{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":24,"total_is_capped":false,"direct_labels_cover":7,"predictions_cover":24,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"09653c74ed9a","filters":{"venue":"Journal of Informetrics"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1625741757646505,"gpt":0.461230812010258,"spread":0.2986566362456075,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005143026,0.000129941,0.0003511144,0.002696105,0.0001399593,0.000564661,0.001146486,0.00009929523,0.0001592671],"category_scores_gemma":[0.01392897,0.00008007385,0.0002072168,0.006532171,0.00009178272,0.001492325,0.0005768408,0.0003836702,0.0001820861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002511939,"about_ca_system_score_gemma":0.0004533368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.659744e-7,"about_ca_topic_score_gemma":0.00001676263,"domain_scores_codex":[0.9946781,0.00009176932,0.001204393,0.0001357718,0.003602813,0.000287128],"domain_scores_gemma":[0.9924446,0.0005814467,0.001507576,0.0003328017,0.004641754,0.000491819],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001680066,0.0002486687,0.08089256,0.00001386591,0.0001025426,0.0005347956,0.007694155,0.002152574,0.0001840762,0.0008710309,0.776254,0.1293717],"study_design_scores_gemma":[0.005329125,0.006081738,0.1872246,0.0002061332,0.0000591458,0.001232117,0.3126979,0.007620133,0.001597444,0.03228666,0.4448856,0.0007794421],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9072387,0.0003756068,0.004229239,0.01081091,0.00209565,0.0001747164,0.0000201748,0.00001826995,0.07503673],"genre_scores_gemma":[0.9938337,0.000009749548,0.0009988385,0.0003847626,0.0004355559,0.000001539587,0.000001674148,0.000008486495,0.004325695],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3313684,"threshold_uncertainty_score":0.9943771,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03318613078372981,"gpt":0.2246175135931572,"spread":0.1914313828094274,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005592057,0.0000672317,0.0003630412,0.00107665,0.00004745733,0.00003664097,0.0001448037,0.00004782137,0.00008694271],"category_scores_gemma":[0.0004705535,0.00006552786,0.0002565494,0.001522101,0.00001013074,0.0003752064,0.00001182433,0.0001061118,0.00001362439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008542649,"about_ca_system_score_gemma":0.00002630758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004894198,"about_ca_topic_score_gemma":0.000002109678,"domain_scores_codex":[0.9985117,0.000003844315,0.001232794,0.00005638079,0.00007639603,0.0001188775],"domain_scores_gemma":[0.9985275,0.00003188783,0.0009774502,0.0001177785,0.000284398,0.0000610473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000839723,0.000338534,0.01626334,0.00007751512,0.0003555415,0.000007081393,0.001035291,0.0507536,0.00007342836,0.8896799,0.001397277,0.03993452],"study_design_scores_gemma":[0.003594837,0.002336805,0.0859136,0.0002201354,0.0001874963,0.0001572898,0.002447918,0.610596,0.0001833228,0.1666143,0.1267955,0.0009528384],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5203165,0.00664136,0.4561185,0.0004460558,0.0004763668,0.00009590785,0.0001303104,0.00000911957,0.01576588],"genre_scores_gemma":[0.9966174,0.000534031,0.002677776,0.00003333569,0.00007506856,2.074494e-7,0.000006151674,0.000003125945,0.00005287848],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7230656,"threshold_uncertainty_score":0.2672149,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7615079244057587,"gpt":0.5814149810599263,"spread":0.1800929433458324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.04101369,0.00009900937,0.0004234182,0.1109624,0.0002802733,0.001924173,0.002607298,0.00007132521,0.0002152492],"category_scores_gemma":[0.06266278,0.00006096113,0.0001600715,0.1933785,0.0005928454,0.003366094,0.0004716681,0.0005731593,0.00004958181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001693561,"about_ca_system_score_gemma":0.001163386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006436821,"about_ca_topic_score_gemma":0.000001064269,"domain_scores_codex":[0.9866026,0.00005301276,0.001699982,0.0001741103,0.0110738,0.0003964832],"domain_scores_gemma":[0.9801992,0.003468207,0.001946454,0.0004003372,0.01341592,0.0005698986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005273462,0.000142576,0.8050559,0.00001378168,0.000033738,0.000006758122,0.0004309151,0.0002643725,0.01254389,0.00492798,0.005962202,0.1705651],"study_design_scores_gemma":[0.0009957056,0.0006346954,0.9617082,0.00003229881,0.00001192268,0.0004549203,0.002244784,0.004562397,0.001810222,0.003378106,0.02403009,0.0001366924],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9774283,0.0009921509,0.006927924,0.0003412193,0.001078017,0.00008019164,0.000005367358,0.000001817805,0.01314503],"genre_scores_gemma":[0.9908,0.0008836331,0.007609293,0.00006906245,0.00006409344,1.586928e-7,1.020828e-7,0.000004226714