{"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"},"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009298171,0.0001719667,0.000471165,0.0002023614,0.0003761721,0.0001892167,0.0005610075,0.00002468832,0.0002205096],"category_scores_gemma":[0.000181724,0.0001519818,0.00008339222,0.0007334145,0.0001690274,0.0008913937,0.0004271677,0.0001063686,0.0003861588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009464934,"about_ca_system_score_gemma":0.00005740831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001222784,"about_ca_topic_score_gemma":0.001949362,"domain_scores_codex":[0.9982867,0.00001237846,0.0004459409,0.0008048568,0.00006909014,0.0003810633],"domain_scores_gemma":[0.9988109,0.00008777108,0.0001220373,0.0008187035,0.0000358413,0.0001247613],"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":[0.00001060733,0.000118831,0.01713679,0.02247106,0.0001865933,0.000009245267,0.0007666974,7.461655e-7,0.00002130857,0.1479037,0.5840291,0.2273454],"study_design_scores_gemma":[0.00006605892,0.00001797192,0.006106639,0.001704849,0.00004096961,0.000004609405,0.00003322426,0.0004619916,0.000001686661,0.001438177,0.9899378,0.0001859784],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001083969,0.9544646,0.0007182815,0.03204933,0.002552497,0.0009511679,0.004002891,0.0001365412,0.004040786],"genre_scores_gemma":[0.002281938,0.994312,0.001304868,0.0003949652,0.0005982385,0.00008964306,0.00005515569,0.00001872759,0.0009444559],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4059088,"threshold_uncertainty_score":0.619764,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003094924,0.0001186795,0.0001861299,0.0001316695,0.0003576565,0.001048501,0.0007738419,0.00002325938,0.0002595436],"category_scores_gemma":[0.0001449678,0.0000954576,0.00003576015,0.0006635477,0.0002771638,0.005150991,0.0001187494,0.00009867291,0.002362094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007143326,"about_ca_system_score_gemma":0.00008595153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008245239,"about_ca_topic_score_gemma":0.00001023436,"domain_scores_codex":[0.9983459,0.0000082702,0.0008744707,0.0004415561,0.00008030573,0.0002495196],"domain_scores_gemma":[0.999258,0.00009024968,0.0001066448,0.0004341835,0.00003091657,0.0000799843],"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":[0.000001169518,0.000005801409,0.00003223691,0.0004892091,0.000007549967,3.920564e-7,0.0004102588,0.000003530376,0.000001458386,0.6106782,0.0003827124,0.3879875],"study_design_scores_gemma":[0.000019073,0.00001781065,0.0003162884,0.001137861,0.00001262595,0.00002082571,0.0002406338,0.02522876,0.0002778899,0.097722,0.874724,0.0002822141],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.004243881,0.2582699,0.3868949,0.01625395,0.004912856,0.003511627,0.00118579,0.0004195935,0.3243075],"genre_scores_gemma":[0.4842326,0.5120512,0.002141552,0.0006997079,0.0001210292,0.00008004207,0.0002710629,0.00001885914,0.0003839908],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.8743413,"threshold_uncertainty_score":0.9999885,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009840042,0.0001134249,0.0002129471,0.0001974052,0.0009343359,0.00005732999,0.001509724,0.00003665907,0.004340237],"category_scores_gemma":[0.006457493,0.00008100081,0.00001621472,0.003087141,0.0003588386,0.002241161,0.0006784991,0.0004349449,0.08477777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002642397,"about_ca_system_score_gemma":0.002675481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000156063,"about_ca_topic_score_gemma":0.00001975582,"domain_scores_codex":[0.9967688,0.0004249819,0.000350005,0.0006400966,0.001231611,0.0005844865],"domain_scores_gemma":[0.9966175,0.0006233743,0.0002250483,0.001947434,0.0003376783,0.0002489695],"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":[0.00009179147,0.