{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":552,"total_is_capped":false,"direct_labels_cover":2,"predictions_cover":552,"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":"b13bc4f485d2","filters":{"topic":"Advanced Text Analysis Techniques"}},"results":[{"id":"W2561541699","doi":"10.1111/isj.12131","title":"Minimum sample size estimation in PLS‐SEM: The inverse square root and gamma‐exponential methods","year":2016,"lang":"en","type":"article","venue":"Information Systems Journal","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2185,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Square root; Mathematics; Inverse; Statistics; Sample size determination; Multivariate statistics; Monte Carlo method; Exponential function; Applied mathematics; Mean squared error; Mathematical optimization; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.01700328630793958,"gpt":0.3136178639966472,"spread":0.2966145776887076,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002168184,0.0001298243,0.0001962848,0.0002990386,0.0001987247,0.0005335019,0.0004800769,0.00007368105,0.000009210449],"category_scores_gemma":[0.0009620477,0.00007424982,0.00006181205,0.0003711214,0.00004768301,0.005522749,0.0001286664,0.0001681694,0.00002403553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001509296,"about_ca_system_score_gemma":0.00006379608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005050493,"about_ca_topic_score_gemma":0.00002297803,"domain_scores_codex":[0.9981467,0.0003458088,0.0008046859,0.0001077897,0.00038224,0.0002127488],"domain_scores_gemma":[0.9978858,0.0008788225,0.0006179528,0.0003205032,0.00020979,0.00008709372],"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":[0.00006603969,0.00005221154,0.01067927,0.0001282269,0.0001228121,0.00001377293,0.01588891,0.009870796,0.003192819,0.02772638,0.006601599,0.9256572],"study_design_scores_gemma":[0.002673162,0.0001987228,0.01854604,0.0006870316,0.00004084875,0.001188558,0.001258869,0.8788605,0.002567165,0.03249478,0.06077348,0.0007108104],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01774475,0.00005485686,0.9806929,0.0007228454,0.0003027145,0.0002045123,0.000002922887,0.00008499324,0.000189461],"genre_scores_gemma":[0.7817312,0.00003122324,0.2180006,0.0001003236,0.00006696827,0.00002688513,0.000001055586,0.000004910951,0.00003675043],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9249464,"threshold_uncertainty_score":0.514457,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2895553377","doi":"10.21105/joss.00774","title":"quanteda: An R package for the quantitative analysis of textual data","year":2018,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1323,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"De Beers (Canada)","funders":"London School of Economics and Political Science","keywords":"R package; Computer science; Natural language processing; Information retrieval; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.1220943930715411,"gpt":0.4211929597768534,"spread":0.2990985667053123,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.004167535,0.0001558396,0.00054127,0.0002683861,0.000391836,0.0002402852,0.01254417,0.00004375356,0.00003024529],"category_scores_gemma":[0.001105249,0.00007963314,0.0002094026,0.001693816,0.0003750261,0.001851049,0.001945869,0.0002174175,0.000003480573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002991083,"about_ca_system_score_gemma":0.0001214414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001627808,"about_ca_topic_score_gemma":0.0004185615,"domain_scores_codex":[0.9980505,0.0003504214,0.0006517118,0.0002475818,0.0004786876,0.0002211177],"domain_scores_gemma":[0.9930553,0.002177055,0.001266117,0.002479251,0.0009476524,0.00007461584],"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":[0.002890169,0.001775626,0.01532343,0.00007572374,0.03198026,0.00003398627,0.09723904,0.013109,0.01162362,0.07515208,0.05927325,0.6915238],"study_design_scores_gemma":[0.002760484,0.008019617,0.02275652,0.0003343966,0.01696845,0.0001923147,0.03210618,0.8089886,0.01792297,0.03450182,0.0539887,0.001459998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01186885,0.0003177095,0.9867201,0.0006576189,0.00004444946,0.0002658181,0.00005657759,0.0000347991,0.00003406258],"genre_scores_gemma":[0.6446717,0.00005855404,0.354731,0.0003031508,0.00009062464,0.00000362435,0.0000123908,0.00001755909,0.0001113095],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7958795,"threshold_uncertainty_score":0.9927984,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1494478641","doi":"10.1007/978-0-387-69810-6","title":"The Statistical Analysis of Recurrent Events","year":2007,"lang":"en","type":"book","venue":"Statistics for biology and health","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":738,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.04241724093842392,"gpt":0.4368227611509031,"spread":0.3944055202124792,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001266276,0.0001835364,0.0006893912,0.0003163643,0.0002623255,0.00001211584,0.0004561247,0.0001784925,0.000004388939],"category_scores_gemma":[0.0001191283,0.0001323971,0.00009483824,0.0002120888,0.0002967982,0.00002046089,0.0001402388,0.0002322869,0.000001012012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001200338,"about_ca_system_score_gemma":0.0004358872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002951105,"about_ca_topic_score_gemma":0.0007366113,"domain_scores_codex":[0.9983696,0.00008388935,0.0006582354,0.0004072265,0.000129778,0.000351247],"domain_scores_gemma":[0.9969296,0.001677961,0.0006494544,0.0004372803,0.0001962935,0.0001094336],"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":[0.00000978739,0.00001192442,0.00010522,0.0000478925,0.0003889765,4.065811e-7,0.00003198848,9.523905e-7,1.502846e-7,0.8069956,0.01069866,0.1817084],"study_design_scores_gemma":[0.0001043877,0.0006148924,0.001643809,0.0000227298,0.0003426138,5.924763e-7,0.000002506909,0.006178811,0.000001422086,0.8959312,0.09500562,0.0001513568],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[5.778415e-7,0.001839002,0.9936213,0.0002408233,0.0001431239,0.0003229695,0.002816711,0.0000308449,0.0009846049],"genre_scores_gemma":[0.0002964574,0.00615879,0.9733283,0.0003703051,0.00006555268,0.00003811824,0.002545356,0.00001841743,0.01717873],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1815571,"threshold_uncertainty_score":0.5398996,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2072435181","doi":"10.1207/s1532690xci2402_3","title":"Helping Students Understand Challenging Topics in Science Through Ontology Training","year":2006,"lang":"en","type":"article","venue":"Cognition and Instruction","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":285,"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":"Spencer Foundation; Andrew W. Mellon Foundation","keywords":"Ontology; Conceptual change; Science education; Task (project management); Mathematics education; Computer science; Concept learning; Psychology; Epistemology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.04250187749906544,"gpt":0.3179108858070179,"spread":0.2754090083079525,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001752595,0.00006933545,0.00009721542,0.000219062,0.000196348,0.0001071767,0.0001684402,0.00003871259,0.000002058132],"category_scores_gemma":[0.00001896095,0.00007494411,0.0000149779,0.0004786354,0.0001390677,0.001213692,0.00007660504,0.00008737662,8.795813e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008566287,"about_ca_system_score_gemma":0.0000214854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002788172,"about_ca_topic_score_gemma":0.00008739248,"domain_scores_codex":[0.9991961,0.00001967716,0.0001621678,0.0002709548,0.000185504,0.0001655704],"domain_scores_gemma":[0.999751,0.0000115862,0.00006200401,0.0001024592,0.00005331017,0.00001963496],"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":[0.000008116258,0.00007723346,0.00524651,0.00002470962,0.000009151458,0.00001412874,0.004390986,0.0001264196,0.008563037,0.5915635,0.000008676211,0.3899675],"study_design_scores_gemma":[0.002089723,0.0001382543,0.06929427,0.0002129532,0.0000193074,0.0001829715,0.004709634,0.02971581,0.02308815,0.8691937,0.0008030568,0.0005521354],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4038395,0.00006399833,0.5915224,0.0001998631,0.0001090458,0.00006596902,1.516114e-7,0.0001041509,0.004094966],"genre_scores_gemma":[0.972892,0.00007372345,0.02687557,0.0000909938,0.00004454733,0.000004954133,0.00000159823,0.000002666967,0.00001396671],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5690525,"threshold_uncertainty_score":0.3056132,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1544240449","doi":"10.1007/3-540-45486-1_4","title":"Using Noun Phrase Heads to Extract Document Keyphrases","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":236,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Noun phrase; Automatic summarization; Natural language processing; Artificial intelligence; Phrase; Task (project management); Extractor; Head (geology); Noun; Proper noun; Information retrieval; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02587671481000824,"gpt":0.3118338681191701,"spread":0.2859571533091619,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008015468,0.0008493769,0.0008659037,0.001818369,0.0003690381,0.0008799173,0.004735611,0.00032709,0.0001159118],"category_scores_gemma":[0.00007938177,0.0008105002,0.000266506,0.001410989,0.0004896864,0.001350065,0.001606442,0.0008389102,0.0001261041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009142265,"about_ca_system_score_gemma":0.0005884468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007533775,"about_ca_topic_score_gemma":0.0001077748,"domain_scores_codex":[0.9940944,0.00004985449,0.0008304117,0.002428661,0.00154484,0.001051825],"domain_scores_gemma":[0.9961856,0.0003098284,0.0003374068,0.002523535,0.0002373004,0.0004063031],"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":[0.000008562523,0.00004396748,0.00001893735,0.00001500982,0.00001633165,0.0002275119,0.000368284,0.07397829,0.0008479581,0.009247679,0.00002827972,0.9151992],"study_design_scores_gemma":[0.000356848,0.0004476858,0.0000412519,0.001134824,0.00004616012,0.0002626024,2.445738e-7,0.4026644,0.01628928,0.5576288,0.01854985,0.002578116],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002024125,0.0005558684,0.9941915,0.0005267109,0.0005555977,0.000586416,0.000005567061,0.0004827605,0.002893188],"genre_scores_gemma":[0.07828948,0.000106027,0.9180698,0.002771928,0.0004111596,0.00001623614,0.000004402255,0.00005756747,0.0002733528],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9126211,"threshold_uncertainty_score":0.9994346,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148404145","doi":"10.3115/v1/d14-1168","title":"Abstractive Summarization of Product Reviews Using Discourse Structure","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":200,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Automatic summarization; Computer science; Natural language processing; Product (mathematics); Linguistics; Artificial intelligence; Mathematics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.01939090081418264,"gpt":0.326621961672267,"spread":0.3072310608580843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000206115,0.00008584302,0.0001923725,0.0000784545,0.00003515889,0.00002292516,0.0003560932,0.00002334645,0.0000147863],"category_scores_gemma":[0.0001160165,0.00006362198,0.00004765931,0.0003364688,0.00003602854,0.0006262644,0.00008728488,0.00006171958,0.000002099888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002137373,"about_ca_system_score_gemma":0.00001583635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002424975,"about_ca_topic_score_gemma":0.00001821899,"domain_scores_codex":[0.999231,0.00006039278,0.0002304677,0.000245811,0.0001354856,0.00009682238],"domain_scores_gemma":[0.9990905,0.00002273099,0.0002358737,0.0005343946,0.00009222569,0.000024297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003254374,0.00007364931,0.002190842,0.00006536068,0.00002829654,6.128021e-7,0.0003882456,0.00193746,0.3085596,0.1716157,0.0004678043,0.5146692],"study_design_scores_gemma":[0.000146615,0.00006660767,0.003485296,0.0000977317,0.00005129654,0.000006907339,0.00002211302,0.1606044,0.7611035,0.06768873,0.006308234,0.0004186393],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009509153,0.00007545534,0.988964,0.00009284387,0.00003815789,0.0001544137,5.577827e-7,0.00007890109,0.001086548],"genre_scores_gemma":[0.6051015,0.00001373821,0.3947635,0.00003058021,0.00002740049,0.000001249332,0.000001810495,0.000003221597,0.00005703692],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5955923,"threshold_uncertainty_score":0.2594429,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2946989286","doi":"10.1007/s41237-019-00085-5","title":"A concept analysis of methodological research on composite-based structural equation modeling: bridging PLSPM and GSCA","year":2019,"lang":"en","type":"article","venue":"Behaviormetrika","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":191,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Structural equation modeling; Path analysis (statistics); Computer science; Bridging (networking); Econometrics; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.3321505942566969,"gpt":0.4802027912565942,"spread":0.1480521969998973,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001716572,0.0001615272,0.000540507,0.002237994,0.000117027,0.00009744045,0.0006518269,0.0001170261,0.00003604261],"category_scores_gemma":[0.000203933,0.0001392997,0.0001924156,0.004772638,0.0001074118,0.0003024728,0.0002404786,0.0003180062,0.000003928169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001147798,"about_ca_system_score_gemma":0.0000436725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001603069,"about_ca_topic_score_gemma":0.000006728459,"domain_scores_codex":[0.9972486,0.0005341731,0.0004192276,0.0006199189,0.0008548273,0.0003232122],"domain_scores_gemma":[0.9976761,0.000990823,0.0001707664,0.0007449172,0.0003254537,0.00009192798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001830683,0.0003677298,0.2266694,0.00003947076,0.0004793942,0.00002284345,0.001164561,0.39331,0.1137843,0.04322961,0.00002502095,0.2207247],"study_design_scores_gemma":[0.0002651075,0.0002682285,0.0273346,0.00001605203,0.000168206,8.345312e-7,0.00003321066,0.9408641,0.03008584,0.0008035165,0.000003200863,0.0001571074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5124916,0.0000504346,0.4871296,0.00004049622,0.00001672821,0.0001463251,0.000003634067,0.00007128318,0.00004980051],"genre_scores_gemma":[0.823235,0.000003837834,0.1766585,0.00003568517,0.000008477283,0.00001129833,0.00002085933,0.000007112222,0.00001928248],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5475541,"threshold_uncertainty_score":0.5680476,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2230887875","doi":"10.1080/10888438.2015.1107073","title":"The Random Forests statistical technique: An examination of its value for the study of reading","year":2016,"lang":"en","type":"article","venue":"Scientific Studies of Reading","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":168,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Reading (process); Computer science; Random forest; Statistical analysis; Value (mathematics); Statistics; Artificial intelligence; Machine learning; Mathematics; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04712200114569937,"gpt":0.3674317793021761,"spread":0.3203097781564768,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005625145,0.0001339015,0.0003712152,0.0002112855,0.0006265735,0.00005650282,0.001191704,0.00002972005,6.90354e-7],"category_scores_gemma":[0.00262273,0.00006351219,0.00008044647,0.0007180067,0.0006618169,0.0004280414,0.000381981,0.0000518974,3.873511e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000600706,"about_ca_system_score_gemma":0.00003195294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007264964,"about_ca_topic_score_gemma":0.00006586709,"domain_scores_codex":[0.9978935,0.0002175406,0.0006036109,0.0004337087,0.0005984955,0.000253124],"domain_scores_gemma":[0.9928188,0.004800117,0.0005465073,0.0008948438,0.0009089899,0.00003072895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001126794,0.000408231,0.001530901,0.0001609145,0.0005057239,0.000001793495,0.0119029,0.0001360155,0.1937785,0.2099987,0.0008667946,0.5805969],"study_design_scores_gemma":[0.002750124,0.001959498,0.01200564,0.0007698658,0.0003801917,0.00000509582,0.01156336,0.02331621,0.8872185,0.05854448,0.0009987445,0.000488312],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06508529,0.0003818865,0.9326547,0.00009692932,0.0002664528,0.001365132,0.00001166216,0.00006101234,0.00007693116],"genre_scores_gemma":[0.9708036,0.00007808747,0.02864284,0.000001736779,0.00001642231,0.0002262699,6.675174e-7,0.000008559219,0.0002218847],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9057183,"threshold_uncertainty_score":0.481916,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1970043789","doi":"10.1145/1645953.1646076","title":"Detecting topic evolution in scientific literature","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":165,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Science Foundation","keywords":"Latent Dirichlet allocation; Computer science; Topic model; Data science; Citation; Inheritance (genetic algorithm); Scientific literature; Information retrieval; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.006675345525235707,"gpt":0.262146813315761,"spread":0.2554714677905253,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002368335,0.00006376281,0.00007547873,0.0003010411,0.00008206994,0.0002677713,0.0004112652,0.00004021115,0.000003860107],"category_scores_gemma":[0.00004548704,0.00005574146,0.00003481483,0.001557235,0.0000135609,0.0008026955,0.00005519394,0.0001133071,0.000009899591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008328947,"about_ca_system_score_gemma":0.00001579977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004640381,"about_ca_topic_score_gemma":0.00003847483,"domain_scores_codex":[0.9992388,0.00002404926,0.0001308867,0.0002953446,0.0001419681,0.0001688751],"domain_scores_gemma":[0.9994776,0.00001512343,0.00003226987,0.0003941212,0.00005432241,0.00002652169],"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":[0.000001660967,0.00007905807,0.003108842,0.000004995446,0.000002612986,0.00003044942,0.0009665766,0.0001716749,0.05595215,0.4716208,0.0002304384,0.4678307],"study_design_scores_gemma":[0.0002747195,0.0001257587,0.07230069,0.000120887,0.000003420995,0.00002419438,0.00003660046,0.1264195,0.07166678,0.7265724,0.002002954,0.0004520738],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04784755,0.000207644,0.9479027,0.0004176419,0.00006832802,0.00005906055,4.775541e-8,0.0003461228,0.00315088],"genre_scores_gemma":[0.8388192,0.00000131365,0.1603789,0.00009707922,0.00001551372,0.000001889024,4.390623e-7,0.000001148629,0.0006844748],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7909717,"threshold_uncertainty_score":0.2582124,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1486865875","doi":"10.48550/arxiv.cs/0308033","title":"Coherent Keyphrase Extraction via Web Mining","year":2003,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Extraction (chemistry); Web mining; World Wide Web; Web page","retraction":null,"screen_n_in":null,"score":{"opus":0.04399676745781409,"gpt":0.3191097352841954,"spread":0.2751129678263813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003965453,0.000448274,0.0004989083,0.0002955291,0.0001528121,0.0001485629,0.001396822,0.000357486,0.00008856856],"category_scores_gemma":[0.00009715125,0.0004654715,0.0002889007,0.0004249987,0.00005958653,0.0005081909,0.001109714,0.0008305334,0.0002202134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002740706,"about_ca_system_score_gemma":0.000159085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003540766,"about_ca_topic_score_gemma":0.00004516877,"domain_scores_codex":[0.9972146,0.0001626913,0.0005707777,0.001172021,0.0004338588,0.0004460345],"domain_scores_gemma":[0.9970845,0.0001030539,0.0005688661,0.001905648,0.0001795716,0.000158337],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000467456,0.001694163,0.5481009,0.0005904728,0.00112753,0.0008819703,0.00238842,0.004415721,0.1470184,0.007560967,0.01857356,0.2676011],"study_design_scores_gemma":[0.002603175,0.00067088,0.1954626,0.002001885,0.001023123,0.000372711,0.0003206511,0.234498,0.330547,0.09351613,0.1285353,0.01044865],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3406997,0.0003095153,0.6552979,0.0002051333,0.0006513252,0.0002586925,0.000002054571,0.0007689939,0.001806656],"genre_scores_gemma":[0.8700726,0.0001617552,0.1281973,0.0003090204,0.0001505136,0.0001316456,0.00001988276,0.00003851875,0.0009187944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5293729,"threshold_uncertainty_score":0.9997797,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163284121","doi":"10.1080/07421222.2000.11045646","title":"The Use of Explanations in Knowledge-Based Systems: Cognitive Perspectives and a Process-Tracing Analysis","year":2000,"lang":"en","type":"article","venue":"Journal of Management Information Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":144,"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","keywords":"Protocol analysis; Cognition; Comprehension; Process tracing; Process (computing); Knowledge management; Cognitive psychology; Computer science; Exploratory analysis; Tracing; Psychology; Qualitative analysis; Data science; Qualitative research; Cognitive science","retraction":null,"screen_n_in":null,"score":{"opus":0.02140219480498735,"gpt":0.289623304492584,"spread":0.2682211096875967,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009924205,0.00009335287,0.0002676555,0.001202803,0.0001054214,0.0004114279,0.0003026405,0.00002757149,0.000001648038],"category_scores_gemma":[0.00006087607,0.00006635769,0.00008614118,0.001584033,0.00003762794,0.003420568,0.00002755193,0.00009403218,0.000002396022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009027639,"about_ca_system_score_gemma":0.00003114821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002095382,"about_ca_topic_score_gemma":0.00001130883,"domain_scores_codex":[0.9983367,0.000135255,0.0009397232,0.00007888584,0.0003980218,0.0001114603],"domain_scores_gemma":[0.9979829,0.0002697918,0.0008978171,0.000177907,0.0006363121,0.00003531855],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001329933,0.0002854295,0.007626833,0.0009166214,0.002624576,0.00001658198,0.03499127,0.8032353,0.000005666233,0.04645509,0.0003626401,0.103347],"study_design_scores_gemma":[0.0008654243,0.0001149285,0.008270774,0.0008206132,0.0004080061,0.00001750652,0.03412315,0.9497358,0.00005419584,0.0001182925,0.00526869,0.0002026026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03200971,0.0007947917,0.9646885,0.00008066866,0.00004534854,0.0003825813,0.000003342393,0.00002866456,0.001966401],"genre_scores_gemma":[0.9975293,0.000264215,0.002071362,0.00001187854,0.0000104361,0.00002645045,0.000001839329,0.000002276679,0.00008226526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9655195,"threshold_uncertainty_score":0.3967409,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3125334212","doi":"10.17705/1jais.00237","title":"A Theory-Driven Design Framework for Social Recommender Systems","year":2010,"lang":"en","type":"article","venue":"Journal of the Association for Information Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; City University of New York","keywords":"Recommender system; Computer science; Competence (human resources); Similarity (geometry); Designtheory; Design science; Artificial intelligence; Information retrieval; Knowledge management; Human–computer interaction; Psychology; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.02622215138912869,"gpt":0.3018622921912353,"spread":0.2756401408021066,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005134041,0.0001207022,0.0003205136,0.0002106754,0.0004017367,0.0006248638,0.001030206,0.0002368114,6.557469e-7],"category_scores_gemma":[0.001942069,0.00008434384,0.0003467242,0.0003430661,0.00001227874,0.002450791,0.00006165054,0.0003300897,0.000005477131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003901857,"about_ca_system_score_gemma":0.0001177889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001837401,"about_ca_topic_score_gemma":5.597698e-7,"domain_scores_codex":[0.9978777,0.0002346473,0.001023315,0.0000743139,0.0005775643,0.0002124949],"domain_scores_gemma":[0.9925618,0.001356831,0.004141179,0.0002617499,0.001631636,0.00004676392],"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":[0.00003098027,0.00002208545,0.0002518112,0.00004931197,0.0002135562,3.397823e-8,0.002300001,0.00440332,0.0001885555,0.9679269,0.02227327,0.00234023],"study_design_scores_gemma":[0.002212572,0.000305587,0.0007432893,0.00022749,0.000251802,0.00004993411,0.001749121,0.2362011,0.001769832,0.2248732,0.5310254,0.0005907014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000163006,0.00001685601,0.9941766,0.00113664,0.003243557,0.0008554814,0.00001637985,0.00006545175,0.000325982],"genre_scores_gemma":[0.8218882,0.000005290149,0.1762631,0.000318496,0.0008711318,0.0001848867,0.0000045321,0.00001465718,0.000449692],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8217252,"threshold_uncertainty_score":0.6025575,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2336430626","doi":"10.1037/apl0000108","title":"Initial investigation into computer scoring of candidate essays for personnel selection.","year":2016,"lang":"en","type":"article","venue":"Journal of Applied Psychology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":134,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Campion College","funders":"","keywords":"PsycINFO; Dilemma; Notice; Leverage (statistics); Computer science; Data science; Psychology; Predictive validity; Context (archaeology); Scale (ratio); Selection (genetic algorithm); Personnel selection; Disadvantage; Applied psychology; Social psychology; Artificial intelligence; MEDLINE; Management; Clinical psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.02172397624619364,"gpt":0.3300711010410206,"spread":0.308347124794827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004644094,0.0001027801,0.000279673,0.0003402005,0.00006187381,0.00001625562,0.0004934114,0.00008205151,0.000007431508],"category_scores_gemma":[0.00002055986,0.00007413855,0.00009903928,0.0002812818,0.00009506955,0.0003124183,0.00005107207,0.0001132254,0.000002384227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000553004,"about_ca_system_score_gemma":0.00005536285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002897082,"about_ca_topic_score_gemma":0.000005700098,"domain_scores_codex":[0.9989471,0.00003225331,0.0004959835,0.0002049086,0.0001589356,0.0001607698],"domain_scores_gemma":[0.9986736,0.0001323569,0.0006648156,0.0001991718,0.0002596668,0.00007034501],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003057059,0.0001186147,0.000951594,0.00003364234,0.0001972607,0.0000064707,0.00275912,0.0002106336,0.5212338,0.1264827,0.003945152,0.3437554],"study_design_scores_gemma":[0.003912698,0.001444989,0.001734662,0.0001422514,0.00007721538,0.0002178546,0.00007218639,0.004437962,0.2809942,0.703979,0.002582719,0.0004043331],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07459085,0.00001244094,0.9239041,0.0007528269,0.0002405714,0.00009342061,6.275342e-7,0.00003142462,0.0003737255],"genre_scores_gemma":[0.5988911,0.00001216591,0.4005917,0.0002773812,0.0002086923,0.00000694346,2.33506e-7,0.000006253531,0.000005481494],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5774963,"threshold_uncertainty_score":0.3023282,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2345836734","doi":"10.3758/s13423-016-1053-2","title":"The principals of meaning: Extracting semantic dimensions from co-occurrence models of semantics","year":2016,"lang":"en","type":"review","venue":"Psychonomic Bulletin & Review","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":129,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Semantics (computer science); Meaning (existential); Linguistics; Cognitive psychology; Natural language processing; Cognitive science; Epistemology; Programming language; Computer science; Psychotherapist; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.07264841213761936,"gpt":0.3794374996201949,"spread":0.3067890874825755,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002053376,0.0007070921,0.003765243,0.0001742193,0.000169386,0.00005977189,0.003908284,0.0002163553,0.00007760468],"category_scores_gemma":[0.0004368117,0.0004316811,0.001335697,0.0005118484,0.0002392698,0.000168104,0.0006544654,0.0005437888,0.0002086139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001037,"about_ca_system_score_gemma":0.0002410768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001609898,"about_ca_topic_score_gemma":0.000001984611,"domain_scores_codex":[0.9941463,0.000696933,0.003063838,0.001090359,0.0004946957,0.0005078793],"domain_scores_gemma":[0.9884364,0.002919252,0.004808929,0.003452674,0.0002467064,0.0001360282],"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":[9.235105e-7,0.00005220631,4.975574e-7,0.01284098,0.0002343277,0.000002082711,0.0000311771,0.000002390412,0.00000329632,0.008067524,0.005481442,0.9732832],"study_design_scores_gemma":[0.00005829312,0.00001919936,1.326438e-7,0.1447892,0.0006080528,0.00001227421,0.000002036614,0.0001254251,0.00001186549,0.002793652,0.8512012,0.0003787362],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[3.02305e-7,0.8738935,0.1231332,0.0004099481,0.0002521592,0.001261412,0.00007696773,0.0001080302,0.0008644558],"genre_scores_gemma":[0.0000263415,0.9702747,0.02921614,0.00008295566,0.00006167097,0.0001671366,0.00002803032,0.00004754377,0.00009546444],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9729044,"threshold_uncertainty_score":0.9998135,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2040027527","doi":"10.3758/s13423-015-0808-5","title":"A rational model of function learning","year":2015,"lang":"en","type":"review","venue":"Psychonomic Bulletin & Review","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Air Force Office of Scientific Research; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Similarity (geometry); Associative learning; Associative property; Psychology; Artificial intelligence; Function (biology); Equivalence (formal languages); Probabilistic logic; Regression; Machine learning; Rational function; Regression analysis; Computer science; Cognitive psychology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.08088215470050462,"gpt":0.3658428833187138,"spread":0.2849607286182092,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001466453,0.0004667323,0.00254736,0.0002276653,0.00005702496,0.00004240735,0.001414361,0.0001851197,0.0001524729],"category_scores_gemma":[0.0001180312,0.000400274,0.0008945009,0.0005170126,0.00004971989,0.0001313516,0.000273744,0.0005404102,0.0007190124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001804838,"about_ca_system_score_gemma":0.0003458558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002174452,"about_ca_topic_score_gemma":2.521062e-7,"domain_scores_codex":[0.9968276,0.0003643903,0.001419457,0.0007963431,0.0003393612,0.0002528552],"domain_scores_gemma":[0.9967993,0.0001187997,0.001577318,0.001165893,0.0002250444,0.0001135731],"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":[7.280056e-7,0.00002516528,5.708684e-8,0.01442866,0.00006774333,2.961374e-7,0.000003669115,0.00005918859,1.254685e-7,0.003532871,0.03503672,0.9468448],"study_design_scores_gemma":[0.00005627872,0.00003688643,1.954531e-8,0.03085356,0.0005021545,0.00001147456,2.873907e-7,0.001337608,9.783754e-8,0.001294421,0.9655828,0.0003244215],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[3.331467e-9,0.6479406,0.3488362,0.0001571602,0.00009351386,0.0005475985,0.000002946581,0.0001398961,0.002282165],"genre_scores_gemma":[1.779485e-7,0.9207743,0.07724998,0.0002391119,0.00008276767,0.0002968891,0.00005321702,0.00004050894,0.00126304],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9465203,"threshold_uncertainty_score":0.9998449,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111310810","doi":"10.1145/1148170.1148262","title":"Statistical precision of information retrieval evaluation","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":107,"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":"Computer science; Data mining; Concordance; Population; Information retrieval; Confidence interval; Statistics; Degree (music); Statistical hypothesis testing; Data collection; Test (biology); Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01181805756965918,"gpt":0.3080099634055263,"spread":0.2961919058358671,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005499591,0.00004588248,0.00007830852,0.0001247692,0.00002239619,0.00003407607,0.0002225074,0.00002989786,0.00005352787],"category_scores_gemma":[0.0001688422,0.00003862924,0.00002225758,0.0003439371,0.00001846294,0.001219678,0.00006668088,0.00003300899,0.00002299102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004300844,"about_ca_system_score_gemma":0.00003480012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003109322,"about_ca_topic_score_gemma":0.000004411604,"domain_scores_codex":[0.9989877,0.00004138542,0.0002835751,0.00008867666,0.0005252996,0.00007339815],"domain_scores_gemma":[0.999234,0.00008570028,0.0001111082,0.0002574902,0.0002965509,0.0000152017],"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":[0.00000945989,0.00003644426,0.0003623952,0.000005313819,0.000003663206,1.899659e-7,0.00004534424,0.0008726837,0.002431027,0.7295376,0.002575831,0.26412],"study_design_scores_gemma":[0.0002061151,0.00007080677,0.01556617,0.000006322141,0.00001102377,0.00000142465,0.000005284544,0.5960891,0.06921358,0.3175053,0.001233332,0.00009156233],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0049689,0.000008971912,0.9836541,0.00005482512,0.00002350613,0.0001228859,0.000001238847,0.0001143119,0.01105121],"genre_scores_gemma":[0.584218,0.000001050291,0.4157148,0.00001509806,0.000005983457,0.000001907628,0.00001349663,8.27482e-7,0.00002885727],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5952164,"threshold_uncertainty_score":0.1575255,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106377293","doi":"10.1109/hicss.1999.772650","title":"The functionality attribute of cybergenres","year":2003,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Tuple; The Internet; Class (philosophy); Content (measure theory); World Wide Web; Multimedia; Information retrieval; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01553119694393844,"gpt":0.2669524419538304,"spread":0.251421245009892,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003867059,0.00004676404,0.00006875095,0.00002143743,0.0001022255,0.00002147187,0.0003883223,0.00001669887,0.0000296587],"category_scores_gemma":[0.0001173124,0.00002794542,0.00006023933,0.0003110137,0.00004614492,0.0001616698,0.00006338066,0.00003822061,0.00001160538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001365938,"about_ca_system_score_gemma":0.00002304006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001100663,"about_ca_topic_score_gemma":0.00002152329,"domain_scores_codex":[0.9993985,0.00005659866,0.0001476378,0.0001258503,0.0001679679,0.0001034888],"domain_scores_gemma":[0.9991891,0.000146188,0.00005946909,0.000477671,0.0001054701,0.00002214936],"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":[3.890773e-7,0.0000117501,0.001706066,5.537808e-7,0.00001163224,1.986801e-7,0.000007995649,0.00001945119,0.0005170816,0.9907223,0.002194814,0.004807745],"study_design_scores_gemma":[0.0001474136,0.00005625165,0.01479072,0.000003829085,0.00001163887,0.000007098981,0.00004115133,0.001924475,0.2456074,0.4428737,0.2943206,0.0002157083],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001816695,0.0001351819,0.983503,0.0003494426,0.00005603956,0.000036582,3.015579e-7,0.0001119257,0.01399081],"genre_scores_gemma":[0.8916189,0.00003194823,0.1057052,0.00009513836,0.000006975751,0.000007436386,3.373897e-7,0.000002129277,0.002531914],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8898022,"threshold_uncertainty_score":0.1139581,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2250595592","doi":"10.3115/v1/w14-4407","title":"A Template-based Abstractive Meeting Summarization: Leveraging Summary and Source Text Relationships","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":100,"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":"Automatic summarization; Readability; Computer science; Template; Sentence; Natural language processing; Information retrieval; Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02111276075879438,"gpt":0.2450902321805714,"spread":0.223977471421777,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000678648,0.000141952,0.0001579644,0.0001946728,0.0003692729,0.0001847761,0.0003221926,0.00006982795,0.000009174621],"category_scores_gemma":[0.0002589215,0.0001360647,0.0000430683,0.0004275178,0.0000495578,0.0007735579,0.0001497425,0.0002145211,0.00001446686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004258615,"about_ca_system_score_gemma":0.00002887687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004654372,"about_ca_topic_score_gemma":0.00003439734,"domain_scores_codex":[0.9987681,0.0001484402,0.00025189,0.0004162908,0.0002141797,0.0002010822],"domain_scores_gemma":[0.9985409,0.0007129553,0.0001491107,0.0004158665,0.00009974564,0.00008138982],"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":[0.00003772158,0.0002737815,0.2496283,0.0001454447,0.0001697871,0.00001721899,0.003274142,0.05604264,0.01149254,0.2884952,0.007883492,0.3825397],"study_design_scores_gemma":[0.0003799021,0.00004626684,0.01450991,0.0001101515,0.00002325133,0.000007722999,0.0001158432,0.9365352,0.01120245,0.02105471,0.01551745,0.0004971825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003616695,0.0000414696,0.9778963,0.0007663359,0.00003209901,0.0000984271,2.267603e-7,0.0006240784,0.01692434],"genre_scores_gemma":[0.7205691,0.000003850734,0.2786137,0.000269415,0.00004389878,0.000009458846,0.000004312913,0.000009987335,0.0004762542],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8804925,"threshold_uncertainty_score":0.5548559,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962704246","doi":"10.18653/v1/p18-1062","title":"Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Automatic summarization; Computer science; Zhàng; Submodular set function; Natural language processing; Sentence; Maximization; Artificial intelligence; Linguistics; Volume (thermodynamics); Mathematics; Philosophy; History; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.01322545130685726,"gpt":0.2521054262172721,"spread":0.2388799749104148,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001430006,0.0001409598,0.0001409006,0.0001327325,0.0002074439,0.0001190196,0.0002948871,0.00005527166,0.000008967841],"category_scores_gemma":[0.00005045316,0.0001093611,0.00001798144,0.0004929872,0.0001124336,0.001020025,0.0001659032,0.00007514378,0.000005672152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003063364,"about_ca_system_score_gemma":0.00001755638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008092722,"about_ca_topic_score_gemma":0.00008078085,"domain_scores_codex":[0.9989023,0.00005573969,0.0001871539,0.0004435728,0.0002319447,0.0001793233],"domain_scores_gemma":[0.9990113,0.00004771875,0.0001353098,0.0003602281,0.0003794975,0.000065988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001901701,0.0006800952,0.1462069,0.0001010053,0.000199914,0.00004293198,0.004951778,0.004746107,0.6247545,0.02189462,0.0002632509,0.1959687],"study_design_scores_gemma":[0.0004121035,0.0001084548,0.02185082,0.00006992781,0.00001209421,0.000006234664,0.00007718201,0.8245628,0.1519323,0.00066496,0.00008960891,0.0002134919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04957534,0.00002561243,0.948944,0.0001316394,0.00002239468,0.0001876912,4.218159e-7,0.0004291562,0.0006837433],"genre_scores_gemma":[0.585518,0.00001816757,0.4142978,0.00007514988,0.00001347515,0.00000656873,0.000006271495,0.000007046188,0.00005751298],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8198167,"threshold_uncertainty_score":0.4459618,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2950657507","doi":"10.1073/pnas.1914370116","title":"Predicting