,0.0005694132],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1704285,"threshold_uncertainty_score":0.999112,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02861058399649574,"gpt":0.2999498346330988,"spread":0.271339250636603,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001615135,0.0001047761,0.0002596898,0.001426321,0.00005290531,0.0006337626,0.0002771881,0.00003541393,0.00001916698],"category_scores_gemma":[0.0001215727,0.00008847788,0.00007898083,0.004810335,0.00001896291,0.001107938,0.00005189686,0.0001990245,0.000002325739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001477333,"about_ca_system_score_gemma":0.0002611042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002435801,"about_ca_topic_score_gemma":0.00008372693,"domain_scores_codex":[0.9985888,0.00002784319,0.0006212418,0.00009487788,0.0004555221,0.0002116865],"domain_scores_gemma":[0.9980536,0.00004715278,0.0005639202,0.0001961766,0.0008766748,0.0002625513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001295653,0.0003919435,0.7938276,0.00000548853,0.000110836,0.00002037066,0.001554965,0.05039096,0.0001386736,0.008269743,0.06434599,0.0808139],"study_design_scores_gemma":[0.005414414,0.003991776,0.08217112,0.0002432505,0.0002814507,0.00004777244,0.01733043,0.2520186,0.003126364,0.02626679,0.6071882,0.001919876],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9041324,0.0001349072,0.09388477,0.0003567406,0.0004851342,0.0001617246,0.000005598371,0.00001272811,0.0008259914],"genre_scores_gemma":[0.9912719,0.00000376411,0.008075641,0.00004763037,0.0004287526,0.000002549457,0.0000130789,0.000008255554,0.0001484074],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7116565,"threshold_uncertainty_score":0.6111387,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8625684102688479,"gpt":0.6369410142134144,"spread":0.2256273960554335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.08664001,0.000123222,0.0004175805,0.01888852,0.0003518747,0.001590636,0.002343496,0.00008944279,0.0003031812],"category_scores_gemma":[0.1750674,0.00005168754,0.0002458131,0.07359594,0.0001724134,0.001090724,0.0003479643,0.0007105495,0.000004361861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007210799,"about_ca_system_score_gemma":0.0002802911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002950919,"about_ca_topic_score_gemma":0.00009245669,"domain_scores_codex":[0.9919401,0.0008160906,0.001950036,0.0001471359,0.004819212,0.0003274081],"domain_scores_gemma":[0.9023029,0.08699787,0.002723191,0.0004984051,0.00716746,0.0003101496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002112679,0.00004922317,0.2721176,0.000001028673,0.00006666061,0.00000363406,0.004415684,0.00008648844,0.00014133,0.000237512,0.003648741,0.7190208],"study_design_scores_gemma":[0.0002638885,0.0006688722,0.9481404,0.00002586161,0.00001766603,0.00008378363,0.007247873,0.01057215,0.004204731,0.02746362,0.001181229,0.000129907],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5615881,0.002218191,0.4349326,0.0001335196,0.0006724619,0.00007362675,0.000004335055,0.000001505901,0.0003756328],"genre_scores_gemma":[0.9760702,0.001268342,0.02232267,0.0001675551,0.0001570375,4.19767e-7,4.25643e-7,0.000004980884,0.000008424648],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7188909,"threshold_uncertainty_score":0.9994458,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02438825478114541,"gpt":0.3143265421653923,"spread":0.2899382873842469,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001134585,0.00008780943,0.0001969932,0.001228811,0.00008514188,0.0006589502,0.0006823311,0.00004483468,0.000008700011],"category_scores_gemma":[0.001240697,0.00006068455,0.00008380615,0.002072843,0.00005991041,0.0009375507,0.0001900956,0.0002787869,0.000007115701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009304599,"about_ca_system_score_gemma":0.0001770119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007411035,"about_ca_topic_score_gemma":7.124311e-7,"domain_scores_codex":[0.9989768,0.0000143843,0.0003574893,0.00009936048,0.0003773911,0.0001745937],"domain_scores_gemma":[0.9984486,0.000155974,0.0004678817,0.0002230102,0.0005958303,0.0001086883],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008800341,0.0002067353,0.241246,0.0004746381,0.0002213845,0.0002161552,0.004858661,0.0001926563,0.006588845,0.1996656,0.004434083,0.5418073],"study_design_scores_gemma":[0.004951824,0.005495757,0.1454226,0.001572761,0.0001835895,0.006089255,0.0003182428,0.216072,0.02823632,0.5646284,0.02433107,0.002698166],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5171636,0.00822198,0.4724397,0.000119735,0.001038274,0.0001047901,0.000002125259,0.0000858498,0.0008239539],"genre_scores_gemma":[0.7005275,0.00001681925,0.299332,0.00002725949,0.00003783292,6.629558e-8,2.774665e-7,0.000002600428,0.00005557611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5391091,"threshold_uncertainty_score":0.6354272,