{"meta":{"query_hash":"7ab68898f731","filters":{"venue":"EPJ Data Science"},"cohort_total":14,"direct_labels_cover":0,"predictions_cover":14,"exported":14,"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/7ab68898f731","api":"https://metacan.xera.ac/api/v1/cohort?venue=EPJ+Data+Science"},"results":[{"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.7717071333746156,"score_gpt":0.6827132583531631,"score_spread":0.0889938750214525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096119600","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":[0.99644595,0.00013769326,0.0022629777,0.000094134106,0.00022939453,0.00034694528,0.00016904014,0.0000073091546,0.00030653132],"genre_scores_gemma":[0.9988333,0.000027857239,0.0010592006,0.000026049765,0.000024668207,0.0000025310053,0.0000012210226,0.0000042374836,0.000020964406],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98048836,0.00053607626,0.0010964015,0.00180948,0.015160574,0.0009090835],"domain_scores_gemma":[0.9853236,0.0055246465,0.00063201535,0.0036467647,0.0039287903,0.0009442047],"candidate_categories":["metaresearch","bibliometrics","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.16038962,0.00016778891,0.0004807424,0.053718746,0.0006870691,0.0032842674,0.009054329,0.000039860228,0.00009091958],"category_scores_gemma":[0.1493065,0.00010697721,0.000028955074,0.26192713,0.002896502,0.008303492,0.0068159755,0.00032232836,0.000014227023],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020354944,0.00048805316,0.8842402,0.0000038962835,0.0000035315402,0.0002263047,0.0030596748,0.00024932172,0.0038113897,0.00028837763,0.00010107159,0.107507795],"study_design_scores_gemma":[0.0010373531,0.00083769945,0.90415895,0.000018762848,0.000004920641,0.00025413264,0.021093855,0.07000024,0.00061767723,0.0016504817,0.00009823749,0.00022767218],"about_ca_topic_score_codex":0.008801027,"about_ca_topic_score_gemma":0.0011028282,"teacher_disagreement_score":0.2082084,"about_ca_system_score_codex":0.00018804465,"about_ca_system_score_gemma":0.0009488858,"threshold_uncertainty_score":0.999817},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2809649834510432,"score_gpt":0.349388351430047,"score_spread":0.06842336797900378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110349231","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":[0.7751907,0.069463916,0.0064426735,0.025353959,0.0012835539,0.0023831958,0.10050499,0.0012351098,0.018141901],"genre_scores_gemma":[0.985813,0.0035878904,0.005029009,0.0004913386,0.00019173334,0.000008925834,0.004632716,0.000028517496,0.00021684114],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9969103,0.000045013185,0.00023774014,0.0013058946,0.0010361413,0.00046492164],"domain_scores_gemma":[0.9932521,0.00011419568,0.00012070002,0.005026563,0.0002629769,0.0012234664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023880336,0.00021335695,0.00031232668,0.00012678417,0.00014035183,0.00012418593,0.0019979987,0.00002402518,0.000017483306],"category_scores_gemma":[0.0018665441,0.00016473018,0.000008689292,0.00026508307,0.0013182465,0.0028066842,0.002764277,0.00012630646,0.00001750232],"study_design_candidate":"observational","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":[0.0043061776,0.0032975096,0.25161475,0.002801885,0.0004747644,0.003965703,0.004473478,0.00004233699,0.010009386,0.0139105655,0.04613005,0.6589734],"study_design_scores_gemma":[0.0059644324,0.00063913397,0.6634562,0.0011665807,0.00022450346,0.00046277742,0.0072525553,0.024772577,0.0003060361,0.00015756779,0.29399985,0.0015977732],"about_ca_topic_score_codex":0.000078221216,"about_ca_topic_score_gemma":0.0004962185,"teacher_disagreement_score":0.65737563,"about_ca_system_score_codex":0.00005098374,"about_ca_system_score_gemma":0.001901258,"threshold_uncertainty_score":0.6717502},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.3376502821107572,"score_gpt":0.46811139645195754,"score_spread":0.13046111434120033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137811660","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010366115,0.000016036676,0.9838091,0.0023691903,0.0009880613,0.00030379582,0.00032