0002815633,0.05820413,0.01176847,0.00003317377,0.00004034673,0.002487469,0.000003905929,0.0004672471,0.02153959,0.7660674,0.1390149],"study_design_scores_gemma":[0.0001997062,0.00005346709,0.05060159,0.00320812,0.00002578023,0.000005149747,0.0008535639,0.0002875531,0.000009688245,0.00011162,0.944522,0.0001218221],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"review","genre_scores_codex":[0.2046859,0.02092548,0.001771836,0.3038434,0.01656822,0.04607164,0.004616072,0.00375353,0.397764],"genre_scores_gemma":[0.1747547,0.6938335,0.002785293,0.0787685,0.001189512,0.00238856,0.01056194,0.0002223123,0.03549568],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.6729081,"threshold_uncertainty_score":0.9965699,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01276404,0.0002901242,0.0006117942,0.0002937549,0.0006115463,0.001858449,0.006373471,0.00004906009,0.002279165],"category_scores_gemma":[0.008162572,0.000182146,0.0003173643,0.004676575,0.0004798172,0.002885684,0.003285018,0.00035756,0.02124036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002459989,"about_ca_system_score_gemma":0.0003928393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002806229,"about_ca_topic_score_gemma":0.00007693882,"domain_scores_codex":[0.9907728,0.0002056713,0.001179786,0.001921075,0.005302015,0.0006186007],"domain_scores_gemma":[0.9942906,0.0006083571,0.0001810619,0.004132807,0.0003834006,0.0004036959],"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":[0.000003021168,0.00005067049,0.0001903316,0.0003037854,0.000009374489,0.00004628603,0.0001963631,0.00000307411,0.00002854254,0.003648924,0.41962,0.5758996],"study_design_scores_gemma":[0.00004804217,0.00005980326,0.002548475,0.006367806,0.0001059273,0.00004270952,0.000592051,0.000129924,0.00001180305,0.000796187,0.9890572,0.0002400792],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.004581599,0.5995319,0.1306285,0.1913414,0.03510955,0.007129094,0.01568632,0.00113918,0.01485242],"genre_scores_gemma":[0.6276546,0.2813161,0.03701887,0.03668421,0.004021058,0.0003975951,0.0003613487,0.00017444,0.01237178],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.623073,"threshold_uncertainty_score":0.9991777,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01742361,0.000156847,0.0003240411,0.000136058,0.0001596961,0.0005984019,0.01602822,0.00004211215,0.0001005945],"category_scores_gemma":[0.001285422,0.0001049846,0.00002234579,0.003614072,0.0001943361,0.008180785,0.004133427,0.0003452192,0.001302945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005067093,"about_ca_system_score_gemma":0.0009145419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000498924,"about_ca_topic_score_gemma":0.0000403679,"domain_scores_codex":[0.9964851,0.0002812791,0.0004836367,0.001249628,0.000928582,0.0005718398],"domain_scores_gemma":[0.9935037,0.0001466668,0.0001959476,0.005966259,0.00006702739,0.0001203793],"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":[0.000005240895,0.0002786911,0.01635727,0.004283177,0.00000759969,0.00005842178,0.00112775,0.00001307534,0.000599472,0.1006321,0.0897145,0.7869227],"study_design_scores_gemma":[0.0001735072,0.00001788739,0.01147856,0.003789786,0.00001082526,0.0000319126,0.00003160869,0.03013577,0.00001307251,0.0005885107,0.953468,0.0002606019],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03392798,0.16264,0.5854682,0.1834429,0.005077125,0.009701144,0.0012906,0.0006386189,0.01781343],"genre_scores_gemma":[0.7618012,0.1007641,0.06466085,0.07015685,0.0004818247,0.0001167551,0.00166539,0.00004241146,0.0003106362],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8637534,"threshold_uncertainty_score":0.9994746,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005918182,0.00007893746,0.0001376815,0.00007464103,0.0001430678,0.00008277071,0.000385216,0.00002081856,0.0001344396],"category_scores_gemma":[0.001637401,0.0000680292,0.00001285317,0.001200766,0.0002301767,0.002220065,0.0001612229,0.00009765709,0.0001789891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004023798,"about_ca_system_score_gemma":0.00004623983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008917291,"about_ca_topic_score_gemma":0.000005150107,"domain_scores_codex":[0.9983351,0.00002877884,0.0002689758,0.0009932687,0.0002055797,0.0001682447],"domain_scores_gemma":[0.9960387,0.00001435492,0.00003120255,0.003752819,0.00007969008,0.0000832699],"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":[0.000001035577,0.000003658923,0.0005533761,0.001349468,0.000002965939,4.364061e-7,0.00003143125,0.00005919372,0.003637616,0.004577717,0.0126445,0.9771386],"study_design_scores_gemma":[0.00004748447,0.00002559451,0.007686118,0.0003006065,0.00003014001,0.00007124254,0.00004674256,0.04515906,0.001122662,0.0006863567,0.9446188,0.000205219],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8244354,0.04693706,0.02956281,0.03968604,0.01709881,0.008303,0.0009130643,0.01671887,0.01634498],"genre_scores_gemma":[0.6624819,0.3185297,0.01358614,0.0008819402,0.002304201,0.0002126525,0.001448252,0.00007668198,0.000478575],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9769334,"threshold_uncertainty_score":0.277415,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.008293966,0.0001104844,0.0002383523,0.0001976387,0.0002527042,0.0003439317,0.006092518,0.00001510807,0.00003674283],"category_scores_gemma":[0.002471406,0.00007211018,0.000008522559,0.001272505,0.001542961,0.009279613,0.003164242,0.00009037178,0.00001470591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008932981,"about_ca_system_score_gemma":0.0003677697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000755506,"about_ca_topic_score_gemma":0.0001152905,"domain_scores_codex":[0.9982775,0.0000121413,0.0003435151,0.0006248449,0.0004741128,0.0002679066],"domain_scores_gemma":[0.9970082,0.0001761328,0.0001793631,0.002295871,0.0003296751,0.00001076204],"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":[0.000001954876,0.00002461071,0.00005048674,0.003890155,0.000001526069,0.000001156212,0.00001003371,7.922451e-8,0.0000189398,0.2837306,0.009051923,0.7032185],"study_design_scores_gemma":[0.00006086253,0.00000380167,0.002844325,0.003174435,0.00006055666,0.000002517191,0.0002794252,0.00371035,0.000006442098,0.002525595,0.9872217,0.0001100529],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001883562,0.6548253,0.08905501,0.1414414,0.00344227,0.009623018,0.01208381,0.0001976418,0.087448],"genre_scores_gemma":[0.02977265,0.9527848,0.007738712,0.008486386,0.000147319,0.00004462032,0.0009802054,0.000008668784,0.00003659427],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9781697,"threshold_uncertainty_score":0.999285,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.02344427,0.000129059,0.0002972903,0.0003094508,0.001021791,0.000716537,0.03529165,0.000008249886,0.0001816653],"category_scores_gemma":[0.01055081,0.0000927673,0.00002135665,0.009609573,0.001932778,0.01561365,0.03012978,0.0002524861,0.0001620985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001978013,"about_ca_system_score_gemma":0.004095063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001518646,"about_ca_topic_score_gemma":0.00007364167,"domain_scores_codex":[0.992788,0.0003231901,0.0007031405,0.001548355,0.004092944,0.0005444046],"domain_scores_gemma":[0.9898822,0.001019931,0.0003475378,0.008180021,0.0004026288,0.0001676646],"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":[0.000009065026,0.0002519139,0.0006481833,0.0003156221,0.00001531006,0.00003698084,0.00006783066,0.0002040997,0.0004850687,0.4901627,0.1639879,0.3438154],"study_design_scores_gemma":[0.00005752272,0.00001669986,0.001741486,0.0001329102,0.00001246928,0.00003052592,0.00000733566,0.2161016