{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":14,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":14,"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":"7ab68898f731","filters":{"venue":"EPJ Data Science"}},"results":[{"id":"W2110349231","doi":"10.1140/epjds/s13688-015-0054-0","title":"Enhancing disease surveillance with novel data streams: challenges and opportunities","year":2015,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":239,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Institute of General Medical Sciences; Economic and Social Research Council; National Institutes of Health; Santa Fe Institute","keywords":"Computer science; Data science; Public health surveillance; Social media; Public health; Key (lock); Big data; Management science; Computer security; Data mining; World Wide Web; Engineering; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.2809649834510432,"gpt":0.349388351430047,"spread":0.06842336797900378,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002388034,0.000213357,0.0003123267,0.0001267842,0.0001403518,0.0001241859,0.001997999,0.00002402518,0.00001748331],"category_scores_gemma":[0.001866544,0.0001647302,0.000008689292,0.0002650831,0.001318246,0.002806684,0.002764277,0.0001263065,0.00001750232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005098374,"about_ca_system_score_gemma":0.001901258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007822122,"about_ca_topic_score_gemma":0.0004962185,"domain_scores_codex":[0.9969103,0.00004501318,0.0002377401,0.001305895,0.001036141,0.0004649216],"domain_scores_gemma":[0.9932521,0.0001141957,0.0001207,0.005026563,0.0002629769,0.001223466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.004306178,0.00329751,0.2516147,0.002801885,0.0004747644,0.003965703,0.004473478,0.00004233699,0.01000939,0.01391057,0.04613005,0.6589734],"study_design_scores_gemma":[0.005964432,0.000639134,0.6634562,0.001166581,0.0002245035,0.0004627774,0.007252555,0.02477258,0.0003060361,0.0001575678,0.2939999,0.001597773],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7751907,0.06946392,0.006442674,0.02535396,0.001283554,0.002383196,0.100505,0.00123511,0.0181419],"genre_scores_gemma":[0.985813,0.00358789,0.005029009,0.0004913386,0.0001917333,0.000008925834,0.004632716,0.0000285175,0.0002168411],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6573756,"threshold_uncertainty_score":0.6717502,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2803567385","doi":"10.1140/epjds/s13688-018-0166-4","title":"Prestige drives epistemic inequality in the diffusion of scientific ideas","year":2018,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"National Science Foundation","keywords":"Prestige; Competition (biology); Quality (philosophy); Citation; Set (abstract data type); Sociology; Mechanism (biology); Work (physics); Computer science; Inequality; Epistemology; Positive economics; Public relations; Political science; Economics; Mathematics; Law; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.05309980083670798,"gpt":0.3519476272919705,"spread":0.2988478264552625,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002929509,0.00007182766,0.0001157454,0.0001202111,0.0003020678,0.0001480292,0.002711172,0.000009085121,0.0001002895],"category_scores_gemma":[0.00007539338,0.00004830137,0.00002308965,0.00148512,0.001865573,0.0005790526,0.001005685,0.00008081573,0.00001257427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001171269,"about_ca_system_score_gemma":0.0001314721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006455852,"about_ca_topic_score_gemma":0.000150757,"domain_scores_codex":[0.9985731,0.00009532672,0.0002437578,0.0004403659,0.0004350599,0.000212389],"domain_scores_gemma":[0.9978594,0.00009798099,0.0001313018,0.001784438,0.00009269666,0.00003423178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009497825,0.0003762304,0.7284397,0.00001348195,0.000009041855,7.641391e-7,0.003354777,0.0000088944,0.09999277,0.1334308,0.005043597,0.02932038],"study_design_scores_gemma":[0.0003545645,0.0001178839,0.7522799,0.0001937768,0.00004191919,0.00000146569,0.001359179,0.07121553,0.0246943,0.1372088,0.01206635,0.0004662964],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9910631,0.00001830163,0.005951061,0.0001432544,0.00007648548,0.0001309862,0.00006782525,0.00001375165,0.002535244],"genre_scores_gemma":[0.9983202,8.112905e-7,0.001468742,0.0000151994,0.00009687215,0.000004630196,0.00005705893,0.000002337325,0.00003410064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07529848,"threshold_uncertainty_score":0.687378,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2626890125","doi":"10.1140/epjds/s13688-017-0108-6","title":"Inferring