421478,0.000054194355,0.0017692922],"genre_scores_gemma":[0.94888914,0.0000056571007,0.047843687,0.0010523499,0.00032146164,0.0000376039,0.00066229457,0.000008421314,0.0011793865],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961376,0.00017339672,0.00052927295,0.0010376145,0.0016696863,0.00045243354],"domain_scores_gemma":[0.99593645,0.0013051842,0.00028571786,0.0020501306,0.00028329328,0.00013923249],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03493439,0.00010174597,0.00015646641,0.00021792413,0.000809848,0.0011719317,0.0036839843,0.000034471876,0.00009560783],"category_scores_gemma":[0.017893953,0.00008225974,0.000032428245,0.0012826668,0.00022939655,0.0051701115,0.0013769515,0.00007587486,0.00020451988],"study_design_candidate":"simulation_or_modeling","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":[0.000030627107,0.00014335386,0.0012079381,0.00001758145,0.000005758546,4.9335546e-7,0.002202626,0.002575997,0.0007175249,0.24468563,0.09711516,0.6512973],"study_design_scores_gemma":[0.00020867826,0.000036720678,0.0053847646,0.000011961335,0.0000070949536,4.2407942e-7,0.002097685,0.7581882,0.00006551889,0.019250482,0.21461946,0.00012904497],"about_ca_topic_score_codex":0.000023081107,"about_ca_topic_score_gemma":0.0001291563,"teacher_disagreement_score":0.938523,"about_ca_system_score_codex":0.000033677377,"about_ca_system_score_gemma":0.00005842218,"threshold_uncertainty_score":0.99986494},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.19593295680681566,"score_gpt":0.47651314161055247,"score_spread":0.2805801848037368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626890125","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":[0.99555945,0.000030621544,0.0015326384,0.00036846852,0.00013273003,0.00019220138,0.00031685014,0.000035497844,0.0018315593],"genre_scores_gemma":[0.99885744,0.000029914134,0.00062482816,0.000088835724,0.00021441307,0.0000070683145,0.00010942901,0.0000054978527,0.00006258215],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99729556,0.000090827685,0.00030445703,0.0009150562,0.0008857407,0.0005083527],"domain_scores_gemma":[0.9963869,0.000106460626,0.0001941893,0.0030274098,0.00013992313,0.00014513914],"candidate_categories":["sts","open_science"],"consensus_categories":["sts"],"category_scores_codex":[0.004866041,0.00011138806,0.00019020292,0.00015655902,0.00460461,0.0005836264,0.008683933,0.00006689504,0.00012809681],"category_scores_gemma":[0.0021843167,0.00012009374,0.00002269358,0.00073176355,0.0029135055,0.0086305635,0.0009893563,0.00020958923,0.000029178898],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018673489,0.0004484341,0.881671,0.00006219566,0.000025550546,0.000024116307,0.037370637,0.014647055,0.01019607,0.0031445718,0.00019811814,0.052193545],"study_design_scores_gemma":[0.000559528,0.000013901565,0.7101102,0.0001073799,0.000068683315,7.2239675e-7,0.004594128,0.26177928,0.00026865973,0.0006915543,0.021112837,0.00069313025],"about_ca_topic_score_codex":0.21034823,"about_ca_topic_score_gemma":0.2802511,"teacher_disagreement_score":0.24713221,"about_ca_system_score_codex":0.00018064378,"about_ca_system_score_gemma":0.0015577581,"threshold_uncertainty_score":0.99979997},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.053099800836707976,"score_gpt":0.3519476272919705,"score_spread":0.29884782645526253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803567385","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":[0.9910631,0.000018301625,0.005951061,0.00014325444,0.00007648548,0.0001309862,0.000067825255,0.000013751649,0.0025352442],"genre_scores_gemma":[0.9983202,8.112905e-7,0.001468742,0.000015199395,0.00009687215,0.000004630196,0.000057058933,0.0000023373254,0.000034100638],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985731,0.00009532672,0.00024375778,0.00044036593,0.0004350599,0.00021238903],"domain_scores_gemma":[0.99785936,0.00009798099,0.0001313018,0.0017844382,0.00009269666,0.000034231784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029295094,0.00007182766,0.00011574535,0.00012021113,0.00030206778,0.00014802918,0.0027111717,0.000009085121,0.000100289544],"category_scores