{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":514,"total_is_capped":false,"direct_labels_cover":5,"predictions_cover":514,"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":"0eee3839674e","filters":{"topic":"Computational and Text Analysis Methods"}},"results":[{"id":"W2943121181","doi":"10.5465/annals.2017.0099","title":"Topic Modeling in Management Research: Rendering New Theory from Textual Data","year":2019,"lang":"en","type":"article","venue":"Academy of Management Annals","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":591,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Alberta","funders":"","keywords":"Rendering (computer graphics); Computer science; Novelty; Data science; Grounded theory; Topic model; Artificial intelligence; Sociology; Qualitative research; Social science","retraction":null,"screen_n_in":null,"score":{"opus":0.5970884422744959,"gpt":0.5250309813464068,"spread":0.07205746092808907,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007083338,0.00009442992,0.0002047972,0.0004212036,0.0001204496,0.00005290255,0.001187926,0.00006990022,0.0007227428],"category_scores_gemma":[0.00007099858,0.00009603249,0.00005616639,0.0007289557,0.0000665771,0.0003383047,0.0009513783,0.0002289419,0.0001125493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003522082,"about_ca_system_score_gemma":0.00002030265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001305076,"about_ca_topic_score_gemma":0.0001104318,"domain_scores_codex":[0.9972942,0.0006636182,0.0003594464,0.0004052415,0.000919192,0.0003583346],"domain_scores_gemma":[0.9991099,0.0004126694,0.0000790889,0.0002930107,0.00002674511,0.00007856575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000378401,0.00006217256,0.001103593,0.00004993464,0.0002373431,0.000004139348,0.002609948,0.005222112,0.000007656677,0.5809451,0.004216002,0.4055042],"study_design_scores_gemma":[0.0006426582,0.00001372131,0.008901128,0.0002195357,0.00006005491,4.173423e-8,0.01993834,0.03336783,0.00002015784,0.7858561,0.1507393,0.00024115],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3596272,0.002533396,0.04405904,0.02481732,0.0002438439,0.001518457,0.00001944217,0.0001153285,0.5670659],"genre_scores_gemma":[0.9611557,0.00146235,0.01014465,0.0003705586,0.0001895528,0.000006954129,0.00002774444,0.00001012595,0.02663234],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6015285,"threshold_uncertainty_score":0.7913527,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3171347074","doi":"10.21105/joss.03272","title":"academictwitteR: an R package to access the Twitter Academic Research Product Track v2 API endpoint","year":2021,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":227,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Track (disk drive); Product (mathematics); World Wide Web; Computer science; Operating system; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.282066190315972,"gpt":0.5272027382753877,"spread":0.2451365479594156,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.02321084,0.0001514982,0.0003489116,0.0001614656,0.001612901,0.0008740528,0.004838706,0.0001099395,0.0008098061],"category_scores_gemma":[0.003906479,0.00008419524,0.0001684868,0.001682252,0.0003758983,0.0009989723,0.001222232,0.002034369,0.00006638609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001381531,"about_ca_system_score_gemma":0.0007649268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005461139,"about_ca_topic_score_gemma":0.0002390383,"domain_scores_codex":[0.9908301,0.006077447,0.0006228181,0.0002777985,0.001682495,0.000509402],"domain_scores_gemma":[0.9950559,0.002557163,0.0003719301,0.0004856998,0.00121735,0.0003120106],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000734108,0.0003309719,0.0322767,0.0000387492,0.0005236564,0.0001147947,0.4282492,0.005572506,0.003364336,0.001334275,0.1754019,0.3520588],"study_design_scores_gemma":[0.0006145071,0.0001758961,0.07105198,0.0002109945,0.0002542024,0.0001829211,0.07361166,0.00005850608,0.003923704,0.0510583,0.7984021,0.000455261],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8707079,0.001277709,0.01760686,0.1083772,0.0003101357,0.0005908949,0.00000550439,0.00002973923,0.00109406],"genre_scores_gemma":[0.9781699,0.0004490298,0.004457824,0.005625874,0.002603048,0.00001425445,0.000003834017,0.00003898702,0.00863731],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6230002,"threshold_uncertainty_score":0.9996868,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2406594196","doi":"10.5121/csit.2016.60616","title":"A Text Mining Research Based on LDA Topic Modelling","year":2016,"lang":"en","type":"article","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":174,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; Topic model; Natural language processing; Artificial intelligence; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.3539824256636802,"gpt":0.5065979207347818,"spread":0.1526154950711016,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002238237,0.0000367315,0.00006477089,0.0001367541,0.0003820228,0.00004248943,0.0001337015,0.0000323588,0.001480689],"category_scores_gemma":[0.0003025434,0.00002253636,0.00004867057,0.0003778314,0.0001225147,0.00005900429,0.0000173696,0.00004689607,0.0001330482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005991804,"about_ca_system_score_gemma":0.0001244484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007231758,"about_ca_topic_score_gemma":0.0003207025,"domain_scores_codex":[0.9985658,0.000452413,0.00008966259,0.0001557801,0.000531271,0.0002051028],"domain_scores_gemma":[0.9977511,0.001933754,0.00001525438,0.0000894215,0.0001411879,0.0000692808],"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":[0.00002221646,0.00007564839,0.002919797,0.000003255185,0.00001511378,0.0000045373,0.002801353,0.01268139,0.0002029692,0.4375475,0.002189453,0.5415367],"study_design_scores_gemma":[0.0005454011,0.0001052266,0.001399702,0.00009941353,0.00001148017,1.126349e-7,0.002767607,0.6384366,0.0004070286,0.1501144,0.2058404,0.0002725761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06962962,0.00001361895,0.4955644,0.0155115,0.00008399764,0.00007203109,4.53643e-7,0.00005234391,0.4190721],"genre_scores_gemma":[0.9451762,0.000005051319,0.02447445,0.0001618968,0.0001848316,0.000005045871,2.611065e-7,0.00000295353,0.02998924],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8755466,"threshold_uncertainty_score":0.9994321,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2041314074","doi":"10.1017/s0007123411000160","title":"Language and Ideology in Congress","year":2011,"lang":"en","type":"article","venue":"British Journal of Political Science","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":168,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Kellogg's (Canada)","funders":"","keywords":"Ideology; Legislature; Interpretation (philosophy); Political science; Politics; Law; Linguistics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.03988064428790917,"gpt":0.3808767252756357,"spread":0.3409960809877265,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002823573,0.00002820284,0.0001125535,0.0001218728,0.0001469262,0.00005993298,0.0002256757,0.00002450387,0.0001902429],"category_scores_gemma":[0.001865381,0.00002864195,0.00002853977,0.000374677,0.001537692,0.0002676093,0.00004097692,0.0001120654,0.000002070385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005335929,"about_ca_system_score_gemma":0.0002562169,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01102274,"about_ca_topic_score_gemma":0.00300027,"domain_scores_codex":[0.9988883,0.0001740846,0.0001959574,0.00008554204,0.0003147825,0.000341375],"domain_scores_gemma":[0.9992604,0.0001947969,0.00005990883,0.00002512942,0.0001598664,0.0002999048],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000004916567,0.00005253862,0.02825695,0.00000189457,0.000003246606,0.000426722,0.004098954,6.270691e-7,0.0001596481,0.907314,0.00002261025,0.05965789],"study_design_scores_gemma":[0.0001716634,0.0000355337,0.8824768,0.00003446583,0.000007001068,0.000369997,0.004482092,0.00004999534,0.0001267288,0.1119566,0.0002283709,0.00006074194],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9784529,0.0002565875,0.0005291972,0.0005045805,0.0001588203,0.00001960665,6.96054e-7,0.000003179792,0.02007444],"genre_scores_gemma":[0.9951311,0.00002373827,0.004463433,0.0001853764,0.00008616359,2.310813e-7,3.102762e-8,0.000001121793,0.0001088278],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8542199,"threshold_uncertainty_score":0.9955629,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2954211942","doi":"10.1017/pan.2019.26","title":"Word Embeddings for the Analysis of Ideological Placement in Parliamentary Corpora","year":2019,"lang":"en","type":"article","venue":"Political Analysis","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":165,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"","keywords":"Ideology; Metadata; Parliament; Computer science; Context (archaeology); Politics; Word (group theory); Natural language processing; Language model; Linguistics; Artificial intelligence; Data science; Sociology; Political science; World Wide Web; Law; History","retraction":null,"screen_n_in":null,"score":{"opus":0.0491700587411518,"gpt":0.3975014255878185,"spread":0.3483313668466667,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001867207,0.0001073115,0.0006255668,0.0006880751,0.0001339763,0.00003632222,0.0003053385,0.00006713858,0.002971638],"category_scores_gemma":[0.0003549925,0.00007271509,0.0009514176,0.0049555,0.0002635733,0.00006072969,0.00006355239,0.00009093471,0.00001247374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001329862,"about_ca_system_score_gemma":0.00006294303,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01311325,"about_ca_topic_score_gemma":0.008319763,"domain_scores_codex":[0.997936,0.0003328713,0.0004899523,0.0003005651,0.000512365,0.0004282832],"domain_scores_gemma":[0.9957979,0.003569937,0.0001437199,0.000211132,0.0001444224,0.00013294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004668024,0.0001525012,0.6167433,0.000006253571,0.007426981,9.622667e-7,0.0007421725,0.0239499,0.00001149165,0.3470255,0.00006010291,0.003834141],"study_design_scores_gemma":[0.0004017786,0.00004844732,0.6224132,0.000005960657,0.02188396,6.712597e-8,0.008680864,0.3015081,0.00002782479,0.04095277,0.003826772,0.0002502849],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9429736,0.0001336416,0.04617698,0.006420952,0.00007011883,0.0003423429,0.00004300031,0.00002145771,0.003817872],"genre_scores_gemma":[0.9960397,0.00001117648,0.002475505,0.0005110274,0.00005417972,0.00003108749,0.00004739685,0.000003367989,0.0008265743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3060727,"threshold_uncertainty_score":0.9979398,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3000486466","doi":"10.31222/osf.io/5rksu","title":"Open Science Practices are on the Rise: The State of Social Science (3S) Survey","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":137,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Transparency (behavior); Open science; Quarter (Canadian coin); Social science; Sociology; State (computer science); Science studies; Field (mathematics); Political science; Public relations; Geography; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.2535066719527609,"gpt":0.5222285857905022,"spread":0.2687219138377414,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.05683086,0.0001620689,0.0003268606,0.0001926211,0.00324352,0.001994578,0.009463623,0.00006001117,0.00035797],"category_scores_gemma":[0.01179637,0.00008280936,0.0001227509,0.002608485,0.006026961,0.0005320704,0.004959317,0.0005127752,0.00005929667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001827227,"about_ca_system_score_gemma":0.005345448,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03054155,"about_ca_topic_score_gemma":0.008059555,"domain_scores_codex":[0.9934461,0.002479046,0.0003502925,0.0007211849,0.002614902,0.0003884831],"domain_scores_gemma":[0.9909355,0.004934613,0.001817639,0.0006224627,0.001610707,0.00007905067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001970014,0.0007323119,0.04045147,0.0000677678,0.0002983402,0.000002614778,0.07934243,0.009480038,0.0002651156,0.7493153,0.008887301,0.1109603],"study_design_scores_gemma":[0.000183643,0.00004260651,0.8558775,0.00007207046,0.00008182071,2.604667e-7,0.01237651,0.00754004,0.0004052763,0.09859644,0.02433775,0.0004860821],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4677436,0.0001031309,0.001501223,0.02639569,0.001508915,0.0017625,0.00008321582,0.00004111652,0.5008606],"genre_scores_gemma":[0.9909395,0.00003960191,0.0005771886,0.0003563675,0.0001227183,0.00002091031,0.00000206079,0.000006107291,0.007935523],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8154261,"threshold_uncertainty_score":0.9990414,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2900532930","doi":"10.1111/joes.12370","title":"ECONOMETRICS MEETS SENTIMENT: AN OVERVIEW OF METHODOLOGY AND APPLICATIONS","year":2020,"lang":"en","type":"article","venue":"Journal of Economic Surveys","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":137,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Innoviris; Vrije Universiteit Brussel; Institut de Valorisation des Données; European Commission; Universiteit Gent; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Econometrics; Econometric model; Field (mathematics); Econometric analysis; Economics; Sentiment analysis; Computer science; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4794215240349278,"gpt":0.4705475097426656,"spread":0.008874014292262145,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007902524,0.00005080066,0.0003162964,0.0001551421,0.00007127466,0.00002554446,0.0001721256,0.000038038,0.000362823],"category_scores_gemma":[0.0003070141,0.00004977991,0.000103542,0.0002151978,0.0000876819,0.0002014969,0.00002880247,0.00006499338,0.000006855361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004142281,"about_ca_system_score_gemma":0.0001462102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002064699,"about_ca_topic_score_gemma":0.000201063,"domain_scores_codex":[0.9974344,0.001847643,0.0004630626,0.0001031531,0.00007116222,0.00008054798],"domain_scores_gemma":[0.9977334,0.001415039,0.0005387334,0.00005507073,0.00009753851,0.0001602736],"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":[0.00003415056,0.0001591406,0.09103461,0.00005664806,0.0006273984,0.000003263923,0.006281322,0.005237329,0.0002036826,0.2176695,0.0004398403,0.6782531],"study_design_scores_gemma":[0.00223186,0.0007640257,0.4048176,0.00003148934,0.000602716,0.00003064263,0.006556598,0.009945751,0.0005788821,0.1909043,0.3828132,0.0007228749],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6478972,0.01307376,0.3160417,0.01082777,0.0006637804,0.000363055,0.00005217793,0.0000221824,0.01105833],"genre_scores_gemma":[0.9644853,0.002017415,0.03265548,0.0002161954,0.0005524604,0.000001711126,0.000003278436,0.000006709526,0.0000614202],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6775302,"threshold_uncertainty_score":0.3972658,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391220979","doi":"10.1287/mksc.2023.0454","title":"Frontiers: Determining the Validity of Large Language Models for Automated Perceptual Analysis","year":2024,"lang":"en","type":"article","venue":"Marketing Science","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":131,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Perception; Computer science; Data science; Human language; Natural language processing; Language model; Artificial intelligence; Cognitive psychology; Machine learning; Econometrics; Economics; Psychology; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04878391879767375,"gpt":0.4075470857221072,"spread":0.3587631669244334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01630735,0.00006390642,0.0001501737,0.0002763127,0.0008360062,0.0002334918,0.0004600353,0.00002654893,0.00005640084],"category_scores_gemma":[0.002301138,0.00004507177,0.0001952221,0.002911232,0.000483462,0.000288195,0.00007410417,0.00005758837,0.000001335922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006002837,"about_ca_system_score_gemma":0.0002310021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001471048,"about_ca_topic_score_gemma":0.0001720601,"domain_scores_codex":[0.9982141,0.0004795403,0.0001880457,0.0002735005,0.0005704641,0.0002743751],"domain_scores_gemma":[0.9977688,0.001780049,0.00006709395,0.0001290827,0.0002031853,0.0000518484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009320002,0.0003063875,0.1306297,0.0002662795,0.001199715,0.00001141606,0.3754472,0.05558162,0.002863087,0.06064278,0.01003861,0.3629201],"study_design_scores_gemma":[0.00003841783,0.000006407776,0.02677472,0.00001396792,0.0001849045,7.511179e-8,0.007862331,0.9633987,0.00002259775,0.0008911893,0.0007392697,0.00006741362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7531711,0.0001464237,0.2401451,0.0004182319,0.0003096164,0.0001473324,0.00002233415,0.0002138379,0.005426083],"genre_scores_gemma":[0.972694,0.000004615933,0.02671732,0.00003667946,0.00007638059,0.000007386324,0.00000372378,0.000003674961,0.0004562317],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9078171,"threshold_uncertainty_score":0.6429968,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2593732251","doi":"10.1017/s0922156517000085","title":"Can Quantitative Methods Complement Doctrinal Legal Studies? Using Citation Network and Corpus Linguistic Analysis to Understand International Courts","year":2017,"lang":"en","type":"article","venue":"Leiden Journal of International Law","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":130,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Centre for International Governance Innovation","funders":"","keywords":"Legal translation; Political science; Empirical legal studies; Law; Jurisprudence; Sources of law; International law; Comparative law; Human rights; Legal culture; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.2317016934668139,"gpt":0.5415538491311146,"spread":0.3098521556643007,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004080969,0.0001478884,0.000431115,0.0004338882,0.001053723,0.000679892,0.000642905,0.00004224051,0.0001083169],"category_scores_gemma":[0.002861509,0.0001380034,0.000233996,0.0002656725,0.000349105,0.0004394622,0.0001700778,0.0001826079,0.000001387217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000505232,"about_ca_system_score_gemma":0.000196235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002866746,"about_ca_topic_score_gemma":0.00953317,"domain_scores_codex":[0.9973094,0.0005135266,0.0007068941,0.0002296071,0.00102298,0.0002175741],"domain_scores_gemma":[0.9949474,0.001111402,0.001209919,0.0001278896,0.002410942,0.0001924411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001602251,0.0000440281,0.01277402,0.000003964568,0.004831705,0.00006278778,0.006080362,0.02346533,0.00007433244,0.9488153,0.0001254265,0.003562445],"study_design_scores_gemma":[0.002914418,0.0006135492,0.1117235,0.0005112183,0.004663415,0.0001297222,0.02238035,0.0707543,0.0001475285,0.6659808,0.1191019,0.001079272],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2174494,0.001036071,0.7246612,0.02543532,0.007014138,0.0003222636,0.00005593791,0.00002238154,0.02400335],"genre_scores_gemma":[0.7687677,0.0001135817,0.2295234,0.0002992243,0.0009900789,0.000001300049,0.000006699536,0.000006017501,0.0002919332],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5513183,"threshold_uncertainty_score":0.8104492,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3194827031","doi":"10.1177/14614448211038761","title":"Using social media images as data in social science research","year":2021,"lang":"en","type":"article","venue":"New Media & Society","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Social Sciences and Humanities Research Council of Canada; Nova Scotia Research Innovation Trust","keywords":"Social media; Data science; Thematic analysis; Computer science; Social research; Coding (social sciences); Narrative; Thematic map; Sociology; Social science; Qualitative research; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.4689358522654855,"gpt":0.5683473242748014,"spread":0.09941147200931594,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01006614,0.000116914,0.0002722182,0.0001214352,0.002516166,0.0003394945,0.00118216,0.0001620179,0.0005955409],"category_scores_gemma":[0.006321823,0.0001244994,0.0001626479,0.004691537,0.002066911,0.000653989,0.0008560035,0.000567504,0.00003889979],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004795832,"about_ca_system_score_gemma":0.007240322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002419374,"about_ca_topic_score_gemma":0.003624452,"domain_scores_codex":[0.99463,0.0009437486,0.0002921229,0.0006686097,0.002718687,0.0007468741],"domain_scores_gemma":[0.9964302,0.002279525,0.00008368169,0.0002685993,0.0006959111,0.0002420873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001441641,0.0002233345,0.003290547,0.00001977135,0.00006885591,0.00005614609,0.6958946,0.00001034596,0.01126632,0.04375123,0.08770554,0.1576989],"study_design_scores_gemma":[0.001970747,0.00001463836,0.09363744,0.00006960946,0.0001423534,0.000006478816,0.486969,0.003711825,0.001720477,0.2724172,0.1383357,0.00100457],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8226558,0.002811308,0.004004207,0.04665803,0.003662856,0.0005485596,0.0001364712,0.000270516,0.1192523],"genre_scores_gemma":[0.9455628,0.0002767115,0.043841,0.0005729463,0.008623658,0.000005141135,0.0001034271,0.00002324824,0.0009910963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2286659,"threshold_uncertainty_score":0.9987824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1597876521","doi":"10.1002/9781119959847.ch1","title":"“It Looks Great but How do I know if it Fits?”: An Introduction to Meta‐Synthesis Research","year":2011,"lang":"en","type":"other","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":76,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Selection (genetic algorithm); Computer science; Qualitative research; Management science; Epistemology; Data science; Engineering ethics; Sociology; Engineering; Artificial intelligence; Social science; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.2145971558398435,"gpt":0.4432425419013202,"spread":0.2286453860614767,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004891579,0.0002655406,0.0005924327,0.00101272,0.0004874101,0.0003295468,0.0007026056,0.0003504501,0.2104387],"category_scores_gemma":[0.001251473,0.0002098891,0.0003102255,0.001039998,0.000321857,0.0001498586,0.000140212,0.0003169074,0.001709376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001245197,"about_ca_system_score_gemma":0.0002386782,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01319981,"about_ca_topic_score_gemma":0.04271001,"domain_scores_codex":[0.9948844,0.002274096,0.0002183982,0.0008529355,0.001258272,0.0005118983],"domain_scores_gemma":[0.9979029,0.0006365693,0.0001204728,0.00054347,0.0004558128,0.0003407359],"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":[0.00001022306,0.00005186575,0.00001470464,0.00001153018,0.0006352609,0.000002582775,0.001735386,0.000003682963,0.000007151706,0.01579281,0.8926718,0.08906297],"study_design_scores_gemma":[0.00003439701,0.0000407611,0.00002561962,0.00001678241,0.0004709319,5.855602e-7,0.002167393,0.00001430188,0.00006281322,0.003932786,0.9929624,0.0002712715],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00001576913,0.0003413611,0.004781873,0.04299243,0.0004524098,0.0004002494,0.00002013651,0.000178792,0.950817],"genre_scores_gemma":[0.0003769214,0.0002306548,0.02271494,0.000203551,0.005438645,0.000156769,0.00001409269,0.0001240962,0.9707403],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2087294,"threshold_uncertainty_score":0.9990679,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3019170642","doi":"10.1017/s0008423920000372","title":"(Un)Covering the COVID-19 Pandemic: Framing Analysis of the Crisis in Canada","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Political Science","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto; Université Laval","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Pandemic; Framing (construction); Political science; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Crisis management; Economic history; Geography; History; Outbreak; Law; Medicine; Infectious disease (medical specialty); Virology","retraction":null,"screen_n_in":null,"score":{"opus":0.07415035811355343,"gpt":0.3646452236737246,"spread":0.2904948655601712,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002551524,0.00005362451,0.0001978271,0.0002170172,0.000575939,0.00006800212,0.0009810531,0.00002126836,0.0002083799],"category_scores_gemma":[0.006795766,0.00003296958,0.0001373262,0.00459262,0.000749976,0.0001250053,0.00003570982,0.0002057993,3.252394e-7],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001770968,"about_ca_system_score_gemma":0.02979302,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9951761,"about_ca_topic_score_gemma":0.9985225,"domain_scores_codex":[0.9980182,0.0003133247,0.0003320745,0.0001178026,0.000718297,0.0005002985],"domain_scores_gemma":[0.9971367,0.0007593858,0.0001516787,0.00009478367,0.0001915655,0.001665869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001808748,0.00000283676,0.7179936,0.000003088863,0.00006565308,0.00002232338,0.00659101,0.01051735,0.00003307233,0.2628677,0.0001627434,0.001738738],"study_design_scores_gemma":[0.0000846766,0.00000997495,0.9607868,0.000006839928,0.0002082463,0.000005785355,0.01696173,0.00643796,0.00002918829,0.008220413,0.007152923,0.00009545288],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9145692,0.00009695295,0.002973965,0.08121545,0.0001714763,0.00004466738,0.00001367663,0.000001444775,0.0009131939],"genre_scores_gemma":[0.9912723,0.000002297093,0.0002118868,0.008428462,0.00007672355,2.894215e-7,8.837021e-8,0.000001508743,0.000006413681],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2546473,"threshold_uncertainty_score":0.9757072,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4251909731","doi":"10.1142/p981","title":"Exploring Big Historical Data","year":2014,"lang":"en","type":"book","venue":"IMPERIAL COLLEGE PRESS eBooks","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":66,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Carleton University","funders":"","keywords":"Big data; History; Computer science; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.485653745540465,"gpt":0.3824765685860768,"spread":0.1031771769543882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001676229,0.0003232319,0.0006994303,0.0001751563,0.0006887456,0.0001629626,0.001613407,0.0003204962,0.0000997285],"category_scores_gemma":[0.0004981976,0.0003293525,0.0002282566,0.00004423105,0.0002139844,0.0001561968,0.0007519909,0.0003910275,0.00003123391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000925234,"about_ca_system_score_gemma":0.001449245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003580117,"about_ca_topic_score_gemma":0.002008956,"domain_scores_codex":[0.9965826,0.0006880765,0.0005373327,0.0007672058,0.0009987358,0.0004260258],"domain_scores_gemma":[0.9974359,0.0008667222,0.0002995917,0.000916803,0.0002065336,0.0002743961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001185523,0.00003450274,0.000001045287,0.00006974395,0.0002840412,0.00004492692,0.003545606,0.00001079192,0.00002191188,0.5092502,0.330179,0.1564396],"study_design_scores_gemma":[0.0002452094,0.00002533981,0.000001495735,0.00004618697,0.000178944,0.000001103036,0.00002460878,0.0001156718,0.000007841228,0.01266673,0.9863007,0.000386145],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00003803726,0.0004490459,0.001314253,0.0001389877,0.006577002,0.0003902168,0.0002137793,0.0001783022,0.9907004],"genre_scores_gemma":[0.0006508743,0.00009653581,0.001569188,0.00006678184,0.0149137,0.00007964166,0.0001330169,0.0000559319,0.9824343],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6561217,"threshold_uncertainty_score":0.9999158,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2567467453","doi":"10.18653/v1/d16-1148","title":"Analyzing Framing through the Casts of Characters in the News","year":2016,"lang":"en","type":"article","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Washington","keywords":"Framing (construction); Computer science; History; Archaeology","retraction":null,"screen_n_in":null,"score":{"opus":0.0615801185775051,"gpt":0.3893943235540798,"spread":0.3278142049765747,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001113121,0.00003320662,0.00007197339,0.00002622964,0.0001484821,0.00002123012,0.0002210464,0.00001781078,0.0001500064],"category_scores_gemma":[0.0002186585,0.00001226818,0.00006076069,0.0003984286,0.0001206504,0.0001162651,0.00001807826,0.00003655388,0.000008426013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001563545,"about_ca_system_score_gemma":0.00003543416,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007286337,"about_ca_topic_score_gemma":0.007561085,"domain_scores_codex":[0.9990914,0.0004109982,0.0001290358,0.00007361876,0.0001940614,0.0001009005],"domain_scores_gemma":[0.9985247,0.001285809,0.00005965031,0.00008723648,0.00003272864,0.00000985487],"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":[0.000006279131,0.00004551692,0.07093674,0.000002797077,0.00004531765,0.000002483617,0.08086672,0.00004441618,0.0006110313,0.3994273,0.0004203744,0.447591],"study_design_scores_gemma":[0.0005225298,0.00003767985,0.5542151,0.0000849706,0.00008643481,0.000001766461,0.08896431,0.000450331,0.0004292971,0.2198157,0.1350738,0.0003180188],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8100499,0.0001161528,0.06441492,0.05420946,0.0001356016,0.0001473817,8.576977e-7,0.0000162466,0.07090952],"genre_scores_gemma":[0.9976819,0.00003804541,0.001027185,0.0003439703,0.00009882306,0.00000230393,1.763979e-7,0.000001301185,0.0008062824],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4832784,"threshold_uncertainty_score":0.9993242,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2917452130","doi":"10.1002/wcc.576","title":"Frontiers in data analytics for adaptation research: Topic modeling","year":2019,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Climate Change","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Adaptation (eye); Corporate governance; Leverage (statistics); Data science; Topic model; Convention; Climate change adaptation; Vulnerability (computing); Political science; Climate change; Computer science; Sociology; Social science; Business; Ecology","retraction":null,"screen_n_in":null,"score":{"opus":0.661302599603033,"gpt":0.5346772663937048,"spread":0.1266253332093281,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007799397,0.0001245166,0.0004368225,0.0003470336,0.0003614901,0.00008078039,0.0007041884,0.00007870225,0.0001236355],"category_scores_gemma":[0.0002750148,0.0001113074,0.0001353916,0.0007991454,0.00007117434,0.0005934939,0.000767879,0.0001882442,0.00009090336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001753483,"about_ca_system_score_gemma":0.00005104111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00010907,"about_ca_topic_score_gemma":0.002283693,"domain_scores_codex":[0.9974548,0.000737867,0.0005117635,0.000483969,0.0003511666,0.0004604482],"domain_scores_gemma":[0.9988197,0.000302727,0.0001302269,0.0004996904,0.0001608097,0.00008681877],"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":[0.0001715696,0.0002661156,0.009321008,0.001037838,0.0000731067,0.000007560795,0.1457882,0.002588287,0.00001624718,0.01107536,0.009751912,0.8199028],"study_design_scores_gemma":[0.0002321321,0.00005224028,0.0001473595,0.0007117902,0.00003555408,3.339221e-7,0.02553132,0.8843768,2.536175e-7,0.02012347,0.06861006,0.0001787501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2719417,0.1503023,0.4292999,0.05443639,0.01207297,0.02522913,0.000826634,0.000403707,0.05548728],"genre_scores_gemma":[0.728947,0.1242736,0.1357518,0.0006992465,0.003813161,0.001322397,0.002106222,0.0001032278,0.002983329],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8817884,"threshold_uncertainty_score":0.4538983,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3165669050","doi":"10.1007/s11135-021-01164-0","title":"Algorithmic thinking in the public interest: navigating technical, legal, and ethical hurdles to web scraping in the social sciences","year":2021,"lang":"en","type":"article","venue":"Quality & Quantity","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Winnipeg; Carleton University; University of Toronto","funders":"","keywords":"Context (archaeology); Openness to experience; The Internet; Data sharing; Social media; Computer science; Principle of legality; World Wide Web; Data science; Internet privacy; Knowledge management; Public relations; Engineering ethics; Political science; Engineering; Psychology; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.279075911413793,"gpt":0.5367740553267564,"spread":0.2576981439129634,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.02932939,0.00009678854,0.0002256535,0.00008486362,0.002071254,0.001032303,0.0006901355,0.0001401892,0.00002165442],"category_scores_gemma":[0.004677947,0.00006630199,0.00009617786,0.002277889,0.0007891106,0.0002344408,0.0001949291,0.0009413156,0.000003911037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006220794,"about_ca_system_score_gemma":0.0004073613,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005149908,"about_ca_topic_score_gemma":0.1129986,"domain_scores_codex":[0.9919869,0.006035917,0.0004312891,0.0003518078,0.0008730531,0.0003210708],"domain_scores_gemma":[0.9963589,0.003250593,0.0001100502,0.0001322432,0.000110254,0.00003798389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002446206,0.00007148054,0.01381082,0.00001180822,0.000005825359,0.00001198926,0.02662207,0.000007560797,0.0002427275,0.9467217,0.0000997335,0.01239179],"study_design_scores_gemma":[0.0004890515,0.00008299443,0.3293266,0.000317921,0.00003806274,0.00002109642,0.2757947,0.002629536,0.00004096744,0.3664366,0.02416955,0.0006527834],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8201777,0.0001723295,0.002268042,0.1762933,0.00007313512,0.0001336691,0.000002291511,0.00002519236,0.0008543915],"genre_scores_gemma":[0.9880632,0.00002824416,0.006229956,0.005477095,0.0001774037,0.00001374054,0.000002451803,0.000002939193,0.000004951105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5802851,"threshold_uncertainty_score":0.9995096,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2578588058","doi":"10.1017/s0008423916001165","title":"Digitization of the Canadian Parliamentary Debates","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Political Science","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"","keywords":"Digitization; House of Commons; Political science; Architecture; Politics; Commons; Public administration; Library science; Media studies; Computer science; Sociology; Geography; Law; Telecommunications; Parliament; Archaeology","retraction":null,"screen_n_in":null,"score":{"opus":0.04302063556107077,"gpt":0.3648532980313726,"spread":0.3218326624703018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0016382,0.00004155531,0.00009448113,0.0001820176,0.002859258,0.0003601473,0.00107933,0.00002905629,0.0001537231],"category_scores_gemma":[0.003748757,0.00002944227,0.00007551714,0.0002777265,0.003048855,0.0004020554,0.00001920739,0.00009303835,0.000002827996],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007070474,"about_ca_system_score_gemma":0.015425,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9705923,"about_ca_topic_score_gemma":0.9947588,"domain_scores_codex":[0.9986835,0.00008462875,0.0001916317,0.00007357745,0.0004549439,0.0005116911],"domain_scores_gemma":[0.9974084,0.00009901572,0.0001734716,0.0001492127,0.0005008053,0.001669034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[3.920013e-7,0.000002914571,0.1416765,0.000001037972,0.000005240062,0.000006535107,0.0006417116,0.00002908103,0.00001933166,0.8527229,0.0001709262,0.004723422],"study_design_scores_gemma":[0.0000472285,0.0000110019,0.9320996,0.00002519091,0.0000148687,0.000005288927,0.0007140479,0.00009992487,0.0002579543,0.06102996,0.005643808,0.00005110227],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8986006,0.00005330582,0.0003519087,0.04180527,0.001100892,0.00008202303,0.00001903805,0.000001960127,0.05798501],"genre_scores_gemma":[0.9988765,0.000001066159,0.0003613151,0.0004281864,0.0001685268,1.928658e-7,1.472954e-7,0.000001713232,0.0001623164],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.791693,"threshold_uncertainty_score":0.9996642,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2791572729","doi":"10.1073/pnas.1719792115","title":"Measuring discursive influence across scholarship","year":2018,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Air Force Office of Scientific Research; Killam Trusts; John Templeton Foundation; National Science Foundation","keywords":"Scholarship; TRACE (psycholinguistics); Citation; Sociology; Data science; Measure (data warehouse); Epistemology; Social science; Computer science; Political science; Library science; Linguistics; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.1460954563481362,"gpt":0.4331857178187166,"spread":0.2870902614705804,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.005486681,0.00006633589,0.0001216052,0.0001007634,0.001141357,0.00007101503,0.001096171,0.00006170673,0.00002489848],"category_scores_gemma":[0.003709208,0.00004516776,0.00009344577,0.001623504,0.00338508,0.000894398,0.0001634843,0.0001333214,0.000004992986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005004075,"about_ca_system_score_gemma":0.00007837037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006058375,"about_ca_topic_score_gemma":0.000003392282,"domain_scores_codex":[0.9973919,0.00003193639,0.0002629257,0.000211128,0.001898595,0.0002035246],"domain_scores_gemma":[0.9981591,0.000275052,0.0003827965,0.000005914979,0.001127107,0.00005003287],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002135169,0.00007084293,0.1669579,0.0000345377,0.00004773209,5.536651e-9,0.01453174,0.0002558268,0.08288123,0.727555,0.0002143143,0.007429482],"study_design_scores_gemma":[0.00008522854,0.00002318479,0.5275096,0.00008769597,0.00001184706,9.624521e-7,0.001858748,0.0001959246,0.05857642,0.4104816,0.00107398,0.00009476118],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.976941,0.00004974052,0.000007519916,0.003763857,0.00002658693,0.00008895613,0.000004378226,0.00001231887,0.01910562],"genre_scores_gemma":[0.9961377,0.000009494225,0.003129105,0.0002206338,0.000224544,0.000003623039,2.188911e-8,0.000001989492,0.0002728965],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3605518,"threshold_uncertainty_score":0.9993271,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2257785951","doi":"10.1016/j.shpsc.2015.12.016","title":"What are narratives good for?","year":2016,"lang":"en","type":"article","venue":"Studies in History and Philosophy of Science Part C Studies in History and Philosophy of Biological and Biomedical Sciences","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":52,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Narrative; Contingency; Narrative criticism; Narrative network; Narrative inquiry; Natural (archaeology); Epistemology; History; Sociology; Aesthetics; Literature; Art; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.3121875705006407,"gpt":0.4168443495923639,"spread":0.1046567790917232,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004903316,0.0002140377,0.0007441942,0.0004276861,0.0008246391,0.000008252544,0.0003732872,0.0001111787,0.0000279055],"category_scores_gemma":[0.001681318,0.0001231495,0.00008574708,0.0006798981,0.1007795,0.0005386194,0.0002809702,0.0001043204,3.199464e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000302777,"about_ca_system_score_gemma":0.0001697957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000259876,"about_ca_topic_score_gemma":0.00006469302,"domain_scores_codex":[0.9973385,0.0003448018,0.0006142128,0.0007403136,0.0005782208,0.0003839772],"domain_scores_gemma":[0.9970418,0.002112503,0.0003546425,0.00009429484,0.0002291115,0.0001675999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003588384,0.0006638003,0.05567006,0.0006440502,0.0001909758,0.00001723179,0.1512539,0.000001897329,0.001846211,0.7406457,0.0009522541,0.04775508],"study_design_scores_gemma":[0.0006073237,0.00105616,0.004004645,0.001058753,0.00002084896,0.000002651281,0.03108933,0.000007397234,0.00002700097,0.9019172,0.05987448,0.0003342644],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6804372,0.2886324,0.00002988257,0.0198666,0.003700455,0.0004399058,0.00002134681,0.00001993512,0.006852204],"genre_scores_gemma":[0.9591364,0.03943753,0.0008321453,0.0001893633,0.0002893539,0.00003448888,4.125575e-7,0.000002123224,0.00007817981],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2786992,"threshold_uncertainty_score":0.9016677,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2028141008","doi":"10.1111/j.1740-9713.2012.00583.x","title":"Big