{"meta":{"query_hash":"09653c74ed9a","filters":{"venue":"Journal of Informetrics"},"cohort_total":24,"direct_labels_cover":7,"predictions_cover":24,"exported":24,"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/09653c74ed9a","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Informetrics"},"results":[{"id":"W1221429143","doi":"10.1016/j.joi.2015.08.002","title":"How to become an important player in scientific collaboration networks?","year":2015,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":88,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Publication; Computer science; Productivity; Quality (philosophy); Position (finance); Work (physics); Data science; Knowledge management; Business; Engineering","score_opus":0.02861058399649574,"score_gpt":0.29994983463309877,"score_spread":0.271339250636603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1221429143","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":[0.9041324,0.00013490723,0.093884766,0.00035674064,0.0004851342,0.00016172456,0.0000055983705,0.000012728113,0.00082599145],"genre_scores_gemma":[0.9912719,0.0000037641103,0.008075641,0.000047630372,0.00042875262,0.000002549457,0.0000130788985,0.000008255554,0.00014840742],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985888,0.000027843185,0.0006212418,0.00009487788,0.00045552212,0.00021168654],"domain_scores_gemma":[0.99805355,0.00004715278,0.00056392024,0.00019617664,0.00087667484,0.00026255127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016151352,0.00010477614,0.00025968978,0.0014263213,0.00005290531,0.00063376257,0.00027718814,0.000035413934,0.000019166979],"category_scores_gemma":[0.0001215727,0.00008847788,0.00007898083,0.0048103346,0.000018962906,0.0011079378,0.000051896855,0.00019902454,0.0000023257392],"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":[0.00012956528,0.00039194347,0.7938276,0.0000054885304,0.00011083604,0.000020370659,0.0015549647,0.050390955,0.00013867361,0.008269743,0.06434599,0.0808139],"study_design_scores_gemma":[0.005414414,0.003991776,0.08217112,0.00024325053,0.00028145066,0.00004777244,0.01733043,0.25201863,0.003126364,0.026266789,0.60718817,0.0019198755],"about_ca_topic_score_codex":0.000024358014,"about_ca_topic_score_gemma":0.000083726925,"teacher_disagreement_score":0.71165645,"about_ca_system_score_codex":0.00014773334,"about_ca_system_score_gemma":0.00026110417,"threshold_uncertainty_score":0.6111387},"labels":[],"label_agreement":null},{"id":"W1993562201","doi":"10.1016/j.joi.2014.01.003","title":"Counting and comparing publication output with and without equalizing and inflationary bias","year":2014,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":35,"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":"","keywords":"Ranking (information retrieval); Accreditation; Econometrics; Publication bias; Statistics; Differential (mechanical device); Computer science; Psychology; Actuarial science; Economics; Information retrieval; Mathematics; Political science; Law; Physics","score_opus":0.6028694960870139,"score_gpt":0.5223753468198439,"score_spread":0.08049414926717002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993562201","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":[0.9708526,0.0008300747,0.023130773,0.00043615812,0.00008599652,0.00007504528,0.0000011668034,0.000005476833,0.0045826975],"genre_scores_gemma":[0.99215126,0.0003894248,0.0070991362,0.00013857576,0.000070401824,5.150214e-7,6.8236346e-7,0.000005723141,0.00014430161],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99467325,0.0000748926,0.00089155283,0.00018657462,0.0039295717,0.00024417345],"domain_scores_gemma":[0.9897245,0.0038692812,0.001213045,0.00018787346,0.004637379,0.00036792568],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.02380218,0.00010488248,0.00032028157,0.041538224,0.00023783596,0.0030963866,0.00038572587,0.0000687047,0.0000066634025],"category_scores_gemma":[0.058910325,0.000064202315,0.000028292277,0.04789078,0.00014193263,0.0022004764,0.0002952331,0.00027165748,0.0000031680606],"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":[0.00001946364,0.000009529494,0.8382184,0.000009234125,0.000009827171,5.6375677e-7,0.00015524906,0.00003325488,0.000013015403,0.0009704842,0.00038444845,0.16017652],"study_design_scores_gemma":[0.00092651596,0.00034466645,0.9143086,0.00003148107,0.000011754796,0.00019220624,0.00049017626,0.058356095,0.000031867454,0.0012037498,0.023976535,0.0001263679],"about_ca_topic_score_codex":0.000017648834,"about_ca_topic_score_gemma":0.000004415027,"teacher_disagreement_score":0.16005014,"about_ca_system_score_codex":0.00004243861,"about_ca_system_score_gemma":0.000105773055,"threshold_uncertainty_score":0.9979385},"labels":[],"label_agreement":null},{"id":"W2004655250","doi":"10.1016/j.joi.2008.06.005","title":"Biomedical innovation at the laboratory, clinical and commercial interface: A new method for mapping research projects, publications and patents in the field of microarrays","year":2008,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Biomedical and Engineering Education","field":"Engineering","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; McGill University","funders":"National Institute of Mental Health; Office of Extramural Research, National Institutes of Health; Canadian Institutes of Health Research; Health Canada; National Institutes of Health","keywords":"Field (mathematics); Biomedicine; Data science; Computer science; Interface (matter); Software; Government (linguistics); Information retrieval; Bioinformatics","score_opus":0.16258717243686877,"score_gpt":0.4348576260224379,"score_spread":0.2722704535855691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004655250","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":[0.8737782,0.00080460816,0.11707667,0.007607296,0.00039642237,0.00025120616,0.000007802512,0.000007605546,0.00007017918],"genre_scores_gemma":[0.9718865,0.0014071679,0.0259382,0.0003555914,0.00034958453,0.000012678544,0.000006762602,0.000009840411,0.000033650787],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900556,0.000040838415,0.00055084523,0.000042093205,0.00023814451,0.00012250511],"domain_scores_gemma":[0.99804467,0.0014325181,0.00009630105,0.000078784855,0.00029982007,0.000047877267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033154835,0.000048900645,0.00012260859,0.0007558158,0.00007324055,0.000020967356,0.00014738605,0.0001011506,0.000003149223],"category_scores_gemma":[0.0037250058,0.000028332577,0.000021272435,0.0025890416,0.000092689355,0.000115784205,0.000034993507,0.00040367988,2.7287123e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011140841,0.00023713343,0.09509811,0.00075006846,0.00013947583,0.0000020404816,0.014489179,0.0000766595,0.003002563,0.00085542136,0.53460777,0.3506302],"study_design_scores_gemma":[0.0031949056,0.0011736371,0.47271648,0.00030733107,0.00003831919,0.000246268,0.00601841,0.015626755,0.0025438347,0.0005001137,0.49736446,0.00026947522],"about_ca_topic_score_codex":0.000020529058,"about_ca_topic_score_gemma":0.000005503285,"teacher_disagreement_score":0.37761837,"about_ca_system_score_codex":0.000035292043,"about_ca_system_score_gemma":0.00013194642,"threshold_uncertainty_score":0.4459449},"labels":[],"label_agreement":null},{"id":"W2041260947","doi":"10.1016/j.joi.2010.07.005","title":"What's