_gemma":[0.00007539338,0.000048301372,0.000023089653,0.0014851204,0.0018655725,0.0005790526,0.0010056853,0.000080815735,0.000012574265],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009497825,0.00037623043,0.72843975,0.000013481953,0.000009041855,7.6413914e-7,0.0033547769,0.0000088944,0.099992774,0.13343082,0.0050435974,0.029320383],"study_design_scores_gemma":[0.00035456454,0.00011788389,0.75227994,0.00019377677,0.00004191919,0.00000146569,0.001359179,0.07121553,0.024694296,0.1372088,0.012066352,0.0004662964],"about_ca_topic_score_codex":0.00064558524,"about_ca_topic_score_gemma":0.00015075704,"teacher_disagreement_score":0.07529848,"about_ca_system_score_codex":0.000011712694,"about_ca_system_score_gemma":0.00013147209,"threshold_uncertainty_score":0.687378},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.3333258322916927,"score_gpt":0.41532751569389453,"score_spread":0.08200168340220182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120906435","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":[0.7243405,0.014058426,0.06952718,0.15063012,0.003182348,0.00091210986,0.0024714763,0.0006779752,0.03419985],"genre_scores_gemma":[0.9929035,0.0009644776,0.0021218192,0.00047416933,0.00034793568,0.0000043266195,0.0025625792,0.000005427389,0.0006157674],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99702865,0.0002679921,0.00024319187,0.0011701181,0.000958243,0.0003318301],"domain_scores_gemma":[0.99617475,0.00022616165,0.00009603487,0.0030801008,0.00027390075,0.00014907266],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038042534,0.000092229464,0.00013584647,0.00009680862,0.0012136666,0.00067586545,0.003739542,0.00005677488,0.0012594898],"category_scores_gemma":[0.002275284,0.000093472736,0.00002114806,0.00085184973,0.00084913743,0.0034180875,0.0011579078,0.00012996061,0.0002777143],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002592591,0.0010778238,0.0292879,0.000115829986,0.0002528302,0.00011073959,0.2786119,0.00019009646,0.03961062,0.016724717,0.0637834,0.5702082],"study_design_scores_gemma":[0.00056890986,0.00002514098,0.095032565,0.00023593589,0.00030435534,0.0000023821317,0.12230022,0.09239521,0.0041122865,0.018008262,0.66584814,0.0011666141],"about_ca_topic_score_codex":0.031290058,"about_ca_topic_score_gemma":0.23547363,"teacher_disagreement_score":0.6020647,"about_ca_system_score_codex":0.00008213813,"about_ca_system_score_gemma":0.0010753914,"threshold_uncertainty_score":0.9996535},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.10829082900540199,"score_gpt":0.40998729853231647,"score_spread":0.3016964695269145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165666381","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":[0.9874366,0.00013826089,0.00029537943,0.00049100467,0.0006214501,0.000052738105,0.00017621994,0.00006025982,0.010728096],"genre_scores_gemma":[0.99859446,0.00036490362,0.0006430492,0.000083531966,0.00010770462,0.0000017119216,0.00006134612,0.000003333758,0.00013995034],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984827,0.000113487295,0.00012589783,0.00051681703,0.00044951492,0.00031155205],"domain_scores_gemma":[0.99916774,0.00031823775,0.00004763276,0.0002547249,0.0000458296,0.00016585454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001302659,0.00007002481,0.000103692604,0.000038245955,0.0007195678,0.00062389486,0.000636062,0.000049399776,0.00015998422],"category_scores_gemma":[0.002782862,0.000068484354,0.000011626622,0.0003092863,0.0011523698,0.0014167747,0.00039473255,0.000113358044,0.000026543803],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014298523,0.00014504843,0.59880054,0.00002292284,0.000013722593,0.00011314779,0.026070692,0.0000010327531,0.0068928036,0.037364617,0.00023840777,0.33032274],"study_design_scores_gemma":[0.0001423607,0.000011906531,0.9838867,0.000058150166,0.000008772115,0.0000037264292,0.008146577,0.0001822453,0.00008321173,0.0039104526,0.003372918,0.00019298581],"about_ca_topic_score_codex":0.00062733935,"about_ca_topic_score_gemma":0.0032287142,"teacher_disagreement_score":0.38508612,"about_ca_system_score_codex":0.00005110294,"about_ca_system_score_gemma":0.00012