research trends with semantic and neural networks with an application in quantum physics","year":2020,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"Universität Wien; Austrian Science Fund","keywords":"Artificial neural network; Quantum; Computer science; Physics; Artificial intelligence; Quantum mechanics","retraction":null,"screen_n_in":null,"score":{"opus":0.06736840998995927,"gpt":0.3578810530827379,"spread":0.2905126430927786,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00107234,0.00007075514,0.0001212668,0.0001612811,0.0001578594,0.00005350732,0.001010922,0.00003368927,1.731466e-7],"category_scores_gemma":[0.00007324939,0.00004269429,0.00001415399,0.003391878,0.0006176758,0.001263916,0.0002024179,0.0002488344,3.149378e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001671449,"about_ca_system_score_gemma":0.00001519788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001245092,"about_ca_topic_score_gemma":8.620942e-7,"domain_scores_codex":[0.9982503,0.00001272336,0.0001784802,0.0003424763,0.001062951,0.0001530493],"domain_scores_gemma":[0.9993784,0.00009054865,0.0002297773,0.00001388727,0.0002465911,0.00004078478],"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":[0.0001016292,0.0001617205,0.400779,0.0001239193,0.000027198,7.371766e-8,0.003029264,0.05287139,0.04373689,0.4517408,0.00005646078,0.04737166],"study_design_scores_gemma":[0.00008496174,0.0001909664,0.03242437,0.00003476817,0.00000298496,0.00000295539,0.0001044977,0.9399105,0.007642353,0.0195468,0.000002527812,0.00005228274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9745488,0.00005187589,0.01761239,0.00710471,0.000001724275,0.0001967197,7.89568e-7,0.00005640853,0.0004266068],"genre_scores_gemma":[0.9800105,0.000006497237,0.0198064,0.0001192067,0.00003742372,0.00001438189,6.450248e-8,0.000002914211,0.000002627358],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8870391,"threshold_uncertainty_score":0.2275852,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2953722276","doi":"10.1016/j.ipm.2019.102063","title":"A multi-centrality index for graph-based keyword extraction","year":2019,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Centrality; Betweenness centrality; PageRank; Computer science; Clustering coefficient; Cluster analysis; Graph; Artificial intelligence; Data mining; Natural language processing; Information retrieval; Theoretical computer science; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01397295543473869,"gpt":0.2989504196007305,"spread":0.2849774641659918,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003660819,0.0001375734,0.0001294557,0.0003616163,0.0001403117,0.0003951232,0.0004776535,0.00004876306,0.000008091645],"category_scores_gemma":[0.00001367955,0.0001347611,0.0000826362,0.0005614907,0.0000172716,0.004635443,0.00008658486,0.00007922481,0.00005093828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001144923,"about_ca_system_score_gemma":0.00003104425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005427016,"about_ca_topic_score_gemma":0.000002081643,"domain_scores_codex":[0.9988089,0.00001515004,0.0004047324,0.0002085057,0.0003219728,0.0002407078],"domain_scores_gemma":[0.9989888,0.00001918225,0.0003598099,0.0003994864,0.0001891275,0.00004356863],"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":[0.00002568861,0.0001182913,0.001095972,0.0006030032,0.00002926549,5.37352e-7,0.0003496749,0.009555063,0.0000794947,0.009800004,0.0004027241,0.9779403],"study_design_scores_gemma":[0.001078959,0.00003381771,0.007995318,0.00008780326,0.00001919952,7.755364e-7,0.0000922242,0.9403892,0.001364928,0.005125605,0.04354413,0.0002680633],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001378752,0.00001598634,0.9954499,0.0002982869,0.0001115375,0.0007560275,0.00000124272,0.0005685277,0.001419768],"genre_scores_gemma":[0.5957311,0.000003641267,0.4033107,0.0006041412,0.000006837212,0.0001370085,0.00002099374,0.000004647972,0.0001810093],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9776722,"threshold_uncertainty_score":0.5495397,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2150630862","doi":"10.1075/ml.5.1.06baa","title":"A real experiment is a factorial experiment?","year":2010,"lang":"en","type":"article","venue":"The Mental Lexicon","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":89,"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":"Factorial experiment; Mathematics; Statistics; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01636144710900018,"gpt":0.3160083406347708,"spread":0.2996468935257707,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001771372,0.000175884,0.0001563629,0.0000539354,0.0002037486,0.0001387524,0.001134458,0.00005990662,0.0002405239],"category_scores_gemma":[0.000006302678,0.0001215291,0.000113374,0.0001678479,0.0001026171,0.000387304,0.0004584637,0.000213906,0.0001002023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008462057,"about_ca_system_score_gemma":0.00003156433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001475652,"about_ca_topic_score_gemma":0.00001491519,"domain_scores_codex":[0.9987447,0.00004286963,0.0002056584,0.000361881,0.0003704465,0.0002744668],"domain_scores_gemma":[0.9988342,0.00003239697,0.00009802637,0.0009309946,0.00002318886,0.00008118291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001255698,0.00008791169,0.00004244703,8.165018e-7,0.00002173757,0.000002621514,0.005688558,2.502804e-7,0.9280198,0.05740183,0.002503691,0.006217807],"study_design_scores_gemma":[0.0002501748,0.00009138152,0.00005106594,0.00000365988,0.00000496752,0.000006652485,0.0001243708,0.0008806179,0.9745613,0.006755418,0.01710172,0.000168709],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.869728,0.0001352336,0.09049683,0.003482895,0.003485202,0.0009652104,0.000008972474,0.001316592,0.03038106],"genre_scores_gemma":[0.9747329,0.0000147098,0.02387558,0.0003110745,0.000284113,0.00008233158,0.000002990259,0.00001336546,0.0006829132],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1050049,"threshold_uncertainty_score":0.4955815,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107363066","doi":"10.1002/asi.23367","title":"The invariant distribution of references in scientific articles","year":2015,"lang":"en","type":"article","venue":"Journal of the Association for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"Canada Research Chairs","keywords":"Bibliometrics; Computer science; Scientific communication; Section (typography); Information retrieval; Library science; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.01949208080998927,"gpt":0.2780394076808985,"spread":0.2585473268709092,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00650615,0.00003506287,0.0000904613,0.0003890444,0.0002698785,0.0002293869,0.0009650913,0.00004477568,4.694763e-8],"category_scores_gemma":[0.00616389,0.00001914276,0.00002492085,0.002934388,0.0003023293,0.002877363,0.0001714522,0.00009491187,5.541735e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002575399,"about_ca_system_score_gemma":0.0003584513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003212143,"about_ca_topic_score_gemma":0.00001731448,"domain_scores_codex":[0.9987477,0.00002458807,0.0004376125,0.00005227456,0.000612745,0.0001250446],"domain_scores_gemma":[0.9962636,0.0001202592,0.001092989,0.0001826776,0.002316853,0.00002365611],"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":[0.00001010734,0.00002409589,0.02417442,0.000003872837,0.00001050292,7.72858e-8,0.001221478,0.0001216134,0.001703794,0.8908622,0.001397072,0.08047076],"study_design_scores_gemma":[0.001010194,0.0003006714,0.03365213,0.00005685765,0.00002078503,0.00002581336,0.002972267,0.03390698,0.09930582,0.7704799,0.05811789,0.000150646],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.784822,0.0001440299,0.1835492,0.02992264,0.0006996354,0.0003528349,0.000005985471,0.00004813968,0.0004555653],"genre_scores_gemma":[0.9973907,0.00001576835,0.002541279,0.0000245497,0.000004245691,0.000003589212,2.708014e-7,4.459139e-7,0.00001911805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2125687,"threshold_uncertainty_score":0.7379197,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2089286873","doi":"10.1037/h0087425","title":"The p-value fallacy and how to avoid it.","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Experimental Psychology/Revue canadienne de psychologie expérimentale","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":88,"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":"Fallacy; Null hypothesis; Psychology; Value (mathematics); Statistical hypothesis testing; Interpretation (philosophy); p-value; Econometrics; Statistics; Alternative hypothesis; Inference; Cognitive psychology; Mathematics; Epistemology; Artificial intelligence; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.0283444507547641,"gpt":0.3147546726853978,"spread":0.2864102219306337,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001537147,0.0003856657,0.0004377395,0.00056228,0.000627517,0.0003408297,0.002164668,0.0001835343,0.000043042],"category_scores_gemma":[0.0004141956,0.0003412184,0.0001960074,0.0006895017,0.0004396847,0.0005402764,0.00008446534,0.0005113573,0.00002006393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009917932,"about_ca_system_score_gemma":0.0003967555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006983363,"about_ca_topic_score_gemma":0.01722547,"domain_scores_codex":[0.9967964,0.0003478467,0.0005497069,0.0007308581,0.0001341757,0.001441034],"domain_scores_gemma":[0.9960164,0.0001644341,0.0003757627,0.001167918,0.0001489617,0.002126475],"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":[0.0001548718,0.0004600649,0.01124445,0.00002115098,0.0006356601,0.003519077,0.02275015,0.00008447829,0.3154028,0.2798843,0.3391333,0.02670969],"study_design_scores_gemma":[0.003932185,0.004057729,0.008758072,0.0002406145,0.00007664855,0.01370555,0.01869086,0.0001673958,0.1449554,0.03148971,0.771781,0.002144767],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8606627,0.01110372,0.06804077,0.04195042,0.003759834,0.000793481,0.0000168357,0.0001000646,0.01357217],"genre_scores_gemma":[0.944757,0.0001042281,0.04726009,0.007176421,0.0001168645,0.00004315158,0.000001222724,0.00003723325,0.0005037285],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4326477,"threshold_uncertainty_score":0.999904,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153207410","doi":"10.1145/1978942.1979167","title":"Review spotlight","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":83,"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":"Computer science; Product (mathematics); Adjective; Quality (philosophy); World Wide Web; Noun; Information retrieval; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.04088631501555477,"gpt":0.2811978908767365,"spread":0.2403115758611817,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001175767,0.00005399183,0.00009753057,0.00003680103,0.00002008614,0.000008297684,0.0006557313,0.00001312025,0.0002528748],"category_scores_gemma":[0.00001417228,0.00003980322,0.00005025896,0.0002918318,0.00001161367,0.0003403831,0.0001381978,0.00003510785,0.0002973087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000803016,"about_ca_system_score_gemma":0.000007311043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008533242,"about_ca_topic_score_gemma":0.000002526447,"domain_scores_codex":[0.9995361,0.00001408313,0.0001119503,0.0001655447,0.00007313144,0.00009917752],"domain_scores_gemma":[0.9993274,0.000007264055,0.00003417206,0.0005574161,0.00003742611,0.00003632997],"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":[2.669506e-7,0.00003853339,0.0001478077,0.00005282949,0.00001014135,0.00001152496,0.00007056102,2.47899e-8,0.000158785,0.7848809,0.04487449,0.1697541],"study_design_scores_gemma":[0.00009921318,0.00009389287,0.00106091,0.0005984436,0.00003309425,0.00003890418,0.000003521717,0.001085371,0.08161593,0.223622,0.6911693,0.0005794518],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00000686855,0.003985227,0.8540983,0.0002580994,0.00001736717,0.00005310471,2.676555e-8,0.0005706573,0.1410103],"genre_scores_gemma":[0.01283827,0.005022283,0.9745328,0.00606633,0.00000959176,0.00001366245,2.283222e-7,0.000004537333,0.001512327],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6462948,"threshold_uncertainty_score":0.3821401,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2032328503","doi":"10.1007/s10791-009-9108-x","title":"Document clustering of scientific texts using citation contexts","year":2009,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Information retrieval; Computer science; Document clustering; Citation; Vocabulary; Context (archaeology); Similarity (geometry); Representation (politics); Document retrieval; Natural language processing; Artificial intelligence; World Wide Web; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.0160256859248469,"gpt":0.2950436954188471,"spread":0.2790180094940002,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004991781,0.00008795421,0.0001313024,0.0004504971,0.0001252266,0.0002914423,0.0003874276,0.00004483317,0.000008330959],"category_scores_gemma":[0.0001120901,0.00008700669,0.00005907105,0.001012773,0.00004293321,0.004929793,0.00007694725,0.00006564358,0.00001839687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000102123,"about_ca_system_score_gemma":0.00005679828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003224357,"about_ca_topic_score_gemma":8.041845e-7,"domain_scores_codex":[0.9987367,0.00002385109,0.0004896937,0.0001185582,0.0004796878,0.0001514541],"domain_scores_gemma":[0.9988553,0.00002792194,0.0003641493,0.0003516878,0.0003563927,0.00004456832],"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":[0.00006801321,0.00006210744,0.0001788734,0.00005857395,0.00003056094,0.000002354211,0.005232785,0.01538972,0.04377983,0.08165631,0.0003050675,0.8532358],"study_design_scores_gemma":[0.0007095921,0.0002734871,0.004252001,0.0001070285,0.00001836316,0.000017211,0.00008620138,0.7957874,0.162362,0.03252544,0.003489282,0.0003719551],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07608683,0.00002104312,0.922473,0.0001017454,0.0001384385,0.0001526482,0.000001153878,0.0001453661,0.0008797561],"genre_scores_gemma":[0.8730282,0.000001792197,0.1267933,0.0001273347,0.000009851551,6.357538e-7,0.000008104314,0.000001526252,0.00002923284],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8528638,"threshold_uncertainty_score":0.3573981,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4255165398","doi":"10.4018/978-1-59140-441-5.ch008","title":"KEA","year":2004,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Information retrieval; Metadata; Feature (linguistics); Artificial intelligence; License; Natural language processing; World Wide Web; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01472894233422973,"gpt":0.2612281464799091,"spread":0.2464992041456794,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00008270163,0.0004644538,0.0004964414,0.0001118552,0.00008982103,0.000150369,0.001745729,0.0003849827,0.00003229647],"category_scores_gemma":[0.00001007471,0.000466316,0.000354541,0.00003760803,0.0001022472,0.0001453144,0.0006374099,0.000323573,0.000479513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005838915,"about_ca_system_score_gemma":0.0002626255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003248463,"about_ca_topic_score_gemma":0.00003654609,"domain_scores_codex":[0.9979367,0.0000092138,0.0003833201,0.0007833321,0.0005229439,0.0003644601],"domain_scores_gemma":[0.9979621,0.00001748319,0.000270224,0.001458815,0.0001301384,0.0001612972],"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":[0.000001448353,0.000004153389,0.000001061135,0.000007104262,0.00004658915,0.0001088475,0.00001292757,0.000006129679,0.000009736801,0.9741659,0.0008654149,0.02477073],"study_design_scores_gemma":[0.0001075648,0.00004849753,0.00000315944,0.0001090096,0.00003201895,0.00003344919,3.443112e-7,0.00003797815,0.0002417881,0.9436193,0.05532156,0.0004453513],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[9.825625e-7,0.0002075962,0.2556575,0.00006990276,0.0001400724,0.000157435,0.00001161724,0.0008982154,0.7428567],"genre_scores_gemma":[0.1053416,0.00003249164,0.3819483,0.003102078,0.0006623414,0.00005443146,0.000007867005,0.0001497674,0.5087011],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2341556,"threshold_uncertainty_score":0.9997789,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2950982165","doi":"","title":"Coherent Keyphrase Extraction via Web Mining","year":2003,"lang":"en","type":"preprint","venue":"NPARC","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Information retrieval; Task (project management); Cluster analysis; Search engine indexing; Natural language processing; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02164678121118828,"gpt":0.3037006518615237,"spread":0.2820538706503354,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003432683,0.0003273917,0.0003890276,0.000258324,0.0001010293,0.0001863876,0.001167595,0.0002784174,0.0002130094],"category_scores_gemma":[0.00005881532,0.000340928,0.0002169778,0.0002973562,0.00004095743,0.0003173082,0.0008780428,0.0006420348,0.00007399585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002281433,"about_ca_system_score_gemma":0.0001454951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006969637,"about_ca_topic_score_gemma":0.00001750884,"domain_scores_codex":[0.9977785,0.000132729,0.0004156922,0.0008785992,0.0004563522,0.0003381482],"domain_scores_gemma":[0.9977864,0.00007746082,0.0003968017,0.001478487,0.0001373578,0.0001235042],"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":[0.00001544321,0.0005353153,0.0008061539,0.0002286291,0.000298872,0.0002424151,0.0008945004,0.001402345,0.2365303,0.03251776,0.03043401,0.6960942],"study_design_scores_gemma":[0.0004567455,0.0001182844,0.000444511,0.0003575189,0.0001506451,0.00008779627,0.00004113475,0.2889412,0.07819459,0.5884381,0.04090295,0.001866554],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008318343,0.0001143364,0.9631808,0.0002929224,0.0005773955,0.0002713865,0.000002798427,0.0007920093,0.02644999],"genre_scores_gemma":[0.4581722,0.00008069454,0.5405839,0.0001655376,0.00008674183,0.000108307,0.00001153082,0.00002233117,0.0007687232],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6942276,"threshold_uncertainty_score":0.9999043,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100784475","doi":"10.1177/1461445612466468","title":"Rhetorical relations in multimodal documents","year":2013,"lang":"en","type":"article","venue":"Discourse Studies","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Rhetorical question; Presentational and representational acting; Computer science; Natural language processing; Coherence (philosophical gambling strategy); Linguistics; Categorization; Set (abstract data type); Artificial intelligence; Subject (documents); Mathematics; World Wide Web; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.0271779675503826,"gpt":0.3780032763737782,"spread":0.3508253088233956,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001022108,0.000112102,0.0001893231,0.0001367977,0.00009830178,0.00004755469,0.0003588297,0.00002709051,0.00001979111],"category_scores_gemma":[0.0001074604,0.0000895986,0.00005360205,0.000406727,0.00008650868,0.0009947611,0.000302647,0.0001089943,0.0002218925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001010029,"about_ca_system_score_gemma":0.00001334032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008388793,"about_ca_topic_score_gemma":0.00005312973,"domain_scores_codex":[0.9990517,0.00003691512,0.000233088,0.0002725355,0.0001866706,0.0002190372],"domain_scores_gemma":[0.9993976,0.00008117341,0.00006297478,0.0003363697,0.00008351319,0.00003837362],"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":[0.000005957179,0.00106274,0.2004381,0.00002952307,0.000625159,0.00007703651,0.02048631,0.001385872,0.001427103,0.4965787,0.05761363,0.2202699],"study_design_scores_gemma":[0.001787015,0.0002249361,0.3080752,0.0002178506,0.00007910738,0.000009252465,0.007542364,0.0734346,0.002538037,0.5984262,0.00597042,0.001695109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2687026,0.002938935,0.6976633,0.01416286,0.0005008915,0.0009032972,0.000001962167,0.0008909834,0.01423511],"genre_scores_gemma":[0.9307705,0.00009638823,0.06773224,0.00006728614,0.00002573125,0.0001496797,8.590833e-7,0.000005195459,0.001152098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6620679,"threshold_uncertainty_score":0.3653725,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161427841","doi":"","title":"Summarizing Emails with Conversational Cohesion and Subjectivity","year":2008,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":66,"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":"Automatic summarization; Cohesion (chemistry); Computer science; PageRank; Cosine similarity; Natural language processing; Artificial intelligence; Graph; Sentence; Empirical research; Information retrieval; Subjectivity; Theoretical computer science; Pattern recognition (psychology); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01336756495223629,"gpt":0.2436825173727591,"spread":0.2303149524205229,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005475976,0.00008702647,0.0001557552,0.00006476924,0.0003661705,0.00002804876,0.0002327875,0.00004476954,2.688988e-7],"category_scores_gemma":[0.00470842,0.00007067721,0.00006115325,0.0002436779,0.00005630504,0.00006903361,0.0001041411,0.00007745086,4.074625e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001441364,"about_ca_system_score_gemma":0.0001117305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001600998,"about_ca_topic_score_gemma":0.000007850972,"domain_scores_codex":[0.998931,0.00006599862,0.0002368311,0.000188357,0.0004577815,0.0001200251],"domain_scores_gemma":[0.9962969,0.001856415,0.0005642357,0.000132519,0.001124882,0.00002501478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003608725,0.0001057225,0.6116477,0.00005273688,0.0001581404,0.000001944237,0.0006961052,0.07089256,0.0002573885,0.3148366,0.00085511,0.0004598935],"study_design_scores_gemma":[0.001315175,0.0002075095,0.2991844,0.0001450173,0.0001055637,0.00001835701,0.00003321941,0.5126092,0.006137724,0.1761356,0.003662907,0.0004452879],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07226845,0.00003212084,0.9253579,0.0004662924,0.0002111419,0.0002940832,0.00001888923,0.0001294875,0.001221631],"genre_scores_gemma":[0.7667304,0.000002116247,0.2330418,0.00005520412,0.00006129601,0.000005775817,0.000008838416,0.000005578057,0.00008905098],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6944619,"threshold_uncertainty_score":0.5636758,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W152717974","doi":"10.63317/5h9g23tpswhr","title":"Automatically Identifying Changes in the Semantic Orientation of Words","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":66,"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":"Computer science; Task (project management); Natural language processing; Word (group theory); Artificial intelligence; Orientation (vector space); Semantic change; Meaning (existential); Baseline (sea); Word-sense disambiguation; Semantic role labeling; Linguistics; Psychology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01640136917437291,"gpt":0.3180775501979433,"spread":0.3016761810235704,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004732391,0.0000503664,0.00008585837,0.0001328711,0.00002654472,0.00005141469,0.0006453936,0.00002619887,0.00002043565],"category_scores_gemma":[0.00007414127,0.00003281632,0.00002466496,0.0005926313,0.00003290497,0.0002841094,0.00008770217,0.000101686,0.000006169648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005668612,"about_ca_system_score_gemma":0.00001014961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002937163,"about_ca_topic_score_gemma":0.0009158296,"domain_scores_codex":[0.9993591,0.00003497417,0.0001539991,0.000133299,0.0002189951,0.00009965734],"domain_scores_gemma":[0.9993582,0.0001106227,0.00006883599,0.0004094089,0.00004052488,0.00001244784],"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":[0.000001120833,0.0001069027,0.006216047,0.00003583606,0.00001007738,0.000008210855,0.006140888,0.00001124685,0.09876198,0.7909017,0.0001134441,0.09769253],"study_design_scores_gemma":[0.0003833293,0.0001245387,0.1090447,0.00009554806,0.00002809402,0.00002689029,0.001068813,0.2719529,0.2857227,0.3306896,0.0004505949,0.0004122627],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1529148,0.000003708336,0.8445749,0.0008809917,0.00005110328,0.00008712077,5.67995e-8,0.0001095903,0.001377755],"genre_scores_gemma":[0.7793295,0.00000251996,0.2204779,0.0001258462,0.000009233047,0.00001104317,3.284003e-7,0.000001823023,0.00004172075],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6264148,"threshold_uncertainty_score":0.1338211,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138954094","doi":"10.1145/1097047.1097059","title":"Narrative text classification for automatic key phrase extraction in web document corpora","year":2005,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Automatic summarization; Information retrieval; Plain text; Key (lock); Natural language processing; Phrase; tf–idf; Artificial intelligence; Ranking (information retrieval); Document clustering; Information extraction; HTML element; Web page; Keyword extraction; Cluster analysis; World Wide Web; Term (time)","retraction":null,"screen_n_in":null,"score":{"opus":0.02461358341141394,"gpt":0.3336148891383208,"spread":0.3090013057269069,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003379104,0.0001223924,0.0001556581,0.0002371328,0.00007702831,0.00009196351,0.0003497747,0.00005572673,0.00006631777],"category_scores_gemma":[0.00005061362,0.0001105642,0.00006086158,0.0004438656,0.00002452244,0.001483573,0.00004581281,0.0000853126,0.00005019926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002980529,"about_ca_system_score_gemma":0.00005655519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001050066,"about_ca_topic_score_gemma":0.0003320111,"domain_scores_codex":[0.998867,0.00004840355,0.0003539338,0.0003541282,0.0001921637,0.0001844223],"domain_scores_gemma":[0.9991518,0.00009365062,0.0002052135,0.0004122195,0.00008830085,0.00004886623],"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":[0.00001263192,0.0003618763,0.0003174042,0.00001910172,0.00002548563,0.000003077579,0.005403575,0.0006599881,0.04071084,0.2299132,0.004983912,0.7175889],"study_design_scores_gemma":[0.00039267,0.00007072539,0.001284575,0.00002067634,0.000007207837,0.000004262358,0.0004689286,0.9514095,0.01820568,0.02024778,0.007676095,0.0002118791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04118503,0.00002473838,0.9530451,0.002940278,0.00003683452,0.0004721308,4.162337e-7,0.0004843523,0.001811073],"genre_scores_gemma":[0.6076561,0.000008658535,0.3913634,0.0001454497,0.00002346424,0.0001634593,0.000003916133,0.000004881918,0.0006307636],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9507495,"threshold_uncertainty_score":0.4508676,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2603222250","doi":"10.1017/s0269888917000029","title":"The state of the art in semantic relatedness: a framework for comparison","year":2017,"lang":"en","type":"article","venue":"The Knowledge Engineering Review","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; WordNet; Closeness; Semantic similarity; Similarity (geometry); Strengths and weaknesses; Representation (politics); Domain (mathematical analysis); Metric (unit); Data science; Information retrieval; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02277658548795489,"gpt":0.3350866112312231,"spread":0.3123100257432682,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00124264,0.0001366069,0.0003500015,0.00002796532,0.0002600932,0.00007912945,0.002863405,0.00003117141,7.011637e-7],"category_scores_gemma":[0.001270604,0.00006516041,0.0001632491,0.0003164824,0.00007800072,0.0001434472,0.0004515054,0.0002984411,0.00001528406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003778853,"about_ca_system_score_gemma":0.00002820639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002434124,"about_ca_topic_score_gemma":0.00002050413,"domain_scores_codex":[0.9990218,0.00006408245,0.0004012596,0.0001730689,0.0001217837,0.0002179688],"domain_scores_gemma":[0.9969714,0.0006470021,0.0002988218,0.00198006,0.00008037101,0.00002228734],"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":[0.000008327102,0.000154522,0.0005333703,0.004561862,0.0001948595,0.00000244043,0.00240088,0.00400587,0.0003382199,0.2714649,0.004822389,0.7115124],"study_design_scores_gemma":[0.0002707999,0.00006191943,0.005796297,0.02757338,0.0001746956,0.000009746751,0.000009370128,0.5686952,0.003181486,0.08032832,0.3133547,0.0005440623],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005141936,0.1036244,0.8928441,0.001749143,0.0002904073,0.0007374853,6.351911e-7,0.0000910705,0.0001485664],"genre_scores_gemma":[0.8454099,0.0496047,0.1024472,0.000164593,0.0001230878,0.000633939,9.667364e-7,0.00007193816,0.001543642],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8448957,"threshold_uncertainty_score":0.5320966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169142063","doi":"10.1613/jair.3940","title":"Topic Segmentation and Labeling in Asynchronous Conversations","year":2013,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Computer science; Asynchronous communication; Segmentation; Artificial intelligence; Conversation; Natural language processing; Exploit; Graph; Linguistics; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1082659095785678,"gpt":0.424850168063926,"spread":0.3165842584853582,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001483233,0.00005607758,0.0001292637,0.0006173765,0.00009331142,0.0002190246,0.0004075541,0.00003963238,0.00005487368],"category_scores_gemma":[0.0003308776,0.00004950662,0.00003205341,0.000753769,0.00009904255,0.001067455,0.0001150136,0.0003548369,0.00003760059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001364216,"about_ca_system_score_gemma":0.0000981612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001492061,"about_ca_topic_score_gemma":0.00006485697,"domain_scores_codex":[0.9985737,0.0001609762,0.0004621408,0.0001356075,0.0004470028,0.0002206006],"domain_scores_gemma":[0.9986854,0.0003300168,0.0001209393,0.0001559603,0.0006273811,0.00008034636],"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":[0.000005079478,0.00009118294,0.00166586,0.000009693793,0.00001290541,0.00002145948,0.002088136,0.0005984973,0.04945802,0.0401774,0.00006379978,0.905808],"study_design_scores_gemma":[0.00005879125,0.0004367064,0.001808388,0.0000965072,0.000004935979,0.00003980524,0.003578268,0.1695396,0.2807754,0.543384,0.0001115992,0.0001660705],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.214954,0.000177129,0.7828961,0.001651909,0.000049527,0.0001354386,8.147802e-8,0.00001141254,0.0001244048],"genre_scores_gemma":[0.8893526,0.0002283799,0.1103128,0.00002616236,0.00005024385,0.000007254876,1.301088e-7,0.000003137727,0.00001924419],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9056419,"threshold_uncertainty_score":0.2112059,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2621499279","doi":"10.1037/xlm0000455","title":"Exploring the self-ownership effect: Separating stimulus and response biases.","year":2017,"lang":"en","type":"article","venue":"Journal of Experimental Psychology Learning Memory and Cognition","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":61,"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":"Economic and Social Research Council","keywords":"Categorization; Cognitive psychology; Stimulus (psychology); PsycINFO; Psychology; Perception; Prioritization; Object (grammar); Information processing; Task (project management); Social psychology; Computer science; Artificial intelligence; Business; Economics; Political science; MEDLINE","retraction":null,"screen_n_in":null,"score":{"opus":0.09530499901207543,"gpt":0.3885107134879918,"spread":0.2932057144759164,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001550594,0.000122437,0.0001934847,0.0001212752,0.000818793,0.0002157875,0.0003360191,0.0000438121,0.000004207895],"category_scores_gemma":[0.0004571401,0.00008744654,0.00006015483,0.00006031756,0.0001649143,0.001264311,0.0001410782,0.0004127598,0.000002475369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002145886,"about_ca_system_score_gemma":0.00001253368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001261363,"about_ca_topic_score_gemma":2.892218e-7,"domain_scores_codex":[0.9986997,0.0005482541,0.0002442358,0.0002069655,0.0001535133,0.0001473569],"domain_scores_gemma":[0.998625,0.0005036257,0.0004996367,0.0002414684,0.00006030417,0.0000699692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001898575,0.0002240887,0.002456811,0.000015178,0.0002157445,0.0003280238,0.01056624,0.00008456237,0.7246523,0.0003210829,0.0001110203,0.2591264],"study_design_scores_gemma":[0.006282896,0.008794182,0.08923363,0.0006024441,0.0002440431,0.003979533,0.004464976,0.006958601,0.8749256,0.002829205,0.0008841663,0.0008007255],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9898168,0.0005793973,0.007969677,0.0006035087,0.0001889668,0.00008056129,9.976421e-8,0.00005228969,0.0007087436],"genre_scores_gemma":[0.9947664,0.0001081864,0.004795257,0.0001898637,0.00009522943,0.000012444,2.550536e-7,0.000007522355,0.00002481164],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2583257,"threshold_uncertainty_score":0.6297576,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3027864066","doi":"10.1145/3377939","title":"Story Forest","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":60,"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":"Timeline; Computer science; Event (particle physics); Information retrieval; The Internet; Novelty; World Wide Web; Cluster analysis; Set (abstract data type); News aggregator; Graph; Data science; Artificial intelligence; History","retraction":null,"screen_n_in":null,"score":{"opus":0.06664237805374586,"gpt":0.3114345391788544,"spread":0.2447921611251086,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0001210553,0.0002262196,0.000257621,0.000106143,0.0002176148,0.0002156184,0.005876232,0.0000758915,0.00005461461],"category_scores_gemma":[0.0001133996,0.0002197622,0.0001137857,0.0006317184,0.00007222089,0.003915032,0.0003020019,0.0003907169,0.0004892565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005866664,"about_ca_system_score_gemma":0.0001077944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003863608,"about_ca_topic_score_gemma":0.0002811239,"domain_scores_codex":[0.9981965,0.00009602082,0.0002393066,0.0009877858,0.0002320595,0.0002483482],"domain_scores_gemma":[0.995061,0.0003462591,0.00007550845,0.00430856,0.00004851175,0.0001601719],"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":[0.0001185077,0.001511925,0.0006964733,0.00005939703,0.000684283,0.0000717228,0.003272465,0.001935378,0.005527878,0.0104373,0.04901138,0.9266733],"study_design_scores_gemma":[0.002612652,0.0008706229,0.004697907,0.0002544108,0.0006033848,0.0000112368,0.0005607742,0.2985135,0.04590346,0.06312782,0.5796736,0.003170673],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001281829,0.0003572182,0.9932447,0.003050372,0.0002207741,0.0001441147,0.000643295,0.0005813295,0.000476389],"genre_scores_gemma":[0.8561631,0.0001285432,0.1419536,0.0007959017,0.0001525868,0.00002994107,0.0003889267,0.00003012964,0.0003573156],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9235026,"threshold_uncertainty_score":0.9995025,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2966026905","doi":"10.24963/ijcai.2019/712","title":"Unsupervised Neural Aspect Extraction with Sememes","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":57,"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":"Youth Innovation Promotion Association; National Natural Science Foundation of China; Ant Financial Services Group; Tencent; National Key Research and Development Program of China; Youth Innovation Promotion Association of the Chinese Academy of Sciences","keywords":"Computer science; Artificial intelligence; Natural language processing; Semantics (computer science); Coherence (philosophical gambling strategy); Sentence; Context (archaeology); Word (group theory); Artificial neural network; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.007519555874121481,"gpt":0.2530384046953645,"spread":0.2455188488212431,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007170908,0.00009880518,0.0001158117,0.0000938266,0.00003666807,0.00008258252,0.0004174907,0.00002622892,0.0001589143],"category_scores_gemma":[0.000004290051,0.00006981702,0.00004186933,0.000378691,0.00001346642,0.001051819,0.00007524088,0.00008676764,0.0001401174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002725672,"about_ca_system_score_gemma":0.00001555403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002765012,"about_ca_topic_score_gemma":0.0000284082,"domain_scores_codex":[0.9992018,0.00002103305,0.0001059653,0.0003026043,0.0002089137,0.0001596354],"domain_scores_gemma":[0.9992718,0.00003554985,0.00004586588,0.0005494943,0.00005822046,0.00003908098],"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":[0.00006596466,0.000363755,0.0799307,0.0000448148,0.0001929207,0.00009508349,0.0007240584,0.003294942,0.1541113,0.3859894,0.003211428,0.3719757],"study_design_scores_gemma":[0.001152023,0.0009353722,0.03835895,0.00003541324,0.00003608726,0.0001304665,0.0001624326,0.7048553,0.221192,0.01531081,0.01670067,0.001130452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1167257,0.00002141184,0.8626634,0.0004836322,0.00004837278,0.0001348496,9.512994e-8,0.0007982769,0.01912429],"genre_scores_gemma":[0.8349108,0.00000380406,0.1624468,0.0002273653,0.00001574823,0.000006193251,8.767555e-7,0.000006339643,0.002382172],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7181851,"threshold_uncertainty_score":0.2847055,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4322751637","doi":"10.1108/ejm-07-2020-0542","title":"A comparative study of the predictive power of component-based approaches to structural equation modeling","year":2022,"lang":"en","type":"article","venue":"European Journal of Marketing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba; McGill University","funders":"","keywords":"Structural equation modeling; Component (thermodynamics); Computer science; Predictive power; Predictive modelling; Econometrics; Path analysis (statistics); Partial least squares