familiar is excellent: The impact of exposure effect on perceived journal quality","year":2010,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Knowledge Management and Sharing","field":"Social Sciences","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Lakehead University","funders":"","keywords":"Ranking (information retrieval); Journal ranking; Preference; Psychology; Interpretation (philosophy); Quality (philosophy); Perception; Test (biology); Field (mathematics); Statistics; Computer science; Information retrieval; Library science; Epistemology; Mathematics; Citation; Philosophy","score_opus":0.03543923403875162,"score_gpt":0.38120894412437206,"score_spread":0.34576971008562046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041260947","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":[0.96666956,0.00023020287,0.000040121744,0.0002908707,0.0022104986,0.00012859068,0.0000012974198,0.0000052916657,0.03042356],"genre_scores_gemma":[0.99638057,0.001845298,0.00005903848,0.000082348895,0.0007922848,4.5584247e-7,2.2157731e-7,0.0000071433183,0.00083264627],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9975993,0.00021408674,0.0007494767,0.000065425425,0.0010816219,0.00029009185],"domain_scores_gemma":[0.9969495,0.00096792885,0.0010536457,0.00019123763,0.0006548114,0.00018287546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007849666,0.0001348015,0.0003261236,0.0006641998,0.00047166244,0.0005191746,0.0007701939,0.00013017851,0.00031126998],"category_scores_gemma":[0.0034098122,0.000073334115,0.0006114868,0.0010907174,0.00015437382,0.0012875905,0.000060710794,0.00097360567,0.000022005734],"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":[0.0006090593,0.00045062607,0.25033572,0.00011143116,0.00068456685,0.000034481996,0.13643035,0.0002484006,0.0016724867,0.0024916944,0.02568338,0.5812478],"study_design_scores_gemma":[0.0021982312,0.0031734582,0.92754024,0.00021455735,0.00013324512,0.000029484674,0.029353436,0.00008931986,0.0005049774,0.0012365634,0.035203036,0.00032345622],"about_ca_topic_score_codex":0.00016166453,"about_ca_topic_score_gemma":0.00007743726,"teacher_disagreement_score":0.6772045,"about_ca_system_score_codex":0.00014483937,"about_ca_system_score_gemma":0.0002525846,"threshold_uncertainty_score":0.5006413},"labels":[],"label_agreement":null},{"id":"W2062524032","doi":"10.1016/j.joi.2013.04.005","title":"Web traffic and organization performance measures: Relationships and data sources examined","year":2013,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Web visibility and informetrics","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Webometrics; Web traffic; Hyperlink; Computer science; World Wide Web; The Internet; Web page","score_opus":0.05613253156085697,"score_gpt":0.23673782459212364,"score_spread":0.18060529303126666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062524032","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":[0.9435187,0.00072171487,0.05488941,0.0002757384,0.00016027066,0.00010581314,0.0000019763568,0.000025624506,0.00030076096],"genre_scores_gemma":[0.9755023,0.0024409597,0.021827618,0.00011874874,0.00005926893,3.7325893e-7,0.00000362956,0.000005525113,0.000041552077],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985312,0.000034706547,0.00062584685,0.00013619493,0.00050403236,0.00016801778],"domain_scores_gemma":[0.99771154,0.00048779757,0.0004655732,0.00042674397,0.00074408844,0.00016426803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018656439,0.000110970475,0.00018518309,0.0011989267,0.000218403,0.0005359854,0.0008510167,0.00009891752,0.00000798178],"category_scores_gemma":[0.005196332,0.00008615638,0.000017021366,0.0036234816,0.00005957503,0.0068376497,0.00033470528,0.00032738034,0.00001385087],"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":[0.0000086051605,0.00006963426,0.19500124,0.00010215428,0.000045694764,0.000002030236,0.0017488046,0.0008346569,0.000042232266,0.0008505114,0.0035011552,0.79779327],"study_design_scores_gemma":[0.00093603745,0.00045588074,0.74449277,0.000050697905,0.000022366658,0.00035022324,0.00042722817,0.23688346,0.0001255254,0.00011928131,0.015884284,0.00025223393],"about_ca_topic_score_codex":0.000002560386,"about_ca_topic_score_gemma":0.000001950714,"teacher_disagreement_score":0.797541,"about_ca_system_score_codex":0.000046259323,"about_ca_system_score_gemma":0.00020063692,"threshold_uncertainty_score":0.622087},"labels":[],"label_agreement":null},{"id":"W2084394153","doi":"10.1016/j.joi.2014.08.002","title":"On the citation lifecycle of papers with delayed recognition","year":2014,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Citation; Period (music); History; Computer science; Library science; Art","score_opus":0.4451528031489057,"score_gpt":0.4940995388492365,"score_spread":0.04894673570033081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084394153","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":[0.951852,0.00006615481,0.015718821,0.0008022254,0.0003861642,0.00011038734,0.000008188403,0.0000031403035,0.031052882],"genre_scores_gemma":[0.9973194,0.00013076689,0.0019708334,0.00034652572,0.00007492804,8.901943e-7,8.454812e-7,0.0000051483803,0.00015068268],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9906089,0.00015404541,0.00095786306,0.00011451167,0.007947132,0.00021758441],"domain_scores_gemma":[0.97220755,0.018820189,0.0015762856,0.00032728445,0.0068628723,0.00020584333],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.02585763,0.00008693258,0.00024140731,0.04640892,0.00011767154,0.00050835125,0.0010541314,0.0000682532,0.0002500326],"category_scores_gemma":[0.13636468,0.000038466806,0.00014463886,0.13701229,0.00009807595,0.00056153967,0.000065469736,0.0003060749,0.00006279257],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040489365,0.00017182385,0.015962537,0.00000778089,0.00006161419,0.0000039011998,0.0002589644,0.00093393505,0.00034839878,0.0037765827,0.017725358,0.9603442],"study_design_scores_gemma":[0.007815254,0.030693645,0.6575505,0.00028557726,0.00014818774,0.00026101398,0.0068695913,0.026439797,0.018345818,0.14299807,0.10764584,0.0009466815],"about_ca_topic_score_codex":0.000007660648,"about_ca_topic_score_gemma":0.000002820761,"teacher_disagreement_score":0.95939755,"about_ca_system_score_codex":0.00006553471,"about_ca_system_score_gemma":0.00016329857,"threshold_uncertainty_score":0.9643992},"labels":[],"label_agreement":null},{"id":"W2092739591","doi":"10.1016/j.joi.2009.12.001","title":"Combining