{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":18,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":18,"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":"ddb50c5bddf8","filters":{"venue":"Harvard Data Science Review"}},"results":[{"id":"W4391382837","doi":"10.1162/99608f92.d3197524","title":"Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment","year":2024,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Defense, Military, and Policy Studies","field":"Economics, Econometrics and Finance","cited_by":35,"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":"Differential privacy; Software deployment; Internet privacy; Computer science; Differential (mechanical device); Computer security; Engineering; Data mining; Aerospace engineering; Software engineering","authors":[{"name":"Rachel Cummings","is_ca":false},{"name":"Damien Desfontaines","is_ca":false},{"name":"David Evans","is_ca":false},{"name":"Roxana Geambasu","is_ca":false},{"name":"Yangsibo Huang","is_ca":false},{"name":"Matthew Jagielski","is_ca":false},{"name":"Peter Kairouz","is_ca":false},{"name":"Gautam Kamath","is_ca":true},{"name":"Sewoong Oh","is_ca":false},{"name":"Olga Ohrimenko","is_ca":false},{"name":"Nicolas Papernot","is_ca":false},{"name":"Ryan Rogers","is_ca":false},{"name":"Milan Shen","is_ca":false},{"name":"Shuang Song","is_ca":false},{"name":"Weijie Su","is_ca":false},{"name":"Andreas Terzis","is_ca":false},{"name":"Abhradeep Thakurta","is_ca":false},{"name":"Sergei Vassilvitskii","is_ca":false},{"name":"Yu-Xiang Wang","is_ca":false},{"name":"Li Xiong","is_ca":false},{"name":"Sergey Yekhanin","is_ca":false},{"name":"Dahua Yu","is_ca":false},{"name":"Huanyu Zhang","is_ca":false},{"name":"Wanrong Zhang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06757007992727386,"gpt":0.3223673161332591,"spread":0.2547972362059853,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0424603,0.001368815,0.001970284,0.001786814,0.00237852,0.01260981,0.005084927,0.009596006,0.01286202],"category_scores_gemma":[0.06640749,0.0009276541,0.001721564,0.003375833,0.009451522,0.0532192,0.008312952,0.01662257,0.003506101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003598472,"about_ca_system_score_gemma":0.006188106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00161179,"about_ca_topic_score_gemma":0.001719606,"domain_scores_codex":[0.9801216,0.01101579,0.0009839644,0.002106685,0.004495412,0.00127659],"domain_scores_gemma":[0.9075533,0.06676883,0.002737785,0.00967878,0.009492037,0.003769332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002203169,0.000208276,0.002832206,0.002177682,0.00009278408,0.0002703666,0.0008353622,0.006271123,0.001864485,0.5428176,0.03557689,0.4068329],"study_design_scores_gemma":[0.00006265954,0.0003740233,0.0009031859,0.002877859,0.00004262297,0.0005764516,0.002288804,0.0117843,0.001689023,0.7090074,0.270285,0.0001087404],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.008173124,0.1852445,0.414282,0.359344,0.002823223,0.0002935429,0.0004558113,0.001188698,0.02819509],"genre_scores_gemma":[0.2411494,0.3079347,0.3976886,0.03813275,0.006610413,0.0006869567,0.0008761396,0.0005896726,0.006331503],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.0424603,"threshold_uncertainty_score":0.2245542,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392785285","doi":"10.1162/99608f92.35a2f3ff","title":"The Turing Transformation: Artificial Intelligence, Intelligence Augmentation, and Skill Premiums","year":2024,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Economic Development and Digital Transformation","field":"Economics, Econometrics and Finance","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Creative Destruction Lab; University of Toronto","funders":"","keywords":"Transformation (genetics); Turing; Computer science; Artificial intelligence; Cognitive science; Cognitive psychology; Psychology; Programming language","authors":[{"name":"Ajay Agrawal","is_ca":true},{"name":"Joshua S. Gans","is_ca":true},{"name":"Avi Goldfarb","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.119222361682757,"gpt":0.3099406749929042,"spread":0.1907183133101473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003386061,0.0003600739,0.0005489261,0.002234846,0.0007551545,0.002967042,0.0009221697,0.001109537,0.008558319],"category_scores_gemma":[0.01598667,0.0001996252,0.0006647178,0.001941289,0.009287149,0.00651344,0.00241625,0.002514222,0.0006219877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001916525,"about_ca_system_score_gemma":0.0007697146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002156626,"about_ca_topic_score_gemma":0.001404297,"domain_scores_codex":[0.9986985,0.0004486678,0.00008645107,0.0002357085,0.0003664332,0.0001642424],"domain_scores_gemma":[0.9894539,0.006181076,0.001516809,0.001461065,0.0008104653,0.000576699],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001377757,0.00008289904,0.01197664,0.000277844