social influence in transport mode choice using mobile phone data","year":2017,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":72,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Thailand Research Fund","keywords":"Interpersonal ties; Mode (computer interface); Public transport; Mobile phone; Mode choice; Phone; Social network (sociolinguistics); Computer science; Social psychology; Psychology; Telecommunications; Transport engineering; Engineering; Social media; Human–computer interaction; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.1959329568068157,"gpt":0.4765131416105525,"spread":0.2805801848037368,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science"],"consensus_categories":["sts"],"category_scores_codex":[0.004866041,0.0001113881,0.0001902029,0.000156559,0.00460461,0.0005836264,0.008683933,0.00006689504,0.0001280968],"category_scores_gemma":[0.002184317,0.0001200937,0.00002269358,0.0007317635,0.002913506,0.008630564,0.0009893563,0.0002095892,0.0000291789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001806438,"about_ca_system_score_gemma":0.001557758,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2103482,"about_ca_topic_score_gemma":0.2802511,"domain_scores_codex":[0.9972956,0.00009082769,0.000304457,0.0009150562,0.0008857407,0.0005083527],"domain_scores_gemma":[0.9963869,0.0001064606,0.0001941893,0.00302741,0.0001399231,0.0001451391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001867349,0.0004484341,0.881671,0.00006219566,0.00002555055,0.00002411631,0.03737064,0.01464706,0.01019607,0.003144572,0.0001981181,0.05219354],"study_design_scores_gemma":[0.000559528,0.00001390156,0.7101102,0.0001073799,0.00006868332,7.223967e-7,0.004594128,0.2617793,0.0002686597,0.0006915543,0.02111284,0.0006931302],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9955595,0.00003062154,0.001532638,0.0003684685,0.00013273,0.0001922014,0.0003168501,0.00003549784,0.001831559],"genre_scores_gemma":[0.9988574,0.00002991413,0.0006248282,0.00008883572,0.0002144131,0.000007068315,0.000109429,0.000005497853,0.00006258215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2471322,"threshold_uncertainty_score":0.9998,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137811660","doi":"10.1140/epjds/s13688-014-0011-3","title":"Exploiting citation networks for large-scale author name disambiguation","year":2014,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":53,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Metadata; Ranking (information retrieval); Citation; Similarity (geometry); Cluster analysis; Precision and recall; Bibliographic coupling; Parameterized complexity; Heuristics","retraction":null,"screen_n_in":null,"score":{"opus":0.3376502821107572,"gpt":0.4681113964519575,"spread":0.1304611143412003,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03493439,0.000101746,0.0001564664,0.0002179241,0.000809848,0.001171932,0.003683984,0.00003447188,0.00009560783],"category_scores_gemma":[0.01789395,0.00008225974,0.00003242824,0.001282667,0.0002293966,0.005170112,0.001376951,0.00007587486,0.0002045199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003367738,"about_ca_system_score_gemma":0.00005842218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002308111,"about_ca_topic_score_gemma":0.0001291563,"domain_scores_codex":[0.9961376,0.0001733967,0.0005292729,0.001037615,0.001669686,0.0004524335],"domain_scores_gemma":[0.9959365,0.001305184,0.0002857179,0.002050131,0.0002832933,0.0001392325],"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":[0.00003062711,0.0001433539,0.001207938,0.00001758145,0.000005758546,4.933555e-7,0.002202626,0.002575997,0.0007175249,0.2446856,0.09711516,0.6512973],"study_design_scores_gemma":[0.0002086783,0.00003672068,0.005384765,0.00001196134,0.000007094954,4.240794e-7,0.002097685,0.7581882,0.00006551889,0.01925048,0.2146195,0.000129045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01036611,0.00001603668,0.9838091,0.00236919,0.0009880613,0.0003037958,0.0003242148,0.00005419436,0.001769292],"genre_scores_gemma":[0.9488891,0.000005657101,0.04784369,0.00105235,0.0003214616,0.0000376039,0.0006622946,0.000008421314,0.001179387],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.938523,"threshold_uncertainty_score":0.9998649,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096119600","doi":"10.1140/epjds/s13688-014-0024-y","title":"Inequality