Data and City Living – What can it do for Us?","year":2012,"lang":"en","type":"article","venue":"Significance","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Big data; Data science; Computer science; Gerontology; Medicine; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.1951561860669645,"gpt":0.4091075099082735,"spread":0.213951323841309,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001867775,0.00005492326,0.0001002853,0.00002824377,0.0003436855,0.0001733257,0.0002346915,0.00003065836,0.00007545083],"category_scores_gemma":[0.0005841433,0.00005155431,0.00002535726,0.000183005,0.0001205913,0.000460133,0.00007996212,0.00004152815,0.000003310261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002632739,"about_ca_system_score_gemma":0.00008379409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008780809,"about_ca_topic_score_gemma":0.001993544,"domain_scores_codex":[0.9991701,0.0001442042,0.00009986699,0.0001911495,0.0001739656,0.0002207457],"domain_scores_gemma":[0.9986318,0.0009679899,0.00005822521,0.0001740244,0.00005751802,0.0001104221],"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":[0.000009863554,0.0000869627,0.1682417,0.00002988226,0.00006429582,4.231451e-7,0.02270878,0.00001965841,0.0002435973,0.01864271,0.004798769,0.7851533],"study_design_scores_gemma":[0.0001778855,0.00002413951,0.1243893,0.00009637775,0.0001057046,6.282782e-7,0.01854789,0.001764609,0.00009523247,0.01273522,0.8416381,0.0004249795],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7989768,0.009012558,0.1573695,0.01526929,0.003894567,0.0010096,0.0001702942,0.0001459322,0.01415151],"genre_scores_gemma":[0.9907868,0.0002776791,0.006739585,0.0003002885,0.000813008,0.00001271206,0.000008646979,0.000004318839,0.001056954],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8368393,"threshold_uncertainty_score":0.2643386,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2076133938","doi":"10.7202/013259ar","title":"Differences in News Translation between Broadcasting and Newspapers: A Case Study of Korean-English Translation1","year":2006,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Newspaper; Linguistics; Translation (biology); Rendering (computer graphics); Broadcasting (networking); Literary translation; Computer science; Advertising; History; Media studies; Sociology; Artificial intelligence; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.1200677126363066,"gpt":0.348027203817123,"spread":0.2279594911808164,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001585152,0.0001314651,0.0004329761,0.000306129,0.0004227389,0.0001421518,0.0001137403,0.00004740663,0.00003580574],"category_scores_gemma":[0.0001416196,0.0001083442,0.0001443288,0.0007507242,0.0001734403,0.000452201,0.000005263717,0.0002065397,1.502389e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002540911,"about_ca_system_score_gemma":0.00005487051,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01614919,"about_ca_topic_score_gemma":0.04355295,"domain_scores_codex":[0.9974309,0.001161211,0.0005965488,0.000189921,0.0004193776,0.0002020443],"domain_scores_gemma":[0.9987063,0.0007820787,0.0002074266,0.00005748646,0.0001537534,0.00009298975],"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":[0.00001070376,0.0001772495,0.4703715,0.000008906719,0.000216139,0.00009793253,0.03381298,0.0004185478,0.0000344489,0.0002283243,0.000002523461,0.4946207],"study_design_scores_gemma":[0.002522377,0.0003903659,0.8853145,0.00005553877,0.002828032,0.0002497536,0.06986929,0.0008442158,0.00003196804,0.0360161,0.001405296,0.0004725561],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9867269,0.00570645,0.00670782,0.0001600332,0.00007148382,0.0001775196,0.000002515491,0.00001523779,0.0004320044],"genre_scores_gemma":[0.9934403,0.000346111,0.00576261,0.000004244871,0.0003945922,0.000003429446,0.000001602348,0.00000748842,0.00003967952],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4941482,"threshold_uncertainty_score":0.9904023,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4395027451","doi":"10.1109/comst.2024.3392642","title":"The Metaverse: Survey, Trends, Novel Pipeline Ecosystem &amp; Future Directions","year":2024,"lang":"en","type":"article","venue":"IEEE Communications Surveys & Tutorials","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure; Concordia University; Polytechnique Montréal","funders":"","keywords":"Pipeline (software); Ecosystem; Environmental resource management; Computer science; Environmental science; Data science; Ecology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.1336653216643221,"gpt":0.4212711845858061,"spread":0.287605862921484,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.03337285,0.0001995317,0.0003524622,0.0002649313,0.003340016,0.0007750129,0.001597357,0.0001492336,0.0002329359],"category_scores_gemma":[0.001850164,0.0001526235,0.0003183294,0.002978304,0.0003873403,0.0002869238,0.0001701476,0.0003609491,0.0003125122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002395405,"about_ca_system_score_gemma":0.0005131554,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01167999,"about_ca_topic_score_gemma":0.3459639,"domain_scores_codex":[0.9838197,0.01417711,0.0006956735,0.0003458018,0.0006125888,0.0003490828],"domain_scores_gemma":[0.9826034,0.01480707,0.0001846766,0.001563458,0.0006983851,0.0001430408],"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":[0.00002391384,0.0005527092,0.001505136,0.00002795019,0.001361701,0.000001842497,0.0134241,0.0004792005,0.0004629304,0.258271,0.1372499,0.5866396],"study_design_scores_gemma":[0.00009095101,0.000004456494,0.005251839,0.00001663327,0.0001077144,0.000001460884,0.0004730837,0.0006648409,0.000007179043,0.001164197,0.9920327,0.0001849248],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01701276,0.1088423,0.3950018,0.115435,0.1698737,0.002797478,0.006221852,0.004565915,0.1802493],"genre_scores_gemma":[0.8925195,0.01413056,0.009583615,0.00007898769,0.009852289,0.000253264,0.0009571193,0.00007492468,0.07254977],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8755067,"threshold_uncertainty_score":0.9979575,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3168278108","doi":"10.1017/pan.2021.37","title":"Cross-Domain Topic Classification for Political Texts","year":2021,"lang":"en","type":"article","venue":"Political Analysis","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"H2020 European Research Council; University of Essex; Università Bocconi; Eidgenössische Technische Hochschule Zürich; Wissenschaftszentrum Berlin für Sozialforschung; York University; London School of Economics and Political Science","keywords":"Computer science; Classifier (UML); Domain (mathematical analysis); Artificial intelligence; Natural language processing; Labeled data; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.08141688647427724,"gpt":0.4642052680106769,"spread":0.3827883815363996,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007856417,0.0001055195,0.0003253566,0.0001876098,0.0005060387,0.0002035653,0.0001762034,0.0001120647,0.001600706],"category_scores_gemma":[0.002016568,0.00010191,0.0006446657,0.001447743,0.0003368338,0.00009907457,0.00004120969,0.00008955732,0.000051118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002061624,"about_ca_system_score_gemma":0.0002901785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009328364,"about_ca_topic_score_gemma":0.001083222,"domain_scores_codex":[0.9976563,0.0004228544,0.0003549136,0.0003862333,0.0004512079,0.000728459],"domain_scores_gemma":[0.9973983,0.001274734,0.00006703155,0.0002221348,0.0005577386,0.000480123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003705971,0.00008464647,0.03590837,0.000006173726,0.0003500464,0.000003177129,0.0001595834,0.0000154646,0.00003819566,0.9610949,0.00004632563,0.002289372],"study_design_scores_gemma":[0.0002150421,0.00001210954,0.180781,0.000002922412,0.001080018,8.4032e-7,0.001651643,0.00556631,0.0001711143,0.7706351,0.03967771,0.0002062131],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2049179,0.0001622702,0.5352697,0.0642454,0.0002497449,0.0002179305,0.00009016116,0.0001465781,0.1947003],"genre_scores_gemma":[0.974386,0.000002272496,0.01544651,0.001074984,0.0006297972,0.00002857651,0.0001058904,0.000006734825,0.008319268],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.769468,"threshold_uncertainty_score":0.999312,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3170686427","doi":"10.3389/frai.2021.664737","title":"Gender Bias in the News: A Scalable Topic Modelling and Visualization Framework","year":2021,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Simon Fraser University","keywords":"Latent Dirichlet allocation; Topic model; Mainstream; Representation (politics); Entertainment; Politics; Computer science; Data science; Psychology; Political science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1975284295315101,"gpt":0.4108134902179633,"spread":0.2132850606864532,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001299819,0.00007071626,0.0001369119,0.0001277202,0.0002086447,0.0001560267,0.0001549831,0.00008336277,0.00007065399],"category_scores_gemma":[0.0006460531,0.00006282828,0.00003954435,0.001282398,0.0001273195,0.0001310506,0.00002851368,0.0001579221,0.000005355392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005290855,"about_ca_system_score_gemma":0.0001130084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001049795,"about_ca_topic_score_gemma":0.002219079,"domain_scores_codex":[0.9983554,0.0006463682,0.0002825939,0.0002353153,0.0002810227,0.0001993316],"domain_scores_gemma":[0.9993113,0.0004198262,0.00004830017,0.0001074079,0.00007691314,0.00003626067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001270062,0.0001154592,0.03826321,0.00001100845,0.0000130218,0.00002095999,0.0507783,0.1205887,0.000006099225,0.5991264,0.0001934386,0.1908706],"study_design_scores_gemma":[0.000008865415,0.000004011322,0.0004100101,0.00002170065,0.000006923286,3.89123e-7,0.02631952,0.2860455,0.0001050859,0.6846856,0.002313704,0.00007869106],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05443779,0.0009835433,0.9409968,0.001124059,0.0004116388,0.00009487075,4.791751e-7,0.00001187347,0.00193897],"genre_scores_gemma":[0.9133832,0.0005939916,0.08526044,0.0004054182,0.0001906417,0.00001063195,0.000003423686,0.000004942305,0.0001473392],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8589454,"threshold_uncertainty_score":0.2562063,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4292819996","doi":"10.1177/14614448221113923","title":"Participatory censorship: How online fandom community facilitates authoritarian rule","year":2022,"lang":"en","type":"article","venue":"New Media & Society","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; Concordia University","funders":"","keywords":"Censorship; Authoritarianism; Social media; Sociology; Citizen journalism; Politics; Online community; Public relations; Political science; Media studies; Democracy; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.1814214380344424,"gpt":0.3824314028423084,"spread":0.2010099648078661,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003783159,0.0001326128,0.0002638205,0.00003147169,0.003097752,0.00007439173,0.0004772793,0.00007485886,0.00131934],"category_scores_gemma":[0.001032923,0.0001356019,0.0003842939,0.0006057953,0.0003025352,0.0001395335,0.0002185643,0.0007888089,0.00001558348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000254744,"about_ca_system_score_gemma":0.0005082842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006317821,"about_ca_topic_score_gemma":0.00605155,"domain_scores_codex":[0.9953926,0.002950005,0.0002099206,0.00020855,0.0008423841,0.0003965397],"domain_scores_gemma":[0.9968083,0.002433998,0.0001039178,0.0002285398,0.0001042981,0.0003209364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003896382,0.000620285,0.01462425,0.00002015611,0.0002750392,0.000005473744,0.8139145,0.0006176696,0.0003447399,0.01036309,0.1080351,0.05114078],"study_design_scores_gemma":[0.0008608231,0.0000445936,0.03666632,0.0000051782,0.000108922,6.530913e-7,0.4003659,0.001385287,0.00002104567,0.03812501,0.522103,0.0003133177],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9715183,0.0007287168,0.001146509,0.0238416,0.0008737658,0.0001946365,0.0001603487,0.000208479,0.0013277],"genre_scores_gemma":[0.9835557,0.00004874622,0.0109316,0.0006809042,0.0006376334,0.00002994663,0.000193974,0.00001255659,0.003908904],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.414068,"threshold_uncertainty_score":0.9995936,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4398440537","doi":"10.7910/dvn/dus88v","title":"2019 Canadian Election Study (CES) - Online Survey","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto; Toronto Metropolitan University; Université du Québec à Montréal; Western