{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":6,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":6,"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":"627b644e1b00","filters":{"venue":"Journal of Data Mining & Digital Humanities"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5182855834595688,"gpt":0.373077971203399,"spread":0.1452076122561697,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00344014,0.0001920566,0.0002423827,0.0004447706,0.000351121,0.01759966,0.003299101,0.0000357486,0.000001583462],"category_scores_gemma":[0.002423241,0.0001523287,0.00001316465,0.0003085408,0.000136134,0.2038663,0.006392448,0.0006116889,0.00000109334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001294898,"about_ca_system_score_gemma":0.0001513234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004400302,"about_ca_topic_score_gemma":0.0001243198,"domain_scores_codex":[0.9977111,0.0001100453,0.0005382451,0.000734024,0.0005814972,0.0003251158],"domain_scores_gemma":[0.9965087,0.001187015,0.0004457112,0.00163023,0.0001659838,0.00006234945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002270673,0.0001108907,0.0007111778,0.00130078,0.000518868,0.000535071,0.02173737,0.0002424033,0.0001672999,0.04171383,0.007090257,0.925645],"study_design_scores_gemma":[0.001109105,0.0002731113,0.0008716537,0.006784629,0.000130093,0.0002364449,0.03820325,0.9148959,0.00004684715,0.01111917,0.02580512,0.0005246853],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6941439,0.01035454,0.2615125,0.02406758,0.001660892,0.001035623,0.004780882,0.000212003,0.002232062],"genre_scores_gemma":[0.9879782,0.005518936,0.005112689,0.00007129106,0.0003070719,0.000004623175,0.0009487867,0.00001934818,0.00003903412],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9251203,"threshold_uncertainty_score":0.9834202,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3966178400552383,"gpt":0.3990141504154591,"spread":0.002396310360220755,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001094196,0.00006013961,0.0001762066,0.0001946278,0.00006190549,0.0002610555,0.0005383425,0.00004293335,0.00001895211],"category_scores_gemma":[0.002595684,0.00005437464,0.0000320006,0.00009754,0.0002599061,0.003507979,0.00006352877,0.00007055189,0.00000383729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006611968,"about_ca_system_score_gemma":0.000632474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002796211,"about_ca_topic_score_gemma":0.002319005,"domain_scores_codex":[0.9989525,0.0000359228,0.0004019192,0.00006853428,0.0003457196,0.0001953833],"domain_scores_gemma":[0.9986801,0.0004193857,0.0003280142,0.0001352952,0.0003443264,0.00009289389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004599814,0.0006912299,0.2761371,0.0003100445,0.0002199295,0.00005648406,0.3427959,0.00001449666,0.00007691305,0.1130466,0.1342027,0.1319887],"study_design_scores_gemma":[0.0009583226,0.0005395809,0.001859426,0.0003034534,0.00003848581,0.00001567626,0.2591229,0.000040027,0.0001289653,0.006020803,0.7307523,0.000220041],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9780607,0.0002446524,0.0000554257,0.0002579089,0.0003084891,0.0000728417,0.000272306,0.000006090516,0.02072161],"genre_scores_gemma":[0.9977703,0.00005511909,0.001104908,0.00006284551,0.0004948216,9.599231e-7,0.00006984954,0.000005947741,0.0004352189],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5965497,"threshold_uncertainty_score":0.3107463,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1025658813022736,"gpt":0.2855709712024714,"spread":0.1830050899001978,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007861331,0.0001932165,0.00033584,0.0004529327,0.00055789,0.001613868,0.002563575,0.00003162889,0.000336617],"category_scores_gemma":[0.0001915641,0.0001273378,0.0001100542,0.0002035188,0.0007632062,0.002917652,0.0007036751,0.0002617799,0.00009219533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002896408,"about_ca_system_score_gemma":0.00009604775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002325102,"about_ca_topic_score_gemma":0.001481961,"domain_scores_codex":[0.9981419,0.00006591727,0.0006452088,0.0003526744,0.0005490309,0.000245218],"domain_scores_gemma":[0.9972888,0.0001392564,0.0004585569,0.00158215,0.0004207538,0.0001104682],"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":[0.0002628414,0.0002198463,0.0003135318,0.00005700948,0.001276032,0.00002968234,0.09382171,0.000002396993,0.000009788089,0.04093117,0.8315885,0.03148748],"study_design_scores_gemma":[0.0001374906,0.0002898324,0.0002836191,0.00005630786,0.0004566827,0.00001191064,0.009197361,0.00007336084,0.000001563789,0.00005256835,0.9892775,0.0001617729],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1391014,0.009356389,0.003974973,0.005642741,0.006955252,0.001395467,0.0193687,0.0002957392,0.8139093],"genre_scores_gemma":[0.980054,0.00005274824,0.0005457561,0.001867991,0.009256097,0.000003214626,0.002161864,0.00004232023,0.006016067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8409525