and cumulative advantage in science careers: a case study of high-impact journals","year":2014,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Citation; Inequality; Publishing; Citation impact; Productivity; Publication; Gini coefficient; Competition (biology); Set (abstract data type); Econometrics; Economic inequality; Sociology; Economics; Computer science; Mathematics; Political science; Library science; Economic growth; Law; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.7717071333746156,"gpt":0.6827132583531631,"spread":0.0889938750214525,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.1603896,0.0001677889,0.0004807424,0.05371875,0.0006870691,0.003284267,0.009054329,0.00003986023,0.00009091958],"category_scores_gemma":[0.1493065,0.0001069772,0.00002895507,0.2619271,0.002896502,0.008303492,0.006815976,0.0003223284,0.00001422702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001880447,"about_ca_system_score_gemma":0.0009488858,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008801027,"about_ca_topic_score_gemma":0.001102828,"domain_scores_codex":[0.9804884,0.0005360763,0.001096401,0.00180948,0.01516057,0.0009090835],"domain_scores_gemma":[0.9853236,0.005524646,0.0006320153,0.003646765,0.00392879,0.0009442047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002035494,0.0004880532,0.8842402,0.000003896283,0.00000353154,0.0002263047,0.003059675,0.0002493217,0.00381139,0.0002883776,0.0001010716,0.1075078],"study_design_scores_gemma":[0.001037353,0.0008376995,0.9041589,0.00001876285,0.000004920641,0.0002541326,0.02109385,0.07000024,0.0006176772,0.001650482,0.00009823749,0.0002276722],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996446,0.0001376933,0.002262978,0.00009413411,0.0002293945,0.0003469453,0.0001690401,0.000007309155,0.0003065313],"genre_scores_gemma":[0.9988333,0.00002785724,0.001059201,0.00002604977,0.00002466821,0.000002531005,0.000001221023,0.000004237484,0.00002096441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2082084,"threshold_uncertainty_score":0.999817,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4367308548","doi":"10.1140/epjds/s13688-023-00378-6","title":"Differences in collaboration structures and impact among prominent researchers in Europe and North America","year":2023,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Agència de Gestió d'Ajuts Universitaris i de Recerca; Ministerio de Ciencia e Innovación; Ministerio de Economía y Competitividad; Generalitat de Catalunya","keywords":"Scope (computer science); Politics; Political science; Quality (philosophy); Network structure; Regional science; Public relations; Sociology; Computer science; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.7026761929763207,"gpt":0.5976172621589622,"spread":0.1050589308173585,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.01876575,0.0001091699,0.0002120767,0.03052936,0.0002408983,0.003857204,0.003320937,0.00003236718,0.00004258576],"category_scores_gemma":[0.07016835,0.00006858769,0.000007777818,0.3630759,0.001597289,0.003132403,0.003337,0.0002348381,0.00002564244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007519998,"about_ca_system_score_gemma":0.0006235932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001185735,"about_ca_topic_score_gemma":0.002196324,"domain_scores_codex":[0.9920694,0.0002533686,0.000397091,0.001149597,0.005464918,0.0006656224],"domain_scores_gemma":[0.9957792,0.001859625,0.0001180953,0.0009284239,0.0009008026,0.0004138926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009839652,0.0000121691,0.9524395,0.000002240972,7.702135e-7,0.0000188109,0.0005042848,0.00002279612,0.0006799927,0.00003373722,0.001205273,0.04507057],"study_design_scores_gemma":[0.0001591227,0.00008741731,0.9399556,0.000005419381,3.976064e-7,0.000001063672,0.001079495,0.05759397,0.00003493228,0.0003896696,0.0006079426,0.00008498407],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9982383,0.0002363027,0.0000250074,0.0006900068,0.00008607082,0.0002747998,0.0001994348,0.00001167271,0.0002384203],"genre_scores_gemma":[0.9984804,0.001069269,0.0002703019,0.00001722408,0.00001313546,0.000005975108,0.00002231361,0.000003786309,0.0001176241],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3325466,"threshold_uncertainty_score":0.9971769,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3165666381","doi":"10.1140/epjds/s13688-021-00281-y","title":"Inferring