University","funders":"","keywords":"Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.06690661034692758,"gpt":0.365365284635189,"spread":0.2984586742882614,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001895258,0.0002282268,0.000391408,0.0003451996,0.0006274579,0.0002158505,0.0007821653,0.0002053308,0.01612945],"category_scores_gemma":[0.001552762,0.0002399765,0.0001124215,0.0009996528,0.0000891612,0.0002131881,0.000143729,0.0004491826,0.0660624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003418374,"about_ca_system_score_gemma":0.001778916,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9702021,"about_ca_topic_score_gemma":0.9959114,"domain_scores_codex":[0.9962445,0.001833025,0.0003278241,0.0005399779,0.0006801831,0.0003744437],"domain_scores_gemma":[0.9982472,0.0003511537,0.000188283,0.0004629859,0.0002234066,0.0005269789],"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":[0.0000152208,0.0001480213,0.0005244662,0.000004715486,0.0001441578,0.00004499243,0.0002058124,0.00001631276,8.264323e-8,0.00001303267,0.997789,0.001094168],"study_design_scores_gemma":[0.0001659805,0.00005348602,0.01148441,0.000006705565,0.0001805237,4.860663e-7,0.0004930132,0.00003697853,4.57149e-8,0.00003327379,0.9872873,0.0002578352],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001097304,0.000001017749,0.00004956712,0.00005156764,0.0009127416,0.0003546842,0.9982871,0.00003974594,0.0001937893],"genre_scores_gemma":[0.0001856882,0.0001452569,0.0001883665,0.0004639476,0.0008065757,0.000006324064,0.9973446,0.00001297745,0.0008463116],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04993295,"threshold_uncertainty_score":0.9847699,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2810369529","doi":"10.1017/s1049096518000926","title":"Data Access, Transparency, and Replication: New Insights from the Political Behavior Literature","year":2018,"lang":"en","type":"article","venue":"PS Political Science & Politics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Transparency (behavior); Politics; Replication (statistics); Political science; Data sharing; Public relations; Law; Statistics; Medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1624169664032016,"gpt":0.4777498636635403,"spread":0.3153328972603388,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.001066359,0.000185919,0.0002314135,0.0001007636,0.001870444,0.001169348,0.002631595,0.000131198,0.0002029179],"category_scores_gemma":[0.003453588,0.0001299546,0.00006280626,0.001113637,0.006479746,0.001135114,0.0005819288,0.0002788829,0.0000417159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002229792,"about_ca_system_score_gemma":0.002072186,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02372494,"about_ca_topic_score_gemma":0.003278499,"domain_scores_codex":[0.9958006,0.0003009583,0.00040722,0.0009430301,0.001155021,0.001393127],"domain_scores_gemma":[0.9952132,0.001169596,0.00007348862,0.001316333,0.0004766749,0.001750707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002014296,0.00004730816,0.008505541,0.000001643653,0.000007238344,0.000002812575,0.001478559,6.088865e-8,0.00004166053,0.986424,0.0006489634,0.002840246],"study_design_scores_gemma":[0.0001446134,0.00003753418,0.2119705,0.00002928758,0.0001302867,0.000006055762,0.001153489,0.0006123733,0.0002363622,0.7218442,0.06359286,0.0002424668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5897177,0.001225621,0.01509721,0.2610517,0.001639605,0.00101617,0.001170737,0.0003688925,0.1287124],"genre_scores_gemma":[0.9852973,0.00001756982,0.004124695,0.006197371,0.003718916,0.000008200292,0.00007831482,0.000009788174,0.0005478346],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3955796,"threshold_uncertainty_score":0.9998676,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2886358838","doi":"10.18653/v1/w16-56","title":"Proceedings of the First Workshop on NLP and Computational Social Science","year":2016,"lang":"en","type":"paratext","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Pacific Northwest National Laboratory; Office of Naval Research; University of Toronto; University of California, San Diego; Defense Advanced Research Projects Agency; Universiteit van Tilburg; University of Massachusetts Amherst; Freie Universität Berlin; Centre National de la Recherche Scientifique; University of Melbourne; Institute for Quantitative Social Science, Harvard University; University of Pittsburgh; Korea Advanced Institute of Science and Technology; University of Minnesota; National Science Foundation; Princeton University; University of Washington; Harvard Business School; Ohio State University; University of Pennsylvania; Multidisciplinary University Research Initiative; McGill University; Microsoft Research; University College London; Carnegie Mellon University","keywords":"Computer science; Artificial intelligence; Natural language processing; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.04071723295587542,"gpt":0.3739174452502604,"spread":0.333200212294385,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00102636,0.0001240196,0.0002222894,0.0001630255,0.001499654,0.0001430545,0.0004981581,0.0001219056,0.001131697],"category_scores_gemma":[0.0002151577,0.00007194578,0.0001159595,0.0008779225,0.001983869,0.000125095,0.0001569614,0.0001401014,0.0001171745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001030439,"about_ca_system_score_gemma":0.0004763988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007813546,"about_ca_topic_score_gemma":0.00005527712,"domain_scores_codex":[0.9981986,0.00003344324,0.0002144904,0.0003130657,0.001031326,0.0002090818],"domain_scores_gemma":[0.9985806,0.0005228676,0.0002527221,0.00004191083,0.0005444848,0.00005746158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001741297,0.00006710447,0.0003813481,0.00004608736,0.00005881742,9.058711e-8,0.005635635,0.00008396174,0.00001804044,0.6956017,0.2574655,0.0406243],"study_design_scores_gemma":[0.0002996347,0.00002497877,0.01496909,0.000288441,0.00006166114,6.337885e-7,0.001585016,0.0003265702,0.00005098372,0.04998845,0.9320052,0.0003993143],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.003859871,0.00005605096,0.0005373643,0.008937941,0.0005988809,0.0001875351,0.00001544224,0.00001288181,0.985794],"genre_scores_gemma":[0.5050321,0.0001150847,0.002193243,0.0009606777,0.001765175,0.00001891874,0.00000497608,0.0000184935,0.4898914],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.6745397,"threshold_uncertainty_score":0.9998003,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4310576792","doi":"10.1177/00491241221123088","title":"From Ends to Means: The Promise of Computational Text Analysis for Theoretically Driven Sociological Research","year":2022,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Skepticism; Field (mathematics); Relevance (law); Management science; Set (abstract data type); Computational model; Epistemology; Selection (genetic algorithm); Computational sociology; Data science; Process (computing); Sociology; Artificial intelligence; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.4486729254285306,"gpt":0.6277772920025255,"spread":0.1791043665739949,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.09616744,0.0001766877,0.000715454,0.0006165434,0.004796056,0.0001142436,0.001994361,0.0002516362,0.004642138],"category_scores_gemma":[0.02166873,0.0001152811,0.0007760964,0.005022982,0.004946711,0.00005269825,0.001329954,0.001723004,0.00002307089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004313441,"about_ca_system_score_gemma":0.0006834728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009205526,"about_ca_topic_score_gemma":0.0000515748,"domain_scores_codex":[0.9332029,0.06137319,0.0006671379,0.0008738088,0.002848344,0.001034646],"domain_scores_gemma":[0.9047949,0.09248824,0.0001317736,0.0003849402,0.001896946,0.0003032136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004812182,0.0004857278,0.003958033,0.000008001253,0.001018059,0.000004815085,0.03666909,0.02182173,0.0009749343,0.860086,0.002007676,0.07248474],"study_design_scores_gemma":[0.000247517,0.0005179988,0.01307212,0.0000030618,0.0001115888,2.106438e-7,0.03173113,0.01215058,0.00003163528,0.9228437,0.01913661,0.0001538423],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2435351,0.0005064528,0.6876985,0.05424897,0.0001922619,0.002563378,0.0002869354,0.00009804356,0.01087034],"genre_scores_gemma":[0.6546878,0.00001998512,0.3429888,0.0002439734,0.0004391833,0.0009805417,0.00007061293,0.00001138434,0.0005576586],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4111527,"threshold_uncertainty_score":0.9977612,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3113091126","doi":"10.1016/j.bdr.2020.100173","title":"Agreeing to Disagree: Choosing Among Eight Topic-Modeling Methods","year":2020,"lang":"en","type":"article","venue":"Big Data Research","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Hong Kong Polytechnic University","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Data science; Artificial intelligence; Coherence (philosophical gambling strategy); Field (mathematics); Context (archaeology); Machine learning; Management science; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.8645336607084751,"gpt":0.6295130273678069,"spread":0.2350206333406683,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009259239,0.00009170833,0.0001949661,0.0001888215,0.001004764,0.0003741746,0.001508523,0.00006751506,0.0002103635],"category_scores_gemma":[0.006129509,0.00008455684,0.00005553034,0.002016731,0.0001575994,0.0003724009,0.001405045,0.0003608269,0.0001145059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000080818,"about_ca_system_score_gemma":0.0002620197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006251721,"about_ca_topic_score_gemma":0.002660237,"domain_scores_codex":[0.9955417,0.001895229,0.0002518596,0.0005997883,0.001182187,0.0005292619],"domain_scores_gemma":[0.9975135,0.001157119,0.00003124427,0.0005158762,0.0002933542,0.0004888658],"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":[0.00001801186,0.00002496227,0.003656276,0.00001653674,0.00003847262,0.000013008,0.006914508,0.000562519,0.0005418501,0.003426272,0.002598736,0.9821888],"study_design_scores_gemma":[0.0002749028,0.00005755342,0.004460173,0.00007652569,0.00003784292,4.969021e-7,0.006673796,0.5352027,0.0002549113,0.007789413,0.4447511,0.0004205507],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0312003,0.0005318184,0.9240699,0.02678004,0.0002935114,0.0003721925,0.00003846282,0.00007921696,0.01663457],"genre_scores_gemma":[0.8032299,0.0001023059,0.1918783,0.0005724387,0.002881619,0.00001486103,0.0001326033,0.00002024315,0.0011677],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9817683,"threshold_uncertainty_score":0.9450773,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391464262","doi":"10.1162/qss_a_00285","title":"Large-scale text analysis using generative language models: A case study in discovering public value expressions in AI patents","year":2024,"lang":"en","type":"article","venue":"Quantitative Science Studies","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; Snap","keywords":"Generative grammar; Natural language processing; Scale (ratio); Value (mathematics); Computer science; Generative model; Artificial intelligence; Linguistics; Machine learning; Geography; Cartography; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.2553169436416557,"gpt":0.5238114656364624,"spread":0.2684945219948067,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004589079,0.0001581162,0.000400745,0.001667974,0.001162907,0.0003684238,0.0002608649,0.00002556232,0.00001683716],"category_scores_gemma":[0.0008308379,0.0001246912,0.000123847,0.01105967,0.000752338,0.001719394,0.0002850913,0.0001847978,0.000003557703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000386888,"about_ca_system_score_gemma":0.0003830986,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.009356229,"about_ca_topic_score_gemma":0.112171,"domain_scores_codex":[0.9967972,0.0009426446,0.0003689601,0.0006520539,0.0007587001,0.0004804506],"domain_scores_gemma":[0.9987276,0.0007081497,0.00007110113,0.0001383552,0.0002645648,0.00009020454],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.000003841752,0.0002570648,0.03065536,0.000008849272,0.0002860525,0.0006471293,0.8510596,0.0891554,0.0003903407,0.02659447,0.000003172498,0.0009387207],"study_design_scores_gemma":[0.00009261802,0.00002336919,0.002632314,0.00003627691,0.00008065416,0.000001369845,0.57946,0.4135927,0.00001121583,0.003951295,0.000005198558,0.0001130049],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9467995,0.002240204,0.04970578,0.0003653085,0.0001667548,0.0002688332,0.00001482843,0.00003366812,0.0004051544],"genre_scores_gemma":[0.9898112,0.00006019706,0.00991893,0.00003651321,0.00003065304,0.00004214632,0.000001285286,0.000006243813,0.00009277736],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3244373,"threshold_uncertainty_score":0.9972405,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2070320835","doi":"10.1002/asi.22797","title":"In their own image? a comparison of doctoral students' and faculty members' referencing behavior","year":2013,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science and Technology","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Doctoral dissertation; Library science; Psychology; University faculty; Sociology; Medical education; Higher education; Medicine; Political science; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.05346329054850051,"gpt":0.4297384152809274,"spread":0.3762751247324269,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001694904,0.00005044056,0.0002114823,0.0002236115,0.000303388,0.00009532333,0.0004079746,0.00003155461,0.000005037105],"category_scores_gemma":[0.0003953855,0.00003110878,0.00008489273,0.001611328,0.001901089,0.001444228,0.0001170697,0.0001288781,3.186697e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007454341,"about_ca_system_score_gemma":0.0001958242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004520236,"about_ca_topic_score_gemma":0.00004007399,"domain_scores_codex":[0.9989512,0.00002742856,0.0003797235,0.00005296973,0.0004539617,0.0001347082],"domain_scores_gemma":[0.9981428,0.0001087823,0.0008010832,0.000062981,0.0008441246,0.00004018865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002242729,0.0001484363,0.4211032,0.00002499036,0.00008058869,1.414959e-7,0.07663483,0.0000450288,0.007390565,0.01249338,0.002343373,0.4797131],"study_design_scores_gemma":[0.001216905,0.0004675222,0.4516275,0.00005718101,0.0001116289,0.00002474053,0.4977546,0.005339785,0.003410261,0.01379171,0.02592946,0.0002687487],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953949,0.00001733642,0.0006983243,0.00358367,0.00004658139,0.0001499801,0.000002475972,0.000004894108,0.000101855],"genre_scores_gemma":[0.9882087,0.00003521848,0.01154501,0.0001786094,0.00001191538,0.000007125128,2.322145e-7,9.334358e-7,0.00001229993],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4794443,"threshold_uncertainty_score":0.7004643,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2077014275","doi":"10.3138/cjccj.2013.e44","title":"Beyond Frequency: Perceived Realism and the <i>CSI</i> Effect","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Criminology and Criminal Justice/La Revue canadienne de criminologie et de justice pénale","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Realism; Context (archaeology); Psychology; Social psychology; Moderation; Criminal justice; Economic Justice; Criminology; Political science; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.05552850342321045,"gpt":0.3268272035254285,"spread":0.271298700102218,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.007653142,0.0003331813,0.0007387552,0.0005052941,0.001375237,0.0002259563,0.0007073006,0.0004421368,0.00008639523],"category_scores_gemma":[0.01339991,0.0002737035,0.0002071147,0.0001662541,0.003060427,0.0002606193,0.00005426641,0.001082712,0.000004679093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004627501,"about_ca_system_score_gemma":0.002612838,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.06115086,"about_ca_topic_score_gemma":0.190528,"domain_scores_codex":[0.9939553,0.00360732,0.0006092361,0.0003925671,0.0001633523,0.001272204],"domain_scores_gemma":[0.9897971,0.007469755,0.0004408369,0.0002785833,0.0005103576,0.001503324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002165916,0.00001890067,0.001227644,0.0005734515,0.0001721696,0.0008014799,0.08029524,0.0002171072,0.0001689686,0.8718218,0.0008425186,0.04364415],"study_design_scores_gemma":[0.006138946,0.001817235,0.1362503,0.0005397647,0.0442807,0.01148578,0.2872393,0.002516788,0.0000828485,0.4669559,0.04106016,0.001632265],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9574408,0.002303749,0.004077378,0.01522962,0.0006362599,0.0001896551,0.00001187555,0.00002404399,0.02008664],"genre_scores_gemma":[0.9885638,0.001035586,0.004677878,0.004633607,0.0007727731,0.00001471244,0.000005379431,0.00002554116,0.0002707277],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4048658,"threshold_uncertainty_score":0.9999715,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410554739","doi":"10.1177/00491241251339188","title":"Updating “The Future of Coding”: Qualitative Coding with Generative Large Language Models","year":2025,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Russell Sage Foundation","keywords":"Coding (social sciences); Generative grammar; Computer science; Natural language processing; Linguistics; Qualitative research; Artificial intelligence; Sociology; Social science","retraction":null,"screen_n_in":null,"score":{"opus":0.2818745422435381,"gpt":0.6225325648240265,"spread":0.3406580225804884,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.04042321,0.0001178569,0.0003649787,0.0001701724,0.001677359,0.00006897556,0.0005026357,0.0001769391,0.0002370867],"category_scores_gemma":[0.0025708,0.00006646978,0.0001473957,0.0016509,0.001451326,0.0001056277,0.0002281118,0.0007973563,0.000003221759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001248944,"about_ca_system_score_gemma":0.0002825468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003871115,"about_ca_topic_score_gemma":0.0002233953,"domain_scores_codex":[0.9705421,0.02758991,0.000309702,0.0003485035,0.0007048061,0.0005049744],"domain_scores_gemma":[0.9836655,0.01517398,0.0001217887,0.0001800652,0.0007807243,0.00007790979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003357737,0.00004334928,0.0001109683,0.00001072084,0.00009170164,0.000001980707,0.1327832,0.00008180809,0.0007955644,0.823782,0.0002319007,0.04203318],"study_design_scores_gemma":[0.0001886675,0.00006571945,0.0003307612,0.00002457674,0.00002096569,1.406636e-7,0.5135484,0.003798995,0.000438294,0.4792315,0.002260648,0.00009127773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05357642,0.001910926,0.8853077,0.01080898,0.0001221268,0.0004653877,0.00001659326,0.00005142595,0.0477404],"genre_scores_gemma":[0.6370149,0.0001343241,0.3607495,0.0002346493,0.0002982038,0.00005661263,0.000009084752,0.000005569766,0.001497242],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5834385,"threshold_uncertainty_score":0.9996223,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2800743636","doi":"10.2139/ssrn.3067734","title":"The R Package sentometrics to Compute, Aggregate and Predict with Textual Sentiment","year":2017,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke; Center for Interuniversity Research and Analysis on Organizations; HEC Montréal","funders":"","keywords":"Indexation; Computer science; Sentiment analysis; Aggregate (composite); R package; Workflow; Index (typography); Information retrieval; Natural language processing; Database; World Wide Web; Programming language; Economics; Monetary policy","retraction":null,"screen_n_in":null,"score":{"opus":0.01744146395906499,"gpt":0.334739107158963,"spread":0.3172976431998981,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004418742,0.00009406971,0.0001272518,0.0001179236,0.003944156,0.0007976125,0.000457822,0.00003109958,0.00000793667],"category_scores_gemma":[0.0003140935,0.00005801465,0.00005939437,0.0002903959,0.00022328,0.0001802575,0.00009386491,0.0005205122,0.00001062226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003004193,"about_ca_system_score_gemma":0.0009735456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000453202,"about_ca_topic_score_gemma":0.00763434,"domain_scores_codex":[0.9977893,0.0001876222,0.0001554927,0.00015697,0.0005974216,0.001113162],"domain_scores_gemma":[0.9989974,0.0002745561,0.0002166323,0.0001699065,0.0001629281,0.0001784975],"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":[0.0000615044,0.00004570713,0.01910262,0.000001613795,0.0003891138,0.00001022729,0.001487927,0.0001085194,0.00001436816,0.352288,0.0003648629,0.6261256],"study_design_scores_gemma":[0.002697946,0.001398735,0.1492094,0.000102521,0.0004125561,0.0003709529,0.02381145,0.003030013,0.00006947229,0.6055241,0.2124802,0.0008926824],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7132931,0.003246805,0.2438518,0.02552818,0.0004205142,0.0003911793,0.000003714476,0.0000526935,0.01321199],"genre_scores_gemma":[0.9908342,0.0024601,0.001196594,0.00007459034,0.000452046,0.000002492667,6.592327e-7,0.000007782959,0.004971567],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6252329,"threshold_uncertainty_score":0.9973526,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2478027989","doi":"10.1177/0049124116661575","title":"A Novel Sequential Mixed-method Technique for Contrastive Analysis of Unscripted Qualitative Data","year":2016,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"NeuroDevNet; University of British Columbia","funders":"","keywords":"Computer science; Multimethodology; Qualitative research; Qualitative property; Subject (documents); Data science; Contrastive analysis; Psychology; Linguistics; Mathematics education; Machine learning; Sociology; World Wide Web; Social science","retraction":null,"screen_n_in":null,"score":{"opus":0.6465089207335274,"gpt":0.6967122529922157,"spread":0.05020333225868834,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1059114,0.000175042,0.0009059802,0.000688202,0.0006933319,0.00004309599,0.001326583,0.0003901141,0.0005254287],"category_scores_gemma":[0.04424926,0.0001092397,0.0005027043,0.003232901,0.002637985,0.0001893729,0.0005433421,0.0003829368,0.000004353989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002204354,"about_ca_system_score_gemma":0.0004968577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001544299,"about_ca_topic_score_gemma":0.0002483529,"domain_scores_codex":[0.9632133,0.03358316,0.0006545266,0.0008738209,0.000951824,0.0007233442],"domain_scores_gemma":[0.9201405,0.07688267,0.0002694574,0.0005154745,0.001975653,0.0002162404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003004478,0.0003271537,0.0003313028,0.0000189912,0.00279425,0.000001653819,0.01563836,0.00001738616,0.3173119,0.427686,0.0003959411,0.2351766],"study_design_scores_gemma":[0.001243988,0.0004673033,0.007119973,0.00005188831,0.001369287,6.855699e-7,0.04876507,0.004536291,0.01128122,0.9090495,0.01558926,0.000525572],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001972137,0.0001537275,0.9917595,0.002953119,0.0001092889,0.0008710806,0.0006754445,0.0000485827,0.001457094],"genre_scores_gemma":[0.1124354,0.00005246648,0.8862245,0.00004705455,0.0001951497,0.0002851333,0.00008490017,0.0000109824,0.0006644233],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4813634,"threshold_uncertainty_score":0.9719766,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4213310220","doi":"10.1016/j.jbi.2022.104034","title":"Non-negative matrix factorization temporal topic models and clinical text data identify COVID-19 pandemic effects on primary healthcare and community health in Toronto, Canada","year":2022,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"North York General Hospital; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Pandemic; Health care; Computer science; Medicine; Artificial intelligence; Psychology; Coronavirus disease 2019 (COVID-19); Disease; Infectious disease (medical specialty); Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.1456593808156004,"gpt":0.4946154215590821,"spread":0.3489560407434817,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008250027,0.00008116043,0.0003762396,0.0001068494,0.0007054157,0.00004466859,0.0003551907,0.00006194109,0.00002172361],"category_scores_gemma":[0.001132525,0.00006876075,0.00003347026,0.0002675152,0.0001506424,0.0004551261,0.0002952649,0.0007822679,8.973559e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001773376,"about_ca_system_score_gemma":0.003910055,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5491458,"about_ca_topic_score_gemma":0.5819404,"domain_scores_codex":[0.9961269,0.001807573,0.001024686,0.00006902782,0.000803971,0.0001678471],"domain_scores_gemma":[0.9959227,0.002672577,0.0007085741,0.0001360559,0.00007267934,0.0004873826],"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":[0.0003471769,0.0008178347,0.2744833,0.0015464,0.0003439021,0.00004667877,0.1204805,0.001192136,0.000001801816,0.002359889,0.01757953,0.5808008],"study_design_scores_gemma":[0.008766117,0.004421555,0.4569317,0.0005147171,0.000175083,0.0001433405,0.226297,0.1716876,6.106646e-7,0.04645593,0.08377127,0.000835118],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9221342,0.0009981659,0.05770069,0.01699413,0.001133697,0.0005475688,0.0002004061,0.00001629001,0.0002748076],"genre_scores_gemma":[0.9908535,0.0008213358,0.003946499,0.004109676,0.0001381453,0.000001467521,0.0001076827,0.000003416166,0.00001826638],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5799657,"threshold_uncertainty_score":0.6936269,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4317910427","doi":"10.1177/20539517221149106","title":"Formally comparing topic models and human-generated qualitative coding of physician mothers’ experiences of workplace discrimination","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Human Genome Research Institute","keywords":"Coding (social sciences); Computer science; Thematic analysis; Leverage (statistics); Data science; Qualitative research; Topic model; Context (archaeology); Artificial