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7915538673463653,"gpt":0.540354756721656,"spread":0.2511991106247093,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.01495354,0.0001272192,0.0004413208,0.04018199,0.0001495333,0.0008303365,0.00330858,0.00005683511,0.0001627929],"category_scores_gemma":[0.0823548,0.00006357809,0.0003950083,0.1990595,0.00009759679,0.001463883,0.0009447991,0.0006211129,0.00003357273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008873425,"about_ca_system_score_gemma":0.0002110194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001456027,"about_ca_topic_score_gemma":0.000002251459,"domain_scores_codex":[0.9885271,0.0001116479,0.001771761,0.0001793483,0.009060611,0.0003494958],"domain_scores_gemma":[0.9864179,0.006254009,0.001516772,0.0004108214,0.004887001,0.0005135037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001813168,0.0001320049,0.3689688,0.00003572954,0.00009770814,0.0000447281,0.00320254,0.0005698271,0.0009917931,0.0008397754,0.007894688,0.6170411],"study_design_scores_gemma":[0.001212332,0.001771045,0.8981692,0.00004539438,0.00003207087,0.00005192269,0.009519179,0.002848189,0.006095413,0.0007903354,0.07922098,0.0002439947],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9832191,0.000219523,0.007797399,0.004284617,0.0007978045,0.00009901529,0.00002178753,0.000005640619,0.003555152],"genre_scores_gemma":[0.9981847,0.0006638176,0.0005127842,0.0003566549,0.000189049,0.000001078924,4.506854e-7,0.000006738394,0.0000846594],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6167971,"threshold_uncertainty_score":0.9706967,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.578649466269294,"gpt":0.5307756849711357,"spread":0.04787378129815834,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","scholarly_communication","open_science"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.1064923,0.0001624005,0.0003675137,0.04023067,0.001036211,0.003272895,0.005699869,0.0001395429,0.0001218355],"category_scores_gemma":[0.1304809,0.0000635925,0.0002634895,0.1128657,0.0002254288,0.001014482,0.000268404,0.00200126,0.00001638157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001151407,"about_ca_system_score_gemma":0.002000716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001791349,"about_ca_topic_score_gemma":0.000006087939,"domain_scores_codex":[0.9819484,0.0002931,0.002368455,0.0001816106,0.01469241,0.0005159747],"domain_scores_gemma":[0.9701793,0.01480492,0.002778466,0.0008279893,0.01090424,0.0005051063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002490517,0.0003844371,0.02483931,0.000008932821,0.00004866494,0.00001010842,0.0007071499,0.0008745607,0.000638387,0.001544114,0.007483589,0.9632117],"study_design_scores_gemma":[0.00437344,0.002875979,0.573015,0.0001171348,0.00004966682,0.0005630559,0.005224383,0.1334154,0.01052798,0.01385085,0.2552591,0.0007280212],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9258365,0.0001783194,0.05949329,0.001244591,0.001632263,0.0002520132,0.000004545694,0.000004447551,0.011354],"genre_scores_gemma":[0.9684832,0.00007673225,0.03076491,0.0002756705,0.0001787093,0.000001972883,3.860031e-7,0.000008352406,0.0002100832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9624836,"threshold_uncertainty_score":0.9996797,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4491389199918624,"gpt":0.4977714261719171,"spread":0.04863250618005466,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.03880285,0.00006519083,0.0002989432,0.2631896,0.0003220919,0.0007097691,0.0009078757,0.00006207877,0.00008298349],"category_scores_gemma":[0.05595456,0.00003888203,0.0001006613,0.5223318,0.001456942,0.0009468233,0.0001484987,0.0002005452,0.000003039682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003474572,"about_ca_system_score_gemma":0.0003618094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006230965,"about_ca_topic_score_gemma":0.000005064133,"domain_scores_codex":[0.9931503,0.00009667665,0.001115134,0.0001624412,0.005285262,0.0001902083],"domain_scores_gemma":[0.9817904,0.00540901,0.001713215,0.000370009,0.01054232,0.0001750182],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000121598,0.0000655792,0.9788967,0.000008456062,0.00008784457,7.866167e-8,0.000525241,0.000002166752,0.0002313189,0.007932939,0.001728416,0.01050904],"study_design_scores_gemma":[0.0001680838,0.0002213714,0.9913083,0.0000153467,0.00009359846,0.000001102392,0.0009438558,0.002690363,0.0002791467,0.002785725,0.001450689,0.00004241627],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939219,0.0001248581,0.002215443,0.0002238805,0.0001461011,0.00008207306,0.0001122631,0.000001427921,0.003172086],"genre_scores_gemma":[0.9987865,0.0002723852,0.0008155452,0.0000119517,0.00001575413,5.328227e-7,0.000002955361,0.000002204105,0.00009215053],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2591421,"threshold_uncertainty_score":0.9897547,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