,0.000004982679,0.000184643,0.7815948,0.0001150426],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006442209,0.02244198,0.9086236,0.02025857,0.002729475,0.004388968,0.03681201,0.0003021474,0.003799069],"genre_scores_gemma":[0.0461474,0.0802732,0.857308,0.01159403,0.0001065695,0.0002032689,0.004095652,0.00003635579,0.0002354696],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6176069,"threshold_uncertainty_score":0.9981545,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01520452,0.0001806796,0.0004279747,0.0004731114,0.000264294,0.001361394,0.01171219,0.00005730332,0.003762689],"category_scores_gemma":[0.01391485,0.0001375681,0.00002472908,0.007387759,0.0002084989,0.009244401,0.007072378,0.0002128551,0.0151168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001073331,"about_ca_system_score_gemma":0.0003832127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001754103,"about_ca_topic_score_gemma":0.00008713342,"domain_scores_codex":[0.994378,0.0003979357,0.001002311,0.001835224,0.002012671,0.0003738707],"domain_scores_gemma":[0.9913082,0.0004960886,0.0001957989,0.007633305,0.000241165,0.0001254568],"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":[0.000006683358,0.0001018046,0.00006921301,0.0001554524,0.000006479927,0.000007522959,0.00004072033,0.00006766745,0.00001101887,0.09815302,0.6566022,0.2447782],"study_design_scores_gemma":[0.0001213541,0.0000176545,0.0008921414,0.002360533,0.00001945094,8.180194e-7,0.00004264775,0.002341711,0.00001222854,0.005505571,0.9885294,0.0001564177],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.001857673,0.01645766,0.2102841,0.4164377,0.004368391,0.01512971,0.03695855,0.0004718614,0.2980343],"genre_scores_gemma":[0.03491804,0.10081,0.1597218,0.5483087,0.0007956866,0.0006892511,0.04794962,0.0001214405,0.1066855],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.3319273,"threshold_uncertainty_score":0.9996753,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01052821,0.00009779503,0.0001769289,0.00004149961,0.002314687,0.001014186,0.002839674,0.00002862924,0.00007005289],"category_scores_gemma":[0.004641918,0.00005487736,0.00002321435,0.001846469,0.001392974,0.001809103,0.0003947277,0.0003611564,0.00003475251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001167352,"about_ca_system_score_gemma":0.002093107,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1944916,"about_ca_topic_score_gemma":0.6467139,"domain_scores_codex":[0.9979199,0.0004443353,0.0002263649,0.0004199905,0.0005002242,0.0004892152],"domain_scores_gemma":[0.9984381,0.0005008598,0.00008595752,0.0007567011,0.00008473721,0.0001336019],"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":[0.000001684777,0.00002513708,0.02183512,0.0005420264,0.00001041853,0.00001061011,0.03429788,3.034883e-7,0.000006795792,0.3372995,0.01513337,0.5908371],"study_design_scores_gemma":[0.00003761701,0.000004120006,0.004012678,0.001938039,0.00002102504,0.000003726995,0.01024564,0.0001847975,0.000001070776,0.0003489756,0.983115,0.00008737589],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.02294831,0.1694448,0.0001580648,0.6664194,0.0006259857,0.004179337,0.0001493271,0.00007329763,0.1360015],"genre_scores_gemma":[0.975378,0.01956181,0.0001636353,0.004750344,0.00005175307,0.00003864554,0.00001212849,0.000002597573,0.00004113047],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9679816,"threshold_uncertainty_score":0.9989842,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006343241,0.0002049438,0.0002574095,0.0001871871,0.000575754,0.001318557,0.00814305,0.00003507293,0.0002588726],"category_scores_gemma":[0.001250554,0.0001353294,0.00008208959,0.005306665,0.0004342335,0.008220511,0.002836374,0.0003307462,0.006335052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001491192,"about_ca_system_score_gemma":0.0007211705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