,0.00007593008,0.000100077,0.0004661677,0.004167547,0.000431917,0.8772116,0.005418465,0.0996531],"study_design_scores_gemma":[0.00002476683,0.00006797989,0.02594468,0.0002114981,0.00003117417,0.0001795783,0.0002009903,0.00512518,0.0004792736,0.9482409,0.0194688,0.00002519741],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3760924,0.07199842,0.08576479,0.08096451,0.0009158817,0.000123634,0.0009855379,0.0004782756,0.3826765],"genre_scores_gemma":[0.9798655,0.008000037,0.004119873,0.00167739,0.0005095208,0.00005109487,0.0001473431,0.00004697734,0.005582167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008558319,"threshold_uncertainty_score":0.0286305,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4367177363","doi":"10.1162/99608f92.81172cdd","title":"On “A conversation with Sir David Cox”","year":2023,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Dental Education, Practice, Research","field":"Health Professions","cited_by":7,"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":"Conversation; Psychology; Psychoanalysis; Communication","authors":[{"name":"Nancy Reid","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2761699729883755,"gpt":0.5653658902526287,"spread":0.2891959172642532,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0428167,0.002356553,0.004514732,0.005376144,0.009917335,0.015319,0.006239567,0.06045484,0.01767555],"category_scores_gemma":[0.2377684,0.001935301,0.002921693,0.00480781,0.009444307,0.01956668,0.009499338,0.07708996,0.01192726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007362939,"about_ca_system_score_gemma":0.01522293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02351475,"about_ca_topic_score_gemma":0.05030495,"domain_scores_codex":[0.9643561,0.01424276,0.004238283,0.003488154,0.01135237,0.002322348],"domain_scores_gemma":[0.8005537,0.1491206,0.0084623,0.003987277,0.02279082,0.01508525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001583663,0.000004815027,0.00003722034,0.000067204,0.00001182488,0.00003352452,0.00007296322,0.000006055984,0.00001391358,0.0008573307,0.9970117,0.001867568],"study_design_scores_gemma":[0.00004627768,0.00001361871,0.0002740695,0.0007562099,0.00003533496,0.00007832663,0.000477735,0.00003294357,0.00004154925,0.003154612,0.9950394,0.00004985766],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"other","genre_scores_codex":[0.00002468374,0.005429954,0.00009005279,0.9389057,0.05478423,0.00001113137,0.00005046101,0.00001200803,0.0006918063],"genre_scores_gemma":[0.0001985524,0.001437944,0.00009304508,0.9689953,0.02733335,0.00003380737,0.0000191966,0.0000223533,0.001866318],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.06045484,"threshold_uncertainty_score":0.2264391,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394820768","doi":"10.1162/99608f92.d949f941","title":"Government Interventions to Avert Future Catastrophic AI Risks","year":2024,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Leadership, Behavior, and Decision-Making Studies","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Government (linguistics); Psychological intervention; Business; Risk analysis (engineering); Psychology; Psychiatry","authors":[{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4249351892336851,"gpt":0.5346952383454162,"spread":0.1097600491117311,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0236509,0.0005453671,0.0005149799,0.002657045,0.002191376,0.004246806,0.001927313,0.005504921,0.006051889],"category_scores_gemma":[0.09536259,0.0002844135,0.000822522,0.001789381,0.005464025,0.004435601,0.00428901,0.005455183,0.0008001031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004448302,"about_ca_system_score_gemma":0.01621342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006576412,"about_ca_topic_score_gemma":0.01199139,"domain_scores_codex":[0.9780813,0.01437258,0.0007237998,0.0009751766,0.003809307,0.002037828],"domain_scores_gemma":[0.9417145,0.04078101,0.006035818,0.00379984,0.006230528,0.001438349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009319708,0.0002730773,0.007397887,0.001795157,0.0003018582,0.0003738243,0.003321937,0.004234254,0.0005875605,0.652654,0.1031079,0.2258594],"study_design_scores_gemma":[0.0001245506,0.0002489643,0.0129421,0.005544527,0.0002211455,0.000279103,0.006462879,0.002234465,0.001366114,0.3129132,0.6575816,0.00008151213],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.03614201,0.08959468,0.03817091,0.5689905,0.007264552,0.0006575038,0.00036605,0.0004167396,0.258397],"genre_scores_gemma":[0.7592312,0.06228551,0.02141718,0.1358644,0.004013772,0.001267077,0.0002608018,0.0001111782,0.015549],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0236509,"threshold_uncertainty_score":0.1250794,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2954249017","doi":"10.1162/99608f92.130f856e","title":"(A) Data in the Life: Authorship Attribution in Lennon-McCartney