psychological traits from spending categories and dynamic consumption patterns","year":2021,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Digital Marketing and Social Media","field":"Social Sciences","cited_by":27,"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":"Extraversion and introversion; Neuroticism; Burstiness; Big Five personality traits; Psychology; Database transaction; Consumption (sociology); Trait; Personality; Social psychology; Cognitive psychology; Computer science; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.108290829005402,"gpt":0.4099872985323165,"spread":0.3016964695269145,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001302659,0.00007002481,0.0001036926,0.00003824595,0.0007195678,0.0006238949,0.000636062,0.00004939978,0.0001599842],"category_scores_gemma":[0.002782862,0.00006848435,0.00001162662,0.0003092863,0.00115237,0.001416775,0.0003947325,0.000113358,0.0000265438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005110294,"about_ca_system_score_gemma":0.0001281731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006273394,"about_ca_topic_score_gemma":0.003228714,"domain_scores_codex":[0.9984827,0.0001134873,0.0001258978,0.000516817,0.0004495149,0.0003115521],"domain_scores_gemma":[0.9991677,0.0003182378,0.00004763276,0.0002547249,0.0000458296,0.0001658545],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001429852,0.0001450484,0.5988005,0.00002292284,0.00001372259,0.0001131478,0.02607069,0.000001032753,0.006892804,0.03736462,0.0002384078,0.3303227],"study_design_scores_gemma":[0.0001423607,0.00001190653,0.9838867,0.00005815017,0.000008772115,0.000003726429,0.008146577,0.0001822453,0.00008321173,0.003910453,0.003372918,0.0001929858],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9874366,0.0001382609,0.0002953794,0.0004910047,0.0006214501,0.00005273811,0.0001762199,0.00006025982,0.0107281],"genre_scores_gemma":[0.9985945,0.0003649036,0.0006430492,0.00008353197,0.0001077046,0.000001711922,0.00006134612,0.000003333758,0.0001399503],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3850861,"threshold_uncertainty_score":0.6016232,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3120906435","doi":"10.1140/epjds/s13688-020-00254-7","title":"Challenges when identifying migration from geo-located Twitter data","year":2021,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"McGill University","keywords":"Geolocation; Suspect; Data science; Computer science; Set (abstract data type); Social media; Reliability (semiconductor); TRACE (psycholinguistics); Data set; Internet privacy; World Wide Web; Sociology; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.3333258322916927,"gpt":0.4153275156938945,"spread":0.08200168340220182,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003804253,0.00009222946,0.0001358465,0.00009680862,0.001213667,0.0006758654,0.003739542,0.00005677488,0.00125949],"category_scores_gemma":[0.002275284,0.00009347274,0.00002114806,0.0008518497,0.0008491374,0.003418087,0.001157908,0.0001299606,0.0002777143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008213813,"about_ca_system_score_gemma":0.001075391,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03129006,"about_ca_topic_score_gemma":0.2354736,"domain_scores_codex":[0.9970286,0.0002679921,0.0002431919,0.001170118,0.000958243,0.0003318301],"domain_scores_gemma":[0.9961748,0.0002261616,0.00009603487,0.003080101,0.0002739007,0.0001490727],"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":[0.00002592591,0.001077824,0.0292879,0.00011583,0.0002528302,0.0001107396,0.2786119,0.0001900965,0.03961062,0.01672472,0.0637834,0.5702082],"study_design_scores_gemma":[0.0005689099,0.00002514098,0.09503257,0.0002359359,0.0003043553,0.000002382132,0.1223002,0.09239521,0.004112286,0.01800826,0.6658481,0.001166614],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7243405,0.01405843,0.06952718,0.1506301,0.003182348,0.0009121099,0.002471476,0.0006779752,0.03419985],"genre_scores_gemma":[0.9929035,0.0009644776,0.002121819,0.0004741693,0.0003479357,0.00000432662,0.002562579,0.000005427389,0.0006157674],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6020647,"threshold_uncertainty_score":0.9996535,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4291178448","doi":"10.1140/epjds/s13688-022-00357-3","title":"Reaching