03543923403875162,"gpt":0.3812089441243721,"spread":0.3457697100856205,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007849666,0.0001348015,0.0003261236,0.0006641998,0.0004716624,0.0005191746,0.0007701939,0.0001301785,0.00031127],"category_scores_gemma":[0.003409812,0.00007333411,0.0006114868,0.001090717,0.0001543738,0.00128759,0.00006071079,0.0009736057,0.00002200573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001448394,"about_ca_system_score_gemma":0.0002525846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001616645,"about_ca_topic_score_gemma":0.00007743726,"domain_scores_codex":[0.9975993,0.0002140867,0.0007494767,0.00006542543,0.001081622,0.0002900918],"domain_scores_gemma":[0.9969495,0.0009679288,0.001053646,0.0001912376,0.0006548114,0.0001828755],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0006090593,0.0004506261,0.2503357,0.0001114312,0.0006845669,0.000034482,0.1364304,0.0002484006,0.001672487,0.002491694,0.02568338,0.5812478],"study_design_scores_gemma":[0.002198231,0.003173458,0.9275402,0.0002145574,0.0001332451,0.00002948467,0.02935344,0.00008931986,0.0005049774,0.001236563,0.03520304,0.0003234562],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9666696,0.0002302029,0.00004012174,0.0002908707,0.002210499,0.0001285907,0.00000129742,0.000005291666,0.03042356],"genre_scores_gemma":[0.9963806,0.001845298,0.00005903848,0.0000823489,0.0007922848,4.558425e-7,2.215773e-7,0.000007143318,0.0008326463],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6772045,"threshold_uncertainty_score":0.5006413,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.103223804081119,"gpt":0.3570945740796192,"spread":0.2538707699985002,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006002615,0.0002562066,0.0007645148,0.004770265,0.00009594231,0.0001751355,0.0008552774,0.0001769419,5.245337e-7],"category_scores_gemma":[0.002962127,0.0001922174,0.0001054542,0.006009157,0.0001019414,0.005555848,0.0004168262,0.0006421939,0.00000123582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006156411,"about_ca_system_score_gemma":0.0004255455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004123575,"about_ca_topic_score_gemma":0.000008155375,"domain_scores_codex":[0.996476,0.0001051539,0.001605737,0.0001951677,0.001231582,0.0003863743],"domain_scores_gemma":[0.9949323,0.001200263,0.001505047,0.0003761934,0.001714299,0.0002719241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003411088,0.0000925449,0.01488059,0.00003487435,0.00006781059,0.00004908803,0.003022848,0.9637439,0.000006136033,0.001512195,0.0007795466,0.01546937],"study_design_scores_gemma":[0.0009498698,0.000508794,0.0004374191,0.0002065637,0.0000256892,0.00007024848,0.0009411998,0.9887267,0.0002075702,0.005726562,0.001970956,0.0002283904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1738014,0.003715484,0.8218133,0.00005970649,0.0001602452,0.0001123533,0.000001118719,0.00004238317,0.0002940542],"genre_scores_gemma":[0.68673,0.002247306,0.3108272,0.00009233856,0.00004273399,0.000002947163,7.02843e-7,0.00001018971,0.000046579],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5129287,"threshold_uncertainty_score":0.7838399,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Webometrics; Web traffic; Hyperlink; Computer science; World Wide Web; The Internet; Web page","retraction":null,"screen_n_in":null,"score":{"opus":0.05613253156085697,"gpt":0.2367378245921236,"spread":0.1806052930312667,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001865644,0.0001109705,0.0001851831,0.001198927,0.000218403,0.0005359854,0.0008510167,0.00009891752,0.00000798178],"category_scores_gemma":[0.005196332,0.00008615638,0.00001702137,0.003623482,0.00005957503,0.00683765,0.0003347053,0.0003273803,0.00001385087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004625932,"about_ca_system_score_gemma":0.0002006369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002560386,"about_ca_topic_score_gemma":0.000001950714,"domain_scores_codex":[0.9985312,0.00003470655,0.0006258468,0.0001361949,0.0005040324,0.0001680178],"domain_scores_gemma":[0.9977115,0.0004877976,0.0004655732,0.000426744,0.0007440884,0.000164268],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00000860516,0.00006963426,0.1950012,0.0001021543,0.00004569476,0.000002030236,0.001748805,0.0008346569,0.00004223227,0.0008505114,0.003501155,0.7977933],"study_design_scores_gemma":[0.0009360375,0.0004558807,0.7444928,0.0000506979,0.00002236666,0.0003502232,0.0004272282,0.2368835,0.0001255254,0.0001192813,0.01588428,0.0002522339],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9435187,0.0007217149,0.05488941,0.0002757384,0.0001602707,0.0001058131,0.000001976357,0.00002562451,0.000300761],"genre_scores_gemma":[0.9755023,0.00244096,0.02182762,0.0001187487,0.00005926893,3.732589e-7,0.00000362956,0.000005525113,0.00004155208],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.797541,"threshold_uncertainty_score":0.622087,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Citation; Period (music); History; Computer science; Library science; Art","retraction":null,"screen_n_in":null,"score":{"opus":0.4451528031489057,"gpt":0.4940995388492365,"spread":0.04894673570033081,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.02585763,0.00008693258,0.0002414073,0.04640892,0.0001176715,0.0005083513,0.001054131,0.0000682532,0.0002500326],"category_scores_gemma":[0.1363647,0.00003846681,0.0001446389,0.1370123,0.00009807595,0.0005615397,0.00006546974,0.0003060749,0.00006279257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006553471,"about_ca_system_score_gemma":0.0001632986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007660648,"about_ca_topic_score_gemma":0.000002820761,"domain_scores_codex":[0.9906089,0.0001540454,0.0009578631,0.0001145117,0.007947132,0.0002175844],"domain_scores_gemma":[0.9722075,0.01882019,0.001576286,0.0003272844,0.006862872,0.0002058433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004048937,0.0001718238,0.01596254,0.00000778089,0.00006161419,0.0000039012,0.0002589644,0.0009339351,0.0003483988,0.003776583,0.01772536,0.9603442],"study_design_scores_gemma":[0.007815254,0.03069364,0.6575505,0.0002855773,0.0001481877,0.000261014,0.006869591,0.0264398,0.01834582,0.1429981,0.1076458,0.0009466815],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.951852,0.00006615481,0.01571882,0.0008022254,0.0003861642,0.0001103873,0.000008188403,0.000003140304,0.03105288],"genre_scores_gemma":[0.9973194,0.0001307669,0.001970833,0.0003465257,0.00007492804,8.901943e-7,8.454812e-7,0.00000514838,0.0001506827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9593976,"threshold_uncertainty_score":0.9643992,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06226207505265736,"gpt":0.3336898294886794,"spread":0.2714277544360221,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005930937,0.00009910073,0.0002974665,0.006650744,0.0009387701,0.0002403844,0.0002416024,0.00005016886,0.00009188963],"category_scores_gemma":[0.008182838,0.00007066798,0.0001136166,0.01262571,0.00005884217,0.0005296748,0.0004072672,0.0005974965,4.183141e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001310949,"about_ca_system_score_gemma":0.00005175743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006483559,"about_ca_topic_score_gemma":0.000003430961,"domain_scores_codex":[0.9977144,0.00008478769,0.0009610798,0.0001279178,0.0009315129,0.0001803048],"domain_scores_gemma":[0.9967723,0.0009725893,0.001505815,0.00008189143,0.0006247219,0.00004266522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002400362,0.00001048678,0.1638108,0.000003111984,0.00007825355,0.00000394933,0.0009805617,0.02349165,0.001421632,0.0003219697,0.00001250353,0.8098411],"study_design_scores_gemma":[0.0004091769,0.0002535004,0.01309305,0.00001031672,0.00008198345,0.0004332488,0.1617035,0.815938,0.0003394486,0.002783739,0.004783438,0.0001705767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8011331,0.0007728072,0.1974352,0.00006890304,0.0001178021,0.00002994034,9.476346e-7,0.00001866387,0.0004226834],"genre_scores_gemma":[0.9946579,0.00003587163,0.005202374,0.00002340722,0.00002679591,4.765734e-7,2.857891e-7,0.000004652689,0.00004827767],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8096705,"threshold_uncertainty_score":0.9796212,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6028694960870139,"gpt":0.5223753468198439,"spread":0.08049414926717002,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.02380218,0.0001048825,0.0003202816,0.04153822,0.000237836,0.003096387,0.0003857259,0.0000687047,0.000006663402],"category_scores_gemma":[0.05891033,0.00006420232,0.00002829228,0.04789078,0.0001419326,0.002200476,0.0002952331,0.0002716575,0.000003168061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004243861,"about_ca_system_score_gemma":0.0001057731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001764883,"about_ca_topic_score_gemma":0.000004415027,"domain_scores_codex":[0.9946733,0.0000748926,0.0008915528,0.0001865746,0.003929572,0.0002441735],"domain_scores_gemma":[0.9897245,0.003869281,0.001213045,0.0001878735,0.004637379,0.0003679257],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001946364,0.000009529494,0.8382184,0.000009234125,0.000009827171,5.637568e-7,0.0001552491,0.00003325488,0.0000130154,0.0009704842,0.0003844484,0.1601765],"study_design_scores_gemma":[0.000926516,0.0003446664,0.9143086,0.00003148107,0.0000117548,0.0001922062,0.0004901763,0.0583561,0.00003186745,0.00120375,0.02397653,0.0001263679],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9708526,0.0008300747,0.02313077,0.0004361581,0.00008599652,0.00007504528,0.000001166803,0.000005476833,0.004582698],"genre_scores_gemma":[0.9921513,0.0003894248,0.007099136,0.0001385758,0.00007040182,5.150214e-7,6.823635e-7,0.000005723141,0.0001443016],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