intelligence; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.4102039748049899,"gpt":0.469404413208051,"spread":0.05920043840306116,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001271993,0.00005749032,0.0001680026,0.00002938616,0.000288578,0.00002965882,0.0002406338,0.00003132535,0.000005024455],"category_scores_gemma":[0.00004887821,0.00005323977,0.00005159267,0.0005138638,0.000243473,0.0003568784,0.0001441653,0.00003971324,3.931233e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001850591,"about_ca_system_score_gemma":0.00004551365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009221418,"about_ca_topic_score_gemma":0.0004596195,"domain_scores_codex":[0.999025,0.0002155369,0.0001984767,0.0001671289,0.0002786219,0.0001152428],"domain_scores_gemma":[0.9993427,0.0002568786,0.0001514437,0.0001277882,0.00009390854,0.00002724698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00000289988,0.0000269436,0.000323369,0.00003467322,0.00005952643,8.273729e-8,0.961262,0.0006737225,0.001128943,0.02511784,0.0005746231,0.01079534],"study_design_scores_gemma":[0.000161261,0.0000139187,0.002125768,0.00004498506,0.00003223593,2.285594e-8,0.8771676,0.1107249,0.0003798973,0.009074437,0.000178265,0.00009669325],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9668676,0.00008829956,0.03136003,0.0001307504,0.00006672888,0.00007635985,0.00002047775,0.0000252223,0.001364568],"genre_scores_gemma":[0.9959987,0.00006680912,0.003507771,0.0000238673,0.00007177993,0.000005304631,0.0001339004,0.000003303264,0.0001885497],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1100512,"threshold_uncertainty_score":0.2219538,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2788605280","doi":"10.63317/37krdg6qf9fs","title":"‘Aye’ or ‘No’? Speech-level Sentiment Analysis of Hansard UK Parliamentary Debate Transcripts","year":2018,"lang":"en","type":"article","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Open Text (Canada)","funders":"","keywords":"Sentiment analysis; Speech recognition; Computer science; Political science; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.1028646903379803,"gpt":0.3909686534896928,"spread":0.2881039631517125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00100422,0.0001155728,0.0003566472,0.0003107926,0.0002711902,0.00004511785,0.0002445393,0.00005432757,0.02331135],"category_scores_gemma":[0.00006048522,0.00008644684,0.0003516767,0.001797281,0.0002955686,0.0001017323,0.00002815326,0.00004559956,0.0001082749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006276587,"about_ca_system_score_gemma":0.0001198529,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01474443,"about_ca_topic_score_gemma":0.05179675,"domain_scores_codex":[0.9982051,0.0002853196,0.0003680733,0.0002697352,0.0006200718,0.0002516936],"domain_scores_gemma":[0.9990588,0.0002000135,0.0001121993,0.0001687614,0.0003342576,0.0001260116],"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":[0.0007522622,0.001477797,0.1663357,0.00005545283,0.02406999,0.00006780273,0.05710647,0.0007765222,0.01049616,0.01947954,0.03697456,0.6824077],"study_design_scores_gemma":[0.004284956,0.001807649,0.3922742,0.0001450685,0.02861989,0.000005788621,0.04523959,0.08415449,0.06563094,0.03308611,0.3415081,0.003243224],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7823691,0.00005788203,0.1253863,0.00237599,0.0006020888,0.0002845156,0.00006503532,0.00008965179,0.08876941],"genre_scores_gemma":[0.936596,0.00002807635,0.03805843,0.0005557947,0.0002132437,0.000004706078,0.00001923986,0.000006012098,0.0245185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6791645,"threshold_uncertainty_score":0.9918165,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3215074405","doi":"10.1145/3492844","title":"The Computational Thematic Analysis Toolkit","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Computer science; Transparency (behavior); Thematic analysis; Data science; Variety (cybernetics); Interface (matter); Coding (social sciences); Computational model; Thematic map; Modular design; Computational sociology; Process (computing); Human–computer interaction; World Wide Web; Qualitative research; Artificial intelligence; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.07997970442216792,"gpt":0.4028001203780254,"spread":0.3228204159558574,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001647848,0.0001083877,0.0001956824,0.0002309381,0.002900333,0.0002159847,0.001629405,0.00002274153,0.0002706053],"category_scores_gemma":[0.0003552384,0.00007205446,0.0004009545,0.001275467,0.0001385637,0.0002028374,0.0006650299,0.0002756003,0.000008119102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000208388,"about_ca_system_score_gemma":0.00003550332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001755693,"about_ca_topic_score_gemma":0.00005039763,"domain_scores_codex":[0.9981291,0.0001494142,0.0003734918,0.0002366329,0.0009372852,0.000174025],"domain_scores_gemma":[0.9978759,0.001042273,0.0005070298,0.0002217914,0.0003171521,0.00003582297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001666922,0.0006901192,0.01126169,0.00004115318,0.002847062,7.824016e-7,0.03038829,0.1791376,0.0004501612,0.6607906,0.03104617,0.08317975],"study_design_scores_gemma":[0.0005919762,0.0003245728,0.0596584,0.00006424575,0.001176378,0.000009686335,0.01469754,0.1813595,0.0003678095,0.6821853,0.05903118,0.0005334652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9706594,0.00002678777,0.002556158,0.01157919,0.0009827405,0.0003613638,0.000005008842,0.00008155954,0.01374781],"genre_scores_gemma":[0.9945369,0.000002384054,0.003431254,0.000299421,0.0002742634,0.00004025976,0.000004775711,0.000007691439,0.00140303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08264628,"threshold_uncertainty_score":0.9983978,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4306178485","doi":"10.3233/jid-220013","title":"Natural language processing (NLP) aided qualitative method in health research","year":2022,"lang":"en","type":"article","venue":"Journal of Integrated Design and Process Science","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mount Royal University; Alberta Health Services; Concordia University; University of Calgary","funders":"","keywords":"Computer science; Natural language processing; Sentence; Cluster analysis; Artificial intelligence; Workload; Context (archaeology); Automatic summarization; Qualitative research; Information retrieval; Text mining; Data science; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.2305358605394815,"gpt":0.5988821724556453,"spread":0.3683463119161638,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.06778664,0.00007748484,0.0002444322,0.001015889,0.001620364,0.0002253929,0.0005472592,0.00002059118,0.00006593845],"category_scores_gemma":[0.003842853,0.00005835735,0.00003798657,0.005815874,0.0006215968,0.0006571188,0.00005781788,0.0008443847,4.501537e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004572506,"about_ca_system_score_gemma":0.00551518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001038099,"about_ca_topic_score_gemma":0.0001211412,"domain_scores_codex":[0.9913536,0.0058123,0.0004854101,0.0002203177,0.001751236,0.0003771363],"domain_scores_gemma":[0.9963799,0.001584369,0.000393959,0.00004792781,0.001420294,0.0001735949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002253344,0.0001333892,0.000198294,0.0000432143,0.00001177429,0.00003839637,0.6586795,0.006182144,0.002561882,0.004363092,0.0001700944,0.3273929],"study_design_scores_gemma":[0.0004493449,0.0004613136,0.0003707524,0.0001604419,0.000006536657,0.00005873448,0.8696294,0.08643594,0.0007456653,0.04033119,0.001183956,0.0001666815],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3380183,0.0199121,0.6248225,0.01409986,0.0004655462,0.0006756596,0.000005237407,0.00003999702,0.001960816],"genre_scores_gemma":[0.9113969,0.00004431833,0.08806462,0.0001997412,0.00003915363,0.000007593708,4.527754e-7,0.000003819974,0.0002433972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5733786,"threshold_uncertainty_score":0.9996794,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034470301","doi":"10.1016/j.forsciint.2020.110364","title":"Social media forensics applied to assessment of post–critical incident social reaction: The case of the 2017 Manchester Arena terrorist attack","year":2020,"lang":"en","type":"article","venue":"Forensic Science International","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université du Québec à Trois-Rivières","funders":"Economic and Social Research Council","keywords":"Latent Dirichlet allocation; Social media; Law enforcement; Terrorism; Computer science; Data science; Topic model; Set (abstract data type); Event (particle physics); Computational sociology; Perception; Digital forensics; Computer security; Internet privacy; World Wide Web; Artificial intelligence; Political science; Law; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.1042927051340976,"gpt":0.4482298001236109,"spread":0.3439370949895133,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001263302,0.00009813211,0.0001799094,0.00008099398,0.0008948811,0.0000924079,0.0008191608,0.0000466547,0.0001008099],"category_scores_gemma":[0.001490141,0.000065423,0.000168062,0.0007993705,0.002234282,0.0001903494,0.000316381,0.0001604848,0.000006355721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000172012,"about_ca_system_score_gemma":0.0004755954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002480266,"about_ca_topic_score_gemma":0.001673727,"domain_scores_codex":[0.9976832,0.0001225944,0.0003668635,0.0002710422,0.001345995,0.0002103071],"domain_scores_gemma":[0.998012,0.0006789398,0.0002387685,0.0001145903,0.0008559932,0.00009972517],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00007327194,0.0001108957,0.005333135,0.00001641284,0.0000965334,0.00002663713,0.09981826,0.0002780766,0.00294997,0.8316269,0.006631658,0.05303826],"study_design_scores_gemma":[0.0009838896,0.0001616218,0.8241169,0.00005888437,0.0002802479,0.00008250863,0.07057107,0.01126947,0.002980193,0.07641232,0.01238681,0.0006960595],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8947524,0.000004063885,0.003420217,0.08772933,0.001430443,0.0002309664,0.00004736887,0.00001532153,0.01236986],"genre_scores_gemma":[0.9954017,4.859766e-7,0.002741016,0.0008815258,0.0009230687,0.00001153008,0.000005418493,0.00000456852,0.0000306207],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8187838,"threshold_uncertainty_score":0.8232305,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4393100941","doi":"10.1007/978-3-031-54752-2","title":"AI-Generated Popular Culture","year":2024,"lang":"en","type":"book","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Popular culture; Computer science; Sociology; Media studies","retraction":null,"screen_n_in":null,"score":{"opus":0.04177498592570473,"gpt":0.3866558812883201,"spread":0.3448808953626153,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004385765,0.000145707,0.0002276712,0.0001153771,0.0002313218,0.0001921966,0.0002026128,0.0003044145,0.003010273],"category_scores_gemma":[0.00004228041,0.0001120222,0.000246656,0.0002626196,0.00008419432,0.0000485322,0.00004592682,0.0003019114,0.001251968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001164901,"about_ca_system_score_gemma":0.0007060075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000281279,"about_ca_topic_score_gemma":0.001859905,"domain_scores_codex":[0.9987682,0.0001407522,0.0001750146,0.0002837727,0.0004761505,0.0001560712],"domain_scores_gemma":[0.9995528,0.00003021234,0.00004506276,0.00009888869,0.0001799948,0.00009308453],"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":[4.458691e-7,0.000003612478,0.000001805295,0.000007949877,0.00007893519,0.00001092811,0.001223645,0.00001101613,0.000001452376,0.4566963,0.5365307,0.005433203],"study_design_scores_gemma":[0.00001453043,0.000004077593,9.33071e-7,0.00001956671,0.00009507131,2.948013e-7,0.00005952536,0.000113312,9.432882e-7,0.2262152,0.7733497,0.0001268898],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000002211598,0.00241293,0.001249649,0.002816669,0.0006579655,0.00009008621,0.00001158437,0.0001947313,0.9925642],"genre_scores_gemma":[0.00004076306,0.0001613216,0.002472322,0.001066923,0.001735481,0.00000405191,0.0002274316,0.00001675074,0.994275],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2368189,"threshold_uncertainty_score":0.9995257,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3194665160","doi":"10.18637/jss.v099.i02","title":"The <i>R</i> Package <b>sentometrics</b> to Compute, Aggregate, and Predict with Textual Sentiment","year":2021,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institut de Valorisation des Données; Innoviris; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"R package; Computer science; Aggregate (composite); Indexation; Sentiment analysis; Workflow; Index (typography); Volatility (finance); Series (stratigraphy); Information retrieval; Econometrics; Natural language processing; Mathematics; World Wide Web; Database; Programming language; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.01761164827682454,"gpt":0.3292169960357477,"spread":0.3116053477589231,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00110605,0.00008664134,0.0002196519,0.00009270222,0.0005012577,0.000252784,0.0001513039,0.00003243086,0.00009184972],"category_scores_gemma":[0.002493791,0.00005308473,0.00005484381,0.0008837108,0.0002144434,0.00009202225,0.00007322339,0.0001724496,0.000006386404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006563176,"about_ca_system_score_gemma":0.0002886017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004925055,"about_ca_topic_score_gemma":0.0001658341,"domain_scores_codex":[0.9981265,0.0002879419,0.0003286307,0.00013439,0.0008974347,0.0002251173],"domain_scores_gemma":[0.9950793,0.003612903,0.0001723116,0.00007689303,0.000702607,0.0003559786],"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":[0.00020928,0.0003088526,0.03624225,0.00003248741,0.0004950528,0.001027982,0.003020219,0.0005181176,0.00003436216,0.08286735,0.02618069,0.8490633],"study_design_scores_gemma":[0.002781057,0.001506102,0.3451328,0.0003764574,0.0007443082,0.0004890179,0.01012514,0.0009894442,0.0002326279,0.0720166,0.5648035,0.0008029312],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01996706,0.0006574104,0.9753965,0.003137889,0.0001664431,0.00007648762,0.00003595183,0.00001449757,0.0005477208],"genre_scores_gemma":[0.4031909,0.0004291772,0.5935204,0.0007842412,0.0006025687,0.000003207941,0.000009824729,0.00001753731,0.001442174],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8482604,"threshold_uncertainty_score":0.385532,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4224311899","doi":"10.1111/cars.12378","title":"A