the bubble may not be enough: news media role in online political polarization","year":2022,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Social Media and Politics","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"Connaught Fund; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Politics; Polarization (electrochemistry); Presidential system; Centrality; Political science; Presidential election; Social media; Biology and political orientation; News media; Metric (unit); Computer science; Public relations; Business; Mathematics; Law; Statistics; Marketing","retraction":null,"screen_n_in":null,"score":{"opus":0.1080335363287633,"gpt":0.3881391399147623,"spread":0.2801056035859991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002672524,0.00007663845,0.0001063108,0.0001087445,0.001990614,0.0001614871,0.002450351,0.0000386211,0.0001658412],"category_scores_gemma":[0.005407999,0.00006587127,0.00001768657,0.001344463,0.001193038,0.0008345178,0.0009707978,0.0003890715,0.00001184022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003263739,"about_ca_system_score_gemma":0.001312858,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05186131,"about_ca_topic_score_gemma":0.0113955,"domain_scores_codex":[0.9969355,0.0004423754,0.0002044892,0.0003679754,0.001316442,0.0007331558],"domain_scores_gemma":[0.998331,0.0007612253,0.00006269495,0.0005797679,0.00004417643,0.0002211985],"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":[0.000005057177,0.0001039777,0.019656,0.000001599481,0.000001563746,0.000005786076,0.05514158,0.000009520827,0.001541707,0.918427,0.0006990083,0.004407212],"study_design_scores_gemma":[0.0002173276,0.00003284367,0.01597988,0.000007645729,0.0000131935,0.000003517534,0.258981,0.00126988,0.000263633,0.007392019,0.7156034,0.000235695],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8058448,0.0001008631,0.00005007186,0.1778148,0.002438133,0.0003739728,0.001372558,0.00008410759,0.01192068],"genre_scores_gemma":[0.9943566,0.00001631103,0.0006524179,0.003908492,0.0006599381,0.000009013959,0.0002022437,0.000006666648,0.00018832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9110349,"threshold_uncertainty_score":0.9993086,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4379794872","doi":"10.1140/epjds/s13688-023-00394-6","title":"Do poverty and wealth look the same the world over? A comparative study of 12 cities from five high-income countries using street images","year":2023,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Urban Green Space and Health","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of British Columbia","funders":"Medical Research Council; Wellcome Trust","keywords":"Atlanta; Socioeconomic status; Poverty; Inequality; Geography; Urbanization; Disadvantage; Urban studies; Metropolitan area; Regional science; Economic growth; Economic geography; Sociology; Political science; Demography; Population; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.063362490875996,"gpt":0.3357606276805064,"spread":0.2723981368045104,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001357843,0.000141805,0.0002239792,0.0000659532,0.0009818599,0.0001849782,0.001609838,0.00001582367,0.000264833],"category_scores_gemma":[0.00004731338,0.00007794888,0.00001206156,0.0009549997,0.00241173,0.001197094,0.002185525,0.0001636979,0.00004447607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001080041,"about_ca_system_score_gemma":0.0001080807,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.06453367,"about_ca_topic_score_gemma":0.1319456,"domain_scores_codex":[0.997817,0.0001329279,0.0002307546,0.0005540404,0.0008871707,0.0003780964],"domain_scores_gemma":[0.9980608,0.0005371417,0.0001888293,0.001107124,0.00001544475,0.0000906084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002020978,0.00003677295,0.9753866,0.000005553472,0.00001005469,0.000003197809,0.009604933,0.000236349,0.0002299782,0.0002073928,0.01416788,0.00009111891],"study_design_scores_gemma":[0.0002587905,0.0001049794,0.9696659,0.00003061892,0.00002078808,6.866959e-7,0.02328176,0.005249154,0.00006367887,0.0003219493,0.0008880647,0.0001135786],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996758,0.0001161998,0.0000144032,0.001172649,0.0001247732,0.0004405738,0.001109098,0.00002293281,0.0002413598],"genre_scores_gemma":[0.9987534,0.00008694152,0.0002158608,0.0005064013,0.00004330193,0.000005548335,0.00001477802,0.000005430056,0.0003683157],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06741197,"threshold_uncertainty_score":0.9416957,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4412385652","doi":"10.1140/epjds/s13688-025-00561-x","title":"Solana’s