{"meta":{"query_hash":"627b644e1b00","filters":{"venue":"Journal of Data Mining & Digital Humanities"},"cohort_total":6,"direct_labels_cover":0,"predictions_cover":6,"exported":6,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/627b644e1b00","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Data+Mining+%26+Digital+Humanities"},"results":[{"id":"W2802812759","doi":"10.46298/jdmdh.4457","title":"Prosopographical data analysis. Application to the Angevin officers (XIII–XV centuries)","year":2018,"lang":"en","type":"article","venue":"Journal of Data Mining & Digital Humanities","topic":"Medieval European Literature and History","field":"Arts and Humanities","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Agence Nationale de la Recherche","keywords":"Prosopography; Relation (database); Online analytical processing; History; Visualization; Classics; Data science; Computer science; Database; Data warehouse; Data mining","score_opus":0.10256588130227359,"score_gpt":0.2855709712024714,"score_spread":0.1830050899001978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802812759","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13910143,0.009356389,0.0039749728,0.005642741,0.006955252,0.001395467,0.019368704,0.00029573918,0.8139093],"genre_scores_gemma":[0.98005396,0.00005274824,0.0005457561,0.0018679907,0.009256097,0.0000032146256,0.0021618642,0.000042320225,0.006016067],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99814194,0.00006591727,0.00064520875,0.00035267437,0.0005490309,0.00024521802],"domain_scores_gemma":[0.9972888,0.00013925639,0.00045855687,0.0015821505,0.00042075384,0.000110468216],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007861331,0.00019321647,0.00033583996,0.0004529327,0.00055789,0.0016138677,0.0025635753,0.000031628886,0.00033661697],"category_scores_gemma":[0.00019156406,0.00012733781,0.000110054185,0.00020351881,0.00076320616,0.002917652,0.0007036751,0.0002617799,0.00009219533],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026284138,0.0002198463,0.00031353178,0.00005700948,0.0012760321,0.000029682338,0.09382171,0.000002396993,0.000009788089,0.04093117,0.8315885,0.031487484],"study_design_scores_gemma":[0.00013749061,0.0002898324,0.00028361913,0.000056307865,0.00045668267,0.000011910641,0.009197361,0.00007336084,0.0000015637893,0.000052568346,0.98927754,0.00016177286],"about_ca_topic_score_codex":0.000023251017,"about_ca_topic_score_gemma":0.0014819615,"teacher_disagreement_score":0.8409525,"about_ca_system_score_codex":0.000028964081,"about_ca_system_score_gemma":0.00009604775,"threshold_uncertainty_score":0.99942255},"labels":[],"label_agreement":null},{"id":"W3125727712","doi":"10.46298/jdmdh.21","title":"Deception in Speeches of Candidates for Public Office","year":2015,"lang":"en","type":"article","venue":"Journal of Data Mining & Digital Humanities","topic":"Media Influence and Politics","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada; Queen's University","funders":"","keywords":"Deception; Persona; Subconscious; Perception; Psychology; Presidential system; Skepticism; Social psychology; Perspective (graphical); Politics; Cognitive psychology; Computer science; Political science; Epistemology; Artificial intelligence; Human–computer interaction; Law; Philosophy","score_opus":0.3966178400552383,"score_gpt":0.39901415041545907,"score_spread":0.0023963103602207547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125727712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97806066,0.00024465244,0.0000554257,0.00025790892,0.0003084891,0.0000728417,0.000272306,0.0000060905163,0.020721609],"genre_scores_gemma":[0.9977703,0.000055119093,0.0011049078,0.00006284551,0.0004948216,9.599231e-7,0.000069849535,0.000005947741,0.00043521886],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989525,0.000035922796,0.00040191915,0.00006853428,0.00034571957,0.00019538327],"domain_scores_gemma":[0.99868006,0.0004193857,0.00032801423,0.00013529518,0.0003443264,0.00009289389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010941963,0.000060139606,0.00017620664,0.0001946278,0.00006190549,0.00026105545,0.00053834246,0.000042933352,0.000018952109],"category_scores_gemma":[0.0025956838,0.00005437464,0.000032000604,0.00009754,0.00025990605,0.0035079792,0.000063528765,0.00007055189,0.00000383729],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004599814,0.0006912299,0.27613705,0.00031004447,0.0002199295,0.00005648406,0.3427959,0.000014496659,0.00007691305,0.11304658,0.13420266,0.13198873],"study_design_scores_gemma":[0.0009583226,0.00053958094,0.0018594256,0.00030345342,0.000038485807,0.00001567626,0.25912288,0.000040027004,0.0001289653,0.0060208025,0.73075235,0.00022004097],"about_ca_topic_score_codex":0.00027962108,"about_ca_topic_score_gemma":0.0023190046,"teacher_disagreement_score":0.5965497,"about_ca_system_score_codex":0.00006611968,"about_ca_system_score_gemma":0.000632474,"threshold_uncertainty_score":0.31074634},"labels":[],"label_agreement":null},{"id":"W4225331178","doi":"10.46298/jdmdh.9123","title":"Towards