commercial citation indexes and open-access bibliographic databases to delimit highly interdisciplinary research fields for citation analysis","year":2010,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Stem Cell Network","keywords":"Citation; Scientometrics; Scopus; Computer science; Field (mathematics); Data science; Citation analysis; Bibliometrics; Information retrieval; Citation database; World Wide Web; MEDLINE; Political science; Mathematics","score_opus":0.7928641188145871,"score_gpt":0.6879661796861452,"score_spread":0.10489793912844192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092739591","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":[0.9036646,0.00015210477,0.091467895,0.0024353494,0.00088694255,0.00043593667,0.00007825988,0.0000052539845,0.0008736557],"genre_scores_gemma":[0.9831178,0.00034456886,0.015981695,0.0002786119,0.00015281807,0.000016221657,0.000017284887,0.000009859153,0.00008111616],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99010926,0.00020628335,0.0016145251,0.00038700708,0.007141712,0.0005411944],"domain_scores_gemma":[0.96002716,0.021608217,0.0009846956,0.0005705445,0.016105654,0.0007037154],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.05869103,0.00015279908,0.0005735782,0.48406318,0.000734689,0.011320538,0.0048370166,0.00015494044,0.000077305165],"category_scores_gemma":[0.10494123,0.00010940261,0.00025612794,0.59861636,0.00018346072,0.006110222,0.00438198,0.0009325778,0.000007934746],"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":[0.0004482073,0.00022502754,0.59348595,0.000020180149,0.00020528183,0.000009253269,0.0008784445,0.00032440643,0.000417366,0.0022819794,0.059336856,0.34236702],"study_design_scores_gemma":[0.001301745,0.0015994317,0.9647441,0.00002703627,0.00009713349,0.000017153068,0.0021413828,0.005401949,0.0005542421,0.012551223,0.011320458,0.00024416635],"about_ca_topic_score_codex":0.00017384371,"about_ca_topic_score_gemma":0.00066864456,"teacher_disagreement_score":0.3712581,"about_ca_system_score_codex":0.000060177947,"about_ca_system_score_gemma":0.00034348725,"threshold_uncertainty_score":0.9897058},"labels":[],"label_agreement":null},{"id":"W2129840456","doi":"10.1016/j.joi.2009.03.010","title":"Modeling a century of citation distributions","year":2009,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Complex Systems and Time Series Analysis","field":"Economics, Econometrics and Finance","cited_by":143,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Citation; Computer science; Function (biology); Simple (philosophy); Set (abstract data type); Mathematical economics; Econometrics; Mathematics; Epistemology; Library science; Philosophy","score_opus":0.03318613078372981,"score_gpt":0.22461751359315724,"score_spread":0.19143138280942743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129840456","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":[0.52031654,0.00664136,0.45611846,0.00044605575,0.00047636678,0.000095907846,0.0001303104,0.00000911957,0.015765881],"genre_scores_gemma":[0.99661744,0.000534031,0.0026777757,0.000033335687,0.00007506856,2.074494e-7,0.0000061516744,0.0000031259453,0.000052878477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851173,0.0000038443145,0.0012327937,0.00005638079,0.00007639603,0.0001188775],"domain_scores_gemma":[0.99852747,0.00003188783,0.0009774502,0.00011777845,0.00028439803,0.0000610473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005592057,0.000067231704,0.00036304115,0.0010766503,0.000047457328,0.000036640966,0.00014480372,0.000047821366,0.00008694271],"category_scores_gemma":[0.0004705535,0.00006552786,0.0002565494,0.0015221012,0.000010130742,0.00037520644,0.000011824326,0.00010611179,0.000013624393],"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":[0.0000839723,0.00033853395,0.01626334,0.00007751512,0.0003555415,0.000007081393,0.001035291,0.0507536,0.00007342836,0.8896799,0.0013972773,0.03993452],"study_design_scores_gemma":[0.003594837,0.0023368048,0.0859136,0.00022013536,0.0001874963,0.00015728979,0.0024479176,0.610596,0.00018332285,0.16661426,0.12679552,0.0009528384],"about_ca_topic_score_codex":0.000048941984,"about_ca_topic_score_gemma":0.0000021096776,"teacher_disagreement_score":0.7230656,"about_ca_system_score_codex":0.000085426494,"about_ca_system_score_gemma":0.000026307576,"threshold_uncertainty_score":0.26721486},"labels":[],"label_agreement":null},{"id":"W2134386090","doi":"10.1016/j.joi.2010.04.001","title":"The development of an AI journal ranking based on the revealed preference approach","year":2010,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Ranking (information retrieval); Journal ranking; Impact factor; Citation; Preference; Computer science; Index (typography); Information retrieval; Field (mathematics); Citation analysis; Domain (mathematical analysis); Library science; Data science; Operations research; Statistics; World Wide Web; Mathematics; Political science","score_opus":0.578649466269294,"score_gpt":0.5307756849711357,"score_spread":0.047873781298158335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134386090","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":[0.9258365,0.0001783194,0.05949329,0.0012445912,0.0016322633,0.00025201324,0.0000045456936,0.000004447551,0.011354001],"genre_scores_gemma":[0.9684832,0.00007673225,0.030764908,0.00027567046,0.00017870929,0.0000019728832,3.8600305e-7,0.000008352406,0.00021008316],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98194844,0.00029310005,0.002368455,0.00018161055,0.014692408,0.00051597465],"domain_scores_gemma":[0.97017926,0.014804917,0.0027784656,0.0008279893,0.010904237,0.00050510635],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication","open_science"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.10649229,0.00016240048,0.00036751365,0.04023067,0.0010362114,0.003272895,0.005699869,0.00013954286,0.00012183549],"category_scores_gemma":[0.13048086,0.0000635925,0.0002634895,0.112865664,0.00022542883,0.0010144822,0.000268404,0.00200126,0.000016381568],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024905172,0.0003844371,0.024839312,0.000008932821,0.000048664937,0.00001010842,0.00070714985,0.0008745607,0.00063838705,0.001544114,0.007483589,0.9632117],"study_design_scores_gemma":[0.00437344,0.0028759788,0.57301503,0.00011713478,0.00004966682,0.0005630559,0.005224383,0.13341539,0.010527979,0.013850848,0.25525907,0.0007280212],"about_ca_topic_score_codex":0.0000017913493,"about_ca_topic_score_gemma":0.0000060879393,"teacher_disagreement_score":0.96248364,"about_ca_system_score_codex":0.000115140734,"about_ca_system_score_gemma":0.0020007158,"threshold_uncertainty_score":0.99967974},"labels":[{"model":"gemma","categories":["bibliometrics"],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["bibliometrics","metaresearch"],"domain":"evaluation","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2150897866","doi":"10.1016/j.joi.2011.06.002","title":"Comparing