Songs","year":2019,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Music and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Melody; Chord (peer-to-peer); Authorship attribution; Musical; Lyrics; Period (music)","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.1606490110483889,"gpt":0.3739416594571497,"spread":0.2132926484087608,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002535443,0.0002608548,0.0001708475,0.001851838,0.0004279179,0.0009495039,0.0004240941,0.0004900226,0.003380704],"category_scores_gemma":[0.02838287,0.00007933949,0.0001820945,0.003811009,0.0006332219,0.0009311324,0.0006438967,0.000598489,0.0008054697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000666104,"about_ca_system_score_gemma":0.0003138632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01195576,"about_ca_topic_score_gemma":0.0158968,"domain_scores_codex":[0.9989306,0.0005012475,0.0001154257,0.0001493455,0.0002463154,0.00005708891],"domain_scores_gemma":[0.9796317,0.01291625,0.002832168,0.001262221,0.002896136,0.0004614601],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000693208,0.00008657265,0.729234,0.0008184275,0.0001224929,0.0007671591,0.003349451,0.003917872,0.001675015,0.009096727,0.04393413,0.2063049],"study_design_scores_gemma":[0.00005126502,0.0001329308,0.8248125,0.0006867766,0.00009306111,0.0009186296,0.004770938,0.04497848,0.003519273,0.01771966,0.1022411,0.00007547013],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9096428,0.006207497,0.02661587,0.01225311,0.0006265852,0.0001419742,0.02344193,0.0003199958,0.02075012],"genre_scores_gemma":[0.9837335,0.000718874,0.006101095,0.0002899211,0.0001612654,0.00004740556,0.006365106,0.00002104926,0.00256183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01195576,"threshold_uncertainty_score":0.02377236,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385297687","doi":"10.1162/99608f92.9ba2bd43","title":"Reinforcing Reproducibility and Replicability: An Introduction","year":2023,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"BIM and Construction Integration","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"National Science Foundation","keywords":"Reproducibility; Computer science; Statistics; Mathematics","authors":[{"name":"Lars Vilhuber","is_ca":false},{"name":"Ian M. Schmutte","is_ca":false},{"name":"Aleksandr Michuda","is_ca":false},{"name":"Marie Connolly","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05219805125579313,"gpt":0.3084426474261471,"spread":0.2562445961703539,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06195481,0.001752576,0.001796854,0.006650229,0.005796846,0.01804293,0.003826359,0.0105501,0.01059155],"category_scores_gemma":[0.1732961,0.001216569,0.00210421,0.006616653,0.03119809,0.02871359,0.0073823,0.02056634,0.00392148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008747092,"about_ca_system_score_gemma":0.010852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004790736,"about_ca_topic_score_gemma":0.004032794,"domain_scores_codex":[0.9301143,0.04375318,0.005232831,0.005047298,0.01438955,0.001462868],"domain_scores_gemma":[0.7228094,0.2321932,0.005493474,0.01043149,0.02684219,0.002230204],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005919458,0.00004624989,0.0005535533,0.002345415,0.00005138389,0.0001829597,0.005782756,0.0006394406,0.00048676,0.7134391,0.1953113,0.08110183],"study_design_scores_gemma":[0.00001530017,0.00005436761,0.0003187555,0.003015654,0.00002226916,0.0002405186,0.001040086,0.0006830131,0.0002902753,0.2654099,0.7288497,0.00006009503],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.001493261,0.2479542,0.1285734,0.4913547,0.08038438,0.0005311648,0.0004235283,0.0005564016,0.04872889],"genre_scores_gemma":[0.08644813,0.3088619,0.126915,0.2241935,0.2117034,0.002186368,0.0006074829,0.002357292,0.03672697],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.9380452,"threshold_uncertainty_score":0.3276523,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409640743","doi":"10.1162/99608f92.abf14c9d","title":"Challenges and Opportunities for Statistics in the Era of Data Science","year":2025,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Data science; Statistics; Computer science; Mathematics","authors":[{"name":"Claudia Kirch","is_ca":false},{"name":"Soumendra N. Lahiri","is_ca":false},{"name":"Harald Binder","is_ca":false},{"name":"Werner Brannath","is_ca":false},{"name":"Ivor Cribben","is_ca":true},{"name":"Holger Dette","is_ca":false},{"name":"Philipp Doebler","is_ca":false},{"name":"Oliver Y. Feng","is_ca":false},{"name":"Axel Gandy","is_ca":false},{"name":"Sonja Greven","is_ca":false},{"name":"Barbara Hammer","is_ca":false},{"name":"Stefan Harmeling","is_ca":false},{"name":"Thomas Hotz","is_ca":false},{"name":"Göran Kauermann","is_ca":false},{"name":"Joscha Krause","is_ca":false},{"name":"Georg Krempl","is_ca":false},{"name":"Alicia Nieto-Reyes","is_ca":false},{"name":"Ostap Okhrin","is_ca":false},{"name":"Hernando