transaction network: analysis, insights, and comparison","year":2025,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Digital Platforms and Economics","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Database transaction; Computer science; Network analysis; Econometrics; Statistical physics; Artificial intelligence; Economics; Physics; Engineering; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03624091006558341,"gpt":0.2643046972778095,"spread":0.2280637872122261,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003854835,0.00006624349,0.0001292145,0.0002557147,0.0002811754,0.001479242,0.0005304945,0.00001806899,0.00002451868],"category_scores_gemma":[0.00002524639,0.00005673206,0.00001630787,0.001379472,0.0001401027,0.01178998,0.0002985338,0.00005081503,0.00004589858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001260447,"about_ca_system_score_gemma":0.00002572438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003252689,"about_ca_topic_score_gemma":0.001256996,"domain_scores_codex":[0.999248,3.43223e-7,0.0001524109,0.000323793,0.00009093346,0.0001844653],"domain_scores_gemma":[0.9995112,0.00001253036,0.00006460479,0.0003745133,0.00002691124,0.00001026873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006048136,0.0001851369,0.1978691,0.0001510419,0.000306725,0.000004137093,0.0001021942,0.01849425,0.0002366911,0.56414,0.04188742,0.1765628],"study_design_scores_gemma":[0.0001692711,0.00000293249,0.06450276,0.00001447206,0.0001786061,2.146623e-7,0.0003153947,0.7645676,0.00001252006,0.008965191,0.1610969,0.0001741372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8507079,0.0003062025,0.02349835,0.0004348185,0.0007460475,0.0001386869,0.00001143745,0.0000828181,0.1240737],"genre_scores_gemma":[0.9987677,0.00001707068,0.0002058919,0.0006726653,0.000109278,8.49028e-7,0.0001104887,0.000001927832,0.0001140927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7460733,"threshold_uncertainty_score":0.9995573,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413745650","doi":"10.1140/epjds/s13688-025-00582-6","title":"AGECovP: identifying ageism and analyzing COVID-19 discourse on older adults in YouTube","year":2025,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Aging and Gerontology Research","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Computer science; Psychology; Sociology; Medicine; Virology","retraction":null,"screen_n_in":null,"score":{"opus":0.1165992880726862,"gpt":0.5068965799335734,"spread":0.3902972918608872,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002458202,0.0001024639,0.00014854,0.0005212713,0.0003648072,0.0001324343,0.001336125,0.00005723356,0.0001534404],"category_scores_gemma":[0.001045086,0.00008992921,0.00001262487,0.0009583331,0.0009411297,0.0005449839,0.0007646268,0.0003178298,0.0000862711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007261255,"about_ca_system_score_gemma":0.0002813043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001754717,"about_ca_topic_score_gemma":0.001392677,"domain_scores_codex":[0.9979645,0.0001451888,0.0001849029,0.0009602122,0.000244335,0.000500863],"domain_scores_gemma":[0.9982948,0.0002826865,0.00004200804,0.00119228,0.00002428403,0.0001639576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003774704,0.0006746102,0.6767343,0.0002157176,0.00007136492,0.001034793,0.04482531,0.00003030173,0.0003977915,0.05345824,0.03810879,0.1840713],"study_design_scores_gemma":[0.002259745,0.00006687111,0.9693982,0.0003458477,0.00002215744,0.00003247526,0.02060575,0.003154748,0.00006005492,0.0009677325,0.002739877,0.0003465331],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9765801,0.000901191,0.00377997,0.006115432,0.0007151207,0.0002392653,0.00007579374,0.00004901554,0.01154404],"genre_scores_gemma":[0.9957056,0.00001805158,0.0002198977,0.001010607,0.00002659312,0.00001218565,0.00003146642,0.000004382212,0.002971193],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2926639,"threshold_uncertainty_score":0.3667207,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409271193","doi":"10.1140/epjds/s13688-025-00549-7","title":"Twitter-MusicPD: melody of minds - navigating user-level data on multiple mental health disorders and music preferences","year":2025,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Mental Health via Writing","field":"Psychology","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 Guelph; Toronto Metropolitan University; McMaster University","funders":"","keywords":"Mental health; Psychology; Computer science; Psychiatry","retraction":null,"screen_n_in":null,"score":{"opus":0.2304294699678719,"gpt":0.4631044083909127,"spread":0.2326749384230408,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002586351,0.0001725305,0.0002596296,0.0001439996,0.0006197999,0.00007288902,0.002825717,0.00004584292,0.0001200105],"category_scores_gemma":[0.0004446134,0.0001610665,0.00001052035,0.0007872815,0.0007638414,0.0009038227,0.002603232,0.0002839486,0.00001846774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007161275,"about_ca_system_score_gemma":0.0003447625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004118755,"about_ca_topic_score_gemma":0.002249509,"domain_scores_codex":[0.9969468,0.0001561849,0.000537144,0.001261369,0.000501617,0.0005969284],"domain_scores_gemma":[0.9967806,0.0004527536,0.0002870775,0.002283489,0.00002718354,0.0001688576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001488785,0.0007840581,0.2437169,0.0005674794,0.00004368452,0.0000034221,0.01419914,0.000002704736,0.003633197,0.00329584,0.04430951,0.6892952],"study_design_scores_gemma":[0.005136062,0.001191065,0.8809414,0.00361126,0.00004000484,0.00002809199,0.05036683,0.01856433,0.001666486,0.000715294,0.03669326,0.001045907],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9886967,0.0004362089,0.0003085846,0.002534537,0.001211825,0.0006754379,0.00318,0.00003664415,0.00292005],"genre_scores_gemma":[0.9903339,0.00004879224,0.007052886,0.001504625,0.00004102731,0.00001379664,0.000827479,0.000009760898,0.0001677219],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6882493,"threshold_uncertainty_score":0.65681,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4390747461","doi":"10.1140/epjds/s13688-023-00432-3","title":"What relational event models can reveal: Commentary on Thomas Grund’s “Dynamics of Denunciation: The Limits of a Scandal”","year":2024,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Opinion Dynamics and Social Influence","field":"Physics and Astronomy","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 Alberta","funders":"","keywords":"Denunciation; Sociology; Event (particle physics); Context (archaeology); Scholarship; Epistemology; Dynamics (music); Politics; Value (mathematics); Computer science; Law; Political science; History; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.05772423295545753,"gpt":0.3359620390459492,"spread":0.2782378060904917,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007706337,0.00007561437,0.0001006757,0.00005159962,0.0001975228,0.0001175535,0.0007482843,0.00001653313,0.00001732302],"category_scores_gemma":[0.00001518649,0.00005696105,0.00003806238,0.0004363904,0.0003360939,0.001137465,0.0002383822,0.0001212152,0.000002103028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007250141,"about_ca_system_score_gemma":0.0003309682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004282244,"about_ca_topic_score_gemma":0.00009910996,"domain_scores_codex":[0.998863,0.00003216149,0.0002359733,0.000257348,0.0004744536,0.0001370406],"domain_scores_gemma":[0.9990812,0.0001505847,0.0001096271,0.0005159441,0.00010021,0.00004244576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004792769,0.00005895122,0.003613261,0.00001557259,0.00002266411,3.358769e-7,0.001075727,0.009483384,0.00009115945,0.9739447,0.002616506,0.009072937],"study_design_scores_gemma":[0.0001254039,0.00005257156,0.004294244,0.0003376117,0.00002139778,4.799102e-7,0.001209898,0.9230866,0.0001530023,0.06791875,0.002658411,0.0001415872],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8355507,0.001116322,0.05220902,0.08277759,0.005464083,0.001189925,0.01238504,0.00006413661,0.009243228],"genre_scores_gemma":[0.9988204,0.00004060021,0.0003362767,0.0002415776,0.0001090076,0.000004825942,0.0003250689,0.000005201327,0.0001170377],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9136032,"threshold_uncertainty_score":0.2322804,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}