the expert survey and citation impact journal ranking methods: Example from the field of Artificial Intelligence","year":2011,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":81,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Lakehead University","funders":"","keywords":"Ranking (information retrieval); Journal ranking; Consistency (knowledge bases); Citation; Computer science; Information retrieval; Quality (philosophy); Field (mathematics); Data science; Publication; Artificial intelligence; World Wide Web; Mathematics; Advertising; Business","score_opus":0.8625684102688479,"score_gpt":0.6369410142134144,"score_spread":0.22562739605543347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150897866","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":[0.5615881,0.0022181908,0.4349326,0.00013351964,0.0006724619,0.00007362675,0.0000043350547,0.0000015059006,0.00037563278],"genre_scores_gemma":[0.97607017,0.0012683419,0.022322671,0.0001675551,0.00015703747,4.19767e-7,4.2564298e-7,0.000004980884,0.000008424648],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99194014,0.0008160906,0.0019500357,0.00014713588,0.0048192125,0.00032740814],"domain_scores_gemma":[0.9023029,0.086997874,0.0027231907,0.0004984051,0.0071674604,0.0003101496],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.08664001,0.000123222,0.00041758054,0.01888852,0.00035187474,0.0015906361,0.0023434958,0.00008944279,0.00030318118],"category_scores_gemma":[0.17506737,0.00005168754,0.00024581308,0.07359594,0.0001724134,0.0010907243,0.00034796426,0.00071054953,0.000004361861],"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":[0.00021126788,0.000049223167,0.27211764,0.0000010286726,0.00006666061,0.0000036340602,0.004415684,0.00008648844,0.00014133003,0.00023751201,0.0036487414,0.7190208],"study_design_scores_gemma":[0.00026388853,0.0006688722,0.94814044,0.000025861615,0.000017666032,0.00008378363,0.0072478727,0.0105721485,0.0042047314,0.02746362,0.0011812288,0.00012990696],"about_ca_topic_score_codex":0.002950919,"about_ca_topic_score_gemma":0.00009245669,"teacher_disagreement_score":0.7188909,"about_ca_system_score_codex":0.000072107985,"about_ca_system_score_gemma":0.00028029107,"threshold_uncertainty_score":0.9994458},"labels":[],"label_agreement":null},{"id":"W2191720934","doi":"10.1016/j.joi.2015.09.003","title":"Are top-cited papers more interdisciplinary?","year":2015,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Interdisciplinary Research and Collaboration","field":"Decision Sciences","cited_by":144,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université de Montréal","funders":"Humanities and Social Sciences Youth Foundation, Ministry of Education of the People's Republic of China; Fonds de Recherche du Québec-Société et Culture; National Office for Philosophy and Social Sciences; Ministry of Education of the People's Republic of China","keywords":"Citation; Bibliometrics; Citation impact; Rank (graph theory); Computer science; Focus (optics); Citation analysis; Percentile; Data science; Percentile rank; Library science; Information retrieval; Statistics; Mathematics","score_opus":0.1625741757646505,"score_gpt":0.461230812010258,"score_spread":0.2986566362456075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2191720934","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":[0.9072387,0.00037560685,0.004229239,0.010810909,0.0020956497,0.00017471636,0.000020174795,0.000018269948,0.075036734],"genre_scores_gemma":[0.9938337,0.000009749548,0.0009988385,0.00038476262,0.00043555588,0.0000015395867,0.0000016741477,0.000008486495,0.004325695],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99467814,0.00009176932,0.0012043933,0.00013577181,0.003602813,0.00028712803],"domain_scores_gemma":[0.9924446,0.00058144674,0.0015075755,0.00033280166,0.004641754,0.000491819],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005143026,0.00012994104,0.00035111437,0.0026961046,0.00013995926,0.000564661,0.0011464859,0.000099295234,0.0001592671],"category_scores_gemma":[0.013928972,0.00008007385,0.00020721677,0.006532171,0.00009178272,0.0014923253,0.0005768408,0.00038367015,0.00018208614],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016800658,0.00024866866,0.080892555,0.0000138659125,0.000102542566,0.0005347956,0.0076941545,0.002152574,0.00018407621,0.0008710309,0.776254,0.12937166],"study_design_scores_gemma":[0.0053291246,0.0060817376,0.18722457,0.00020613322,0.000059145797,0.0012321167,0.31269786,0.007620133,0.0015974436,0.03228666,0.44488564,0.00077944214],"about_ca_topic_score_codex":8.6597436e-7,"about_ca_topic_score_gemma":0.000016762631,"teacher_disagreement_score":0.3313684,"about_ca_system_score_codex":0.00025119394,"about_ca_system_score_gemma":0.00045333683,"threshold_uncertainty_score":0.99437714},"labels":[],"label_agreement":null},{"id":"W2624878181","doi":"10.1016/j.joi.2017.05.002","title":"Predicting the age of researchers using bibliometric data","year":2017,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Predictive power; Proxy (statistics); Linear regression; Statistics; Regression analysis; Linear model; Predictive modelling; Regression; Computer science; Econometrics; Demography; Mathematics","score_opus":0.9265886468305123,"score_gpt":0.6788366096396239,"score_spread":0.24775203719088845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624878181","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":[0.97202164,0.0032995353,0.011462543,0.00074799673,0.0016024617,0.00022597738,0.00009184606,0.0000049184064,0.010543075],"genre_scores_gemma":[0.991174,0.001995039,0.006082259,0.00005390812,0.00030438654,3.2638633e-7,0.0000019015642,0.0000125059,0.00037567844],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9759151,0.00023794973,0.0023295966,0.0003254248,0.020500913,0.0006910502],"domain_scores_gemma":[0.94990224,0.02102988,0.006678452,0.005444531,0.016290773,0.00065410975],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication","open_science"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.121967174,0.0001547612,0.0005692417,0.53863,0.0009983619,0.0065729124,0.021457842,0.00015282328,0.00011422231],"category_scores_gemma":[0.587162,0.00008024789,0.00027559837,0.67729837,0.00067360053,0.0048652748,0.0052293884,0.00096058304,0.00002042498],"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":[0.000051026127,0.00008953251,0.64308447,0.000015217658,0.00006979349,0.000060864546,0.00012445301,0.00017931337,0.00036428694,0.00010244322,0.010309351,0.3455493],"study_design_scores_gemma":[0.0010566734,0.00052354345,0.90057963,0.000054961165,0.000041703777,0.00015292803,0.0013717499,0.03288492,0.00064295804,0.0016581863,0.06085078,0.00018196274],"about_ca_topic_score_codex":0.0002959062,"about_ca_topic_score_gemma":0.000010978725,"teacher_disagreement_score":0.46519488,"about_ca_system_score_codex":0.00015883385,"about_ca_system_score_gemma":0.0010531151,"threshold_uncertainty_score":0.9944584},"labels":[],"label_agreement":null},{"id":"W2736387275","doi":"10.1016/j.joi.2017.07.003","title":"DataCite