000924201,"about_ca_topic_score_gemma":0.00002077043,"domain_scores_codex":[0.9964877,0.0001225951,0.000497275,0.001248897,0.0009891655,0.0006543495],"domain_scores_gemma":[0.9951817,0.0002099203,0.00008257289,0.004137822,0.0002104397,0.0001775056],"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":[3.411185e-7,0.00002692971,0.00003603183,0.0009802855,0.00001067502,0.00003181087,0.0003181082,0.00001720862,0.001158578,0.1521634,0.1805523,0.6647043],"study_design_scores_gemma":[0.00000842393,0.0000170925,0.00005534928,0.002751827,0.00001789513,0.00004345911,0.00001553434,0.2189485,0.0009498262,0.00248461,0.7745386,0.0001688263],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.00009748259,0.08522278,0.8624473,0.04437024,0.001876865,0.001089006,0.00004784547,0.0006322328,0.004216209],"genre_scores_gemma":[0.06089101,0.8160458,0.07485501,0.04480279,0.0007844145,0.0002502937,0.0000781731,0.00007508175,0.002217488],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7875924,"threshold_uncertainty_score":0.9997182,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.004429432,0.0003393341,0.0004681728,0.0002570252,0.000331111,0.001269109,0.1926206,0.00007887654,0.0001139342],"category_scores_gemma":[0.02056331,0.0002091211,0.00003520507,0.003908,0.000784192,0.01237544,0.3820584,0.0005501868,0.0009407089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007870257,"about_ca_system_score_gemma":0.0008234417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001541299,"about_ca_topic_score_gemma":0.000006976814,"domain_scores_codex":[0.9942278,0.0001166108,0.0005348664,0.00290543,0.001482012,0.0007333232],"domain_scores_gemma":[0.9315095,0.0001973453,0.0001902381,0.06775735,0.0001253921,0.0002202032],"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":[0.000003205243,0.00005936872,0.00007034187,0.002599328,0.00003158922,0.0001918458,0.00001040421,4.186759e-7,0.000967138,0.008105271,0.479296,0.5086651],"study_design_scores_gemma":[0.00007399735,0.00004218098,0.0001070108,0.01233523,0.00004640112,0.0001085958,0.000001127974,0.3310303,0.0002103789,0.003379811,0.6523378,0.0003271528],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001960151,0.04428541,0.9041715,0.04418037,0.00134761,0.001140025,0.001140416,0.003033341,0.0005052958],"genre_scores_gemma":[0.002247533,0.1784386,0.8168365,0.0009114912,0.0001316694,0.00002890848,0.001312232,0.00003319291,0.00005983409],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.508338,"threshold_uncertainty_score":0.9998372,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002038368,0.0001020252,0.0001778907,0.00007476928,0.0004219495,0.0002029176,0.002669481,0.00002561824,0.0129709],"category_scores_gemma":[0.0003016304,0.00007882791,0.00003925592,0.001515905,0.0005115775,0.001219663,0.000657352,0.0002376394,0.01403635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006131183,"about_ca_system_score_gemma":0.0005904905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001584178,"about_ca_topic_score_gemma":0.0000388489,"domain_scores_codex":[0.9982133,0.0001383763,0.0003469494,0.0006476864,0.0003314853,0.0003221864],"domain_scores_gemma":[0.9968035,0.0001775306,0.00007677614,0.002734483,0.00008644891,0.0001213284],"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":[7.455915e-7,0.00005458864,0.0005275832,0.001332684,0.00001224176,0.00000415958,0.002940309,9.028656e-8,0.00001906933,0.2254868,0.4339018,0.3357199],"study_design_scores_gemma":[0.00001641816,0.000009822579,0.00228295,0.002380466,0.00002180619,0.00003231081,0.0005590391,0.00005089926,8.514905e-7,0.0003330336,0.9942135,0.00009888132],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002174972,0.6197724,0.002193698,0.07027858,0.00845096,0.000933998,0.0003511045,0.0004830773,0.2973186],"genre_scores_gemma":[0.07043683,0.8879127,0.01256324,0.01787