Ombao","is_ca":false},{"name":"Florian Pein","is_ca":false},{"name":"Michal Pešta","is_ca":false},{"name":"Dimitris N. Politis","is_ca":false},{"name":"Li‐Xuan Qin","is_ca":false},{"name":"Tom Rainforth","is_ca":false},{"name":"Holger Rauhut","is_ca":false},{"name":"Henry W. J. Reeve","is_ca":false},{"name":"David Salinas","is_ca":false},{"name":"Johannes Schmidt-Hieber","is_ca":false},{"name":"Clayton Scott","is_ca":false},{"name":"Johan Segers","is_ca":false},{"name":"Myra Spiliopoulou","is_ca":false},{"name":"Adalbert Wilhelm","is_ca":false},{"name":"Ines Wilms","is_ca":false},{"name":"Yi Yu","is_ca":false},{"name":"Johannes Lederer","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4736845305441111,"gpt":0.4180949198526878,"spread":0.05558961069142337,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1518123,0.001495425,0.004271997,0.008697428,0.005045139,0.02015693,0.004269716,0.01715722,0.005668201],"category_scores_gemma":[0.1825534,0.001349321,0.002544315,0.008862064,0.04848498,0.05526893,0.01082859,0.03634132,0.0027594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008853793,"about_ca_system_score_gemma":0.01819619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003454399,"about_ca_topic_score_gemma":0.001880521,"domain_scores_codex":[0.9058151,0.0639004,0.003883298,0.005157582,0.01944326,0.001800247],"domain_scores_gemma":[0.5830945,0.3701651,0.005110968,0.01451295,0.02150908,0.005607412],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004376227,0.00003582269,0.0003310235,0.0006649467,0.00004664982,0.0000693115,0.0007263682,0.0007737778,0.0001083834,0.9318642,0.03000138,0.03533437],"study_design_scores_gemma":[0.0000165873,0.00002762522,0.0002584491,0.0008355925,0.00001027203,0.00007943179,0.0005887022,0.0009767711,0.00005913998,0.8967131,0.1003903,0.00004403423],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.001079378,0.2170265,0.04416353,0.7221779,0.007605814,0.00003585628,0.0002238552,0.0001513052,0.007535898],"genre_scores_gemma":[0.11542,0.460293,0.1096385,0.2026408,0.1052236,0.0005534158,0.0005336704,0.0006754072,0.005021674],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8481877,"threshold_uncertainty_score":0.8028698,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4307407759","doi":"10.1162/99608f92.13e1d60e","title":"The Use of Data Science in a National Statistical Office","year":2022,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Data Analysis with R","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Statistics Canada","funders":"","keywords":"Data science; Computer science","authors":[{"name":"Sevgui Erman","is_ca":true},{"name":"Eric Rancourt","is_ca":true},{"name":"Yanick Beaucage","is_ca":true},{"name":"Andre Loranger","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2546039632704132,"gpt":0.3974377244224109,"spread":0.1428337611519977,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1577007,0.0008676118,0.001429736,0.007379442,0.003691574,0.01169575,0.00355019,0.005429953,0.004681365],"category_scores_gemma":[0.2483169,0.0008169844,0.001041713,0.01120803,0.02353781,0.01587445,0.00681858,0.01504665,0.003556926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009824232,"about_ca_system_score_gemma":0.02497109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008457003,"about_ca_topic_score_gemma":0.003574512,"domain_scores_codex":[0.7951872,0.138755,0.01498232,0.01210322,0.03707491,0.001897259],"domain_scores_gemma":[0.5702175,0.2780346,0.01969665,0.05236619,0.07450867,0.005176491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002865022,0.00002464159,0.001012372,0.001137051,0.00006332695,0.00007714754,0.0007566739,0.0007008445,0.0002400652,0.7596975,0.1072438,0.1290179],"study_design_scores_gemma":[0.00001160094,0.00003078152,0.0008432032,0.00205377,0.00002833327,0.0001153144,0.0003703076,0.0007384562,0.0002734263,0.1117066,0.8837913,0.00003701291],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.002094476,0.1620041,0.2050534,0.5019432,0.02115439,0.0003209406,0.001622518,0.001073619,0.1047333],"genre_scores_gemma":[0.1353939,0.2499857,0.3646327,0.1696845,0.04383723,0.001572199,0.002706324,0.002333509,0.02985372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1577007,"threshold_uncertainty_score":0.8340108,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406435392","doi":"10.1162/99608f92.6f5dfc6f","title":"Data Literacy in Industry: High Time to Focus on Operationalization Through Middle Managers","year":2025,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Dalhousie University","keywords":"Operationalization; Focus (optics); Middle management; Business; Literacy; Psychology; Marketing; Pedagogy","authors":[{"name":"Dan Koloski","is_ca":false},{"name":"Berkeley Almand-Hunter","is_ca":false},{"name":"Stephen Gatchell","is_ca":false},{"name":"Valerie