817308,"threshold_uncertainty_score":0.60162324},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.10803353632876328,"score_gpt":0.38813913991476234,"score_spread":0.28010560358599906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291178448","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":[0.8058448,0.00010086311,0.000050071856,0.17781481,0.0024381331,0.0003739728,0.0013725578,0.00008410759,0.0119206775],"genre_scores_gemma":[0.9943566,0.000016311025,0.00065241795,0.0039084917,0.0006599381,0.000009013959,0.0002022437,0.0000066666485,0.00018832003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99693555,0.00044237543,0.0002044892,0.0003679754,0.0013164418,0.0007331558],"domain_scores_gemma":[0.99833095,0.0007612253,0.000062694955,0.00057976786,0.000044176428,0.00022119847],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002672524,0.00007663845,0.0001063108,0.00010874447,0.001990614,0.0001614871,0.0024503514,0.000038621103,0.0001658412],"category_scores_gemma":[0.0054079993,0.000065871274,0.000017686567,0.0013444632,0.0011930377,0.00083451776,0.00097079785,0.00038907153,0.000011840225],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005057177,0.00010397767,0.019656,0.0000015994814,0.0000015637455,0.0000057860757,0.05514158,0.000009520827,0.0015417067,0.918427,0.00069900835,0.0044072117],"study_design_scores_gemma":[0.00021732763,0.00003284367,0.015979884,0.000007645729,0.000013193502,0.0000035175337,0.25898105,0.0012698799,0.00026363303,0.0073920186,0.71560335,0.00023569497],"about_ca_topic_score_codex":0.05186131,"about_ca_topic_score_gemma":0.011395499,"teacher_disagreement_score":0.91103494,"about_ca_system_score_codex":0.00032637393,"about_ca_system_score_gemma":0.0013128583,"threshold_uncertainty_score":0.99930865},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.7026761929763207,"score_gpt":0.5976172621589622,"score_spread":0.10505893081735851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367308548","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":[0.99823827,0.00023630269,0.000025007404,0.00069000677,0.000086070824,0.00027479976,0.00019943478,0.000011672709,0.00023842028],"genre_scores_gemma":[0.9984804,0.0010692695,0.00027030185,0.000017224076,0.000013135464,0.0000059751083,0.000022313612,0.0000037863092,0.00011762414],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9920694,0.0002533686,0.00039709103,0.0011495968,0.0054649184,0.0006656224],"domain_scores_gemma":[0.99577916,0.0018596251,0.000118095275,0.0009284239,0.00090080255,0.00041389262],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.018765748,0.00010916993,0.00021207669,0.030529356,0.00024089827,0.0038572035,0.0033209373,0.000032367177,0.000042585758],"category_scores_gemma":[0.070168346,0.00006858769,0.000007777818,0.36307594,0.0015972886,0.0031324034,0.0033370003,0.00023483811,0.00002564244],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009839652,0.000012169101,0.9524395,0.0000022409718,7.7021355e-7,0.0000188109,0.0005042848,0.00002279612,0.00067999266,0.000033737222,0.0012052734,0.04507057],"study_design_scores_gemma":[0.00015912275,0.00008741731,0.9399556,0.000005419381,3.9760639e-7,0.0000010636721,0.0010794952,0.05759397,0.00003493228,0.00038966956,0.00060794264,0.000084984065],"about_ca_topic_score_codex":0.0011857349,"about_ca_topic_score_gemma":0.0021963243,"teacher_disagreement_score":0.33254656,"about_ca_system_score_codex":0.00007519998,"about_ca_system_score_gemma":0.0006235932,"threshold_uncertainty_score":0.9971769},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.063362490875996,"score_gpt":0.33576062768050635,"score_spread":0.27239813680451036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379794872","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":[0.996758,0.000116199786,0.000014403204,0.0011726491,0.00012477319,0.00044057376,0.0011090979,0.000022932812,0.00024135983],"genre_scores_gemma":[0.9987534,0.00008694152,0.00021586078,0.0005064013,0.00004330193,0.000005548335,0.000014778023,0.0000054300563,0.00036831573],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99781704,0.00013292792,0.00023075458,0.00055404037,0.0008871707