613,0.0005030489,0.0003129515,0.000545037,0.00003703434,0.009813054],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5603117,"threshold_uncertainty_score":0.9879314,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005328293,0.0003678574,0.000970688,0.0001840144,0.0002960386,0.0009965481,0.003562409,0.0001489691,0.004157988],"category_scores_gemma":[0.03011395,0.0003138957,0.00007876779,0.0004858209,0.0007590405,0.001307394,0.002931772,0.0006994878,0.0004925373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002133821,"about_ca_system_score_gemma":0.002025586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001167483,"about_ca_topic_score_gemma":0.00008073721,"domain_scores_codex":[0.9955972,0.0007503927,0.0007100989,0.001675095,0.0008346872,0.0004325599],"domain_scores_gemma":[0.9909022,0.002696558,0.0005351464,0.005031225,0.0005500508,0.0002847544],"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":[0.000005356767,0.0004730379,0.0001301052,0.009808996,0.0000944532,0.00001738727,0.0007794744,0.000001671458,0.00001533411,0.3701014,0.4750051,0.1435677],"study_design_scores_gemma":[0.0001269354,0.00001883881,0.005227458,0.02961453,0.0009266466,0.000008280336,0.001503474,0.001187913,0.00001447575,0.4438809,0.5167221,0.0007683837],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003538575,0.07515152,0.7963198,0.00557072,0.0224403,0.003630915,0.09285996,0.0006217571,0.003051109],"genre_scores_gemma":[0.00005539654,0.3435973,0.6507672,0.001241632,0.0002233235,0.0001318155,0.003351903,0.00001893852,0.0006124747],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2684458,"threshold_uncertainty_score":0.9999313,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007354282,0.00008454031,0.0002563568,0.00007976666,0.00008811364,0.0000679701,0.001304102,0.00001835404,0.0001678478],"category_scores_gemma":[0.0120783,0.00006785514,0.00001394957,0.001036207,0.0002981852,0.0004835382,0.000252905,0.00009556715,0.0001283364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005559475,"about_ca_system_score_gemma":0.0008602187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003385193,"about_ca_topic_score_gemma":0.00006966185,"domain_scores_codex":[0.9985283,0.0002915775,0.0003182796,0.0004089827,0.0002368363,0.0002160093],"domain_scores_gemma":[0.9973278,0.000647706,0.00009283228,0.001755698,0.0001046806,0.00007130247],"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":[0.000001370195,0.0001795125,0.001192856,0.001899374,0.000004645317,0.000003016188,0.0000374683,2.464366e-7,0.00008236063,0.7852187,0.146229,0.06515151],"study_design_scores_gemma":[0.0001600463,0.00001557136,0.01100921,0.003460703,0.0001094253,0.00000676914,0.000165485,0.0005592922,0.0001118784,0.4219846,0.562195,0.00022205],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005872179,0.05276747,0.7645779,0.06835255,0.01113776,0.007415919,0.003621598,0.001042251,0.08521243],"genre_scores_gemma":[0.01605153,0.1717,0.8022621,0.007640671,0.00005955293,0.00009692985,0.0003327576,0.00001905216,0.001837407],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.415966,"threshold_uncertainty_score":0.9962434,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.02494943,0.0001403298,0.0003233534,0.0001464871,0.0006653403,0.001233736,0.03371926,0.00001612514,0.00004206243],"category_scores_gemma":[0.008746939,0.00007877979,0.00002584274,0.007435407,0.000992078,0.006885674,0.00936281,0.000196468,0.0001173512],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008736226,"about_ca_system_score_gemma":0.007340629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000619069,"about_ca_topic_score_gemma":0.0001680546,"domain_scores_codex":[0.9949085,0.000405248,0.0007272977,0.001456689,0.001980061,0.0005222638],"domain_scores_gemma":[0.9847987,0.0007583501,0.0003406215,0.01347019,0.0004926841,0.0001394432],"