an empirical evaluation of translated texts and translation quality","year":2022,"lang":"en","type":"article","venue":"Journal of Data Mining & Digital Humanities","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Machine translation; Natural language processing; Phraseology; Source text; Artificial intelligence; Context (archaeology); Quality (philosophy); Translation (biology); Linguistics","score_opus":0.27107377730309534,"score_gpt":0.42736644358020137,"score_spread":0.15629266627710603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225331178","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9242461,0.0077083576,0.066032365,0.0004072322,0.00016165804,0.00015288961,0.0002706218,0.00009354719,0.00092726917],"genre_scores_gemma":[0.9216195,0.0000055978953,0.07821501,0.000043789423,0.000036250687,0.0000013762826,0.00006556122,0.00000610572,0.0000068356344],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99805874,0.0002118633,0.0005065902,0.00017524812,0.0009491388,0.00009844533],"domain_scores_gemma":[0.99884355,0.00010443584,0.0004080652,0.00032519066,0.00028372803,0.000035014327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022683837,0.000089087276,0.00019532845,0.00020922393,0.0001271307,0.00031332715,0.0010402331,0.000027050615,0.00001729089],"category_scores_gemma":[0.00011666883,0.000079894955,0.00003420454,0.00017320337,0.000070560454,0.0055226777,0.00021549096,0.00018336091,7.177104e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043674427,0.00011239367,0.0003142122,0.000032409138,0.000029320197,0.000007852225,0.015313401,0.000012240027,0.00033115235,0.0009197293,0.00015753813,0.9827261],"study_design_scores_gemma":[0.013693294,0.01543895,0.037668757,0.0013143623,0.0012708674,0.00422514,0.039372295,0.400887,0.014369007,0.4404227,0.027445616,0.0038920084],"about_ca_topic_score_codex":0.000011233488,"about_ca_topic_score_gemma":0.000010453335,"teacher_disagreement_score":0.9788341,"about_ca_system_score_codex":0.000041140873,"about_ca_system_score_gemma":0.00021305462,"threshold_uncertainty_score":0.40038082},"labels":[],"label_agreement":null},{"id":"W4392910228","doi":"10.46298/jdmdh.10403","title":"Exploring Data Provenance in Handwritten Text Recognition Infrastructure: Sharing and Reusing Ground Truth Data, Referencing Models, and Acknowledging Contributions. Starting the Conversation on How We Could Get It Done","year":2024,"lang":"en","type":"article","venue":"Journal of Data Mining & Digital Humanities","topic":"Research Data Management Practices","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Conversation; Ground truth; Reuse; Provenance; Computer science; Natural language processing; Artificial intelligence; Linguistics; Engineering; Geology; Philosophy","score_opus":0.5182855834595688,"score_gpt":0.37307797120339903,"score_spread":0.14520761225616974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392910228","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6941439,0.010354542,0.26151255,0.024067577,0.001660892,0.0010356234,0.0047808816,0.000212003,0.0022320622],"genre_scores_gemma":[0.9879782,0.005518936,0.005112689,0.00007129106,0.00030707192,0.000004623175,0.0009487867,0.000019348176,0.000039034123],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771106,0.00011004534,0.00053824513,0.00073402404,0.00058149715,0.00032511578],"domain_scores_gemma":[0.9965087,0.0011870145,0.00044571116,0.0016302295,0.00016598383,0.00006234945],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0034401396,0.00019205663,0.0002423827,0.0004447706,0.000351121,0.017599657,0.0032991015,0.000035748602,0.0000015834622],"category_scores_gemma":[0.002423241,0.00015232868,0.000013164649,0.0003085408,0.00013613395,0.20386626,0.0063924477,0.0006116889,0.0000010933403],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002270673,0.000110890716,0.0007111778,0.0013007801,0.00051886804,0.00053507095,0.021737373,0.0002424033,0.00016729994,0.041713834,0.007090257,0.925645],"study_design_scores_gemma":[0.0011091054,0.00027311128,0.00087165367,0.006784629,0.00013009296,0.0002364449,0.038203247,0.9148959,0.000046847148,0.011119175,0.025805123,0.00052468525],"about_ca_topic_score_codex":0.000044003016,"about_ca_topic_score_gemma":0.00012431979,"teacher_disagreement_score":0.9251203,"about_ca_system_score_codex":0.00012948981,"about_ca_system_score_gemma":0.00015132342,"threshold_uncertainty_score":0.9834202},"labels":[],"label_agreement":null},{"id":"W4394803700","doi":"10.46298/jdmdh.10542","title":"The