as a novel bibliometric source: Coverage, strengths and limitations","year":2017,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Research Data Management Practices","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Ministerio de Economía y Competitividad; European Commission","keywords":"Bibliometrics; Open data; Value (mathematics); Scientometrics; Production (economics); Open source","score_opus":0.14822043850723518,"score_gpt":0.4057818156424827,"score_spread":0.2575613771352475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736387275","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":[0.03325908,0.00036496116,0.9441281,0.0016219808,0.00035933344,0.0001113121,0.00001666338,0.000014507123,0.020124054],"genre_scores_gemma":[0.82623017,0.046298936,0.12259447,0.0005813465,0.00020848164,0.0000026919965,0.0000071165055,0.000014856067,0.004061934],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978737,0.000025213996,0.0004853805,0.00015361427,0.0011969991,0.00026508357],"domain_scores_gemma":[0.99396294,0.0027228063,0.0014331597,0.0010407802,0.00059207436,0.00024824045],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["bibliometrics","scholarly_communication"],"category_scores_codex":[0.0024860909,0.00010946318,0.0001828057,0.033697996,0.00044079038,0.017304137,0.003552781,0.000047204347,0.0000035634862],"category_scores_gemma":[0.07102973,0.00008948933,0.000059189486,0.021948336,0.0000723594,0.11098276,0.0015643623,0.0003776359,0.0000134537895],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021145494,0.00014688088,0.0060075573,0.00004342084,0.00012908781,0.000065248154,0.00011980323,0.00011259496,0.000041747215,0.062392987,0.00411018,0.9268094],"study_design_scores_gemma":[0.0014089049,0.0005580144,0.14347853,0.000038102527,0.000031892243,0.00027052243,0.00010735784,0.0046061426,0.000079904356,0.00059218315,0.84863436,0.00019407908],"about_ca_topic_score_codex":0.000032405187,"about_ca_topic_score_gemma":0.0000045038487,"teacher_disagreement_score":0.92661524,"about_ca_system_score_codex":0.00004646216,"about_ca_system_score_gemma":0.00019534807,"threshold_uncertainty_score":0.99884063},"labels":[{"model":"gemma","categories":["bibliometrics"],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2762227057","doi":"10.1016/j.joi.2017.08.008","title":"Mapping science using Library of Congress Subject Headings","year":2017,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Subject (documents); Library of congress; Computer science; Information retrieval; Library science; Library of Congress Classification; Data science; Library classification","score_opus":0.6384368990329121,"score_gpt":0.5833211230820153,"score_spread":0.055115775950896784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2762227057","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":[0.9748696,0.0005421247,0.0044210674,0.00024239764,0.0020624148,0.00009437589,0.000014974763,0.0000044728304,0.01774855],"genre_scores_gemma":[0.98688066,0.00053864165,0.011858002,0.00006332413,0.00013767152,1.7040603e-7,1.5265884e-7,0.000008588626,0.00051281543],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98470527,0.00004818306,0.0018066365,0.00025140063,0.012602639,0.0005858891],"domain_scores_gemma":[0.9825504,0.003134933,0.0044447468,0.0010091577,0.008259776,0.00060102943],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication","open_science"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.036379527,0.0001379398,0.0005627316,0.15875909,0.0008683075,0.0065993713,0.008046128,0.000102552665,0.00016132419],"category_scores_gemma":[0.16882387,0.000090465175,0.00028915354,0.18151087,0.0010716353,0.009738696,0.0016195731,0.0004331194,0.000019386485],"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":[0.000055519893,0.00009712867,0.73172945,0.00002332576,0.000027484037,0.000053145643,0.0002860258,0.00012497231,0.0062505947,0.0008795857,0.005254867,0.2552179],"study_design_scores_gemma":[0.0019365711,0.00087186147,0.83449596,0.00022243733,0.00001910701,0.0004167346,0.0020466389,0.019352091,0.067934565,0.0065845875,0.06565077,0.00046868995],"about_ca_topic_score_codex":0.000038306513,"about_ca_topic_score_gemma":6.147794e-7,"teacher_disagreement_score":0.2547492,"about_ca_system_score_codex":0.0001480388,"about_ca_system_score_gemma":0.0018544471,"threshold_uncertainty_score":0.99732083},"labels":[{"model":"gemma","categories":["bibliometrics"],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2781044009","doi":"10.1016/j.joi.2017.12.005","title":"On the relationships between bibliographic characteristics of scientific documents and citation and Mendeley readership counts: A large-scale analysis of Web of Science publications","year":2018,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Audience measurement; Citation; Citation analysis; Altmetrics; Discipline; Web of science; Set (abstract data type); Citation impact","score_opus":0.4491389199918624,"score_gpt":0.49777142617191705,"score_spread":0.04863250618005466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2781044009","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":[0.9939219,0.0001248581,0.0022154434,0.00022388055,0.00014610111,0.000082073064,0.000112263064,0.000001427921,0.0031720856],"genre_scores_gemma":[0.9987865,0.00027238522,0.00081554515,0.000011951695,0.000015754127,5.328227e-7,0.0000029553614,0.0000022041047,0.000092150534],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9931503,0.000096676646,0.0011151342,0.00016244117,0.005285262,0.00019020835],"domain_scores_gemma":[0.9817904,0.0054090098,0.0017132147,0.000370009,0.010542318,0.00017501823],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.03880285,0.000065190834,0.00029894317,0.26318964,0.00032209186,0.00070976914,0.0009078757,0.00006207877,0.00008298349],"category_scores_gemma":[0.055954557,0.000038882026,0.00010066127,0.5223318,0.0014569421,0.00094682333,0.0001484987,0.00020054523,0.0000030396816],"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":[0.000012159795,0.0000655792,0.97889674,0.0000084560625,0.00008784457,7.866167e-8,0.00052524096,0.000002166752,0.00023131889,0.007932939,0.0017284163,0.010509042],"study_design_scores_gemma":[0.00016808382,0.00022137139,0.99130833,0.000015346699,0.00009359846,0.0000011023924,0.0009438558,0.0026903632,0.0002791467,0.0027857246,0.0014506887,0.00004241627],"about_ca_topic_score_codex":0.0000062309646,"about_ca_topic_score_gemma":0.0000050641333,"teacher_disagreement_score":0.25914213,"about_ca_system_score_codex":0.000034745724,"about_ca_system_score_gemma":0.00036180936,"threshold_uncertainty_score":0.98975474},"labels":[],"label_agreement":null},{"id":"W2908106500","doi":"10.1016/j.joi.2018.12.005","title":"Comparing