Logan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3341478690928784,"gpt":0.4925317085383525,"spread":0.1583838394454742,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06047932,0.0003868741,0.0009838102,0.003460395,0.003087539,0.01272769,0.002321777,0.005479942,0.006899583],"category_scores_gemma":[0.08397029,0.0005037491,0.0005988291,0.002667945,0.008284007,0.02298473,0.00886511,0.01304451,0.00184855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007583472,"about_ca_system_score_gemma":0.02430934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007448986,"about_ca_topic_score_gemma":0.00908864,"domain_scores_codex":[0.9768754,0.01196075,0.001427388,0.001708933,0.005608947,0.002418618],"domain_scores_gemma":[0.8600767,0.08586016,0.006521391,0.005824016,0.02784897,0.0138689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001394994,0.000156169,0.004124447,0.004344674,0.00006896252,0.0002325273,0.009593167,0.0002536875,0.0007260648,0.2454442,0.1953017,0.539615],"study_design_scores_gemma":[0.00004230674,0.0001594651,0.005649219,0.008376099,0.00003391262,0.0001761625,0.008478012,0.0002565942,0.0004678436,0.07408214,0.9022263,0.00005179878],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.005490908,0.1923912,0.005759309,0.7749096,0.005844197,0.00004683624,0.00005870078,0.00006918951,0.01543007],"genre_scores_gemma":[0.2669588,0.2495859,0.01272987,0.4346513,0.01692521,0.0004157706,0.0002414527,0.0003097171,0.01818197],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06047932,"threshold_uncertainty_score":0.3198491,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411542049","doi":"10.1162/99608f92.dc58eb7a","title":"Navigating the Privacy Landscape: Harmonizing Legislative and Public Sector Approaches in the Canadian Context","year":2025,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Criminal Law and Evidence","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Statistics Canada","funders":"","keywords":"Legislature; Context (archaeology); Public sector; Political science; Public relations; Internet privacy; Public administration; Geography; Computer science; Law; Archaeology","authors":[{"name":"Pierre Desrochers","is_ca":true},{"name":"Eric Rancourt","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3568609369470643,"gpt":0.4034727452268728,"spread":0.04661180827980849,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06236385,0.0006976157,0.001189421,0.01170168,0.06430032,0.04348149,0.007844977,0.007582105,0.004068254],"category_scores_gemma":[0.07501945,0.001143688,0.001036062,0.01996798,0.05957602,0.01079135,0.01427923,0.01151758,0.0002718237],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.4934841,"about_ca_system_score_gemma":0.7156559,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9964389,"about_ca_topic_score_gemma":0.9979838,"domain_scores_codex":[0.9234424,0.02720972,0.002535145,0.004935916,0.02523106,0.01664585],"domain_scores_gemma":[0.9035336,0.0407812,0.003292507,0.003494139,0.03897553,0.009922929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004903227,0.00004457109,0.007397032,0.0004990572,0.00006097889,0.0006324354,0.1744667,0.00214639,0.0005928638,0.731578,0.03782732,0.04470574],"study_design_scores_gemma":[0.00003325559,0.00003760189,0.02096964,0.002009067,0.0001336783,0.0002208574,0.3186182,0.002209255,0.0008647981,0.0988128,0.5557391,0.0003517969],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.09525631,0.02565179,0.01430663,0.6202232,0.001100022,0.0004118767,0.0007353351,0.0001738191,0.242141],"genre_scores_gemma":[0.9282249,0.01363371,0.01138578,0.03237316,0.000206352,0.0001866151,0.0002421207,0.0001255542,0.01362179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4934841,"threshold_uncertainty_score":0.5874866,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4398764826","doi":"10.1162/99608f92.f86474d0","title":"A Familiar, Invisible Engine Is Driving the AI Revolution","year":2024,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Aeronautics; Psychology; Automotive engineering; Engineering","authors":[{"name":"Matan Gavish","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06234315868469324,"gpt":0.3537710257510638,"spread":0.2914278670663705,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01034016,0.0008005183,0.0007181512,0.00268487,0.004939445,0.0144034,0.001606552,0.006576578,0.01395594],"category_scores_gemma":[0.0288992,0.00057993,0.000789948,0.00252147,0.0218415,0.02455292,0.00647494,0.01007108,0.00643333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005130311,"about_ca_system_score_gemma":0.00445265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006734265,"about_ca_topic_score_gemma":0.004573849,"domain_scores_codex":[0.9913037,0.003489626,0.0002901347,0.001390957,0.002666209,0.0008593736],"domain_scores_gemma":[0.9821987,0.009427145,0.001267898,0.002213553,0.002644068,0.002248711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001150749,0.00008612173,0.001849907,0.0003118785,0.00004510616,0.0001709222,0.002939414,0.0007580924,0.0006970516,0.8106794,0.1321716,0.05017535],"study_design_scores_gemma":[0.00003096084,0.00004669244,0.00174839,0.0004087597,0.00002291381,0.0001916353,0.002271471,0.001236792,0.0004627717,0.4285786,0.5649275,0.00007353896],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.02056629,0.03988842,0.03763195,0.6355388,0.01103238,0.00007176297,0.0006991855,0.0008679624,0.2537034],"genre_scores_gemma":[0.6186202,0.04630553,0.03296184,0.1819685,0.01966524,0.0003137851,0.0008469281,0.001277373,0.09804067],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.0144034,"threshold_uncertainty_score":0.0546847,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400451566","doi":"10.1162/99608f92.6a5d7a87","title":"Differentially