1600501,"threshold_uncertainty_score":0.9979385,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1482204385072352,"gpt":0.4057818156424827,"spread":0.2575613771352475,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["bibliometrics","scholarly_communication"],"category_scores_codex":[0.002486091,0.0001094632,0.0001828057,0.033698,0.0004407904,0.01730414,0.003552781,0.00004720435,0.000003563486],"category_scores_gemma":[0.07102973,0.00008948933,0.00005918949,0.02194834,0.0000723594,0.1109828,0.001564362,0.0003776359,0.00001345379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004646216,"about_ca_system_score_gemma":0.0001953481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003240519,"about_ca_topic_score_gemma":0.000004503849,"domain_scores_codex":[0.9978737,0.000025214,0.0004853805,0.0001536143,0.001196999,0.0002650836],"domain_scores_gemma":[0.9939629,0.002722806,0.00143316,0.00104078,0.0005920744,0.0002482405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002114549,0.0001468809,0.006007557,0.00004342084,0.0001290878,0.00006524815,0.0001198032,0.000112595,0.00004174721,0.06239299,0.00411018,0.9268094],"study_design_scores_gemma":[0.001408905,0.0005580144,0.1434785,0.00003810253,0.00003189224,0.0002705224,0.0001073578,0.004606143,0.00007990436,0.0005921831,0.8486344,0.0001940791],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03325908,0.0003649612,0.9441281,0.001621981,0.0003593334,0.0001113121,0.00001666338,0.00001450712,0.02012405],"genre_scores_gemma":[0.8262302,0.04629894,0.1225945,0.0005813465,0.0002084816,0.000002691997,0.000007116505,0.00001485607,0.004061934],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9266152,"threshold_uncertainty_score":0.9988406,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9265886468305123,"gpt":0.6788366096396239,"spread":0.2477520371908885,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","scholarly_communication","open_science"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.1219672,0.0001547612,0.0005692417,0.53863,0.0009983619,0.006572912,0.02145784,0.0001528233,0.0001142223],"category_scores_gemma":[0.587162,0.00008024789,0.0002755984,0.6772984,0.0006736005,0.004865275,0.005229388,0.000960583,0.00002042498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001588338,"about_ca_system_score_gemma":0.001053115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002959062,"about_ca_topic_score_gemma":0.00001097873,"domain_scores_codex":[0.9759151,0.0002379497,0.002329597,0.0003254248,0.02050091,0.0006910502],"domain_scores_gemma":[0.9499022,0.02102988,0.006678452,0.005444531,0.01629077,0.0006541098],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005102613,0.00008953251,0.6430845,0.00001521766,0.00006979349,0.00006086455,0.000124453,0.0001793134,0.0003642869,0.0001024432,0.01030935,0.3455493],"study_design_scores_gemma":[0.001056673,0.0005235435,0.9005796,0.00005496117,0.00004170378,0.000152928,0.00137175,0.03288492,0.000642958,0.001658186,0.06085078,0.0001819627],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9720216,0.003299535,0.01146254,0.0007479967,0.001602462,0.0002259774,0.00009184606,0.000004918406,0.01054308],"genre_scores_gemma":[0.991174,0.001995039,0.006082259,0.00005390812,0.0003043865,3.263863e-7,0.000001901564,0.0000125059,0.0003756784],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4651949,"threshold_uncertainty_score":0.9944584,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1625871724368688,"gpt":0.4348576260224379,"spread":0.2722704535855691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003315483,0.00004890065,0.0001226086,0.0007558158,0.00007324055,0.00002096736,0.000147386,0.0001011506,0.000003149223],"category_scores_gemma":[0.003725006,0.00002833258,0.00002127244,0.002589042,0.00009268936,0.0001157842,0.00003499351,0.0004036799,2.728712e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003529204,"about_ca_system_score_gemma":0.0001319464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002052906,"about_ca_topic_score_gemma":0.000005503285,"domain_scores_codex":[0.9990056,0.00004083841,0.0005508452,0.0000420932,0.0002381445,0.0001225051],"domain_scores_gemma":[0.9980447,0.001432518,0.00009630105,0.00007878485,0.0002998201,0.00004787727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001114084,0.0002371334,0.09509811,0.0007500685,0.0001394758,0.000002040482,0.01448918,0.0000766595,0.003002563,0.0008554214,0.5346078,0.3506302],"study_design_scores_gemma":[0.003194906,0.001173637,0.4727165,0.0003073311,0.00003831919,0.000246268,0.00601841,0.01562675,0.002543835,0.0005001137,0.4973645,0.0002694752],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8737782,0.0008046082,0.1170767,0.007607296,0.0003964224,0.0002512062,0.000007802512,0.000007605546,0.00007017918],"genre_scores_gemma":[0.9718865,0.001407168,0.0259382,0.0003555914,0.0003495845,0.00001267854,0.000006762602,0.000009840411,0.00003365079],