journal and paper level classifications of science","year":2019,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":95,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Computer science; Bibliometrics; Information retrieval; Robustness (evolution); Discipline; Data science; Data mining; Social science; Sociology","score_opus":0.7615079244057587,"score_gpt":0.5814149810599263,"score_spread":0.18009294334583237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908106500","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":[0.97742826,0.0009921509,0.006927924,0.0003412193,0.0010780166,0.00008019164,0.000005367358,0.0000018178048,0.01314503],"genre_scores_gemma":[0.9908,0.0008836331,0.007609293,0.00006906245,0.000064093445,1.5869284e-7,1.0208281e-7,0.0000042267143,0.0005694132],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9866026,0.00005301276,0.0016999821,0.00017411028,0.011073798,0.00039648317],"domain_scores_gemma":[0.98019916,0.003468207,0.0019464537,0.00040033722,0.013415924,0.0005698986],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.04101369,0.00009900937,0.00042341824,0.11096243,0.0002802733,0.0019241725,0.0026072976,0.00007132521,0.00021524915],"category_scores_gemma":[0.06266278,0.000060961127,0.0001600715,0.19337851,0.0005928454,0.0033660943,0.00047166809,0.0005731593,0.000049581813],"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":[0.000052734624,0.00014257598,0.8050559,0.000013781682,0.000033738,0.0000067581223,0.0004309151,0.00026437247,0.012543892,0.00492798,0.005962202,0.17056514],"study_design_scores_gemma":[0.0009957056,0.0006346954,0.9617082,0.000032298813,0.0000119226825,0.00045492034,0.0022447843,0.004562397,0.001810222,0.0033781056,0.024030086,0.00013669241],"about_ca_topic_score_codex":0.000006436821,"about_ca_topic_score_gemma":0.0000010642685,"teacher_disagreement_score":0.17042845,"about_ca_system_score_codex":0.0001693561,"about_ca_system_score_gemma":0.0011633858,"threshold_uncertainty_score":0.99911195},"labels":[],"label_agreement":null},{"id":"W2967837635","doi":"10.1016/j.joi.2019.07.004","title":"Analyzing linguistic complexity and scientific impact","year":2019,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Qinglan Project of Jiangsu Province of China; Major Program of National Fund of Philosophy and Social Science of China","keywords":"Computer science; Linguistics; Linguistic sequence complexity; Natural language processing; Data science; Philosophy","score_opus":0.024388254781145414,"score_gpt":0.3143265421653923,"score_spread":0.2899382873842469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967837635","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":[0.5171636,0.00822198,0.47243974,0.000119735,0.0010382739,0.00010479005,0.0000021252592,0.000085849795,0.0008239539],"genre_scores_gemma":[0.70052755,0.000016819251,0.299332,0.000027259493,0.00003783292,6.629558e-8,2.7746646e-7,0.000002600428,0.000055576107],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99897677,0.000014384299,0.00035748928,0.00009936048,0.00037739114,0.00017459375],"domain_scores_gemma":[0.9984486,0.00015597405,0.00046788173,0.00022301023,0.0005958303,0.00010868828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011345848,0.00008780943,0.00019699318,0.0012288113,0.00008514188,0.0006589502,0.0006823311,0.000044834676,0.000008700011],"category_scores_gemma":[0.0012406965,0.000060684546,0.00008380615,0.002072843,0.000059910406,0.00093755074,0.00019009557,0.00027878687,0.000007115701],"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":[0.000088003406,0.00020673526,0.24124597,0.00047463807,0.00022138451,0.00021615521,0.0048586614,0.00019265628,0.006588845,0.19966556,0.0044340827,0.5418073],"study_design_scores_gemma":[0.0049518244,0.005495757,0.14542256,0.0015727615,0.00018358951,0.006089255,0.00031824285,0.21607204,0.028236322,0.5646284,0.024331074,0.0026981656],"about_ca_topic_score_codex":0.0000074110353,"about_ca_topic_score_gemma":7.124311e-7,"teacher_disagreement_score":0.5391091,"about_ca_system_score_codex":0.00009304599,"about_ca_system_score_gemma":0.00017701191,"threshold_uncertainty_score":0.6354272},"labels":[],"label_agreement":null},{"id":"W3032915873","doi":"10.1016/j.joi.2020.101041","title":"Early-stage reciprocity in sustainable scientific collaboration","year":2020,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Population and Public Health; China Postdoctoral Science Foundation; King Saud University","keywords":"Reciprocity (cultural anthropology); Sustainability; Teamwork; Altruism (biology); Sustainable development; Computer science; Knowledge management; Business; Political science; Sociology; Economics; Psychology; Management; Social psychology; Social science","score_opus":0.017741395700650812,"score_gpt":0.27440477691771387,"score_spread":0.25666338121706306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032915873","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":[0.9585823,0.00007071118,0.031953946,0.00035562395,0.000078422585,0.00014259314,0.000004804761,0.000013013325,0.008798577],"genre_scores_gemma":[0.9960714,0.0000054128286,0.0029852786,0.00005645227,0.0001835084,0.0000014729442,0.0000041919243,0.000005600501,0.00068667694],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99883884,0.000023213724,0.0005365516,0.000078630896,0.00033275434,0.00019003525],"domain_scores_gemma":[0.9985138,0.00006193089,0.0004960751,0.00009598664,0.00072996155,0.00010225042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007177897,0.00007856038,0.00021380378,0.0006826236,0.00008413639,0.0002766599,0.00022354335,0.000027440297,0.00012862355],"category_scores_gemma":[0.00019004961,0.00007095079,0.00009824798,0.0057001286,0.00002818584,0.0007429281,0.00006349855,0.0002492592,0.0000064397723],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018065648,0.0002649607,0.8275644,0.00008510716,0.0001452885,0.000049140934,0.005054066,0.005948918,0.00044879076,0.07810176,0.03944029,0.0427166],"study_design_scores_gemma":[0.0027046797,0.0010731223,0.07065767,0.00008227421,0.00011853847,0.0000027767894,0.015661849,0.018292792,0.009268406,0.012416641,0.868996,0.0007252058],"about_ca_topic_score_codex":0.000051902753,"about_ca_topic_score_gemma":0.0000040408418,"teacher_disagreement_score":0.82955575,"about_ca_system_score_codex":0.00010037732,"about_ca_system_score_gemma":0.0002521278,"threshold_uncertainty_score":0.2893289},"labels":[],"label_agreement":null},{"id":"W3115533035","doi":"10.1016/j.joi.2020.101124","title":"Exploring the interdisciplinarity patterns of highly cited papers","year":2020,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université de