new method for computational cultural cartography: From neural word embeddings to transformers and Bayesian mixture models","year":2022,"lang":"en","type":"article","venue":"Canadian Review of Sociology/Revue canadienne de sociologie","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Latent semantic analysis; Word (group theory); Natural language processing; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.05651616741544198,"gpt":0.3614541987538037,"spread":0.3049380313383618,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002404261,0.0002221254,0.0006953763,0.0002240812,0.001058924,0.00001849287,0.000446107,0.00017681,0.0003336293],"category_scores_gemma":[0.0005655517,0.0002347345,0.0004220416,0.0004757235,0.0003834465,0.0001048581,0.00004054785,0.0003600774,7.10632e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001033128,"about_ca_system_score_gemma":0.001900109,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1992704,"about_ca_topic_score_gemma":0.3725011,"domain_scores_codex":[0.9970363,0.001031264,0.0004471903,0.0005005028,0.0001120177,0.000872718],"domain_scores_gemma":[0.9970164,0.001292956,0.0001848028,0.0001228032,0.000246586,0.001136436],"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":[0.00008448603,0.00003714802,0.01265378,0.001111005,0.001140264,0.00004959306,0.2594139,0.03634843,0.00009915502,0.2360244,0.06589232,0.3871456],"study_design_scores_gemma":[0.0009396999,0.0003497073,0.01499225,0.0004656831,0.000767373,0.00002331522,0.09646279,0.02707679,0.000001505673,0.7292238,0.1285169,0.001180117],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4385815,0.06874357,0.3233156,0.1579032,0.001352761,0.004028159,0.00411053,0.0001517042,0.001813066],"genre_scores_gemma":[0.7907278,0.001514908,0.1890123,0.01695406,0.000415681,0.0003603096,0.0007250723,0.00003378937,0.0002560983],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4931995,"threshold_uncertainty_score":0.9572197,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3121876164","doi":"10.1007/s11606-020-06579-3","title":"The Gender of COVID-19 Experts in Newspaper Articles: a Descriptive Cross-Sectional Study","year":2021,"lang":"en","type":"article","venue":"Journal of General Internal Medicine","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; University of Calgary; University of British Columbia","funders":"Cumming School of Medicine, University of Calgary","keywords":"Newspaper; Medicine; Pandemic; Cross-sectional study; Confidence interval; Coronavirus disease 2019 (COVID-19); Family medicine; Media studies; Sociology; Pathology; Disease; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1685033957827846,"gpt":0.4774958725633728,"spread":0.3089924767805882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003568822,0.0000824236,0.0002731947,0.0001541616,0.0002037609,0.00005128644,0.0002673465,0.00003758876,0.0005862672],"category_scores_gemma":[0.003154045,0.00004949735,0.0001416504,0.000448761,0.0003487384,0.0001355128,0.00004980223,0.0001951029,0.000001138904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002480914,"about_ca_system_score_gemma":0.0005599462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004527837,"about_ca_topic_score_gemma":0.005194733,"domain_scores_codex":[0.9970495,0.000890366,0.0008337634,0.0001244744,0.000938728,0.000163229],"domain_scores_gemma":[0.9977173,0.0008481207,0.0004052084,0.0000840529,0.0007420596,0.0002032904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003334941,0.0003543167,0.9263462,0.000005892295,0.0002996318,0.0003267351,0.05640892,0.001552649,0.003577436,0.003512706,0.002730745,0.004551309],"study_design_scores_gemma":[0.002645213,0.0005074268,0.8696663,0.00005088245,0.00007189186,0.0001583968,0.08427249,0.0006291827,0.00032027,0.0218574,0.01969861,0.0001218942],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9854115,0.001486963,0.005787532,0.003829,0.0009725495,0.00006776635,6.67744e-7,0.000003078355,0.00244094],"genre_scores_gemma":[0.9935048,0.000143375,0.0008614921,0.0006372352,0.001202317,0.000002317088,3.630094e-7,0.000004633219,0.003643441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05667982,"threshold_uncertainty_score":0.6844764,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2991039843","doi":"10.1075/ahs.10","title":"Keeping in Touch","year":2019,"lang":"en","type":"book","venue":"Advances in historical sociolinguistics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.03113628056745455,"gpt":0.3771019742061559,"spread":0.3459656936387014,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008896841,0.0002239157,0.0006672237,0.0002903095,0.0001663892,0.00002180861,0.0004109842,0.0004542781,0.0001224669],"category_scores_gemma":[0.003726312,0.0002574023,0.0001885169,0.0003463476,0.0001502425,0.00006939386,0.00007140057,0.000780666,0.00007615265],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0101425,"about_ca_system_score_gemma":0.0009223855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007890483,"about_ca_topic_score_gemma":0.002847776,"domain_scores_codex":[0.997595,0.0002678527,0.000627855,0.0004539703,0.0006386261,0.0004166934],"domain_scores_gemma":[0.9970666,0.002170634,0.0002890503,0.0001831248,0.0001951151,0.00009544867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002507894,0.0001476282,0.004994207,0.0002030712,0.00002942593,0.0001958585,0.01080846,0.004444357,2.214994e-7,0.9168327,0.009111498,0.05320753],"study_design_scores_gemma":[0.000105136,0.00001046043,0.00004479074,0.00009418049,0.00001633521,1.489032e-7,0.00005878459,0.0001991538,3.141164e-8,0.2626831,0.7365559,0.0002319711],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00001567276,0.01710461,0.003069079,0.0001605154,0.003964501,0.0002068176,0.000005522415,0.00004602947,0.9754273],"genre_scores_gemma":[0.005823168,0.00715763,0.01188619,0.0002407627,0.004502016,0.00002203824,0.00005482194,0.0000528227,0.9702606],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.7274445,"threshold_uncertainty_score":0.9999878,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2889291357","doi":"10.1017/pan.2018.30","title":"Ideological Scaling of Social Media Users: A Dynamic Lexicon Approach","year":2018,"lang":"en","type":"article","venue":"Political Analysis","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Université Laval","funders":"University of Cambridge; Ministère de l'Économie, de la Science et de l'Innovation - Québec; Compute Canada; Université Laval","keywords":"Ideology; Social media; Voting behavior; Lexicon; Politics; Voting; Dimension (graph theory); Rhetoric; Sociology; Computer science; Political science; Linguistics; Artificial intelligence; Law; Mathematics; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.06638905123520183,"gpt":0.4087408830263073,"spread":0.3423518317911055,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001149528,0.0001059543,0.0004617273,0.0003309243,0.0003848767,0.00004178699,0.0002644502,0.0001301535,0.001135943],"category_scores_gemma":[0.001126849,0.00008877956,0.0005451319,0.002124665,0.001413932,0.00007692658,0.00006996466,0.0001074297,0.00003296647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008797409,"about_ca_system_score_gemma":0.0001048655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001414722,"about_ca_topic_score_gemma":0.001693639,"domain_scores_codex":[0.9976777,0.0005903096,0.0003748458,0.0002921371,0.0005937112,0.0004713406],"domain_scores_gemma":[0.9983584,0.0009015237,0.00009962659,0.0001136149,0.0003066309,0.0002201621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001159608,0.0001274781,0.007862151,0.000004990037,0.0006239943,9.762823e-7,0.003689764,0.00003345395,0.00003012587,0.9841724,0.00001915251,0.003423897],"study_design_scores_gemma":[0.0004478823,0.00006137211,0.2610231,0.00000773271,0.005743788,0.000001015533,0.01508927,0.1440292,0.0001455116,0.5710807,0.001763217,0.0006071302],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6774475,0.00005148462,0.2320105,0.003977599,0.0001080691,0.00008975571,0.00002496405,0.0001069264,0.08618324],"genre_scores_gemma":[0.9852787,0.000001364663,0.01385047,0.0001557879,0.0004638983,0.00000407428,0.00002744112,0.00000464574,0.0002136165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4130917,"threshold_uncertainty_score":0.9997771,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3111126926","doi":"10.1007/s11229-020-02915-6","title":"Eight journals over eight decades: a computational topic-modeling approach to contemporary philosophy of science","year":2020,"lang":"en","type":"article","venue":"Synthese","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":20,"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","funders":"Canada Research Chairs; Canada Foundation for Innovation","keywords":"Philosophy of science; Philosophy of language; Philosophy of computer science; Epistemology; History and philosophy of science; Empiricism; Philosophy of biology; Field (mathematics); Object (grammar); Western philosophy; Metaphysics; Social science; Sociology; Philosophy; Mathematics; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.1796726069853583,"gpt":0.4014957260038886,"spread":0.2218231190185303,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001516164,0.0001022353,0.0002574527,0.0002314282,0.0004215657,0.00009118524,0.0004932457,0.00004513321,0.0001693348],"category_scores_gemma":[0.001009169,0.00008945991,0.000132119,0.001464765,0.0004441871,0.000331673,0.0000990367,0.0001154055,0.00001899792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005049388,"about_ca_system_score_gemma":0.0005379089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001980831,"about_ca_topic_score_gemma":0.000003904394,"domain_scores_codex":[0.9978458,0.0002324087,0.0003673217,0.0003177121,0.001027406,0.0002094084],"domain_scores_gemma":[0.9987287,0.0003672732,0.0001294527,0.00009860459,0.000353208,0.0003227542],"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":[0.0001855316,0.0006243662,0.009603049,0.0001293041,0.0002810103,0.00001560116,0.09922926,0.2772897,0.002710863,0.5792299,0.001494396,0.02920703],"study_design_scores_gemma":[0.0005983724,0.0001024743,0.003589226,0.0001891547,0.00006829432,0.000003102896,0.006936365,0.764739,0.0005867271,0.2101787,0.01235681,0.0006518288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2295472,0.000816112,0.5639122,0.01652698,0.0002334584,0.0004633118,0.0000308022,0.00006787362,0.1884021],"genre_scores_gemma":[0.9570311,0.000006266332,0.04166081,0.0008478362,0.0003789612,0.000006120716,0.000002941711,0.000006562337,0.00005938022],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7274839,"threshold_uncertainty_score":0.3648069,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":["bibliometrics","sts"],"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":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3165231223","doi":"10.1037/amp0000903","title":"Expert predictions of societal change: Insights from the world after COVID project.","year":2021,"lang":"en","type":"article","venue":"American Psychologist","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Ontario Ministry of Research and Innovation; Social Sciences and Humanities Research Council of Canada; Templeton World Charity Foundation","keywords":"PsycINFO; Pandemic; Coronavirus disease 2019 (COVID-19); Psychology; Value (mathematics); Politics; Scientific consensus; Set (abstract data type); Social psychology; Public relations; Sociology; Political science; MEDLINE; Law; Medicine; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1072679459642904,"gpt":0.4593135807908237,"spread":0.3520456348265334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001892373,0.00007555533,0.00016491,0.0000409983,0.0002714552,0.00003598385,0.0002046193,0.0000250913,0.0004693757],"category_scores_gemma":[0.0001593487,0.00005352275,0.0001507377,0.001312391,0.001434505,0.00007094163,0.00004581622,0.0001057295,0.00001257165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003745817,"about_ca_system_score_gemma":0.0001437269,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01502655,"about_ca_topic_score_gemma":0.01987435,"domain_scores_codex":[0.9985972,0.0005642213,0.0001694529,0.0002492884,0.000279839,0.000139996],"domain_scores_gemma":[0.9989141,0.0005693447,0.0001321254,0.0002185817,0.0001138449,0.00005195707],"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":[0.0002172457,0.001543506,0.1380833,0.000007817526,0.001021829,0.0001104547,0.2152639,0.00004382344,0.0008434431,0.02770985,0.1790975,0.4360573],"study_design_scores_gemma":[0.0002173193,0.00005316085,0.2980708,0.00001560288,0.00006120303,0.000001115806,0.03255815,0.00009659046,0.0000404521,0.005203196,0.6635001,0.0001823881],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.66421,0.009377549,0.03091113,0.1203657,0.002763818,0.001015096,0.0002778056,0.0003800124,0.1706989],"genre_scores_gemma":[0.9866201,0.0002127312,0.005300362,0.005454336,0.0006654638,0.0001035827,0.00002388126,0.000005792666,0.001613743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4844025,"threshold_uncertainty_score":0.9980104,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}