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3776184,"threshold_uncertainty_score":0.4459449,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7928641188145871,"gpt":0.6879661796861452,"spread":0.1048979391284419,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.05869103,0.0001527991,0.0005735782,0.4840632,0.000734689,0.01132054,0.004837017,0.0001549404,0.00007730517],"category_scores_gemma":[0.1049412,0.0001094026,0.0002561279,0.5986164,0.0001834607,0.006110222,0.00438198,0.0009325778,0.000007934746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006017795,"about_ca_system_score_gemma":0.0003434872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001738437,"about_ca_topic_score_gemma":0.0006686446,"domain_scores_codex":[0.9901093,0.0002062834,0.001614525,0.0003870071,0.007141712,0.0005411944],"domain_scores_gemma":[0.9600272,0.02160822,0.0009846956,0.0005705445,0.01610565,0.0007037154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004482073,0.0002250275,0.593486,0.00002018015,0.0002052818,0.000009253269,0.0008784445,0.0003244064,0.000417366,0.002281979,0.05933686,0.342367],"study_design_scores_gemma":[0.001301745,0.001599432,0.9647441,0.00002703627,0.00009713349,0.00001715307,0.002141383,0.005401949,0.0005542421,0.01255122,0.01132046,0.0002441664],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9036646,0.0001521048,0.09146789,0.002435349,0.0008869426,0.0004359367,0.00007825988,0.000005253984,0.0008736557],"genre_scores_gemma":[0.9831178,0.0003445689,0.01598169,0.0002786119,0.0001528181,0.00001622166,0.00001728489,0.000009859153,0.00008111616],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3712581,"threshold_uncertainty_score":0.9897058,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01774139570065081,"gpt":0.2744047769177139,"spread":0.2566633812170631,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007177897,0.00007856038,0.0002138038,0.0006826236,0.00008413639,0.0002766599,0.0002235433,0.0000274403,0.0001286235],"category_scores_gemma":[0.0001900496,0.00007095079,0.00009824798,0.005700129,0.00002818584,0.0007429281,0.00006349855,0.0002492592,0.000006439772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001003773,"about_ca_system_score_gemma":0.0002521278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005190275,"about_ca_topic_score_gemma":0.000004040842,"domain_scores_codex":[0.9988388,0.00002321372,0.0005365516,0.0000786309,0.0003327543,0.0001900353],"domain_scores_gemma":[0.9985138,0.00006193089,0.0004960751,0.00009598664,0.0007299616,0.0001022504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001806565,0.0002649607,0.8275644,0.00008510716,0.0001452885,0.00004914093,0.005054066,0.005948918,0.0004487908,0.07810176,0.03944029,0.0427166],"study_design_scores_gemma":[0.00270468,0.001073122,0.07065767,0.00008227421,0.0001185385,0.000002776789,0.01566185,0.01829279,0.009268406,0.01241664,0.868996,0.0007252058],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9585823,0.00007071118,0.03195395,0.000355624,0.00007842258,0.0001425931,0.000004804761,0.00001301332,0.008798577],"genre_scores_gemma":[0.9960714,0.000005412829,0.002985279,0.00005645227,0.0001835084,0.000001472944,0.000004191924,0.000005600501,0.0006866769],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8295557,"threshold_uncertainty_score":0.2893289,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0561466103949233,"gpt":0.2499877970366727,"spread":0.1938411866417494,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002513051,0.0001740323,0.0004145639,0.004160278,0.0004223343,0.0000936272,0.0003673964,0.00009485387,0.001135823],"category_scores_gemma":[0.001075487,0.0001813779,0.0001618812,0.007234946,0.00003610332,0.00107486,0.0001495089,0.0006463935,0.00009102733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005711061,"about_ca_system_score_gemma":0.0001137765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003488643,"about_ca_topic_score_gemma":5.826487e-7,"domain_scores_codex":[0.9975646,0.00002020818,0.001697088,0.0001450004,0.0002429056,0.0003301851],"domain_scores_gemma":[0.9966962,0.000114311,0.002685862,0.0001913587,0.0002425259,0.00006971365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000508724,0.000175095,0.9418544,0.00008826686,0.0001191308,0.000005170022,0.003987478,0.002249709,0.00006256653,0.04150205,0.007762387,0.002142913],"study_design_scores_gemma":[0.003370756,0.001894378,0.5782592,0.00006794091,0.00003253742,0.0001418477,0.003262587,0.005646558,0.003259467,0.003487182,0.3994334,0.001144102],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9848,0.0001922441,0.0003334201,0.00008556531,0.001439454,0.0001215431,0.00004693774,0.00001794896,0.01296287],"genre_scores_gemma":[0.996564,0.00005362384,0.000313246,0.0007563661,0.0002736002,0.00000325775,0.00002596528,0.00002428253,0.001985641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.391671,"threshold_uncertainty_score":0.9997773,