Montréal","funders":"National Office for Philosophy and Social Sciences","keywords":"Computer science; Data science; Bibliometrics; Information retrieval; World Wide Web","score_opus":0.7915538673463653,"score_gpt":0.540354756721656,"score_spread":0.25119911062470934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115533035","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":[0.9832191,0.00021952298,0.007797399,0.0042846175,0.0007978045,0.00009901529,0.00002178753,0.000005640619,0.0035551523],"genre_scores_gemma":[0.99818474,0.0006638176,0.00051278423,0.00035665493,0.00018904897,0.0000010789245,4.5068538e-7,0.000006738394,0.000084659405],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9885271,0.00011164795,0.0017717608,0.0001793483,0.009060611,0.0003494958],"domain_scores_gemma":[0.9864179,0.0062540085,0.0015167717,0.00041082143,0.0048870007,0.00051350374],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.014953543,0.00012721922,0.0004413208,0.04018199,0.00014953327,0.00083033653,0.0033085796,0.00005683511,0.00016279289],"category_scores_gemma":[0.0823548,0.00006357809,0.0003950083,0.19905947,0.00009759679,0.001463883,0.0009447991,0.0006211129,0.00003357273],"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":[0.00018131682,0.00013200495,0.36896878,0.000035729536,0.00009770814,0.0000447281,0.0032025396,0.0005698271,0.0009917931,0.0008397754,0.007894688,0.6170411],"study_design_scores_gemma":[0.0012123319,0.0017710455,0.89816916,0.000045394376,0.000032070868,0.000051922692,0.009519179,0.0028481889,0.006095413,0.00079033535,0.07922098,0.00024399467],"about_ca_topic_score_codex":0.000014560274,"about_ca_topic_score_gemma":0.0000022514587,"teacher_disagreement_score":0.6167971,"about_ca_system_score_codex":0.00008873425,"about_ca_system_score_gemma":0.00021101936,"threshold_uncertainty_score":0.97069675},"labels":[{"model":"gemma","categories":["metaresearch","bibliometrics"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4213241381","doi":"10.1016/j.joi.2022.101256","title":"Female inventors over time: Factors affecting female Inventors’ innovation performance","year":2022,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Innovation Policy and R&D","field":"Economics, Econometrics and Finance","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"HEC Montréal","keywords":"Business; Production (economics); European patent office; Panel data; Demographic economics; Industrial organization; Economics; International trade; Microeconomics","score_opus":0.0561466103949233,"score_gpt":0.24998779703667268,"score_spread":0.19384118664174937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213241381","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":[0.98480004,0.0001922441,0.00033342006,0.00008556531,0.0014394544,0.00012154307,0.000046937737,0.000017948962,0.012962867],"genre_scores_gemma":[0.99656403,0.000053623844,0.000313246,0.0007563661,0.00027360016,0.0000032577498,0.00002596528,0.000024282526,0.0019856407],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975646,0.000020208183,0.0016970881,0.00014500042,0.00024290556,0.00033018505],"domain_scores_gemma":[0.99669623,0.000114311,0.002685862,0.0001913587,0.0002425259,0.00006971365],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025130513,0.00017403229,0.00041456393,0.004160278,0.0004223343,0.000093627204,0.00036739637,0.00009485387,0.0011358225],"category_scores_gemma":[0.001075487,0.0001813779,0.00016188122,0.0072349464,0.00003610332,0.0010748603,0.00014950894,0.0006463935,0.00009102733],"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":[0.000050872404,0.00017509496,0.94185436,0.00008826686,0.000119130804,0.000005170022,0.0039874776,0.0022497089,0.00006256653,0.041502047,0.0077623874,0.0021429132],"study_design_scores_gemma":[0.003370756,0.0018943776,0.5782592,0.00006794091,0.000032537424,0.00014184767,0.003262587,0.005646558,0.0032594674,0.0034871816,0.3994334,0.0011441016],"about_ca_topic_score_codex":0.000034886434,"about_ca_topic_score_gemma":5.8264874e-7,"teacher_disagreement_score":0.391671,"about_ca_system_score_codex":0.0005711061,"about_ca_system_score_gemma":0.00011377651,"threshold_uncertainty_score":0.99977726},"labels":[{"model":"gemma","categories":["bibliometrics"],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W423015428","doi":"10.1016/j.joi.2015.05.001","title":"Modelling count response variables in informetric studies: Comparison among count, linear, and lognormal regression models","year":2015,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Capital Medical University","keywords":"Count data; Statistics; Negative binomial distribution; Poisson regression; Akaike information criterion; Mathematics; Regression analysis; Linear regression; Poisson distribution; Overdispersion; Log-normal distribution; Generalized linear model; Binomial regression; Regression diagnostic; Econometrics; Polynomial regression; Population","score_opus":0.103223804081119,"score_gpt":0.3570945740796192,"score_spread":0.2538707699985002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W423015428","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":[0.17380138,0.0037154844,0.8218133,0.000059706494,0.00016024518,0.000112353264,0.0000011187186,0.000042383173,0.00029405425],"genre_scores_gemma":[0.68673,0.002247306,0.31082717,0.00009233856,0.000042733995,0.0000029471632,7.0284295e-7,0.000010189707,0.000046578996],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996476,0.00010515386,0.0016057367,0.0001951677,0.0012315819,0.0003863743],"domain_scores_gemma":[0.9949323,0.0012002634,0.0015050469,0.00037619343,0.0017142985,0.0002719241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060026147,0.00025620664,0.0007645148,0.0047702654,0.000095942305,0.00017513546,0.0008552774,0.00017694189,5.2453373e-7],"category_scores_gemma":[0.002962127,0.00019221741,0.000105454244,0.006009157,0.000101941405,0.005555848,0.00041682617,0.0006421939,0.0000012358203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034110877,0.0000925449,0.014880593,0.000034874352,0.000067810586,0.00004908803,0.0030228484,0.96374387,0.000006136033,0.0015121952,0.0007795466,0.015469374],"study_design_scores_gemma":[0.0009498698,0.000508794,0.00043741913,0.00020656371,0.000025689204,0.00007024848,0.00094119983,0.98872674,0.0002075702,0.005726562,0.001970956,0.0002283904],"about_ca_topic_score_codex":0.000041235755,"about_ca_topic_score_gemma":0.000008155375,"teacher_disagreement_score":0.51292866,"about_ca_system_score_codex":0.00061564107,"about_ca_system_score_gemma":0.00042554547,"threshold_uncertainty_score":0.7838399},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4308297793","doi":"10.1016/j.joi.2022.101344","title":"Detecting emerging technologies and their evolution using deep learning and weak signal analysis","year":2022,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Innovation