regression; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.103315132782719,"gpt":0.2758739453762855,"spread":0.1725588125935665,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005321373,0.0001011955,0.0002779581,0.0002011071,0.0001816153,0.00002169998,0.001127508,0.000004608787,0.000005694137],"category_scores_gemma":[0.0002419329,0.00007516953,0.0001181791,0.0005128438,0.0000266387,0.0001838107,0.0006077823,0.0002740837,1.314972e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007010536,"about_ca_system_score_gemma":0.00004166452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000238877,"about_ca_topic_score_gemma":6.937975e-7,"domain_scores_codex":[0.9943043,0.004037138,0.0006941378,0.0001633764,0.0006892469,0.0001117898],"domain_scores_gemma":[0.9980727,0.0003124592,0.001056819,0.0003070509,0.0002119657,0.00003897277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003182762,0.0001579149,0.002384919,0.000006321972,0.00008022134,0.000007234073,0.01297087,0.9802907,0.002248701,0.00008268259,0.00001883768,0.001433394],"study_design_scores_gemma":[0.000537235,0.0008646654,0.01812398,0.00006744446,0.00003449006,0.000009905712,0.007941086,0.9709042,0.001306754,0.0001103551,0.000006491233,0.00009339986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5915803,0.00002064738,0.4078018,0.00006226628,0.00004513946,0.0001385496,0.00000113497,0.000009577985,0.000340626],"genre_scores_gemma":[0.9585967,1.52829e-7,0.04135392,0.00002047839,0.00001505401,0.000001792435,2.640555e-7,0.000008333154,0.000003293869],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3670164,"threshold_uncertainty_score":0.3065324,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W423015428","doi":"10.1016/j.joi.2015.05.001","title":"Modelling count response variables in informetric studies: Comparison among count, linear, and lognormal regression models","year":2015,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Capital Medical University","keywords":"Count data; Statistics; Negative binomial distribution; Poisson regression; Akaike information criterion; Mathematics; Regression analysis; Linear regression; Poisson distribution; Overdispersion; Log-normal distribution; Generalized linear model; Binomial regression; Regression diagnostic; Econometrics; Polynomial regression; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.103223804081119,"gpt":0.3570945740796192,"spread":0.2538707699985002,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006002615,0.0002562066,0.0007645148,0.004770265,0.00009594231,0.0001751355,0.0008552774,0.0001769419,5.245337e-7],"category_scores_gemma":[0.002962127,0.0001922174,0.0001054542,0.006009157,0.0001019414,0.005555848,0.0004168262,0.0006421939,0.00000123582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006156411,"about_ca_system_score_gemma":0.0004255455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004123575,"about_ca_topic_score_gemma":0.000008155375,"domain_scores_codex":[0.996476,0.0001051539,0.001605737,0.0001951677,0.001231582,0.0003863743],"domain_scores_gemma":[0.9949323,0.001200263,0.001505047,0.0003761934,0.001714299,0.0002719241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003411088,0.0000925449,0.01488059,0.00003487435,0.00006781059,0.00004908803,0.003022848,0.9637439,0.000006136033,0.001512195,0.0007795466,0.01546937],"study_design_scores_gemma":[0.0009498698,0.000508794,0.0004374191,0.0002065637,0.0000256892,0.00007024848,0.0009411998,0.9887267,0.0002075702,0.005726562,0.001970956,0.0002283904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1738014,0.003715484,0.8218133,0.00005970649,0.0001602452,0.0001123533,0.000001118719,0.00004238317,0.0002940542],"genre_scores_gemma":[0.68673,0.002247306,0.3108272,0.00009233856,0.00004273399,0.000002947163,7.02843e-7,0.00001018971,0.000046579],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5129287,"threshold_uncertainty_score":0.7838399,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W81794110","doi":"","title":"Adaptive User Interfaces for Intelligent E-Learning: Issues and Trends","year":2004,"lang":"en","type":"article","venue":"Journal of the Association for Information Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; University of Waterloo","funders":"","keywords":"Computer science; Human–computer interaction; User interface; The Internet; Context (archaeology); Multimedia; Domain (mathematical analysis); World Wide Web; Process (computing); User interface design; User experience design","retraction":null,"screen_n_in":null,"score":{"opus":0.01541633088549207,"gpt":0.2851988313401981,"spread":0.269782500454706,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001202553,0.00007787719,0.0001934616,0.0002281673,0.0001463911,0.0002908669,0.000373107,0.00006147919,2.441534e-7],"category_scores_gemma":[0.000414063,0.00005251212,0.0001382576,0.0002484837,0.00000896353,0.00235559,0.00005705459,0.0001052312,0.000001784242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004234179,"about_ca_system_score_gemma":0.0000304026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008474117,"about_ca_topic_score_gemma":0.0000025309,"domain_scores_codex":[0.9988598,0.00004588782,0.0006067787,0.00005091772,0.0003280323,0.0001086082],"domain_scores_gemma":[0.9969102,0.0001465682,0.00198671,0.0001048584,0.0008209301,0.00003072794],"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":[0.0001925573,0.0001248469,0.006310654,0.000190852,0.001214628,2.921027e-7,0.0358915,0.1747512,0.0004695197,0.6525521,0.01973875,0.1085631],"study_design_scores_gemma":[0.00292695,0.001367531,0.003071587,0.0004363878,0.0001816322,0.00005148482,0.005451752,0.05543789,0.02067502,0.0200517,0.8898531,0.0004949677],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002339268,0.0001358289,0.9950093,0.001437205,0.0004505993,0.0002341615,0.000004481243,0.00003905549,0.0003500962],"genre_scores_gemma":[0.9786858,0.00003436556,0.01977826,0.00006941454,0.00008850959,0.0000221751,0.000001740716,0.000004203801,0.001315513],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9763466,"threshold_uncertainty_score":0.2804837,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2251442452","doi":"10.3115/v1/p14-1115","title":"Abstractive Summarization of Spoken and Written Conversations Based on Phrasal Queries","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Computer science; Natural language processing; Multi-document summarization; Artificial intelligence; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.005305981004063103,"gpt":0.2309992697379352,"spread":0.2256932887338721,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001268447,0.00006225965,0.0001008201,0.0001113536,0.00003954905,0.00002647323,0.0001512597,0.00003000604,0.00001646204],"category_scores_gemma":[0.00007156787,0.00005517469,0.0000226205,0.0001682186,0.00005807945,0.0003457733,0.00003841493,0.00004076797,0.000003414768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001442916,"about_ca_system_score_gemma":0.00001671783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004579184,"about_ca_topic_score_gemma":0.00002182454,"domain_scores_codex":[0.9994839,0.00003122197,0.0001209418,0.0001664639,0.0001291019,0.00006836671],"domain_scores_gemma":[0.999384,0.000178382,0.00008348897,0.0002451637,0.00008197629,0.00002694771],"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":[0.000020707,0.000143635,0.01832837,0.00002104682,0.0000308458,0.000001058553,0.0004953444,0.00197294,0.009539726,0.9134555,0.0004738216,0.05551699],"study_design_scores_gemma":[0.0003624823,0.0002276361,0.05370656,0.00002196482,0.00001723673,6.118834e-7,0.00006068268,0.7975121,0.1172653,0.02914965,0.001458063,0.0002177926],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006570118,0.000001776338,0.9826031,0.0005538804,0.00001363103,0.00006333814,9.990163e-7,0.0001293808,0.01006373],"genre_scores_gemma":[0.8676026,0.000002257559,0.1320939,0.00019618,0.000007302334,0.000004373197,0.000004097426,0.000002931179,0.00008632628],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8843058,"threshold_uncertainty_score":0.2249959,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2806157614","doi":"10.1075/term.00012.amj","title":"Distributed specificity for automatic terminology extraction","year":2018,"lang":"en","type":"article","venue":"Terminology International Journal of Theoretical and Applied Issues in Specialized Communication","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; Carleton University; University of Ottawa","funders":"","keywords":"Computer science; Terminology; Artificial intelligence; Classifier (UML); Filter (signal processing); Natural language processing; Representation (politics); Domain (mathematical analysis); Pattern recognition (psychology); Computer vision; Linguistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0178733567441031,"gpt":0.3525913017325484,"spread":0.3347179449884453,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000602428,0.0001400371,0.0003571798,0.0003288777,0.00008711033,0.00008012469,0.001684912,0.0001442904,0.00008016363],"category_scores_gemma":[0.0002544752,0.0001237947,0.00007863151,0.0001484331,0.0009587926,0.0003102068,0.0003661946,0.0002519523,0.000006065185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001139656,"about_ca_system_score_gemma":0.00002708148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002667946,"about_ca_topic_score_gemma":0.000006330364,"domain_scores_codex":[0.9985374,0.0001421985,0.0007138874,0.0002081735,0.0002132786,0.0001850579],"domain_scores_gemma":[0.998149,0.0004647307,0.0005160295,0.0004471419,0.0003750375,0.00004800059],"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":[0.0001365501,0.0001187344,0.0001375959,0.000002704486,0.00004329689,0.000005261978,0.000306769,0.000002308368,0.002484425,0.8884551,0.0002114836,0.1080958],"study_design_scores_gemma":[0.001113732,0.0002075396,0.002835205,0.00004614548,0.0000251635,0.0001857371,0.00008113847,0.006697954,0.02212559,0.9567363,0.009782816,0.0001627232],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1656751,0.0002324488,0.8201202,0.01034882,0.0004292305,0.0002886013,0.00000716264,0.0001013705,0.002797034],"genre_scores_gemma":[0.8446758,0.0003840783,0.1544594,0.0001651309,0.0002649658,0.00001884223,0.00001157384,0.000006773431,0.00001343603],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6790007,"threshold_uncertainty_score":0.50482,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140162241","doi":"10.1007/s11192-011-0589-1","title":"Author disambiguation using multi-aspect similarity indicators","year":2011,"lang":"en","type":"article","venue":"Scientometrics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":48,"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; Genome Canada","keywords":"Similarity (geometry); Recall; Precision and recall; Computer science; Task (project management); Measure (data warehouse); Information retrieval; Key (lock); Data mining; Artificial intelligence; Natural language processing; Psychology; Cognitive psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.2003679371428773,"gpt":0.3850923397812263,"spread":0.184724402638349,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.001450396,0.000154435,0.0001825386,0.005632685,0.0002468751,0.0001707102,0.001437407,0.00009159531,0.00002730618],"category_scores_gemma":[0.0009301903,0.0001457812,0.0001027673,0.0292352,0.0001241912,0.00112845,0.0005025721,0.0001777672,0.00003255807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002435515,"about_ca_system_score_gemma":0.00008151416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007318229,"about_ca_topic_score_gemma":0.00001171848,"domain_scores_codex":[0.9977328,0.00007072586,0.0003002518,0.0005834282,0.0009090232,0.0004037952],"domain_scores_gemma":[0.9984842,0.00006259727,0.0002368593,0.0008169024,0.0001971705,0.0002023053],"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":[0.000009446847,0.001864625,0.3969854,0.00004410848,0.0001100204,0.00007000408,0.01015378,0.0002472493,0.008101798,0.125403,0.0006532187,0.4563573],"study_design_scores_gemma":[0.0005977476,0.0001790324,0.3545432,0.00002753197,0.00007081143,0.00001526575,0.0001162244,0.5287514,0.09066588,0.02152439,0.002424808,0.001083638],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06664888,0.00007596157,0.9314774,0.00003842164,0.0002942264,0.0001413117,0.000002071367,0.0004454151,0.0008762671],"genre_scores_gemma":[0.5548025,0.000003072061,0.4450245,0.00005052084,0.00001237458,0.000003334687,0.000001051423,0.00000629034,0.00009630904],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5285042,"threshold_uncertainty_score":0.9913989,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2066433987","doi":"10.1371/journal.pone.0071914","title":"Connected Text Reading and Differences in Text Reading Fluency in Adult Readers","year":2013,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":48,"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":"FP7 People: Marie-Curie Actions; National Science Foundation","keywords":"Reading (process); Fluency; Computer science; Cognitive psychology; Cognition; Reading comprehension; Psychology; Linguistics; Artificial intelligence; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.03104002281181654,"gpt":0.2376431754671723,"spread":0.2066031526553558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001775535,0.0001941682,0.0004213604,0.0005102419,0.00006201693,0.0001452452,0.0005610976,0.0001000003,0.00003036407],"category_scores_gemma":[0.00043201,0.0001842594,0.00002700843,0.0009894958,0.00008305709,0.001105385,0.0001999824,0.0002715099,0.000043141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009572521,"about_ca_system_score_gemma":0.00002108881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007826106,"about_ca_topic_score_gemma":0.0002548917,"domain_scores_codex":[0.9982364,0.0000977684,0.0004031876,0.000560119,0.0002993475,0.0004032095],"domain_scores_gemma":[0.9989112,0.0002713646,0.0001305144,0.0004686757,0.0001242038,0.0000940368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000175741,0.001522163,0.6534303,0.0002648906,0.0001656531,0.00007046146,0.01178382,0.000006739996,0.2412344,0.03468141,0.0002529968,0.05656956],"study_design_scores_gemma":[0.001975507,0.0004834536,0.5109109,0.004273822,0.00008991396,0.00001483041,0.002193634,0.2308527,0.1489158,0.09819087,0.00001788319,0.002080779],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9863021,0.00009675146,0.01063436,0.0009924609,0.00001179844,0.0003656136,6.542166e-7,0.0002956671,0.001300615],"genre_scores_gemma":[0.9242008,0.0001914154,0.07513737,0.000175395,0.00001622463,0.0001010223,0.000001897622,0.0000127807,0.000163047],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2308459,"threshold_uncertainty_score":0.7513881,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3014604514","doi":"10.2196/17642","title":"Using