Private Linear Regression With Linked Data","year":2024,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Linear regression; Regression; Statistics; Mathematics","authors":[{"name":"Shurong Lin","is_ca":false},{"name":"Elliot Paquette","is_ca":true},{"name":"Eric D. Kolaczyk","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1064976625576048,"gpt":0.3586239172977485,"spread":0.2521262547401437,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01637228,0.001096471,0.001707724,0.001679493,0.0009082244,0.003529729,0.002736693,0.002557793,0.00110185],"category_scores_gemma":[0.05509384,0.0008970556,0.001398088,0.00282222,0.003158351,0.005609598,0.005275646,0.004133466,0.00069303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002692196,"about_ca_system_score_gemma":0.002076353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00116608,"about_ca_topic_score_gemma":0.0006990469,"domain_scores_codex":[0.9847074,0.01033174,0.0004669895,0.001801318,0.002305161,0.0003875162],"domain_scores_gemma":[0.9617254,0.02834095,0.00236321,0.005840314,0.001421487,0.0003086262],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002433827,0.00009502353,0.001809456,0.000192157,0.0001450246,0.0002160595,0.0002963006,0.5209941,0.002286623,0.373639,0.001795248,0.09828769],"study_design_scores_gemma":[0.00002323802,0.00003312896,0.0001937136,0.00001949045,0.00001278029,0.00006858278,0.00001969156,0.8117849,0.00146951,0.1851327,0.001222124,0.00002006263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004631045,0.0003052757,0.9937968,0.0005257108,0.0000202318,0.00002386818,0.00006303187,0.0001587387,0.000475256],"genre_scores_gemma":[0.4772837,0.001746551,0.5153559,0.0007438667,0.0003874699,0.000355856,0.0005900972,0.000211437,0.003325166],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01637228,"threshold_uncertainty_score":0.08658594,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391378488","doi":"10.1162/99608f92.e3d09bff","title":"Discerning Audiences Through Like Buttons","year":2024,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Communication in Education and Healthcare","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University","keywords":"Aesthetics; Art; Computer science","authors":[{"name":"Carina Albrecht","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2906058399536966,"gpt":0.5471223570002874,"spread":0.2565165170465908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003442109,0.0003064139,0.0003652096,0.002423955,0.001593583,0.006927375,0.0005481479,0.001439442,0.02417994],"category_scores_gemma":[0.01789919,0.0002757172,0.0002471271,0.001411192,0.001861995,0.008607834,0.001607649,0.002468904,0.004835078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008459448,"about_ca_system_score_gemma":0.0009356412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003554758,"about_ca_topic_score_gemma":0.009651462,"domain_scores_codex":[0.9983632,0.0006697315,0.00008154932,0.0002407155,0.0004939847,0.0001508087],"domain_scores_gemma":[0.9857038,0.008720125,0.001228151,0.0003222426,0.00320967,0.0008160482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0001912939,0.0000490664,0.0047536,0.001177886,0.00002540983,0.0001369162,0.01377208,0.00002492148,0.0005839582,0.03067159,0.8019843,0.146629],"study_design_scores_gemma":[0.00001819062,0.00003900839,0.01279474,0.001204417,0.0000237062,0.0001522296,0.00951266,0.0000735509,0.0004066376,0.004574955,0.9711741,0.00002596067],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.04264472,0.1232504,0.005054062,0.3524427,0.03706995,0.0002396235,0.003017036,0.0005328022,0.4357488],"genre_scores_gemma":[0.44004,0.1221059,0.006986658,0.1437463,0.05026682,0.0006386405,0.002438454,0.001180827,0.2325964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02417994,"threshold_uncertainty_score":0.08088994,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406971547","doi":"10.1162/99608f92.7fcd521d","title":"What Are Statistical Assumptions About? An Answer From Perspectivism","year":2025,"lang":"en","type":"preprint","venue":"Harvard Data Science Review","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Perspectivism; Epistemology; Computer science; Econometrics; Mathematics; Philosophy","authors":[{"name":"Kino