Diffusion and Forecasting","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; National Research Council Canada","funders":"","keywords":"Emerging technologies; Prosperity; Computer science; Data science; Field (mathematics); Identification (biology); Emerging markets; Domain (mathematical analysis); Risk analysis (engineering); Management science; Artificial intelligence; Business; Engineering; Political science; Mathematics","score_opus":0.062262075052657365,"score_gpt":0.3336898294886794,"score_spread":0.2714277544360221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308297793","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":[0.8011331,0.00077280717,0.19743516,0.00006890304,0.00011780206,0.000029940342,9.4763465e-7,0.000018663872,0.00042268343],"genre_scores_gemma":[0.9946579,0.000035871628,0.0052023744,0.000023407218,0.000026795911,4.7657343e-7,2.857891e-7,0.000004652689,0.000048277674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977144,0.00008478769,0.00096107984,0.00012791784,0.0009315129,0.00018030478],"domain_scores_gemma":[0.9967723,0.0009725893,0.0015058153,0.000081891434,0.00062472187,0.00004266522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005930937,0.000099100725,0.0002974665,0.0066507435,0.00093877007,0.00024038444,0.00024160244,0.000050168863,0.00009188963],"category_scores_gemma":[0.008182838,0.00007066798,0.00011361664,0.012625715,0.000058842168,0.0005296748,0.00040726725,0.0005974965,4.183141e-7],"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":[0.000024003624,0.000010486785,0.1638108,0.0000031119841,0.00007825355,0.00000394933,0.0009805617,0.023491653,0.0014216321,0.00032196974,0.0000125035285,0.8098411],"study_design_scores_gemma":[0.00040917686,0.0002535004,0.013093046,0.000010316723,0.000081983446,0.0004332488,0.16170351,0.815938,0.0003394486,0.0027837385,0.0047834376,0.00017057672],"about_ca_topic_score_codex":0.0000064835585,"about_ca_topic_score_gemma":0.0000034309612,"teacher_disagreement_score":0.8096705,"about_ca_system_score_codex":0.00013109487,"about_ca_system_score_gemma":0.000051757426,"threshold_uncertainty_score":0.97962123},"labels":[{"model":"gemma","categories":["bibliometrics"],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4403785816","doi":"10.1016/j.joi.2025.101759","title":"WISDOM: An AI-powered framework for emerging research detection using weak signal analysis and advanced topic modelling","year":2025,"lang":"en","type":"preprint","venue":"Journal of Informetrics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; National Research Council Canada","funders":"","keywords":"SIGNAL (programming language); Computer science; Detection theory; Data science; Artificial intelligence; Telecommunications","score_opus":0.20340031051241791,"score_gpt":0.525670070531794,"score_spread":0.32226976001937613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403785816","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":[0.08964142,0.0009882273,0.907922,0.00021076552,0.0005198701,0.00020325294,0.000008299594,0.0000107222995,0.0004953926],"genre_scores_gemma":[0.540474,0.0010055904,0.4576967,0.00004039083,0.00062496855,0.0000047547755,0.0000055449623,0.000007555582,0.00014050606],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968462,0.00041990262,0.0009273671,0.00024573161,0.0012119506,0.00034885874],"domain_scores_gemma":[0.99332017,0.0025470743,0.00088834687,0.00016623642,0.0028806885,0.0001974642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077046375,0.00016641308,0.0006253293,0.005751865,0.00083107786,0.00038728295,0.00041350577,0.0003780236,0.000031567746],"category_scores_gemma":[0.0026837217,0.00015965864,0.0005133205,0.0066186283,0.000118442746,0.00052376534,0.00018836705,0.0012768216,1.6790122e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000100389065,0.00004061509,0.0011987255,0.000084539606,0.0007870835,0.0000015840732,0.0028980428,0.7103825,0.000012959596,0.0061861384,0.0000042548686,0.27830315],"study_design_scores_gemma":[0.00023258718,0.00011756912,0.0003491975,0.00017095335,0.00095850695,0.0000012706666,0.0032976777,0.77649933,0.00007948073,0.21513577,0.002951028,0.00020665079],"about_ca_topic_score_codex":0.000648601,"about_ca_topic_score_gemma":0.00027602844,"teacher_disagreement_score":0.45083258,"about_ca_system_score_codex":0.00044617266,"about_ca_system_score_gemma":0.00091197685,"threshold_uncertainty_score":0.65106905},"labels":[],"label_agreement":null},{"id":"W4410484490","doi":"10.1016/j.joi.2025.101686","title":"Measuring the university–industry–government relations synthesized by the Triple Helix and the diversity","year":2025,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"University-Industry-Government Innovation Models","field":"Business, Management and Accounting","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute on Governance","funders":"Nanjing University; National Natural Science Foundation of China","keywords":"Triple helix; Diversity (politics); Government (linguistics); Computer science; Political science; Business; Data science; Library science; Engineering management; Engineering; Linguistics; Stereochemistry; Chemistry; Philosophy","score_opus":0.02322332636499285,"score_gpt":0.19133554529258026,"score_spread":0.1681122189275874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410484490","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":[0.7024268,0.00040561013,0.024102736,0.07531756,0.0011980649,0.0009092484,0.000026733574,0.000046674766,0.1955666],"genre_scores_gemma":[0.9888159,0.0000642171,0.000056947953,0.0023692518,0.00013071626,2.8169285e-7,7.482438e-7,0.000004719152,0.008557222],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985001,0.00004097347,0.00031075982,0.00008131255,0.0009082792,0.00015856489],"domain_scores_gemma":[0.9980074,0.00069161307,0.0007685046,0.0001999394,0.0003185447,0.0000139737385],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0021605592,0.00011855764,0.0001709309,0.00029758964,0.0014987875,0.00025287515,0.0007077271,0.00016393697,0.00007017067],"category_scores_gemma":[0.0013135514,0.00006530282,0.00010980605,0.002381463,0.00018678505,0.001341898,0.0007481354,0.0009911945,0.000007058722],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014102295,0.00021668001,0.23333472,0.00009211099,0.0011525779,0.00002362864,0.0010270531,0.0030458507,0.000062067906,0.31918383,0.4157097,0.024741542],"study_design_scores_gemma":[0.006457349,0.00002034709,0.03761597,0.00012163684,0.00083167804,0.0000125777515,0.018333312,0.007725863,0.00008900959,0.0019387895,0.92659867,0.00025479254],"about_ca_topic_score_codex":0.000112025555,"about_ca_topic_score_gemma":0.00000987252,"teacher_disagreement_score":0.510889,"about_ca_system_score_codex":0.00037504573,"about_ca_system_score_gemma":0.00006683643,"threshold_uncertainty_score":0.9998011},"labels":[],"label_agreement":null}]}