,0.0003780964],"domain_scores_gemma":[0.9980608,0.0005371417,0.00018882933,0.0011071243,0.000015444746,0.000090608395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013578427,0.00014180502,0.0002239792,0.0000659532,0.0009818599,0.0001849782,0.0016098378,0.000015823669,0.00026483298],"category_scores_gemma":[0.00004731338,0.00007794888,0.000012061556,0.0009549997,0.0024117301,0.0011970942,0.0021855247,0.00016369786,0.000044476074],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020209776,0.00003677295,0.97538656,0.000005553472,0.00001005469,0.0000031978086,0.009604933,0.00023634903,0.00022997819,0.00020739285,0.014167882,0.000091118905],"study_design_scores_gemma":[0.00025879053,0.00010497943,0.96966594,0.00003061892,0.000020788082,6.866959e-7,0.02328176,0.0052491543,0.00006367887,0.00032194934,0.0008880647,0.000113578615],"about_ca_topic_score_codex":0.064533666,"about_ca_topic_score_gemma":0.13194564,"teacher_disagreement_score":0.067411974,"about_ca_system_score_codex":0.00010800414,"about_ca_system_score_gemma":0.00010808067,"threshold_uncertainty_score":0.9416957},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.057724232955457526,"score_gpt":0.33596203904594923,"score_spread":0.2782378060904917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390747461","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":[0.83555067,0.0011163218,0.052209023,0.08277759,0.005464083,0.0011899248,0.012385042,0.00006413661,0.0092432285],"genre_scores_gemma":[0.9988204,0.000040600215,0.0003362767,0.00024157764,0.00010900764,0.000004825942,0.00032506892,0.0000052013265,0.00011703767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886304,0.000032161486,0.00023597333,0.00025734803,0.00047445358,0.00013704062],"domain_scores_gemma":[0.9990812,0.00015058475,0.000109627064,0.0005159441,0.00010020996,0.000042445765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077063375,0.00007561437,0.00010067571,0.000051599618,0.0001975228,0.00011755346,0.00074828434,0.000016533133,0.000017323022],"category_scores_gemma":[0.0000151864915,0.000056961053,0.00003806238,0.0004363904,0.0003360939,0.0011374652,0.00023838221,0.0001212152,0.0000021030282],"study_design_candidate":"theoretical_or_conceptual","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":[0.000004792769,0.00005895122,0.0036132606,0.000015572594,0.000022664108,3.358769e-7,0.0010757267,0.009483384,0.00009115945,0.9739447,0.0026165056,0.009072937],"study_design_scores_gemma":[0.00012540391,0.00005257156,0.004294244,0.00033761165,0.00002139778,4.7991017e-7,0.0012098984,0.92308664,0.00015300226,0.06791875,0.0026584112,0.00014158717],"about_ca_topic_score_codex":0.00042822445,"about_ca_topic_score_gemma":0.00009910996,"teacher_disagreement_score":0.91360325,"about_ca_system_score_codex":0.00007250141,"about_ca_system_score_gemma":0.00033096824,"threshold_uncertainty_score":0.23228043},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University; McMaster University","funders":"","keywords":"Mental health; Psychology; Computer science; Psychiatry","score_opus":0.23042946996787192,"score_gpt":0.4631044083909127,"score_spread":0.2326749384230408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409271193","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":[0.9886967,0.00043620885,0.0003085846,0.0025345366,0.0012118251,0.00067543786,0.00318,0.00003664415,0.0029200504],"genre_scores_gemma":[0.9903339,0.00004879224,0.007052886,0.0015046247,0.000041027313,0.0000137966435,0.000827479,0.000009760898,0.0001677219],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99694675,0.00015618495,0.000537144,0.0012613686,0.00050161703,0.0005969284],"domain_scores_gemma":[0.99678063,0.0004527536,0.0002870775,0.002283489,0.000027183543,0.00016885763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025863505,0.00017253052,0.00025962957,0.00014399964,0.00061979995,0.000072889015,0.0028257167,0.000045842924,0.00012001047],"category_scores_gemma":[0.00044461343,0.00016106648,0.000010520351,0.0007872815,0.0007638414,0.00090382266,0.0026032322,0.00028394855,0.000018467741],"study_design_candidate":"observational","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