,"threshold_uncertainty_score":0.9994226,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2710737773030953,"gpt":0.4273664435802014,"spread":0.156292666277106,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002268384,0.00008908728,0.0001953285,0.0002092239,0.0001271307,0.0003133272,0.001040233,0.00002705062,0.00001729089],"category_scores_gemma":[0.0001166688,0.00007989495,0.00003420454,0.0001732034,0.00007056045,0.005522678,0.000215491,0.0001833609,7.177104e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004114087,"about_ca_system_score_gemma":0.0002130546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001123349,"about_ca_topic_score_gemma":0.00001045333,"domain_scores_codex":[0.9980587,0.0002118633,0.0005065902,0.0001752481,0.0009491388,0.00009844533],"domain_scores_gemma":[0.9988436,0.0001044358,0.0004080652,0.0003251907,0.000283728,0.00003501433],"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":[0.00004367443,0.0001123937,0.0003142122,0.00003240914,0.0000293202,0.000007852225,0.0153134,0.00001224003,0.0003311523,0.0009197293,0.0001575381,0.9827261],"study_design_scores_gemma":[0.01369329,0.01543895,0.03766876,0.001314362,0.001270867,0.00422514,0.0393723,0.400887,0.01436901,0.4404227,0.02744562,0.003892008],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9242461,0.007708358,0.06603236,0.0004072322,0.000161658,0.0001528896,0.0002706218,0.00009354719,0.0009272692],"genre_scores_gemma":[0.9216195,0.000005597895,0.07821501,0.00004378942,0.00003625069,0.000001376283,0.00006556122,0.00000610572,0.000006835634],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9788341,"threshold_uncertainty_score":0.4003808,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1937526202284116,"gpt":0.3030778760184903,"spread":0.1093252557900787,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001048402,0.0001334587,0.0002298792,0.0001096825,0.0003781549,0.001138936,0.002598311,0.00002991523,0.000001158607],"category_scores_gemma":[0.0004060553,0.00007917797,0.00007862596,0.0001328643,0.0001762347,0.003672651,0.0007468448,0.0002023209,0.000003527266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001743777,"about_ca_system_score_gemma":0.0005431799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001614299,"about_ca_topic_score_gemma":0.000029235,"domain_scores_codex":[0.9985312,0.00005099702,0.0006555007,0.0001338982,0.0003843599,0.0002439933],"domain_scores_gemma":[0.9974395,0.001007369,0.0008053657,0.0005527225,0.0001610702,0.00003398562],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002542696,0.00007130602,0.00003871055,0.0001697447,0.0002090681,0.00001228718,0.6311435,0.00119233,0.00001999339,0.1576338,0.01953827,0.1899455],"study_design_scores_gemma":[0.000406301,0.0001357502,0.0001530598,0.0007466994,0.00001932585,0.0001031612,0.1556592,0.757216,0.0000570839,0.07320493,0.0120745,0.0002239774],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1678548,0.003076673,0.7295034,0.005982498,0.0007581522,0.0004279931,0.0005517669,0.0002879297,0.09155677],"genre_scores_gemma":[0.9690569,0.0003139122,0.02980924,0.0001563502,0.0002993757,0.000003413637,0.00002522881,0.00001952593,0.0003160691],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8012021,"threshold_uncertainty_score":0.999898,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Computational biology; Information retrieval; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.1301717141655876,"gpt":0.3188513975220842,"spread":0.1886796833564967,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003480814,0.0001008679,0.0002194644,0.0002403567,0.00004436528,0.001106651,0.001668345,0.00002613747,0.00001056548],"category_scores_gemma":[0.0001138953,0.00007754767,0.00006574588,0.0001311396,0.00009606294,0.007824013,0.0006005683,0.0001154354,0.000007292272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000382557,"about_ca_system_score_gemma":0.0002113766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001841344,"about_ca_topic_score_gemma":0.000008619695,"domain_scores_codex":[0.9988279,0.00001611844,0.0004842136,0.0001581661,0.0003616651,0.0001519904],"domain_scores_gemma":[0.9990243,0.0002118039,0.0002202421,0.0004185771,0.00009335241,0.00003177128],"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":[0.00006421727,0.0002335361,0.01321977,0.001147656,0.00118449,0.003910232,0.03850044,0.00003993919,0.0009391669,0.1613643,0.06773587,0.7116603],"study_design_scores_gemma":[0.004350022,0.008141015,0.01999262,0.01996902,0.0007266733,0.01384713,0.1212333,0.0562746,0.01097432,0.1103235,0.6300892,0.004078514],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8803372,0.008195013,0.0669428,0.0005451368,0.003273624,0.0001077809,0.0001834375,0.0002133612,0.04020167],"genre_scores_gemma":[0.9839544,0.00003482899,0.01539855,0.00003632369,0.0001638438,2.179954e-7,0.00001000726,0.000006847033,0.000394941],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7075818,"threshold_uncertainty_score":0.9999303,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}