Challenges of HTR Model Training: Feedback from the Project Donner le gout de l'archive a l'ere numerique","year":2023,"lang":"en","type":"article","venue":"Journal of Data Mining & Digital Humanities","topic":"Mathematics, Computing, and Information Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski; Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada; Université de Montréal; Université de Sherbrooke; Université du Québec à Rimouski","keywords":"Training (meteorology); Gout; Psychology; Computer science; Physical medicine and rehabilitation; Medicine; Physics; Internal medicine; Meteorology","score_opus":0.1937526202284116,"score_gpt":0.3030778760184903,"score_spread":0.10932525579007868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394803700","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16785483,0.0030766733,0.7295034,0.005982498,0.00075815216,0.0004279931,0.00055176695,0.00028792967,0.091556765],"genre_scores_gemma":[0.9690569,0.00031391217,0.029809237,0.00015635022,0.00029937574,0.0000034136367,0.000025228814,0.00001952593,0.00031606914],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985312,0.000050997023,0.0006555007,0.00013389815,0.0003843599,0.00024399333],"domain_scores_gemma":[0.9974395,0.0010073695,0.00080536574,0.0005527225,0.0001610702,0.000033985623],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010484016,0.00013345866,0.00022987918,0.00010968251,0.00037815492,0.0011389365,0.0025983106,0.000029915227,0.0000011586066],"category_scores_gemma":[0.00040605527,0.000079177975,0.00007862596,0.00013286428,0.0001762347,0.0036726505,0.0007468448,0.00020232092,0.000003527266],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025426956,0.00007130602,0.000038710554,0.00016974474,0.00020906806,0.000012287183,0.6311435,0.0011923298,0.000019993386,0.15763384,0.019538268,0.18994553],"study_design_scores_gemma":[0.000406301,0.00013575022,0.00015305981,0.0007466994,0.000019325846,0.000103161154,0.15565924,0.757216,0.0000570839,0.073204935,0.012074499,0.00022397743],"about_ca_topic_score_codex":0.000016142987,"about_ca_topic_score_gemma":0.000029235,"teacher_disagreement_score":0.80120206,"about_ca_system_score_codex":0.000017437773,"about_ca_system_score_gemma":0.00054317986,"threshold_uncertainty_score":0.99989796},"labels":[],"label_agreement":null},{"id":"W4402821732","doi":"10.46298/jdmdh.12520","title":"Temporal Sequencing of Documents","year":2024,"lang":"en","type":"article","venue":"Journal of Data Mining & Digital Humanities","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Computational biology; Information retrieval; Biology","score_opus":0.1301717141655876,"score_gpt":0.31885139752208425,"score_spread":0.18867968335649665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402821732","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8803372,0.008195013,0.0669428,0.0005451368,0.003273624,0.000107780856,0.00018343747,0.00021336121,0.04020167],"genre_scores_gemma":[0.9839544,0.000034828994,0.015398554,0.000036323694,0.0001638438,2.179954e-7,0.000010007262,0.0000068470326,0.00039494096],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988279,0.000016118442,0.00048421364,0.00015816615,0.00036166512,0.0001519904],"domain_scores_gemma":[0.9990243,0.00021180394,0.00022024213,0.00041857714,0.00009335241,0.00003177128],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00034808138,0.000100867896,0.00021946442,0.00024035672,0.00004436528,0.0011066514,0.0016683448,0.000026137468,0.00001056548],"category_scores_gemma":[0.00011389525,0.00007754767,0.00006574588,0.00013113956,0.00009606294,0.007824013,0.00060056825,0.000115435396,0.0000072922717],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064217274,0.00023353612,0.013219769,0.0011476561,0.0011844902,0.003910232,0.03850044,0.000039939194,0.00093916693,0.16136435,0.067735866,0.7116603],"study_design_scores_gemma":[0.004350022,0.008141015,0.019992622,0.019969022,0.00072667334,0.013847131,0.12123333,0.056274597,0.010974324,0.11032352,0.6300892,0.004078514],"about_ca_topic_score_codex":0.000018413444,"about_ca_topic_score_gemma":0.000008619695,"teacher_disagreement_score":0.7075818,"about_ca_system_score_codex":0.0000382557,"about_ca_system_score_gemma":0.00021137661,"threshold_uncertainty_score":0.9999303},"labels":[],"label_agreement":null}]}