542291,"spread":0.2943902675190335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001188929,0.00008363689,0.0001042205,0.0002728811,0.0001110696,0.001196929,0.002541186,0.00002836465,0.00001503807],"category_scores_gemma":[0.0002143988,0.00005583356,0.00003526057,0.0005586133,0.0001486908,0.005336446,0.0008779272,0.0001959662,0.000009287833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003926964,"about_ca_system_score_gemma":0.000322832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000794579,"about_ca_topic_score_gemma":0.000003084294,"domain_scores_codex":[0.9983529,0.00002013464,0.0003030351,0.0002802142,0.0008693205,0.0001744121],"domain_scores_gemma":[0.9987628,0.00009968621,0.0001425622,0.0002947788,0.0005692882,0.0001308783],"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":[0.00004270152,0.00009181028,0.001126926,0.00002275566,0.0001136733,0.0005883134,0.0003685266,0.0008027544,0.02100178,0.00982073,0.06168272,0.9043373],"study_design_scores_gemma":[0.0001589669,0.00006819865,0.0006372954,0.0002874661,0.00001404602,0.0002852243,0.00004708281,0.968047,0.0005873211,0.002088516,0.02768345,0.00009549414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2280758,0.00718664,0.6752317,0.06269053,0.02342705,0.000282136,0.0002172948,0.0002190456,0.002669819],"genre_scores_gemma":[0.9768567,0.0006398914,0.02081049,0.000730463,0.0008629233,3.36126e-7,0.0000111572,0.000004845231,0.00008320807],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9672442,"threshold_uncertainty_score":0.9998399,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2806326686","doi":"10.1007/s41060-018-0130-1","title":"FACTORBASE: multi-relational structure learning with SQL all the way","year":2018,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"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; China Scholarship Council; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Statistical relational learning; Relational database; SQL; Relational model; Database design; Database model; Bayesian network; Relational database management system; Data definition language; Database; Machine learning; Artificial intelligence; Data mining","authors":[{"name":"Oliver Schulte","is_ca":true},{"name":"Zhensong Qian","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09284649269330404,"gpt":0.3453022686637123,"spread":0.2524557759704083,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009230549,0.00008003561,0.00008193051,0.0001452244,0.0002169941,0.000500072,0.002909906,0.00002329566,0.00001504828],"category_scores_gemma":[0.0002561168,0.00004443105,0.0000154307,0.00030924,0.0005324135,0.002399799,0.0004897666,0.0002634867,0.000002947136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003636873,"about_ca_system_score_gemma":0.0003733755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001166806,"about_ca_topic_score_gemma":0.00001910843,"domain_scores_codex":[0.9983018,0.00002556633,0.0002217464,0.0002202687,0.001087287,0.0001433479],"domain_scores_gemma":[0.997867,0.00008307526,0.0002446094,0.0002818842,0.001430143,0.00009327372],"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":[0.0002076067,0.0004845835,0.07017756,0.00001906377,0.001226452,0.0003599051,0.01165924,0.01957573,0.03483419,0.3757946,0.008525337,0.4771357],"study_design_scores_gemma":[0.0003953224,0.0001989354,0.01015676,0.00006101766,0.00002418872,0.0004363911,0.0001382273,0.9749972,0.0006813369,0.001590153,0.01117599,0.0001444922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04811003,0.00005922109,0.9474202,0.003922069,0.0003322816,0.00002153882,0.00001905616,0.000009074186,0.0001065642],"genre_scores_gemma":[0.9458467,0.00004168498,0.05332601,0.0005080135,0.0002305224,7.498291e-8,0.000004420889,0.000002446663,0.00004017249],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9554214,"threshold_uncertainty_score":0.5407379,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416776409","doi":"10.1007/s41060-025-00884-y","title":"Social media data mining of human behaviour during bushfire evacuation","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Public Relations and Crisis Communication","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"National Institute of Standards and Technology","keywords":"Geolocation; Social media; Geotagging; Resource (disambiguation); Data collection; Lexicon; Open data","authors":[{"name":"Junfeng Wu","is_ca":false},{"name":"Xiangmin Zhou","is_ca":false},{"name":"Erica D. Kuligowski","is_ca":false},{"name":"Dhirendra Singh","is_ca":false},{"name":"Enrico Ronchi","is_ca":false},{"name":"Max Kinateder","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1614186176657868,"gpt":0.4751142063894374,"spread":0.3136955887236506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003242945,0.00004227979,0.0001010751,0.000410611,0.0005096616,0.0002234451,0.003347302,0.00003498935,0.00001602021],"category_scores_gemma":[0.001643684,0.00003955482,0.00001788016,0.0005846882,0.0005247502,0.002929281,0.0007917493,0.0001053655,3.007887e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008702218,"about_ca_system_score_gemma":0.0006945052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001224978,"about_ca_topic_score_gemma":0.0003337563,"domain_scores_codex":[0.9983168,0.00005299039,0.000386545,0.0001380393,0.001010707,0.00009487743],"domain_scores_gemma":[0.9977958,0.000126075,0.000396535,0.0003539608,0.001282724,0.00004495039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00007639926,0.0008019475,0.3145976,0.00003521629,0.0005468979,0.00002261906,0.0384569,0.00005930081,0.01260896,0.3202076,0.0198002,0.2927864],"study_design_scores_gemma":[0.002381847,0.00006632076,0.8453893,0.0006286937,0.0005570056,0.00002497083,0.08627123,0.02326721,0.0007884148,0.01253696,0.02761013,0.0004778961],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9852527,0.0001932155,0.0007265481,0.008761218,0.000324295,0.00004018356,0.00009213424,0.000005670287,0.00460402],"genre_scores_gemma":[0.9982762,0.0003772688,0.001024878,0.0000306115,0.0001706762,1.584366e-7,0.0000653578,0.000001508833,0.00005334017],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5307917,"threshold_uncertainty_score":0.6220176,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}