Zhao","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5070296381043464,"gpt":0.5557659503054858,"spread":0.04873631220113939,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07930588,0.001186577,0.003465769,0.003461604,0.004337441,0.01234974,0.004294261,0.01091022,0.006524261],"category_scores_gemma":[0.2198577,0.001191393,0.002020935,0.003199285,0.05385489,0.0540955,0.008812854,0.02332156,0.001861192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006124943,"about_ca_system_score_gemma":0.005087793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002895013,"about_ca_topic_score_gemma":0.0009046867,"domain_scores_codex":[0.9292024,0.04661575,0.003247148,0.006664574,0.01292131,0.001348906],"domain_scores_gemma":[0.7022638,0.2534401,0.009193217,0.01695611,0.0157559,0.00239086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000302296,0.00001184427,0.0003096766,0.0001429723,0.00004156681,0.00003299266,0.001395274,0.0004091069,0.00003981602,0.9847009,0.005882724,0.007002861],"study_design_scores_gemma":[0.000009075843,0.000004191966,0.00006924812,0.00008769424,0.000004357296,0.00001555049,0.0003104424,0.0002861886,0.00002417932,0.9929427,0.006238849,0.000007565064],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.008041171,0.01726137,0.2328926,0.7016321,0.003134027,0.00004600529,0.0004316172,0.0001888946,0.03637224],"genre_scores_gemma":[0.7118878,0.02201616,0.09756321,0.138751,0.02284752,0.0005010956,0.0007472221,0.0008052613,0.004880683],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.07930588,"threshold_uncertainty_score":0.4194146,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415667311","doi":"10.1162/99608f92.28e9f828","title":"An Undergraduate Course in Causality","year":2025,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Course (navigation); Set (abstract data type); Causality (physics); Quarter (Canadian coin); Graduate students; Advice (programming)","authors":[{"name":"Lea Bottmer","is_ca":false},{"name":"Guido W. Imbens","is_ca":false},{"name":"Jason Weitze","is_ca":false},{"name":"Mary Wootters","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.383188568202988,"gpt":0.5747813044805024,"spread":0.1915927362775143,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003919149,0.001326806,0.001269529,0.001831531,0.001245423,0.002447594,0.001058761,0.001496998,0.2749538],"category_scores_gemma":[0.0104052,0.0004923027,0.001034762,0.001616483,0.0006963753,0.00318503,0.002829715,0.002655365,0.07717764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002494331,"about_ca_system_score_gemma":0.005091452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001779238,"about_ca_topic_score_gemma":0.004085799,"domain_scores_codex":[0.9988742,0.0002177528,0.00009275222,0.0001839609,0.0004174314,0.0002138435],"domain_scores_gemma":[0.9942749,0.001506237,0.0002620179,0.0004147702,0.001513807,0.002028233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005231241,0.0002941453,0.0009523887,0.0002655848,0.00001153455,0.0001116941,0.0001739469,0.0002540478,0.0004189407,0.01029241,0.8556942,0.1314788],"study_design_scores_gemma":[0.00005637728,0.0001404233,0.003604172,0.0004261748,0.00001453388,0.0002543275,0.0002253094,0.0006180539,0.0003010463,0.03309239,0.9612535,0.00001367498],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.02273497,0.03095343,0.09227399,0.1561235,0.04660886,0.001658921,0.02451909,0.01391769,0.6112096],"genre_scores_gemma":[0.1106109,0.02247709,0.07088618,0.06427172,0.01969436,0.001973025,0.02689284,0.003211053,0.6799828],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2749538,"threshold_uncertainty_score":0.919812,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3172682396","doi":"10.1162/99608f92.8bb28793","title":"The Building Blocks of Statistical Education in the Data Science Ecosystem","year":2021,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Data Analysis with R","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Ecosystem; Data science; Environmental science; Environmental resource management; Computer science; Ecology; Biology","authors":[{"name":"Alison L. Gibbs","is_ca":true},{"name":"Nathan Taback","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06011675050366747,"gpt":0.3821871329555472,"spread":0.3220703824518797,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1671763,0.001077674,0.00256828,0.009802377,0.003083384,0.01532749,0.004240379,0.008033035,0.005835505],"category_scores_gemma":[0.2367003,0.001606939,0.001676025,0.005594398,0.04117147,0.02793367,0.007473532,0.02848493,0.002029876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008620433,"about_ca_system_score_gemma":0.02015848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01219446,"about_ca_topic_score_gemma":0.008938782,"domain_scores_codex":[0.9291757,0.04744381,0.004286975,0.004340554,0.01273813,0.002014898],"domain_scores_gemma":[0.5376019,0.3781458,0.005840208,0.02645