":[0.00014887846,0.0007840581,0.24371691,0.0005674794,0.00004368452,0.0000034221,0.0141991405,0.000002704736,0.0036331974,0.00329584,0.044309508,0.6892952],"study_design_scores_gemma":[0.005136062,0.0011910647,0.8809414,0.0036112603,0.000040004838,0.000028091988,0.05036683,0.018564329,0.0016664859,0.00071529404,0.036693256,0.0010459066],"about_ca_topic_score_codex":0.0041187555,"about_ca_topic_score_gemma":0.0022495089,"teacher_disagreement_score":0.6882493,"about_ca_system_score_codex":0.00007161275,"about_ca_system_score_gemma":0.00034476255,"threshold_uncertainty_score":0.65681005},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03624091006558341,"score_gpt":0.26430469727780953,"score_spread":0.22806378721222612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412385652","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":[0.8507079,0.00030620254,0.023498354,0.00043481853,0.0007460475,0.00013868691,0.000011437452,0.0000828181,0.12407373],"genre_scores_gemma":[0.99876773,0.00001707068,0.00020589195,0.0006726653,0.000109277986,8.4902797e-7,0.00011048866,0.0000019278323,0.00011409274],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999248,3.4322295e-7,0.00015241088,0.00032379304,0.000090933456,0.00018446527],"domain_scores_gemma":[0.9995112,0.000012530357,0.00006460479,0.00037451333,0.000026911237,0.000010268726],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003854835,0.00006624349,0.00012921449,0.0002557147,0.00028117537,0.0014792422,0.0005304945,0.00001806899,0.000024518684],"category_scores_gemma":[0.00002524639,0.000056732064,0.000016307868,0.0013794722,0.00014010267,0.011789976,0.00029853382,0.000050815033,0.000045898578],"study_design_candidate":"simulation_or_modeling","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":[0.000060481365,0.0001851369,0.19786914,0.0001510419,0.00030672498,0.000004137093,0.000102194186,0.018494254,0.00023669109,0.56413996,0.041887417,0.17656285],"study_design_scores_gemma":[0.00016927114,0.0000029324904,0.06450276,0.000014472064,0.00017860613,2.1466234e-7,0.00031539475,0.7645676,0.000012520064,0.008965191,0.16109692,0.00017413718],"about_ca_topic_score_codex":0.00032526886,"about_ca_topic_score_gemma":0.0012569962,"teacher_disagreement_score":0.7460733,"about_ca_system_score_codex":0.000012604467,"about_ca_system_score_gemma":0.00002572438,"threshold_uncertainty_score":0.9995573},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.11659928807268619,"score_gpt":0.5068965799335734,"score_spread":0.39029729186088724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413745650","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":[0.97658014,0.00090119103,0.0037799696,0.0061154324,0.0007151207,0.00023926533,0.00007579374,0.000049015543,0.01154404],"genre_scores_gemma":[0.9957056,0.000018051576,0.00021989773,0.0010106066,0.000026593121,0.000012185647,0.00003146642,0.000004382212,0.0029711933],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979645,0.0001451888,0.00018490288,0.0009602122,0.00024433498,0.000500863],"domain_scores_gemma":[0.9982948,0.00028268652,0.000042008036,0.0011922802,0.000024284027,0.00016395756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002458202,0.00010246391,0.00014853996,0.00052127126,0.00036480723,0.00013243429,0.0013361252,0.000057233556,0.0001534404],"category_scores_gemma":[0.001045086,0.00008992921,0.000012624868,0.0009583331,0.0009411297,0.0005449839,0.00076462684,0.00031782984,0.0000862711],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037747042,0.0006746102,0.6767343,0.00021571758,0.00007136492,0.001034793,0.04482531,0.00003030173,0.00039779153,0.053458244,0.038108792,0.18407127],"study_design_scores_gemma":[0.0022597446,0.00006687111,0.9693982,0.00034584771,0.000022157443,0.00003247526,0.020605754,0.0031547481,0.000060054925,0.0009677325,0.0027398767,0.00034653308],"about_ca_topic_score_codex":0.0017547174,"about_ca_topic_score_gemma":0.0013926773,"teacher_disagreement_score":0.29266387,"about_ca_system_score_codex":0.00007261255,"about_ca_system_score_gemma":0.00028130432,"threshold_uncertainty_score":0.36672068},"labels":[],"label_agreement":null}]}