Natural Language Processing Techniques to Provide Personalized Educational Materials for Chronic Disease Patients in China: Development and Assessment of a Knowledge-Based Health Recommender System","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Ontology; Computer science; Recommender system; Information retrieval; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02777049579753333,"gpt":0.3899926387165861,"spread":0.3622221429190527,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005164957,0.000138637,0.0003200047,0.000159387,0.00007683365,0.00005578326,0.0003211941,0.00004453657,0.000003044831],"category_scores_gemma":[0.0001187266,0.0001162112,0.00002946279,0.0003171547,0.00003622258,0.0003535687,0.0001777542,0.0001141845,3.246222e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007251229,"about_ca_system_score_gemma":0.002701008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007184322,"about_ca_topic_score_gemma":0.00001020962,"domain_scores_codex":[0.9983373,0.00005584238,0.0007552668,0.0001524245,0.0004847681,0.0002144335],"domain_scores_gemma":[0.9990623,0.00005339364,0.0003374276,0.0001263016,0.0001423829,0.0002782119],"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":[0.00009953639,0.0007277688,0.002877187,0.02530985,0.00005080316,0.000002733396,0.06640373,0.00003918828,0.0003060365,0.004781003,0.001019581,0.8983826],"study_design_scores_gemma":[0.001335635,0.0002533908,0.004119781,0.003602431,0.00001194102,0.000001789437,0.0008211212,0.9834988,0.003316613,0.00005300645,0.00260239,0.0003831579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1113048,0.0001995431,0.8843226,0.002271401,0.00004296899,0.001659278,0.00001185089,0.0001560454,0.0000315258],"genre_scores_gemma":[0.5496538,0.000001522073,0.4494133,0.0006284248,0.00002345232,0.0002392043,0.00003285635,0.000005923237,0.000001523216],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9834595,"threshold_uncertainty_score":0.4791472,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2398387993","doi":"","title":"CLASSY 2011 at TAC: Guided and Multi-lingual Summaries and Evaluation Metrics.","year":2011,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.04780621551233317,"gpt":0.324504377454933,"spread":0.2766981619425999,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00104608,0.0001077656,0.000165271,0.0001608317,0.0002089679,0.00003654369,0.00023047,0.00005215218,0.00001831232],"category_scores_gemma":[0.0000994167,0.00009607228,0.00001928612,0.0002489443,0.0004409464,0.0003775311,0.0002861502,0.00005176086,0.000002634521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001432311,"about_ca_system_score_gemma":0.00002448178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003331351,"about_ca_topic_score_gemma":0.00002185844,"domain_scores_codex":[0.9991679,0.00009982639,0.0002179103,0.0002755738,0.0001347372,0.0001040656],"domain_scores_gemma":[0.9989671,0.0002304541,0.0001540805,0.0003820125,0.0002155826,0.00005082064],"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":[0.00001523896,0.00003082849,0.001175733,0.00001458009,0.00002109278,1.400022e-7,0.001436233,8.77321e-7,0.0009357852,0.8873763,0.00003915108,0.108954],"study_design_scores_gemma":[0.0002556317,0.00004550294,0.004524725,0.000004268662,0.00008796801,0.000009244351,0.0003493918,0.002041736,0.06745026,0.923468,0.001588362,0.0001749448],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1002366,0.003671511,0.8939388,0.00006106684,0.00001309253,0.0004032171,0.000006197003,0.0001162711,0.001553172],"genre_scores_gemma":[0.9219581,0.0004556336,0.07715297,0.00002639844,0.0000118145,0.0001343065,0.000008275831,0.000005897666,0.0002466089],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8217215,"threshold_uncertainty_score":0.3917714,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2091597866","doi":"10.1075/ssol.1.1.06dix","title":"The scientific study of literature","year":2011,"lang":"en","type":"article","venue":"Scientific Study of Literature","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":46,"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":"Reading (process); Context (archaeology); Cognition; Computer science; Cognitive science; Scientific literature; Domain (mathematical analysis); Event (particle physics); Psychology; Epistemology; Data science; Cognitive psychology; Neuroscience; Linguistics; History","retraction":null,"screen_n_in":null,"score":{"opus":0.02404426383237939,"gpt":0.2786062161423486,"spread":0.2545619523099692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002694002,0.000359546,0.0005107088,0.0008662406,0.001352761,0.002046181,0.004328735,0.0001175057,0.00001260522],"category_scores_gemma":[0.0001792581,0.0002318879,0.0002015109,0.008470151,0.0006076177,0.001273862,0.001043836,0.0004894055,0.000008610586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003326882,"about_ca_system_score_gemma":0.00008266947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001679109,"about_ca_topic_score_gemma":0.0001649384,"domain_scores_codex":[0.9951006,0.0004042723,0.0009191996,0.001430517,0.001619527,0.0005258608],"domain_scores_gemma":[0.993511,0.0001473039,0.0006354849,0.003931227,0.001646014,0.0001289541],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.00014535,0.0170357,0.02021774,0.0001185778,0.00055238,0.0001762826,0.8815633,0.00002827312,0.01709953,0.02372252,0.01235478,0.02698558],"study_design_scores_gemma":[0.01937137,0.03125059,0.2696778,0.004431269,0.001627372,0.0002350422,0.1973215,0.009680705,0.1943322,0.1819109,0.08191078,0.008250518],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9895038,0.002384622,0.002710968,0.00004774922,0.002403409,0.001601519,0.00002063693,0.000232695,0.001094579],"genre_scores_gemma":[0.9892875,0.000005792036,0.006447896,0.00001049512,0.00003957266,0.00006278135,0.000008735263,0.0000171327,0.004120117],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6842418,"threshold_uncertainty_score":0.9999474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163490678","doi":"","title":"Use of Keyphrase Extraction Software for Creation of an AEC/FM Thesaurus","year":2000,"lang":"en","type":"article","venue":"NPARC","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Thesaurus; Extractor; Computer science; Software; The Internet; Process (computing); Domain (mathematical analysis); Information retrieval; World Wide Web; Software engineering; Natural language processing; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02853358991606894,"gpt":0.3131675310217468,"spread":0.2846339411056779,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000131924,0.00007330809,0.0001457793,0.00009512404,0.00003735668,0.00002189559,0.0002688179,0.0000477654,0.0001039309],"category_scores_gemma":[0.0000977303,0.00006947477,0.00006615898,0.0002601107,0.00003564501,0.001050473,0.00001955169,0.00004048733,0.000002403457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002273702,"about_ca_system_score_gemma":0.00002171598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002741661,"about_ca_topic_score_gemma":0.00001227878,"domain_scores_codex":[0.9992772,0.00003409177,0.0002232357,0.0001980025,0.0001637461,0.000103716],"domain_scores_gemma":[0.9990458,0.0001413373,0.000144612,0.0004706403,0.0001634151,0.00003420334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003112592,0.0001322676,0.0002005052,0.00001331691,0.00001152898,8.807249e-7,0.0001814725,0.0004775523,0.08185988,0.004717353,0.000147571,0.9122266],"study_design_scores_gemma":[0.0002972839,0.0004030048,0.003098919,0.00003794174,0.00004315684,0.000006336831,0.0000152384,0.1055659,0.7910597,0.09201366,0.007239498,0.0002193196],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1603461,0.000007364235,0.8388078,0.00004889977,0.00001397669,0.0001501901,0.00000703466,0.0001349226,0.0004837282],"genre_scores_gemma":[0.4887007,0.00001227322,0.5110304,0.00002041885,0.0000119683,0.00001117141,0.000007052437,0.00000495561,0.0002010348],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9120072,"threshold_uncertainty_score":0.2833099,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2086368750","doi":"10.1145/371920.372162","title":"When experts agree","year":2001,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":43,"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":"Watson; Citation; Library science; Research center; George (robot); Center (category theory); Computer science; World Wide Web; Operations research; Engineering; Political science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.0188195129517892,"gpt":0.2764848424940115,"spread":0.2576653295422223,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006340977,0.0000678159,0.00008116745,0.00007215115,0.0000413636,0.00005607597,0.0006714587,0.00002486071,0.0001767108],"category_scores_gemma":[0.00001316505,0.00005434506,0.0000456383,0.000211056,0.0000155112,0.0005173616,0.0001838548,0.00003044796,0.0000979774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002035884,"about_ca_system_score_gemma":0.000007844028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003267912,"about_ca_topic_score_gemma":0.0000371569,"domain_scores_codex":[0.9993666,0.00001282342,0.000100555,0.000219397,0.0001458011,0.000154782],"domain_scores_gemma":[0.9992997,0.00002126516,0.00002567081,0.0005682178,0.00003557985,0.00004955722],"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":[0.000001837505,0.00007736084,0.002704471,0.000001254558,0.00001887845,0.00008648784,0.0007772437,0.00001424179,0.004416933,0.317626,0.0660877,0.6081876],"study_design_scores_gemma":[0.0002394703,0.00008530289,0.001032281,0.00001078964,0.000006025892,0.00008168467,0.00006770849,0.03592671,0.03689488,0.3967483,0.5283648,0.0005419954],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00146551,0.00005177784,0.9293705,0.001281737,0.00002856983,0.00003667757,2.392577e-8,0.0007393796,0.06702583],"genre_scores_gemma":[0.3102618,0.00003103647,0.6749644,0.001194487,0.00003637757,0.00001067713,3.566226e-7,0.000004843851,0.01349605],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6076456,"threshold_uncertainty_score":0.2216127,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978683092","doi":"10.1177/016224390202700301","title":"From Thing to Sign and “Natural Object”: Toward a Genetic Phenomenology of Graph Interpretation","year":2002,"lang":"en","type":"article","venue":"Science Technology & Human Values","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Trois-Rivières; Lakehead University; University of Victoria","funders":"","keywords":"Interpretation (philosophy); Epistemology; Natural science; Phenomenology (philosophy); Reading (process); Natural (archaeology); Object (grammar); Sign (mathematics); Computer science; Semiotics; Cognitive science; Sociology; Linguistics; Psychology; Artificial intelligence; Mathematics; Philosophy; History","retraction":null,"screen_n_in":null,"score":{"opus":0.01471340560740698,"gpt":0.2846390009863392,"spread":0.2699255953789322,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003218258,0.0001842416,0.0003167101,0.002120802,0.0003809619,0.00009016663,0.002192585,0.0001104695,0.00001620261],"category_scores_gemma":[0.0001935782,0.0001735383,0.00004906369,0.002884495,0.002262568,0.0007195526,0.0009106157,0.0002377956,0.00001279081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007610271,"about_ca_system_score_gemma":0.00002167586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003924225,"about_ca_topic_score_gemma":0.00001242126,"domain_scores_codex":[0.9980142,0.00004446759,0.0003580406,0.0008399995,0.0003291056,0.0004141851],"domain_scores_gemma":[0.998672,0.00006300657,0.0001950761,0.0008270259,0.0001720461,0.00007083837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003685187,0.00008400834,0.002135172,0.000009715753,0.00003900191,0.0000136371,0.01992217,0.0001166716,0.6194432,0.08635549,0.0000675784,0.2718096],"study_design_scores_gemma":[0.0001872377,0.0005522243,0.005057841,0.00006060524,0.0000265681,0.00001875498,0.00119469,0.03226395,0.135312,0.8248989,0.000043336,0.0003839303],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.626125,0.0007933382,0.3712466,0.0007279652,0.00008047781,0.0001642471,7.951227e-7,0.0006077649,0.0002538355],"genre_scores_gemma":[0.7922873,0.00002250821,0.2075025,0.0001200457,0.00001292177,0.00002082255,3.198244e-7,0.000006402292,0.00002719053],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7385434,"threshold_uncertainty_score":0.8336526,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}