534,0.04393832,0.008018426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006350913,0.0000816996,0.001000007,0.0008829995,0.0001333243,0.00006240906,0.0006136157,0.001117986,0.0002440072,0.8484194,0.02534067,0.1220404],"study_design_scores_gemma":[0.0000515368,0.00007293071,0.001188176,0.00153563,0.00004583918,0.00008845757,0.0002585919,0.001904769,0.0003776784,0.8760873,0.1183039,0.00008517411],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.003125282,0.1890635,0.2078987,0.5705324,0.005438528,0.000152175,0.0003038772,0.0007418512,0.02274369],"genre_scores_gemma":[0.2291955,0.2181686,0.3589146,0.1534057,0.02788854,0.001308501,0.0005301218,0.001621259,0.008967203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1671763,"threshold_uncertainty_score":0.8841234,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415741689","doi":"10.1162/99608f92.dbc60044","title":"AI and Writing in the Straddle Generation","year":2025,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Cybernetics and Technology in Society","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"","keywords":"Column (typography); Straddle; Face (sociological concept); Technical writing; Affect (linguistics)","authors":[{"name":"Benjamin Outar","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1138791503751696,"gpt":0.3484377760184191,"spread":0.2345586256432495,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00526403,0.0002059695,0.0004253721,0.002285286,0.002085418,0.006230391,0.0006541876,0.002517562,0.005205438],"category_scores_gemma":[0.01118254,0.0002003255,0.0003146485,0.001759974,0.008165288,0.00602417,0.002046612,0.005103211,0.001733565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002884875,"about_ca_system_score_gemma":0.004277583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01031742,"about_ca_topic_score_gemma":0.01231733,"domain_scores_codex":[0.9961654,0.001964801,0.0002718173,0.0002913375,0.0009795723,0.0003271188],"domain_scores_gemma":[0.9865326,0.008641291,0.0009769467,0.0005102285,0.00215949,0.001179542],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"qualitative","study_design_scores_codex":[0.0000714467,0.00008105011,0.001626199,0.001499691,0.00005898129,0.0005274144,0.01857856,0.0002106679,0.0003797936,0.2765705,0.3575334,0.3428624],"study_design_scores_gemma":[0.000008935134,0.00002504852,0.001560674,0.0008556711,0.000008641221,0.0003859875,0.002657985,0.00002809835,0.0001073786,0.01737971,0.9769687,0.00001309252],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.004577162,0.765931,0.0006500402,0.1732541,0.005801444,0.00001104022,0.00005461075,0.00003010935,0.04969054],"genre_scores_gemma":[0.1406465,0.7471969,0.0008497859,0.05651212,0.01085534,0.00004740408,0.0001367668,0.0001084097,0.04364672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9979146,"threshold_uncertainty_score":0.02783918,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407949312","doi":"10.1162/99608f92.d605e50f","title":"The Problem of Terroir in the Anthropocene","year":2025,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Global Energy and Sustainability Research","field":"Energy","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Anthropocene; Terroir; Environmental ethics; Geography; History; Archaeology; Philosophy; Art","authors":[{"name":"E. M. Wolkovich","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04118287588800967,"gpt":0.3828525447909881,"spread":0.3416696689029785,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01651415,0.0003220273,0.000855147,0.002134807,0.002356594,0.006160604,0.00186449,0.001965489,0.00568781],"category_scores_gemma":[0.02695253,0.0003395642,0.0005726637,0.00671832,0.01221289,0.02050065,0.004637253,0.006841182,0.000782225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003776154,"about_ca_system_score_gemma":0.006660203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01422848,"about_ca_topic_score_gemma":0.01726153,"domain_scores_codex":[0.9910166,0.00455752,0.0008813934,0.001069692,0.002030447,0.0004442669],"domain_scores_gemma":[0.9761254,0.01522662,0.001630344,0.002629158,0.003793523,0.0005949371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001121757,0.00002112399,0.005274879,0.002512505,0.00008397482,0.0002926027,0.011242,0.0004265295,0.0003403328,0.5327879,0.08246309,0.3644428],"study_design_scores_gemma":[0.000004481913,0.0000151889,0.003612093,0.001569956,0.00001402622,0.0001533633,0.004514212,0.00006813851,0.0001046497,0.04531059,0.9446142,0.00001902368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.01929961,0.5477925,0.01339281,0.3264773,0.01024713,0.00006654135,0.001560224,0.0001519556,0.08101198],"genre_scores_gemma":[0.2628909,0.6019635,0.01633935,0.0825986,0.0110204,0.0002800742,0.001949935,0.0003647647,0.02259246],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01651415,"threshold_uncertainty_score":0.08733624,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}