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":[8.255843e-7,0.0001824908,0.0004794633,0.0006235457,0.00001007641,0.00001981263,0.0001003591,0.000005810746,0.001073619,0.410523,0.03015772,0.5568233],"study_design_scores_gemma":[0.00007308503,0.00001615968,0.002400703,0.002481626,0.00006618269,0.0001885063,0.0001715993,0.08350869,0.0002873335,0.0009230645,0.9096445,0.0002385271],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002442169,0.08978606,0.8661001,0.02313457,0.003295935,0.002952287,0.003411936,0.0001353773,0.008741581],"genre_scores_gemma":[0.2495193,0.2186564,0.5224229,0.007307416,0.0003204093,0.0001180174,0.001489741,0.00003035612,0.0001355925],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8794868,"threshold_uncertainty_score":0.9998031,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00155858,0.00004322384,0.0000812977,0.00002758643,0.0003039276,0.0002530451,0.0006048257,0.00001145446,0.0001663243],"category_scores_gemma":[0.0000918254,0.00002757387,0.00001025775,0.0001522493,0.0005796427,0.0003725618,0.0002093094,0.00009509964,0.00002106066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008677883,"about_ca_system_score_gemma":0.00004947751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003710137,"about_ca_topic_score_gemma":0.0001963381,"domain_scores_codex":[0.9994236,0.00002213513,0.0001407948,0.0001944796,0.0001113831,0.0001076108],"domain_scores_gemma":[0.9994442,0.00002774795,0.00002627284,0.0004599302,0.00003303239,0.000008858086],"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":[5.151871e-8,0.00001005847,0.0001414515,0.0001348173,0.000001431549,6.203029e-7,0.0004817425,3.593201e-8,0.00002976374,0.8844914,0.03258191,0.08212672],"study_design_scores_gemma":[0.00003117379,0.000004449021,0.00028534,0.0004342552,0.00001306044,0.000001797731,0.0003890765,0.0006676054,0.000005249032,0.001379726,0.9967488,0.00003947579],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.08765728,0.3604715,0.0009847513,0.2072148,0.002290728,0.004432869,0.0008116378,0.0003251152,0.3358113],"genre_scores_gemma":[0.803207,0.1702753,0.0005025445,0.02536277,0.0001786864,0.00003767719,0.00009592729,0.000004170044,0.000335949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9641669,"threshold_uncertainty_score":0.244012,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007776748,0.00007913492,0.0001867972,0.00005218383,0.0003405598,0.00008302239,0.004071784,0.00002079645,0.00009452888],"category_scores_gemma":[0.001522085,0.00003697127,0.00003537826,0.002578766,0.001417474,0.0004303645,0.000873219,0.0001497116,0.00004895069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006112895,"about_ca_system_score_gemma":0.0006237768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009841471,"about_ca_topic_score_gemma":0.0004812214,"domain_scores_codex":[0.9981015,0.0003140921,0.0003435831,0.0003382629,0.000529022,0.0003735104],"domain_scores_gemma":[0.9975098,0.0002549035,0.00005626055,0.001974459,0.0001710835,0.00003343118],"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":[0.000006481551,0.00007355882,0.000584661,0.001222446,0.000005510236,0.000004268295,0.00003422667,0.00003440769,0.00002926327,0.4927525,0.007352023,0.4979006],"study_design_scores_gemma":[0.00005764121,0.0000139504,0.001638666,0.0008121722,0.000008410741,0.000003027475,0.0001590512,0.0002580464,0.00004374397,0.01028616,0.986675,0.00004410813],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.005815123,0.1879584,0.0004232498,0.1340152,0.0004497532,0.004428322,0.0001527375,0.00009512393,0.6666621],"genre_scores_gemma":[0.5132052,0.4792365,0.001595278,0.004597136,0.00004519671,0.0002119596,0.00008251011,0.00001173847,0.001014468],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.979323,"threshold_uncertainty_score":0.7566455,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}