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6384368990329121,"gpt":0.5833211230820153,"spread":0.05511577595089678,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","scholarly_communication","open_science"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.03637953,0.0001379398,0.0005627316,0.1587591,0.0008683075,0.006599371,0.008046128,0.0001025527,0.0001613242],"category_scores_gemma":[0.1688239,0.00009046518,0.0002891535,0.1815109,0.001071635,0.009738696,0.001619573,0.0004331194,0.00001938649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001480388,"about_ca_system_score_gemma":0.001854447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003830651,"about_ca_topic_score_gemma":6.147794e-7,"domain_scores_codex":[0.9847053,0.00004818306,0.001806636,0.0002514006,0.01260264,0.0005858891],"domain_scores_gemma":[0.9825504,0.003134933,0.004444747,0.001009158,0.008259776,0.0006010294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005551989,0.00009712867,0.7317294,0.00002332576,0.00002748404,0.00005314564,0.0002860258,0.0001249723,0.006250595,0.0008795857,0.005254867,0.2552179],"study_design_scores_gemma":[0.001936571,0.0008718615,0.834496,0.0002224373,0.00001910701,0.0004167346,0.002046639,0.01935209,0.06793457,0.006584588,0.06565077,0.0004686899],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9748696,0.0005421247,0.004421067,0.0002423976,0.002062415,0.00009437589,0.00001497476,0.00000447283,0.01774855],"genre_scores_gemma":[0.9868807,0.0005386416,0.011858,0.00006332413,0.0001376715,1.70406e-7,1.526588e-7,0.000008588626,0.0005128154],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2547492,"threshold_uncertainty_score":0.9973208,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02322332636499285,"gpt":0.1913355452925803,"spread":0.1681122189275874,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002160559,0.0001185576,0.0001709309,0.0002975896,0.001498788,0.0002528752,0.0007077271,0.000163937,0.00007017067],"category_scores_gemma":[0.001313551,0.00006530282,0.0001098061,0.002381463,0.0001867851,0.001341898,0.0007481354,0.0009911945,0.000007058722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003750457,"about_ca_system_score_gemma":0.00006683643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001120256,"about_ca_topic_score_gemma":0.00000987252,"domain_scores_codex":[0.9985001,0.00004097347,0.0003107598,0.00008131255,0.0009082792,0.0001585649],"domain_scores_gemma":[0.9980074,0.0006916131,0.0007685046,0.0001999394,0.0003185447,0.00001397374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001410229,0.00021668,0.2333347,0.00009211099,0.001152578,0.00002362864,0.001027053,0.003045851,0.00006206791,0.3191838,0.4157097,0.02474154],"study_design_scores_gemma":[0.006457349,0.00002034709,0.03761597,0.0001216368,0.000831678,0.00001257775,0.01833331,0.007725863,0.00008900959,0.00193879,0.9265987,0.0002547925],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7024268,0.0004056101,0.02410274,0.07531756,0.001198065,0.0009092484,0.00002673357,0.00004667477,0.1955666],"genre_scores_gemma":[0.9888159,0.0000642171,0.00005694795,0.002369252,0.0001307163,2.816928e-7,7.482438e-7,0.000004719152,0.008557222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.510889,"threshold_uncertainty_score":0.9998011,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2034003105124179,"gpt":0.525670070531794,"spread":0.3222697600193761,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007704637,0.0001664131,0.0006253293,0.005751865,0.0008310779,0.000387283,0.0004135058,0.0003780236,0.00003156775],"category_scores_gemma":[0.002683722,0.0001596586,0.0005133205,0.006618628,0.0001184427,0.0005237653,0.000188367,0.001276822,1.679012e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004461727,"about_ca_system_score_gemma":0.0009119769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000648601,"about_ca_topic_score_gemma":0.0002760284,"domain_scores_codex":[0.9968462,0.0004199026,0.0009273671,0.0002457316,0.001211951,0.0003488587],"domain_scores_gemma":[0.9933202,0.002547074,0.0008883469,0.0001662364,0.002880689,0.0001974642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001003891,0.00004061509,0.001198726,0.00008453961,0.0007870835,0.000001584073,0.002898043,0.7103825,0.0000129596,0.006186138,0.000004254869,0.2783031],"study_design_scores_gemma":[0.0002325872,0.0001175691,0.0003491975,0.0001709534,0.0009585069,0.000001270667,0.003297678,0.7764993,0.00007948073,0.2151358,0.002951028,0.0002066508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08964142,0.0009882273,0.907922,0.0002107655,0.0005198701,0.0002032529,0.000008299594,0.0000107223,0.0004953926],"genre_scores_gemma":[0.540474,0.00100559,0.4576967,0.00004039083,0.0006249686,0.000004754776,0.000005544962,0.000007555582,0.0001405061],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4508326,"threshold_uncertainty_score":0.651069,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}